Equipment fault detection and maintenance prediction system and method

Abstract

The invention discloses an equipment fault detection and maintenance prediction system and method, and the method comprises the steps: an information collection module monitors the working state of equipment in real time through a sensor, collects operation data, and an information processing module carries out the arrangement and induction of the operation data, the fault diagnosis and analysis module analyzes the data output by the information processing module through an artificial intelligence model and identifies potential fault hidden dangers, and the diagnosis generation and push module receives the potential fault hidden danger information to generate a fault list and pushes the fault list to machine maintenance personnel. A machine maintenance worker in the maintenance confirmation and feedback module carries out equipment maintenance according to a fault list, an actual fault information record is fed back to the server after maintenance is completed, and the data analysis and prediction module adopts the actual fault record fed back by the machine maintenance worker as a new historical data source predicted by the artificial intelligence model to carry out archiving analysis and prediction. The data sources are continuously increased, the artificial intelligence model is continuously optimized, and the accuracy of fault prediction and maintenance suggestions can be gradually improved.

Description

Technical Field

[0001] The present invention relates to a system and method for equipment fault detection and maintenance prediction, and belongs to the field of industrial automation intelligent manufacturing. Background Art

[0002] As the complexity and intelligence of industrial equipment continue to increase, traditional equipment fault diagnosis and maintenance modes often rely on manual experience and regular inspections, which not only increases the maintenance cost of the equipment, but also poses the risk of delayed fault diagnosis and misdiagnosis. Therefore, this application proposes to use a combination of sensor technology and artificial intelligence to monitor the equipment's operating status in real time, and to predict faults and make intelligent decisions based on historical data, thereby improving the timeliness and accuracy of fault handling and the overall operation and maintenance efficiency of the equipment. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a system and method for equipment fault detection and maintenance prediction, so as to solve the problem that the existing equipment fault diagnosis and maintenance mode often relies on manual experience and regular inspections, which not only increases the maintenance cost of the equipment, but also has the risk of delayed fault diagnosis and misdiagnosis.

[0004] In order to achieve the above object, the present invention is implemented through the following technical solutions: a system and method for equipment fault detection and maintenance prediction, which includes: An information collection module, wherein a plurality of sensors are provided inside the information collection module, and the sensors can monitor the working status of the equipment in real time and collect various operation data of the construction site in real time; An information processing module, which is used to organize and summarize various data collected by the information collection module; A fault diagnosis and analysis module, which analyzes the data output by the information processing module through an artificial intelligence model to identify potential fault hazards; A diagnosis generation and push module, which receives the potential fault information provided by the fault diagnosis and analysis module to generate a fault list, and pushes it to the mobile terminal of the mechanic in an automated manner; In the maintenance confirmation and feedback module, the maintenance personnel carry out equipment maintenance according to the fault list generated by the diagnosis generation and push module. After the maintenance is completed, the maintenance personnel record the actual fault information and feed it back to the server through the mobile terminal; The data analysis and prediction module uses the actual fault records fed back by the mechanics in the maintenance confirmation and feedback module as a new historical data source for artificial intelligence model prediction to perform archive analysis and prediction.

[0005] Furthermore, the operating data collected by the information collection module includes temperature, vibration, pressure, current, and voltage. The information collection module is also configured with basic equipment information and maintenance personnel information.

[0006] Furthermore, the basic equipment information configured in the information collection module includes the name of the equipment, the status of the equipment, the location of the equipment and the maintenance record of the equipment, and the mechanic information configured in the information collection module includes the personnel name, the personnel's years of work experience, the personnel's contact information and the personnel's qualification certificates.

[0007] Furthermore, the data analysis algorithm adopted by the fault diagnosis and analysis module is one of deep learning or machine learning. The algorithm is used to train the historical fault data of the equipment to optimize the diagnosis model and improve the accuracy of fault detection.

[0008] Furthermore, the fault list generated in the diagnosis generation and push module includes the faulty component, fault type, severity and preliminary handling suggestions.

[0009] Furthermore, the maintenance confirmation and feedback module also includes a user interface for the mechanic to record and send back actual fault information, wherein the actual fault information includes the maintenance process, component replacement and maintenance method of the mechanic.

[0010] Furthermore, the data analysis and prediction module can predict the failures that will occur in the equipment within a certain time range in the future based on the new historical data, issue early warnings and generate corresponding maintenance suggestions, thereby achieving failure prevention and maintenance.

[0011] Furthermore, the system also includes a database for storing historical fault data, maintenance records and actual fault information sent back by mechanics, so as to facilitate learning and optimization of the artificial intelligence model.

[0012] A method for equipment fault detection and maintenance prediction, the method comprising the following steps: S1. Collect equipment operation data through the information collection module; S2. Arrange the collected operation data through the information processing module; S3. Analyze the collated data through the fault diagnosis and analysis module to identify potential equipment faults; S4. Based on the potential fault information provided by the fault diagnosis and analysis module, the diagnosis generation and push module generates a fault list and pushes it to the mobile terminal of the mechanic; S5. The maintenance personnel conducts maintenance inspection according to the fault list on the mobile terminal, and after the inspection, the actual fault information is fed back to the server through the maintenance confirmation and feedback module; S6. The data analysis and prediction module updates and improves the database based on the actual fault information fed back by mechanics, optimizes the artificial intelligence model to improve the accuracy of future fault predictions, and predicts future faults based on the updated model and generates preventive maintenance recommendations.

[0013] The beneficial effects of the present invention are: When the user wants to use a system for equipment fault detection and maintenance prediction of the present application, the sensor on the equipment will transmit the collected equipment operation data to the information processing module through the information collection module. The information processing module will organize the collected data and output it to the fault diagnosis and analysis module, and combine the artificial intelligence model with the operation data to identify potential fault hazards and generate a fault list by the diagnosis generation and push module, which will be transmitted to the mechanic's mobile terminal in an automated manner. After the mechanic completes the maintenance according to the fault list, the actual fault information record will be fed back to the server. Finally, the artificial intelligence model will use the actual fault information as a new historical data source for archiving, analysis and prediction. In this process, since the artificial intelligence is equipped with a corresponding data analysis algorithm, the accuracy of the fault prediction of the entire system will continue to improve by continuously updating the database information, thereby improving the timeliness and accuracy of fault handling and the overall operation and maintenance efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A schematic diagram of the structure of a system for equipment fault detection and maintenance prediction according to the present invention; Figure 2 It is a structural schematic diagram of the information collection module of the present invention; Figure 3 The present invention is a schematic diagram of the steps of a method for equipment fault detection and maintenance prediction.

[0015] The reference numerals are: 1. Information collection module; 2. Information processing module; 3. Fault diagnosis and analysis module; 4. Diagnosis generation and push module; 5. Maintenance confirmation and feedback module; 6. Data analysis and prediction module. DETAILED DESCRIPTION

[0016] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0017] Figure 1 This is a schematic diagram of the structure of a system for equipment fault detection and maintenance prediction according to the present invention. Figure 2 It is a structural schematic diagram of the information collection module of the present invention.

[0018] like Figure 1 , Figure 2 As shown, the present invention provides a system and method technical solution for equipment fault detection and maintenance prediction: it includes: An information collection module 1, wherein the information collection module 1 is internally equipped with a plurality of sensors, and the sensors can monitor the working status of the equipment in real time and collect various operation data of the construction site in real time; An information processing module 2, which is used to organize and summarize various data collected by the information collection module 1; A fault diagnosis and analysis module 3, which analyzes the data output by the information processing module 2 through an artificial intelligence model to identify potential fault hazards; The diagnosis generation and push module 4 receives the potential fault information provided by the fault diagnosis and analysis module 3 to generate a fault list, and pushes it to the mobile terminal of the mechanic in an automated manner; Maintenance confirmation and feedback module 5, the maintenance personnel perform equipment maintenance according to the fault list generated by the diagnosis generation and push module 4, and after the maintenance is completed, the maintenance personnel record the actual fault information and feedback it to the server through the mobile terminal; The data analysis and prediction module 6 uses the actual fault records fed back by the mechanics in the maintenance confirmation and feedback module 5 as a new historical data source for artificial intelligence model prediction, and performs archive analysis and prediction.

[0019] In order to achieve comprehensive detection of the equipment, the operating data collected by the information collection module 1 include temperature, vibration, pressure, current, and voltage. The information collection module 1 is also configured with basic equipment information and maintenance personnel information.

[0020] In order to obtain equipment information and contact mechanics in a timely manner, the basic equipment information configured in the information collection module 1 includes the name of the equipment, the status of the equipment, the location of the equipment and the maintenance record of the equipment. The mechanic information configured in the information collection module 1 includes the name of the personnel, the years of work of the personnel, the contact information of the personnel and the qualification certificates of the personnel.

[0021] In order to optimize the artificial intelligence model, the data analysis algorithm adopted by the fault diagnosis and analysis module 3 is one of deep learning or machine learning. The algorithm is used to train the historical fault data of the equipment to optimize the diagnosis model and improve the accuracy of fault detection.

[0022] In order to generate a detailed fault list for the convenience of inspection by mechanics, the fault list generated by the diagnosis generation and push module 4 includes the faulty component, fault type, severity and preliminary treatment suggestions.

[0023] In order to facilitate data interaction, the maintenance confirmation and feedback module 5 also includes a user interface for the mechanic to record and send back actual fault information, wherein the actual fault information includes the maintenance process, component replacement and maintenance method of the mechanic.

[0024] In order to prevent and maintain equipment failures, the data analysis and prediction module 6 can predict equipment failures that will occur within a certain period of time in the future based on new historical data, issue early warnings and generate corresponding maintenance suggestions to prevent and maintain failures.

[0025] In order to facilitate the model to collect historical data for learning, the system also includes a database for storing historical fault data, maintenance records and actual fault information sent back by mechanics, so as to facilitate the learning and optimization of the artificial intelligence model.

[0026] Figure 3 The present invention is a schematic diagram of the steps of a method for equipment fault detection and maintenance prediction, which adopts the above-mentioned equipment fault detection and maintenance prediction system. Figure 3 As shown, in order to facilitate the fault inspection of the equipment, the present invention also provides a method for equipment fault detection and maintenance prediction, the method comprising the following steps: S1, collecting equipment operation data through information collection module 1; S2, arranging the collected operation data through the information processing module 2; S3, analyzing the collated data through the fault diagnosis and analysis module 3 to identify potential equipment faults; S4, combining the potential fault information provided by the fault diagnosis and analysis module 3, the diagnosis generation and push module 4 generates a fault list and pushes it to the mobile terminal of the mechanic; S5, the mechanic performs maintenance inspection according to the fault list on the mobile terminal, and after the inspection, the actual fault information is fed back to the server through the maintenance confirmation and feedback module 5; S6, data analysis and prediction module 6 updates and improves the database based on the actual fault information fed back by mechanics, optimizes the artificial intelligence model to improve the accuracy of future fault predictions, and the system predicts future faults based on the updated model and generates preventive maintenance recommendations.

[0027] When the user wants to use a system for equipment fault detection and maintenance prediction of the present application, the sensor on the equipment will transmit the collected equipment operation data to the information processing module 2 through the information collection module 1. The information processing module 2 will organize the collected data and output it to the fault diagnosis and analysis module 3. Combined with the artificial intelligence model, the operation data will identify potential fault hazards and the diagnosis generation and push module 4 will generate a fault list, which will be transmitted to the mobile terminal of the mechanic in an automated manner. After the mechanic completes the maintenance according to the fault list, the actual fault information record will be fed back to the server. Finally, the artificial intelligence model will use the actual fault information as a new historical data source for archiving, analysis and prediction. In this process, since the artificial intelligence is equipped with a corresponding data analysis algorithm, the accuracy of the fault prediction of the entire system will continue to improve by continuously updating the database information, thereby improving the timeliness and accuracy of fault handling and the overall operation and maintenance efficiency of the equipment.

[0028] The present application discloses a system for equipment fault detection and maintenance prediction, which uses an artificial intelligence system to combine real-time data provided by sensors and historical data in a database for intelligent analysis, greatly improving the timeliness and accuracy of fault detection. As the amount of data continues to increase, maintenance personnel can also conduct timely inspections through the predictive maintenance suggestions given by the system, thereby avoiding long-term downtime of equipment due to faults and improving the availability of equipment.

[0029] This system shares a server with the mechanic's mobile terminal, so that after the diagnosis generation and push module outputs the fault list, the maintenance information can be promptly transmitted to the mechanic's mobile terminal, so that the mechanic can quickly obtain fault information and maintenance suggestions, reducing the time of manual search and diagnosis. After the maintenance is completed, the mechanic can quickly transmit the actual fault information to the server as a new data source. The artificial intelligence system can continuously learn and optimize the model based on the new fault data, thereby providing more accurate maintenance decisions.

[0030] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A system for equipment fault detection and maintenance prediction, characterized in that: It includes: An information collection module (1), wherein the information collection module (1) is internally equipped with a plurality of sensors, and the sensors can monitor the working status of the equipment in real time and collect various operating data of the construction site in real time; An information processing module (2), the information processing module (2) being used to sort out and summarize various data collected by the information collection module (1); A fault diagnosis and analysis module (3), wherein the fault diagnosis and analysis module (3) analyzes the data output by the information processing module (2) through an artificial intelligence model to identify potential fault hazards; A diagnosis generation and push module (4), the diagnosis generation and push module (4) receiving the fault potential information provided by the fault diagnosis and analysis module (3) to generate a fault list, and pushes it to a mobile terminal of a mechanic repair personnel in an automated manner; A maintenance confirmation and feedback module (5), in which a maintenance worker performs equipment maintenance according to the fault list generated by the diagnosis generation and push module (4). After the maintenance is completed, the maintenance worker records the actual fault information and feeds it back to the server via a mobile terminal; A data analysis and prediction module (6), wherein the data analysis and prediction module (6) uses the actual fault records fed back by the mechanics in the maintenance confirmation and feedback module (5) as a new historical data source for artificial intelligence model prediction, and performs archive analysis and prediction. The maintenance confirmation and feedback module (5) further comprises a user interface for the mechanic to record and send back actual fault information, wherein the actual fault information comprises the maintenance process, component replacement and maintenance method of the mechanic.

2. The system for equipment fault detection and maintenance prediction according to claim 1, characterized in that: The operating data collected by the information collection module (1) includes temperature, vibration, pressure, current and voltage. The information collection module (1) is also configured with basic equipment information and maintenance personnel information.

3. The system for equipment fault detection and maintenance prediction according to claim 2, characterized in that: The basic equipment information configured in the information collection module (1) includes the name of the equipment, the status of the equipment, the location of the equipment and the maintenance record of the equipment. The repair personnel information configured in the information collection module (1) includes the personnel name, the personnel's working experience, the personnel's contact information and the personnel's qualification certificates.

4. The system for equipment fault detection and maintenance prediction according to claim 1, characterized in that: The data analysis algorithm adopted by the fault diagnosis and analysis module (3) is a type of deep learning or machine learning. The algorithm is used to train the historical fault data of the equipment to optimize the diagnosis model and improve the accuracy of fault detection.

5. The system for equipment fault detection and maintenance prediction according to claim 1, characterized in that: The fault list generated in the diagnosis generation and push module (4) includes the faulty component, fault type, severity and preliminary handling suggestions.

6. The system for equipment fault detection and maintenance prediction according to claim 1, characterized in that: The data analysis and prediction module (6) can predict the failures that will occur in the equipment within a certain time range in the future based on the new historical data, issue early warnings and generate corresponding maintenance suggestions, thereby achieving failure prevention and maintenance.

7. The system for equipment fault detection and maintenance prediction according to claim 1, characterized in that: The system also includes a database for storing historical fault data, maintenance records and actual fault information sent back by mechanics to facilitate learning and optimization of the artificial intelligence model.

8. A method for equipment fault detection and maintenance prediction, applicable to a system for equipment fault detection and maintenance prediction as claimed in any one of claims 1 to 7, characterized in that: The method comprises the following steps: S1. Collecting equipment operation data through the information collection module (1); S2, arranging the collected operation data through the information processing module (2); S3, analyzing the collated data through the fault diagnosis and analysis module (3) to identify potential equipment faults; S4, combining the potential fault information provided by the fault diagnosis and analysis module (3), the diagnosis generation and push module (4) generates a fault list and pushes it to the mobile terminal of the mechanic; S5, the mechanic performs maintenance inspection according to the fault list on the mobile terminal, and after the inspection, the actual fault information is fed back to the server through the maintenance confirmation and feedback module (5); S6. Data analysis and prediction module (6) updates and improves the database based on the actual fault information fed back by the mechanics, optimizes the artificial intelligence model to improve the accuracy of future fault predictions, and predicts future faults based on the updated model and generates preventive maintenance recommendations.

Images