CN108107360B

CN108107360B - Motor fault identification method and system

Info

Publication number: CN108107360B
Application number: CN201711269578.7A
Authority: CN
Inventors: 王远航; 丁小健; 孟苓辉; 杨剑锋; 刘文威; 李小兵; 黄创绵
Original assignee: China Electronic Product Reliability and Environmental Testing Research Institute
Current assignee: China Electronic Product Reliability and Environmental Testing Research Institute
Priority date: 2017-12-05
Filing date: 2017-12-05
Publication date: 2020-07-17
Anticipated expiration: 2037-12-05
Also published as: CN108107360A

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

There is a close electromagnetic and mechanical relationship between the various major functional components of the machine (including the stator, rotor, core, air gap, bearing assembly), and their states affect each other. Damage to a component is highly likely to cause abnormality in other components, and abnormality in a component may be caused by a plurality of causes. The fault detection of the electric machine follows the fault behavior of the electric machine. The occurrence of all faults can cause the occurrence of corresponding fault symptoms, the symptom occurrence can be judged through the change of related parameters, and the task of fault identification can comprise the steps of judging whether the symptom parameters are abnormal or not and determining which faults are caused after the parameters are abnormal.

In order to determine the relationship between the occurrence of a fault and a specific symptom parameter, a symptom extraction and fault analysis technology surrounding a specific fault (such as a broken bar, insulation breakdown, turn-to-turn short circuit, bearing damage and the like) is continuously provided, along with the richness of monitoring means and the improvement of a diagnosis method, more and more motor faults can be more accurately expressed, for example, a traditional logic diagnosis method of the motor faults is used, in order to depict the many-to-many relationship between the motor faults and the symptoms, the incidence relationship expression is realized through a Boolean matrix, and the diagnosis is carried out by utilizing the logic operation of the matrix.

In the implementation process, the inventor finds that at least the following problems exist in the conventional technology: hundreds of symptoms and dozens of fault modes in the traditional logic diagnosis method for motor faults are easy to form a huge sparse matrix; namely, the traditional technology can only identify and diagnose the symptom of a single fault mode or perform fusion diagnosis of multiple sensors, and has poor expandability and practicability in practical application.

Disclosure of Invention

Therefore, it is necessary to provide a method and a system for identifying a motor fault, aiming at the problem that the conventional fault identification method is poor in expandability and practicability.

In order to achieve the above object, in one aspect, an embodiment of the present invention provides a motor fault identification method, including 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; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault inference rule; the fault judgment rule comprises the steps of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises the steps of processing each fault judgment occurrence probability according to the fault correlation rule to obtain a fault correlation reasoning result, comparing the signal monitoring parameter and the performance tracking parameter with fault maintenance case data respectively to obtain a case reasoning result, and weighting and averaging to obtain each fault probability;

and sequencing the fault probabilities to obtain a fault identification result of the motor.

In one embodiment, the signal monitoring parameters comprise electrical parameters of the motor, temperature parameters of each component, working parameters and state parameters; the performance tracking parameters comprise motor power, motor efficiency, minimum torque, maximum torque, locked rotor current and temperature rise;

the method comprises the following steps of processing signal monitoring parameters and performance tracking parameters based on a fault knowledge base according to preset fault identification rules to obtain the fault probability of the motor when the motor fails:

constructing a fault basic information base of the motor; the fault basic information base comprises fault attribute information;

and constructing a fault knowledge base according to the fault attribute information.

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

the step of constructing the fault basic information base comprises the following steps:

dividing fault objects step by step according to the motor fault characteristics, and introducing a virtual structure with the motor fault characteristics to obtain a fault object division structure model of the motor;

carrying out fault mode analysis according to the fault object division structure model to determine each potential fault of the motor; generating fault attribute information according to each potential fault;

the step of constructing the fault knowledge base comprises the following steps:

according to the fault tree analysis, a cause-effect relation chain of each fault in the fault attribute information is obtained;

and generating fault maintenance case data according to the fault object partition structure model, the signal monitoring parameters and the performance tracking parameters.

In one embodiment, the fault correlation reasoning result comprises a complete fault mechanism result and a concurrent fault result;

according to the fault reasoning rule, the step of processing the fault judgment occurrence probability comprises the following steps:

according to the fault association rule, when confirming that each fault corresponding to each fault judgment occurrence probability is on the same fault association link, obtaining a complete fault mechanism result through probability calculation;

or

And when the faults corresponding to the fault judgment occurrence probability are confirmed to be on different fault associated links, obtaining a concurrent fault result through probability calculation.

In one embodiment, the method further comprises the following steps 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 rule to obtain the fault probability of the motor when the motor fails:

when the monitored signal monitoring parameter and the performance tracking parameter exceed the corresponding alarm values, an abnormal alarm is sent out;

the method also comprises the following steps after the step of obtaining the fault identification result of the motor:

determining a maintenance plan according to the fault identification result;

and updating the fault maintenance case data according to the fault identification result and the maintenance plan.

On one hand, the embodiment of the invention also provides a motor fault identification system, which comprises:

the state monitoring unit is used for carrying out signal acquisition monitoring on the running motor to obtain signal monitoring parameters of the motor;

the performance tracking unit is used for processing the signal monitoring parameters to obtain performance tracking parameters of the motor;

the fault identification unit is used for processing the signal monitoring parameters and the performance tracking parameters based on the fault knowledge base according to preset fault identification rules to obtain the fault probability of the motor when the motor fails; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault inference rule; the fault judgment rule comprises the steps of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises the steps of processing each fault judgment occurrence probability according to the fault correlation rule to obtain a fault correlation reasoning result, comparing the signal monitoring parameter and the performance tracking parameter with fault maintenance case data respectively to obtain a case reasoning result, and weighting and averaging to obtain each fault probability;

and the sequencing unit is used for sequencing the fault probabilities to obtain the fault identification result of the motor. In one of the embodiments, the first and second electrodes are,

further comprising:

the fault basic information management unit is used for constructing a fault basic information base of the motor; the fault basic information base comprises fault attribute information;

and the fault knowledge base unit is used for constructing a fault knowledge base according to the fault attribute information.

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

the fault basic information management unit includes:

the fault object dividing module is used for dividing fault objects step by step according to the motor fault characteristics and introducing a virtual structure with the motor fault characteristics to obtain a fault object dividing structure model of the motor;

the fault mode analysis module is used for carrying out fault mode analysis according to the fault object division structure model and determining each potential fault of the motor;

the fault attribute information management module is used for generating fault attribute information according to each potential fault;

the failure knowledge base unit includes:

the fault association rule module is used for obtaining a cause-and-effect relationship chain of each fault in the fault attribute information according to the fault tree analysis;

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

In one aspect, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the embodiments of the motor fault identification method.

In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the embodiments of the motor fault identification method described above.

One of the above technical solutions has the following advantages and beneficial effects:

the method comprises the steps of collecting and monitoring signals of a motor in operation to obtain signal monitoring parameters of the motor, further performing performance tracking on the motor, processing related parameters based on a complete fault knowledge base through a preset fault identification rule, further realizing fault management, performance tracking, criterion management and symptom management from a bottom layer, and meanwhile obtaining a fault identification conclusion capable of assisting maintenance personnel in diagnosing and overhauling based on fault maintenance case data by adopting a fault reasoning mechanism coordinated with fault identification. The embodiment of 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; the embodiment of the invention is based on a motor fault knowledge management and fault identification mechanism, has stronger practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

Drawings

Fig. 1 is a schematic flow chart of a motor fault identification method according to embodiment 1 of the present invention;

FIG. 2 is a schematic diagram of an architecture of each link in the embodiment of the motor fault identification method of the present invention;

FIG. 3 is a schematic diagram illustrating the division of a fault object in the embodiment of the motor fault identification method of the present invention;

FIG. 4 is a schematic diagram illustrating a failure mode analysis in an embodiment of the motor failure identification method of the present invention;

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

FIG. 6 is a schematic flow chart illustrating a fault identification process according to an embodiment of the motor fault identification method of the present invention;

fig. 7 is a schematic structural diagram of a motor fault identification system in embodiment 1 of the present invention.

Detailed Description

To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

Unless defined otherwise, 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 terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

The invention relates to a motor fault identification method and a system, which are characterized in that professional terms related in each embodiment are explained and defined as follows:

a motor: is a device for converting electric energy into mechanical energy. Generally, a rotating magnetic field is generated by an electrified coil (i.e. a stator winding) and acts on a rotor to form a magnetoelectric dynamic rotating torque. The motors are divided into direct current motors and alternating current motors according to different power supplies, most of the motors in the power system are alternating current motors and can be synchronous motors or motors (the rotating speed of a stator magnetic field of the motor is different from the rotating speed of a rotor and keeps synchronous speed). The motor mainly comprises a stator and a rotor, and the direction of the forced movement of the electrified conducting wire in a magnetic field is related to the current direction and the direction of a magnetic induction line (magnetic field direction). The working principle of the motor is that the magnetic field exerts force on current to rotate the motor.

And (3) fault identification: and judging the state of the system, identifying the system abnormality and positioning the fault reason according to all available current and historical running information of the equipment.

Knowledge management: the failure knowledge is all the product design, standard and experience related formatted information related to failure identification.

The reasoning mechanism is as follows: the logic and flow of the fault identification result are deduced from a plurality of fault knowledge.

The embodiment 1 of the motor fault identification method of the invention:

in order to solve the problem that the traditional fault identification method is poor in expandability and practicability, the invention provides an embodiment 1 of a motor fault identification method; fig. 1 is a schematic flow chart of a motor fault identification method according to embodiment 1 of the present invention; as shown in fig. 1, the following steps may be included:

step S110: 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;

specifically, the state monitoring in the embodiment of the present invention is a source basis for fault identification, and may include two parts, namely a signal acquisition scheme and a state tracking scheme; the signal acquisition scheme of the motor can acquire main parameters related to motor faults, and users often do not require to install sensors such as vibration and temperature in the motor in consideration of cost in the motor in an application field, and an industrial field does not necessarily have a perfect monitoring means.

The effectiveness and comprehensiveness of fault identification in the embodiment of the invention greatly depend on the comprehensiveness of state monitoring data. In the performance tracking scheme, the variation condition of key performance of the motor is considered, the performance parameter of the motor is an important representation of whether the motor is abnormal, and different performance degradation phenomena can be caused when different faults occur. The performance tracking parameters can be calculated by the related parameters obtained in the signal acquisition scheme.

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

Step S120: 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; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault inference rule; the fault judgment rule comprises the steps of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises the steps of processing each fault judgment occurrence probability according to the fault correlation rule to obtain a fault correlation reasoning result, comparing the signal monitoring parameter and the performance tracking parameter with fault maintenance case data respectively to obtain a case reasoning result, and weighting and averaging to obtain each fault probability;

specifically, the fault knowledge base is fault knowledge for completing fault identification in the embodiment of the invention, and may include fault association rules and fault maintenance case data; the fault association rule can refer to a cause-and-effect relationship chain of fault occurrence, and fault causes of the fault are found layer by layer from fault phenomena by adopting a top-down analysis method. For example, overheating of the motor may be caused by overheating of the stator, overheating of the rotor, overheating of the bearing, abnormal heat dissipation and the like, overheating of the stator and the like may be caused by friction between the stator and the rotor and the like, and thus, a causal graph of all faults in the fault basic information is built up by recursion. Further, the occurrence frequency of all fault causes causing the fault can be analyzed on a fault-by-fault basis based on the causal graph.

The fault repair case data in the embodiment of the present invention may include: fault phenomenon, working condition description, abnormal parameters, confirmed fault diagnosis, spare part replacement and maintenance measures; and the fault identification mechanism (rule) solves the problem of how to carry out fault location and provide a maintenance scheme by monitoring parameters and combining a fault knowledge base. And matching the signal monitoring parameters and the performance tracking parameters with a preset symptom criterion library one by one, wherein the preset symptom criterion library comprises faults and symptoms corresponding to the faults, and each fault and a symptom record thereof can be further confirmed by a field expert at the later stage.

The preset symptom criterion base is used for judging the change of monitoring parameters possibly caused by the occurrence of faults; and the fault judgment is reverse, which faults are judged according to the monitored parameter change, and because one fault can correspond to a plurality of parameter changes and one parameter change can also be caused by a plurality of faults, the fault judgment can only carry out rough fault occurrence probability calculation through symptom matching number.

Therefore, according to the fault judgment rule, each measured parameter is matched with the symptom criterion base one by one, one fault corresponds to a plurality of symptoms in each record, and the probability of the fault is higher when the number of the matched symptoms is larger. Taking the ratio of the matched symptom number to the total symptom number as the occurrence probability of the fault; for example, m symptoms are currently monitored; n symptoms are recorded in the Xth record in a preset symptom criterion library; if k of n are matched, k/n is the probability of the fault. Meanwhile, with the accumulation of the monitoring data and the fault data, the preset symptom criterion base is extensible, and the symptom data can be manually updated and can also be obtained by analyzing and correcting historical data.

In addition, which faults occur in the motor can be obtained according to the fault judgment rule, but all fault reasons and complete fault mechanisms cannot be located. Therefore, the embodiment of the invention provides a fault reasoning rule, the fault and probability information obtained by the fault judgment is substituted into the fault association rule, and a fault association reasoning result is obtained through fault probability calculation.

Meanwhile, the fault reasoning rule also comprises the step of comparing the real-time monitoring parameters with fault maintenance case data to obtain a case reasoning result; and further carrying out weighting and averaging on the fault association rule reasoning result and the case reasoning result to obtain each fault probability.

Step S130: sorting the fault probabilities to obtain a fault identification result of the motor;

specifically, the faults obtained by the fault reasoning mechanism may be sorted according to the probability, a preset number, for example, 10 faults are taken, and the relevant fields include complete information that is helpful for the maintenance personnel to diagnose and overhaul; and further forming a fault identification result.

In summary, in the embodiment 1 of the motor fault identification method of the present invention, the motor is monitored and tracked; according to the normal range of the monitoring parameters or the performance parameters, when the actual measurement parameters exceed the range, according to the abnormal parameter representation, preliminarily judging what faults or which faults occur; and reasoning is carried out according to the preliminarily determined symptom faults and the previously established rule association, fault recording cases and the like to obtain which internal hidden faults or external faults cause the motor to have faults. And arranging fault reasons from large to small according to the calculated probability obtained by reasoning to obtain a fault identification result, thereby formulating a maintenance plan.

The embodiment of 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; the embodiment of the invention is based on a motor fault knowledge management and fault identification mechanism, has stronger practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

In a specific embodiment, the signal monitoring parameters comprise electrical parameters of the motor, temperature parameters of each component, working parameters and state parameters; the performance tracking parameters comprise motor power, motor efficiency, minimum torque, maximum torque, locked rotor current and temperature rise;

Specifically, the signal acquisition scheme of the motor in the embodiment of the invention can acquire four main parameters related to motor faults: three-phase voltage, three-phase current, frequency and other electrical parameters; three-phase effective values, peak values and the like can be respectively monitored in real time through the voltage and current clamp, and three-phase voltage and current waveforms can be regularly monitored through the wave recorder and the like aiming at motors in certain occasions with high requirements on safety and reliability; temperature parameters of a motor shell, a winding, a bearing and the like; the temperature of the shell can be acquired by attaching a temperature sensor on the shell; the temperature of the bearing can be obtained by installing a temperature sensor on a bearing cover close to the bearing; the winding temperature can be monitored by embedding a thermocouple (such as PT100) in each phase winding. Working parameters such as motor rotating speed, torque, continuous operation time and the like; the torque sensor can be installed at the output end of the motor for real-time monitoring. Motor noise, housing/bearing cap vibration, etc. And a vibration sensor and a noise tester are arranged at the positions of the shell, the bearing seat or the bearing cover and the like for real-time acquisition. While performance tracking for fault identification may include tracking the following parameters: motor power, motor efficiency, motor torque, minimum torque, maximum torque, locked rotor current, and temperature rise.

FIG. 2 is a schematic diagram of an architecture 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 links such as fault basic information management, a state monitoring scheme, fault knowledge base construction, a fault identification mechanism, and a fault identification conclusion of the motor. Firstly, through basic work, according to design, standard and experience, the fault knowledge of the motor is informed; then, state monitoring conditions of a working environment where the motor is located, all parameters capable of being monitored and performance capable of being tracked are determined; obtaining an association rule among internal faults of the motor, collecting fault maintenance records, and conducting normalization; monitoring and tracking the motor; meanwhile, according to the normal range of the monitoring parameters or the performance parameters, when the actually measured parameters exceed the range, abnormal alarm is carried out; when the abnormal alarm is carried out, what fault or faults can be preliminarily judged according to the abnormal parameter representation; furthermore, reasoning can be carried out according to the preliminarily determined symptom faults and according to the previously established rule association, fault recording cases and the like, and the motor faults caused by the internal hidden faults or the external faults are obtained. Finally, fault reasons can be arranged from large to small according to the calculated probability obtained by inference, and a fault identification result is obtained, so that a maintenance plan is made.

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

Specifically, fig. 3 is a schematic diagram illustrating the division of a fault object in the embodiment of the motor fault identification method of the present invention; as shown in fig. 3, the fault object is the occurrence subject of the fault mode, such as heat generation of the motor, and there may be three subjects, a motor housing, a stator winding, and front and rear bearings. According to the target depth of fault identification, whether a fault main body is further decomposed is determined, and for example, the heating of the bearing can be divided into the heating of different parts such as an inner ring, an outer ring and balls.

The method for dividing the fault object in the embodiment of the invention considers occurrence main bodies of all potential fault modes of the motor, preferably, fault object division can be carried out step by step on the basis of a traditional Bill of Material (BOM) according to fault behavior characteristics of the motor, and the method mainly comprises the following steps:

1. removing objects that fail little or no;

2. if different objects with the same model have different fault expressions at different positions, the objects need to be listed and labeled respectively (the number of the objects with the same model is often given in BOM);

3. a virtual structure with motor fault characteristics is introduced, wherein the virtual structure comprises a heat dissipation system (a fan, a fan cover and key connection components of the fan and the fan cover, and any fault can cause the heat dissipation problem of a motor system), a bearing lubrication system (comprising lubricating oil, a bearing cover, a sealing element and the like, wherein the lubrication problem can cause the problems of abnormal sound, vibration, temperature rise and the like of the motor), a power supply system (a power supply, a junction box, a connector and the like, the three-phase voltage and current characteristics of the bearing lubrication system have great influence on the motor), an air gap (a gap between a stator and a rotor, and the motor performance is influenced when; the fault of the virtual structure is a comprehensive expression of some functional abnormalities, and during fault identification, the refinement of the functional abnormalities can greatly promote the management of subsequent fault association and the decomposition of fault subjects.

FIG. 4 is a schematic diagram illustrating a failure mode analysis in an embodiment of the motor failure identification method of the present invention; as shown in fig. 4, the failure mode analysis method determines potential failure modes of the failure objects one by one from top to bottom based on the dividing structure of the failure objects (as shown in the above figure), such as the motor, which has failure modes of being unable to start, overheating, abnormal sound, oil slinging, 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 a cause and effect relationship chain of occurrence of a fault, preferably, a fault cause of the fault can be found layer by layer from a fault phenomenon by referring to a Fault Tree Analysis (FTA) top-down analysis method, and fig. 5 is a schematic diagram of the fault association rule in the embodiment of the motor fault identification method of the present invention; as shown in fig. 5. The overheating of the motor may be caused by the overheating of the stator, the overheating of the rotor, the overheating of the bearing, the abnormal heat dissipation and the like, and the overheating of the stator and the like may be caused by the friction between the stator and the rotor and the like, so that a causal relationship diagram of all faults in the fault basic information is established, as shown in fig. 5, and the association relationship is represented by an arrow.

In the causal relationship diagram, the occurrence frequency of all fault causes causing the fault is analyzed one by one, for example, for the motor overheating, the fault causes include 4 types of stator overheating, bearing overheating, rotor overheating and heat dissipation abnormity, and according to fault statistics or expert experience, the frequency caused by the 4 types of causes is respectively 50 times, 35 times, 10 times and 5 times in 100 times of motor overheating. Then the corresponding association arrow may be accompanied by relevant frequency experience information.

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

the fault phenomenon is as follows: description of the performance of the fault;

and (3) description of working conditions: the environment, working conditions and load conditions before and after the occurrence of the fault;

abnormal parameters: signal acquisition and state tracking parameter values at the time of the fault and at a previous period of time;

and (3) confirming the fault: the number of faults with problems can be confirmed;

replacement of spare parts: repairing the replaced component;

maintenance measures are as follows: the specific process of maintenance.

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

and according to the fault association rule, when confirming that each fault corresponding to each fault judgment occurrence probability is positioned on different fault association links, obtaining a concurrent fault result through probability calculation.

Specifically, the fault inference mechanism in each embodiment of the motor fault identification method of the present invention substitutes the fault and probability information obtained according to the fault determination rule into the fault association rule, and if it is determined that the probability of "motor-overheat" is 0.6, in the figure, the probability of "stator-overheat" is 0.6 × 0.5 — 0.3, the probability of rotor overheat is 0.6 × 0.35 — 0.21, and so on; multiple probabilities on multiple faulty links can be summed, if stator-rotor phase rub can be caused by stator overheating or rotor overheating, then the probability of fault for stator-rotor phase rub is as in fig. 5: 0.3 × 0.1+0.21 × 0.6 ═ 0.156.

If a plurality of faults obtained by the fault judgment are on a fault associated link, the fault link is likely to be a complete mechanism of the fault; if the "motor-overheating" and the "rotor-dynamic imbalance" obtained according to the above-mentioned failure determination rule have a certain occurrence probability, it is likely that the rotor imbalance causes uneven breath, which causes rubbing of the stator and the rotor, which causes temperature rise of the stator and the rotor, which causes heating of the motor. The failure probability on the link is obtained by the same failure probability calculation method, namely a complete failure mechanism result.

If the faults obtained by the fault judgment rule are more and not on one fault link, more complex concurrent faults can occur, and the occurrence probability of each fault, namely the concurrent fault result, is obtained according to the same fault probability calculation method;

the fault reasoning rule in the embodiment of the invention also comprises the steps of comparing the real-time monitoring parameters with the abnormal parameters in the fault maintenance case data, if the abnormal parameters are all matched, taking the fully matched case as a similar case, giving a fault probability to the confirmed fault in the fault maintenance case data, and using the ratio of the number of the abnormal parameters in the case to the total number of the current abnormal parameters for the fault probability. Carrying out weighted averaging on the probabilities of the multiple faults of the multiple cases;

further, the fault reasoning rule in the embodiment of the invention performs weighted averaging on the fault association rule reasoning result and the case reasoning result to obtain each fault probability.

In a specific embodiment, 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 rule to obtain the fault probability of the motor when the motor fails further comprises the following steps:

determining a maintenance plan according to the fault identification result;

Specifically, the abnormal alarm mechanism matches the abnormal alarm table item by item, and an abnormal alarm is performed when any one of the abnormal alarm table exceeds the normal range. Meanwhile, fault maintenance case data can be updated according to the confirmed diagnosis and maintenance measures.

In order to further explain the technical scheme of the invention in detail, a motor fault identification process applying the motor fault identification method of the invention is taken as an example for explanation, fig. 6 is a flow schematic diagram of the fault identification process in the embodiment of the motor fault identification method of the invention, and as shown in fig. 6, the motor fault identification method of the invention comprises links such as fault basic information management, a state monitoring scheme, fault knowledge base construction, a fault identification mechanism and a fault identification conclusion of a motor. (Note that each small graph in FIG. 6 is only used to show a certain process in the identification process, and is not used to show specific values, data or contents.)

(1) Fault-based information management

The fault basic information management provides basic information for constructing a knowledge base required by fault identification, and comprises fault object division, fault mode analysis, fault information normalization and the like.

(1.1) Fault object partitioning (see correspondence above)

(1.2) failure mode analysis (see the corresponding above)

(1.3) Fault Attribute information management

For all potential faults of the motor, fault attribute information can be determined one by one according to expert experience (manual input), and the motor fault attribute information management comprises the following steps:

occurrence level: according to the fault maintenance records of the motors of the same type, fault occurrence frequency is defined in a grading way, for example, dividing according to the proportion of hundred fault occurrence times or annual fault occurrence times;

the type of failure: dividing into related faults and non-related faults, wherein related faults refer to indirect faults, namely faults which are caused by other faults and can be eliminated through the repair of the fault reason; a non-correlated fault refers to a fault that is caused directly by itself and requires repair/replacement of the currently faulty object to be repaired. The division of the fault types has significance for the confirmation of the maintenance tasks after the fault identification, and only the non-related faults need to be maintained.

The diagnosis method comprises the following steps: the non-related fault must be a mode how to determine whether the fault occurs or not, including operation investigation, namely investigation can be carried out during normal operation; the method comprises the following steps of (1) stopping and checking, namely checking only by carrying out specific operation after stopping; and (4) disassembling for investigation, namely, dismantling the machine for investigation after shutdown.

The diagnosis equipment comprises: the equipment required for determining the diagnosis, which is commonly used for determining the diagnosis of the motor, comprises an eye inspection instrument, an ammeter, a tachometer, a temperature recorder, a power analyzer, a laser centering instrument, a vibration meter, a resistance meter, a voltage withstanding instrument, a dynamic balancing instrument, a professional overhaul instrument and the like. The vibration detection method needs to be specifically determined according to the instrument and equipment conditions of the motor application field, if a vibration meter is arranged on the field, certain vibration problems can be confirmed in an operation and inspection mode, and if the vibration meter is not arranged on the field, machine halt inspection and even disassembly inspection can be carried out, and even professional maintenance is carried out.

The confirmation method comprises the following steps: describing the specific operation of how to confirm the fault by using the diagnosis confirming equipment;

maintenance measures are as follows: after the fault is confirmed, the fault can be eliminated by how to carry out maintenance operation.

Specific examples are shown in table 1 below.

TABLE 1 Motor Fault Attribute information management

(2) Condition monitoring

The state monitoring is the source basis of fault identification and comprises a signal acquisition scheme and a state tracking scheme.

(2.1) Signal acquisition scheme

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

(2.2) a state tracking scheme;

on the basis of signal acquisition, each state parameter of the motor needs to be further calculated and obtained, as shown in table 3 below.

(3) Fault knowledge base construction

The fault knowledge base is fault knowledge for completing the fault identification, and comprises 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 of	f0	/
4	Temperature of the motor	T0	Shell body
				5	Temperature of winding	Tp	Winding head
6	Bearing vibration	Vb	Front/rear bearing seat/bearing cover/engine base
				7	Bearing temperature	Tb	Front/rear bearing seat/bearing cover/engine base
8	Rotational speed	Rpm	Between the output shaft and the load
				9	Torque of	Tor	Between the output shaft and the load
10	Vibration	V0	Outer casing
				11	Continuous on/off time	Tr/Ts	/
12	Noise(s)	No	/
				13	…	…	…

TABLE 3 Motor Performance tracking parameters

(3.1) failure association rule base

The fault association rule refers to a cause-and-effect relationship chain of fault occurrence, and the fault cause is found layer by layer from the fault phenomenon by referring to a Fault Tree Analysis (FTA) top-down analysis method, as shown in the following figure. The overheating of the motor can be caused by the overheating of the stator, the overheating of the rotor, the overheating of the bearing, the abnormal heat dissipation and other reasons, the overheating of the stator and the like can be caused by the mutual friction of the stator and the rotor, and the like, so that the recurrence is carried out to establish a causal relationship diagram of all faults in the fault basic information

(3.2) library of Performance tracking records

The performance tracking record library monitors and stores (2.1) state acquisition parameters and (2.2) performance tracking parameters in the actual operation process of the motor in real time;

(3.3) failure maintenance case library

The troubleshooting case data includes: the fault phenomenon is as follows: description of the performance of the fault; and (3) description of working conditions: the environment, working conditions and load conditions before and after the occurrence of the fault; abnormal parameters: signal acquisition and state tracking parameter values at the time of the fault and in the previous period of time, and reference (3.2) performance tracking records; and (3) confirming the fault: the fault with the problem is confirmed to be diagnosed, and a plurality of faults can be diagnosed, and fault information is quoted (1.3); replacement of spare parts: repairing the replaced component, and introducing (1.1) a fault object; maintenance measures are as follows: the specific process of maintenance.

Here, the trouble maintenance database records conventional trouble maintenance data. Specifically, if a certain current motor needs to be subjected to fault identification, the invention can firstly store the past historical fault maintenance records (including replaced parts) of the motor, one identification scheme for performing fault identification at present is to perform matching with implementation parameters in a case library according to current real-time parameters, the matched records show what maintenance is performed due to what reasons when similar exceptions occur in the past, and further the information can be provided for maintenance personnel, and after fault diagnosis and maintenance are performed according to identification conclusions, the information of replaced spare parts, maintenance processes and the like is recorded back to the case library, so that the case library has one more record.

(4) Fault identification mechanism

The fault identification mechanism solves the problems of how to perform abnormal alarm, fault location and maintenance scheme by monitoring parameters and combining a fault knowledge base.

(4.1) anomaly alarm mechanism

And the abnormal alarm mechanism is matched item by item according to the abnormal alarm table, and if any one of the abnormal alarm table exceeds the normal range, abnormal alarm is carried out. The exception alarm table (as shown in table 4 below) includes: GB/T1032-2012 and the like, such as requirements on temperature rise, vibration and noise level; the specific design requirements of the motor, such as the tolerance upper and lower limits of various performance parameters such as efficiency, torque and the like; expert experience, standards and design requirements may be relatively broad, and some alarm values may be adjusted empirically.

TABLE 4 abnormal alarm watch

(4.2) failure determination mechanism

The exception alarm simply tells you whether a fault is likely to occur, but cannot determine where the fault has occurred.

The failure judgment mechanism is characterized in that when abnormal alarming is carried out, the (2.1) acquisition parameters and the (2.2) performance parameters are matched with a symptom criterion base one by one, the symptom criterion base consists of failures and symptoms corresponding to the failures, the failures refer to the (1.3), and the symptoms are the (2.1) and the (2.2). Each fault and its symptom records may be audited and confirmed by domain experts. As shown in table below-table 5:

the symptom criterion base is used for judging the change of monitoring parameters possibly caused by the occurrence of faults; and the fault judgment is reverse, which faults are judged according to the monitored parameter change, and because one fault can correspond to a plurality of parameter changes and one parameter change can also be caused by a plurality of faults, the fault judgment can only carry out rough fault occurrence probability calculation through symptom matching number.

Therefore, each measured parameter is matched with the symptom criterion library one by one, in each record, one fault corresponds to a plurality of symptoms, and the probability of the fault is higher as the number of matched symptoms is larger. And taking the ratio of the matching symptom number to the total symptom number as the occurrence probability of the fault. Specifically, m symptoms are currently monitored; the X-th record of the symptom bank records n symptoms; if k of n are matched, then k/n is the probability.

(4.3) Fault reasoning mechanism

The above fault determination can determine which faults occur in the motor, but cannot locate all fault reasons and complete fault mechanisms. Therefore, the fault inference mechanism described above substitutes the fault and probability information obtained by the above-mentioned (4.2) fault determination into (3.1) fault association rule, and if it is determined that the probability of "motor-overheat" is 0.6, then in the figure, the probability of "stator-overheat" is 0.6 × 0.5 — 0.3, the probability of rotor overheat is 0.6 × 0.35 — 0.21, and so on; multiple probabilities on multiple faulty links can be summed up, if stator-rotor rub may be caused by stator overheating or rotor overheating, then the fault probability for stator-rotor rub is as in the example figures: 0.3 × 0.1+0.21 × 0.6 ═ 0.156.

If a plurality of faults obtained by the (4.2) fault judgment are on a fault-associated link, the fault link is likely to be a complete mechanism of the fault; if it is determined that there is a certain probability that the "motor-overheating" and the "rotor-dynamic imbalance" are obtained as in (4.2) above, it is likely that the imbalance of the rotor causes uneven breath, which causes rubbing of the stator and the rotor, which causes temperature rise of the stator and the rotor, which causes heating of the motor. The failure probability on the link is obtained by the same failure probability calculation method.

If the faults obtained in the step (4.2) are more and not on one fault link, more complex concurrent faults can occur, and the occurrence probability of each fault is obtained according to the same fault probability calculation method;

the fault reasoning mechanism also comprises a step of comparing the real-time monitoring parameters with the abnormal parameters of the case base (3.4), if the abnormal parameters are all matched, the completely matched case is taken as a similar case, the confirmed fault in the case base (namely fault maintenance case data) is endowed with a fault probability, and the fault probability is the ratio of the number of the abnormal parameters of the case to the total number of the current abnormal parameters. Carrying out weighted averaging on the probabilities of the multiple faults of the multiple cases;

based on a fault reasoning mechanism (namely a fault reasoning rule), the fault association rule reasoning result and the case reasoning result are weighted and averaged to obtain each fault probability.

(5) Maintenance plan

The maintenance schedule sorts the faults obtained by the fault reasoning mechanism according to the probability, the first 10 faults are taken, and the related fields comprise complete information which is helpful for the maintenance personnel to diagnose and overhaul;

and (4) failure: reference 1.3, including fault object (1.1) and fault mode (1.2)

The occurrence probability: quote (4.3)

The type of failure: applications (1.3)

The diagnosis equipment comprises: quote (1.3)

The confirmation method comprises the following steps: quote (1.3)

Maintenance measures are as follows: quote (1.3)

TABLE 5 symptom criterion base

Based on the 4.2 reasoning, a fault identification result is formed, as shown in the following table-6.

TABLE 6 Fault identification results

Serial number

Faulty object

Failure mode

Probability of occurrence

Origin of origin

Diagnostic device

Method for confirming diagnosis

Maintenance measures

Quote (1.1)

Quote (1.2)

Decimal fraction

Rules/cases

Quote (1.3)

Finally, the fault case is updated according to the confirmed diagnosis and maintenance measures (3.3).

In each embodiment of the motor fault identification method, fault knowledge is a basic basis of fault identification, the invention provides a good and extensible management method, which is a basic condition for realizing effective fault identification for different motors, and the fault knowledge management method provided by the invention is extensible: 1. the fault base management module can respectively establish different fault base databases according to different basic structure compositions, different fault expressions and different field test means of different motors; 2. the state monitoring module can arrange and install different sensors according to the conditions of different motor application fields, and the system can be respectively arranged on the signal acquisition and performance tracking items; 3. in the fault knowledge base module, the threshold values of different power sizes and different application occasions of each motor are different and need to be determined according to the object and the application site thereof, and the motor can be updated.

The embodiment of the invention acquires and monitors signals of a motor in operation to obtain signal monitoring parameters of the motor, further tracks the performance of the motor, processes related parameters based on a complete fault knowledge base through presetting fault identification rules, further realizes fault management, performance tracking, criterion management and symptom management from a bottom layer, and simultaneously adopts a fault reasoning mechanism coordinated with fault identification to obtain a fault identification conclusion capable of assisting maintenance personnel in diagnosing and overhauling based on fault maintenance case data. The embodiment of 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; the embodiment of the invention is based on a motor fault knowledge management and fault identification mechanism, has stronger practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

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

in order to solve the problem that the traditional fault identification method is poor in expandability and practicability, the invention provides an embodiment 1 of a motor fault identification system; fig. 7 is a schematic structural diagram of a motor fault identification system in embodiment 1 of the present invention. As shown in fig. 7, may include

The state monitoring unit 710 is used for performing signal acquisition and monitoring on the running motor to obtain signal monitoring parameters of the motor;

the performance tracking unit 720 is used for processing the signal monitoring parameters to obtain performance tracking parameters of the motor;

the fault identification unit 730 is used for processing the signal monitoring parameters and the performance tracking parameters based on the fault knowledge base according to preset fault identification rules to obtain the fault probabilities when the motor fails; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault inference rule; the fault judgment rule comprises the steps of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises the steps of processing each fault judgment occurrence probability according to the fault correlation rule to obtain a fault correlation reasoning result, comparing the signal monitoring parameter and the performance tracking parameter with fault maintenance case data respectively to obtain a case reasoning result, and weighting and averaging to obtain each fault probability;

and the sorting unit 740 is used for sorting the fault probabilities to obtain the fault identification result of the motor. In one of the embodiments, the first and second electrodes are,

further comprising:

a fault basic information management unit 750 for constructing a fault basic information base of the motor; the fault basic information base comprises fault attribute information;

and the fault knowledge base unit 760 is used for constructing a fault knowledge base according to the fault attribute information.

the fault basic information management unit 750 includes:

the fault object dividing module 752 is configured to divide fault objects step by step according to the motor fault characteristics, and introduce a virtual structure having the motor fault characteristics to obtain a fault object dividing structure model of the motor;

a failure mode analysis module 754, configured to perform failure mode analysis according to the failure object partition structure model, and determine each potential failure of the motor;

a fault attribute information management module 756 for generating fault attribute information according to each potential fault;

the failure knowledge base unit 760 includes:

a fault association rule module 762, configured to obtain a cause-and-effect relationship chain of each fault in the fault attribute information according to fault tree analysis;

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

Specifically, it should be noted that the unit modules in the embodiments of the motor fault identification system can correspondingly implement the flow steps in the embodiments of the motor fault identification method, and details are not repeated here.

In one embodiment, a computer device is further provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the motor fault identification method in any one of the above embodiments.

When the processor of the computer equipment executes a program, a fault knowledge management method can be formed by combining cases, standards and experiences by realizing any one of the motor fault identification methods in the embodiments, and fault identification reasoning can be carried out by utilizing the knowledge; the embodiment of the invention is based on a motor fault knowledge management and fault identification mechanism, has stronger practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

In addition, it can be understood by those skilled in the art that all or part of the processes in the methods for implementing the embodiments described above can be implemented by instructing the relevant hardware through a computer program, where the program can be stored in a non-volatile computer-readable storage medium, and in the embodiments of the present invention, the program can be stored in the storage medium of the computer system and executed by at least one processor in the computer system, so as to implement the processes including the embodiments of the motor fault identification methods described above.

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

The computer storage medium, the computer program stored therein, by implementing the processes including the embodiments of the motor fault identification methods as described above, can form a fault knowledge management method in combination with cases, standards and experiences, and perform fault identification reasoning using these knowledge; the embodiment of the invention is based on a motor fault knowledge management and fault identification mechanism, has stronger practicability and expandability, and provides a comprehensive solution for online fault diagnosis and offline fault location of motor operation and rapid system fault repair.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A motor fault identification method is characterized by comprising the following steps:

carrying out signal acquisition monitoring on a motor in operation to obtain a signal monitoring parameter of the motor, and processing the signal monitoring parameter to obtain a performance tracking parameter of the motor; the performance tracking parameters comprise motor power, motor efficiency, minimum torque, maximum torque, locked rotor current and temperature rise;

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 of the motor when the motor fails; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault reasoning rule; the fault judgment rule comprises the step of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises a fault correlation reasoning result obtained by processing each fault judgment occurrence probability according to the fault correlation rule, and a case reasoning result obtained by comparing the signal monitoring parameter and the performance tracking parameter with the fault maintenance case data respectively, and carrying out weighting and averaging to obtain each fault probability;

2. The motor fault identification method according to claim 1, wherein the signal monitoring parameters comprise electrical parameters, temperature parameters of each component, working parameters and state parameters of the motor;

the method comprises the following steps of processing the signal monitoring parameters and the performance tracking parameters based on a fault knowledge base according to preset fault identification rules to obtain the fault probability of the motor when the motor fails:

and constructing the fault knowledge base 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;

performing fault mode analysis according to the fault object division structure model to determine each potential fault of the motor; generating the fault attribute information according to the potential faults;

the step of constructing the fault knowledge base comprises:

obtaining the cause-effect relationship chain of each fault in the fault attribute information according to fault tree analysis;

and generating the fault maintenance case data 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 comprises a complete fault mechanism result and a concurrent fault result;

according to the fault association rule, when confirming that each fault corresponding to each fault judgment occurrence probability is on the same fault association link, obtaining the complete fault mechanism result through probability calculation;

or

And when the faults corresponding to the fault judgment occurrence probabilities are confirmed to be on different fault associated links, obtaining the concurrent fault result through probability calculation.

5. The motor fault identification method according to claim 4, wherein the step of processing the signal monitoring parameters and the performance tracking parameters based on a fault knowledge base according to a preset fault identification rule to obtain each fault probability when the motor fails further comprises the steps of:

when the signal monitoring parameters and the performance tracking parameters are monitored to exceed corresponding alarm values, an abnormal alarm is sent out;

the method further comprises the following steps after the step of obtaining the fault identification result of the motor:

determining a maintenance plan according to the fault identification result;

6. A motor fault identification system, comprising:

the performance tracking unit is used for processing the signal monitoring parameters to obtain performance tracking parameters of the motor; the performance tracking parameters comprise motor power, motor efficiency, minimum torque, maximum torque, locked rotor current and temperature rise;

the fault identification unit is used for 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; the fault knowledge base comprises fault association rules and fault maintenance case data; the preset fault identification rule comprises a fault judgment rule and a fault reasoning rule; the fault judgment rule comprises the step of respectively matching the signal monitoring parameters and the performance tracking parameters with each symptom record in a preset symptom criterion base one by one to obtain the fault judgment occurrence probability when the motor fails; the fault reasoning rule comprises a fault correlation reasoning result obtained by processing each fault judgment occurrence probability according to the fault correlation rule, and a case reasoning result obtained by comparing the signal monitoring parameter and the performance tracking parameter with the fault maintenance case data respectively, and carrying out weighting and averaging to obtain each fault probability;

and the sequencing unit is used for sequencing the fault probabilities to obtain a fault identification result of the motor.

7. The motor fault identification system of claim 6, wherein the signal monitoring parameters include electrical parameters, component temperature parameters, operating parameters, and status parameters of the motor;

further comprising:

and the fault knowledge base unit is used for constructing the fault knowledge base according to the fault attribute information.

8. The motor fault identification system of claim 7, wherein the fault association rule is a causal relationship chain;

the fault basic information management unit includes:

the fault attribute information management module is used for generating the fault attribute information according to each potential fault;

the failure knowledge base unit includes:

the fault association rule module is used for obtaining the cause-and-effect relationship chain of each fault in the fault attribute information according to fault tree analysis;

and the fault maintenance case library module is used for generating the fault maintenance case data according to the fault object division structure model, the signal monitoring parameters and the performance tracking parameters.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented when the processor executes the program.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.