CN108107360B - Motor fault identification method and system - Google Patents

Abstract

The invention relates to a motor fault identification method and a system, wherein the motor fault identification method comprises the following steps: carrying out signal acquisition monitoring on a running motor to obtain a signal monitoring parameter of the motor, and processing the signal monitoring parameter to obtain a performance tracking parameter of the motor; processing the signal monitoring parameters and the performance tracking parameters based on a fault knowledge base according to preset fault identification rules to obtain fault probabilities when the motor fails; sorting the fault probabilities to obtain a fault identification result of the motor; the invention provides a fault identification mechanism which can be continuously expanded, a fault knowledge management method is formed by combining cases, standards and experiences, and fault identification reasoning is carried out by utilizing the knowledge; based on motor fault knowledge management and a fault identification mechanism, the method has strong practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

Description

Motor fault identification method and system

technical field

The invention relates to the technical field of motor fault processing, in particular to a motor fault identification method and system.

Background technique

There are close electromagnetic and mechanical connections between the main functional components of the motor (including stator, rotor, iron core, air gap, bearing assembly), and their states affect each other. The damage of one part is very likely to cause the abnormality of other parts, and the abnormality of one part may be caused by many reasons. The fault identification of the motor follows the fault characteristics of the motor. The occurrence of all faults will cause the occurrence of corresponding fault symptoms. The occurrence of symptoms can be judged by the changes of relevant parameters. The task of fault identification can include judging whether the symptom parameters are abnormal, and how to determine which faults are caused when the parameters are abnormal. .

In order to determine the relationship between fault occurrence and specific symptom parameters, symptom extraction and fault analysis techniques for specific faults (such as broken bars, insulation breakdown, inter-turn short circuit, bearing damage, etc.) have been continuously proposed. With the enrichment of monitoring methods, diagnostic methods With the improvement of , more and more motor faults can be expressed more accurately, such as the traditional logical diagnosis method of motor faults, in order to describe the many-to-many relationship between motor faults and symptoms, the Boolean matrix is used to express this relationship. , using matrix logic operations for diagnosis.

During the implementation process, the inventor found that there are at least the following problems in the traditional technology: in the traditional motor fault logic diagnosis method, there are hundreds of symptoms and dozens of failure modes, which are easy to form a huge sparse matrix; that is, the traditional technology can only focus on a single fault Pattern recognition and diagnosis, or multi-sensor fusion diagnosis, have poor scalability and practicability in practical applications.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a motor fault identification method and system for the problems of poor scalability and practicability of traditional fault identification methods.

In order to achieve the above purpose, on the one hand, an embodiment of the present invention provides a method for identifying a motor fault, including the following steps:

Perform signal acquisition and monitoring on the running motor, obtain the signal monitoring parameters of the motor, process the signal monitoring parameters, and obtain the performance tracking parameters of the motor;

According to the preset fault identification rules, the signal monitoring parameters and performance tracking parameters are processed based on the fault knowledge base to obtain the probability of each fault when the motor fails; the fault knowledge base includes fault association rules and fault maintenance case data; the preset fault identification rules include faults Judgment rules and fault reasoning rules; fault judgment rules include matching the signal monitoring parameters and performance tracking parameters with each symptom record in the preset symptom criterion database one by one to obtain the probability of occurrence of each fault judgment when the motor fails; fault reasoning rules Including the probability of occurrence of each fault determined according to the fault association rules, the obtained fault correlation reasoning results, and the case reasoning results obtained by comparing the signal monitoring parameters and performance tracking parameters with the fault maintenance case data respectively, weighted and averaged, Get the probability of each failure;

The probability of each fault is sorted by size, and the fault identification result of the motor is obtained.

In one embodiment, the signal monitoring parameters include electrical parameters of the motor, temperature parameters of various components, working parameters and state parameters; the performance tracking parameters include motor power, motor efficiency, minimum torque, maximum torque, stall torque, Stall current and temperature rise;

Before the step of processing the signal monitoring parameters and the performance tracking parameters based on the fault knowledge base according to the preset fault identification rules, and obtaining the probability of each fault when the motor fails, the steps further include:

Build the fault basic information database of the motor; the fault basic information database includes the fault attribute information;

Build a fault knowledge base according to fault attribute information.

In one of the embodiments, the fault association rule is a causal relationship chain;

The steps to build a fault base information base include:

According to the fault characteristics of the motor, the fault objects are divided step by step, and the virtual structure with the fault characteristics of the motor is introduced to obtain the structure model of the fault object division of the motor;

According to the fault object division structure model, the failure mode analysis is carried out, and the potential faults of the motor are determined; and the fault attribute information is generated according to the potential faults;

The steps to build a fault knowledge base include:

According to the fault tree analysis, the causal relationship chain of each fault in the fault attribute information is obtained;

According to the fault object division structure model, signal monitoring parameters and performance tracking parameters, the fault maintenance case data is generated.

In one of the embodiments, the fault correlation reasoning result includes a complete fault mechanism result and a concurrent fault result;

According to the fault inference rules, the steps of processing the probability of fault determination include:

According to the fault association rule, when it is confirmed that each fault corresponding to the probability of occurrence of each fault is on the same fault-related link, the complete fault mechanism result is obtained through probability calculation;

or

When it is confirmed that each fault corresponding to the occurrence probability of each fault judgment is on a different fault-related link, the concurrent fault result is obtained through probability calculation.

In one of the embodiments, before the step of processing the signal monitoring parameters and performance tracking parameters based on the fault knowledge base according to the preset fault identification rule, and obtaining the probability of each fault when the motor fails, the steps further include:

When it is detected that the signal monitoring parameters and performance tracking parameters exceed the corresponding alarm values, an abnormal alarm is issued;

After the step of obtaining the fault identification result of the motor, it also includes the following steps:

According to the fault identification results, determine the maintenance plan;

According to the fault identification result and maintenance plan, update the fault maintenance case data.

On the one hand, an embodiment of the present invention also provides a motor fault identification system, including:

The state monitoring unit is used to collect and monitor the signal of the motor in operation, and obtain the signal monitoring parameters of the motor;

The performance tracking unit is used to process the signal monitoring parameters and obtain the performance tracking parameters of the motor;

The fault identification unit is used to process signal monitoring parameters and performance tracking parameters based on the fault knowledge base according to the preset fault identification rules, and obtain each fault probability when the motor fails; the fault knowledge base includes fault association rules and fault maintenance case data; It is assumed that the fault identification rules include fault judgment rules and fault inference rules; the fault judgment rules include matching the signal monitoring parameters and performance tracking parameters with each symptom record in the preset symptom criterion database one by one, so as to obtain each fault judgment when the motor fails. Occurrence probability; fault inference rules include the probability of occurrence of each fault determined by processing each fault according to the fault correlation rule, the obtained fault correlation inference results, and the case inference results obtained by comparing the signal monitoring parameters and performance tracking parameters with the fault maintenance case data respectively. , perform weighted averaging to obtain the probability of each failure;

The sorting unit is used for sorting the probability of each fault to obtain the fault identification result of the motor. In one of the embodiments,

In one embodiment, the signal monitoring parameters include electrical parameters of the motor, temperature parameters of various components, working parameters and state parameters; the performance tracking parameters include motor power, motor efficiency, minimum torque, maximum torque, stall torque, Stall current and temperature rise;

Also includes:

The fault basic information management unit is used to construct the fault basic information database of the motor; the fault basic information database includes the fault attribute information;

The fault knowledge base unit is used to construct a fault knowledge base according to the fault attribute information.

In one of the embodiments, the fault association rule is a causal relationship chain;

The fault basic information management unit includes:

The fault object division module is used to divide the fault objects step by step according to the fault characteristics of the motor, and introduce a virtual structure with the fault characteristics of the motor to obtain the fault object division structure model of the motor;

The failure mode analysis module is used to analyze the failure mode according to the fault object division structure model, and determine the potential faults of the motor;

The fault attribute information management module is used to generate fault attribute information according to each potential fault;

Fault knowledge base units include:

The fault association rule module is used to obtain the causal relationship chain of each fault in the fault attribute information according to the fault tree analysis;

The fault maintenance case library module is used to divide the structural model, signal monitoring parameters and performance tracking parameters according to the fault object, and generate fault maintenance case data.

On the one hand, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the above embodiments of the motor fault identification method are implemented. step.

On the other hand, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of each embodiment of the above-mentioned motor fault identification method.

A technical scheme in the above-mentioned technical scheme has the following advantages and beneficial effects:

Collect and monitor the signal of the motor in operation, obtain the signal monitoring parameters of the motor, and then track the performance of the motor. Through the preset fault identification rules, the relevant parameters are processed based on the complete fault knowledge base, and then the fault management and performance are realized from the bottom layer. Tracking, criterion management and symptom management, and at the same time adopt a fault reasoning mechanism coordinated with fault identification, based on fault maintenance case data, to obtain fault identification conclusions that can assist maintenance personnel in diagnosis and maintenance. The embodiment of the present invention provides a fault identification mechanism that can be continuously expanded, forms a fault knowledge management method by combining cases, standards and experience, and uses these knowledge to perform fault identification and reasoning; the embodiment of the present invention is based on the motor fault knowledge management and fault identification mechanism. , has strong practicability and scalability, and proposes a comprehensive solution for online fault diagnosis and offline fault location of motor operation, as well as rapid repair of system faults.

Description of drawings

1 is a schematic flowchart of Embodiment 1 of a motor fault identification method according to the present invention;

2 is a schematic diagram of the structure of each link in the embodiment of the motor fault identification method of the present invention;

3 is a schematic diagram of the division of fault objects in the embodiment of the motor fault identification method of the present invention;

4 is a schematic diagram of failure mode analysis in an embodiment of a motor fault identification method according to the present invention;

5 is a schematic diagram of a fault association rule in an embodiment of the motor fault identification method of the present invention;

6 is a schematic flowchart of a fault identification process in an embodiment of a motor fault identification method according to the present invention;

FIG. 7 is a schematic structural diagram of Embodiment 1 of the motor fault identification system of the present invention.

Detailed ways

In order to facilitate understanding of the present invention, the present invention will be described more fully hereinafter with reference to the related drawings. Preferred embodiments of the invention are shown in the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Explanation and definitions of technical terms involved in the embodiments of the motor fault identification method and system of the present invention:

Motor: A device that converts electrical energy into mechanical energy. Generally, the energized coil (that is, the stator winding) is used to generate a rotating magnetic field and act on the rotor to form a magneto-electric rotational torque. Motors are divided into DC motors and AC motors according to different power sources. Most of the motors in the power system are AC motors, which can be synchronous motors or motors (the stator magnetic field speed of the motor and the rotor rotation speed do not maintain a synchronous speed). The motor is mainly composed of a stator and a rotor, and the direction of the energized wire in the magnetic field is related to the direction of the current and the direction of the magnetic field line (magnetic field direction). The working principle of the motor is that the force of the magnetic field on the current causes the motor to rotate.

Fault identification: Judging system status, identifying system abnormalities, and locating fault causes through all available current and historical operating information of the equipment.

Knowledge management: Fault knowledge is all formatted information related to product design, standards and experience related to fault identification.

Reasoning mechanism: The logic and process of inferring fault identification results from numerous fault knowledge.

Embodiment 1 of the motor fault identification method of the present invention:

In order to solve the problems of poor scalability and practicability of the traditional fault identification method, the present invention provides a first embodiment of a motor fault identification method; FIG. 1 is a schematic flowchart of the first embodiment of the motor fault identification method of the present invention; FIG. 1 shown, may include the following steps:

Step S110 : collecting and monitoring signals of the motor in operation, obtaining signal monitoring parameters of the motor, processing the signal monitoring parameters, and obtaining performance tracking parameters of the motor;

Specifically, the state monitoring in the embodiment of the present invention is the source basis for fault identification, and may include two parts: a signal acquisition scheme and a state tracking scheme; the motor signal acquisition scheme can collect the main parameters related to the motor fault, and in the application site Because of cost considerations, users often do not require vibration and temperature sensors to be installed inside the motor, and industrial sites do not necessarily have complete monitoring methods.

The effectiveness and comprehensiveness of the fault identification in the embodiment of the present invention largely depends on the comprehensiveness of the condition monitoring data. In the performance tracking scheme, the changes in the key performance of the motor are considered. The motor performance parameters are an important indicator of whether the motor is abnormal. Different faults will lead to different performance degradation phenomena. The above-mentioned performance tracking parameters can be calculated from the relevant parameters obtained in the signal acquisition scheme.

It should be noted that, since the signal acquisition scheme is limited by the monitoring means at the motor application site, if the relevant parameters of the calculation process are not monitored, the performance cannot be tracked.

Step S120: According to the preset fault identification rules, the signal monitoring parameters and performance tracking parameters are processed based on the fault knowledge base to obtain each fault probability when the motor fails; the fault knowledge base includes fault association rules and fault maintenance case data; preset fault identification The rules include fault judgment rules and fault inference rules; the fault judgment rules include matching the signal monitoring parameters and performance tracking parameters with each symptom record in the preset symptom criterion database one by one to obtain the probability of occurrence of each fault judgment when the motor fails; The fault inference rules include the probability of occurrence of each fault determined according to the fault association rules, the obtained fault correlation inference results, and the case inference results obtained by comparing the signal monitoring parameters and performance tracking parameters with the fault maintenance case data, and weighting them. Take the average to get the probability of each failure;

Specifically, the fault knowledge base is the fault knowledge for completing the fault identification in the embodiment of the present invention, and may include fault association rules and fault maintenance case data; wherein, the fault association rules may refer to the causal relationship chain of fault occurrence, and a top-down method is adopted. Analytical method to find the cause of the failure layer by layer from the failure phenomenon. For example, motor overheating may be caused by stator overheating, rotor overheating, bearing overheating, abnormal heat dissipation, etc., and stator overheating may be caused by stator and rotor rubbing. Further, based on the above-mentioned causal relationship diagram, the frequency of occurrence of all failure causes causing the failure can be analyzed one by one.

The fault maintenance case data in the embodiment of the present invention may include: fault phenomenon, working condition description, abnormal parameters, fault diagnosis, replacement of spare parts, and maintenance measures; and the fault identification mechanism (rule) solves the problem by monitoring parameters, combined with fault knowledge base, how to Locating faults and giving maintenance solutions. Match the signal monitoring parameters and performance tracking parameters with the preset symptom criterion database one by one. The preset symptom criterion database includes faults and the symptoms corresponding to the faults. Each fault and its symptom records can be further confirmed by domain experts in the later stage.

The preset symptom criterion database is to assume that a fault occurs, and to judge the changes of monitoring parameters that may be caused; while the fault judgment is inverse, and judges which faults have occurred according to the changes of the monitored parameters. Because one fault may correspond to multiple parameter changes, and one Parameter changes may also be caused by multiple faults, so the fault determination can only be calculated roughly by the number of symptom matching.

Therefore, in the embodiment of the present invention, according to the fault determination rule, each measured parameter is matched with the above symptom criterion database one by one. In each record, one fault corresponds to multiple symptoms. bigger. The ratio of the number of matching symptoms to the total number of symptoms is used as the probability of occurrence of the fault; for example, m symptoms are currently monitored; there are n symptoms in the X-th record in the preset symptom criterion database; if k out of n are matched , then k/n is the probability of occurrence of the fault. At the same time, with the accumulation of monitoring data and fault data, the preset symptom criterion database is expandable, and symptom data can be updated manually or obtained through analysis and correction from historical data.

In addition, according to the fault determination rules, the faults of the motor can be obtained, but all the fault causes and complete fault mechanisms cannot be located. Therefore, the embodiment of the present invention proposes a fault inference rule, and substitutes the fault and probability information obtained by the above fault determination into the fault association rule, and obtains the fault correlation inference result through the calculation of the fault probability.

At the same time, the fault reasoning rule also includes comparing the real-time monitoring parameters with the fault maintenance case data to obtain the case reasoning result; and then weighted and averaging the fault association rule reasoning result and the case reasoning result to obtain each fault probability.

Step S130: Ranking the probability of each failure to obtain a fault identification result of the motor;

Specifically, the faults obtained by the above-mentioned fault reasoning mechanism can be sorted by probability, and the pre-set number, such as 10, can be selected, and the relevant fields include complete information that is helpful for maintenance personnel to diagnose and repair; further form fault identification results. .

To sum up, the first embodiment of the motor fault identification method of the present invention monitors and tracks the motor; according to the normal range of the monitoring parameters or performance parameters, when the measured parameters exceed the range, according to the abnormal parameter characterization, it is preliminarily determined what fault or which fault occurred. Several faults; based on the preliminary judgment of symptom faults, inferences based on previously established rule associations and fault record cases, etc., to obtain which internal hidden faults or external faults caused the motor to fail. According to the calculated probabilities obtained by reasoning, the causes of the faults are arranged in descending order, and the fault identification results are obtained, so as to formulate the maintenance plan.

The embodiment of the present invention provides a fault identification mechanism that can be continuously expanded, forms a fault knowledge management method by combining cases, standards and experience, and uses these knowledge to perform fault identification and reasoning; the embodiment of the present invention is based on the motor fault knowledge management and fault identification mechanism. , has strong practicability and scalability, and proposes a comprehensive solution for online fault diagnosis and offline fault location of motor operation, as well as rapid repair of system faults.

In a specific embodiment, the signal monitoring parameters include electrical parameters of the motor, temperature parameters of various components, working parameters and state parameters; performance tracking parameters include motor power, motor efficiency, minimum torque, maximum torque, stall torque , stall current and temperature rise;

Before the step of processing the signal monitoring parameters and the performance tracking parameters based on the fault knowledge base according to the preset fault identification rules, and obtaining the probability of each fault when the motor fails, the steps further include:

Build the fault basic information database of the motor; the fault basic information database includes the fault attribute information;

Build a fault knowledge base according to fault attribute information.

Specifically, the signal acquisition scheme of the motor in the embodiment of the present invention can collect four types of main parameters related to the motor fault: three-phase voltage, three-phase current, frequency and other electrical parameters; the three-phase effective parameters can be monitored in real time through voltage and current clamps respectively For some motors with high safety and reliability requirements, the three-phase voltage and current waveforms can be monitored regularly through a wave recorder; the temperature parameters of the motor casing, windings, bearings, etc.; the casing temperature can be passed through the casing. The temperature of the bearing can be obtained by attaching a temperature sensor; the temperature of the bearing can be obtained by installing a temperature sensor on the bearing cover close to the bearing; the temperature of the winding can be monitored by pre-embedding a thermocouple (such as PT100) in each phase winding. Working parameters such as motor speed, torque, continuous running time, etc.; can be monitored in real time by installing a torque sensor at the motor output. Status parameters such as motor noise, housing/bearing cap vibration, etc. Real-time acquisition is performed by installing vibration sensors and noise testers in the housing, bearing housing, or bearing cover. The performance tracking for fault identification can include tracking the following parameters: motor power, motor efficiency, motor torque, minimum torque, maximum torque, stall torque, stall current, and temperature rise.

FIG. 2 is a schematic diagram of the structure of each link in the embodiment of the motor fault identification method of the present invention; as shown in FIG. 2 , each embodiment of the motor fault identification method of the present invention may include basic information management of motor faults, state monitoring scheme, fault knowledge base construction, Fault identification mechanism and fault identification conclusions and other links. First, through basic work, according to design, standards, and experience, the fault knowledge of the motor is obtained; then, the state monitoring conditions of the working environment of the motor, as well as all the parameters that can be monitored and the performance can be tracked; then the internal fault of the motor is obtained. According to the association rules between them, collect fault maintenance records, and conduct regularization; and monitor and track the motor; at the same time, according to the normal range of monitoring parameters or performance parameters, when the measured parameters exceed the range, an abnormal alarm will be issued; At the same time, it can preliminarily determine what fault or several faults have occurred based on the abnormal parameter representation; further, based on the preliminarily determined symptom fault, inference can be made based on the previously established rule association and fault record cases, etc., to obtain which internal faults Hidden or external faults cause the motor to fail. Finally, according to the calculated probability obtained by reasoning, the fault causes can be arranged from large to small, and the fault identification result can be obtained, so as to formulate a maintenance plan.

In a specific embodiment, the fault association rule is a causal relationship chain;

The steps to build a fault base information base include:

According to the fault characteristics of the motor, the fault objects are divided step by step, and the virtual structure with the fault characteristics of the motor is introduced to obtain the structure model of the fault object division of the motor;

According to the fault object division structure model, the failure mode analysis is carried out, and the potential faults of the motor are determined; and the fault attribute information is generated according to the potential faults;

The steps to build a fault knowledge base include:

According to the fault tree analysis, the causal relationship chain of each fault in the fault attribute information is obtained;

According to the fault object division structure model, signal monitoring parameters and performance tracking parameters, the fault maintenance case data is generated.

Specifically, FIG. 3 is a schematic diagram of the division of fault objects in the embodiment of the motor fault identification method of the present invention; as shown in FIG. 3 , the fault object is the main body of the failure mode. Windings and front and rear bearings. According to the target depth of fault identification, it is decided whether to further decompose the main body of the fault. For example, the heating of the bearing can be divided into the heating of different components such as the inner ring, the outer ring and the ball.

The method for classifying fault objects in the embodiment of the present invention will consider the occurrence subjects of all potential fault modes of the motor. Preferably, on the basis of a traditional bill of materials (Bill of Material, BOM), fault objects can be classified step by step according to the fault behavior characteristics of the motor division, mainly including:

1. Remove objects that will not or hardly fail;

2. If different objects of the same model have different faults in different positions, they need to be listed and labeled separately (the same model in the BOM often only gives the number);

3. Introduce a virtual structure with motor fault characteristics, including heat dissipation system (composed of fans, hoods and their key connections, any fault may cause heat dissipation problems in the motor system), bearing lubrication system (including lubricating oil, bearing caps, seals, etc.) parts, etc., the lubrication problem will cause abnormal noise, vibration, temperature rise and other problems of the motor), power supply system (power supply, junction box, terminal block, etc., whose three-phase voltage and current characteristics have a huge impact on the motor), air gap (the gap between the stator and the rotor) The gap between them, too large, too small or uneven will affect the performance of the motor), etc.; the fault of the virtual structure is a comprehensive expression of a certain type of functional abnormality. During the fault identification, the extraction of the functional abnormality can greatly promote the management of subsequent fault associations. and breakdown of the fault body.

FIG. 4 is a schematic diagram of the failure mode analysis in the embodiment of the motor fault identification method of the present invention; as shown in FIG. 4 , the failure mode analysis method is based on the fault object division structure (as shown in the above figure), and the potential fault objects are identified one by one from the top to the bottom. The failure mode of the motor, such as the motor, has failure modes such as failure to start, overheating, abnormal noise, oil rejection, smoke, vibration, etc. All potential faults inside and outside the motor are determined by "fault object + fault mode".

Further, the fault association rule refers to the causal relationship chain of the fault occurrence. Preferably, the top-down analysis method of fault tree analysis (FTA) can be referred to, and the fault cause can be found layer by layer from the fault phenomenon. Figure 5 shows the fault of the motor in the present invention. A schematic diagram of the fault association rule in the embodiment of the identification method; as shown in FIG. 5 . Motor overheating may be caused by stator overheating, rotor overheating, bearing overheating, abnormal heat dissipation, etc., and stator overheating may be caused by stator and rotor rubbing. 5. The relationship is represented by arrows.

For the above causal relationship diagram, analyze the frequency of all fault causes that cause the fault one by one. For example, for motor overheating, there are four types of failure causes: stator overheating, bearing overheating, rotor overheating, and abnormal heat dissipation. According to fault statistics or expert experience , in 100 times of motor overheating, the frequencies caused by 4 reasons are 50 times, 35 times, 10 times and 5 times respectively. Then, the corresponding relationship arrows can be attached with relevant frequency experience information.

The fault maintenance case data in the embodiment of the present invention may include:

Failure phenomenon: description of failure performance;

Description of working conditions: the environment, working conditions and load conditions before and after the failure;

Abnormal parameters: signal acquisition and state tracking parameter values at the moment of failure and the previous period;

Diagnosing faults: Diagnosing faults with problems, there can be multiple;

Replacement Spare Parts: Repair and replace parts;

Maintenance measures: the specific process of maintenance.

In a specific embodiment, the fault correlation reasoning result includes a complete fault mechanism result and a concurrent fault result;

According to the fault inference rules, the steps of processing the probability of fault determination include:

According to the fault association rule, when it is confirmed that each fault corresponding to the probability of occurrence of each fault is on the same fault-related link, the complete fault mechanism result is obtained through probability calculation;

According to the fault association rule, when it is confirmed that the faults corresponding to the occurrence probability of each fault are on different fault-related links, the concurrent fault result is obtained through probability calculation.

Specifically, the fault reasoning mechanism of each embodiment of the motor fault identification method of the present invention substitutes the above-mentioned fault and probability information obtained according to the fault determination rule into the fault association rule. If it is determined that the probability of "motor-overheating" is 0.6, then In the figure, the probability of "stator-overheating" is 0.6*0.5=0.3, the probability of rotor overheating is 0.6*0.35=0.21, and so on; multiple probabilities on multiple faulty links can be accumulated, such as the possibility of stator-rotor friction. Caused by the overheating of the stator or the overheating of the rotor, the failure probability of the stator and rotor rubbing against each other as shown in Figure 5 is: 0.3*0.1+0.21*0.6=0.156.

If the multiple faults obtained by the above fault judgment are on a fault-related link, then this fault link is likely to be the complete mechanism of the fault; for example, the above fault judgment rules obtain "motor-overheating" and "rotor-motionless" "Balance" has a certain probability of occurrence, then it is likely that the rotor is unbalanced, causing uneven air, causing the stator and rotor to rub, causing the temperature of the stator and the rotor to rise, causing the motor to heat up. The failure probability on this link is obtained by the same failure probability calculation method, that is, the complete failure mechanism result.

If there are many faults obtained by the above fault determination rules, and not all of them are on one faulty link, more complex concurrent faults may occur, and the probability of occurrence of each fault is obtained according to the same fault probability calculation method, that is, the concurrent fault result;

The fault reasoning rule in the embodiment of the present invention further includes comparing the real-time monitoring parameters with the abnormal parameters in the fault maintenance case data. If all the abnormal parameters match, the fully matched cases are regarded as "similar cases", and the fault maintenance The diagnosed failure in the data is assigned a failure probability, and the failure probability is the ratio of the number of abnormal parameters in this case to the total number of current abnormal parameters. The probability of multiple failures in multiple cases is weighted and averaged;

Further, in the fault inference rule in the embodiment of the present invention, the inference result of the fault association rule and the case inference result are weighted and averaged to obtain each fault probability.

In a specific embodiment, before the step of processing the signal monitoring parameters and performance tracking parameters based on the fault knowledge base according to the preset fault identification rules, and obtaining the probability of each fault when the motor fails, the steps further include:

When it is detected that the signal monitoring parameters and performance tracking parameters exceed the corresponding alarm values, an abnormal alarm is issued;

After the step of obtaining the fault identification result of the motor, it also includes the following steps:

According to the fault identification results, determine the maintenance plan;

According to the fault identification result and maintenance plan, update the fault maintenance case data.

Specifically, the abnormal alarm mechanism matches items one by one according to the abnormal alarm table, and if any item exceeds the normal range, an abnormal alarm is issued. At the same time, the fault maintenance case data can be updated according to the diagnosis and maintenance measures.

In order to further elaborate the technical solution of the present invention, the motor fault identification process using the motor fault identification method of the present invention is taken as an example for illustration. FIG. 6 is a schematic flowchart of the fault identification process in the embodiment of the motor fault identification method of the present invention, as shown in FIG. 6 As shown, the motor fault identification method of the present invention includes the steps of basic information management of motor faults, state monitoring scheme, fault knowledge base construction, fault identification mechanism and fault identification conclusion. (It should be noted that the small graphs in Figure 6 are only used to represent a certain process in the identification process, and are not used to represent specific numerical values, data or content)

(1) Fault basic information management

Fault basic information management provides basic information for building a knowledge base for fault identification, including fault object division, fault mode analysis, and fault information regulation.

(1.1) Division of fault objects (see the corresponding content above)

(1.2) Failure mode analysis (see the corresponding content above)

(1.3) Fault attribute information management

For all potential faults of the above-mentioned motors, the fault attribute information can be determined one by one according to expert experience (manual input). The management of motor fault attribute information includes:

Occurrence level: According to the fault maintenance records of similar motors, the fault occurrence frequency is classified and defined, for example, according to the proportion of the number of faults per hundred times, or according to the number of fault occurrences per year;

Fault type: divided into related faults and non-related faults, related faults refer to indirect faults, that is, faults caused by other faults and can be eliminated by repairing the cause of the fault; non-related faults refer to directly caused by itself and need to be repaired/replaced the current fault object faults that can be repaired. The division of fault types is meaningful for the confirmation of maintenance tasks after fault identification. Only non-related faults need maintenance.

Diagnosis method: non-related faults must, that is, how to diagnose whether the fault occurs, including operation inspection, that is, it can be checked during normal operation; shutdown inspection, that is, it needs to perform specific operations after shutdown; dismantling inspection, that is, after shutdown It needs to be disassembled for inspection.

Diagnosis equipment: equipment required for diagnosis, commonly used motor diagnosis equipment includes visual inspection, ammeter, tachometer, temperature recorder, power analyzer, laser alignment instrument, vibration meter, resistance meter, withstand voltage meter, dynamic balancer , professional maintenance, etc. It needs to be determined according to the equipment conditions of the motor application site. If there is a vibration meter on site, some vibration problems can be diagnosed through the "operation inspection" method. Even send it to a professional for repair.

Diagnosis method: describe the specific operation of how to use the diagnosis equipment to diagnose the fault;

Maintenance measures: After the fault is diagnosed, how to carry out maintenance and repair operations can eliminate the fault.

The details are shown in Table 1 below.

Table 1 - Motor fault attribute information management

(2) Condition monitoring

Condition monitoring is the source basis of fault identification, including signal acquisition scheme and status tracking scheme.

(2.1) Signal acquisition scheme

The signal acquisition scheme of the motor of the present invention can collect the main parameters related to the motor fault, as shown in Table 2 below:

(2.2) Status tracking scheme;

On the basis of signal acquisition, it is necessary to further calculate and obtain various state parameters of the motor, as shown in Table 3 below.

(3) Construction of fault knowledge base

The fault knowledge base is the fault knowledge for completing the fault identification, including fault association rules, performance tracking records, abnormal symptom criteria and fault maintenance cases;

Table 2 - Motor Signal Monitoring Parameters

serial number Monitoring parameters parameter code Monitoring location 1 Three-phase voltage U — 2 Three-phase current I — 3 frequency f0 / 4 Motor temperature T0 case 5 Winding temperature Tp winding end 6 bearing vibration Vb Front/rear bearing housing/bearing cap/frame 7 Bearing temperature Tb Front/rear bearing housing/bearing cap/frame 8 Rotating speed Rpm Between output shaft and load 9 torque Tor Between output shaft and load 10 vibration V0 shell 11 Continuous working time/downtime Tr/Ts / 12 noise No / 13 … … …

Table 3 - Motor Performance Tracking Parameters

(3.1) Fault association rule base

The fault association rule refers to the causal relationship chain of fault occurrence. Refer to the top-down analysis method of fault tree analysis (FTA) to find the fault cause layer by layer from the fault phenomenon, as shown in the following figure. Motor overheating may be caused by stator overheating, rotor overheating, bearing overheating, abnormal heat dissipation, etc., and stator overheating may be caused by stator-rotor rubbing, etc. In this way, a causal relationship diagram of all faults in the basic fault information is established.

(3.2) Performance tracking library

The performance tracking record library will monitor and save the (2.1) state acquisition parameters and (2.2) performance tracking parameters in the actual running process of the motor in real time;

(3.3) Fault maintenance case library

The fault maintenance case data includes: fault phenomenon: description of fault performance; working condition description: environment, working conditions and load conditions before and after the fault occurs; abnormal parameters: signal acquisition and state tracking parameter values at the time of fault and a period of time before, refer to ( 3.2) Performance tracking records; Diagnosis of faults: Diagnose the faults with problems, which can be multiple, and refer to (1.3) fault information; Replace spare parts: Repair and replace parts, refer to (1.1) fault objects; Maintenance measures: The specific process of maintenance.

Among them, it should be noted that the fault maintenance database records the past fault maintenance data. Specifically, if the fault identification of a current motor is to be carried out, the present invention can firstly store its past historical fault maintenance records (including replaced parts), and now one of the identification schemes for fault identification is based on The current real-time parameters are "matched" with the "implementation parameters" in the case library, and the matched records indicate what caused similar abnormalities in the past, and what maintenance was done. This information can then be provided to maintenance personnel, and at the same time After the fault diagnosis and maintenance are carried out based on these identification conclusions, the replaced spare parts, maintenance process and other information are recorded back to the case database, so that there is one more record in the case database.

(4) Fault identification mechanism

The fault identification mechanism solves the problem of how to perform abnormal alarms, locate faults and provide maintenance plans by monitoring parameters and combining with the fault knowledge base.

(4.1) Abnormal alarm mechanism

The abnormal alarm mechanism matches items one by one according to the abnormal alarm table, and if any item exceeds the normal range, an abnormal alarm is performed. The abnormal alarm table (as shown in Table 4 below) includes: GB/T 1032-2012 and other relevant standard requirements, such as requirements for temperature rise, vibration, and noise level; specific design requirements of the motor, such as efficiency, torque, etc. Upper and lower tolerance limits for performance parameters; expert experience, standards and design requirements may be relatively broad, and some alarm values can be adjusted based on experience.

Table 4 - Abnormal alarm table

(4.2) Fault determination mechanism

Anomaly alarms only tell you if there might be a fault, but not where the fault is.

The fault determination mechanism is to match the (2.1) acquisition parameters and (2.2) performance parameters with the symptom criterion database one by one while the abnormal alarm occurs. The symptom criterion database is composed of the fault and the symptom corresponding to the failure. (1.3), the indications are described in (2.1) and (2.2). Each fault and its symptom records can be reviewed and confirmed by domain experts. As shown in the following table - table 5:

The symptom criterion database assumes that a fault occurs, and judges the possible changes in monitoring parameters; the fault judgment is reversed, and judges which faults have occurred according to the changes of the monitored parameters. Because one fault may correspond to multiple parameter changes, and one parameter changes It may also be caused by multiple faults, so the fault judgment can only be used to calculate the approximate fault occurrence probability through the matching number of symptoms.

Therefore, each measured parameter is matched with the above symptom criterion database one by one. In each record, one fault corresponds to multiple symptoms. The more the matched symptoms, the greater the probability of the fault. Take the ratio of the number of matching symptoms to the total number of symptoms as the probability of occurrence of the fault. Specifically, m signs are currently monitored; there are n signs in the X record of the sign library; if k out of n are matched, then k/n is the probability.

(4.3) Fault reasoning mechanism

The above fault determination can determine which faults have occurred in the motor, but cannot locate all the fault causes and the complete fault mechanism. Therefore, the fault reasoning mechanism described above substitutes the fault and probability information obtained from the above (4.2) fault judgment into the fault association rule (3.1), if it is determined that the probability of "motor-overheating" is 0.6, then in the figure, "stator" The probability of "overheating" is 0.6*0.5=0.3, the probability of rotor overheating is 0.6*0.35=0.21, and so on; multiple probabilities on multiple fault links can be accumulated, such as stator-rotor phase friction may be caused by stator overheating or rotor overheating Caused by overheating, the failure probability of stator and rotor rubbing as shown in the example figure is: 0.3*0.1+0.21*0.6=0.156.

If multiple faults obtained by the above (4.2) fault judgment are on a fault-related link, then this fault link is likely to be the complete mechanism of the fault; as in the above (4.2) judgment, the “motor-overheating” and “motor-overheating” are obtained. Rotor-dynamic unbalance" has a certain probability of occurrence, then it is likely that the rotor is unbalanced, causing uneven air, causing the stator and rotor to rub, causing the temperature of the stator and the rotor to rise, causing the motor to heat up. The failure probability on this link is obtained by the same failure probability calculation method.

If there are many faults obtained in the above (4.2), and not all of them are on one faulty link, more complex concurrent faults may occur, and the probability of occurrence of each fault is obtained according to the same fault probability calculation method;

The fault reasoning mechanism also includes comparing the real-time monitoring parameters with the abnormal parameters of the (3.4) case database. If all the abnormal parameters match, the fully matched cases will be regarded as "similar cases", and the case database (that is, the fault maintenance case data) The diagnosed fault in is assigned a fault probability, and the fault probability is the ratio of the number of abnormal parameters in this case to the total number of current abnormal parameters. The probability of multiple failures in multiple cases is weighted and averaged;

Based on the fault inference mechanism (ie, fault inference rules), the inference results of the fault association rules and the case inference results are weighted and averaged to obtain the probability of each fault.

(5) Maintenance plan

In the maintenance schedule table, the faults obtained by the above-mentioned fault reasoning mechanism are sorted by probability, and the top 10 are selected, and the relevant fields include complete information related to the diagnosis and maintenance of the maintenance personnel;

Failures: Reference 1.3, including failure objects (1.1) and failure modes (1.2)

Probability of Occurrence: Reference (4.3)

Fault Type: Application (1.3)

Diagnostic Equipment: References (1.3)

Diagnosis method: reference (1.3)

Maintenance Actions: References (1.3)

Table 5 - Symptom Criterion Database

According to the reasoning in 4.2, the fault identification result is formed, as shown in the following table-table 6.

Table 6 - Fault Identification Results

serial number fault object failure mode probability of occurrence source Diagnosis equipment Diagnosis method Maintenance measures References (1.1) Citation (1.2) decimal Rules/Cases Citation (1.3) Citation (1.3) Citation (1.3)

Finally, update the fault case (3.3) according to the diagnosis and maintenance measures.

In each embodiment of the motor fault identification method of the present invention, fault knowledge is the basic basis for fault identification. The present invention provides a good and scalable management method, which is the basic condition for effective fault identification for different motors. The present invention proposes The fault knowledge management method is scalable: 1. The fault basic management module can establish different fault basic databases according to the basic structure of different motors, different fault performance, and different on-site testing methods; 2. Condition monitoring module, Different sensors can be arranged and installed according to the conditions of different motor application sites, and the system can also be set separately in the setting of signal acquisition and performance tracking items; 3. In the fault knowledge base module, each motor has different power levels and different applications. The thresholds are different for different occasions and need to be determined according to the object and its application site, and can be updated.

In the embodiment of the present invention, signals are collected and monitored for the motor in operation, and the signal monitoring parameters of the motor are obtained, and then the performance of the motor is tracked, and the relevant parameters are processed based on the complete fault knowledge base by presetting fault identification rules, and then from the bottom layer. It realizes fault management, performance tracking, criterion management and symptom management. At the same time, a fault reasoning mechanism coordinated with fault identification is adopted. Based on fault maintenance case data, fault identification conclusions that can assist maintenance personnel in diagnosis and maintenance are obtained. The embodiment of the present invention provides a fault identification mechanism that can be continuously expanded, forms a fault knowledge management method by combining cases, standards and experience, and uses these knowledge to perform fault identification and reasoning; the embodiment of the present invention is based on the motor fault knowledge management and fault identification mechanism. , has strong practicability and scalability, and proposes a comprehensive solution for online fault diagnosis and offline fault location of motor operation, as well as rapid repair of system faults.

Embodiment 1 of the motor fault identification system of the present invention:

In order to solve the problem of poor scalability and practicability of the traditional fault identification method, the present invention provides a first embodiment of a motor fault identification system; FIG. 7 is a schematic structural diagram of the first embodiment of the motor fault identification system of the present invention. As shown in Figure 7, it can include

The state monitoring unit 710 is used to collect and monitor the signal of the motor in operation, and obtain the signal monitoring parameters of the motor;

A performance tracking unit 720, configured to process signal monitoring parameters to obtain performance tracking parameters of the motor;

The fault identification unit 730 is configured to process signal monitoring parameters and performance tracking parameters based on the fault knowledge base according to preset fault identification rules, and obtain each fault probability when the motor fails; the fault knowledge base includes fault association rules and fault maintenance case data; The preset fault identification rules include fault judgment rules and fault inference rules; the fault judgment rules include matching the signal monitoring parameters and performance tracking parameters with each symptom record in the preset symptom criterion database one by one to obtain the faults when the motor fails. Determine the probability of occurrence; the fault inference rules include the probability of occurrence of each fault determined according to the fault association rule, the obtained fault correlation inference result, and the case inference obtained by comparing the signal monitoring parameters and performance tracking parameters with the fault maintenance case data respectively. As a result, weighted average is performed to obtain each failure probability;

The sorting unit 740 is configured to sort each fault probability by size to obtain a fault identification result of the motor. In one of the embodiments,

In a specific embodiment, the signal monitoring parameters include electrical parameters of the motor, temperature parameters of various components, working parameters and state parameters; performance tracking parameters include motor power, motor efficiency, minimum torque, maximum torque, stall torque , stall current and temperature rise;

Also includes:

A fault basic information management unit 750, configured to construct a fault basic information database of the motor; the fault basic information database includes fault attribute information;

The fault knowledge base unit 760 is configured to construct a fault knowledge base according to the fault attribute information.

In a specific embodiment, the fault association rule is a causal relationship chain;

The fault basic information management unit 750 includes:

The fault object division module 752 is used to divide the fault objects step by step according to the fault characteristics of the motor, and introduce a virtual structure with the fault characteristics of the motor to obtain the fault object division structure model of the motor;

The failure mode analysis module 754 is configured to analyze the failure mode according to the fault object division structure model, and determine each potential failure of the motor;

A fault attribute information management module 756, configured to generate fault attribute information according to each potential fault;

The fault knowledge base unit 760 includes:

The fault association rule module 762 is configured to obtain the causal relationship chain of each fault in the fault attribute information according to the fault tree analysis;

The fault maintenance case library module 764 is configured to divide the structural model, signal monitoring parameters and performance tracking parameters according to the fault object, and generate fault maintenance case data.

Specifically, it should be noted that the unit modules in each embodiment of the above-mentioned motor fault identification system can correspondingly implement each process step in the above-mentioned embodiment of the above-mentioned motor fault identification method, which will not be repeated here.

In one embodiment, a computer device is also provided, the computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements each of the above-mentioned programs when executing the program. Any one of the motor fault identification methods in the embodiments.

In the computer equipment, when the processor executes the program, by implementing any one of the motor fault identification methods in the above-mentioned embodiments, a fault knowledge management method can be formed in combination with cases, standards and experience, and the fault identification and reasoning can be carried out by using these knowledge. ; Based on the knowledge management and fault identification mechanism of motor faults, the embodiment of the present invention has strong practicability and scalability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation, as well as rapid repair of system faults.

In addition, those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable In the storage medium, as in the embodiment of the present invention, the program may be stored in the storage medium of the computer system, and executed by at least one processor in the computer system, so as to realize the embodiments including the above-mentioned methods for identifying motor faults process.

In one embodiment, a storage medium is also provided, on which a computer program is stored, wherein when the program is executed by a processor, any one of the motor fault identification methods in the foregoing embodiments is implemented. The storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM) or the like.

The computer storage medium, and the computer program stored therein, can form a fault knowledge management method in combination with cases, standards and experience by implementing the processes including the embodiments of the above-mentioned motor fault identification methods, and use these knowledge to perform fault identification and reasoning; Based on the motor fault knowledge management and fault identification mechanism, the embodiments of the present invention have strong practicability and scalability, and provide a comprehensive solution for online fault diagnosis and offline fault location of motor operation, as well as quick repair of system faults.

The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above-described embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be regarded as the scope described in this specification.

The above-mentioned embodiments only represent several embodiments of the present invention, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can also be made, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims (10)

1. a motor fault identification method, is characterized in that, comprises the following steps: Perform signal acquisition and monitoring on the motor in operation, obtain the signal monitoring parameters of the motor, process the signal monitoring parameters, and obtain the performance tracking parameters of the motor; wherein, the performance tracking parameters include motor power, motor efficiency, minimum Torque, maximum torque, stall torque, stall current and temperature rise; According to preset fault identification rules, the signal monitoring parameters and the performance tracking parameters are processed based on the fault knowledge base to obtain each fault probability when the motor fails; the fault knowledge base includes fault association rules and fault maintenance case data ; The preset fault identification rules include fault judgment rules and fault inference rules; the fault judgment rules include the signal monitoring parameters, the performance tracking parameters, and each symptom record in the preset symptom criterion database. matching to obtain the probability of occurrence of each fault judgment when the motor fails; the fault inference rule includes processing the probability of occurrence of each fault judgment according to the fault association rule, the obtained fault correlation inference result, and monitoring the signal. The parameters and the performance tracking parameters are respectively compared with the fault maintenance case data, and the obtained case reasoning results are weighted and averaged to obtain each of the fault probabilities; The magnitude of each of the failure probabilities is sorted to obtain the fault identification result of the motor. 2 . The motor fault identification method according to claim 1 , wherein the signal monitoring parameters include electrical parameters of the motor, temperature parameters of each component, working parameters and state parameters; 2 . Before the step of processing the signal monitoring parameters and the performance tracking parameters based on the fault knowledge base according to the preset fault identification rules, and obtaining the probability of each fault when the motor fails, the steps further include: constructing a fault basic information database of the motor; the fault basic information database includes fault attribute information; The fault knowledge base is constructed according to the fault attribute information. 3. The motor fault identification method according to claim 2, wherein the fault association rule is a causal relationship chain; The steps of constructing the fault basic information database include: The fault objects are divided step by step according to the fault characteristics of the motor, and a virtual structure with the fault characteristics of the motor is introduced to obtain the fault object division structure model of the motor; Perform fault mode analysis according to the fault object division structure model to determine each potential fault of the motor; and generate the fault attribute information according to each of the potential faults; The steps of constructing the fault knowledge base include: According to fault tree analysis, the causal relationship chain of each fault in the fault attribute information is obtained; The fault maintenance case data is generated according to the fault object division structure model, the signal monitoring parameters and the performance tracking parameters. 4. The motor fault identification method according to any one of claims 1 to 3, wherein the fault correlation reasoning result includes a complete fault mechanism result and a concurrent fault result; According to the fault inference rule, the step of processing the probability of occurrence of the fault judgment includes: According to the fault association rule, when it is confirmed that the faults corresponding to the occurrence probability of each fault determination are on the same fault-related link, the complete fault mechanism result is obtained through probability calculation; or When it is confirmed that the faults corresponding to the occurrence probabilities of the fault determinations are on different fault-related links, the concurrent fault results are obtained through probability calculation. 5 . The motor fault identification method according to claim 4 , wherein, according to a preset fault identification rule, the signal monitoring parameters and the performance tracking parameters are processed based on a fault knowledge base to obtain when the motor fails. 5 . The steps of each failure probability also include steps: When it is detected that the signal monitoring parameter and the performance tracking parameter exceed the corresponding alarm value, an abnormal alarm is issued; After the step of obtaining the fault identification result of the motor, the step further includes: According to the fault identification result, determine the maintenance plan; The fault maintenance case data is updated according to the fault identification result and the maintenance plan. 6. A motor fault identification system, characterized in that, comprising: a state monitoring unit, used to collect and monitor the signal of the motor in operation, and obtain the signal monitoring parameters of the motor; A performance tracking unit, configured to process the signal monitoring parameters to obtain performance tracking parameters of the motor; wherein the performance tracking parameters include motor power, motor efficiency, minimum torque, maximum torque, stall torque, stall torque transfer current and temperature rise; A fault identification unit, configured to process the signal monitoring parameters and the performance tracking parameters based on a fault knowledge base according to preset fault identification rules, and obtain each fault probability when the motor fails; the fault knowledge base includes fault associations rules and fault maintenance case data; the preset fault identification rules include fault determination rules and fault inference rules; the fault determination rules include the signal monitoring parameters and the performance tracking parameters, respectively, with the preset symptom criteria database Matching each symptom record one by one to obtain the probability of occurrence of each fault judgment when the motor fails; the fault inference rule includes processing the probability of occurrence of each of the fault judgments according to the fault association rule, and the obtained fault correlation inference result, Perform a weighted average with the case reasoning results obtained by comparing the signal monitoring parameters and the performance tracking parameters with the fault maintenance case data respectively to obtain each of the fault probabilities; The sorting unit is configured to sort each of the fault probabilities by size to obtain the fault identification result of the motor. 7. The motor fault identification system according to claim 6, wherein the signal monitoring parameters include electrical parameters of the motor, temperature parameters of each component, working parameters and state parameters; Also includes: a fault basic information management unit, configured to construct a fault basic information database of the motor; the fault basic information database includes fault attribute information; A fault knowledge base unit, configured to construct the fault knowledge base according to the fault attribute information. 8. The motor fault identification system according to claim 7, wherein the fault association rule is a causal relationship chain; The fault basic information management unit includes: The fault object division module is used to divide the fault objects step by step according to the fault characteristics of the motor, and introduce a virtual structure with the fault characteristics of the motor to obtain the fault object division structure model of the motor; a failure mode analysis module, configured to perform failure mode analysis according to the fault object division structure model, and determine each potential fault of the motor; a fault attribute information management module, configured to generate the fault attribute information according to each of the potential faults; The fault knowledge base unit includes: A fault association rule module, configured to obtain the causal relationship chain of each fault in the fault attribute information according to fault tree analysis; A fault maintenance case library module, configured to divide the structure model, the signal monitoring parameter and the performance tracking parameter according to the fault object, and generate the fault maintenance case data. 9. A computer device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements any one of claims 1 to 5 when the processor executes the program the steps of the method. 10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images