CN117270514B - Production process whole-flow fault detection method based on industrial Internet of things - Google Patents
Production process whole-flow fault detection method based on industrial Internet of things Download PDFInfo
- Publication number
- CN117270514B CN117270514B CN202311559137.6A CN202311559137A CN117270514B CN 117270514 B CN117270514 B CN 117270514B CN 202311559137 A CN202311559137 A CN 202311559137A CN 117270514 B CN117270514 B CN 117270514B
- Authority
- CN
- China
- Prior art keywords
- fault
- intelligent manufacturing
- abnormal
- manufacturing equipment
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0256—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults injecting test signals and analyzing monitored process response, e.g. injecting the test signal while interrupting the normal operation of the monitored system; superimposing the test signal onto a control signal during normal operation of the monitored system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to the technical field of intelligent workshop monitoring, and discloses a production process full-flow fault detection method based on an industrial Internet of things, which comprises the steps of obtaining a second running state coefficient of each intelligent manufacturing device, and determining abnormal intelligent manufacturing devices in a preset production time interval based on the second running state coefficient; acquiring abnormal characterization data of the abnormal intelligent manufacturing equipment, determining fault attribute data of the abnormal intelligent manufacturing equipment according to the abnormal characterization data, and determining fault analysis data corresponding to the fault attribute data based on a preset relationship between the fault attribute number and the fault analysis data; collecting an actual measurement voltage set of a fault component in a preset time range according to the fault component zone bit, and determining a fault cause of abnormal intelligent manufacturing equipment based on actual measurement voltage data; the measured voltage set includes a plurality of measured voltages.
Description
Technical Field
The invention relates to the technical field of intelligent workshop monitoring, in particular to a production process full-flow fault detection method based on an industrial Internet of things.
Background
With the rapid development of global manufacturing industry and the continuous innovation of industrial internet and other technologies, production workshops have gradually moved to digitization, intellectualization and automation directions and are transformed into digitalized intelligent workshops; in an intelligent workshop, stable operation and management of equipment are critical to production efficiency and product quality; currently, most of equipment monitoring in an intelligent workshop is performed by transmitting collected data of each item of equipment to a cloud platform; however, as the types and the number of intelligent devices and instruments installed in intelligent workshops are rapidly increased, the cloud centralized data processing mode is easy to cause response delay of real-time services, which is fatal to industrial workshops with high real-time requirements and seriously causes equipment shutdown; therefore, how to ensure that the equipment of the workshop can respond faster when the equipment is operated without stopping the machine, and the method becomes an urgent requirement of the intelligent workshop.
At present, the existing production process full-flow fault detection method based on the industrial internet of things is mostly realized based on cloud design, for example, china patent with the authority of bulletin No. CN113900426B discloses a remote equipment control and fault diagnosis system based on 5G+ industrial internet, for example, china patent with the application publication No. CN115202962A discloses a rapid equipment fault diagnosis method and system based on an industrial internet platform, and although the method can realize remote fault monitoring, the inventor researches and applies the method and the prior art to find that at least the following part of defects exist in the method and the prior art:
(1) With the continuous complexity and increase of intelligent manufacturing equipment, abnormal intelligent manufacturing equipment is difficult to discover in time based on a cloud processing mode, and abnormal components of the abnormal intelligent manufacturing equipment cannot be determined;
(2) The failure cause of the abnormal intelligent manufacturing equipment cannot be determined in time, so that the equipment failure warning information can not respond quickly while the equipment is not stopped.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a production process whole-flow fault detection method based on the industrial Internet of things.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the method for detecting the full-flow fault of the production process based on the industrial Internet of things comprises the following steps:
acquiring a second operation state coefficient of each intelligent manufacturing apparatus, and determining abnormal intelligent manufacturing apparatuses within a preset production time interval based on the second operation state coefficient;
obtaining abnormal characterization data of the abnormal intelligent manufacturing equipment, determining fault attribute data of the abnormal intelligent manufacturing equipment according to the abnormal characterization data, and determining fault analysis data corresponding to the fault attribute data based on a preset relation between the fault attribute number and the fault analysis data, wherein the fault analysis data comprises Z fault reasons and standard fault voltage fluctuation intervals related to the fault reasons; the fault attribute data comprises a fault component and a fault component zone bit, wherein Z is a positive integer greater than zero;
Collecting an actual measurement voltage set of a fault component in a preset time range according to the fault component zone bit, and determining a fault cause of abnormal intelligent manufacturing equipment based on actual measurement voltage data; the set of measured voltages includes a plurality of measured voltages.
Further, the obtaining the second operation state coefficient of each intelligent manufacturing apparatus includes:
acquiring a current time T, and determining a preset production time interval to which the current time T belongs; determining an intelligent manufacturing equipment set at the current moment T based on a preset relation between a preset production time interval and the intelligent manufacturing equipment set, wherein the intelligent manufacturing equipment set comprises N intelligent manufacturing equipment corresponding to each preset production time interval and unique identification data of each corresponding intelligent manufacturing equipment, and N is an integer larger than zero;
and inputting the preset production time interval and the unique identification data of the intelligent manufacturing equipment corresponding to the preset production time interval into a pre-constructed coefficient regression model to acquire the running state coefficient of each intelligent manufacturing equipment.
Further, the pre-construction logic of the coefficient regression model is as follows: acquiring first historical sample data which is pre-stored in a system database and is used for training a coefficient regression model, wherein the first historical sample data comprises a preset production time interval, unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval and a second running state coefficient of the intelligent manufacturing equipment; dividing first historical sample data for training a coefficient regression model into a coefficient training set and a coefficient testing set, constructing a regression network model, taking a preset production time interval in the coefficient training set and unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval as input of the regression network model, taking a second running state coefficient of the intelligent manufacturing equipment in the coefficient training set as output of the regression network model, and training the regression network model to obtain an initial regression network model; and evaluating the model effect of the initial regression network model by using a mean square error algorithm, and screening the corresponding initial regression network model with the value larger than or equal to the preset evaluation value as a coefficient regression model.
Further, the generating logic of the second operation state coefficient is as follows:
acquiring running state data of intelligent manufacturing equipment; the running state data comprise the production task quantity, the processing quality coefficient of the single product and the processing speed of the single product in a certain time;
extracting the correction coefficient of each intelligent manufacturing device based on the preset relation between the intelligent manufacturing device and the correction coefficient;
performing formulated calculation based on the operation state data and the correction coefficients to obtain a second operation state coefficient of each intelligent manufacturing apparatus; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Representing a second operating state coefficient,/->Representing the production task amount per unit time,/>indicating the machining quality coefficient of the finished i-th single-piece product,/->Indicating the processing speed of the ith single-piece product, < >>Representing correction factors->Representing natural constants.
Further, the generation logic of the processing quality coefficient of the ith single-piece product is as follows:
acquiring an image of each single product after processing through a camera device; extracting standard processing images corresponding to the single products, which are prestored in a system database;
taking the image processed by the single product as a first processed image, and taking a standard processed image corresponding to the single product as a second processed image;
Dividing the first processing image and the second processing image into a plurality of areas according to the same dividing rule;
comparing pixel points of the same position areas of the first processing image and the second processing image one by one, and recording a difference area where the difference exists between the first processing image and the second processing image;
counting the number of difference areas with differences to obtain the total number of the difference areas, and taking the total number of the difference areas as the processing quality coefficient of the single product.
Further, determining an abnormal intelligent manufacturing apparatus within a predetermined production time interval, comprising:
extracting a first running state coefficient of abnormal intelligent manufacturing equipment;
comparing the first running state coefficient with the second running state coefficient, and if the first running state coefficient is greater than or equal to the second running state coefficient, judging that the corresponding intelligent manufacturing equipment is normal intelligent manufacturing equipment;
if the first running state coefficient is smaller than the second running state coefficient, the corresponding intelligent manufacturing equipment is judged to be abnormal intelligent manufacturing equipment.
Further, the anomaly characterization data includes an anomaly vibration spectrogram and an anomaly temperature spectrogram;
acquiring anomaly characterization data for an anomaly intelligent manufacturing device, comprising:
a1: acquiring an engine rotating speed R of abnormal intelligent manufacturing equipment and vibration signal data of the abnormal intelligent manufacturing equipment under the engine rotating speed R; constructing a vibration time domain diagram by taking time in vibration signal data as a horizontal axis and taking amplitude in the vibration signal data as a vertical axis;
a2: dividing the vibration time domain graph in equal parts according to T vibration periods to obtain an actual vibration waveform set, wherein the actual vibration waveform set comprises H actual vibration waveforms, and T is a positive integer greater than zero;
a3: extracting an h actual vibration waveform in the actual vibration waveform set, wherein h is a positive integer greater than zero, and the initial value of h is 1;
a4: acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard vibration waveform associated with the corresponding rotating speed interval, calculating the similarity of an actual vibration waveform and the standard vibration waveform, and jumping to the step a5 if the similarity of the actual vibration waveform and the standard vibration waveform is larger than or equal to a preset vibration similarity threshold value; if the similarity between the actual vibration waveform and the standard vibration waveform is smaller than a preset vibration similarity threshold, marking the actual vibration waveform as an abnormal vibration waveform, and jumping to the step a5;
a5: let h=h+1 and jump back to step a3;
a6: repeating the steps a3 to a5 until h=H, ending the cycle, and obtaining a plurality of abnormal vibration waveforms;
a7: and extracting the similarity corresponding to each abnormal vibration waveform, and carrying out Fourier transformation on the abnormal vibration waveform with the minimum similarity to obtain an abnormal vibration spectrogram.
Further, the acquiring the anomaly characterization data of the anomaly intelligent manufacturing apparatus further includes:
b1: acquiring an engine rotating speed R of abnormal intelligent manufacturing equipment and acquiring temperature signal data of the abnormal intelligent manufacturing equipment at the engine rotating speed R; constructing a temperature time domain diagram by taking time in the temperature signal data as a horizontal axis and taking a temperature value in the temperature signal data as a vertical axis;
b2: dividing the temperature time domain graph in equal parts according to W temperature periods to obtain an actual temperature waveform set, wherein the actual temperature waveform set comprises Q actual temperature waveforms, and W is a positive integer greater than zero;
b3: extracting the q-th actual temperature waveform in the actual temperature waveform set, wherein q is a positive integer greater than zero, and the initial value of q is 1;
b4: b5, acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard temperature waveform associated with the corresponding rotating speed interval, calculating the similarity between an actual temperature waveform and the standard temperature waveform, and jumping to the step b5 if the similarity between the actual temperature waveform and the standard temperature waveform is greater than or equal to a preset temperature similarity threshold; if the similarity between the actual temperature waveform and the standard temperature waveform is smaller than the preset temperature similarity threshold, marking the actual temperature waveform as an abnormal temperature waveform, and jumping to the step b5;
b5: let q=q+1 and jump back to step b3;
b6: repeating the steps b 3-b 5 until q=q, ending the cycle to obtain a plurality of abnormal temperature waveforms;
b7: and extracting the similarity corresponding to each abnormal temperature waveform, and carrying out Fourier transformation on the abnormal temperature waveform with the minimum similarity to obtain an abnormal temperature spectrogram.
Further, the determining fault attribute data of the abnormal intelligent manufacturing apparatus includes:
acquiring an abnormal vibration spectrogram and an abnormal temperature spectrogram of abnormal intelligent manufacturing equipment;
and inputting the abnormal vibration spectrogram and the abnormal temperature spectrogram into an attribute data identification model to determine fault attribute data of the abnormal intelligent manufacturing equipment.
Further, the generating logic of the attribute data identification model is as follows: acquiring second historical sample data which is pre-stored in a system database and is used for training an attribute data identification model, wherein the second historical sample data comprises an abnormal vibration spectrogram, an abnormal temperature spectrogram, a fault component and a fault component zone bit; dividing second historical sample data for training an attribute data identification model into an attribute training set and an attribute testing set, constructing a regression network model, taking an abnormal vibration spectrogram and an abnormal temperature spectrogram in the attribute training set as inputs of the regression network model, taking fault components and fault component areas in the attribute training set as outputs of the regression network model, and training the regression network model to obtain an initial regression network model; and performing model test on the initial regression network model by using the sum attribute test set, and screening the corresponding initial regression network model with the accuracy greater than or equal to the preset test as an attribute data identification model.
Further, the determining the failure cause of the abnormal intelligent manufacturing apparatus includes:
c1: extracting a normal voltage fluctuation interval according to a preset relation between the fault component and the normal voltage fluctuation interval; maximum normal voltage of the normal voltage fluctuation intervalAnd minimum normal voltage->；
c2: comparing the measured voltage set with the normal voltage fluctuation interval to obtain the voltage greater than the maximum normal voltage in the measured voltage setIs less than the minimum normal voltage in the set of measured voltages>Is a measured voltage of (2);
c3: will be greater than the maximum normal voltageAs a first measured voltage, and taking a measured voltage less than a minimum normal voltage as a second measured voltage;
c4: respectively counting the number of the first measured voltage and the second measured voltage to obtain the total number of the first measured voltage and the total number of the second measured voltage;
c5: comparing the total number of the first actually measured voltage with the total number of the second actually measured voltage, if the total number of the first actually measured voltage is larger than or equal to the total number of the second actually measured voltage, acquiring the average value of the first actually measured voltage, and jumping to the step c6; if the total number of the first measured voltages is smaller than the total number of the second measured voltages, obtaining the average value of the second measured voltages, and jumping to the step c7;
c6: taking the average value of the first measured voltage as a first average value, comparing the first average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the first average value falls; taking the corresponding fault reason of the corresponding standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment;
c7: taking the average value of the second measured voltage as a second average value, comparing the second average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the second average value falls; and taking the corresponding fault reason corresponding to the standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment.
An electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the production process full-flow fault detection method based on the industrial Internet of things when executing the computer program.
A computer readable storage medium, on which a computer program is stored, which when executed implements the above-described industrial internet of things-based production process full-flow fault detection method.
Compared with the prior art, the invention has the beneficial effects that:
1. the application discloses a production process full-flow fault detection method based on industrial Internet of things, which comprises the steps of firstly, obtaining a second running state coefficient of each intelligent manufacturing device, and determining abnormal intelligent manufacturing devices in a preset production time interval based on the second running state coefficient; then, obtaining abnormal characterization data of the abnormal intelligent manufacturing equipment, determining fault attribute data of the abnormal intelligent manufacturing equipment according to the abnormal characterization data, and determining fault analysis data corresponding to the fault attribute data based on a preset relationship between the fault attribute number and the fault analysis data; finally, collecting actual measurement voltage sets of the fault components within a preset time range according to the fault component zone locations, and determining fault reasons of the abnormal intelligent manufacturing equipment based on the actual measurement voltage data; the measured voltage set comprises a plurality of measured voltages; based on the steps, the method and the device discover the abnormal intelligent manufacturing equipment in time and can not determine the abnormal components of the abnormal intelligent manufacturing equipment.
2. The application discloses a production process whole-flow fault detection method based on an industrial Internet of things, which is used for determining fault analysis data corresponding to fault attribute data based on a preset relation between the fault attribute number and the fault analysis data, so that the fault cause of abnormal intelligent manufacturing equipment can be determined in time; in addition, compared with a cloud remote monitoring mode, the device data acquisition, analysis and alarm are realized at the device end, so that the device fault alarm information can be responded more quickly while the device is operated without stopping; and further is beneficial to ensuring the production stability of the intelligent workshop.
Drawings
FIG. 1 is a schematic diagram of a production process overall fault detection method based on an industrial Internet of things, which is provided by the invention;
FIG. 2 is a schematic diagram of logic for obtaining anomaly characterization data according to the present invention;
FIG. 3 is a schematic diagram of another logic for obtaining anomaly characterization data according to the present invention;
FIG. 4 is a logic diagram for determining the cause of a failure of an abnormal intelligent manufacturing apparatus provided by the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the disclosure of the present embodiment provides a method for detecting a full-flow fault in a production process based on an industrial internet of things, where the method includes:
s101: acquiring a second operation state coefficient of each intelligent manufacturing apparatus, and determining abnormal intelligent manufacturing apparatuses within a preset production time interval based on the second operation state coefficient;
It should be appreciated that: the invention is applied to a digitalized intelligent workshop at an edge, M automatic production lines based on the industrial Internet of things exist in the intelligent workshop, M is a positive integer greater than zero, a plurality of intelligent manufacturing devices are deployed in each automatic production line, and each intelligent manufacturing device executes automatic processing production within a respective preset production time interval; the intelligent manufacturing equipment is internally provided with a plurality of sensors, and the intelligent workshop is provided with a plurality of camera devices, wherein the sensors comprise but are not limited to a vibration sensor, a temperature sensor, a rotating speed sensor and a voltage sensor;
in an implementation, the obtaining the second operating state coefficients for each smart manufacturing device includes:
acquiring a current time T, and determining a preset production time interval to which the current time T belongs; determining an intelligent manufacturing equipment set at the current moment T based on a preset relation between a preset production time interval and the intelligent manufacturing equipment set, wherein the intelligent manufacturing equipment set comprises N intelligent manufacturing equipment corresponding to each preset production time interval and unique identification data of each corresponding intelligent manufacturing equipment, and N is an integer larger than zero;
It should be noted that: the system database is pre-stored with a plurality of preset relations between preset production time intervals and the intelligent manufacturing equipment set; further exemplary illustration is given by the existence of 3 automated lines, each with one intelligent manufacturing facility, m1, m2 and m3 respectively; wherein, the preset production time interval of m1 is 9 to 10 points, the preset production time interval of m2 is 14 to 15 points, and the preset production time interval of m3 is 15 to 16 points; therefore, in this case, there are 3 preset relationships between the preset production time interval and the intelligent manufacturing equipment set, that is, the preset relationship between the preset production time interval (9 to 10 points) and the intelligent manufacturing equipment set, the preset relationship between the preset production time interval (14 to 15 points) and the intelligent manufacturing equipment set, and the preset relationship between the preset production time interval (15 to 16 points) and the intelligent manufacturing equipment set; if the current time T is 9 points for 30 minutes at the moment, the determined intelligent manufacturing equipment set at the current time T is m1;
inputting a preset production time interval and unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval into a pre-constructed coefficient regression model to obtain an operation state coefficient of each intelligent manufacturing equipment;
It should be noted that: the unique identification data is one of a machine identifier or a machine code, which includes but is not limited to a MAC address, an IP address, a serial number, a UUID (universal unique identifier) or other custom identifiers, which is not excessively limited to the present invention;
specifically, the pre-construction logic of the coefficient regression model is as follows: acquiring first historical sample data which is pre-stored in a system database and is used for training a coefficient regression model, wherein the first historical sample data comprises a preset production time interval, unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval and a second running state coefficient of the intelligent manufacturing equipment; dividing first historical sample data for training a coefficient regression model into a coefficient training set and a coefficient testing set, constructing a regression network model, taking a preset production time interval in the coefficient training set and unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval as input of the regression network model, taking a second running state coefficient of the intelligent manufacturing equipment in the coefficient training set as output of the regression network model, and training the regression network model to obtain an initial regression network model; evaluating model effects of the initial regression network model by means of a mean square error algorithm, and screening the corresponding initial regression network model with the evaluation value larger than or equal to the preset evaluation value as a coefficient regression model;
The regression network model comprises, but is not limited to, a random forest regression algorithm model, a support vector machine regression algorithm model, an Xgboost regression algorithm model, a K neighbor regression algorithm model, a neural network algorithm model, a long-term and short-term memory network algorithm model and the like; the mean square error algorithm has the following calculation formula:wherein: />Representing an evaluation value->A sample of the features is represented and,representing the coefficient test set, ++>Representing the true value +_>Representing predicted values +.>Representing the number of test samples in the coefficient test set;
specifically, the logic for generating the second running state coefficient is as follows:
acquiring running state data of intelligent manufacturing equipment; the running state data comprise the production task quantity, the processing quality coefficient of the single product and the processing speed of the single product in a certain time;
extracting the correction coefficient of each intelligent manufacturing device based on the preset relation between the intelligent manufacturing device and the correction coefficient;
performing formulated calculation based on the operation state data and the correction coefficients to obtain a second operation state coefficient of each intelligent manufacturing apparatus; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Representing a second operating state coefficient,/->Representing the production task amount per unit time, />Indicating the machining quality coefficient of the finished i-th single-piece product,/->Indicating the processing speed of the ith single-piece product, < >>Representing correction factors->Representing natural constants;
the generation logic of the processing quality coefficient of the ith single-piece product is as follows:
acquiring an image of each single product after processing through a camera device; extracting standard processing images corresponding to the single products, which are prestored in a system database;
taking the image processed by the single product as a first processed image, and taking a standard processed image corresponding to the single product as a second processed image;
dividing the first processing image and the second processing image into a plurality of areas according to the same dividing rule;
comparing pixel points of the same position areas of the first processing image and the second processing image one by one, and recording a difference area where the difference exists between the first processing image and the second processing image;
it should be noted that: the dividing mode of dividing the area in the first processing image and the dividing mode of dividing the area in the second processing image are identical with the size of the area, then the areas at the same position in the first processing image and the second processing image are compared one by one, the comparison mode adopted by the areas at the same position is that each pixel point is compared one by one, and if the pixel points with differences in the areas at the same position exceed a certain percentage, the difference in the areas at the same position is judged;
Counting the number of difference areas with differences to obtain the total number of the difference areas, and taking the total number of the difference areas as the processing quality coefficient of a single product;
it should be appreciated that: the larger the machining quality coefficient of the single product is, the more serious the defect of the single product is, the lower the machining quality of corresponding intelligent manufacturing equipment is, and the higher the machining quality is on the contrary; the greater the processing speed of a single product is, the less smooth the operation action of the corresponding intelligent manufacturing equipment is, and on the contrary, the operation action is smooth; the larger the production task amount within a certain time, the higher the machining efficiency of the corresponding intelligent manufacturing equipment is, and the lower the machining efficiency is;
wherein, according to the correction coefficient, the fault probability of the intelligent manufacturing equipment is assigned; the calculation formula of the fault probability of the intelligent manufacturing equipment is as follows:(/>) The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />The probability of failure is indicated and,representing the number of historical failures of the smart manufacturing device, +.>Indicating the set number of faults of the intelligent manufacturing equipment, +.>Indicating the number of historical maintenance of the smart manufacturing device, +.>Representing the set maintenance times of the intelligent manufacturing equipment;
it should be appreciated that: the historical failure times are not equal to the historical maintenance times, because for the intelligent manufacturing equipment, shutdown is caused by sudden reasons in some cases, but the intelligent manufacturing equipment can still continue to normally operate after the person is restarted, and for the case that the intelligent manufacturing equipment can still continue to normally operate after the person is restarted, the intelligent manufacturing equipment does not belong to the failure category, but is brought into the maintenance range;
In an implementation, determining an abnormal intelligent manufacturing apparatus within a predetermined production time interval, comprising:
extracting a first running state coefficient of abnormal intelligent manufacturing equipment;
it should be noted that: the calculation process of the first operation state coefficient is the same as the generation process of the second operation state coefficient, and details are referred to above, and will not be repeated here;
comparing the first running state coefficient with the second running state coefficient, and if the first running state coefficient is greater than or equal to the second running state coefficient, judging that the corresponding intelligent manufacturing equipment is normal intelligent manufacturing equipment;
if the first running state coefficient is smaller than the second running state coefficient, judging that the corresponding intelligent manufacturing equipment is abnormal intelligent manufacturing equipment;
s102: obtaining abnormal characterization data of the abnormal intelligent manufacturing equipment, determining fault attribute data of the abnormal intelligent manufacturing equipment according to the abnormal characterization data, and determining fault analysis data corresponding to the fault attribute data based on a preset relation between the fault attribute number and the fault analysis data, wherein the fault analysis data comprises Z fault reasons and standard fault voltage fluctuation intervals related to the fault reasons; the fault attribute data comprises a fault component and a fault component zone bit, wherein Z is a positive integer greater than zero;
Specifically, the abnormal characterization data comprises an abnormal vibration spectrogram and an abnormal temperature spectrogram;
in one embodiment, as shown in fig. 2 (a logical schematic diagram of obtaining anomaly characterization data), obtaining anomaly characterization data for an anomaly smart manufacturing device includes:
a1: acquiring an engine rotating speed R of abnormal intelligent manufacturing equipment and vibration signal data of the abnormal intelligent manufacturing equipment under the engine rotating speed R; constructing a vibration time domain diagram by taking time in vibration signal data as a horizontal axis and taking amplitude in the vibration signal data as a vertical axis;
a2: dividing the vibration time domain graph in equal parts according to T vibration periods to obtain an actual vibration waveform set, wherein the actual vibration waveform set comprises H actual vibration waveforms, and T is a positive integer greater than zero;
a3: extracting an h actual vibration waveform in the actual vibration waveform set, wherein h is a positive integer greater than zero, and the initial value of h is 1;
a4: acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard vibration waveform associated with the corresponding rotating speed interval, calculating the similarity of an actual vibration waveform and the standard vibration waveform, and jumping to the step a5 if the similarity of the actual vibration waveform and the standard vibration waveform is larger than or equal to a preset vibration similarity threshold value; if the similarity between the actual vibration waveform and the standard vibration waveform is smaller than a preset vibration similarity threshold, marking the actual vibration waveform as an abnormal vibration waveform, and jumping to the step a5;
It should be noted that: a plurality of rotating speed intervals are prestored in a system database, each rotating speed interval is associated with a standard vibration waveform, and the standard vibration waveform reflects the normal vibration characterization of the intelligent manufacturing equipment under the fault-free condition;
a5: let h=h+1 and jump back to step a3;
a6: repeating the steps a3 to a5 until h=H, ending the cycle, and obtaining a plurality of abnormal vibration waveforms;
a7: extracting the similarity corresponding to each abnormal vibration waveform, and carrying out Fourier transformation on the abnormal vibration waveform with the minimum similarity to obtain an abnormal vibration spectrogram;
it should be appreciated that: the Fourier transform is specifically one of fast Fourier transform or short-time Fourier transform;
in one specific embodiment, as shown in fig. 3 (another logic schematic diagram for acquiring exception characterization data), the acquiring exception characterization data of the exception intelligent manufacturing apparatus further includes:
b1: acquiring an engine rotating speed R of abnormal intelligent manufacturing equipment and acquiring temperature signal data of the abnormal intelligent manufacturing equipment at the engine rotating speed R; constructing a temperature time domain diagram by taking time in the temperature signal data as a horizontal axis and taking a temperature value in the temperature signal data as a vertical axis;
b2: dividing the temperature time domain graph in equal parts according to W temperature periods to obtain an actual temperature waveform set, wherein the actual temperature waveform set comprises Q actual temperature waveforms, and W is a positive integer greater than zero;
b3: extracting the q-th actual temperature waveform in the actual temperature waveform set, wherein q is a positive integer greater than zero, and the initial value of q is 1;
b4: b5, acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard temperature waveform associated with the corresponding rotating speed interval, calculating the similarity between an actual temperature waveform and the standard temperature waveform, and jumping to the step b5 if the similarity between the actual temperature waveform and the standard temperature waveform is greater than or equal to a preset temperature similarity threshold; if the similarity between the actual temperature waveform and the standard temperature waveform is smaller than the preset temperature similarity threshold, marking the actual temperature waveform as an abnormal temperature waveform, and jumping to the step b5;
it should be noted that: each rotating speed interval is also associated with a standard temperature waveform, and the standard temperature waveform reflects the normal temperature representation of the intelligent manufacturing equipment under the fault-free condition;
b5: let q=q+1 and jump back to step b3;
b6: repeating the steps b 3-b 5 until q=q, ending the cycle to obtain a plurality of abnormal temperature waveforms;
b7: extracting the similarity corresponding to each abnormal temperature waveform, and carrying out Fourier transform on the abnormal temperature waveform with the minimum similarity to obtain an abnormal temperature spectrogram;
in an implementation, the determining fault attribute data for an abnormal intelligent manufacturing apparatus includes:
acquiring an abnormal vibration spectrogram and an abnormal temperature spectrogram of abnormal intelligent manufacturing equipment;
inputting the abnormal vibration spectrogram and the abnormal temperature spectrogram into an attribute data identification model to determine fault attribute data of abnormal intelligent manufacturing equipment;
specifically, the generating logic of the attribute data identification model is as follows: acquiring second historical sample data which is pre-stored in a system database and is used for training an attribute data identification model, wherein the second historical sample data comprises an abnormal vibration spectrogram, an abnormal temperature spectrogram, a fault component and a fault component zone bit; dividing second historical sample data for training an attribute data identification model into an attribute training set and an attribute testing set, constructing a regression network model, taking an abnormal vibration spectrogram and an abnormal temperature spectrogram in the attribute training set as inputs of the regression network model, taking fault components and fault component areas in the attribute training set as outputs of the regression network model, and training the regression network model to obtain an initial regression network model; performing model test on the initial regression network model by using the sum attribute test set, and screening a corresponding initial regression network model with the accuracy greater than or equal to the preset test accuracy as an attribute data identification model;
Wherein the regression network model comprises, but is not limited to, a random forest regression algorithm model, a support vector machine regression algorithm model, a neural network algorithm model and the like;
s103: collecting an actual measurement voltage set of a fault component in a preset time range according to the fault component zone bit, and determining a fault cause of abnormal intelligent manufacturing equipment based on actual measurement voltage data; the measured voltage set comprises a plurality of measured voltages;
in implementation, as shown in fig. 3 (a logic diagram for determining a cause of a failure of an abnormal smart manufacturing device), the determining the cause of the failure of the abnormal smart manufacturing device includes:
c1: extracting a normal voltage fluctuation interval according to a preset relation between the fault component and the normal voltage fluctuation interval; maximum normal voltage of the normal voltage fluctuation intervalAnd minimum normal voltage->；
It should be noted that: the system database is pre-stored with a plurality of normal voltage fluctuation intervals under different conditions (such as working temperature, running time and equipment power), and each normal voltage fluctuation interval reflects the normal voltage fluctuation range of the intelligent manufacturing equipment under the fault-free condition;
c2: comparing the measured voltage set with the normal voltage fluctuation interval to obtain the voltage greater than the maximum normal voltage in the measured voltage set Is less than the minimum normal voltage in the set of measured voltages>Is a measured voltage of (2);
c3: will be greater than the maximum normal voltageAs a first measured voltage, and taking a measured voltage less than a minimum normal voltage as a second measured voltage;
c4: respectively counting the number of the first measured voltage and the second measured voltage to obtain the total number of the first measured voltage and the total number of the second measured voltage;
c5: comparing the total number of the first actually measured voltage with the total number of the second actually measured voltage, if the total number of the first actually measured voltage is larger than or equal to the total number of the second actually measured voltage, acquiring the average value of the first actually measured voltage, and jumping to the step c6; if the total number of the first measured voltages is smaller than the total number of the second measured voltages, obtaining the average value of the second measured voltages, and jumping to the step c7;
c6: taking the average value of the first measured voltage as a first average value, comparing the first average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the first average value falls; taking the corresponding fault reason of the corresponding standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment;
c7: taking the average value of the second measured voltage as a second average value, comparing the second average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the second average value falls; and taking the corresponding fault reason corresponding to the standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment.
Example 2
The embodiment discloses an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes any one of the industrial Internet of things-based production process full-flow fault detection methods provided by the methods when executing the computer program.
Since the electronic device described in this embodiment is an electronic device used to implement the industrial internet of things-based production process overall-flow fault detection method in this embodiment, those skilled in the art can understand the specific implementation manner of the electronic device and various variations thereof based on the industrial internet of things-based production process overall-flow fault detection method described in this embodiment, so how to implement the method in this embodiment of the present application will not be described in detail herein. As long as the electronic equipment adopted by the person skilled in the art to implement the industrial Internet of things-based production process full-flow fault detection method in the embodiment of the application belongs to the scope of protection intended by the application.
Example 3
The embodiment discloses a computer readable storage medium, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the whole-flow fault detection method of the industrial Internet of things-based production process provided by any one of the methods when executing the computer program.
The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and preset parameters, weights and threshold selection in the formulas are set according to the situation by those skilled in the art.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced 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 site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the elements is merely one, and there may be additional divisions in implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected as needed to achieve the objectives of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (12)
1. The production process full-flow fault detection method based on the industrial Internet of things is characterized by comprising the following steps of:
acquiring a second operation state coefficient of each intelligent manufacturing apparatus, and determining abnormal intelligent manufacturing apparatuses within a preset production time interval based on the second operation state coefficient;
the obtaining the second operation state coefficient of each intelligent manufacturing apparatus includes:
acquiring a current time T, and determining a preset production time interval to which the current time T belongs; determining an intelligent manufacturing equipment set at the current moment T based on a preset relation between a preset production time interval and the intelligent manufacturing equipment set, wherein the intelligent manufacturing equipment set comprises N intelligent manufacturing equipment corresponding to each preset production time interval and unique identification data of each corresponding intelligent manufacturing equipment, and N is an integer larger than zero;
inputting a preset production time interval and unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval into a pre-constructed coefficient regression model to obtain an operation state coefficient of each intelligent manufacturing equipment;
obtaining abnormal characterization data of the abnormal intelligent manufacturing equipment, determining fault attribute data of the abnormal intelligent manufacturing equipment according to the abnormal characterization data, and determining fault analysis data corresponding to the fault attribute data based on a preset relation between the fault attribute number and the fault analysis data, wherein the fault analysis data comprises Z fault reasons and standard fault voltage fluctuation intervals related to the fault reasons; the fault attribute data comprises a fault component and a fault component zone bit, wherein Z is a positive integer greater than zero;
Collecting an actual measurement voltage set of a fault component in a preset time range according to the fault component zone bit, and determining a fault cause of abnormal intelligent manufacturing equipment based on actual measurement voltage data; the set of measured voltages includes a plurality of measured voltages.
2. The industrial internet of things-based production process full-flow fault detection method of claim 1, wherein the pre-construction logic of the coefficient regression model is: acquiring first historical sample data which is pre-stored in a system database and is used for training a coefficient regression model, wherein the first historical sample data comprises a preset production time interval, unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval and a second running state coefficient of the intelligent manufacturing equipment; dividing first historical sample data for training a coefficient regression model into a coefficient training set and a coefficient testing set, constructing a regression network model, taking a preset production time interval in the coefficient training set and unique identification data of intelligent manufacturing equipment corresponding to the preset production time interval as input of the regression network model, taking a second running state coefficient of the intelligent manufacturing equipment in the coefficient training set as output of the regression network model, and training the regression network model to obtain an initial regression network model; and evaluating the model effect of the initial regression network model by using a mean square error algorithm, and screening the corresponding initial regression network model with the value larger than or equal to the preset evaluation value as a coefficient regression model.
3. The industrial internet of things-based production process full-flow fault detection method of claim 2, wherein the generating logic of the second operation state coefficient is as follows:
acquiring running state data of intelligent manufacturing equipment; the running state data comprise the production task quantity, the processing quality coefficient of the single product and the processing speed of the single product in a certain time;
extracting the correction coefficient of each intelligent manufacturing device based on the preset relation between the intelligent manufacturing device and the correction coefficient;
performing formulated calculation based on the operation state data and the correction coefficients to obtain a second operation state coefficient of each intelligent manufacturing apparatus; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Representing a second operating state coefficient,/->Representing the production task quantity per unit time, +.>Indicating the machining quality coefficient of the finished i-th single-piece product,/->Indicating the processing speed of the ith single-piece product, < >>Representing correction factors->Representing natural constants.
4. The industrial internet of things-based production process full-flow fault detection method according to claim 3, wherein the generation logic of the processing quality coefficient of the i-th single product is as follows:
Acquiring an image of each single product after processing through a camera device; extracting standard processing images corresponding to the single products, which are prestored in a system database;
taking the image processed by the single product as a first processed image, and taking a standard processed image corresponding to the single product as a second processed image;
dividing the first processing image and the second processing image into a plurality of areas according to the same dividing rule;
comparing pixel points of the same position areas of the first processing image and the second processing image one by one, and recording a difference area where the difference exists between the first processing image and the second processing image;
counting the number of difference areas with differences to obtain the total number of the difference areas, and taking the total number of the difference areas as the processing quality coefficient of the single product.
5. The industrial internet of things-based production process full-flow fault detection method of claim 4, wherein determining abnormal intelligent manufacturing equipment within a predetermined production time interval comprises:
extracting a first running state coefficient of abnormal intelligent manufacturing equipment;
comparing the first running state coefficient with the second running state coefficient, and if the first running state coefficient is greater than or equal to the second running state coefficient, judging that the corresponding intelligent manufacturing equipment is normal intelligent manufacturing equipment;
If the first running state coefficient is smaller than the second running state coefficient, the corresponding intelligent manufacturing equipment is judged to be abnormal intelligent manufacturing equipment.
6. The industrial internet of things-based production process full-flow fault detection method of claim 5, wherein the anomaly characterization data comprises an anomaly vibration spectrogram and an anomaly temperature spectrogram;
acquiring anomaly characterization data for an anomaly intelligent manufacturing device, comprising:
a1: acquiring an engine rotating speed R of the abnormal intelligent manufacturing equipment and acquiring vibration signal data of the abnormal intelligent manufacturing equipment at the engine rotating speed R; constructing a vibration time domain diagram by taking time in vibration signal data as a horizontal axis and taking amplitude in the vibration signal data as a vertical axis;
a2: dividing the vibration time domain graph in equal parts according to T vibration periods to obtain an actual vibration waveform set, wherein the actual vibration waveform set comprises H actual vibration waveforms, and T is a positive integer greater than zero;
a3: extracting an h actual vibration waveform in the actual vibration waveform set, wherein h is a positive integer greater than zero, and the initial value of h is 1;
a4: acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard vibration waveform associated with the corresponding rotating speed interval, calculating the similarity of an actual vibration waveform and the standard vibration waveform, and jumping to the step a5 if the similarity of the actual vibration waveform and the standard vibration waveform is larger than or equal to a preset vibration similarity threshold value; if the similarity between the actual vibration waveform and the standard vibration waveform is smaller than a preset vibration similarity threshold, marking the actual vibration waveform as an abnormal vibration waveform, and jumping to the step a5;
a5: let h=h+1 and jump back to step a3;
a6: repeating the steps a3 to a5 until h=H, ending the cycle, and obtaining a plurality of abnormal vibration waveforms;
a7: and extracting the similarity corresponding to each abnormal vibration waveform, and carrying out Fourier transformation on the abnormal vibration waveform with the minimum similarity to obtain an abnormal vibration spectrogram.
7. The method for detecting a full-flow fault in a production process based on the industrial internet of things according to claim 6, wherein the acquiring the anomaly characterization data of the anomaly intelligent manufacturing device further comprises:
b1: acquiring an engine rotating speed R of abnormal intelligent manufacturing equipment and acquiring temperature signal data of the abnormal intelligent manufacturing equipment at the engine rotating speed R; constructing a temperature time domain diagram by taking time in the temperature signal data as a horizontal axis and taking a temperature value in the temperature signal data as a vertical axis;
b2: dividing the temperature time domain graph in equal parts according to W temperature periods to obtain an actual temperature waveform set, wherein the actual temperature waveform set comprises Q actual temperature waveforms, and W is a positive integer greater than zero;
b3: extracting the q-th actual temperature waveform in the actual temperature waveform set, wherein q is a positive integer greater than zero, and the initial value of q is 1;
b4: b5, acquiring a corresponding rotating speed interval of the engine rotating speed R, extracting a standard temperature waveform associated with the corresponding rotating speed interval, calculating the similarity between an actual temperature waveform and the standard temperature waveform, and jumping to the step b5 if the similarity between the actual temperature waveform and the standard temperature waveform is greater than or equal to a preset temperature similarity threshold; if the similarity between the actual temperature waveform and the standard temperature waveform is smaller than the preset temperature similarity threshold, marking the actual temperature waveform as an abnormal temperature waveform, and jumping to the step b5;
b5: let q=q+1 and jump back to step b3;
b6: repeating the steps b 3-b 5 until q=q, ending the cycle to obtain a plurality of abnormal temperature waveforms;
b7: and extracting the similarity corresponding to each abnormal temperature waveform, and carrying out Fourier transformation on the abnormal temperature waveform with the minimum similarity to obtain an abnormal temperature spectrogram.
8. The method for detecting a fault in a whole production process based on the industrial internet of things according to claim 7, wherein determining fault attribute data of an abnormal intelligent manufacturing apparatus comprises:
acquiring an abnormal vibration spectrogram and an abnormal temperature spectrogram of abnormal intelligent manufacturing equipment;
and inputting the abnormal vibration spectrogram and the abnormal temperature spectrogram into an attribute data identification model to determine fault attribute data of the abnormal intelligent manufacturing equipment.
9. The industrial internet of things-based production process full-flow fault detection method of claim 8, wherein the attribute data identification model generation logic is: acquiring second historical sample data which is pre-stored in a system database and is used for training an attribute data identification model, wherein the second historical sample data comprises an abnormal vibration spectrogram, an abnormal temperature spectrogram, a fault component and a fault component zone bit; dividing second historical sample data for training an attribute data identification model into an attribute training set and an attribute testing set, constructing a regression network model, taking an abnormal vibration spectrogram and an abnormal temperature spectrogram in the attribute training set as inputs of the regression network model, taking fault components and fault component areas in the attribute training set as outputs of the regression network model, and training the regression network model to obtain an initial regression network model; and performing model test on the initial regression network model by using the attribute test set, and screening the corresponding initial regression network model with the accuracy greater than or equal to the preset test as an attribute data identification model.
10. The method for detecting a fault in a whole production process based on the industrial internet of things according to claim 9, wherein the determining a cause of the fault in the abnormal intelligent manufacturing apparatus comprises:
c1: extracting a normal voltage fluctuation interval according to a preset relation between the fault component and the normal voltage fluctuation interval; maximum normal voltage of the normal voltage fluctuation intervalAnd minimum normal voltage->；
c2: comparing the measured voltage set with the normal voltage fluctuation interval to obtain the voltage greater than the maximum normal voltage in the measured voltage setIs less than the minimum normal voltage in the set of measured voltages>Is a measured voltage of (2);
c3: will be greater than the maximum normal voltageAs a first measured voltage, and taking a measured voltage less than a minimum normal voltage as a second measured voltage;
c4: respectively counting the number of the first measured voltage and the second measured voltage to obtain the total number of the first measured voltage and the total number of the second measured voltage;
c5: comparing the total number of the first actually measured voltage with the total number of the second actually measured voltage, if the total number of the first actually measured voltage is larger than or equal to the total number of the second actually measured voltage, acquiring the average value of the first actually measured voltage, and jumping to the step c6; if the total number of the first measured voltages is smaller than the total number of the second measured voltages, obtaining the average value of the second measured voltages, and jumping to the step c7;
c6: taking the average value of the first measured voltage as a first average value, comparing the first average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the first average value falls; taking the corresponding fault reason of the corresponding standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment;
c7: taking the average value of the second measured voltage as a second average value, comparing the second average value with standard fault voltage fluctuation intervals associated with a plurality of fault reasons, and obtaining a corresponding standard fault voltage fluctuation interval in which the second average value falls; and taking the corresponding fault reason corresponding to the standard fault voltage fluctuation interval as the fault reason of the abnormal intelligent manufacturing equipment.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the industrial internet of things based production process full flow fault detection method of any one of claims 1 to 10 when executing the computer program.
12. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed, implements the industrial internet of things based production process full flow fault detection method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311559137.6A CN117270514B (en) | 2023-11-22 | 2023-11-22 | Production process whole-flow fault detection method based on industrial Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311559137.6A CN117270514B (en) | 2023-11-22 | 2023-11-22 | Production process whole-flow fault detection method based on industrial Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117270514A CN117270514A (en) | 2023-12-22 |
| CN117270514B true CN117270514B (en) | 2024-01-26 |
Family
ID=89218179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311559137.6A Active CN117270514B (en) | 2023-11-22 | 2023-11-22 | Production process whole-flow fault detection method based on industrial Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117270514B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117707050B (en) * | 2023-12-25 | 2024-05-07 | 上海滨捷机电有限公司 | Cloud computing-based numerical control machine tool real-time monitoring and data analysis system and method |
| CN117725541B (en) * | 2024-02-07 | 2024-04-16 | 上海强华实业股份有限公司 | Intelligent monitoring and fault diagnosis system for running state of annealing furnace |
| CN118139258B (en) * | 2024-05-06 | 2024-07-12 | 深圳市洛丁光电有限公司 | Self-adaptive disaster-tolerant intelligent single lamp control method and system |
| CN118672240B (en) * | 2024-08-23 | 2024-11-19 | 山东北骏重工有限公司 | Fault-tolerant control system for fault diagnosis of driving motor of new energy mining dump truck |
| CN119004136A (en) * | 2024-09-09 | 2024-11-22 | 苏州数琨创享信息技术有限公司 | Digital intelligent equipment supervision method and system based on data analysis algorithm |
| CN119200535A (en) * | 2024-09-20 | 2024-12-27 | 南京博裕物联科技有限公司 | Equipment data management method and system based on industrial Internet of Things |
| CN118937970A (en) * | 2024-10-09 | 2024-11-12 | 山东海纳智能装备科技股份有限公司 | A mine circuit fault self-diagnosis method and system |
| CN119147964A (en) * | 2024-11-15 | 2024-12-17 | 山东海纳智能装备科技股份有限公司 | Method and system for testing data-enhanced permanent magnet synchronous motor |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112345872A (en) * | 2020-12-04 | 2021-02-09 | 中国南方电网有限责任公司超高压输电公司昆明局 | Converter station secondary circuit abnormity identification and early warning method based on deep confidence network |
| CN114859845A (en) * | 2022-06-09 | 2022-08-05 | 中用科技有限公司 | Intelligent industrial data management system based on internet-of-things controller |
| CN114912895A (en) * | 2022-05-12 | 2022-08-16 | 卡奥斯工业智能研究院(青岛)有限公司 | Production control method and system |
| CN115146074A (en) * | 2022-07-08 | 2022-10-04 | 北京航空航天大学杭州创新研究院 | Fault diagnosis map construction method and related device |
| CN115689341A (en) * | 2022-10-20 | 2023-02-03 | 浙江链捷数字科技有限公司 | Garment quality management method and system based on flexible production chain |
| US20230315062A1 (en) * | 2022-07-15 | 2023-10-05 | Chengdu Qinchuan Iot Technology Co., Ltd. | Industrial internet of things, mthods and mediums for early warning of descending function fault of equipment |
-
2023
- 2023-11-22 CN CN202311559137.6A patent/CN117270514B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112345872A (en) * | 2020-12-04 | 2021-02-09 | 中国南方电网有限责任公司超高压输电公司昆明局 | Converter station secondary circuit abnormity identification and early warning method based on deep confidence network |
| CN114912895A (en) * | 2022-05-12 | 2022-08-16 | 卡奥斯工业智能研究院(青岛)有限公司 | Production control method and system |
| CN114859845A (en) * | 2022-06-09 | 2022-08-05 | 中用科技有限公司 | Intelligent industrial data management system based on internet-of-things controller |
| CN115146074A (en) * | 2022-07-08 | 2022-10-04 | 北京航空航天大学杭州创新研究院 | Fault diagnosis map construction method and related device |
| US20230315062A1 (en) * | 2022-07-15 | 2023-10-05 | Chengdu Qinchuan Iot Technology Co., Ltd. | Industrial internet of things, mthods and mediums for early warning of descending function fault of equipment |
| CN115689341A (en) * | 2022-10-20 | 2023-02-03 | 浙江链捷数字科技有限公司 | Garment quality management method and system based on flexible production chain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117270514A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| US20210241544A1 (en) | Platform for analyzing health of heavy electric machine and analysis method using the same | |
| CN116593811B (en) | Integrated frequency converter running state monitoring system and monitoring method | |
| CN112393931B (en) | Detection method, detection device, electronic equipment and computer readable medium | |
| CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
| CN111122191A (en) | Equipment health alarm threshold setting method based on EWMA control | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN117630800A (en) | Fault diagnosis method and system for automatic calibrating device of electric energy meter | |
| EP4174601A1 (en) | System, apparatus and method for monitoring condition of an asset in technical installation | |
| CN117707050B (en) | Cloud computing-based numerical control machine tool real-time monitoring and data analysis system and method | |
| CN118275034B (en) | Intelligent anti-interference pressure transmitter | |
| CN117574302A (en) | Ocean fishing boat power system abnormality monitoring method and monitoring system | |
| Waters et al. | Vibration anomaly detection using deep autoencoders for smart factory | |
| Chhabria et al. | Predictive Maintenance using Machine Learning on Industrial Water Pumps | |
| CN118706326B (en) | Intelligent diagnosis method and system for pressure transmitter | |
| Hussain et al. | Robust Electric Motor Fault Classification with Extra Trees Classifier on Comprehensive Dataset | |
| CN116928039B (en) | Offshore wind turbine vibration over-limit fault identification method, device, equipment and medium | |
| TWI854128B (en) | Failure detection apparatus and failure detection method | |
| CN119669792A (en) | Adaptive working condition processing method for electrical measuring instrument and mechanical instrument | |
| Hajkova et al. | Application of Modern Approaches to Solving Diagnostic Tasks in Industry | |
| CN119270184A (en) | A system and method for evaluating insulation performance of an insulated voltage transformer | |
| Gerdes et al. | Vibration Resonance Spectrometry (VRS) for the Advanced Streaming Detection of Rotor Unbalance. Machines 2023, 11, 639 | |
| CN119714761A (en) | A method for detecting defects in motor magnetic steel sheets based on vibration analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |