Complex electromechanical equipment fault diagnosis method, equipment, medium and product

Abstract

The invention discloses a complex electromechanical equipment fault diagnosis method and device, a medium and a product, and relates to the field of complex electromechanical system health management.The method comprises the steps that unbalanced influence calculation is conducted on complex electromechanical equipment to be judged in a storage workshop and equipment judged to be of the same model in an experiment workshop, and unbalanced influence factors are determined; constructing a complex electromechanical system fault diagnosis model based on a confidence rule base according to the monitoring information of the key characteristic indexes of the same model equipment and the imbalance influence factors; and obtaining a fault diagnosis result of the to-be-judged complex electromechanical equipment in the storage workshop by adopting the complex electromechanical system fault diagnosis model according to the monitoring information of the to-be-judged complex electromechanical equipment in the storage workshop. According to the method, the accuracy of fault diagnosis of the complex electromechanical equipment under extremely few unbalanced samples can be improved.

Description

Technical Field

[0001] The present application relates to the field of health management of complex electromechanical systems, and in particular to a method, equipment, medium and product for diagnosing faults of complex electromechanical equipment. Background Art

[0002] Complex systems such as aircraft are one of the key systems in the aerospace field. Their reliability during long-term power-on is the key to ensuring the stable and reliable operation of the system. Fault diagnosis refers to the diagnosis of the process in which the system's performance degrades due to large deviations beyond the acceptable range of the system's characteristics or parameters. At present, complex electromechanical equipment is difficult to diagnose during storage because it has just been produced and has very few unbalanced samples. On the one hand, since the number of tests of newly produced equipment is very small during the actual storage process, the storage device data is extremely scarce; at the same time, due to the extremely scarce equipment samples, it is difficult to establish an effective fault diagnosis model, which poses a great hidden danger to the health of the storage device. Therefore, effective diagnosis and monitoring of faults in complex electromechanical equipment has become an urgent need for modern complex industrial processes.

[0003] An analysis of the current problems faced in the fault diagnosis of complex electromechanical equipment can be summarized into three aspects: First, the number of samples is extremely scarce due to the extremely small number of tests on newly produced equipment; second, due to the high coupling between the subsystems of the complex electromechanical system and the use of integrated design, there are many factors that affect its working state. It is difficult to establish an accurate mathematical model relying solely on expert knowledge, which leads to uncertainty in expert knowledge; third, due to the extreme shortage of data and parameters in the storage workshop, it is difficult to establish a fault diagnosis model, and it is difficult to ensure the healthy state of the complex electromechanical equipment in the workshop, which poses a major health hazard.

[0004] Therefore, based on the above problems, a new method for fault diagnosis of complex electromechanical equipment is urgently needed to solve the three problems faced in the fault diagnosis process of complex electromechanical equipment under extremely few unbalanced samples: extremely scarce samples, uncertain expert knowledge, and difficulty in establishing fault diagnosis models. Summary of the invention

[0005] The purpose of this application is to provide a complex electromechanical equipment fault diagnosis method, equipment, medium and product, which can improve the accuracy of complex electromechanical equipment fault diagnosis under very few unbalanced samples.

[0006] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a complex electromechanical equipment fault diagnosis method, the complex electromechanical equipment fault diagnosis method comprising: Calculate the unbalanced impact of the complex electromechanical equipment to be judged in the storage workshop and the equipment of the same model that has been judged in the experimental workshop, and determine the unbalanced impact factor; According to the monitoring information and imbalance influencing factors of key characteristic indicators of the same model of equipment, a complex electromechanical system fault diagnosis model is constructed based on the confidence rule base; According to the monitoring information of the complex electromechanical equipment to be judged in the storage workshop, the fault diagnosis model of the complex electromechanical system is adopted to obtain the fault diagnosis results of the complex electromechanical equipment to be judged in the storage workshop.

[0007] Optionally, performing unbalanced impact calculation on the complex electromechanical equipment to be determined in the storage workshop and the equipment of the same model that has been determined in the experimental workshop to determine the unbalanced impact factor specifically includes: Using the formula Identify the factors that influence imbalances; in, is the imbalance impact factor, o is the fault state number, p is the sample number of the storage workshop, n is the number of samples in the storage workshop, q is the sample number of the experimental workshop, m is the number of samples in the experimental workshop, represents the pth sample in the storage workshop, represents the qth sample in the experimental workshop, Indicates output fault status criteria.

[0008] Alternatively, using the formula Establish a trust rule base; in, For the equipment of the same model that has been judged in the experimental workshop Monitoring information of key characteristic indicators, To obtain the complex electromechanical equipment to be judged sensor, is the attribute weight of the key feature indicator, The reference level corresponding to the key characteristic indicators; For N quality states of the same model of equipment that have been determined, is the corresponding output fault feature vector, is the rule weight, , is the number of rules, The imbalanced impact factor.

[0009] Optionally, the diagnosis process of the complex electromechanical system fault diagnosis model specifically includes: The monitoring information is converted into a unified framework using the imbalanced impact factor to obtain the matching degree of each indicator in each rule; Determine all key characteristics in the The degree of match in the rules; According to all key characteristic indicators in the The matching degree in the rules and the weight of the kth rule determine the activation weight of the rule; According to the activation weights of the rules, the fault diagnosis feature vectors output by all the rules are determined; According to the fault diagnosis feature vectors output by all rules, the evidence reasoning algorithm is used to fuse them to obtain the final output fault diagnosis feature vector; According to the final output fault diagnosis feature vector, the fault diagnosis result is obtained.

[0010] Optionally, the monitoring information is converted into a unified framework using the imbalanced impact factor to obtain the matching degree of each indicator in each rule, including: Using the formula Determine the key characteristic index after conversion in the Matching degree in rules ; in, is the imbalance impact factor, and For the The key characteristic index is Article and The reference level in the rule, is the number of rules after adaptive adjustment, For input data.

[0011] Optionally, based on all key characteristic indicators in the The matching degree in the rules and the weight of the kth rule determine the activation weight of the rule, including: Using the formula Determine The activation weights of the rules ; in, For all key characteristic indicators in The matching degree in the rules, In the fault diagnosis method The weight of the rule, In the fault diagnosis method The weight of the rule, For all key characteristic indicators in The matching degree in the rules, is the number of rules.

[0012] Optionally, the fault diagnosis feature vectors output by all rules are fused using an evidential reasoning algorithm to obtain a final output fault diagnosis feature vector, which specifically includes the following formula: ; ; in, is the confidence level of the nth output result obtained after integrating the input indicator monitoring information, and , For the n The key characteristic index is k The characteristic vector of the system quality state generated by the rules, For the The key characteristic index is k The characteristic vector of the system quality state generated by the rules, N is the number of key characteristic indicators, is the intermediate parameter.

[0013] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the complex electromechanical equipment fault diagnosis method.

[0014] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the complex electromechanical equipment fault diagnosis method when executed by a processor.

[0015] In a fourth aspect, the present application provides a computer program product, including a computer program, which implements the complex electromechanical equipment fault diagnosis method when executed by a processor.

[0016] According to the specific embodiments provided in this application, this application has the following technical effects: The present application provides a method, equipment, medium and product for diagnosing complex electromechanical equipment faults. Based on the belief rule base (BRB), a complex electromechanical system fault diagnosis model under extremely small samples is constructed, which effectively integrates expert knowledge and monitoring information to solve the requirements of extremely lacking storage workshops and limited expert knowledge in the fault diagnosis of complex electromechanical systems under extremely small samples; by calculating the unbalanced impact factor, in the process of fault diagnosis of complex electromechanical systems, the information difference between extremely few test equipment and commonly tested equipment is solved, which lays the foundation for the fault diagnosis of complex electromechanical equipment with extremely few samples, and finally obtains a more accurate fault diagnosis result. The present invention effectively improves the accuracy of fault diagnosis of complex electromechanical systems under extremely few samples in actual environments, and ensures its safe and reliable operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is a flow chart of a method for diagnosing a complex electromechanical equipment fault in one embodiment of the present application; Figure 2 This is a schematic diagram of the test data of monitoring indicators of the same type of equipment that has been determined; Figure 3 This is a schematic diagram of the fault diagnosis results of the inertial navigation system with very few samples. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] In an exemplary embodiment, Figure 1 As shown, a complex electromechanical equipment fault diagnosis method is provided, the method comprising the following S101 to S101. Wherein: S101, performing unbalanced impact calculation on the complex electromechanical equipment to be judged in the storage workshop and the equipment of the same model that has been judged in the experimental workshop, and determining the unbalanced impact factor; Using the formula Identify the factors that influence imbalances; in, is the imbalance impact factor, o is the fault state number, p is the sample number of the storage workshop, n is the number of samples in the storage workshop, q is the sample number of the experimental workshop, m is the number of samples in the experimental workshop, represents the pth sample in the storage workshop, represents the qth sample in the experimental workshop, Indicates output fault status criteria.

[0022] The determination of the imbalanced impact factor can lay the foundation for establishing a fault diagnosis model. In other words, it is difficult to establish a complete fault diagnosis model when the sample is extremely insufficient, and it is impossible to provide favorable protection for the health of complex electromechanical equipment in the storage workshop. Therefore, the primary task of fault diagnosis of complex electromechanical equipment with very few samples is to minimize the sample difference between the very few test equipment and the commonly tested equipment. The imbalanced impact factor is calculated according to the mechanism of complex electromechanical equipment, and then it is as close to the real sample in the experimental workshop as possible, ensuring the authenticity and reliability of the fault diagnosis output results.

[0023] S102, based on the monitoring information and imbalance impact factors of the key characteristic indicators of the same model of equipment, a complex electromechanical system fault diagnosis model is constructed based on the confidence rule base; the key characteristic indicators require experts to select an appropriate number of indicators of the fault diagnosis status based on the actual working conditions of the complex electromechanical system, and the key characteristic indicators are the cumulative pulse equivalent.

[0024] Using the formula Establish a trust rule base; in, For the equipment of the same model that has been judged in the experimental workshop Monitoring information of key characteristic indicators, To obtain the complex electromechanical equipment to be judged sensor, is the attribute weight of the key feature indicator, It is a reference level corresponding to the key characteristic indicators, aiming to transform the multivariate information into a unified framework; For N quality states of the same model of equipment that have been determined, is the corresponding output fault feature vector, is the rule weight, , The imbalanced impact factor.

[0025] The diagnostic process of the complex electromechanical system fault diagnosis model specifically includes: S1, using the imbalanced impact factor to convert the monitoring information into a unified framework, and obtain the matching degree of each indicator in each rule; using the following formula to convert the multivariate monitoring information into a unified framework: ; in, is the key feature index after conversion to the The matching degree in the rules, and For the The key characteristic index is Article and The reference level in the rule needs to be determined based on the information distribution and type of the feature. is the number of rules after adaptive adjustment, For input data.

[0026] S2, determine all key characteristic indicators in the The degree of match in the rules; After obtaining the matching degree of each key feature indicator in each rule, the following formula can be used to calculate the matching degree of all key feature indicators in the first Matching degree in rules : ; ; in, Indicates the relative weight of the indicator; S3, according to all key characteristic indicators in the The matching degree in the rule and the weight of the kth rule determine the activation weight of the rule; different monitoring information will have different effects on different rules, so the activation weight of the rule is used as shown in the following formula: ; in, For all key characteristic indicators in The matching degree in the rules, In the fault diagnosis method The weight of a rule, that is, the importance of this rule relative to other rules in the model. In the fault diagnosis method The weight of the rule, For all key characteristic indicators in The degree of match in the rule.

[0027] S4, determining the fault diagnosis feature vectors output by all rules according to the activation weights of the rules; S5, according to the fault diagnosis feature vectors output by all rules, the evidence reasoning algorithm is used to fuse them to obtain the final output fault diagnosis feature vector; The activated rules will generate system fault diagnosis feature vectors, which represent the results of the rule diagnosis. The fault diagnosis feature vectors output by all rules can be fused through the Evidential Reasoning (ER) algorithm to obtain the final output fault diagnosis feature vector. The ER algorithm analysis form is as follows: ; ; in, is the confidence level of the nth output result obtained after integrating the input indicator monitoring information, and , For the n The key characteristic index is k The characteristic vector of the system quality state generated by the rules, For the The key characteristic index is k The characteristic vector of the system quality state generated by the rules, N is the number of key characteristic indicators.

[0028] S6, obtaining a fault diagnosis result according to the final output fault diagnosis feature vector.

[0029] Assuming a single output level The utility is , the output of complex electromechanical equipment fault diagnosis results is as follows: ; in, It is the final output result of the complex electromechanical system fault diagnosis model built based on BRB, that is, the fault level of the complex electromechanical system obtained from the monitoring information.

[0030] In order to improve the accuracy of judgment, the complex electromechanical system fault diagnosis model is optimized and the integration of data and knowledge is achieved. The parameter optimization process of the complex electromechanical system fault diagnosis model needs to obey the following constraints: ; ; ; ; S103, according to the monitoring information of the complex electromechanical equipment to be judged in the storage workshop, a complex electromechanical system fault diagnosis model is used to obtain the fault diagnosis result of the complex electromechanical equipment to be judged in the storage workshop.

[0031] The parameters of the complex electromechanical equipment fault diagnosis model in the experimental workshop are transferred to the storage workshop, and the expanded samples are input, and finally the fault diagnosis results of the complex electromechanical equipment in the storage workshop are output.

[0032] In order to verify the effectiveness of this application, an experimental verification was conducted on the aircraft inertial navigation system under the influence of partial accelerometer replacement, which mainly includes the following steps: Step 1: Expand the sample of complex electromechanical equipment in the storage workshop; For the inertial navigation system in the storage workshop, due to the very few tests, there are very few samples related to the inertial navigation system. Complex electromechanical systems such as inertial navigation systems are autonomous systems that do not rely on any external information and do not radiate energy to the outside. They have good concealment and are not affected by external electromagnetic interference. They can work in the air, on the surface of the earth and even underwater all day and all the time. They can provide position, speed, heading and attitude angle data, and the navigation information generated has good continuity and low noise. The data update rate is high and the short-term accuracy and stability are good. Therefore, the very few samples of the inertial navigation system in the storage workshop have caused great difficulties for the establishment of the fault diagnosis model and have a great impact on the health of the inertial navigation system. In the experiment, the inertial navigation system samples of the storage workshop were expanded through the inertial navigation system mechanism model as the input of the complex electromechanical system fault diagnosis model. The samples expanded according to the inertial navigation system mechanism model are as follows Figure 2 shown.

[0033] Step 2: Establishment of a fault diagnosis model for the complex electromechanical system of the inertial navigation system of the storage workshop; In the monitoring information of the three accelerometers of the inertial navigation system, combined with the data volume, model complexity, diagnostic accuracy, diagnostic real-time, etc., the reference levels of the monitoring information of the three accelerometers are determined to be 4, T for excellent, F for good, P for qualified, and A for poor, as shown in Table 1. Combined with the rule construction method shown in the confidence rule base, there are 64 rules in the constructed complex electromechanical system fault diagnosis model. Since the accelerometer is easily affected by the environment during actual use, it is necessary to consider the monitoring information of the three accelerometers at the same time when determining the confidence of the rule output. The initial complex electromechanical system fault diagnosis model is shown in Table 2. NO, SO, BO, and UN represent normal operation, can still operate, barely operate, and cannot operate, respectively. In the initial complex electromechanical system fault diagnosis model, it is assumed that the rules are equally important, that is, the rule weight is set to 1.

[0034]

[0035] Table 2

[0036] Step 3: Training and testing of the complex electromechanical system fault diagnosis model for the inertial navigation system of the storage workshop; After the inertial navigation system samples in the storage workshop were expanded, a sample set of 600 groups was obtained. 200 groups were selected from the sample set as training data to train the constructed complex electromechanical system fault diagnosis model.

[0037] from Figure 3It can be seen that the blue line can accurately derive fault diagnosis results when using the optimized complex electromechanical system fault diagnosis model, and can make accurate diagnoses at some monitoring points where experts cannot accurately judge, effectively overcoming the uncertainty and local ignorance of expert knowledge, achieving effective feedback of monitoring information to expert knowledge, and improving the expert system to achieve effective integration of monitoring information and expert knowledge. After training, the indicator weights of the imbalanced influencing factors are 0.5. The accuracy of the complex electromechanical system fault diagnosis model after training is 97%, with high diagnostic accuracy, which can meet the fault diagnosis needs of the inertial navigation system.

[0038] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for diagnosing a complex electromechanical device fault is implemented.

[0039] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0040] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0041] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0042] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0043] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0044] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0045] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for diagnosing faults of complex electromechanical equipment, characterized in that: The complex electromechanical equipment fault diagnosis method comprises: Calculate the unbalanced impact of the complex electromechanical equipment to be judged in the storage workshop and the equipment of the same model that has been judged in the experimental workshop, and determine the unbalanced impact factor; According to the monitoring information and imbalance influencing factors of key characteristic indicators of the same model of equipment, a complex electromechanical system fault diagnosis model is constructed based on the confidence rule base; According to the monitoring information of the complex electromechanical equipment to be judged in the storage workshop, the fault diagnosis model of the complex electromechanical system is adopted to obtain the fault diagnosis results of the complex electromechanical equipment to be judged in the storage workshop.

2. The complex electromechanical equipment fault diagnosis method according to claim 1, characterized in that: The unbalanced impact calculation of the complex electromechanical equipment to be judged in the storage workshop and the equipment of the same model that has been judged in the experimental workshop is performed to determine the unbalanced impact factor, specifically including: Using the formula Identify the factors that influence imbalances; in, is the imbalance impact factor, o is the fault state number, p is the sample number of the storage workshop, n is the number of samples in the storage workshop, q is the sample number of the experimental workshop, m is the number of samples in the experimental workshop, represents the pth sample in the storage workshop, represents the qth sample in the experimental workshop, Indicates output fault status criteria.

3. The complex electromechanical equipment fault diagnosis method according to claim 1, characterized in that: Using the formula Establish a trust rule base; in, For the equipment of the same model that has been judged in the experimental workshop Monitoring information of key characteristic indicators, To obtain the complex electromechanical equipment to be judged sensor, is the attribute weight of the key feature indicator, The reference level corresponding to the key characteristic indicators; For N quality states of the same model of equipment that have been determined, is the corresponding output fault feature vector, is the rule weight, , is the number of rules, The imbalanced impact factor.

4. The complex electromechanical equipment fault diagnosis method according to claim 1, characterized in that: The diagnostic process of the complex electromechanical system fault diagnosis model specifically includes: The monitoring information is converted into a unified framework using the imbalanced impact factor to obtain the matching degree of each indicator in each rule; Determine all key characteristics in the The degree of match in the rules; According to all key characteristic indicators in the The matching degree in the rules and the weight of the kth rule determine the activation weight of the rule; According to the activation weights of the rules, the fault diagnosis feature vectors output by all the rules are determined; According to the fault diagnosis feature vectors output by all rules, the evidence reasoning algorithm is used to fuse them to obtain the final output fault diagnosis feature vector; According to the final output fault diagnosis feature vector, the fault diagnosis result is obtained.

5. The complex electromechanical equipment fault diagnosis method according to claim 4, characterized in that: The monitoring information is converted into a unified framework using the imbalanced impact factor to obtain the matching degree of each indicator in each rule, including: Using the formula Determine the key characteristic index after conversion in the Matching degree in rules ; in, is the imbalance impact factor, and For the The key characteristic index is Article and The reference level in the rule, is the number of rules after adaptive adjustment, For input data.

6. The complex electromechanical equipment fault diagnosis method according to claim 5, characterized in that: According to all key characteristic indicators in The matching degree in the rules and the weight of the kth rule determine the activation weight of the rule, including: Using the formula Determine The activation weights of the rules ; in, For all key characteristic indicators in The matching degree in the rules, In the fault diagnosis method The weight of the rule, In the fault diagnosis method The weight of the rule, For all key characteristic indicators in The matching degree in the rules, is the number of rules.

7. The complex electromechanical equipment fault diagnosis method according to claim 6, characterized in that: According to the fault diagnosis feature vectors output by all rules, the evidence reasoning algorithm is used to fuse them to obtain the final output fault diagnosis feature vector, which specifically includes the following formula: ； ； in, is the confidence level of the nth output result obtained after integrating the input indicator monitoring information, and , For the n The key characteristic index is k The characteristic vector of the system quality state generated by the rules, For the The key characteristic index is k The characteristic vector of the system quality state generated by the rules, N is the number of key characteristic indicators, is the intermediate parameter.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the complex electromechanical equipment fault diagnosis method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the complex electromechanical equipment fault diagnosis method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the complex electromechanical equipment fault diagnosis method described in any one of claims 1 to 6 is implemented.

Images