CN118793531B

CN118793531B - An engine fault diagnosis optimization method based on working condition portrait and related device

Info

Publication number: CN118793531B
Application number: CN202411261613.0A
Authority: CN
Inventors: 唐波; 黄继轩
Original assignee: Weichai Power Co Ltd
Current assignee: Weichai Power Co Ltd
Priority date: 2024-09-10
Filing date: 2024-09-10
Publication date: 2025-01-17
Anticipated expiration: 2044-09-10
Also published as: CN118793531A

Abstract

The present application discloses an engine fault diagnosis optimization method based on working condition portrait and related devices, the method comprising: obtaining the operating parameters of the engine, the operating parameters comprising at least a plurality of working condition parameters; obtaining the current working condition portrait of the engine according to the operating parameters; processing the current working condition portrait and the initial data version using a diagnosis prediction model to obtain a target data version corresponding to the current working condition portrait; the target data version comprising: a fault diagnosis strategy and a diagnosis support parameter corresponding to the fault diagnosis strategy; the diagnosis prediction model is obtained by training using training samples, the training samples are obtained using a typical working condition library, the typical working condition library comprising a plurality of typical working condition portraits; the target data version is sent to the engine controller, and the controller executes the fault diagnosis strategy according to the diagnosis support parameters, so that the use time of the engine before the fault alarm is extended.

Description

Engine fault diagnosis optimization method and related device based on working condition portrait

Technical Field

The application relates to the technical field of engines, in particular to an engine fault diagnosis optimization method based on a working condition portrait and a related device.

Background

At present, the fault diagnosis of the engine generally adopts the existing road spectrum data and accumulated experience to carry out diagnosis prediction of the fault of the engine.

For parts of the engine, replacement or maintenance is performed when a possible failure is predicted. However, in practical application, the service life and maintenance period of the practical parts can be prolonged due to different operation conditions. For this reason, the fault diagnosis strategy and the diagnosis support parameters under various working conditions are usually calibrated in advance by engineers.

However, in the practical application of the engine, the working condition is changeable, and even if engineers calibrate fault diagnosis strategies and diagnosis support parameters of multiple versions in advance, the service life and maintenance period of engine parts can not be prolonged under certain working condition.

Disclosure of Invention

In view of the above problems, the application provides an engine fault diagnosis optimization method based on a working condition portrait and a related device, so that the service time of an engine before fault alarming is prolonged. The specific scheme is as follows:

the first aspect of the application provides an engine fault diagnosis optimization method based on a working condition portrait, which comprises the following steps:

Obtaining operation parameters of an engine, wherein the operation parameters at least comprise a plurality of working condition parameters;

Obtaining a current working condition image of the engine according to the operation parameters;

Processing the current working condition portrait and the initial data version by using a diagnosis prediction model to obtain a target data version corresponding to the current working condition portrait, wherein the target data version comprises a fault diagnosis strategy and diagnosis support parameters corresponding to the fault diagnosis strategy;

The diagnosis prediction model is obtained by training a training sample, the training sample is obtained by a typical working condition library, and the typical working condition library comprises a plurality of typical working condition portraits;

And sending the target data version to a controller of the engine, and executing the fault diagnosis strategy according to the diagnosis support parameters by the controller so that the service time of the engine before fault alarming is prolonged.

In one possible implementation, the diagnosis prediction model comprises a fault level classification model, a risk classification model, a fault strategy pool and a data optimization model, wherein the fault strategy pool comprises at least one strategy parameter group, and the strategy parameter group at least comprises a fault level parameter, a occurrence degree parameter and a risk degree parameter;

the method for processing the current working condition portrait and the initial data version by using the diagnosis prediction model to obtain a target data version corresponding to the current working condition portrait comprises the following steps:

According to the current working condition portrait, a target working condition portrait and an initial data version are obtained in a data version library;

the data version library comprises at least one typical working condition portrait, wherein each typical working condition portrait corresponds to an optimized data version, the target working condition portrait and the current working condition portrait meet a matching condition, and the initial data version is the optimized data version corresponding to the target working condition portrait;

Obtaining a current fault level corresponding to the target working condition image by using the fault level classification model, wherein the current fault level represents the risk degree of faults of the engine;

Obtaining a current occurrence degree and a current risk degree corresponding to the target working condition portrait by using the risk classification model, wherein the current occurrence degree represents the frequency of the occurrence of the fault of the engine, and the current risk degree represents the risk degree of the occurrence of the fault of the engine;

Screening target parameters matched with the current working condition image in the fault strategy pool according to the current fault level, the current occurrence degree and the current risk degree corresponding to the target working condition image, wherein the target parameters comprise a target fault level, a target occurrence degree and a target risk degree;

And inputting the target fault level, the target occurrence degree, the target risk degree, the current working condition portrait and the initial data version into the data optimization model to obtain a target data version corresponding to the current working condition portrait output by the data optimization model.

In one possible implementation, the diagnosis prediction model comprises a fault level classification model, a risk classification model, a fault strategy pool and a control simulation system, wherein the fault strategy pool comprises at least one strategy parameter group, and the strategy parameter group at least comprises a fault level parameter, a occurrence degree parameter and a risk degree parameter;

inputting the current working condition portrait and an initial data version into a control simulation system corresponding to a controller of the engine, wherein the control simulation system can output initial parameters according to the current working condition portrait by taking the initial data version as a control data version;

adjusting a control data version used in the control simulation system so that initial parameters output by the control simulation system match the target parameters;

And determining a control data version used by the control simulation system when the initial parameters are matched with the target parameters as a target data version corresponding to the current working condition image.

In one possible implementation, the matching condition is that the image similarity between the current operating condition image and the target operating condition image is greater than or equal to a first threshold.

In one possible implementation, obtaining, from the current operating condition representation, a target operating condition representation and an initial data version in a data version library, includes:

obtaining a current working condition type corresponding to the current working condition image by using a clustering model;

Comparing the current working condition type with the working condition type of each typical working condition portrait in the data version library;

If the typical working condition type in the data version library is consistent with the current working condition type, determining the typical working condition portrait consistent with the current working condition type in the data version library as a target working condition portrait and obtaining an optimized data version corresponding to the target working condition portrait;

And if the typical working condition type is not consistent with the current working condition type in the data version library, taking the typical working condition portrait with the largest portrait similarity with the current working condition portrait in the data version library as a target working condition portrait and obtaining an optimized data version corresponding to the target working condition portrait.

In one possible implementation, the training samples are obtained by:

And respectively carrying out the following processing on each typical working condition portrait in the typical working condition library:

Obtaining a current fault level corresponding to the typical working condition image by using the fault level classification model;

obtaining the current occurrence degree and the current risk degree corresponding to the typical working condition portrait by using the risk classification model;

Screening index parameters matched with the typical working condition image in the fault strategy pool according to the current fault level, the current occurrence degree and the current risk degree corresponding to the typical working condition image, wherein the index parameters comprise a fault level index, an occurrence degree index and a risk degree index;

Inputting the typical working condition portrait and the historical data version corresponding to the typical working condition portrait into a control simulation system corresponding to a controller of the engine, wherein the control simulation system can output initial parameters according to the typical working condition portrait by taking the historical data version corresponding to the typical working condition portrait as the control data version;

Adjusting a control data version used in the control simulation system so that initial parameters output by the control simulation system match the index parameters;

the control data version used by the control simulation system when the initial parameters are matched with the index parameters is an output sample in the training sample, and the index parameters, the typical working condition portrait and the historical data version corresponding to the typical working condition portrait are input samples in the training sample.

In one possible implementation, the initial parameter matches the index parameter, including:

the initial fault level is matched with the fault level index, the initial occurrence degree is matched with the occurrence degree index, and the initial risk degree is matched with the risk degree index.

In one possible implementation, after obtaining the target data version corresponding to the current working condition image, the method further includes:

performing generalization treatment on at least one working condition parameter in the current working condition image to obtain a new typical working condition image;

And adding the new typical working condition portrait and the corresponding target data version thereof to the data version library.

The second aspect of the application provides an engine fault diagnosis optimizing device based on a working condition portrait, which comprises:

A parameter obtaining unit for obtaining an operation parameter of the engine, the operation parameters at least comprise a plurality of working condition parameters;

an image obtaining unit for obtaining the current working condition image of the engine according to the operation parameters;

The data processing unit is used for processing the current working condition portrait and the initial data version by utilizing a diagnosis prediction model to obtain a target data version corresponding to the current working condition portrait, wherein the target data version comprises a fault diagnosis strategy and diagnosis support parameters corresponding to the fault diagnosis strategy;

And the data transmission unit is used for transmitting the target data version to a controller of the engine, and the controller executes the fault diagnosis strategy according to the diagnosis support parameters so that the service time of the engine before fault alarming is prolonged.

A third aspect of the present application provides a computer program product comprising computer readable instructions which, when run on an electronic device, cause the electronic device to implement a method of engine fault diagnosis optimisation based on a regime representation of the first aspect or any implementation thereof.

A fourth aspect of the application provides an electronic device comprising at least one processor and a memory coupled to the processor, wherein:

the memory is used for storing a computer program;

the processor is configured to execute the computer program, so that the electronic device can implement the engine fault diagnosis optimization method based on the working condition portrait in the first aspect or any implementation manner of the first aspect.

A fifth aspect of the present application provides a computer storage medium carrying one or more computer programs which, when executed by an electronic device, enable the electronic device to implement a method for diagnosing and optimizing engine faults based on a working condition portrait according to the first aspect or any implementation manner of the first aspect.

By means of the technical scheme, in the engine fault diagnosis optimization method and the related device based on the working condition image, after the operating parameters of the engine including the working condition parameters are obtained, the current working condition image of the engine is obtained according to the operating parameters, then the current working condition image and the initial data version are processed by using the diagnosis prediction model trained by the typical working condition image, so that the target data version corresponding to the current working condition image is obtained, the target data version includes the fault diagnosis strategy and the diagnosis support parameters corresponding to the fault diagnosis strategy, and therefore after the target data version is sent to the controller of the engine, the controller executes the corresponding fault diagnosis strategy according to the diagnosis support parameters in the target data version, and therefore the service time of the engine before fault alarming is prolonged. Therefore, the fault diagnosis strategy and the corresponding diagnosis support parameters can be optimized by utilizing the diagnosis prediction model no matter what working condition state the current working condition image of the engine is, so that the use time of the engine before fault alarming can be prolonged when the controller of the engine executes the fault diagnosis strategy according to the optimized diagnosis support parameters, and the cost of using the engine by a user can be reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of an engine fault diagnosis optimization method based on a working condition portrait according to an embodiment of the present application;

FIG. 2 is a partial flow chart of an engine fault diagnosis optimization method based on a working condition portrait according to an embodiment of the present application;

FIG. 3 is another partial flow chart of an engine fault diagnosis optimization method based on a working condition portrait according to an embodiment of the present application;

FIG. 4 is a flowchart of a further portion of an engine fault diagnosis optimization method based on a condition representation according to an embodiment of the present application;

FIG. 5 is another flow chart of an engine fault diagnosis optimization method based on a working condition representation provided by an embodiment of the application;

FIG. 6 is a further flowchart of an engine fault diagnosis optimization method based on a condition representation according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an engine fault diagnosis optimizing device based on a working condition portrait according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

FIG. 9 is a logic flow diagram of an overall execution of an engine fault automatic diagnosis, prediction and optimization method based on condition adaptive learning in the present application;

FIG. 10 is a flow chart for optimizing fault diagnosis strategy according to the present application;

FIG. 11 is a flowchart of the acquisition of training samples for a virtual calibration model in the present application.

Detailed Description

Embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. The terminology used in the description of the embodiments of the application herein is for the purpose of describing particular embodiments of the application only and is not intended to be limiting of the application.

Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.

The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

The application can be applied to the field of engines, and a plurality of application scenes of landing to products are described below by taking a diesel engine as an example.

Referring to fig. 1, a flowchart of an engine fault diagnosis optimization method based on a working condition portrait according to an embodiment of the present application may be applicable to an electronic device capable of performing data processing, where the electronic device may be a local device connected to an engine or a cloud device connected to the engine. The technical scheme in the embodiment is mainly used for prolonging the service time of the engine before fault alarming.

Specifically, the method in this embodiment may include the following steps:

and 101, obtaining the operation parameters of the engine.

The operation parameters at least comprise a plurality of working condition parameters such as rotating speed, torque, vehicle speed, altitude, temperature, load, acceleration, idle speed and the like.

In one implementation, a plurality of operating parameters of the engine may be collected using a plurality of sensors disposed on the engine in step 101 to obtain operating parameters of the engine.

For example, a data connection is established between the electronic device in the present embodiment and the sensor disposed on the engine, and after the sensor collects the operating parameters, the operating parameters are sent to the electronic device in the present embodiment through the data connection, so that the operating parameters including the operating parameters are obtained on the electronic device.

It should be noted that the operation parameters may also include non-working condition parameters, where the non-working condition parameters refer to parameters that will not change after the engine leaves the factory.

It should be noted that, in this embodiment, the method may be performed under the condition that the operation parameters of the engine change, that is, in this embodiment, whether the operation parameters of the engine change is continuously detected, and if it is detected that the operation parameters of the engine change, step 101 and the subsequent steps are performed.

And 102, obtaining the current working condition image of the engine according to the operation parameters.

Specifically, in step 102, the operation parameters may be filtered to remove abnormal data according to data correlation and range limit, and then cut according to a selected data processing mode (such as driving cycle mode, driving mileage, operation duration, etc.), so as to extract corresponding parameter characteristics such as temperature, altitude, humidity, rotation speed, torque, load, etc., and then construct a current working condition image of the engine according to the parameter characteristics. The current operating condition representation of the engine may be represented by the extracted parametric features, as shown in Table 1.

TABLE 1 current working condition image

And 103, processing the current working condition portrait and the initial data version by using the diagnosis prediction model to obtain a target data version corresponding to the current working condition portrait.

The target data version comprises a fault diagnosis strategy of the engine and diagnosis support parameters corresponding to the fault diagnosis strategy. The diagnostic support parameters refer to parameters that are required by the engine's controller ECU (electronic control unit) for performing a fault diagnosis strategy. The fault diagnosis strategy refers to a strategy used by the controller when performing fault detection and fault alarm on the engine. For example, when the fuel level in the fuel tank decreases to a predetermined value, the controller outputs alarm information indicating that the fuel level is too low.

The diagnosis prediction model is obtained by training a training sample, and the training sample is obtained by using a typical working condition library. The typical operating mode library may include a plurality of typical operating mode representations.

In the initial state, the typical working condition images in the typical working condition library can be manually set by a user, and various different working condition images can be generated by the engine along with the operation of the engine, so that the working condition images in actual operation can be added into the typical working condition library.

In one implementation, the diagnostic prediction model may be constructed based on a machine learning algorithm and trained using training samples, so that the diagnostic prediction model may learn a relationship between an input sample and an output sample in the training samples, where the input sample includes at least a working condition image and a data version (such as a fault diagnosis policy and a diagnostic support parameter), and the output sample is an optimized data version corresponding to the working condition image in the input sample.

Step 104, the target data version is sent to the controller of the engine.

Wherein the fault diagnosis strategy is executed by the controller according to the diagnosis support parameters in the target data version, so that the service time of the engine before fault alarm is prolonged.

Specifically, in step 104, the target data version may be sent to the controller of the engine in a manner of OTA (Over The Air), so that when the controller executes the fault diagnosis strategy according to the diagnosis support parameter in the target data version, the service time of the engine before the fault alarm is prolonged, specifically, the service time of the engine is prolonged from the first time to the second time, and then prompt information is output, so that maintenance personnel can maintain, maintain or replace relevant parts of the engine conveniently.

By means of the technical scheme, in the engine fault diagnosis optimization method based on the working condition image, after the operating parameters of the engine including the working condition parameters are obtained, the current working condition image of the engine is obtained according to the operating parameters, then the current working condition image and the initial data version are processed by using the diagnosis prediction model trained by the typical working condition image, so that the target data version corresponding to the current working condition image is obtained, the target data version includes the fault diagnosis strategy and the diagnosis support parameters corresponding to the fault diagnosis strategy, and therefore after the target data version is sent to the controller of the engine, the controller executes the corresponding fault diagnosis strategy according to the diagnosis support parameters in the target data version, and therefore the service time of the engine before fault alarming is prolonged. Therefore, in this embodiment, no matter what working condition is the current working condition representation of the engine, the diagnosis prediction model can be used to optimize the fault diagnosis strategy and the corresponding diagnosis support parameters, so that when the controller of the engine executes the fault diagnosis strategy according to the optimized diagnosis support parameters, the use duration of the engine before fault alarm can be prolonged, and the cost of using the engine by a user can be reduced.

In one implementation, the diagnostic prediction model may include a fault class classification model, a risk classification model, a fault policy pool, and a data optimization model, where the models may be machine learning models. The fault policy pool may include at least one policy parameter set, where each policy parameter set includes at least a fault level parameter, a occurrence parameter, and a risk parameter.

Based on this, step 103 may be implemented in the following way, as shown in fig. 2:

And 201, obtaining a target working condition portrait and an initial data version in a data version base according to the current working condition portrait.

The data version library comprises at least one typical working condition image, each typical working condition image is correspondingly provided with an optimized data version, and the optimized data version is that when a controller of the engine executes a fault diagnosis strategy according to diagnosis support parameters in the optimized data version, the using time of the engine before fault alarming can be prolonged. For example, the optimized data version for a typical operating portrayal is shown in table 2.

Table 2 optimized data version

The target working condition portrait and the current working condition portrait meet the matching condition, and the initial data version is the optimized data version corresponding to the target working condition portrait.

Specifically, the matching condition is that the image similarity between the current working condition image and the target working condition image is larger than or equal to a first threshold value.

In one case, the target operating condition representation is a typical operating condition representation in the database that is completely consistent with the current operating condition representation;

In another case, the target operating condition representation is not exactly the same as the current operating condition representation, but the target operating condition representation is the typical operating condition representation closest to the current operating condition representation in the data version library.

In one implementation, step 201 may be implemented by:

Firstly, respectively obtaining the image similarity between the current working condition image and each typical working condition image in the data version library, and then screening the typical working condition image with the maximum image similarity from the data version library to be used as the target working condition image.

The image similarity between the working condition images can be obtained through a similarity algorithm or a machine learning model capable of obtaining the similarity. Or in this embodiment, the parameter ranges of the working condition images in which the same working condition parameters are located may be compared, and the image similarity is obtained according to the difference between the parameter ranges.

In another implementation, step 202 may be implemented by:

Firstly, a clustering model is utilized to obtain the current working condition type corresponding to the current working condition image.

And then, comparing the current working condition type with the working condition type of each typical working condition portrait in the data version library, if the typical working condition type is consistent with the current working condition type in the data version library, determining a target working condition portrait determined by the typical working condition portrait consistent with the current working condition type in the data version library and an optimized data version corresponding to the target working condition portrait as an initial data version, and if the typical working condition type is not consistent with the current working condition type in the data version, taking the typical working condition portrait with the largest portrait similarity between the data version library and the current working condition portrait as the target working condition portrait and determining an optimized data version corresponding to the target working condition portrait as the initial data version.

The clustering model can be obtained through training a training sample, so that the clustering model can identify the working condition type corresponding to the input working condition image. At least one working condition parameter is different among different working condition types, and particularly, the parameter ranges where at least one working condition parameter is located are different. The types of conditions that the cluster model has learned may be as shown in table 3:

TABLE 3 types of operating conditions

Type 1	Type 2	...	Type n
				Vehicle speed	Vehicle speed	Vehicle speed	Vehicle speed
Torque moment	Torque moment	Torque moment	Torque moment
				Temperature (temperature)	Temperature (temperature)	Temperature (temperature)	Temperature (temperature)
Humidity of the water	Humidity of the water	Humidity of the water	Humidity of the water
				...	...	...	...

And 202, obtaining the current fault level corresponding to the target working condition image by using a fault level classification model.

Wherein the current fault level characterizes the risk of a fault occurring in the engine. The fault level classification model can be a machine learning model, and the fault level classification model can predict the fault level corresponding to the input working condition image after model training.

For example, the fault level that can be predicted by the fault level classification model may be four kinds of:

a level of fatal failure that affects safe operation of the engine, or protects against a non-compliant condition;

a level of major failure that renders the engine or assembly functional but does not affect the safe operation of the engine;

A general fault level, which can cause a shutdown, but can be repaired by vulnerable spare parts or parts with low value, or a fault which does not cause the shutdown but has affected normal use and needs to be adjusted and repaired;

The level of slight fault is that the level can not cause stop, the normal operation of the engine is not influenced, parts are not required to be replaced, and the fault can be eliminated simply.

And 203, obtaining the current occurrence degree and the current risk degree corresponding to the target working condition portrait by using a risk classification model.

The current occurrence degree represents the frequency of the faults of the engine, and the current risk degree represents the risk degree of the faults of the engine. The risk classification model can be a machine learning model, and the risk classification model can predict the occurrence and risk corresponding to the input working condition image after model training.

For example, the risk classification model can predict three occurrences, high, general and low. The risk classification model can predict three kinds of risk, namely high occurrence risk, medium occurrence risk and low occurrence risk.

It should be noted that, the execution sequence of the step 202 and the step 203 may not be limited by the sequence shown in the drawings, the step 203 may be executed first and then the step 202 may be executed, or the step 202 and the step 203 may be executed simultaneously, and different technical solutions formed by different execution sequences are all within the protection scope of the present application.

And 204, screening out target parameters matched with the current working condition portrait in a fault strategy pool according to the current fault level, the current occurrence degree and the current risk degree corresponding to the target working condition portrait.

The target parameters comprise a target fault level, a target occurrence degree and a target risk degree. The policy parameter set contained in the fault policy pool is used for carrying out customized prediction and reminding on the level, occurrence degree, risk and the like of the engine fault under different working condition images according to early warning conditions, diagnosis conditions, maintenance conditions and the like.

And 205, inputting the target fault level, the target occurrence degree, the target risk degree, the current working condition portrait and the initial data version into the data optimization model to obtain a target data version corresponding to the current working condition portrait output by the data optimization model.

The data optimization model can be obtained by training in advance by using training samples. Training samples of the data optimization model may be obtained using typical operating portraits in a typical operating mode library.

Specifically, in this embodiment, a corresponding training sample may be obtained by performing a procedure as shown in fig. 3 on each typical working condition portrait in the typical working condition library respectively:

Step 301, obtaining a current fault level corresponding to the typical working condition image by using the fault level classification model.

And 302, obtaining the current occurrence degree and the current risk degree corresponding to the typical working condition portrait by using a risk classification model.

It should be noted that, the execution sequence of the step 301 and the step 302 may not be limited by the sequence shown in the drawings, the step 302 may be executed first and then the step 301 may be executed, or the step 301 and the step 302 may be executed simultaneously, and different technical solutions formed by different execution sequences are all within the protection scope of the present application.

Step 303, screening out index parameters matched with the typical working condition image in a fault strategy pool according to the current fault level, the current occurrence degree and the current risk degree corresponding to the typical working condition image.

The index parameters comprise a fault level index, a occurrence degree index and a risk degree index.

Step 304, inputting the historical data version corresponding to the typical working condition image and the typical working condition image into a control simulation system corresponding to a controller of the engine.

The control simulation system can output initial parameters according to the typical working condition portrait by taking the historical data version corresponding to the typical working condition portrait as the control data version. The initial parameters comprise initial fault level, initial occurrence degree and initial risk degree.

Specifically, the control simulation system can also be called as a virtual ECU hardware system, and can simulate the fault diagnosis function of the controller of the engine, namely, fault judgment is carried out according to the control data version, specifically, the fault diagnosis strategy in the control data version is executed according to the diagnosis support parameters in the control data version.

Step 305, adjusting the control data version used in the control simulation system so that the initial parameters output by the control simulation system match the index parameters.

The initial parameter matching index parameter may be that the initial fault level is matched with the fault level index, the initial occurrence degree is matched with the occurrence degree index, and the initial risk degree is matched with the risk degree index.

Specifically, in this embodiment, at least one diagnostic support parameter and fault diagnosis policy in the control data version may be sequentially adjusted according to the difference between the initial parameter and the index parameter output by the control simulation system until the initial parameter matches with the index parameter.

Based on the data, the initial parameters are matched with the index parameters, the control data version used by the control simulation system is an output sample in the training sample, and the index parameters, the typical working condition images and the historical data version corresponding to the typical working condition images are input samples in the training sample. In this way, the input samples are input into the data optimization model, the predicted data version output by the data optimization model is obtained, then the model optimization is carried out on the data optimization model according to the loss function value between the predicted data version and the data version in the samples, and after the optimization of a plurality of training samples, the data optimization model can output the target data version corresponding to the target working condition image aiming at the input data.

In one implementation, the diagnosis prediction model may include a fault level classification model, a risk classification model, a fault policy pool and a control simulation system, where the models may be machine learning models. The fault policy pool may include at least one policy parameter set, where each policy parameter set includes at least a fault level parameter, a occurrence parameter, and a risk parameter.

Based on this, step 103 may be implemented in the following way, as shown in fig. 4:

and 401, obtaining a target working condition portrait and an initial data version in a data version base according to the current working condition portrait.

The data version library comprises at least one typical working condition image, each typical working condition image corresponds to an optimized data version, the target working condition image and the current working condition image meet matching conditions, and the initial data version is the optimized data version corresponding to the target working condition image.

And step 402, obtaining the current fault level corresponding to the target working condition image by using the fault level classification model.

Wherein the current fault level characterizes the risk of a fault occurring in the engine.

And 403, obtaining the current occurrence degree and the current risk degree corresponding to the target working condition portrait by using the risk classification model.

The current occurrence degree represents the frequency of the faults of the engine, and the current risk degree represents the risk degree of the faults of the engine.

It should be noted that, the execution sequence of the step 402 and the step 403 may not be limited by the sequence shown in the drawings, the step 403 may be executed first and then the step 402 may be executed, or the step 402 and the step 403 may be executed simultaneously, and different technical solutions formed by different execution sequences are all within the protection scope of the present application.

And 404, screening out target parameters matched with the current working condition portrait in a fault strategy pool according to the current fault level, the current occurrence degree and the current risk degree corresponding to the target working condition portrait.

The target parameters comprise a target fault level, a target occurrence degree and a target risk degree.

In particular, the implementation of steps 401 to 404 may refer to the implementation of steps 201 to 204 described above, and will not be described in detail here.

Step 405, inputting the current working condition portrait and the initial data version into a control simulation system corresponding to a controller of the engine, wherein the control simulation system can output initial parameters according to the current working condition portrait by taking the initial data version as the control data version.

The initial parameters comprise an initial fault level, an initial occurrence degree and an initial risk degree.

Step 406, adjusting the version of the control data used in the control simulation system so that the initial parameters output by the control simulation system match the target parameters.

The initial parameter is matched with the target parameter, namely the initial fault level is matched with the target fault level, the initial occurrence degree is matched with the target occurrence degree, and the initial risk degree is matched with the target risk degree.

Specifically, in this embodiment, at least one diagnostic support parameter and a fault diagnosis policy in the control data version may be sequentially adjusted according to the difference between the initial parameter and the target parameter output by the control simulation system until the initial parameter matches with the target parameter.

Step 407, determining the control data version used by the control simulation system when the initial parameters are matched with the target parameters as the target data version corresponding to the current working condition image.

It should be noted that, in the flow shown in fig. 4, the initial parameters and the target parameters need to be adjusted multiple times in step 406 to obtain the target data version, and in the flow shown in fig. 2, the data optimization model needs to be run only once in step 205 to obtain the target data version in which the initial parameters and the target parameters are matched, so that the efficiency of obtaining the optimized data version can be improved.

Based on the above implementation, after step 103, the method in this embodiment may further include the following processing, as shown in fig. 5:

step 105, generalizing at least one working condition parameter in the current working condition image to obtain a new typical working condition image.

The generalization processing in this embodiment refers to generalizing the current working condition representation into a new working condition representation capable of representing multiple similar working condition states, namely, a typical working condition representation.

Specifically, in this embodiment, at least one working condition parameter in the current working condition image may be adjusted to a parameter range including a plurality of parameter values, so as to obtain a new typical working condition image.

And 106, adding the new typical working condition portraits and the corresponding target data versions thereof into a data version library.

Therefore, after the target data version is obtained each time, the target data version is added into a data version library, when the working condition parameters of the engine are changed again in subsequent processing, after the new operation parameters and corresponding new working condition images are obtained, the target working condition images meeting the matching conditions with the new working condition images are obtained in the data version library, the corresponding target data version is obtained according to the implementation scheme, after the new target data version is transmitted to the controller of the engine, the controller executes a corresponding fault diagnosis strategy according to the diagnosis support parameters in the new target data version, so that the service time of the engine under the new operation parameters before fault alarm is prolonged, and the user maintenance cost is reduced.

In another implementation, the optimized data version in the data version library may also be preset by the user. For example, a fault diagnostic strategy and corresponding diagnostic support parameters that an engineer manually calibrates prior to engine shipment are added to the database as an optimized data version.

In one implementation, prior to step 104, the method in this embodiment may further include the following processes, as shown in fig. 6:

Step 107, judging whether the target data version is consistent with the current data version used by the controller of the engine, if the target data version is inconsistent with the current data version, executing step 104, executing a corresponding fault diagnosis strategy by the controller of the engine by using the diagnosis support parameters in the received target data version, and if the target data version is consistent with the current data version, ending the current flow, namely not executing step 104, and continuously executing the fault diagnosis strategy by using the diagnosis support parameters in the original data version by the controller of the engine so as to prolong the service time of the engine before fault alarming and reduce the data transmission quantity.

The engine fault diagnosis optimization method based on the working condition portrait is described above, and a device for executing the engine fault diagnosis optimization method based on the working condition portrait is described below.

Referring to fig. 7, a schematic structural diagram of an engine fault diagnosis optimization device based on a working condition portrait according to an embodiment of the present application is shown. The device can be deployed in an electronic device capable of performing data processing, and the electronic device can be a local device connected with an engine or a cloud device connected with the engine. The technical scheme in the embodiment is mainly used for prolonging the service time of the engine before fault alarming.

Specifically, the apparatus in this embodiment may include the following units:

a parameter obtaining unit 701, configured to obtain an operation parameter of an engine, where the operation parameter at least includes a plurality of working condition parameters;

An image obtaining unit 702 for obtaining a current working condition image of the engine according to the operation parameters;

The data processing unit 703 is configured to process the current working condition portrait and the initial data version by using a diagnostic prediction model, so as to obtain a target data version corresponding to the current working condition portrait, where the target data version includes a fault diagnosis policy and a diagnostic support parameter corresponding to the fault diagnosis policy;

and a data transmission unit 704, configured to send the target data version to a controller of the engine, where the controller executes the fault diagnosis strategy according to the diagnosis support parameter, so that a service time period of the engine before fault alarm is prolonged.

By means of the technical scheme, in the engine fault diagnosis optimizing device based on the working condition image, after the operating parameters of the engine including the working condition parameters are obtained, the current working condition image of the engine is obtained according to the operating parameters, then the current working condition image and the initial data version are processed by using the diagnosis prediction model trained by the typical working condition image, so that the target data version corresponding to the current working condition image is obtained, the target data version includes the fault diagnosis strategy and the diagnosis support parameters corresponding to the fault diagnosis strategy, and therefore after the target data version is sent to the controller of the engine, the controller executes the corresponding fault diagnosis strategy according to the diagnosis support parameters in the target data version, and therefore the service time of the engine before fault alarming is prolonged. Therefore, the fault diagnosis strategy and the corresponding diagnosis support parameters can be optimized by utilizing the diagnosis prediction model no matter what working condition state the current working condition image of the engine is, so that the use time of the engine before fault alarming can be prolonged when the controller of the engine executes the fault diagnosis strategy according to the optimized diagnosis support parameters, and the cost of using the engine by a user can be reduced.

The application also provides an electronic device comprising at least one processor and a memory connected to the processor, wherein:

the memory is used for storing a computer program;

Referring to fig. 8, a schematic diagram of an electronic device suitable for use in implementing embodiments of the present application is shown. The electronic device in the embodiment of the present application may include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a desktop computer, and the like. The electronic device shown in fig. 8 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.

As shown in fig. 8, the electronic device may include a processing means (e.g., a central processor, a graphics processor, etc.) 801 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the state where the electronic device is powered on, various programs and data necessary for the operation of the electronic device are also stored in the RAM 803. The processing device 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

In general, devices may be connected to I/O interface 805 including input devices 806, including for example, touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc., output devices 807, including for example, liquid Crystal Displays (LCDs), speakers, vibrators, etc., storage devices 808, including for example, memory cards, hard disks, etc., and communication devices 809. The communication means 809 may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While fig. 8 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

The embodiment of the application also provides a computer program product, which comprises computer readable instructions, and when the computer readable instructions run on the electronic equipment, the electronic equipment is enabled to realize any engine fault diagnosis optimization method based on the working condition image.

The embodiment of the application also provides a computer storage medium which carries one or more computer programs, and when the one or more computer programs are executed by the electronic equipment, the electronic equipment can realize any engine fault diagnosis optimization method based on the working condition image provided by the embodiment of the application.

The following describes the technical scheme of the present application in detail by taking a diesel engine as an example:

At present, the fault diagnosis and prediction of the engine generally adopts the existing road spectrum data and the existing accumulated experience, the running condition and the monitoring data of the current engine are judged and diagnosed and predicted, and the current fault can be accurately prompted under the condition of substantial faults, but the mode belongs to post judgment, and when related faults are prompted, the actual engine has the fault, and the prediction capability is relatively insufficient.

The prediction reminding of the service life and maintenance of the parts adopts a mode of timed replacement or maintenance, but in practical application, the service life and maintenance period of the practical parts can be prolonged due to different operation conditions, so that the use cost of customers is reduced.

Therefore, the current diagnosis strategy is a limited diagnosis strategy based on limited data, and how to scientifically diagnose various faults, predict the service life and maintenance period of parts and the like is a problem which needs to be solved currently.

In view of this, the application adds road spectrum collection and extraction strategies based on the existing limited road spectrum data, and carries out self-learning of engine faults and running conditions based on the original road spectrum data and the processed new road spectrum data after the engine leaves the factory and is loaded, and proposes a consultable recommended diagnosis strategy for the running working condition of the current vehicle, so as to carry out pre-diagnosis, part life prediction, maintenance period prediction, fault early warning and the like of the engine under the condition of ensuring the indexes of optimal performance, emission, economy and the like of the engine.

As shown in FIG. 9, a logic flow diagram is integrally executed for an engine fault automatic diagnosis, prediction and optimization method based on working condition self-adaptive learning in the application. The engine fault automatic diagnosis prediction optimization method based on the working condition self-adaptive learning can be divided into two phases, namely a first phase is an offline manual optimization phase, shown in the left part of fig. 9, and a second phase is a cloud self-learning optimization phase, shown in the right part of fig. 9:

At the cloud, a predefined engine diagnosis library is imported into a typical engine diagnosis library (i.e. the typical working condition library in the previous description), engine working conditions manually updated in a left-hand under-line manual optimization stage are imported into the typical engine diagnosis library, based on the fact, an initial data version is optimized by using a diagnosis prediction model for typical working condition portraits in the typical working condition library to obtain diagnosis logic and data (i.e. target data version) optimized based on a local machine (engine), then fault diagnosis strategies and diagnosis support parameters of a controller optimized based on the local machine are transmitted to the controller of the engine through OTA to update the data of the fault diagnosis strategies and the diagnosis support parameters, and as the engine leaves a factory, working condition parameters of the engine can be detected through sensors to realize data acquisition, data characteristics can be extracted at the cloud to construct portraits (i.e. current working condition portraits) of the vehicle engine, and then automatic clustering is carried out by using a clustering model of the cloud.

If the clustered working condition types are classified, namely, in a diagnostic data version base based on the images, the working condition types are matched with the target working condition images of the current working condition images, so that the diagnostic data versions (namely, the corresponding optimized data versions) in the clustered results are extracted to be initial data versions, then the target working condition images and the initial data versions are processed by utilizing a diagnostic prediction model to obtain target data versions (namely, the diagnostic logic and the data based on the local optimization), and a typical engine diagnosis base is updated, for example, if the current working condition images are not found in the typical engine diagnosis base, the current working condition images are added into the typical engine diagnosis base.

If the working condition type obtained by clustering is new classification, the clustering model is used for training the clustering model after the new working condition portraits of the vehicles are manually extracted, so that the clustering model is added with the new portraits classification, the new working condition portraits are generated as data of a typical engine diagnosis library and are updated to the typical engine diagnosis library, in addition, after the new vehicle portraits are extracted, diagnostic data versions of similar results can be extracted from a diagnostic data version base based on the portraits, and then the target working condition portraits and the initial data versions are processed by utilizing a diagnostic prediction model so as to obtain target data versions.

Further, after the target data version (i.e., the diagnostic logic and data based on the local optimization) is obtained, new portrait data may be added to the data version library after the data generalization process.

The detailed scheme is described as follows:

1. offline manual optimization part:

The part is used after the engine of the machine type or the whole car is developed for the first time or is subjected to major update, and the execution flow is as follows:

1. extracting fault information and fault classification information in the working condition information from a typical engine diagnosis library;

2. Performing rule calibration and test according to the generalized diagnosis rules of various parts and part type classification under standard working conditions;

3. circularly adjusting to obtain an optimal diagnosis parameter (a conservation value in the current state, namely the index parameter in the previous step), and taking the parameter as a target value of subsequent calibration;

4. Generating a controller diagnosis strategy data version applicable to the type of information according to the adjustment;

5. Adding the data version and the predefined working condition information into a cloud image-based data version library to serve as an optimized data version;

6. generating final production version data according to the data, and performing data refreshing (updating) by multiple controllers in the production process;

7. after the whole vehicle or the engine leaves the factory and delivers users, continuously collecting the operation working conditions, road spectrum information and various performance parameters of various engines;

8. manually analyzing the data to extract working conditions, and manually updating the data into a typical engine working condition library of the cloud;

2. cloud self-learning optimization model part:

After delivering the part of engines or the whole vehicle to a user, continuously optimizing the data of the whole vehicle controller by combining the functions of the internet of vehicles, wherein the execution flow is as follows:

1. data extraction and vehicle portraits are carried out through data collected by a vehicle end, and working condition characteristic data based on the specific vehicle is generated;

2. classifying the current vehicle image by using a clustering model;

If the classification is normal, updating the data in a typical engine working condition library by using the working condition information of the portrait, so that the data is more perfect, and synchronously extracting the controller data suitable for the portrait from a data version library based on the portrait according to a clustering result;

such as classification anomalies:

(1) Pushing data to an artificial portrait extraction function;

(2) The work of retraining the clustering model and the like can be performed through manual participation, so that the normal classification is achieved, namely, the clustering model can classify new working condition types;

(3) Meanwhile, the portrait can be redefined as a new vehicle portrait (namely, a working condition portrait) by manual participation, new classification identifiers are added in a data version base of the portrait, and controller data (namely, an initial data version in the previous) closest to the portrait is synchronously extracted from the data version base;

3. The extracted controller diagnosis data is sent to a diagnosis prediction model, and is graded and predicted by matching with data in a typical engine working condition library (namely, the current fault level, the current occurrence degree, the current risk degree, the target fault level, the target occurrence degree and the target risk degree are obtained in the previous step), and finally, the optimal controller diagnosis data (namely, a target data version) suitable for the local machine is obtained, and then the optimal controller diagnosis data is updated to an engine controller through OTA;

4. If the updated new data is newly added portrait data, the data is generalized and then added into a data version base based on the portrait for subsequent use.

In the application, the diagnosis prediction model is subdivided into a fault classification prediction model, a fault risk prediction model, a diagnosis strategy pool based on working condition portraits, a machine learning model and the like, which are formed by the following steps:

the fault classification prediction model classifies faults of the existing engine, and is convenient for different service relatives to process the faults of the engine according to the fault level.

And the fault risk prediction model predicts the frequency and the risk degree of the type of faults so as to prompt service related personnel to pay attention to important fault categories.

And the fault strategy pool is used for carrying out customized prediction and reminding on early warning conditions, diagnosis conditions, maintenance conditions and the like on the classification, occurrence degree, risk level and the like of faults under different working condition data.

As shown in fig. 10, to optimize the flow of the fault diagnosis strategy. The method specifically comprises the following steps:

After initial data of vehicle operation is collected, working condition scanning is input into a strategy pool, meanwhile, an original part diagnosis function model is obtained, part information is extracted, and after the original part diagnosis function model passes through the strategy pool, diagnosis strategies of various parts and functions are executed, wherein:

The method comprises the steps of carrying out fault grading judgment, risk occurrence degree judgment and part category judgment on parts, directly alarming and stopping if a fault level is in a fatal fault, alarming and stopping if the fault level is in a major fault and the risk degree is high, only alarming if the fault level is in a general fault and the risk degree is medium risk or low risk, only prompting after strategy readjustment through a strategy pool if the fault level is in the general fault and the risk degree is low risk, and not processing after strategy readjustment through the strategy pool if the fault level is in a minor fault and the risk degree is low risk, thereby prolonging the service time of an engine before fault alarming.

The following illustrates the optimization of the replacement strategy after a failure of a component:

The components are classified into various important categories such as basic components, important components, general components, electric components, wearing parts, and the like. This example uses an empty cartridge, as shown in table 4:

TABLE4 spare part replacement strategy

Operating condition parameters	Standard working condition	User condition 1	User condition 2
				Air filter life	1000h
Key parameters	Intake negative pressure
				Judgment standard	Differential pressure > -20kpa	Differential pressure > -20kpa	Differential pressure > -20kpa
Indirect index	0-1000 Hours	1000+T1 (500,250,125) <2000 hours	1000+T1+t2 hours
				Strategy 1	Checking the wear condition of the air filter, and if the air filter is damaged and broken, replacing
Policy 2		If the service life is perfect, cleaning the empty filter, continuing to use, prolonging the service life t1, updating the recorded empty filter service life { user working condition 1, service life duration 1000+t1 (500) }, and continuing to use after cleaning the empty filter }
				Strategy 3			If the service life is perfect, cleaning the empty filter, continuing to use, prolonging the service life t2, updating and recording the service life { user working condition 2, service life duration 1000+t1+t2 }, and continuing to use after cleaning the empty filter }

The air filter is used for inputting the rotating speed, the internal torque, the oil injection quantity, the ambient temperature, the ambient pressure, the vehicle speed, the gradient and the altitude in the calibration working condition of a laboratory;

Direct index judgment standard that the intake negative pressure difference is more than-20 kpa;

According to the standard working condition environment, the service time of the air filter is 1000 hours, and in the actual use process, the working condition of a user vehicle is different from the working condition of a standard laboratory, and different maintenance strategies are implemented on the service life of the air filter.

Under the condition of working condition 1, the user has exceeded the original calibration service life for 1000 hours and exceeds t1 hour, at the moment, the air filter appearance is checked to have no obvious damage and aging phenomenon, the air inlet negative pressure difference meets the standard, at the moment, the relation between the working condition and the service life time is established according to the working condition types of different working conditions such as limit working conditions, urban areas, suburban areas and the like, the relation between the working condition and the service life of the parts is established, the correlation coefficient is obtained, and under the specific working condition, the service life of the parts can be prolonged to be equal to the service life value + the correlation coefficient multiplied by the calibration service life value under the original calibration working condition.

The strategy pool under different working conditions can be used as input for the user to individually select the vehicle engine, and if the working conditions of the user in a certain time range change, the user can be reminded of a changeable parameter selection range.

It should be noted that, the data output by the fault classification, the fault risk model and the policy pool, and the closest support data version extracted currently, are sent to a virtual calibration model (i.e. the data optimization model in the foregoing) for model training.

Training samples of the automatic virtual calibration model can be obtained by the procedure shown in fig. 11:

Firstly, an ECU control logic library is a Simulink-based control logic model of all control logics in an ECU in the electric control research and development process, and is a functional module for realizing the whole control logic of an engine.

The control model is a logic correction large model which is obtained in a large number of engine calibration and is based on parameters of the model to be adjusted under various conditions, and the control model is generated through data training.

The working condition scanning input function is a working condition operation logic library generated according to a large amount of calibration experience, the logic library is obtained by generalizing all data of the classification condition of the working condition portrait, and various data are a large amount of automatically generated multidimensional data arrays.

The virtual ECU hardware system is responsible for performing virtual execution (i.e., simulation) according to the extracted ECU control logic (i.e., data version), performing individual scanning and multi-dimensional scanning according to each parameter of each data array, and monitoring the output parameters or intermediate parameters at any time so as to achieve the predefined criteria (i.e., the index parameters in the foregoing).

Stopping when the data meets the expectations (i.e., the initial parameters match the index parameters), or converges to a certain degree.

And for the parameters of the result divergence, later-stage manual confirmation is needed to obtain final result data, namely an output sample in the training sample.

It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. But a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device (which may be a personal computer, a training device, a network device, etc.) to perform the method according to the embodiments of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (Solid STATE DISK, SSD)), etc.

Claims

1. An engine fault diagnosis optimization method based on operating condition portrait, characterized in that the method comprises:

Obtaining operating parameters of the engine, wherein the operating parameters include at least a plurality of operating condition parameters;

According to the operating parameters, a current operating condition profile of the engine is obtained;

The current operating condition profile and the initial data version are processed by using a diagnostic prediction model to obtain a target data version corresponding to the current operating condition profile; the target data version includes: a fault diagnosis strategy and a diagnostic support parameter corresponding to the fault diagnosis strategy;

The diagnostic prediction model is obtained by training using training samples, and the training samples are obtained using a typical operating condition library, and the typical operating condition library contains multiple typical operating condition portraits;

Sending the target data version to a controller of the engine, and having the controller execute the fault diagnosis strategy according to the diagnosis support parameter, so that the use time of the engine before a fault alarm is extended;

The diagnostic prediction model includes: a fault level classification model, a risk classification model, a fault strategy pool and a data optimization model; the fault strategy pool includes at least one strategy parameter group, and the strategy parameter group includes at least a fault level parameter, an occurrence parameter and a risk parameter;

Wherein, using the diagnostic prediction model, processing is performed according to the current working condition profile and the initial data version to obtain the target data version corresponding to the current working condition profile, including:

The data version library includes at least one typical working condition portrait, each of which corresponds to an optimized data version; the target working condition portrait and the current working condition portrait meet the matching condition; the initial data version is the optimized data version corresponding to the target working condition portrait;

Using the fault level classification model, obtaining a current fault level corresponding to the target operating condition portrait; the current fault level represents the degree of danger of the fault occurring in the engine;

Using the risk classification model, the current occurrence degree and the current risk degree corresponding to the target operating condition profile are obtained; the current occurrence degree represents the frequency of the engine failure, and the current risk degree represents the risk degree of the engine failure;

According to the current fault level, current occurrence degree and current risk degree corresponding to the target operating condition profile, in the fault strategy pool, target parameters matching the current operating condition profile are screened out, the target parameters including target fault level, target occurrence degree and target risk degree;

Inputting the target fault level, the target occurrence degree, the target risk degree, the current operating condition portrait and the initial data version into the data optimization model to obtain the target data version corresponding to the current operating condition portrait output by the data optimization model; or,

The diagnostic prediction model includes: a fault level classification model, a risk classification model, a fault strategy pool and a control simulation system; the fault strategy pool includes at least one strategy parameter group, and the strategy parameter group includes at least a fault level parameter, an occurrence parameter and a risk parameter;

According to the current fault level, current occurrence degree and current risk degree corresponding to the target operating condition profile, in the fault strategy pool, target parameters matching the current operating condition profile are screened out, wherein the target parameters include a target fault level, a target occurrence degree and a target risk degree;

Inputting the current operating condition portrait and the initial data version into a control simulation system corresponding to the controller of the engine, the control simulation system can output initial parameters according to the current operating condition portrait using the initial data version as the control data version; the initial parameters include: initial fault level, initial occurrence degree, and initial risk degree;

Adjusting the control data version used in the control simulation system so that the initial parameters output by the control simulation system match the target parameters;

The control data version used by the control simulation system when the initial parameters match the target parameters is determined as the target data version corresponding to the current operating condition portrait.

2. The method according to claim 1 is characterized in that the matching condition is: the portrait similarity between the current working condition portrait and the target working condition portrait is greater than or equal to a first threshold.

3. The method according to claim 2, characterized in that, according to the current working condition portrait, obtaining the target working condition portrait and the initial data version in the data version library comprises:

Using a clustering model, obtaining a current operating condition type corresponding to the current operating condition portrait;

Compare the current working condition type with the working condition type of each typical working condition portrait in the data version library;

If there is a typical operating condition type in the data version library that is consistent with the current operating condition type, the typical operating condition portrait in the data version library that is consistent with the current operating condition type is determined as the target operating condition portrait, and the optimized data version corresponding to the target operating condition portrait is determined as the initial data version;

If there is no typical operating condition type in the data version library that is consistent with the current operating condition type, the typical operating condition portrait with the greatest portrait similarity with the current operating condition portrait in the data version library is used as the target operating condition portrait and the optimized data version corresponding to the target operating condition portrait is determined as the initial data version.

4. The method according to claim 1, characterized in that the training samples are obtained by:

The following processing is performed on each typical working condition image in the typical working condition library:

Using the fault level classification model, obtaining the current fault level corresponding to the typical working condition portrait;

Using the risk classification model, obtaining the current occurrence degree and current risk degree corresponding to the typical working condition portrait;

According to the current fault level, current occurrence degree and current risk degree corresponding to the typical working condition portrait, in the fault strategy pool, index parameters matching the typical working condition portrait are screened out; the index parameters include: fault level index, occurrence degree index and risk degree index;

The typical operating condition portrait and the historical data version corresponding to the typical operating condition portrait are input into the control simulation system corresponding to the controller of the engine, and the control simulation system can output initial parameters according to the typical operating condition portrait using the historical data version corresponding to the typical operating condition portrait as the control data version; the initial parameters include: initial fault level, initial occurrence degree, and initial risk degree;

Adjusting the control data version used in the control simulation system so that the initial parameters output by the control simulation system match the indicator parameters;

Among them, the control data version used by the control simulation system when the initial parameters match the index parameters is the output sample in the training sample; the index parameters, the typical operating condition portrait and the historical data version corresponding to the typical operating condition portrait are the input samples in the training sample.

5. The method according to claim 4, characterized in that the initial parameter matches the indicator parameter, comprising:

The initial fault level matches the fault level index, the initial occurrence degree matches the occurrence degree index, and the initial risk degree matches the risk degree index.

6. The method according to claim 1, characterized in that after obtaining the target data version corresponding to the current working condition portrait, the method further comprises:

Generalizing at least one operating condition parameter in the current operating condition profile to obtain a new typical operating condition profile;

The new typical working condition portrait and its corresponding target data version are added to the data version library.

7. An engine fault diagnosis and optimization device based on operating condition portrait, characterized in that the device comprises:

A parameter obtaining unit, used to obtain operating parameters of the engine, wherein the operating parameters at least include a plurality of operating condition parameters;

A portrait obtaining unit, used for obtaining a current operating condition portrait of the engine according to the operating parameters;

A data processing unit, used to process the current operating condition portrait and the initial data version using a diagnostic prediction model to obtain a target data version corresponding to the current operating condition portrait; the target data version includes: a fault diagnosis strategy and a diagnostic support parameter corresponding to the fault diagnosis strategy;

A data transmission unit, used for sending the target data version to the controller of the engine, and the controller executes the fault diagnosis strategy according to the diagnosis support parameter, so that the service life of the engine before the fault alarm is extended;

The data processing unit uses the diagnostic prediction model to process the current working condition profile and the initial data version to obtain the target data version corresponding to the current working condition profile, including:

8. An electronic device comprising at least one processor and a memory connected to the processor, wherein:

The memory is used to store computer programs;

The processor is used to execute the computer program so that the electronic device can implement an engine fault diagnosis optimization method based on operating condition profiling as described in any one of claims 1 to 6.