Industrial equipment fault diagnosis method and system based on dynamic optimization

Abstract

The application relates to an industrial equipment fault diagnosis method and system based on dynamic optimization. The method comprises the following steps: generating a fault symptom vector according to obtained industrial equipment data, adopting a corresponding industrial mechanism model to diagnose a fault according to the fault symptom vector, obtaining a fault cause to realize diagnosis of the industrial equipment, constructing fault history data by using data obtained by the diagnosis and a real fault cause, and optimizing and iterating parameters in the industrial mechanism model by using the fault history data, so that the diagnosis result is more accurate in the next fault diagnosis. The method can quickly obtain a fault cause to obtain a fault source, facilitate subsequent targeted repair, make the equipment more quickly restore a working state, and make the fault diagnosis result of the industrial mechanism model more and more accurate through optimization and iteration of the industrial mechanism model by using diagnosis data.

Description

Technical Field

[0001] This application relates to the field of equipment fault diagnosis technology, and in particular to a method and system for diagnosing industrial equipment faults based on dynamic optimization. Background Technology

[0002] In industrial production, various industrial equipment plays a crucial role, such as mechanical and electrical equipment on production lines. Failures in this equipment can lead to production interruptions, damage, and additional repair costs. Therefore, real-time monitoring and accurate diagnosis of the health status of industrial equipment are essential for improving productivity and reducing costs.

[0003] Traditionally, fault diagnosis of industrial equipment has relied primarily on periodic inspections and human experience. However, this approach suffers from low accuracy, high latency, and dependence on specialized skills. In recent years, with the rapid development of IoT technology, the number of sensors and data acquisition devices deployed on industrial equipment has gradually increased, providing a wealth of real-time data for analysis and diagnosis. However, traditional cloud-based processing models may face challenges such as data transmission latency, privacy protection, and network stability.

[0004] Therefore, it is necessary to study a more efficient, real-time and accurate method for diagnosing industrial equipment faults, which can analyze real-time data at the edge device to diagnose the cause of the fault, enabling targeted maintenance and rapid resolution of the fault problem. Summary of the Invention

[0005] Therefore, it is necessary to provide a dynamic optimization-based industrial equipment fault diagnosis method and system that can quickly and accurately obtain the cause of the fault, addressing the aforementioned technical problems.

[0006] A method for fault diagnosis of industrial equipment based on dynamic optimization, the method comprising:

[0007] Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data;

[0008] By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0009] Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector.

[0010] The parameters in the corresponding industrial mechanism model are optimized based on the historical failure data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0011] The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

[0012] In one embodiment, when constructing the industrial mechanism model, the relationship between various causes of industrial equipment failures and various symptoms is represented by a fuzzy relation matrix.

[0013] In one embodiment, the equipment data of the industrial equipment is data related to the manifestation of fault symptoms.

[0014] In one embodiment, optimizing the parameters in the corresponding industrial mechanism model based on historical fault data of a certain type of industrial equipment to obtain the optimized industrial mechanism model includes:

[0015] In the historical fault data, the number of times a certain fault symptom occurs due to a certain fault cause is counted, and a fault cause frequency matrix is ​​constructed accordingly.

[0016] The current industrial mechanism model is converted into a corresponding failure cause frequency matrix based on the failure cause frequency matrix and the conversion formula, which serves as the failure cause frequency conversion matrix.

[0017] Based on the failure cause frequency matrix and the failure cause frequency transformation matrix, the parameters in the current industrial mechanism model are optimized using an optimization formula to obtain the optimized industrial mechanism model.

[0018] In one embodiment, the conversion formula is expressed as:

[0019]

[0020] In the above formula, the subscript i represents a certain symptom of a fault, the subscript j represents a certain cause of a fault, and h... ij c represents a parameter in the fault cause frequency transformation matrix. nj The parameter in the fault cause frequency matrix is ​​called the fault cause frequency, and T is a transformation constant.

[0021] In one embodiment, the optimization formula is expressed as:

[0022]

[0023] In the above formula, the subscript i represents a certain fault symptom, the subscript j represents a certain fault cause, and r ij c represents the parameters in the optimized industrial mechanism model. ij and h ij These represent the parameters in the fault cause frequency matrix and the fault cause frequency transformation matrix, respectively.

[0024] In one embodiment, when the industrial equipment fault diagnosis method is used to diagnose the cause of an existing equipment fault, the acquired equipment data is the equipment data after the equipment fault occurred.

[0025] In one embodiment, the industrial equipment fault diagnosis method further includes:

[0026] After optimizing the industrial mechanism model a preset number of times, the optimized industrial mechanism model is used to predict faults in the real-time acquired equipment data.

[0027] An industrial equipment fault diagnosis system based on dynamic optimization, the system comprising multiple device terminals, edge terminals, and the cloud;

[0028] Each of the aforementioned device terminals is used to collect device data and send the device data to the edge terminal;

[0029] The edge terminal is used to acquire equipment data of industrial equipment, generate fault symptom vectors based on the equipment data, and diagnose faults based on fault symptom vectors by using an industrial mechanism model corresponding to the industrial equipment to obtain the cause of the fault in order to diagnose the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0030] The edge device is used to obtain the actual cause of the fault, construct the fault history data corresponding to the industrial equipment based on the actual cause of the fault and the fault symptom vector, and send the fault history data to the cloud.

[0031] The cloud is used to optimize the parameters in the corresponding industrial mechanism model based on the fault history data of a certain type of industrial equipment, to obtain an optimized industrial mechanism model, and then send the optimized industrial mechanism model to the edge terminal.

[0032] The edge terminal is used to perform the next fault diagnosis on the corresponding industrial equipment using the optimized industrial mechanism model.

[0033] An industrial equipment fault diagnosis device based on dynamic optimization, the device comprising:

[0034] The data acquisition module is used to acquire equipment data of industrial equipment and generate fault symptom vectors based on the equipment data.

[0035] The fault cause diagnosis module is used to diagnose the fault by adopting an industrial mechanism model corresponding to the industrial equipment and based on the fault symptom vector to obtain the fault cause in order to diagnose the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0036] The fault history data construction module is used to obtain the actual fault cause and construct the fault history data corresponding to the industrial equipment based on the actual fault cause and fault symptom vector.

[0037] The industrial mechanism model optimization module is used to optimize the parameters in the corresponding industrial mechanism model based on the fault history data of a certain type of industrial equipment, so as to obtain the optimized industrial mechanism model.

[0038] The optimized model fault diagnosis module is used to perform the next fault diagnosis on the corresponding industrial equipment using the optimized industrial mechanism model.

[0039] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0040] Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data;

[0041] By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0042] Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector.

[0043] The parameters in the corresponding industrial mechanism model are optimized based on the historical failure data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0044] The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

[0045] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0046] Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data;

[0047] By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0048] Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector.

[0049] The parameters in the corresponding industrial mechanism model are optimized based on the historical failure data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0050] The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

[0051] The aforementioned dynamic optimization-based industrial equipment fault diagnosis method and system generates fault symptom vectors based on acquired industrial equipment data. It then uses a corresponding industrial mechanism model to diagnose the faults based on these symptom vectors, identifying the causes of the faults. Simultaneously, it constructs historical fault data using the data from this diagnosis and the actual fault causes, and uses this historical data to optimize and iterate the parameters in the industrial mechanism model, making the diagnostic results more accurate in subsequent fault diagnoses. This method allows for rapid identification of fault causes and their root causes, facilitating targeted repairs and enabling the equipment to return to operational status more quickly. Furthermore, the continuous optimization and iteration of the industrial mechanism model based on each diagnostic data point leads to increasingly accurate fault diagnosis results. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating a dynamic optimization-based industrial equipment fault diagnosis method in one embodiment.

[0053] Figure 2 This is a flowchart illustrating the steps of an industrial equipment fault diagnosis method based on an edge collaboration system in one embodiment.

[0054] Figure 3 This is a structural block diagram of an industrial equipment fault diagnosis device based on dynamic optimization in one embodiment;

[0055] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] Traditional fault diagnosis methods based on fuzzy theory rely on expert knowledge to set fuzzy matrices. The resulting industrial mechanism models have low diagnostic accuracy for different types of faults or under different environments. Furthermore, existing methods lack the ability to automatically adjust the parameters of the fuzzy matrix. Figure 1 As shown, a method for fault diagnosis of industrial equipment based on dynamic optimization is provided, including the following steps:

[0058] Step S100: Obtain equipment data of industrial equipment and generate fault symptom vectors based on the equipment data;

[0059] Step S110: The fault is diagnosed by using an industrial mechanism model corresponding to the industrial equipment based on the fault symptom vector to obtain the cause of the fault in order to diagnose the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0060] Step S120: Obtain the actual cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the actual cause of the fault and the fault symptom vector.

[0061] Step S130: Optimize the parameters in the corresponding industrial mechanism model based on the historical fault data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0062] Step S140: Use the optimized industrial mechanism model to perform the next fault diagnosis on the corresponding industrial equipment.

[0063] In this embodiment, while diagnosing the cause of equipment failure using an industrial mechanism model, the generated data is also used to dynamically optimize the parameters in the industrial mechanism model, allowing for continuous automatic parameter adjustment. This makes the diagnostic results of the industrial mechanism model increasingly accurate. This method can be applied to different industrial environments and has a high diagnostic accuracy rate. After diagnosing the cause of industrial equipment failure using this method, the cause of the failure can be quickly repaired.

[0064] In step S100, after acquiring the equipment data of a certain industrial device, it is converted into a fault symptom vector. In fact, when a device malfunctions, different malfunctions will cause corresponding data changes. These changes are called fault symptoms. By analyzing these changed data, the cause of the malfunction can be determined.

[0065] In step S110, an industrial mechanism model is used to analyze the changing data. This industrial mechanism model is a model that integrates professional knowledge such as principles, theorems, and laws from industrial production processes, combined with actual industrial production experience, to form a mechanism and construct a model. Over many years of development, various industries have accumulated a wealth of industry experience and knowledge.

[0066] In this embodiment, when constructing the industrial mechanism model, the relationship between various causes of industrial equipment failures and various symptoms is represented by a fuzzy relation matrix.

[0067] Specifically, the basic principle of industrial mechanism models is based on fuzzy mathematics, which diagnoses the possible causes of equipment failures by analyzing the causal relationships between the causes and symptoms of various failures. Because the relationships between the causes and symptoms of various equipment failures are complex, it is difficult to establish precise mathematical models. Therefore, fuzzy mathematics theory is used to describe the mechanistic relationships between failures and their causes.

[0068] In fuzzy mathematics, elements that neither belong to nor belong to a category are categorized between 0 and 1, and this characteristic is described by membership functions. Fuzzy fault diagnosis involves determining the membership degrees of various faults based on the membership degrees of certain symptoms, thereby inferring the most likely cause of equipment failure.

[0069] Suppose there are j possible fault symptoms for the object being diagnosed, and the statistical fault symptom set is {x1, x2, ... x}. j There are i possible causes for a failure, and the set of possible causes is {y1, y2, ..., y}. i Since the relationship between various causes and symptoms of failure is fuzzy, establishing a mechanistic model is equivalent to establishing a fuzzy relationship matrix between failures and symptoms for a certain type of equipment.

[0070]

[0071] In formula (1), r ij Let R be the membership degree of the fuzzy relation R.

[0072] Based on the acquired equipment fault symptom data, a symptom-specific diagnostic vector V can be constructed, where V = {v1, v2, ... v}. j The fault cause vector W = V*R is obtained through matrix operations. Here, W = {w1, w2, ..., wi}. Sort the w values ​​by magnitude to determine the probability of each corresponding cause y. Output the fault cause corresponding to the maximum value in the w sequence.

[0073] Therefore, the key to constructing an industrial mechanism model lies in the parameters r in the fuzzy matrix R. ij The determination.

[0074] In this embodiment, the parameters r in the initial industrial mechanism model ij The determination is based on expert or industry experience. The equipment data acquired for the industrial equipment is related to the symptoms of a malfunction. Symptoms can be any abnormal phenomena observed when equipment malfunctions, such as abnormal vibrations or excessively high equipment temperatures.

[0075] In this embodiment, there are multiple industrial mechanism models that correspond one-to-one with different industrial equipment. Similarly, when dynamically optimizing the industrial mechanism model, the corresponding equipment data is also applied.

[0076] In step S120, after troubleshooting the equipment based on the fault causes given by the industrial mechanism model, the actual fault causes will be obtained. At this time, fault history data can be constructed based on the actual fault causes and the corresponding fault symptom data, and then the fault history data can be used to optimize the parameters of the industrial mechanism model.

[0077] In this embodiment, the fault history data includes symptom feature vectors, fault cause vectors, actual causes, and fault time.

[0078] In step S130, model optimization is not required after every fault diagnosis. The model can be optimized after obtaining more historical fault data according to the preset optimization mechanism.

[0079] Specifically, the parameters in the corresponding industrial mechanism model are optimized based on the historical fault data of a certain type of industrial equipment to obtain the optimized industrial mechanism model. This includes: counting the number of times a certain fault symptom occurs due to a certain fault cause in the historical fault data, and constructing a fault cause frequency matrix accordingly; converting the current industrial mechanism model into a corresponding fault cause frequency matrix based on the fault cause frequency matrix and the conversion formula, which serves as the fault cause frequency conversion matrix; and finally optimizing each parameter in the current industrial mechanism model using the optimization formula based on the fault cause frequency matrix and the fault cause frequency conversion matrix to obtain the optimized industrial mechanism model.

[0080] In this embodiment, when analyzing historical fault data, the number of times fault symptom i occurs due to fault cause j is counted, denoted as c. ij The number of fault causes is called the number of fault causes, which can be represented in matrix form as follows:

[0081]

[0082] In this embodiment, the conversion formula is expressed as:

[0083]

[0084] In formula (3), the subscript i represents a certain fault symptom, the subscript j represents a certain fault cause, and h ij c represents a parameter in the fault cause frequency transformation matrix. nj The parameter in the fault cause frequency matrix is ​​called the fault cause frequency, and T is a transformation constant.

[0085] In this embodiment, T is set to 10000.

[0086] The transformed fault cause frequency transformation matrix is ​​represented as follows:

[0087]

[0088] In this embodiment, the optimization formula is expressed as:

[0089]

[0090] In formula (5), the subscript i represents a certain fault symptom, the subscript j represents a certain fault cause, and r ij c represents the parameters in the optimized industrial mechanism model. ij and h ij These represent the parameters in the fault cause frequency matrix and the fault cause frequency transformation matrix, respectively.

[0091] In this embodiment, when using an industrial equipment fault diagnosis method to diagnose the cause of an existing equipment fault, the acquired equipment data is the equipment data after the equipment fault occurred.

[0092] In this embodiment, after optimizing the industrial mechanism model a preset number of times, the optimized industrial mechanism model is used to predict faults in the real-time acquired equipment data. That is, when the industrial mechanism model achieves high accuracy after multiple optimization iterations, it can be used to monitor the data uploaded by industrial equipment in real time, thereby enabling timely detection of faults and the implementation of appropriate measures.

[0093] Because this method involves significant latency when invoking the corresponding industrial mechanism model, its implementation in traditional systems may render it unsuitable for certain time-critical scenarios. Therefore, this paper also presents a dynamically optimized industrial equipment fault diagnosis system that implements the above method. This system includes multiple device endpoints, edge endpoints, and a cloud endpoint.

[0094] In this embodiment, the industrial equipment fault diagnosis system adopts an edge collaboration model, which is a computing, communication, and collaboration mode. In this model, edge devices (such as sensors and IoT devices) perform data processing, analysis, and decision-making locally, instead of transmitting all data to a central server for processing. The goal of this model is to achieve faster response times, lower network bandwidth requirements, and better privacy protection on edge devices. The core idea of ​​edge collaboration is to move some data processing tasks from the traditional cloud computing model to edge devices closer to the data source. These devices can perform some data processing, filtering, and analysis locally, transmitting only the necessary key information to the cloud for further processing. This model can reduce the load on cloud servers, reduce network latency, and improve system real-time performance, especially for applications requiring rapid response, such as industrial automation, intelligent transportation, and medical diagnosis.

[0095] At the same time, edge collaboration can also bring privacy and security advantages, because not all data needs to be transmitted to the cloud. Edge devices can perform data anonymization, encryption and protection locally, thereby reducing the potential risk of data leakage.

[0096] In this embodiment, the industrial equipment fault diagnosis system collects equipment data from each device and sends the data to the edge device. Then, the edge device acquires the equipment data from the industrial equipment, generates a fault symptom vector based on the data, and diagnoses the fault using an industrial mechanism model corresponding to the industrial equipment, thereby obtaining the cause of the fault and achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0097] After investigating the cause of the fault on the device, the actual cause of the fault will be obtained, and this data will be fed back to the edge device.

[0098] After obtaining the actual cause of the fault, the edge device constructs a fault history data corresponding to the industrial equipment based on the actual cause of the fault and the fault symptom vector, and then sends the fault history data to the cloud.

[0099] Then, the cloud optimizes the parameters in the corresponding industrial mechanism model based on the historical fault data of a certain type of industrial equipment to obtain the optimized industrial mechanism model, and sends the optimized industrial mechanism model to the edge.

[0100] Finally, at the edge, the optimized industrial mechanism model is used to replace the current model, and the optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment. The steps for implementing the above diagnostic method based on this edge collaborative system can be referenced as follows: Figure 2 As shown.

[0101] In this embodiment, each device can be used to collect data from multiple different types of industrial equipment, or it can be used to collect data from multiple identical devices.

[0102] Next, taking industrial equipment relays as an example, when constructing the industrial mechanism model, based on industry experience and expert experience, the fault symptom set is set as {x1 = no current, x2 = overload current, x3 = poor input / output reset, x4 = insufficient insulation between input and output}, and the fault cause set is set as {y1 = open circuit, y2 = short circuit, y3 = insulation aging, y4 = foreign matter contamination}. The fuzzy matrix is ​​then constructed as follows:

[0103]

[0104] The model is then distributed to the edge and deployed and run on edge computing nodes.

[0105] The device collects relevant data through sensors to form a fault feature vector. Suppose that the feature vector obtained at a certain moment is V = {1, 1, 0, 0}.

[0106] The fault cause vector V = {0.4, 1, 0, 0} is calculated using the industrial mechanism model. The most likely cause of the fault is predicted to be y2, i.e., a short circuit.

[0107] Next, through manual investigation, it was found that the actual fault was a short circuit in y1. The final recorded result format is ({0.4, 1, 0, 0}, {0.4, 1, 0, 0}, y1, timestamp), and this result is saved in the edge computing node.

[0108] At the edge computing nodes, recorded data for a certain period of time is periodically transmitted to the cloud, and the cloud stores the data to form historical fault data.

[0109] The cloud-based system periodically optimizes the parameters of the artificial mechanism model. Assuming the number of failures is statistically analyzed from the model's historical failure database and represented in matrix form:

[0110]

[0111] Set the transformation constant T = 10000, and obtain the number of fault causes for the initial matrix parameter transformation:

[0112]

[0113] The final fuzzy matrix, which is the iteratively optimized industrial mechanism model, is as follows:

[0114]

[0115] In the cloud, a new industrial mechanism model is formed after parameter optimization. The cloud then distributes the updated industrial mechanism model to the edge through model distribution management, and performs a new round of model iteration and optimization.

[0116] The aforementioned dynamic optimization-based industrial equipment fault diagnosis method generates fault symptom vectors based on acquired industrial equipment data. A corresponding industrial mechanism model is then used to diagnose the fault based on these symptom vectors, identifying the fault cause and thus diagnosing the industrial equipment. Simultaneously, the data from this diagnosis, along with the actual fault cause, is used to construct historical fault data. This historical data is then used to optimize and iterate the parameters in the industrial mechanism model, making the diagnostic results more accurate in subsequent fault diagnoses. This method allows for rapid identification of the fault cause and source, facilitating targeted repairs and enabling the equipment to return to operational status more quickly. Furthermore, the industrial mechanism model is continuously optimized and iterated using each diagnostic data iteration, leading to increasingly accurate fault diagnosis results. This method can also diagnose the causes of existing industrial equipment faults and enable real-time monitoring of various industrial equipment for timely fault detection.

[0117] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0118] In one embodiment, such as Figure 3 As shown, a fault diagnosis device for industrial equipment based on dynamic optimization is provided, including: a data acquisition module 200, a fault cause diagnosis module 210, a fault history data construction module 220, an industrial mechanism model optimization module 230, and an optimized model fault diagnosis module 240, wherein:

[0119] Data acquisition module 200 is used to acquire equipment data of industrial equipment and generate fault symptom vectors based on the equipment data;

[0120] The fault cause diagnosis module 210 is used to diagnose the fault by adopting an industrial mechanism model corresponding to the industrial equipment and based on the fault symptom vector to obtain the fault cause in order to diagnose the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0121] The fault history data construction module 220 is used to obtain the actual fault cause and construct the fault history data corresponding to the industrial equipment based on the actual fault cause and fault symptom vector.

[0122] The industrial mechanism model optimization module 230 is used to optimize the parameters in the corresponding industrial mechanism model based on the fault history data of a certain type of industrial equipment, so as to obtain the optimized industrial mechanism model.

[0123] The optimized model fault diagnosis module 240 is used to perform the next fault diagnosis on the corresponding industrial equipment using the optimized industrial mechanism model.

[0124] Specific limitations regarding the dynamic optimization-based industrial equipment fault diagnosis device can be found in the limitations of the dynamic optimization-based industrial equipment fault diagnosis method described above, and will not be repeated here. Each module in the aforementioned dynamic optimization-based industrial equipment fault diagnosis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0125] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a dynamic optimization-based industrial equipment fault diagnosis method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0126] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0127] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0128] Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data;

[0129] By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0130] Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector.

[0131] The parameters in the corresponding industrial mechanism model are optimized based on the historical failure data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0132] The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

[0133] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0134] Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data;

[0135] By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics.

[0136] Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector.

[0137] The parameters in the corresponding industrial mechanism model are optimized based on the historical failure data of a certain type of industrial equipment to obtain the optimized industrial mechanism model.

[0138] The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

[0139] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0140] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0141] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for fault diagnosis of industrial equipment based on dynamic optimization, characterized in that, The method includes: Acquire equipment data from industrial equipment, and generate fault symptom vectors based on the equipment data; By employing an industrial mechanism model corresponding to the industrial equipment, fault diagnosis is performed based on fault symptom vectors to obtain the cause of the fault, thereby achieving the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics; the industrial mechanism model uses a fuzzy relation matrix to characterize the relationship between various fault causes and various fault symptom manifestations. Obtain the true cause of the fault, and construct the corresponding historical fault data of the industrial equipment based on the true cause of the fault and the fault symptom vector. Based on historical fault data of a certain type of industrial equipment, the parameters in the fuzzy relation matrix of the corresponding industrial mechanism model are optimized to obtain an optimized industrial mechanism model. The optimization steps include: statistically analyzing the number of times a certain fault symptom occurs due to a certain fault cause in the historical fault data, constructing a fault cause frequency matrix; converting the parameters of the current industrial mechanism model into a corresponding equivalent frequency matrix using a preset conversion formula; and adjusting each parameter in the fuzzy relation matrix according to the fault cause frequency matrix and the equivalent frequency matrix using a preset optimization formula. The optimized industrial mechanism model is used to perform the next fault diagnosis on the corresponding industrial equipment.

2. The industrial equipment fault diagnosis method according to claim 1, characterized in that, The equipment data of the industrial equipment refers to data related to the manifestation of fault symptoms.

3. The industrial equipment fault diagnosis method according to claim 1, characterized in that, The conversion formula is expressed as follows: In the above formula, the subscript This indicates a certain type of fault symptom, indicated by the subscript. This indicates a specific cause of the malfunction. This is represented by a parameter in the fault cause frequency transformation matrix. A parameter in the fault cause frequency matrix is ​​called the fault cause frequency. This is represented as a conversion constant.

4. The industrial equipment fault diagnosis method according to claim 1, characterized in that, The optimization formula is expressed as follows: In the above formula, the subscript This indicates a certain type of fault symptom, indicated by the subscript. This indicates a specific cause of the malfunction. These are the parameters in the optimized industrial mechanism model. and These represent the parameters in the fault cause frequency matrix and the fault cause frequency transformation matrix, respectively.

5. The industrial equipment fault diagnosis method according to any one of claims 1-4, characterized in that, When the industrial equipment fault diagnosis method described above is used to diagnose the cause of an existing equipment fault, the acquired equipment data is the equipment data after the equipment fault occurred.

6. The industrial equipment fault diagnosis method according to claim 5, characterized in that, The industrial equipment fault diagnosis method also includes: After optimizing the industrial mechanism model a preset number of times, the optimized industrial mechanism model is used to predict faults in the real-time acquired equipment data.

7. An industrial equipment fault diagnosis system based on dynamic optimization, characterized in that, The system includes multiple device terminals, edge terminals, and the cloud; Each of the aforementioned device terminals is used to collect device data and send the device data to the edge terminal; The edge device is used to acquire equipment data of industrial equipment, generate fault symptom vectors based on the equipment data, and diagnose faults by using an industrial mechanism model corresponding to the industrial equipment based on the fault symptom vectors to obtain the cause of the fault and thus achieve the diagnosis of the industrial equipment. The industrial mechanism model is constructed based on fuzzy mathematics; the industrial mechanism model uses a fuzzy relation matrix to represent the relationship between various fault causes and various fault symptom manifestations. The edge device is used to obtain the actual cause of the fault, construct the fault history data corresponding to the industrial equipment based on the actual cause of the fault and the fault symptom vector, and send the fault history data to the cloud. The cloud-based system is used to optimize the parameters in the corresponding industrial mechanism model based on historical fault data of a certain type of industrial equipment, obtaining an optimized industrial mechanism model, and then sending the optimized industrial mechanism model to the edge device. The optimization steps include: counting the number of times a certain fault symptom occurs due to a certain fault cause in the historical fault data, constructing a fault cause frequency matrix; converting the parameters of the current industrial mechanism model into a corresponding equivalent frequency matrix using a preset conversion formula; and adjusting the parameters in the fuzzy relation matrix according to the fault cause frequency matrix and the equivalent frequency matrix using a preset optimization formula. The edge terminal is used to perform the next fault diagnosis on the corresponding industrial equipment using the optimized industrial mechanism model.

Images