Industrial equipment fault prediction and operation and maintenance management system

By designing industrial equipment fault prediction and operation and maintenance management systems, using equipment data acquisition, virtual scenes and fault prediction models, the problem of inability to predict equipment faults and monitoring in advance in the existing technology is solved, and safe and efficient operation of industrial equipment is achieved. Maintenance management.

CN119045393AInactive Publication Date: 2024-11-29SHENYANG CHENYANG INFORMATION TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411545301.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-01
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing technology cannot predict industrial equipment failures in advance, resulting in safety hazards in the security area, and cannot intuitively display the working conditions of the equipment and predict the remaining service life of the equipment under different working conditions. It is impossible to achieve accurate acquisition and intelligent monitoring of the equipment failure time nodes. .

Method used

An industrial equipment fault prediction and operation and maintenance management system was designed, including equipment data acquisition unit, virtual scene fault display unit and equipment fault prediction unit. By acquiring and processing industrial engine operation data, a three-dimensional virtual scene and fault prediction model was constructed, and a three-dimensional virtual scene and fault prediction model was carried out. Data simulation and model training, predict equipment failure time nodes and remaining service life, and perform intelligent monitoring.

Benefits of technology

It realizes the advance prediction and operation and maintenance management of industrial equipment failures, improves equipment safety, can intuitively display the working conditions of the equipment, accurately predict the failure time nodes, and ensures the safe and efficient operation of the equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119045393A_ABST
    Figure CN119045393A_ABST
Patent Text Reader

Abstract

The invention discloses an industrial equipment fault prediction and operation and maintenance management system, and relates to the technical field of operation and maintenance management, and the system comprises an equipment data collection unit which obtains the related data of the operation process of an industrial engine by taking the industrial engine fault prediction and operation and maintenance management system as an example. And the acquired related data of the operation process of the industrial engine are temporarily stored, and the stored related data of the operation process of the industrial engine are processed. The invention provides an industrial equipment fault prediction and operation and maintenance management system, which takes an industrial engine fault prediction and operation and maintenance management system as an example, and obtains and stores related data in the operation process of an industrial engine through an equipment data acquisition unit. And the stored related data of the operation process of the industrial engine is processed, and three-dimensional modeling is performed on the industrial engine through the arranged virtual scene fault display unit.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance management, and in particular to an industrial equipment fault prediction and operation and maintenance management system. Background Art

[0002] A large number of equipment are installed in large industrial enterprises. In order to ensure the safety of enterprise production, it is necessary to monitor the operating status of these equipment, so as to timely discover equipment failures and eliminate equipment safety hazards as soon as possible. The Chinese patent with application number 202210589508.4 discloses "a method and system for operation and maintenance information management based on big data, wherein the operation and maintenance information management system based on big data includes a fault statistics module, a map module, an acquisition module, and a fault prediction module: the map module is used to save the GIS map and mark the number and installation location of the equipment on the GIS map; the acquisition module is used to obtain basic information of the equipment, and the basic information of the equipment includes the brand, installation date and equipment number of the equipment; the fault statistics module is used to count the basic information and fault causes of the faulty equipment; the fault prediction module predicts the failure trend of the equipment according to the basic information of the equipment, which solves the problem that the existing technology cannot predict equipment failures in advance, resulting in safety hazards in the security area. "; This prior art only solves the problem of a front-end security device with automatic alarm in the prior art. When a device failure is detected, an abnormal notification is actively sent to enable the operation and maintenance personnel to carry out timely maintenance. However, during the maintenance period, the security status of the area is still unknown, and there is no guarantee that every faulty device can be repaired in a short time. Therefore, the method of reporting a repair after a failure still has lax security and certain safety hazards. It does not take into account that the working status of the equipment cannot be intuitively displayed based only on the data of the equipment operation, and does not consider predicting the remaining service life of the equipment under different working conditions, and combining the acquisition time of the data required for the prediction, to achieve the acquisition of the equipment failure time node information, and further needs to perform intelligent monitoring of the equipment based on the acquired information. Summary of the invention

[0003] The purpose of the present invention is to provide an industrial equipment fault prediction and operation and maintenance management system to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an industrial equipment fault prediction and operation and maintenance management system, comprising an equipment data acquisition unit, taking an industrial engine fault prediction and operation and maintenance management system as an example, the equipment data acquisition unit acquires relevant data of the industrial engine operation process, temporarily stores the acquired relevant data of the industrial engine operation process, and processes the stored relevant data of the industrial engine operation process; A virtual scene fault display unit, wherein the virtual scene fault display unit performs three-dimensional modeling of the industrial engine based on basic parameters of the industrial engine, and constructs a virtual scene consistent with the actual scene, and places the three-dimensional model in the virtual scene, and then simulates the working condition of the industrial engine based on the processed relevant data of the industrial engine operation process; An equipment failure prediction unit, wherein the equipment failure prediction unit constructs an equipment failure prediction model for industrial engine failure prediction, and simultaneously constructs a sample data set for equipment failure prediction model training, performs model training on the equipment failure prediction model through the sample data set, and performs accuracy verification on the trained equipment failure prediction model, and then outputs a failure prediction result through the trained equipment failure prediction model based on the processed operation data of the industrial engine; The equipment management unit collects and records the prediction results of the equipment failure prediction model, and processes the collected prediction results of the equipment failure prediction model to realize the monitoring of the industrial engine.

[0005] Preferably, the equipment data acquisition unit includes an equipment data acquisition module and an equipment data storage module. The equipment data acquisition module acquires relevant data of the operation process of the industrial engine through the on-site wired network and the dedicated wireless network of the manufacturing workshop where the industrial engine is located, including the workload, speed, temperature and pressure of the industrial engine, and adds a label of the data acquisition time to the acquired data, and collects and stores the time node information of the industrial engine failure in the system's built-in database. The equipment data storage module and the equipment data acquisition module are electrically connected. The equipment data storage module temporarily stores the acquired relevant data of the operation process of the industrial engine in the Redis database, and when new relevant data of the operation process of the industrial engine is acquired, the relevant data of the operation process of the industrial engine stored in the Redis database is stored as the historical operation relevant data of the industrial engine in the built-in database of the system, and the acquired new relevant data of the operation process of the industrial engine is temporarily stored in the Redis database.

[0006] Preferably, the equipment data acquisition unit also includes an equipment data processing module, which is electrically connected to the equipment data storage module. The equipment data processing module processes the stored relevant data of the industrial engine operation process, including data cleaning of the acquired relevant data of the industrial engine operation process, adjusting the sampling time intervals of all types of data with 10 minutes as the standard unit time, and deleting the same type of repeated data collected within the same standard unit time, and when there is data missing in the standard unit time, linear interpolation is performed based on the same type of data value in the previous standard unit time.

[0007] Preferably, the virtual scene fault display unit includes a virtual device three-dimensional modeling module and a virtual device scene modeling module. The virtual device three-dimensional modeling module obtains various parameters of industrial engine components based on the manual of the industrial engine, and performs three-dimensional modeling of various industrial engine components through 3DMax modeling software based on the various parameters of the industrial engine components, and reasonably assembles all industrial engine component models based on the actual positions of various industrial engine components in the industrial engine. The virtual device scene modeling module and the virtual device three-dimensional modeling module are electrically connected. The virtual device scene modeling module imports the three-dimensional model of the industrial engine into the Unity3D virtual simulation platform, and adds virtual elements to the virtual scene based on the actual manufacturing workshop environment in the Unity3D virtual simulation platform, including light sources, backgrounds and sounds, thereby enhancing the realism of the virtual scene.

[0008] Preferably, the virtual scene fault display unit also includes an equipment real-time simulation module, which is electrically connected to the virtual equipment scene modeling module. The equipment real-time simulation module is based on the real-time relevant data of the processed industrial engine operation process stored in the Redis database, and transmits the processed real-time relevant data of the industrial engine operation process to the virtual scene through the MQTT data transmission protocol, and updates the working condition of the industrial engine in the virtual scene based on the transmitted data, thereby simulating the working condition of the industrial engine in the virtual scene, and based on the simulation results, associates the relevant data of the industrial engine operation process stored in the Redis database and the system's built-in database with the corresponding industrial engine working condition simulation results.

[0009] Preferably, the equipment failure prediction unit includes an equipment failure prediction model construction module and a data set construction module. The equipment failure prediction model construction module takes the remaining service life of the industrial engine as the prediction target, constructs an equipment failure prediction model for industrial engine failure prediction, and calculates the time node of the industrial engine failure through the fault prediction algorithm in combination with the remaining service life prediction result of the industrial engine. The specific calculation formula is as follows: ; In the formula, Indicates the time point when the industrial engine fails. represents the remaining useful life prediction result of industrial engines, The time node representing the current normal operation of the industrial engine is represented, and the equipment fault prediction model specifically includes an input end, a hybrid encoder module and an output end, wherein the input end specifically includes an embedding layer, a position encoding layer and a hybrid feature layer, the real-time related data of the input processed industrial engine operation process is extracted through the embedding layer, and the dimension of the extracted data feature is mapped to the model dimension, the data feature is encoded by a relative position encoding method through the position encoding layer and relative position information is added, and the data feature is spliced ​​to form a hybrid feature through the hybrid feature layer, wherein the hybrid encoder module includes a hybrid attention layer, and the weights of each data feature are learned from different relative positions of the data feature through the hybrid attention layer through the self-attention mechanism and the attention mechanism and the weight is distributed, wherein the output end includes a multi-layer feedforward neural network, and the weighted hybrid feature is mapped to the remaining service life and output through the multi-layer feedforward neural network, and the data set construction module uses the processed industrial engine historical operation related data stored in the system's built-in database as sample data, and combines the associated corresponding industrial engine working condition simulation results to construct a sample data set.

[0010] Preferably, the equipment fault prediction unit further includes a model training module and a fault prediction result output module, wherein the model training module is electrically connected to the equipment fault prediction model construction module and the data set construction module respectively, and the model training module performs model training on the equipment fault prediction model based on the constructed sample data set, and after the model training is completed, performs accuracy verification operation through a model accuracy algorithm based on the time node information of the industrial engine failure stored in the database, and the specific calculation formula is as follows: ; In the formula, represents the accuracy value of the equipment failure prediction model, Indicates the number of sample data that are predicted correctly. Indicates the number of sample data with prediction errors. The fault prediction result output module and the model training module are electrically connected. The fault prediction result output module predicts the remaining service life based on the relevant data of the processed industrial engine operation process stored in the Redis database through the trained equipment fault prediction model, thereby obtaining the remaining service life prediction result of the industrial engine under the industrial engine working condition corresponding to the input data.

[0011] Preferably, the equipment management unit includes a fault prediction result collection module and a fault prediction result processing module, the fault prediction result collection module stores the remaining service life prediction result of the industrial engine by the equipment fault prediction model in the system's built-in database, and after the input data is stored in the system's built-in database as historical operation data, the corresponding data, the working condition simulation result of the industrial engine under the corresponding data, and the remaining service life prediction result of the industrial engine under the corresponding data are associated, the fault prediction result processing module is electrically connected to the fault prediction result collection module, the fault prediction result processing module determines the time node of the industrial engine failure based on the remaining service life prediction result of the industrial engine, and performs intelligent monitoring, specifically, when three days ≤ the time node from the industrial engine failure < seven days, the industrial engine is subjected to third-level monitoring, and the monitoring personnel cannot be completely off-duty, when one day ≤ the time node from the industrial engine failure < three days, the industrial engine is subjected to second-level monitoring, and the monitoring personnel cannot be partially off-duty, and when the time node from the industrial engine failure < one day, the industrial engine is subjected to first-level monitoring, and the monitoring personnel cannot be off-duty.

[0012] Compared with the prior art, the beneficial effects of the present invention include at least: the present invention proposes an industrial equipment fault prediction and operation and maintenance management system, taking the industrial engine fault prediction and operation and maintenance management system as an example, the relevant data of the industrial engine operation process is acquired and stored through the set equipment data acquisition unit, and the stored relevant data of the industrial engine operation process is processed, and the industrial engine is three-dimensionally modeled through the set virtual scene fault display unit, and a virtual scene consistent with the actual scene is constructed, so that based on the stored relevant data of the industrial engine operation process, the working condition of the industrial engine is simulated in the virtual scene, which is convenient for intuitive display, and the industrial engine is simulated in the virtual scene. Taking the remaining useful life of industrial engines as the prediction target, an equipment fault prediction model for industrial engine fault prediction is constructed, and the processed historical operation-related data of industrial engines stored in the system's built-in database is used as sample data to construct a sample data set. The equipment fault prediction model is trained and its accuracy is verified through the constructed sample data set, and the remaining useful life is predicted through the trained equipment fault prediction model, so as to determine the fault prediction time node information of the industrial engine under the industrial engine working conditions corresponding to the input data, and the remaining useful life prediction results of the industrial engine are collected and recorded through the set equipment management unit, and intelligent monitoring is performed based on the fault prediction time node information of the industrial engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present invention; Figure 2 This is a schematic diagram of the process flow of the device data acquisition unit according to an embodiment of the present invention; Figure 3 This is a flow chart of a virtual scene fault display unit according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the process flow of a device fault prediction unit according to an embodiment of the present invention; Figure 5 The figure is a flow chart of a device management unit according to an embodiment of the present invention.

[0014] In the figure: 100, equipment data acquisition unit; 101, equipment data acquisition module; 102, equipment data storage module; 103, equipment data processing module; 200, virtual scene fault display unit; 201, virtual equipment three-dimensional modeling module; 202, virtual equipment scene modeling module; 203, equipment real-time simulation module; 300, equipment fault prediction unit; 301, equipment fault prediction model construction module; 302, data set construction module; 303, model training module; 304, fault prediction result output module; 400, equipment management unit; 401, fault prediction result collection module; 402, fault prediction result processing module. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] See also Figure 1-5 , the present invention provides a technical solution: an industrial equipment fault prediction and operation and maintenance management system, including an equipment data acquisition unit 100, taking the industrial engine fault prediction and operation and maintenance management system as an example, the equipment data acquisition unit 100 acquires the relevant data of the industrial engine operation process, and temporarily stores the acquired relevant data of the industrial engine operation process, and processes the stored relevant data of the industrial engine operation process; A virtual scene fault display unit 200, which performs three-dimensional modeling of the industrial engine based on basic parameters of the industrial engine, constructs a virtual scene consistent with the actual scene, and places the three-dimensional model in the virtual scene, and then simulates the working condition of the industrial engine based on the processed relevant data of the industrial engine operation process; The equipment failure prediction unit 300 constructs an equipment failure prediction model for industrial engine failure prediction, and simultaneously constructs a sample data set for equipment failure prediction model training, performs model training on the equipment failure prediction model through the sample data set, and verifies the accuracy of the trained equipment failure prediction model, and then outputs a failure prediction result based on the processed industrial engine operation data through the trained equipment failure prediction model; The equipment management unit 400 collects and records the prediction results of the equipment failure prediction model, and processes the collected prediction results of the equipment failure prediction model to realize the monitoring of the industrial engine.

[0017] The equipment data acquisition unit 100 includes an equipment data acquisition module 101 and an equipment data storage module 102. The equipment data acquisition module 101 acquires relevant data of the operation process of the industrial engine through the on-site wired network and the dedicated wireless network of the manufacturing workshop where the industrial engine is located, including the workload, rotation speed, temperature and pressure of the industrial engine, and adds a label of the data acquisition time to the acquired data, and collects and stores the time node information of the industrial engine failure in the system's built-in database. The equipment data storage module 102 is electrically connected to the equipment data acquisition module 101. The equipment data storage module 102 temporarily stores the acquired relevant data of the operation process of the industrial engine in the Redis database, and when acquiring new relevant data of the operation process of the industrial engine, the relevant data of the operation process of the industrial engine stored in the Redis database is stored as the historical operation relevant data of the industrial engine in the built-in database of the system, and the acquired new relevant data of the operation process of the industrial engine is temporarily stored in the Redis database; The equipment data acquisition unit 100 also includes an equipment data processing module 103, which is electrically connected to the equipment data storage module 102. The equipment data processing module 103 processes the stored data related to the operation process of the industrial engine, including data cleaning of the acquired data related to the operation process of the industrial engine, adjusting the sampling time interval of all types of data with 10 minutes as the standard unit time, and deleting the same type of repeated data collected within the same standard unit time, and when there is data missing within the standard unit time, linear interpolation is performed based on the same type of data value within the previous standard unit time; The virtual scene fault display unit 200 includes a virtual device three-dimensional modeling module 201 and a virtual device scene modeling module 202. The virtual device three-dimensional modeling module 201 obtains various parameters of industrial engine components based on the manual of the industrial engine, and performs three-dimensional modeling of various industrial engine components through 3DMax modeling software based on the various parameters of the industrial engine components, and reasonably assembles all industrial engine component models based on the actual positions of various industrial engine components in the industrial engine. The virtual device scene modeling module 202 and the virtual device three-dimensional modeling module 201 are electrically connected. The virtual device scene modeling module 202 imports the three-dimensional model of the industrial engine into the Unity3D virtual simulation platform, and adds virtual elements, including light sources, backgrounds, and sounds, to the virtual scene based on the actual manufacturing workshop environment in the Unity3D virtual simulation platform, thereby enhancing the realism of the virtual scene; The virtual scene fault display unit 200 also includes a device real-time simulation module 203, which is electrically connected to the virtual device scene modeling module 202. The device real-time simulation module 203 transmits the processed real-time related data of the industrial engine operation process to the virtual scene through the MQTT data transmission protocol based on the processed real-time related data of the industrial engine operation process stored in the Redis database, and updates the working condition of the industrial engine in the virtual scene based on the transmitted data, thereby simulating the working condition of the industrial engine in the virtual scene, and based on the simulation results, associates the relevant data of the industrial engine operation process stored in the Redis database and the system built-in database with the corresponding industrial engine working condition simulation results; The equipment failure prediction unit 300 includes an equipment failure prediction model construction module 301 and a data set construction module 302. The equipment failure prediction model construction module 301 takes the remaining service life of the industrial engine as the prediction target, constructs an equipment failure prediction model for industrial engine failure prediction, and calculates the time node of the industrial engine failure through the fault prediction algorithm in combination with the remaining service life prediction result of the industrial engine. The specific calculation formula is as follows: ; In the formula, Indicates the time point when the industrial engine fails. represents the remaining useful life prediction result of industrial engines, Indicates the time node of the current normal operation of the industrial engine, and the equipment fault prediction model specifically includes an input end, a hybrid encoder module and an output end, wherein the input end specifically includes an embedding layer, a position encoding layer and a hybrid feature layer, the real-time related data of the input processed industrial engine operation process is extracted through the embedding layer, and the dimension of the extracted data feature is mapped to the model dimension, the data feature is encoded by a relative position encoding method through the position encoding layer and the relative position information is added, and the data feature is spliced ​​to form a hybrid feature through the hybrid feature layer, wherein the hybrid encoder module includes a hybrid attention layer, and the weights of each data feature are learned from different relative positions of the data feature through the self-attention mechanism and the attention mechanism through the hybrid attention layer and the weight distribution is performed, wherein the output end includes a multi-layer feedforward neural network, and the weighted hybrid feature is mapped to the remaining service life through the multi-layer feedforward neural network and output, and the data set construction module 302 uses the processed industrial engine historical operation related data stored in the system built-in database as sample data, and combines the associated corresponding industrial engine working condition simulation results to construct a sample data set; The equipment failure prediction unit 300 also includes a model training module 303 and a failure prediction result output module 304. The model training module 303 is electrically connected to the equipment failure prediction model construction module 301 and the data set construction module 302 respectively. The model training module 303 performs model training on the equipment failure prediction model based on the constructed sample data set, and after the model training is completed, based on the time node information of the industrial engine failure stored in the database, performs accuracy verification operation through the model accuracy algorithm. The specific calculation formula is as follows: ; In the formula, represents the accuracy value of the equipment failure prediction model, Indicates the number of sample data that are predicted correctly. Indicates the number of sample data with prediction errors. The fault prediction result output module 304 is electrically connected to the model training module 303. The fault prediction result output module 304 performs a remaining service life prediction based on the processed relevant data of the industrial engine operation process stored in the Redis database through the trained equipment fault prediction model, thereby obtaining a remaining service life prediction result of the industrial engine under the industrial engine working condition corresponding to the input data; The equipment management unit 400 includes a fault prediction result collection module 401 and a fault prediction result processing module 402. The fault prediction result collection module 401 stores the remaining service life prediction result of the industrial engine by the equipment fault prediction model in the system's built-in database, and after the input data is stored in the system's built-in database as historical operation data, the corresponding data, the working condition simulation result of the industrial engine under the corresponding data, and the remaining service life prediction result of the industrial engine under the corresponding data are associated. The fault prediction result processing module 402 is electrically connected to the fault prediction result collection module 401. The fault prediction result processing module 402 determines the time node of the industrial engine failure based on the remaining service life prediction result of the industrial engine, and performs intelligent monitoring. Specifically, when three days ≤ the time node from the industrial engine failure < seven days, the industrial engine is monitored at the third level, and the monitoring personnel cannot be completely off duty. When one day ≤ the time node from the industrial engine failure < three days, the industrial engine is monitored at the second level, and the monitoring personnel cannot be partially off duty. When the time node from the industrial engine failure < one day, the industrial engine is monitored at the first level, and the monitoring personnel cannot be off duty.

[0018] Working principle: The relevant data of the industrial engine operation process is acquired through the equipment data acquisition module 101, and the relevant data of the industrial engine operation process acquired is temporarily stored in the Redis database through the equipment data storage module 102. The stored relevant data of the industrial engine operation process is processed through the equipment data processing module 103. The three-dimensional modeling of the industrial engine components is performed based on the various parameters of the industrial engine components through the virtual equipment three-dimensional modeling module 201 through the 3DMax modeling software. The three-dimensional model of the industrial engine is imported into the Unity3D virtual simulation platform through the virtual equipment scene modeling module 202. The working condition of the industrial engine is simulated in the virtual scene through the equipment real-time simulation module 203. The equipment fault prediction model The construction module 301 constructs an equipment fault prediction model for industrial engine fault prediction. The data set construction module 302 uses the processed industrial engine historical operation related data stored in the system's built-in database as sample data, and constructs a sample data set in combination with the associated corresponding industrial engine working condition simulation results. The model training module 303 trains the equipment fault prediction model based on the constructed sample data set. The fault prediction result output module 304 predicts the remaining service life based on the equipment fault prediction model. The fault prediction result collection module 401 stores the remaining service life prediction results of the industrial engine using the equipment fault prediction model in the system's built-in database. The fault prediction result processing module 402 performs intelligent monitoring of the industrial engine.

[0019] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device.

[0020] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial equipment fault prediction and operation and maintenance management system, characterized by: It comprises an equipment data acquisition unit (100). Taking an industrial engine fault prediction and operation and maintenance management system as an example, the equipment data acquisition unit (100) acquires data related to the operation process of the industrial engine, temporarily stores the acquired data related to the operation process of the industrial engine, and processes the stored data related to the operation process of the industrial engine; A virtual scene fault display unit (200), wherein the virtual scene fault display unit (200) performs three-dimensional modeling of the industrial engine based on basic parameters of the industrial engine, constructs a virtual scene consistent with the actual scene, and places the three-dimensional model in the virtual scene, and then simulates the working condition of the industrial engine based on the processed relevant data of the industrial engine operation process; An equipment failure prediction unit (300), the equipment failure prediction unit (300) constructing an equipment failure prediction model for industrial engine failure prediction, and simultaneously constructing a sample data set for equipment failure prediction model training, training the equipment failure prediction model through the sample data set, and verifying the accuracy of the trained equipment failure prediction model, and then outputting a failure prediction result through the trained equipment failure prediction model based on the processed industrial engine operation data; The equipment management unit (400) collects and records the prediction results of the equipment failure prediction model, and processes the collected prediction results of the equipment failure prediction model to achieve monitoring of the industrial engine.

2. The industrial equipment fault prediction and operation and maintenance management system according to claim 1, characterized in that: The device data acquisition unit (100) comprises a device data acquisition module (101) and a device data storage module (102). The device data acquisition module (101) acquires relevant data of the operation process of the industrial engine through an on-site wired network and a dedicated wireless network in a manufacturing workshop where the industrial engine is located, including the workload, rotation speed, temperature and pressure of the industrial engine, and adds a label of the data acquisition time to the acquired data, and collects and stores the time node information of the industrial engine failure in a database built into the system. The device data storage module (102) is electrically connected to the device data acquisition module (101). The device data storage module (102) temporarily stores the acquired relevant data of the operation process of the industrial engine in a Redis database, and when new relevant data of the operation process of the industrial engine is acquired, the relevant data of the operation process of the industrial engine stored in the Redis database is stored as historical operation relevant data of the industrial engine in the database built into the system, and the acquired new relevant data of the operation process of the industrial engine is temporarily stored in the Redis database.

3. The industrial equipment fault prediction and operation and maintenance management system according to claim 2, characterized in that: The equipment data acquisition unit (100) further comprises an equipment data processing module (103), the equipment data processing module (103) being electrically connected to the equipment data storage module (102), the equipment data processing module (103) processing the stored data related to the operation process of the industrial engine, including data cleaning of the acquired data related to the operation process of the industrial engine, adjusting the sampling time interval of all types of data with 10 minutes as the standard unit time, deleting duplicate data of the same type collected within the same standard unit time, and performing linear interpolation based on the data value of the same type within the previous standard unit time when data is missing within the standard unit time.

4. The industrial equipment fault prediction and operation and maintenance management system according to claim 1, characterized in that: The virtual scene fault display unit (200) comprises a virtual device three-dimensional modeling module (201) and a virtual device scene modeling module (202). The virtual device three-dimensional modeling module (201) obtains various parameters of industrial engine components based on the manual of the industrial engine, and performs three-dimensional modeling of the industrial engine components through 3DMax modeling software based on the various parameters of the industrial engine components, and reasonably assembles all industrial engine component models based on the actual positions of the industrial engine components in the industrial engine. The virtual device scene modeling module (202) and the virtual device three-dimensional modeling module (201) are electrically connected. The virtual device scene modeling module (202) imports the three-dimensional model of the industrial engine into the Unity3D virtual simulation platform, and adds virtual elements, including light sources, backgrounds and sounds, to the virtual scene based on the actual manufacturing workshop environment in the Unity3D virtual simulation platform, thereby enhancing the realism of the virtual scene.

5. The industrial equipment fault prediction and operation and maintenance management system according to claim 4, characterized in that: The virtual scene fault display unit (200) further comprises a device real-time simulation module (203), the device real-time simulation module (203) being electrically connected to the virtual device scene modeling module (202), and the device real-time simulation module (203) transmitting the processed real-time relevant data of the industrial engine operation process to the virtual scene through the MQTT data transmission protocol based on the processed real-time relevant data of the industrial engine operation process stored in the Redis database, and updating the working condition of the industrial engine in the virtual scene based on the transmitted data, thereby simulating the working condition of the industrial engine in the virtual scene, and, based on the simulation result, associating the relevant data of the industrial engine operation process stored in the Redis database and the system built-in database respectively with the corresponding industrial engine working condition simulation result.

6. The industrial equipment fault prediction and operation and maintenance management system according to claim 1, characterized in that: The equipment failure prediction unit (300) comprises an equipment failure prediction model construction module (301) and a data set construction module (302). The equipment failure prediction model construction module (301) takes the remaining service life of the industrial engine as a prediction target, constructs an equipment failure prediction model for industrial engine failure prediction, and calculates the time node of the industrial engine failure through a failure prediction algorithm in combination with the remaining service life prediction result of the industrial engine. The equipment failure prediction model specifically comprises an input end, a hybrid encoder module and an output end. The data set construction module (302) takes the processed industrial engine historical operation related data stored in the system's built-in database as sample data, and constructs a sample data set in combination with the associated corresponding industrial engine working condition simulation results.

7. The industrial equipment fault prediction and operation and maintenance management system according to claim 6, characterized in that: The equipment fault prediction unit (300) further comprises a model training module (303) and a fault prediction result output module (304), wherein the model training module (303) is electrically connected to the equipment fault prediction model construction module (301) and the data set construction module (302), respectively; the model training module (303) performs model training on the equipment fault prediction model based on the constructed sample data set, and after the model training is completed, performs accuracy verification operation through a model accuracy algorithm based on the time node information of the industrial engine failure stored in the database; the fault prediction result output module (304) is electrically connected to the model training module (303), and the fault prediction result output module (304) performs remaining service life prediction through the trained equipment fault prediction model based on the relevant data of the processed industrial engine operation process stored in the Redis database, thereby obtaining the remaining service life prediction result of the industrial engine under the industrial engine working condition corresponding to the input data.

8. The industrial equipment fault prediction and operation and maintenance management system according to claim 1, characterized in that: The equipment management unit (400) comprises a fault prediction result collection module (401) and a fault prediction result processing module (402). The fault prediction result collection module (401) stores the remaining service life prediction result of the industrial engine by the equipment fault prediction model in a system built-in database, and after the input data is stored as historical operation data in the system built-in database, the corresponding data, the working condition simulation result of the industrial engine under the corresponding data, and the remaining service life prediction result of the industrial engine under the corresponding data are associated. The fault prediction result processing module (402) is electrically connected to the fault prediction result collection module (401). The fault prediction result processing module (402) determines the time node when the industrial engine fails based on the remaining service life prediction result of the industrial engine, and performs intelligent monitoring.

Citation Information

Patent Citations

  • Industrial equipment residual life prediction method and device, storage medium and equipment

    CN111460728A

  • Charging pile fault element prediction method and system

    CN112699605A

  • Industrial equipment health management system and method

    CN114282434A

  • Equipment life and fault type prediction method and system based on digital twin technology

    CN115438726A

  • Bearing life prediction method based on improved Transform model

    CN117473411A