An industrial equipment fault prediction method and device, electronic equipment and storage medium

Abstract

The application discloses an industrial equipment fault prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining fault data and steady-state data in the operation process of the industrial equipment; using a pre-set naive Bayes model to process the fault data and the steady-state data to obtain an accuracy coefficient; wherein the accuracy coefficient comprises overall classification accuracy and a Kappa coefficient; determining a fault prior probability and a fault conditional probability associated with the accuracy coefficient, and calculating a posterior probability of the industrial equipment failure according to the fault prior probability and the fault conditional probability. The technical scheme can discover potential fault risks of the equipment in time, so that the effect of solving the fault in advance is achieved, the maintenance cost is reduced, and economic losses are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial equipment failure prediction, and in particular to an industrial equipment failure prediction method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In the manufacturing industry, industrial equipment is one of the guarantees for the smooth completion of each process in the manufacturing process. In the field of civil aviation, various types of industrial equipment are involved in each process of aircraft manufacturing, and the smooth operation of the equipment is the basis for ensuring normal production, so the supervision of the equipment is particularly important.

[0003] However, in actual production, equipment is often repaired after receiving an equipment alarm.

[0004] This not only brings expensive maintenance and repair costs, but also affects the implementation of the production plan, thereby affecting the operation of the entire production system and causing serious economic losses. SUMMARY

[0005] The present application provides an industrial equipment failure prediction method and device, electronic equipment and a storage medium, which can timely discover potential failure risks of the equipment, thereby achieving the effect of solving the failure in advance, reducing maintenance costs and avoiding economic losses.

[0006] According to an aspect of the present application, an industrial equipment failure prediction method is provided, which comprises:

[0007] obtaining failure data and steady-state data in the operation process of the industrial equipment;

[0008] processing the failure data and steady-state data using a pre-set naive Bayes model to obtain an accuracy coefficient; wherein the accuracy coefficient comprises overall classification accuracy and a Kappa coefficient;

[0009] determining a failure prior probability and a failure conditional probability associated with the accuracy coefficient, and calculating a posterior probability of failure of the industrial equipment according to the failure prior probability and the failure conditional probability.

[0010] According to another aspect of the present application, an industrial equipment failure prediction device is provided, which comprises:

[0011] a data acquisition module for obtaining failure data and steady-state data in the operation process of the industrial equipment;

[0012] an accuracy coefficient obtaining module for processing the failure data and steady-state data using a pre-set naive Bayes model to obtain an accuracy coefficient; wherein the accuracy coefficient comprises overall classification accuracy and a Kappa coefficient;

[0013] The posterior probability calculation module is configured to determine a fault prior probability and a fault conditional probability associated with the precision coefficient, and calculate a posterior probability of the industrial equipment being faulty based on the fault prior probability and the fault conditional probability.

[0014] According to another aspect of the present application, there is provided an electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the industrial equipment fault prediction method according to any one of the embodiments of the present application.

[0018] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the industrial equipment fault prediction method according to any one of the embodiments of the present application when executed by the processor.

[0019] The technical solution of the embodiments of the present application obtains the fault data and the steady-state data in the operation process of the industrial equipment, and processes the fault data and the steady-state data by using the pre-set naive Bayes model to obtain the precision coefficient, wherein the precision coefficient comprises the overall classification precision and the Kappa coefficient, then determines the fault prior probability and the fault conditional probability associated with the precision coefficient, and calculates the posterior probability of the industrial equipment being faulty based on the fault prior probability and the fault conditional probability. The technical solution can timely find the potential fault risk of the equipment, thereby achieving the effect of solving the fault in advance, reducing the maintenance cost, and avoiding economic loss.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Figure 1is a flow chart of an industrial equipment fault prediction method according to an embodiment of the present application;

[0023] Figure 2 is a schematic diagram of an industrial equipment fault prediction process according to an embodiment of the present application;

[0024] Figure 3 is a flow chart of an industrial equipment fault prediction process according to an embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of an industrial equipment fault prediction device according to an embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of an electronic device for implementing an industrial equipment fault prediction method according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the personnel in the art without creative labor should belong to the scope of protection of the present application.

[0028] It should be noted that the terms "target" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment One

[0030] Figure 1is a flow chart of an industrial equipment failure prediction method according to an embodiment of the present application. The embodiment can be applied to predict the failure of each industrial equipment. The method can be executed by an industrial equipment failure prediction device which can be realized in the form of hardware and / or software. The industrial equipment failure prediction device can be configured on any electronic device with network communication function, including but not limited to computers, personal digital assistants and the like. As shown in Figure 1 the method comprises the following steps.

[0031] S110, obtaining failure data and steady state data in the running process of the industrial equipment.

[0032] In the embodiment, as the data generated by the industrial equipment is increasing, the running environment of the equipment is becoming more and more complex, and the coupling and correlation between system elements cause the state information of each element to be related to each other. Each data in the running process of the industrial equipment will have a certain influence on the failure of the industrial equipment. Therefore, the influence of each data on the failure of the industrial equipment needs to be considered comprehensively, the potential relationship between each data and the failure of the industrial equipment needs to be mined, and the possibility of equipment failure at a future time can be effectively predicted.

[0033] The industrial equipment can refer to various industrial equipment in each process of aircraft manufacturing. For example, the industrial equipment can refer to a paint spraying mechanical arm, a machine tool and the like.

[0034] In the embodiment, the state of the industrial equipment is divided into two types of failure and steady state. The failure data and the steady state data both include voltage, current, vibration, torque, speed, temperature, humidity and the like. The real-time state data of the equipment can be continuously obtained based on the sensors installed on the industrial equipment. That is, the failure data and the steady state data in the running process of the industrial equipment are obtained in real time.

[0035] In the technical solution, the steady state data in the running process of the industrial equipment can be obtained, comprising:

[0036] obtaining to-be-processed steady state data in the running process of the industrial equipment;

[0037] processing the to-be-processed steady state data by using a pre-set random undersampling technology to obtain steady state data; wherein the number of the steady state data is the same as the number of the failure data.

[0038] In the embodiment, for the equipment for real-time monitoring, time series data is generated, which is a data column of the same index recorded in time sequence, and the time series data related to the operation of the equipment is a series of observation data acquired over time during the operation stage of the equipment. The amount of time series data is huge, and in most of the time, the equipment is in a stable operation state, and only a small part of the time will have an alarm failure. Therefore, the amount of stable state data collected is much more than that of failure data.

[0039] Specifically, the random undersampling technology can be used to process the collected stable state data to be processed to obtain stable state data with the same number of failure data.

[0040] By using the random undersampling technology to process the stable state data to be processed, the imbalance problem of industrial equipment data can be solved, and the accuracy of failure prediction is improved.

[0041] S120, using a pre-set naive Bayes model to process the failure data and the stable state data to obtain an accuracy coefficient; wherein the accuracy coefficient includes overall classification accuracy and Kappa coefficient.

[0042] The overall classification accuracy (Overall Accuracy, OA) is used to represent the proportion of the number of correctly classified samples to the total number of samples. The Kappa coefficient is an index for consistency test and can also be used to measure the effect of classification.

[0043] In the embodiment, the naive Bayes model is based on the Bayes theorem and assumes that the features are independent of each other. First, given the training set, the independence between feature words is assumed as a premise, the joint probability distribution from input to output is learned, and then based on the learned model, the feature attribute set of the sample data is input to obtain the output with the maximum posterior probability.

[0044] Specifically, the set naive Bayes model can be used to classify and process the failure data and the stable state data to obtain the classification results of the failure data and the stable state data, and the accuracy coefficient is calculated based on the classification results.

[0045] In the technical solution, the pre-set naive Bayes model is used to process the failure data and the stable state data to obtain the accuracy coefficient, which includes:

[0046] According to the failure data and the stable state data, training samples and test samples are determined;

[0047] The pre-set naive Bayes model is used to process the training samples and the test samples to obtain a confusion matrix;

[0048] According to a preset calculation formula, sample classification data in the confusion matrix is calculated to obtain an accuracy coefficient.

[0049] In the scheme, a random sample table can be formed based on the fault data and the steady state data, and the training sample and the test sample can be set according to the random sample table. For example, 80% of the samples in the random sample table can be selected as the training sample, and 20% of the samples in the random sample table can be selected as the test sample.

[0050] Specifically, the training sample and the test sample are classified by using the pre-set naive Bayes model, the posterior probability of the test sample is predicted, and then the predicted posterior probability of the test sample is compared with the real posterior probability to construct a confusion matrix.

[0051] The confusion matrix, also known as an error matrix, is a standard format for identifying accuracy evaluation and is represented by an n-row n-column matrix. The confusion matrix includes steady state samples TP classified correctly by the model, steady state samples FN classified incorrectly by the model, fault samples FP classified incorrectly by the model, and fault samples TN classified correctly by the model.

[0052] The overall classification accuracy is calculated by dividing the total number of correctly classified pixels by the total number of pixels. The number of correctly classified pixels is distributed along the diagonal of the confusion matrix, and the total number of pixels is equal to the total number of all real reference pixels.

[0053] Specifically, the overall classification accuracy is calculated by using the following formula:

[0054] Or,

[0055] Wherein, x ii represents correctly classified pixels, and N represents the total number of all real reference pixels.

[0056] In the embodiment, the Kappa coefficient can be obtained by multiplying the total number of all real reference pixels N by the sum of the diagonal x ii of the confusion matrix, subtracting the product of the real reference pixel number x i+ in each category and the total number of classified pixels x +i in the category, and then dividing the result by the square of the total number of pixels N minus the product of the real reference pixel number x i+ in each category and the total number of classified pixels x +i in the category.

[0057] Specifically, the Kappa coefficient is calculated by using the following formula:

[0058]

[0059] By calculating the accuracy coefficient, more optimal sample data can be selected based on the accuracy coefficient for fault prediction, and the accuracy of fault prediction is improved.

[0060] In the technical solution, the training sample and the test sample are processed by using the preset naive Bayes model to obtain a confusion matrix, including:

[0061] The training sample is processed by using the preset naive Bayes model to obtain the prior probability and the conditional probability of the training sample.

[0062] The posterior probability of the test sample is calculated based on the prior probability and the conditional probability of the training sample.

[0063] The posterior probability of the test sample is compared with the real posterior probability determined in advance to obtain sample classification data, and the confusion matrix is constructed based on the sample classification data.

[0064] Specifically, the prior probability and the conditional probability of the corresponding training sample can be selected according to the data in the test sample, and the posterior probability of different data in different test samples is calculated based on the prior probability and the conditional probability of the training sample.

[0065] In the embodiment, if the posterior probability of the test sample is the same as the real posterior probability determined in advance, the sample classification is correct, which can be represented by a number, and if the posterior probability of the test sample is different from the real posterior probability determined in advance, the sample classification is incorrect, which can also be represented by a number.

[0066] By calculating the accuracy coefficient, more optimal sample data can be selected based on the accuracy coefficient for fault prediction, and the accuracy of fault prediction is improved.

[0067] S130, determine the fault prior probability and the fault conditional probability associated with the accuracy coefficient, and calculate the posterior probability of the industrial equipment failure according to the fault prior probability and the fault conditional probability.

[0068] The fault prior probability and the fault conditional probability are obtained by processing the training sample and the test sample based on the naive Bayes model in advance.

[0069] In the embodiment, the fault prior probability and the fault conditional probability associated with the accuracy coefficient can be obtained by searching the sample table based on the accuracy coefficient.

[0070] In the solution, the posterior probability of the fault occurring in different states in the future is further calculated based on the fault prior probability and the fault conditional probability, and the calculation formula is as follows:

[0071]

[0072]

[0073] Wherein, Y={y0, y1}, y0 represents a steady state, and y1 represents a fault. a 11 ,b 11 ,....,f 11 ,g 11 are states of respective indexes. Based on the above probabilities, a probability calculation method of the fault occurrence is as follows:

[0074]

[0075] In the scheme, after obtaining the fault posterior probability, the industrial equipment can be checked in advance according to the size of the fault posterior probability, the fault maintenance cost is reduced, and certain economic losses caused by the use of the industrial equipment are avoided. For example, when it is predicted that the fault posterior probability of the industrial equipment is 80%, the fault of the industrial equipment is checked.

[0076] In the technical scheme, optionally, after obtaining the precision coefficient, the method further comprises:

[0077] comparing the precision coefficient with a preset threshold value to obtain a target precision coefficient;

[0078] Correspondingly, determining the fault prior probability and the fault conditional probability associated with the precision coefficient comprises:

[0079] determining the fault prior probability and the fault conditional probability associated with the target precision coefficient.

[0080] The preset threshold value includes an OA threshold value and a Kappa threshold value, and the size of the preset threshold value can be set according to the industrial equipment fault prediction requirement. For example, the OA threshold value can be set to 0.8, and the Kappa threshold value can be set to 0.6.

[0081] Specifically, the precision coefficient greater than or equal to the preset threshold value can be taken as the target precision coefficient. That is, the precision coefficient with OA greater than or equal to 0.8 and Kappa greater than or equal to 0.6 is taken as the target precision coefficient.

[0082] In the scheme, if the precision coefficient obtained based on the steady state data and the fault data does not meet the constraint of the preset threshold value, the steady state data can be adjusted, and the cycle is continued to find the target precision coefficient meeting the constraint of the preset threshold value. The number of cycles can be set according to the industrial equipment fault prediction requirement, for example, the number of cycles can be set to 10000. That is, after the number of cycles is exceeded, the steady state data is not adjusted.

[0083] By determining the target precision coefficient, the fault prior probability and the fault conditional probability with better performance can be obtained.

[0084] In the technical solution, the failure prior probability and the failure conditional probability associated with the target accuracy coefficient are determined, including:

[0085] According to the target accuracy coefficient, a sample table associated with the target accuracy coefficient is determined.

[0086] The failure prior probability and the failure conditional probability associated with the target accuracy coefficient are obtained by searching the sample table.

[0087] The target accuracy coefficient, the failure prior probability and the failure conditional probability are stored in the sample table, and the failure prior probability and the failure conditional probability associated with the target accuracy coefficient can be obtained by searching the sample table according to the target accuracy coefficient.

[0088] Specifically, the sample table with the maximum target accuracy coefficient can be selected as the optimal sample table, and the failure prior probability and the failure conditional probability stored in the optimal sample table are extracted.

[0089] By determining the failure prior probability and the failure conditional probability, potential failure risks of the equipment can be found in time, so that the effect of solving the failure in advance is achieved, the maintenance cost is reduced, and economic losses are avoided.

[0090] Exemplarily, Figure 2 is a schematic diagram of an industrial equipment failure prediction process provided by Embodiment One of the present application, as shown in Figure 2 The industrial equipment is divided into two types of failure and steady state, and indicators such as voltage, current, vibration, torque, speed, temperature and humidity are selected and brought into a naive Bayes model for training, and then the training result is substituted into the model for failure prediction.

[0091] Exemplarily, Figure 3 is a flowchart of an industrial equipment failure prediction process provided by Embodiment One of the present application, as shown in Figure 3 First, random undersampling processing is performed to obtain steady state data B and failure data A; a random sample table M is constructed based on the steady state data and the failure data; training samples and test samples are set; a naive Bayes model probability is calculated; accuracy coefficients (OA and Kappa) are calculated; it is judged whether OA is greater than or equal to 0.8 and Kappa is greater than or equal to 0.6; if yes, the sample table corresponding to the accuracy coefficient is stored; the optimal sample table is selected from the sample table; the posterior probability is calculated; and the equipment failure risk is calculated. If no, the steady state data is adjusted and the calculation is continued until the loop ends.

[0092] The technical scheme of the embodiment of the present application obtains fault data and steady state data in the running process of the industrial equipment, and processes the fault data and the steady state data by using a pre-set naive Bayes model to obtain a precision coefficient; wherein the precision coefficient comprises overall classification precision and a Kappa coefficient; then the fault prior probability and the fault conditional probability associated with the precision coefficient are determined, and the posterior probability of the fault of the industrial equipment is calculated according to the fault prior probability and the fault conditional probability. By executing the technical scheme, the real-time prediction of the fault risk in the running process of the industrial equipment can be realized, so that the effect of solving the fault in advance is achieved, the maintenance cost is reduced, and economic loss is avoided.

[0093] Embodiment two

[0094] Figure 4 is a structural schematic diagram of an industrial equipment fault device provided according to the embodiment two of the present application. As shown in the figure, the device comprises: Figure 4 The data acquisition module 410 is configured to acquire fault data and steady state data in the running process of the industrial equipment.

[0095] The precision coefficient obtaining module 420 is configured to process the fault data and the steady state data by using a pre-set naive Bayes model to obtain a precision coefficient; wherein the precision coefficient comprises overall classification precision and a Kappa coefficient.

[0096] The posterior probability calculation module 430 is configured to determine the fault prior probability and the fault conditional probability associated with the precision coefficient, and calculate the posterior probability of the fault of the industrial equipment according to the fault prior probability and the fault conditional probability.

[0097] In the technical scheme, the data acquisition module 410 can be configured to:

[0098] acquire to-be-processed steady state data in the running process of the industrial equipment;

[0099] process the to-be-processed steady state data by using a pre-set random undersampling technology to obtain the steady state data; wherein the number of the steady state data is the same as the number of the fault data.

[0100] In the technical scheme, the precision coefficient obtaining module 420 can comprise:

[0101] a sample determining unit configured to determine training samples and test samples according to the fault data and the steady state data;

[0102] a confusion matrix obtaining unit configured to process the training samples and the test samples by using a pre-set naive Bayes model to obtain a confusion matrix.

[0103] In the technical scheme, the precision coefficient obtaining module 420 can comprise:

[0104] The precision coefficient obtaining unit is configured to calculate the sample classification data in the confusion matrix according to a preset calculation formula to obtain a precision coefficient.

[0105] In the technical solution, the confusion matrix obtaining unit is specifically configured to:

[0106] The training sample is processed by using the preset naive Bayes model to obtain a prior probability and a conditional probability of the training sample.

[0107] The posterior probability of the test sample is calculated based on the test sample, the prior probability and the conditional probability of the training sample.

[0108] The posterior probability of the test sample is compared with a predetermined true posterior probability to obtain sample classification data, and the confusion matrix is constructed based on the sample classification data.

[0109] In the technical solution, the device further includes:

[0110] The target precision coefficient obtaining module is configured to compare the precision coefficient with a preset threshold to obtain a target precision coefficient.

[0111] Correspondingly, the posterior probability calculating module 430 includes:

[0112] The fault probability determining unit is configured to determine a fault prior probability and a fault conditional probability associated with the target precision coefficient.

[0113] In the technical solution, the fault probability determining unit is specifically configured to:

[0114] The sample table associated with the target precision coefficient is determined according to the target precision coefficient.

[0115] The fault prior probability and the fault conditional probability associated with the target precision coefficient are obtained by searching the sample table.

[0116] The industrial equipment fault prediction device provided in the embodiment of the application can execute the industrial equipment fault prediction method provided in any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0117] Embodiment three

[0118] Figure 5A structural diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0119] As shown in Figure 5 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0120] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0121] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as an industrial equipment failure prediction method.

[0122] In some embodiments, an industrial equipment failure prediction method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of an industrial equipment failure prediction method as described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform an industrial equipment failure prediction method by other means, e.g., with the aid of firmware.

[0123] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0124] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0125] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0127] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0128] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0129] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0130] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting industrial equipment failures, characterized in that, include: Acquire fault data and steady-state data during the operation of industrial equipment; The fault data and steady-state data are processed using a pre-set Naive Bayes model to obtain accuracy coefficients; wherein, the accuracy coefficients include the overall classification accuracy and the Kappa coefficient; The fault data and steady-state data are processed using a pre-set Naive Bayes model to obtain accuracy coefficients, including: Based on the fault data and steady-state data, training samples and test samples are determined; The training and test samples are processed using a pre-defined Naive Bayes model to obtain a confusion matrix. This process includes: processing the training samples using the pre-defined Naive Bayes model to obtain the prior and conditional probabilities of the training samples; calculating the posterior probability of the test samples based on the prior and conditional probabilities of the test samples and the training samples; comparing the posterior probability of the test samples with the pre-determined true posterior probability to obtain sample classification data; and constructing a confusion matrix based on the sample classification data. The accuracy coefficient is obtained by calculating the sample classification data in the confusion matrix according to the preset calculation formula. Determine the prior probability and conditional probability of failure associated with the accuracy coefficient, and calculate the posterior probability of industrial equipment failure based on the prior probability and conditional probability of failure.

2. The method according to claim 1, characterized in that, Acquire steady-state data during the operation of industrial equipment, including: Acquire steady-state data to be processed during the operation of industrial equipment; The steady-state data to be processed is obtained by using a pre-set random undersampling technique; wherein the number of steady-state data is the same as the number of fault data.

3. The method according to claim 1, characterized in that, After obtaining the accuracy coefficient, the method further includes: The accuracy coefficient is compared with a preset threshold to obtain the target accuracy coefficient; Accordingly, determining the prior probability and conditional probability of the fault associated with the accuracy coefficient includes: Determine the prior probability and conditional probability of the fault associated with the target accuracy coefficient.

4. The method according to claim 3, characterized in that, Determining the prior probability and conditional probability of the fault associated with the target accuracy coefficient includes: Based on the target accuracy coefficient, a sample table associated with the target accuracy coefficient is determined; the fault priors associated with the target accuracy coefficient are obtained by searching the sample table. Probability and fault condition probability.

5. An industrial equipment fault prediction device, characterized in that, include: The data acquisition module is used to acquire fault data and steady-state data during the operation of industrial equipment; The accuracy coefficient acquisition module is used to process the fault data and steady-state data using a pre-set Naive Bayes model to obtain accuracy coefficients; wherein, the accuracy coefficients include the overall classification accuracy and the Kappa coefficient; The accuracy coefficient obtaining module includes: The sample determination unit is used to determine training samples and test samples based on the fault data and steady-state data. The confusion matrix obtaining unit is used to process the training samples and test samples using a pre-set Naive Bayes model to obtain a confusion matrix. Specifically, the confusion matrix obtaining unit is used to process the training samples using a pre-set Naive Bayes model to obtain the prior probability and conditional probability of the training samples; based on the prior probability and conditional probability of the test samples and the training samples, the posterior probability of the test samples is calculated; the posterior probability of the test samples is compared with the pre-determined true posterior probability to obtain sample classification data, and a confusion matrix is ​​constructed based on the sample classification data. The precision coefficient obtaining unit is used to calculate the precision coefficient of the sample classification data in the confusion matrix according to a preset calculation formula; The posterior probability calculation module is used to determine the prior probability and conditional probability of the fault associated with the accuracy coefficient, and to calculate the posterior probability of the industrial equipment failing based on the prior probability and conditional probability of the fault.

6. The apparatus according to claim 5, characterized in that, The data acquisition module is specifically used for: Acquire steady-state data to be processed during the operation of industrial equipment; The steady-state data to be processed is obtained by using a pre-set random undersampling technique; wherein the number of steady-state data is the same as the number of fault data.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform an industrial equipment fault prediction method according to any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the industrial equipment fault prediction method according to any one of claims 1-4.

Images