CN109917772B - PHM rapid prototyping system for remotely evaluating equipment state on line - Google Patents

Abstract

The invention discloses a PHM rapid prototyping system for remote online evaluation of equipment state, which relates to the field of equipment health evaluation and comprises the following components: the PHM application module is arranged at the equipment and used for acquiring the running data of the equipment through various sensors and evaluating the acquired running data by using an embedded real-time diagnosis tool to obtain the state information of the equipment; the PHM maintenance module is arranged at a remote place and used for establishing a communication circuit connected with the PHM application module and providing an algorithm self-training updating toolkit of an embedded real-time diagnosis tool for the PHM application module through the communication circuit. The PHM algorithm model rapid training and algorithm reconstruction are realized, the corresponding algorithm is updated in time according to different states of the equipment, and the technical problems that the adaptability of a solidified equipment diagnosis evaluation scheme in the prior art is poor and the algorithm updating cost is high are solved.

Description

A PHM Rapid Prototyping System for Remote Online Evaluation of Equipment Status

technical field

The invention relates to the field of equipment health assessment, in particular to a PHM rapid prototyping system for remote online assessment of equipment status.

Background technique

Engines in aviation, ships, high-speed railways, and locomotive equipment have a harsh working environment and small space during the execution of tasks. A set of data acquisition, algorithm training, feature extraction, diagnostic evaluation, and data storage is prepared on the equipment. PHM (Prognostic and Health Management, failure prediction and health management) system is difficult to achieve. In particular, for some installations, such as engine life cycle, the applicability of the solidified engine diagnostic evaluation scheme will gradually decrease, and the cost of algorithm update will be high.

SUMMARY OF THE INVENTION

The present invention provides a system for remote online evaluation of equipment status, which solves the technical problem in the prior art that it is difficult to install a PHM system integrating multiple functions on the same equipment, resulting in that the diagnosis result cannot truly reflect the equipment status.

According to one aspect of the present invention, there is provided a PHM rapid prototyping system for remote online evaluation of equipment status, the system comprising:

The PHM maintenance module set on the ground is used to train the PHM algorithm model by using the historical monitoring data of the movable device, and obtain the algorithm configuration file that has been trained, and use the PHM algorithm model and the algorithm configuration file to generate Algorithm toolkit, sent to PHM application module;

The PHM application module provided in the movable device is used to reconstruct the trained PHM algorithm model by using the received algorithm toolkit, and use the trained PHM algorithm model to perform a The current monitoring data of the device is processed to obtain a diagnostic evaluation result of the movable device.

Preferably, the PHM maintenance module is further configured to acquire the historical monitoring data from a database and acquire the PHM algorithm model from the PHM development module before training the PHM algorithm model.

Preferably, the PHM maintenance module includes:

A model training unit for training the PHM algorithm model by loading the historical monitoring data into the PHM algorithm model to obtain an algorithm configuration file containing model parameters of the trained model;

An encapsulation integration unit, configured to encapsulate and integrate the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit.

Preferably, the PHM application module includes:

an algorithm reconstruction unit, configured to parse the algorithm toolkit, obtain the PHM algorithm model and the algorithm configuration file, and load the algorithm configuration file into the PHM algorithm model to obtain a trained PHM algorithm model;

a diagnosis and evaluation unit, configured to perform feature extraction on the current monitoring data of the movable device by using the trained PHM algorithm model to obtain feature data, and evaluate the movable device according to the feature data, A diagnostic evaluation result of the removable device is obtained.

Preferably, the PHM application module further includes:

a data acquisition unit, configured to collect current monitoring data of the movable device, where the current monitoring data includes air path parameter data and vibration parameter data; and/or

A data storage unit for storing the current monitoring data and/or corresponding diagnostic evaluation results.

Preferably, the PHM application module is further configured to save the current monitoring data and/or the corresponding diagnostic evaluation results to a database.

Preferably, the PHM application module is further configured to send the current monitoring data and/or the corresponding diagnostic evaluation results to a human-computer interaction module provided on the movable device.

Preferably, the PHM maintenance module is further configured to generate a control instruction for reconstructing the PHM algorithm model, and when sending the algorithm toolkit to the PHM application module, the PHM algorithm for reconstructing the PHM algorithm is sent to the PHM application module. Model control instructions are sent to the PHM application module.

Preferably, the PHM application module is specifically configured to reconstruct the trained PHM algorithm model according to the control instruction for reconstructing the PHM algorithm model.

Preferably, the PHM maintenance module is a high-performance workstation, and the PHM application module is an industrial computer.

Compared with the prior art, the beneficial effects of the present invention are:

The present invention utilizes the PHM application module arranged at the movable equipment and the maintenance module arranged on the ground, maintains the adaptability of the diagnosis and evaluation scheme, realizes the equipment evaluation result online in real time, accurately and truly reflects the equipment state, and is beneficial to the maintenance of the remote end The personnel maintain the equipment in a timely manner.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and do not limit the scope of the invention as claimed.

Description of drawings

The accompanying drawings, which are part of the present specification, illustrate exemplary embodiments of the invention and, together with the description of the specification, serve to explain the principles of the invention.

1 is a schematic diagram of the PHM rapid prototype system architecture provided by the present invention;

Fig. 2 is a schematic diagram of the composition of the PHM device provided by the present invention;

3 is an overall architecture diagram of a maintenance module and an application module provided by the present invention;

4 is a functional structural diagram of a maintenance module provided by an embodiment of the present invention;

5 is a functional structure diagram of an application module provided by an embodiment of the present invention;

6 is a maintenance module server provided by an embodiment of the present invention;

7 is a hardware architecture diagram of an application module provided by an embodiment of the present invention;

8 is an application module computer provided by an embodiment of the present invention;

9 is a flowchart of a method for maintaining a module provided by an embodiment of the present invention;

10 is a general interface of maintenance module software provided by an embodiment of the present invention;

11 is an algorithm training interface provided by an embodiment of the present invention;

12 is a remote control interface provided by an embodiment of the present invention;

13 is a flowchart of an application module method provided by an embodiment of the present invention;

14 is an overall interface of application module software provided by an embodiment of the present invention;

Fig. 15 is a block diagram of a PHM rapid prototyping system for remote on-line evaluation of equipment status according to the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the main embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The content shown in the invention, modifications or changes are made without departing from the scope of the content of the invention. The illustrative embodiments and descriptions herein are used to explain the present invention, but not to limit the present invention. As used herein, "comprising", "including", "having", "containing" and the like are open-ended terms, meaning including but not limited to.

Fig. 15 is a block diagram of a PHM rapid prototyping system for remote online assessment of equipment status according to the present invention. As shown in Fig. 15, the system includes: a PHM maintenance module arranged on the ground and a PHM arranged in the movable equipment application module.

1. PHM maintenance module set on the ground

The PHM maintenance module set on the ground is used to train the PHM algorithm model by using the historical monitoring data of the movable device, and obtain the algorithm configuration file that has been trained, and use the PHM algorithm model and the algorithm configuration file to generate Algorithm toolkit, sent to the PHM application module.

In one embodiment, the PHM maintenance module may include:

A model training unit for training the PHM algorithm model by loading the historical monitoring data into the PHM algorithm model to obtain an algorithm configuration file;

An encapsulation integration unit, configured to encapsulate and integrate the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit.

In this embodiment, the algorithm configuration file includes model parameters and interface information of the trained model.

In this implementation manner, the preset format may be an existing format or a custom format.

2. The PHM application module set in the movable device

The PHM application module provided in the movable device is used to reconstruct the trained PHM algorithm model by using the received algorithm toolkit, and use the trained PHM algorithm model to perform a The current monitoring data of the device is processed to obtain a diagnostic evaluation result of the movable device.

In one embodiment, the PHM application module may include:

an algorithm reconstruction unit, configured to parse the algorithm toolkit, obtain the PHM algorithm model and the algorithm configuration file, and load the algorithm configuration file into the PHM algorithm model to obtain a trained PHM algorithm model;

a diagnosis and evaluation unit, configured to perform feature extraction on the current monitoring data of the movable device by using the trained PHM algorithm model to obtain feature data, and evaluate the movable device according to the feature data, A diagnostic evaluation result of the removable device is obtained.

On the basis of the above embodiments, the PHM application module may further include:

a data acquisition unit, configured to collect current monitoring data of the movable device, where the current monitoring data includes air path parameter data and vibration parameter data; and/or

A data storage unit for storing the current monitoring data and/or corresponding diagnostic evaluation results.

The working process of a PHM rapid prototyping system for remote online assessment of equipment status of the present invention may be as follows:

The first step: the PHM maintenance module obtains the historical monitoring data from the database, and obtains the PHM algorithm model from the PHM development module.

Step 2: The PHM maintenance module uses the historical monitoring data to train the PHM algorithm model, and obtains an algorithm configuration file after the training is completed.

Step 3: The PHM maintenance module sends data to the PHM application module.

In one embodiment, the PHM maintenance module uses the PHM algorithm model and the algorithm configuration file to generate an algorithm toolkit and send it to the PHM application module.

On the basis of this embodiment, the PHM maintenance module can generate a control instruction for reconstructing the PHM algorithm model, and when sending the algorithm toolkit to the PHM application module, the PHM maintenance module can generate the control instruction for reconstructing the PHM algorithm model. The control instructions of the PHM algorithm model are sent to the PHM application module.

In another embodiment, the PHM maintenance module may only send the algorithm configuration file to the PHM application module.

Based on this embodiment, the PHM maintenance module can generate a control instruction for reconstructing the PHM algorithm model, and when sending the algorithm configuration file to the PHM application module, use the control instruction for reconstructing the PHM algorithm model. The control instructions of the PHM algorithm model are sent to the PHM application module.

Step 4: The PHM application module acquires the current monitoring data of the movable device in real time.

Step 5: The PHM application module reconstructs the trained PHM algorithm model.

In one embodiment, the PHM application module can use the algorithm toolkit to reconstruct the trained PHM algorithm model.

In this embodiment, the PHM application module obtains a new PHM algorithm model and a new configuration file in the new algorithm toolkit by parsing the new algorithm toolkit, and loads the new configuration file into the new PHM algorithm model, to obtain the new PHM algorithm model loaded with the new configuration file, that is, to reconstruct the trained PHM algorithm model.

In another embodiment, the PHM application module reconstructs the trained PHM algorithm model using the algorithm configuration file.

In this embodiment, the PHM application module loads the configuration file into the existing PHM algorithm model, and obtains the PHM algorithm model on which the new configuration file has been loaded.

In the above embodiment, the action of reconstructing the trained PHM algorithm model by the PHM application module may be completed under the control of the control instruction for reconstructing the PHM algorithm model.

Step 6: The PHM application module uses the trained PHM algorithm model to process the current monitoring data to obtain the diagnostic evaluation result of the movable device.

Step 7: The PHM application module performs data storage.

In one embodiment, the PHM application module may save the current monitoring data and/or the corresponding diagnostic evaluation results to a database, so that the PHM maintenance module can call the current monitoring data and/or the corresponding diagnostic evaluation results The results are used to update the algorithm toolkit.

In another embodiment, the PHM application module may save the current monitoring data and/or the corresponding diagnostic evaluation results, and may also send the current monitoring data and/or the corresponding diagnostic evaluation results to the A human-computer interaction module on the movable device, so that the human-computer interaction module can display the current monitoring data and/or the corresponding diagnostic evaluation results in real time.

The above-mentioned PHM maintenance module may be a high-performance workstation, and the above-mentioned PHM application module may be an industrial computer.

The principle of the present invention will be described in detail below with reference to FIG. 1 to FIG. 15 .

Example 1. PHM Rapid Prototyping System

1 is a schematic diagram of the architecture of a PHM rapid prototyping system provided by the present invention. As shown in FIG. 1 , a PHM rapid prototyping system for remote online evaluation of equipment status includes:

The PHM application module 101 (or PHM application model) provided at the equipment is used to collect the equipment operation data through a variety of sensors, and use the embedded real-time diagnostic tool to evaluate and process the collected operation data to obtain the equipment status information;

The remote PHM maintenance module 102 is configured to establish a communication circuit connecting the PHM application module, and provide the PHM application module with an algorithm self-training and updating toolkit of embedded real-time diagnostic tools via the communication circuit.

Further, the PHM rapid prototyping system for remote online evaluation of equipment status further includes: a remote human-computer interaction module for receiving the equipment status information sent by the PHM application module 101, for remote maintenance personnel to receive equipment status according to the real-time information, and maintain equipment in a timely manner.

Further, while the PHM maintenance module 102 provides the PHM application module 101 with an algorithm self-training and updating toolkit of the embedded real-time diagnostic tool, it also receives the equipment real-time operation data transmitted by the PHM application module 101, and provides real-time information on the equipment. Running data for fast training Get algorithm self-training update toolkit in real time.

Further, the PHM maintenance module 102 includes:

Use the data in the database to quickly train the model to obtain a self-training unit for the algorithm of the device;

The configuration file containing the algorithm is packaged and integrated to obtain the package unit of the algorithm toolkit.

Further, the database includes real-time operation data of equipment transmitted by the PHM application module 101 to the PHM maintenance module 102 through a communication circuit.

Further, the real-time operation data of the device includes raw data or data that has undergone feature extraction.

This embodiment implements fast training and algorithm reconstruction of the PHM algorithm model, updates the corresponding algorithm in time according to different states of the equipment, and overcomes the technical problems of poor adaptability and high algorithm update cost of the solidified equipment diagnosis and evaluation scheme in the prior art.

Example 2. PHM device

Fig. 2 is a schematic diagram of the composition of a PHM device provided by the present invention. As shown in Fig. 2, a PHM device for remote online assessment of equipment status includes:

An application device (or evaluation device) 1 connected to the device, including a PHM application module 101, used for collecting the device operation data through a variety of sensors, and using an embedded real-time diagnostic tool to evaluate and process the collected operation data, obtain the device status information;

A maintenance device 2 remotely connected to the evaluation device (or application device) 1 includes a PHM maintenance module 102 for establishing a communication circuit connecting the PHM application module 101, and sending the PHM application module 101 to the PHM application module 101 via the communication circuit An algorithmic self-training update toolkit that provides embedded real-time diagnostic tools.

The application device 1 may be any electronic device that can be loaded with the PHM application module 101 .

Wherein, the maintenance device 2 may be any workstation or computer capable of loading the PHM maintenance module 102 .

Application example: the application of aero-engine

The main purpose of the aero-engine configurable PHM rapid prototyping system is to realize remote reconfiguration and system management of different forms of PHM system configuration according to different application scenarios of aero-engines to support the rapid development and deployment of PHM applications.

The PHM rapid prototyping system for remote on-line evaluation of equipment status provided by the present invention can utilize the monitoring parameters collected during the life cycle of the aero-engine to analyze its parameter characteristics under different working conditions, so as to realize the real-time on-line health assessment and fault diagnosis of the aero-engine , and the storage of related data, providing status monitoring information for the airborne computer and ground management center, and providing data support for engine maintenance decisions. It has 1) support for fast training of PHM algorithm model; 2) support for algorithm toolkit reconstruction; 3) provide engine original monitoring parameters and online diagnosis and evaluation results for aero-engine ground database.

The working environment of aero-engines is relatively harsh and the space is small in the process of performing tasks. It is difficult to configure a PHM system on the aircraft that integrates data acquisition, algorithm training, feature extraction, diagnostic evaluation, and data storage. During the engine life cycle, the applicability of the solidified engine diagnostic evaluation scheme will gradually decrease, and the cost of algorithm update is high. Therefore, in order to realize the real-time monitoring of engine status and improve the efficiency and effect of algorithm use, the configurable PHM rapid prototyping system for aero-engines is divided into two modules: maintenance and application (ie, aero-engine PHM maintenance module and aero-engine PHM application module). Figure 3 is the overall architecture diagram of the maintenance module and the application module provided by the present invention. As shown in Figure 3, the maintenance module on the ground is composed of a high-performance workstation (or PHM maintenance server), which can realize the rapid training and packaging integration of the algorithm ; Airborne application modules include industrial computers (or reconfigurable PHM application computers) with strong environmental adaptability and various sensors (for data acquisition), which can process raw signals online in real time and evaluate engine status. Maintenance and application modules can be wired or wirelessly connected.

1. Function description

1.1 Maintenance module

The functional structure of the maintenance module of the aero-engine configurable PHM rapid prototyping system is shown in Figure 4. The functions include: (1) Algorithm training function: According to the algorithm model of the PHM development module, the original data is called from the database to quickly train the model, and the relevant configuration files are obtained. ; (2) Package integration function: package and integrate the algorithm and its parameters, interfaces and other configuration files according to unified standards to obtain an algorithm toolkit; (3) Communication function: use wired or wireless two-way communication between the maintenance module and the application module protocol for data transfer. In the maintenance module, the input is the algorithm model, and the output is the algorithm toolkit.

1.2. Application module functional requirements

The functional structure of the application module of the aero-engine configurable PHM rapid prototyping system is shown in Figure 5, including: (1) Data acquisition function: The application module can control the sensor to collect engine monitoring data, which is mainly divided into gas path parameters and vibration parameters; (2) Algorithm execution function: The application module can read the PHM algorithm model and its configuration file in the algorithm toolkit, input the collected monitoring data into the PHM algorithm model loaded with the configuration file for calculation, and obtain the engine diagnosis evaluation result (3) algorithm reconstruction function: if the application module receives the new algorithm toolkit sent by the maintenance module, then by analyzing the new algorithm toolkit, obtain the new PHM algorithm model and the new configuration file in the new algorithm toolkit , to obtain the new PHM algorithm model loaded with the new configuration file, if the application module only receives the new configuration file sent by the maintenance module, then load the new configuration file into the existing PHM algorithm model to obtain the Load the PHM algorithm model for the new profile. (4) Data storage function: The application module can store the original monitoring data and algorithm operation results. In the application module, the input is an algorithm toolkit, and the output is the raw monitoring data and online diagnostic evaluation results.

2. System technical scheme

2.1 Hardware technical solution

2.1.1 Maintenance Module Hardware Solution

In order to meet the requirements of multi-process simultaneous operation of the maintenance module and rapid processing of large amounts of data, the maintenance module server should use a workstation with powerful performance as much as possible. As shown in Figure 6, its CPU adopts the fifth-generation Intel top processor - Core i7-5930K, which can effectively ensure the execution speed of CPU operation algorithms. At the same time, most of the currently very popular intelligent algorithms use GPU for higher-speed network training. The GPU of this workstation is specially customized for deep learning, driven by four-way NVIDIA TITAN X, and equipped with the intuitive and easy-to-use DIGITS training system, which greatly enhances its machine. Learn the computing power of algorithms.

2.1.2 Application Module Hardware Solution

The hardware architecture of the application module is shown in Figure 7.

In order to meet the operation requirements of the application module and the real-time requirements of data processing, the application module computer needs to have a relatively powerful CPU. For this purpose, the fanless embedded industrial computer ARK-1550 from Advantech Co., Ltd. is selected, as shown in Figure 8. Its CPU uses the fourth-generation Intel Core i5-4300U, which ensures stability and has a faster computing speed. The industrial computer runs the Windows operating system, supports VGA, HDMI and LDVS display modes, and can view the running status in real time with an external monitor. Considering that the space inside the aircraft is small and the vibration is severe, the working environment is quite harsh, and the body size of the industrial computer is only 223*46.6*133.0mm, the normal working temperature range is -40~85℃, the environmental adaptability is strong, and the noise Small, very suitable as the computing center of the application platform.

In order to collect various parameters required by the system, different types of sensors need to be installed at each test point. In addition to meeting the necessary conditions such as accuracy and sampling rate, sensors should be selected as small in size and strong in environmental adaptability as possible.

2.2 Software technical solutions

2.2.1 Maintenance module software solution

2.2.1.1 Functional Description

During the operation of aero-engines, the working conditions are complex, and the methods for health assessment of working status and fault diagnosis of maintenance status are not static. In order to obtain a better diagnosis and assessment effect, it is necessary to continuously adjust the parameters of each algorithm according to the historical assessment results and the degradation trend of the engine. At the same time, the emergence and improvement of new algorithms such as deep learning models have brought higher accuracy to the diagnostic evaluation of engine conditions. Based on the consideration of rapid algorithm update and iteration, the PHM maintenance module implements the reconstruction technology of the diagnostic evaluation algorithm through the algorithm toolkit, and encapsulates the updated algorithm and its optimized configuration into an algorithm toolkit to easily realize the optimization and adjustment of the diagnostic evaluation process, which is highly efficient Utilize historical evaluation information for PHM rapid prototyping systems.

On the other hand, it is unrealistic to train algorithms such as neural networks that need to use a large amount of data for training on the machine. In order to improve the efficiency of algorithm execution, the maintenance module can make full use of its powerful performance to quickly train the algorithm, and the training completed Configuration files are integrated into the algorithm toolkit, allowing application modules to execute quickly.

2.2.1.2 Implementation method

The maintenance module method flow is shown in Figure 9:

(1) Receive the design scheme of the PHM development module, load the required data from the database into the model, and quickly train the algorithm model;

(2) After training, encapsulate and integrate the algorithm model and configuration file into an algorithm toolkit according to unified rules;

(3) Send the algorithm toolkit and the control instructions to the application module to the application module through wireless communication.

2.2.1.3 Input and output

The input of the maintenance module scheme is: algorithm model and database original data;

The output of the maintenance module scheme is: control instructions and algorithm toolkit for the application module.

It should be noted that the control instructions for the application module include, but are not limited to, control instructions for reconstructing the PHM algorithm model.

2.2.1.4 Functional Visualization

The overall interface of the maintenance module software is shown in Figure 10.

The data from the database can be loaded into the software to train the selected algorithm, as shown in Figure 11.

During the engine maintenance process, the maintenance module can establish a wireless connection with the application module, and realize the remote control of the application module. The original data and result data collected by the application module will be sent to the database. The interface is shown in Figure 12.

2.2.2 Application Module Software Solution

2.2.2.1 Functional Description

The monitoring parameters in the aero-engine life cycle mainly include gas path parameters and vibration data. The application module needs to coordinate various sensors to collect signals such as temperature, flow, pressure, acceleration, etc., and load the algorithm toolkit to process the data, so as to realize the real-time engine Diagnostic evaluation.

2.2.2.2 Implementation method

The application module method flow is shown in Figure 13:

(1) Load the algorithm toolkit sent by the maintenance module;

(2) Coordinate the collection of sensor parameters according to requirements;

(3) Perform preprocessing and feature extraction on the original data, so as to carry out health assessment and fault diagnosis of the engine, and store the results and original data;

(4) Send the results and raw data to the database during engine maintenance.

2.2.2.3 Input and output

The input of the application module scheme is: algorithm toolkit and control instructions;

The output of the application module program is: diagnostic evaluation results and raw monitoring data.

2.2.2.4 Functional Visualization

The overall interface of the application module software is shown in Figure 14. During maintenance, the application module can be connected to an external monitor to view raw monitoring data and historical diagnostic evaluation results.

To sum up, the present invention has the following technical effects:

1. The PHM rapid prototyping system provided by the embodiment of the present invention can use the operating data (such as vibration signal data, gas path parameter data) collected during the life cycle of the equipment (such as electromechanical equipment) to analyze its parameter characteristics under different working conditions , to achieve real-time online health assessment and fault diagnosis of equipment, as well as storage of related data, provide status monitoring information for onboard computers and management centers, and provide data support for equipment maintenance decisions.

2. The PHM rapid prototyping system provided by the embodiment of the present invention can realize the rapid training and algorithm reconstruction of the PHM algorithm model, update the corresponding algorithm in time according to the different states of the equipment, and overcome the poor adaptability of the equipment diagnosis and evaluation scheme solidified in the prior art , the technical problem of high algorithm update cost.

Although the present invention has been described in detail above, the present invention is not limited thereto, and various modifications can be made by those skilled in the art in accordance with the principles of the present invention. Therefore, all modifications made in accordance with the principles of the present invention should be understood as falling within the protection scope of the present invention.

Claims (8)

1. a PHM rapid prototyping system for remote online assessment equipment state, is characterized in that, described system comprises: The PHM maintenance module set on the ground is used to train the PHM algorithm model by using the historical monitoring data of the aircraft to obtain the algorithm configuration file after the training, and use the PHM algorithm model and the algorithm configuration file to generate an algorithm tool package, sent to the PHM application module; The PHM application module set in the aircraft is used for reconstructing the trained PHM algorithm model by using the received algorithm toolkit, and using the trained PHM algorithm model to perform an update on the current state of the aircraft. processing the monitoring data to obtain a diagnostic evaluation result of the aircraft; The PHM maintenance module includes: A model training unit for training the PHM algorithm model by loading the historical monitoring data into the PHM algorithm model to obtain an algorithm configuration file containing model parameters of the trained model; an encapsulation integration unit, configured to encapsulate and integrate the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit; Among them, PHM is fault prediction and health management; Wherein, the PHM maintenance module is further configured to acquire the historical monitoring data from the database and acquire the PHM algorithm model from the PHM development module before training the PHM algorithm model. 2. The system according to claim 1, wherein the PHM application module comprises: an algorithm reconstruction unit, configured to parse the algorithm toolkit, obtain the PHM algorithm model and the algorithm configuration file, and load the algorithm configuration file into the PHM algorithm model to obtain a trained PHM algorithm model; A diagnosis and evaluation unit is used to extract features from the current monitoring data of the aircraft by using the trained PHM algorithm model to obtain feature data, and to evaluate the aircraft according to the feature data to obtain the aircraft diagnostic evaluation results. 3. The system according to claim 2, wherein the PHM application module further comprises: A data acquisition unit, configured to collect current monitoring data of the aircraft, where the current monitoring data includes air path parameter data and vibration parameter data; and/or A data storage unit, configured to store the current monitoring data and/or corresponding diagnostic evaluation results. 4. The system according to claim 3, wherein the PHM application module is further configured to save the current monitoring data and/or the corresponding diagnostic evaluation results to a database. 5. The system according to claim 2 or 3 or 4, wherein the PHM application module is further configured to send the current monitoring data and/or the corresponding diagnostic evaluation result to a device provided on the aircraft. Human-computer interaction module. 6. The system according to claim 1, wherein the PHM maintenance module is further configured to generate a control instruction for reconstructing the PHM algorithm model, and send the algorithm toolkit to the PHM application module At the same time, the control instruction for reconstructing the PHM algorithm model is sent to the PHM application module. 7 . The system according to claim 6 , wherein the PHM application module is specifically configured to reconstruct the trained PHM algorithm model according to the control instruction for reconstructing the PHM algorithm model. 8 . 8. The system according to claim 1, wherein the PHM maintenance module is a high-performance workstation, and the PHM application module is an industrial computer.

Images