Intelligent fault diagnosis method and system for mechanical equipment

Abstract

The invention discloses an intelligent fault diagnosis method and system for mechanical equipment, and relates to the technical field of mechanical equipment fault diagnosis, and the system comprises an equipment group, a data acquisition module, a data transmission system, an automatic repair system, a data analysis and processing system, a cloud platform system and a man-machine interaction system. According to the intelligent fault diagnosis method and system for the mechanical equipment, multiple sensors are arranged, multi-source data in the operation process of the mechanical equipment are collected and fused, the operation state of the mechanical equipment can be comprehensively reflected, and compared with a traditional single data diagnosis mode, the accuracy and reliability of fault diagnosis are greatly improved; a large amount of data is analyzed and processed through the AI technology according to the collected data, a scientific and reasonable processing strategy can be generated, powerful support is provided for operation and maintenance decisions, fusion and updating are automatically carried out through the arranged database, and the efficiency and precision of fault diagnosis are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment fault diagnosis, and in particular to a mechanical equipment intelligent fault diagnosis method and system thereof. Background Art

[0002] With the continuous development of modern industry, science and technology, and economy, industry has become an important criterion for measuring a country's comprehensive strength. The development of industry is inseparable from stable mechanical equipment. A large number of mechanical equipment have good stability in the early stage of operation, but their performance will degrade or even fail over time. Faulty mechanical equipment seriously affects production performance and safety. Therefore, in the production process, the demand for reliability, safety and reduction of manufacturing costs has greatly promoted the development of mechanical equipment fault diagnosis technology.

[0003] Traditional fault diagnosis methods for mechanical equipment rely primarily on manual inspections and empirical judgment. This approach is not only inefficient and highly subjective, but also difficult to detect early potential faults. With the development of sensor technology and information technology, fault diagnosis methods based on sensor data have gradually gained application. However, most existing methods only analyze a single type of data (such as vibration data or temperature data), failing to fully utilize the rich information contained in the multi-source heterogeneous data generated during the operation of mechanical equipment, resulting in insufficient accuracy and timeliness in fault diagnosis. In addition, existing fault diagnosis systems lack adaptive learning capabilities, making it difficult to cope with complex and changing operating conditions and equipment aging. They cannot meet the modern industry's demand for efficient and reliable operation of mechanical equipment, which has a certain adverse impact on people's use. To address the shortcomings of existing technologies, we propose an intelligent fault diagnosis method and system for mechanical equipment. Summary of the Invention

[0004] The main purpose of the present invention is to provide a mechanical equipment intelligent fault diagnosis method and system thereof, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for intelligent fault diagnosis of mechanical equipment, comprising the following steps:

[0007] S1: Install multiple sensors at corresponding positions of the mechanical equipment, and collect multi-source data during the operation of the mechanical equipment through the data acquisition module;

[0008] S2: Establish a database, obtain basic information data of the device to be diagnosed, and store it in the database as historical data;

[0009] S3: using the data acquisition module to transmit the real-time multi-source data to the data analysis and processing system through the data transmission system;

[0010] S4: The data input unit in the data analysis and processing system receives the multi-source data that is pre-processed by the data acquisition module and works in real time, and uses the data enhancement unit to combine the features of different types of data according to the data feature fusion method to generate the features of the fused multi-source data;

[0011] S5: The data analysis and processing system uses the internal AI recognition module to read the database within the cloud platform system, calculates the similarity of the multi-source data characteristics based on real-time work, and compares the similarity of the multi-source data characteristics of real-time work with the fault characteristics of each historical data in the fault knowledge base in the database through the AI ​​analysis module;

[0012] S6: When the multi-source data characteristics of real-time work are fault data, the AI ​​recognition module extracts the multi-source data of real-time work and combines it with the fault knowledge base in the database to update it, obtains new historical data fault characteristics, and stores them in the fault knowledge base;

[0013] S7: The AI ​​analysis module within the data analysis and processing system identifies real-time data fault characteristics and automatically reads the corresponding historical data fault characteristic data. The report generation unit generates alarm and processing solution information, which is promptly pushed to the device terminal of the relevant operator through the cloud server in the cloud platform system. At the same time, the data is transmitted to the automatic repair system through the data transmission system to achieve automatic repair.

[0014] S8: When the automatic repair system fails to eliminate the existing fault data after automatic repair, or when the AI ​​recognition module cannot extract the fault characteristics of the historical data in the fault knowledge base, or when there is no corresponding emergency treatment plan in the fault knowledge base, the fault confirmation alarm information will be sent to the smart terminal device of the relevant management personnel, and an alarm will be issued through the display alarm module at the same time;

[0015] S9: Relevant management personnel use the human-computer interaction system to check the real-time operation data of the equipment, real-time feedback information from various sensors, and historical monitoring videos to identify the cause of the fault. They then use the background controller to perform remote operation and maintenance to troubleshoot the fault, register the equipment operation and maintenance records in the database, and store them in the diagnostic history library in the database according to the fault type and downtime time mark, and update the new fault knowledge base.

[0016] Preferably, the multiple sensors include vibration sensors, temperature sensors, current sensors and pressure sensors.

[0017] Preferably, the multi-source data includes vibration data, temperature data, current data and pressure data.

[0018] An intelligent fault diagnosis system for mechanical equipment, including an equipment group, a data acquisition module, a data transmission system, an automatic repair system, a data analysis and processing system, a cloud platform system, and a human-computer interaction system;

[0019] Equipment group: It is composed of multiple mechanical equipment to facilitate the inspection and maintenance of each mechanical equipment;

[0020] Data acquisition module: contains a variety of sensors, used to collect vibration, temperature, current, pressure and other multi-source data during the operation of mechanical equipment, and perform preliminary preprocessing on the collected data;

[0021] Data transmission system: wirelessly transmits the data collected by the data acquisition module to the data analysis and processing system;

[0022] Automatic repair system: realize simple restart operation and remote connection with the background;

[0023] Data analysis and processing system: Receives data transmitted by the data transmission system, analyzes it through AI, reads the database within the cloud platform system, compares the received data with the information data within the fault knowledge base, and generates corresponding alarm and processing plan information through the report generation unit;

[0024] Cloud platform system: a cloud server equipped with cloud platform server software and storing the corresponding database;

[0025] Human-computer interaction system: Relevant personnel use the human-computer interaction system to identify the cause of the fault, eliminate the fault, and register the equipment operation and maintenance records in the database.

[0026] Preferably, the human-computer interaction system includes four functional items: user management, equipment diagnostic records, database management and background controller;

[0027] User management is used to set the unique permissions of the system "administrator" and manage all user accounts of the system to ensure the confidentiality of the system;

[0028] Device diagnostic records are used to view all diagnostic records in the diagnostic history library in the cloud platform system;

[0029] Knowledge base management is used to modify and expand the diagnostic knowledge in the fault knowledge base;

[0030] The background controller is used for remote operation and maintenance troubleshooting and remote control of the automatic repair system.

[0031] Preferably, the human-computer interaction system further includes a central processing unit, a background controller and a display alarm module.

[0032] Preferably, the automatic repair system is a remote execution system, which is used for an operator to control the running of a corresponding program through a background controller via the remote execution system.

[0033] Preferably, the display alarm module visually displays the diagnosis results output by the fault diagnosis module, and when a fault is detected in the mechanical equipment, promptly issues an alarm signal and displays detailed information such as the fault type and fault severity.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. In the present invention, by setting up multiple sensors and collecting multi-source data during the operation of mechanical equipment and fusing them, the operating status of the mechanical equipment can be fully reflected. Compared with the traditional single data diagnosis method, the accuracy and reliability of fault diagnosis are greatly improved.

[0036] 2. In the present invention, the collected data uses AI technology to analyze and process large amounts of data, which can generate scientific and reasonable processing strategies and provide strong support for operation and maintenance decisions.

[0037] 3. In the present invention, the database is set up to automatically merge and update, which has good adaptability to complex and changeable operating conditions and effectively improves the efficiency and accuracy of fault diagnosis.

[0038] 4. In the present invention, the intelligent fault diagnosis system can realize real-time monitoring and diagnosis of mechanical equipment faults, timely discover potential faults and issue alarms, which helps to reduce equipment downtime, reduce maintenance costs, and improve the safety and reliability of industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0040] Figure 2 It is a schematic diagram of the device group structure of the present invention;

[0041] Figure 3 It is a structural diagram of the data acquisition module of the present invention;

[0042] Figure 4 It is a schematic diagram of the structure of the data analysis and processing system of the present invention;

[0043] Figure 5 It is a schematic diagram of the cloud platform structure of the present invention;

[0044] Figure 6 It is a schematic diagram of the human-computer interaction system of the present invention. DETAILED DESCRIPTION

[0045] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0046] Embodiment 1 provides a method for intelligent fault diagnosis of mechanical equipment, the method comprising the following steps:

[0047] S1: Install multiple sensors at corresponding positions of the mechanical equipment, and collect multi-source data during the operation of the mechanical equipment through the data acquisition module;

[0048] S2: Establish a database, obtain basic information data of the device to be diagnosed, and store it in the database as historical data;

[0049] S3: using the data acquisition module to transmit the real-time multi-source data to the data analysis and processing system through the data transmission system;

[0050] S4: The data input unit in the data analysis and processing system receives the multi-source data that is pre-processed by the data acquisition module and works in real time, and uses the data enhancement unit to combine the features of different types of data according to the data feature fusion method to generate the features of the fused multi-source data;

[0051] S5: The data analysis and processing system uses the internal AI recognition module to read the database within the cloud platform system, calculates the similarity of the multi-source data characteristics based on real-time work, and compares the similarity of the multi-source data characteristics of real-time work with the fault characteristics of each historical data in the fault knowledge base in the database through the AI ​​analysis module;

[0052] S6: When the multi-source data characteristics of real-time work are fault data, the AI ​​recognition module extracts the multi-source data of real-time work and combines it with the fault knowledge base in the database to update it, obtains new historical data fault characteristics, and stores them in the fault knowledge base;

[0053] S7: The AI ​​analysis module within the data analysis and processing system identifies real-time data fault characteristics and automatically reads the corresponding historical data fault characteristic data. The report generation unit generates alarm and processing solution information, which is promptly pushed to the device terminal of the relevant operator through the cloud server in the cloud platform system. At the same time, the data is transmitted to the automatic repair system through the data transmission system to achieve automatic repair.

[0054] S8: When the automatic repair system fails to eliminate the existing fault data after automatic repair, or when the AI ​​recognition module cannot extract the fault characteristics of the historical data in the fault knowledge base, or when there is no corresponding emergency treatment plan in the fault knowledge base, the fault confirmation alarm information will be sent to the smart terminal device of the relevant management personnel, and an alarm will be issued through the display alarm module at the same time;

[0055] S9: Relevant management personnel use the human-computer interaction system to check the real-time operation data of the equipment, real-time feedback information from various sensors, and historical monitoring videos to identify the cause of the fault. They then use the background controller to perform remote operation and maintenance to troubleshoot the fault, register the equipment operation and maintenance records in the database, and store them in the diagnostic history library in the database according to the fault type and downtime time mark, and update the new fault knowledge base.

[0056] Among them, the multiple sensors include vibration sensors, temperature sensors, current sensors and pressure sensors.

[0057] The multi-source data includes vibration data, temperature data, current data and pressure data.

[0058] Vibration sensors, temperature sensors, current sensors, and pressure sensors are installed at key locations on mechanical equipment. Vibration sensors are acceleration-type sensors, installed at locations such as bearing seats to collect vibration acceleration signals during operation. Temperature sensors are thermocouples, installed on components prone to heat, such as motor windings and bearings, to monitor component temperatures in real time. Current sensors are Hall effect sensors, connected in series with the equipment's power supply circuit to obtain the equipment's operating current. Pressure sensors are installed in locations where pressure needs to be monitored, such as hydraulic systems, to collect pressure data.

[0059] Embodiment 2, a mechanical equipment intelligent fault diagnosis system, including an equipment group, a data acquisition module, a data transmission system, an automatic repair system, a data analysis and processing system, a cloud platform system and a human-computer interaction system;

[0060] Equipment group: It is composed of multiple mechanical equipment to facilitate the inspection and maintenance of each mechanical equipment;

[0061] Data acquisition module: contains a variety of sensors, used to collect vibration, temperature, current, pressure and other multi-source data during the operation of mechanical equipment, and perform preliminary preprocessing on the collected data;

[0062] Data transmission system: wirelessly transmits the data collected by the data acquisition module to the data analysis and processing system;

[0063] Automatic repair system: realize simple restart operation and remote connection with the background;

[0064] Data analysis and processing system: Receives data transmitted by the data transmission system, analyzes it through AI, reads the database within the cloud platform system, compares the received data with the information data within the fault knowledge base, and generates corresponding alarm and processing plan information through the report generation unit;

[0065] Cloud platform system: a cloud server equipped with cloud platform server software and storing the corresponding database;

[0066] Human-computer interaction system: Relevant personnel use the human-computer interaction system to identify the cause of the fault, eliminate the fault, and register the equipment operation and maintenance records in the database.

[0067] The human-computer interaction system includes four functional items: user management, equipment diagnostic records, database management and background controller;

[0068] User management is used to set the unique permissions of the system "administrator" and manage all user accounts of the system to ensure the confidentiality of the system;

[0069] Device diagnostic records are used to view all diagnostic records in the diagnostic history library in the cloud platform system;

[0070] Knowledge base management is used to modify and expand the diagnostic knowledge in the fault knowledge base;

[0071] The background controller is used for remote operation and maintenance troubleshooting and remote control of the automatic repair system.

[0072] Wherein, the human-computer interaction system also includes a central processing unit, a background controller and a display alarm module.

[0073] Wherein, the automatic repair system is a remote execution system, which is used for an operator to control the running of a corresponding program through a background controller through the remote execution system.

[0074] The display alarm module visually displays the diagnosis results output by the fault diagnosis module. When a fault is detected in the mechanical equipment, an alarm signal is promptly issued and detailed information such as the fault type and fault severity is displayed.

[0075] The multi-source data features collected in real time and pre-processed and fused are compared with the data features within the fault knowledge base to determine the probability distribution of the current operating status of the mechanical equipment. The set threshold is used to determine whether the equipment is in a fault state. If it is determined to be in a fault state, the AI ​​analysis module identifies the real-time data fault features and automatically reads the corresponding historical data fault feature data. The report generation unit produces alarm and processing plan information, and pushes the alarm and processing plan information to the equipment terminal of the relevant operator in a timely manner through the cloud server in the cloud platform system, and transmits the diagnosis results to the display and alarm module for display and alarm.

[0076] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent fault diagnosis of mechanical equipment, characterized by: The fault diagnosis method comprises the following steps: S1: Install multiple sensors at corresponding positions of the mechanical equipment, and collect multi-source data during the operation of the mechanical equipment through the data acquisition module; S2: Establish a database, obtain basic information data of the device to be diagnosed, and store it in the database as historical data; S3: using the data acquisition module to transmit the real-time multi-source data to the data analysis and processing system through the data transmission system; S4: The data input unit in the data analysis and processing system receives the multi-source data that is pre-processed by the data acquisition module and works in real time, and uses the data enhancement unit to combine the features of different types of data according to the data feature fusion method to generate the features of the fused multi-source data; S5: The data analysis and processing system uses the internal AI recognition module to read the database within the cloud platform system, calculates the similarity of the multi-source data characteristics based on real-time work, and compares the similarity of the multi-source data characteristics of real-time work with the fault characteristics of each historical data in the fault knowledge base in the database through the AI ​​analysis module; S6: When the multi-source data characteristics of real-time work are fault data, the AI ​​recognition module extracts the multi-source data of real-time work and combines it with the fault knowledge base in the database to update it, obtains new historical data fault characteristics, and stores them in the fault knowledge base; S7: The AI ​​analysis module within the data analysis and processing system identifies real-time data fault characteristics and automatically reads the corresponding historical data fault characteristic data. The report generation unit generates alarm and processing solution information, which is promptly pushed to the device terminal of the relevant operator through the cloud server in the cloud platform system. At the same time, the data is transmitted to the automatic repair system through the data transmission system to achieve automatic repair. S8: When the automatic repair system fails to eliminate the existing fault data after automatic repair, or when the AI ​​recognition module cannot extract the fault characteristics of the historical data in the fault knowledge base, or when there is no corresponding emergency treatment plan in the fault knowledge base, the fault confirmation alarm information will be sent to the smart terminal device of the relevant management personnel, and an alarm will be issued through the display alarm module at the same time; S9: Relevant management personnel use the human-computer interaction system to check the real-time operation data of the equipment, real-time feedback information from various sensors, and historical monitoring videos to identify the cause of the fault. They then use the background controller to perform remote operation and maintenance to troubleshoot the fault, register the equipment operation and maintenance records in the database, and store them in the diagnostic history library in the database according to the fault type and downtime time mark, and update the new fault knowledge base.

2. The intelligent fault diagnosis method for mechanical equipment according to claim 1, characterized in that: The various sensors include vibration sensors, temperature sensors, current sensors and pressure sensors.

3. The intelligent fault diagnosis method for mechanical equipment according to claim 1, characterized in that: The multi-source data includes vibration data, temperature data, current data and pressure data.

4. A mechanical equipment intelligent fault diagnosis system, wherein the fault diagnosis system adopts the mechanical equipment intelligent fault diagnosis method according to any one of claims 1 to 3, characterized in that: Including equipment groups, data acquisition modules, data transmission systems, automatic repair systems, data analysis and processing systems, cloud platform systems and human-computer interaction systems; Equipment group: It is composed of multiple mechanical equipment to facilitate the inspection and maintenance of each mechanical equipment; Data acquisition module: contains a variety of sensors, used to collect vibration, temperature, current, pressure and other multi-source data during the operation of mechanical equipment, and perform preliminary preprocessing on the collected data; Data transmission system: wirelessly transmits the data collected by the data acquisition module to the data analysis and processing system; Automatic repair system: realize simple restart operation and remote connection with the background; Data analysis and processing system: Receives data transmitted by the data transmission system, analyzes it through AI, reads the database within the cloud platform system, compares the received data with the information data within the fault knowledge base, and generates corresponding alarm and processing plan information through the report generation unit; Cloud platform system: a cloud server equipped with cloud platform server software and storing the corresponding database; Human-computer interaction system: Relevant personnel use the human-computer interaction system to identify the cause of the fault, eliminate the fault, and register the equipment operation and maintenance records in the database.

5. The intelligent fault diagnosis system for mechanical equipment according to claim 4, characterized in that: The human-computer interaction system includes four functional items: user management, equipment diagnostic records, database management and background controller; User management is used to set the unique permissions of the system "administrator" and manage all user accounts of the system to ensure the confidentiality of the system; Device diagnostic records are used to view all diagnostic records in the diagnostic history library in the cloud platform system; Knowledge base management is used to modify and expand the diagnostic knowledge in the fault knowledge base; The background controller is used for remote operation and maintenance troubleshooting and remote control of the automatic repair system.

6. The intelligent fault diagnosis system for mechanical equipment according to claim 5, characterized in that: The human-computer interaction system also includes a central processing unit, a background controller and a display alarm module.

7. The intelligent fault diagnosis system for mechanical equipment according to claim 6, characterized in that: The automatic repair system is a remote execution system, which is used for operators to control the running of corresponding programs through the remote execution system via a background controller.

8. The intelligent fault diagnosis system for mechanical equipment according to claim 7, characterized in that: The display alarm module visually displays the diagnosis results output by the fault diagnosis module. When a fault in the mechanical equipment is detected, an alarm signal is promptly issued and detailed information such as the fault type and fault severity is displayed.

Images