Data processing method and device based on fault diagnosis and medium

Abstract

The invention discloses a data processing method and device based on fault diagnosis and a medium, and the method comprises the steps: collecting operation data of factory equipment, carrying out the feature reconstruction of the operation data to obtain sample data, and storing the sample data in a preset database; acquiring sample data in the database, taking the sample data as a test sample, performing data analysis on the test sample through a preset analysis model to obtain diagnosis information, determining a fault level of the factory equipment according to the diagnosis information, and comparing the fault level with a preset level threshold; if the fault level is smaller than a level threshold value, updating the analytical model according to diagnosis information corresponding to the fault level; and if the fault level is greater than or equal to the level threshold value, determining a maintenance scheme corresponding to the factory equipment according to the diagnosis information, and maintaining the factory equipment according to the maintenance scheme. According to the method, intelligent analysis is carried out on the data, and accurate prediction and decision support is provided.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, device and medium based on fault diagnosis. Background Art

[0002] With the rapid development of the Internet and information technology, the era of big data has arrived. In this era, the big data interactive artificial intelligence (AI) application platform came into being and became an important achievement of the new generation of information technology. The AI-based data intelligence technology architecture has been widely used in many industries, such as industrial equipment manufacturing. Consumables such as factory equipment are necessities required in the field of industrial production. In the daily industrial production process, the operating status of factory equipment needs to be monitored in real time, and the remaining life of spare parts needs to be reasonably predicted to ensure the safety and reliability of mechanical equipment operation. However, at present, most of the spare parts are regularly inspected by manpower or monitoring equipment, such as cameras, and then the failure of factory equipment is estimated. Monitoring spare parts in the above way has poor reliability and high cost, which makes it difficult to apply to the industrial field. Summary of the invention

[0003] In order to solve the above problems, the present application proposes a data processing method based on fault diagnosis, including: collecting operating data of factory equipment, reconstructing features of the operating data to obtain sample data, and storing the sample data in a preset database; obtaining the sample data in the database to use the sample data as test samples, and performing data analysis on the test samples through a preset analytical model to obtain diagnostic information, determining a fault level of the factory equipment according to the diagnostic information, and comparing the fault level with a preset level threshold; if the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; if the fault level is greater than or equal to the level threshold, determining a maintenance plan corresponding to the factory equipment according to the diagnostic information, and repairing the factory equipment according to the maintenance plan.

[0004] In one example, feature reconstruction is performed on the operating data, specifically including: determining an original time series corresponding to the operating parameters, downsampling the original time series according to a plurality of pre-set time resolutions to obtain a feature sequence for characterizing the operating parameters; reconstructing the feature sequence in feature space to determine the difference between the sample data, to determine a reconstructed feature sequence according to the difference; determining a plurality of cluster center points according to the reconstructed feature sequence, to perform clustering according to the cluster center points, to determine clustered sample data.

[0005] In one example, before performing data analysis on the test sample through a preset analytical model, the method also includes: determining the original data based on the database, and determining multiple features of the original data; performing dimensionality reduction processing on the multiple features to obtain a training set, and determining the corresponding fault conditions based on the original data, and determining a verification set based on the fault conditions; inputting the training set into a predetermined neural network model to train the neural network model based on the training set, and correcting the trained neural network model based on the verification set, so as to obtain the analytical model.

[0006] In one example, the analytical model is updated according to the diagnostic information corresponding to the fault level, specifically including: determining an updated sample according to the diagnostic information corresponding to the fault level and the sample data, reconstructing features of the updated sample to obtain updated sample data, and storing the updated sample data in the database; determining an updated training set and an updated verification set according to the updated sample data, retraining the analytical model according to the updated training set, and correcting the neural network model after the retraining according to the updated verification set, thereby completing the update of the analytical model.

[0007] In one example, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, specifically including: determining a failure probability according to the diagnostic information, and comparing the failure probability with a preset threshold; if the failure probability is greater than the threshold, determining an alarm message, and sending the alarm message to a user interface to visualize the alarm message; determining a corresponding fault location according to the alarm information, and determining a corresponding maintenance plan according to the fault location, the maintenance plan including maintenance equipment, maintenance personnel, and maintenance time; determining the alarm number of the maintenance equipment according to the alarm information, and comparing the alarm number with a preset alarm number threshold; if the alarm number is greater than the alarm number threshold, replacing the maintenance equipment.

[0008] In one example, the method further includes: determining maintenance feedback information of the maintenance plan, and determining a maintenance result of the maintenance plan based on the maintenance feedback information; if the maintenance result shows that the fault has been resolved, updating relevant data in the database and recording maintenance success information; if the maintenance result shows that the fault has not been resolved, correcting the analytical model, and performing data analysis using the corrected analytical model to obtain new diagnostic information.

[0009] In one example, the method further includes: periodically analyzing the data in the database to determine the data change trend of the maintenance equipment; predicting faults based on the data change trend to determine the fault type and the probability of fault occurrence based on the prediction results; formulating a preventive maintenance plan based on the prediction results, and sending the preventive maintenance plan to a user interface to visualize the preventive maintenance plan.

[0010] In one example, the method further includes: determining a priority of the maintenance equipment, wherein the priority is determined based on the impact of the fault type, the fault probability, and the operational importance of the maintenance equipment; determining maintenance tasks according to the priority and the preventive maintenance plan, and sorting the maintenance tasks according to the priority to assign corresponding maintenance teams according to the sorted order, and generating a maintenance task list; displaying the maintenance task list through a user interface, and tracking the progress of the maintenance tasks to update and display the execution status of the maintenance tasks in real time.

[0011] On the other hand, the present application also proposes a data processing device based on fault diagnosis, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the data processing device based on fault diagnosis can execute: collecting operating data of factory equipment, reconstructing features of the operating data to obtain sample data, and storing the sample data in a pre-set database; obtaining the sample data in the database to use the sample data as a test sample, and performing data analysis on the test sample through a pre-set analytical model to obtain diagnostic information, determining the fault level of the factory equipment according to the diagnostic information, and comparing the fault level with a pre-set level threshold; if the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; if the fault level is greater than or equal to the level threshold, determining the maintenance plan corresponding to the factory equipment according to the diagnostic information, and repairing the factory equipment according to the maintenance plan.

[0012] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to: collect operating data of factory equipment, perform feature reconstruction on the operating data to obtain sample data, and store the sample data in a preset database; obtain the sample data in the database to use the sample data as a test sample, and perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine a fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; if the fault level is less than the level threshold, update the analytical model according to the diagnostic information corresponding to the fault level; if the fault level is greater than or equal to the level threshold, determine a maintenance plan corresponding to the factory equipment according to the diagnostic information, and repair the factory equipment according to the maintenance plan.

[0013] This application introduces AI models such as deep learning and machine learning to intelligently analyze data, provide accurate predictions and decision support, and help companies optimize operations and reduce costs. Through feature selection and engineering and advanced intelligent models, the health status of equipment can be accurately captured and faults can be effectively predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flowchart of a data processing method based on fault diagnosis in an embodiment of the present application; Figure 2 It is a schematic diagram of a data processing device based on fault diagnosis in an embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. 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 making creative work are within the scope of protection of the present application.

[0016] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0017] like Figure 1As shown, in order to solve the above problems, an embodiment of the present application provides a data processing method based on fault diagnosis, the method comprising: S101. Collect operating data of factory equipment, reconstruct features of the operating data to obtain sample data, and store the sample data in a preset database.

[0018] Use sensors, API interfaces, web crawlers and other technical means to collect data from multiple sources. For example, sensors installed on machines collect data in real time from equipment, data records provided by institutions, market indexes and other data to ensure the comprehensiveness and real-time nature of the data.

[0019] Preprocess the collected raw operation data, including data cleaning, noise removal, outlier removal, data transformation, such as standardization and normalization. Clean, deduplicate, and convert the collected data to improve data quality. At the same time, label data for specific industries and businesses. Choose appropriate data storage solutions, such as relational databases, non-relational databases, or distributed storage, to meet the needs of efficient data storage and access.

[0020] In one embodiment, the original time series is downsampled according to a plurality of preset time resolutions, such as per second, per minute, per hour, etc. Downsampling refers to selecting some data points from the original time series to reduce the sampling rate of the data. This process can capture the operating characteristics at different time scales. The feature space is reconstructed for the downsampled feature sequence. It involves transforming or combining the features to form a new and more representative feature set. The purpose of feature space reconstruction is to highlight the difference between sample data, that is, the distance or similarity between different samples in the feature space, which can be achieved by calculating the correlation between features, distance metrics, such as Euclidean distance, Manhattan distance, etc., or similarity metrics, such as cosine similarity. According to the difference, the feature sequence can be screened or recombined to obtain a reconstructed feature sequence, which can better reflect the changes and differences in the operating status of the equipment. Based on the reconstructed feature sequence, multiple cluster center points are determined. The cluster center point usually represents the center point of the sample data with similarity in the feature space. Clustering algorithms, such as K-means, DBSCAN, hierarchical clustering, etc., are used to cluster the sample data. The purpose of clustering is to classify similar sample data into the same category, thereby revealing different patterns or categories of equipment operating status. The clustered sample data can be used for further analysis and decision-making, such as equipment failure warning, performance evaluation, etc.

[0021] S102. Acquire the sample data in the database to use the sample data as a test sample, and perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold.

[0022] Retrieve or extract sample data from the database as test samples. Perform data analysis on the test samples using a pre-set and trained analytical model. The analytical model can be a machine learning model, such as a support vector machine SVM, a random forest RF, a neural network NN, etc. The task of the analytical model is to predict or diagnose the operating status or fault type of the equipment based on the input feature data, i.e., the test sample. The output result of the analytical model is the diagnostic information, including the specific fault type, fault probability, fault level, or the health status score of the equipment, etc. The diagnostic information should clearly and accurately reflect the current status of the equipment. According to the diagnostic information, determine the fault level of the factory equipment. The fault level can be a quantitative value, such as a score of 0-100, or a qualitative category, such as normal, minor fault, severe fault, etc. The fault level is determined based on the output of the analytical model and the preset fault level classification criteria. Compare the determined fault level with the pre-set level threshold. The level threshold is determined based on factors such as the equipment's operating requirements, maintenance strategies, and safety standards. If the fault level exceeds the level threshold, it may trigger an alarm, shutdown, maintenance, or other corresponding response measures. Take corresponding follow-up actions, including notifying maintenance personnel, adjusting equipment operating parameters, replacing faulty parts, etc. If the fault level does not exceed the level threshold, the new diagnostic information and fault level are fed back to the database to update the operation history and maintenance records of the equipment.

[0023] In one embodiment, before the test sample is analyzed by the pre-set analytical model, the original operation data of the equipment is retrieved from the database. These data usually contain multiple features, such as temperature, pressure, vibration, current, etc., which can reflect the operation status of the equipment. The selected multiple features are subjected to dimensionality reduction processing, that is, those features most relevant to the equipment failure are selected to reduce the complexity of the data and improve the training efficiency of the model. The dimensionality reduction techniques include principal component analysis (PCA), linear discriminant analysis (LDA), t-SNE, etc. Through dimensionality reduction processing, a simplified feature set can be obtained, which can still retain most of the useful information in the original data. According to the original data and the corresponding fault conditions, the data set is divided into a training set and a validation set. The training set is used to train the neural network model, while the validation set is used to evaluate the performance of the model and make corrections. The fault conditions can be obtained through the historical maintenance records of the equipment, expert judgment or other methods. The training set is input into a predetermined neural network model. The neural network model can be a multi-layer perceptron (MLP), a convolutional neural network (CNN), a recurrent neural network (RNN), etc. The neural network model is trained using the training set, that is, the parameters of the model are adjusted to minimize the prediction error. During the training process, cross-validation and other techniques are used to avoid overfitting. After training, the model is calibrated using the validation set to adjust the model's parameters and improve its generalization ability on unseen data. After training and calibration, the final parsing model is obtained, which can receive the device's feature data as input and output the device's fault diagnosis results.

[0024] S103: If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level.

[0025] In one embodiment, new sample data are collected from actual operation according to the fault level of the device and the corresponding diagnostic information. These sample data contain the operating characteristics of the device and the corresponding fault labels or categories to ensure that these new sample data are representative and can reflect the operating status of the device under different fault levels. The collected update samples are feature reconstructed, and the reconstructed update sample data are stored in the database to help maintain the consistency and integrity of the data. An update training set and an update verification set are divided from the update sample data. The update training set is used to perform secondary training on the neural network model, including adjusting the parameters of the model to adapt to the new data distribution and feature structure, while the update verification set is used to evaluate the performance of the model and make corrections. In the secondary training process, a training strategy and optimization algorithm similar to the initial training are adopted. The neural network model after secondary training is corrected using the update verification set, the purpose of which is to adjust the parameters of the model to improve its prediction accuracy on unseen data. By comparing the prediction results of the model on the update verification set with the actual fault labels, the performance of the model can be evaluated and it can be determined whether further adjustment and optimization are needed. After secondary training and correction, an updated analytical model is obtained. This model can better adapt to the new data distribution and feature structure and improve the accuracy and reliability of fault diagnosis.

[0026] S104: If the fault level is greater than or equal to the level threshold, determine a maintenance plan corresponding to the factory equipment according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

[0027] In one embodiment, the probability of a device failure is calculated using a trained analytical model based on the diagnostic information of the device. The calculated failure probability is compared with a preset failure probability threshold. If the failure probability is greater than the threshold, the device is considered to have a high risk of failure. When the failure probability exceeds the threshold, alarm information, such as the type of failure, severity, etc., is determined. The alarm information is sent to the user interface and displayed to the user in a visual manner so that the user can quickly understand the failure of the device. Based on the alarm information, the specific location of the fault is further analyzed and determined. Based on the fault location, a corresponding maintenance plan is formulated, including determining the required maintenance equipment, maintenance personnel, and maintenance time. According to the maintenance plan, the maintenance personnel are arranged to carry the required maintenance equipment to perform equipment maintenance at the specified maintenance time. Each time an alarm is triggered, the alarm number of the maintenance equipment is recorded. The alarm number is compared with the preset alarm number threshold. If the alarm number exceeds the threshold, it is considered that the maintenance equipment may have serious performance problems or has reached the end of its service life. In this case, the maintenance equipment is replaced to avoid potential failures or accidents.

[0028] In one embodiment, after executing the maintenance plan, relevant data and information in the maintenance process are collected, including the operation records of the maintenance personnel, the state changes of the maintenance equipment, whether the fault is solved, etc., which constitute the maintenance feedback information of the maintenance plan. According to the maintenance feedback information, it is evaluated whether the maintenance plan has successfully solved the fault of the equipment. If the fault has been solved, that is, the equipment has resumed normal operation, the next step is entered; if the fault is not solved, further analysis and action are required. If the maintenance result shows that the fault has been solved, the relevant data in the database is updated, including the operating status of the equipment, maintenance records, maintenance time, etc. At the same time, the maintenance success information is recorded, including the effectiveness of the maintenance plan, the performance of the maintenance personnel, etc., for subsequent analysis and optimization. If the maintenance result shows that the fault is not solved, it means that the current analytical model may have problems or deficiencies. In this case, the analytical model needs to be corrected. The correction may include adjusting the parameters of the model, adding new features, improving the architecture of the model, etc. After the analytical model is corrected, the model is verified and tested using the new or updated data set. Ensure that the corrected model can diagnose the fault of the equipment more accurately and output more reliable diagnostic information.

[0029] In one embodiment, relevant data of the maintenance equipment, such as operating time, fault history, maintenance records, etc., are regularly extracted from the database. These data are processed and analyzed using statistical analysis, data mining or machine learning techniques to identify trends, patterns and anomalies in the data. Based on the analysis results, the data change trends of the maintenance equipment are determined. These trends may indicate that the performance of the equipment is gradually declining or that some components are about to reach the end of their service life. These trends are compared with the normal operating parameters of the equipment to assess the health of the equipment. The data change trends are further analyzed using predictive models, such as time series analysis, machine learning algorithms, etc., to predict the types of faults that may occur in the future and the probability of failure. The predictive model should consider a variety of factors, including the type of equipment, the operating environment, historical fault data, etc. Ensure that the prediction results are accurate and reliable enough to provide strong support for the formulation of preventive maintenance plans. Based on the fault prediction results, a preventive maintenance plan is formulated. This includes determining the time, location, required personnel, spare parts and tools for maintenance. The preventive maintenance plan should aim to maintain the equipment before a failure occurs to reduce downtime, improve equipment reliability and extend equipment life. The preventive maintenance plan is sent to the user interface and displayed to the user in a visual manner. Arrange maintenance personnel to perform maintenance tasks according to the requirements of the preventive maintenance plan.

[0030] In one embodiment, the priority of the maintenance equipment is determined by comprehensively considering the impact of the fault type, such as whether the fault will cause equipment downtime, whether it will affect the operation of the production line, etc.; the probability of failure, that is, the possibility of the fault occurring, and the operational importance of the maintenance equipment, such as the key role of the equipment in the production line, the value of the equipment, etc. Use multi-criteria decision analysis (MCDA) methods, such as analytic hierarchy process (AHP), TOPSIS, etc., to quantify these factors and determine the priority accordingly. According to the preventive maintenance plan and the priority of the maintenance equipment, specific maintenance tasks are formulated. These tasks may include regular inspection of equipment, preventive replacement of parts, cleaning and lubrication, etc., ensuring that each task clearly specifies the required personnel, tools, spare parts and estimated completion time. The maintenance tasks are sorted according to the priority of the maintenance equipment. Tasks with high priority should be executed first to ensure the efficient operation of key equipment and production lines. According to the sorted maintenance tasks, the corresponding maintenance team is assigned, and the availability and workload of the team should also be considered when assigning to avoid task delays and team overload. The sorted maintenance tasks and the assigned maintenance teams are integrated into a maintenance task list. The list should list the name, priority, estimated start and end time, required resources and other information of each task in detail. The maintenance task list is presented to the user through the user interface so that the user can clearly understand the planning and execution status of the maintenance tasks.

[0031] like Figure 2 As shown, the embodiment of the present application also provides a data processing device based on fault diagnosis, including: at least one processor; and, a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable a data processing device based on fault diagnosis to perform: Collecting operation data of factory equipment, reconstructing features of the operation data to obtain sample data, and storing the sample data in a preset database; Acquire the sample data in the database to use the sample data as a test sample, perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; If the fault level is greater than or equal to the level threshold, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

[0032] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows: Collecting operation data of factory equipment, reconstructing features of the operation data to obtain sample data, and storing the sample data in a preset database; Acquire the sample data in the database to use the sample data as a test sample, perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; If the fault level is greater than or equal to the level threshold, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

[0033] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0034] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0035] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0036] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0037] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0038] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0039] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0040] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0041] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0042] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0043] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0044] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0045] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0046] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A data processing method based on fault diagnosis, characterized in that: include: Collecting operation data of factory equipment, reconstructing features of the operation data to obtain sample data, and storing the sample data in a preset database; Acquire the sample data in the database to use the sample data as a test sample, perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; If the fault level is greater than or equal to the level threshold, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

2. The method according to claim 1, characterized in that The feature reconstruction of the operation data specifically includes: Determine an original time series corresponding to the operating parameter, and downsample the original time series according to a plurality of preset time resolutions to obtain a feature series for characterizing the operating parameter; Reconstructing the feature space of the feature sequence to determine the difference between the sample data, and determining a reconstructed feature sequence according to the difference; A plurality of cluster center points are determined according to the reconstructed feature sequence, and clustering is performed according to the cluster center points to determine clustered sample data.

3. The method according to claim 1, characterized in that Before performing data analysis on the test sample using a preset analytical model, the method further includes: Determining original data according to the database, and determining a plurality of features of the original data; Performing dimensionality reduction processing on the multiple features to obtain a training set, and determining corresponding fault conditions according to the original data, so as to determine a verification set according to the fault conditions; The training set is input into a predetermined neural network model to train the neural network model according to the training set, and the trained neural network model is corrected according to the verification set, so as to obtain the analytical model.

4. The method according to claim 3, characterized in that Updating the analytical model according to the diagnostic information corresponding to the fault level specifically includes: Determine an update sample according to the diagnostic information corresponding to the fault level and the sample data, perform feature reconstruction on the update sample to obtain update sample data, and store the update sample data in the database; An updated training set and an updated verification set are determined according to the updated sample data, and the analytical model is retrained according to the updated training set, and the neural network model after the retraining is corrected according to the updated verification set, thereby completing the update of the analytical model.

5. The method according to claim 1, characterized in that Determining a maintenance plan corresponding to the factory equipment according to the diagnostic information specifically includes: Determine a fault probability based on the diagnostic information, and compare the fault probability with a preset threshold; If the failure probability is greater than the threshold, an alarm message is determined, and the alarm message is sent to a user interface to visualize the alarm message; Determine a corresponding fault location according to the alarm information, and determine a corresponding maintenance plan according to the fault location, wherein the maintenance plan includes maintenance equipment, maintenance personnel, and maintenance time; Determine the alarm number of the maintenance equipment according to the alarm information, and compare the alarm number with a preset alarm number threshold; If the alarm number is greater than the alarm number threshold, the maintenance equipment is replaced.

6. The method according to claim 5, characterized in that The method further comprises: Determine maintenance feedback information of the maintenance plan, and determine a maintenance result of the maintenance plan according to the maintenance feedback information; If the maintenance result shows that the fault has been resolved, the relevant data in the database is updated and maintenance success information is recorded; If the maintenance result shows that the fault is not resolved, the analytical model is corrected, and data analysis is performed using the corrected analytical model to obtain new diagnostic information.

7. The method according to claim 5, characterized in that The method further comprises: Performing periodic analysis on the data in the database to determine the data change trend of the maintenance equipment; Perform fault prediction based on the data change trend to determine the fault type and fault occurrence probability based on the prediction result; A preventive maintenance plan is formulated based on the prediction result, and the preventive maintenance plan is sent to a user interface to visualize the preventive maintenance plan.

8. The method according to claim 7, characterized in that The method further comprises: Determining a priority of the maintenance equipment, wherein the priority is determined based on the impact of the fault type, the fault probability, and the operational importance of the maintenance equipment; Determine maintenance tasks according to the priority and the preventive maintenance plan, sort the maintenance tasks according to the priority, assign corresponding maintenance teams according to the sorted order, and generate a maintenance task list; The maintenance task list is displayed through a user interface, and the task progress of the maintenance task is tracked, so as to update and display the execution status of the maintenance task in real time.

9. A data processing device based on fault diagnosis, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the data processing device based on fault diagnosis to perform: Collecting operation data of factory equipment, reconstructing features of the operation data to obtain sample data, and storing the sample data in a preset database; Acquire the sample data in the database to use the sample data as a test sample, perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; If the fault level is greater than or equal to the level threshold, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Collecting operation data of factory equipment, reconstructing features of the operation data to obtain sample data, and storing the sample data in a preset database; Acquire the sample data in the database to use the sample data as a test sample, perform data analysis on the test sample through a preset analytical model to obtain diagnostic information, determine the fault level of the factory equipment according to the diagnostic information, and compare the fault level with a preset level threshold; If the fault level is less than the level threshold, updating the analytical model according to the diagnostic information corresponding to the fault level; If the fault level is greater than or equal to the level threshold, a maintenance plan corresponding to the factory equipment is determined according to the diagnostic information, so as to repair the factory equipment according to the maintenance plan.

Images