Water pump and oil pump online monitoring intelligent fault pre-judging method and system

Abstract

The invention discloses a water pump and oil pump on-line monitoring intelligent fault pre-judgment method and system, and relates to the technical field of automation equipment management, and the method comprises the steps: obtaining the related operation data of first equipment; the related operation data are accessed to a first diagnosis server; the first diagnosis server carries out analysis and processing, and constructs a calculation model for fault diagnosis; and performing optimal start-stop operation control on the first equipment according to the diagnosis result. According to the water pump and oil pump on-line monitoring intelligent fault pre-judgment method, the dynamic monitoring and analysis capacity of the equipment state is achieved, the accuracy and predictability of fault diagnosis are remarkably improved, a scientific and credible analysis basis is provided for equipment maintenance decision making of a user, and finally accidental shutdown and maintenance cost are greatly reduced; and the overall production benefit is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automated equipment management, and in particular to an intelligent fault prediction method and system for online monitoring of a water pump or oil pump. Background Art

[0002] Among the auxiliary equipment in hydropower stations and related industries, water pumps and oil pumps are key equipment. These equipment usually operate in complex working conditions and face continuous high loads, frequent starts and stops, and long-term operation. Traditional protection equipment mostly uses circuit breakers, thermal relays, soft starters, and motor protectors to provide electrical protection. These devices have played an important role in industrial systems in the past. They are mainly used for emergency protection when motors have short circuits, overloads, overcurrents, and other faults, thereby preventing a wider range of equipment damage or circuit hazards. Circuit breakers and thermal relays usually judge the status of equipment through abnormal detection of single parameters such as current and voltage, and take action to cut off the power supply, while soft starters and motor protectors mainly reduce the peak current of motor starting and optimize the protection strategy during motor operation to extend the life of the equipment and improve the operation stability.

[0003] Traditional protection devices will only work when abnormal conditions are detected. They lack the ability to predict and cannot effectively identify minor changes in the operating status of the equipment and potential failure trends. The second is the single signal detection and judgment mechanism. Most of these devices are based on simple logical judgments and cannot perform complex data analysis and in-depth diagnosis. For motors that have been in a critical state for a long time and have slight abnormalities, more sophisticated data analysis may be required to accurately identify hidden dangers. Due to the limitations of traditional protection equipment, operation and maintenance personnel cannot grasp the comprehensive health status of the equipment and often need to wait until the equipment has failed before taking maintenance and repair measures. This not only increases the cost of operation and maintenance, but also causes production downtime, reduced efficiency and greater economic losses. Due to the lack of data perception capabilities, predictive maintenance cannot be effectively carried out, and the system has bottlenecks in improving safety and efficiency. This limitation gradually exposes that the traditional equipment protection mode can no longer adapt to the complex operation and management needs of modern factories and hydropower stations. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing technology has no predictive function for motor failure, and operation and maintenance personnel cannot predict the problem in advance.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for online monitoring of water pumps and oil pumps and intelligent fault prediction, comprising:

[0007] Acquiring relevant operation data of the first device;

[0008] Connecting the relevant operation data to the first diagnostic server;

[0009] The first diagnostic server performs analysis and processing, and constructs a calculation model for fault diagnosis;

[0010] Optimal start / stop operation control is performed on the first device according to the diagnosis result.

[0011] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, wherein: obtaining the relevant operating data of the first device includes obtaining the relevant operating data of the first device by constructing a data perception system.

[0012] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, the access to the first diagnostic server includes accessing data to the first diagnostic server via field bus and Ethernet.

[0013] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, the analysis and processing includes that the data is analyzed and processed and applied by the first diagnostic server to construct an application system.

[0014] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, the construction of the calculation model includes performing data cleaning and screening operations, storing valid data in a database and performing model calculations.

[0015] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, the fault diagnosis includes analyzing the motor overload fault on the operating voltage curve of general electrical equipment; using the refined current analysis method, the motor phase loss, turn-to-turn short circuit, and phase imbalance faults can be obtained.

[0016] As a preferred solution of the intelligent fault prediction method for online monitoring of water pumps and oil pumps described in the present invention, the optimal start-stop operation control includes analyzing and comparing data at different times during the start-up and shutdown process of the equipment, providing an analysis basis for users to identify related faults.

[0017] As a preferred solution of the water pump and oil pump online monitoring intelligent fault prediction system of the present invention, wherein: data perception module: used to obtain the operation data related to the first device, and to build a data perception system through sensors and data collectors installed on the device to obtain the key data of the device operation status, pressure, temperature, and flow;

[0018] Data transmission module: used to connect the collected relevant operation data to the first diagnostic server. This module supports data transmission via field bus and Ethernet to ensure that the data is delivered to the diagnostic server efficiently and in real time.

[0019] Diagnostic analysis module: executed by the first diagnostic server, its main function is to analyze and process the acquired operation data and build a calculation model for fault diagnosis; the data is cleaned, filtered and classified in this module, stored in the database, and the model algorithm is used to diagnose the fault of the equipment status;

[0020] Control operation module: Based on the results of the diagnostic analysis, the first device is optimally started and stopped. This module analyzes and compares the data during the start and stop process of the device to help users identify and predict potential faults, providing support for the safe and efficient operation of the equipment.

[0021] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for online monitoring of water pumps and oil pumps and intelligent fault prediction.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent fault prediction method for online monitoring of a water pump or an oil pump.

[0023] The beneficial effects of the present invention are as follows: it realizes comprehensive data collection and storage of the operating status of water pumps and oil pumps, strengthens the real-time perception capability of equipment status, improves the accuracy of diagnostic analysis, and ultimately enhances the initiative and precision of equipment management. The water pump and oil pump online monitoring intelligent fault prediction method provided by the present invention realizes the dynamic monitoring and analysis capability of equipment status, significantly improves the accuracy and predictability of fault diagnosis, and provides a scientific and reliable analysis basis for users' equipment maintenance decisions, ultimately greatly reducing unexpected downtime and maintenance costs, and improving overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 An overall flow chart of an intelligent fault prediction method for online monitoring of a water pump or oil pump provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0027] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for online monitoring of water pumps and oil pumps for intelligent fault prediction, comprising:

[0028] S1: Obtaining relevant operation data of the first device.

[0029] Furthermore, the obtaining of the operating data related to the first device includes obtaining the operating data related to the first device by constructing a data perception system.

[0030] In an embodiment of the present application, the first device may be a water pump, an oil pump and auxiliary equipment of a hydropower station, and the data perception system may be constructed such that the system uses a 4-20mA analog signal or Modbus communication data to access the PLC system, and the PLC performs relevant data conversion internally. The equipment health diagnosis system collects PLC data through OPC communication.

[0031] Furthermore, data cleaning and screening can be performed by the data processing module in the server to remove redundant, invalid or abnormal data and ensure data quality and availability.

[0032] In an optional embodiment, the data perception system can also be constructed by using a wireless sensor network (WSN) for data collection. Various types of wireless sensor nodes are installed on water pumps, oil pumps and auxiliary equipment of hydropower stations to collect the operating parameters of the equipment in real time (such as vibration, temperature, pressure, etc.). The collected data is transmitted to the gateway device through wireless communication methods (such as Wi-Fi, ZigBee, LoRa, etc.), so as to realize real-time monitoring of the equipment status. The data is first stored and managed in a unified manner. The system can be classified and stored according to parameters such as equipment type, collection point, data type, etc., to form a comprehensive database of structured and unstructured data.

[0033] It should be noted that traditionally, circuit breakers, thermal relays, soft starters, and motor protectors are used as protection devices. Such protection will only work when the motor actually fails. There is no predictive function for motor failures, and operation and maintenance personnel cannot predict them in advance.

[0034] S2: Connecting relevant operating data to the first diagnostic server.

[0035] In the embodiment of the present application, the first diagnostic server may be an equipment health diagnostic server. Accessing the first diagnostic server includes obtaining relevant operation data of water pump and oil pump equipment, accessing the data to the equipment health diagnostic server through a field bus or Ethernet, and the equipment health diagnostic server uniformly stores the data, specifically including A1 to A4:

[0036] A1, Real-time collection of operating data: Through the sensor equipment installed on site, the operating data of water pumps, oil pumps and other equipment are obtained, including but not limited to current, voltage, temperature, vibration and other parameters. These data can be collected in real time to the local data acquisition device or controller through the field bus or Ethernet interface. The data acquisition device monitors the operating status of the equipment in real time and samples data according to the predetermined sampling frequency and signal type to ensure the timeliness and integrity of the data.

[0037] A2, Data transmission and communication protocol conversion: The collected data is sent to the equipment health diagnosis server through the fieldbus protocol or Ethernet protocol. Specific transmission protocols may include Modbus TCP / IP, Ethernet / IP, etc., and the appropriate communication method is selected according to system requirements. If there is a protocol inconsistency problem between the field data acquisition device and the diagnosis server, a gateway or protocol conversion module can be introduced in the middle to achieve data protocol conversion and seamless transmission.

[0038] A3, Data storage management in the diagnostic server: After receiving the transmitted data, the device health diagnostic server performs preliminary verification on the data, including data integrity verification, redundant data removal and data format normalization.

[0039] A4. Data analysis and unified management: The equipment health diagnosis server centrally manages the stored data and uses built-in analysis algorithms or machine learning models to conduct in-depth analysis and processing of equipment operation data. The analysis content may include equipment health status assessment, trend prediction, fault diagnosis, etc.

[0040] Furthermore, the effective data is stored in the server's database, which can select a relational database to store and manage equipment operation data as needed. The server generates diagnostic reports, forecast warnings, and operation optimization suggestions through data analysis, providing scientific support for equipment management and maintenance.

[0041] In an optional embodiment, the relevant operation data access server may also be, B1-B5:

[0042] B1, obtain the field data acquisition devices deployed on the equipment (such as sensor nodes, data collectors, etc.) to collect the equipment's operating data in real time, including key parameters such as current, voltage, temperature, vibration, etc.

[0043] B2, the field data acquisition device can be configured to support multiple communication protocols (such as Modbus, 4-20mA signal, etc.) to meet the needs of different types of equipment, and aggregate data through gateway devices or edge computing nodes.

[0044] B3, the collected data is uploaded to the cloud platform through the local gateway. Network connection methods can include wired Ethernet, Wi-Fi, cellular network (such as 4G / 5G), LoRaWAN, etc. The specific method can be flexibly selected according to the on-site environment. The security of data transmission must be ensured during data upload, such as using TLS / SSL encryption to prevent data tampering or theft.

[0045] B4, the cloud platform centrally stores the received data and cleans, filters and preliminarily processes the data through a distributed data processing architecture (such as cloud databases, distributed computing clusters). This step may include removing redundant data, processing outliers, and converting data formats.

[0046] B5. Data is transmitted to the device health diagnosis server through a secure interface. The cloud platform transmits the processing results and necessary operation data to the device health diagnosis server through a secure data connection interface (such as an interface based on REST API, WebSocket and other technologies).

[0047] It should be noted that security measures such as data encryption and identity authentication are adopted during data transmission to ensure the integrity and security of the data.

[0048] Embodiment 2: The following is an embodiment of the present invention, which provides an intelligent fault prediction method for online monitoring of a water pump or oil pump, comprising:

[0049] S3: The first diagnosis server performs analysis and processing, and builds a calculation model for fault diagnosis.

[0050] Further, the analysis and processing includes that the data is analyzed and processed by the first diagnostic server and applied to construct an application system. The data is analyzed and processed by the device health diagnosis and applied to construct an application system with the device as the core and the device operation management as the focus.

[0051] Furthermore, the construction of the calculation model includes performing data cleaning and screening operations, storing valid data in a database and performing model calculations.

[0052] In the embodiment of the present application, constructing a calculation model for fault diagnosis may specifically include C1 to C4:

[0053] C1, pre-process the collected operation data, including data denoising, data normalization, outlier detection and processing, etc., to ensure the accuracy and consistency of the data. Extract characteristic parameters related to the equipment operation status, such as current fluctuation trend, temperature change rate, vibration frequency characteristics, etc., to provide feature input for model establishment. Feature extraction is the key to model performance and helps to more accurately reflect the equipment operation status.

[0054] C2, build a machine learning-based model and a fault diagnosis model. When training the model, a large amount of historical operation data, including normal operation data and fault data, needs to be input. The model is trained through supervised learning so that it can identify fault characteristics. The model is verified by cross-validation method to ensure the accuracy and generalization ability of the model, and the parameters of the model are optimized according to the verification results.

[0055] C3, build models based on time series analysis, such as long short-term memory networks (LSTM) or ARIMA models, to predict the trend of equipment operation status and identify potential failure trends. Predictive maintenance models can provide early warning of possible equipment failures by identifying the changing trends of operating parameters. Use the prediction data generated by the model to provide preventive maintenance suggestions to operation and maintenance personnel to reduce the occurrence of equipment failures.

[0056] C4, using the fault tree analysis (FTA) method to build a diagnostic model, systematically decompose the possible faults of the equipment and establish logical relationships. By combining the equipment operation data and the logical inference of the model, the current failure mode of the equipment and its possible causes can be determined.

[0057] In an optional embodiment, the fault diagnosis may also be performed by a rule-based expert system diagnosis method, specifically including D1 to D4:

[0058] D1, establish a rule base: through in-depth communication and analysis with experts in the field of equipment, collect and summarize common equipment faults and their corresponding diagnostic rules. Each rule consists of a condition part and a result part. The condition part includes the fault triggering condition, and the result part is the corresponding fault type or recommended treatment measures. The rule base should cover common fault modes and characteristic parameters in equipment operation, usually including logical rules (such as "if the current exceeds the threshold and the temperature exceeds the standard, it is judged as an overload fault"), critical value rules, trend change rules, etc.

[0059] D2, obtain equipment operation data: collect equipment operation data in real time through data acquisition devices or sensor systems, including current, voltage, temperature, vibration, speed and other information. These data will be used as input to the expert system for fault diagnosis. Data acquisition can be connected to the diagnostic system through fieldbus, PLC or other data acquisition devices to ensure the real-time and accuracy of the data.

[0060] D3, rule matching and reasoning process: The reasoning engine matches the device operation data with the rules in the rule base. The reasoning engine will check whether the data meets the condition part of a rule one by one. If the condition part is met, the result part of the rule will be triggered. The reasoning process can be divided into two methods: forward reasoning and reverse reasoning.

[0061] D4, Generate diagnostic results and suggestions: Once the rules are matched successfully, the system generates the corresponding diagnostic results, including the fault type, fault cause, and recommended maintenance or repair measures. The diagnostic results can be presented in a list, table, or other visual form to help users intuitively understand the status of the device. In the case of multiple rule matches, the system can sort the diagnostic results by priority or confidence level to ensure that users can focus on the most important or most likely faults.

[0062] Furthermore, the fault diagnosis includes analyzing the motor overload fault on the operating voltage curve of general electrical equipment; using the refined current analysis method, the motor phase loss, turn-to-turn short circuit and phase imbalance faults can be obtained.

[0063] It should be noted that a diagnostic model that can be updated and self-optimized in real time is constructed, and real-time data and feedback mechanisms are used to enable the model to be adaptively adjusted during operation. This not only improves the accuracy of diagnosis, but also optimizes the diagnostic rules of the model according to the actual operating conditions of the equipment. The online model uses real-time data input and combines historical models for rapid analysis to identify equipment failures or warnings, and achieve rapid response and fault handling decision support. Feedback information is generated based on the model diagnosis results, including fault type, fault severity, and preventive recommendations. The diagnostic results are used to optimize the start and stop control of the equipment to ensure that the equipment operates in the optimal state or is shut down for maintenance when necessary, thereby avoiding greater losses and downtime.

[0064] S4: Performing optimal start / stop operation control on the first device according to the diagnosis result.

[0065] Furthermore, the optimal start-stop operation control includes analyzing and comparing data at different times during the start-up and shutdown process of the equipment, providing an analysis basis for the user to identify related faults.

[0066] Furthermore, we will strengthen the ability to perceive equipment status, utilize comprehensive analysis and diagnostic technology, combined with preventive maintenance and repair management, to achieve intelligent diagnosis and repair decisions for equipment failures, realize closed-loop management of the entire life cycle of equipment, provide a more reliable, efficient and safe equipment operating environment, improve production efficiency, and minimize production interruptions and downtime caused by water pump and oil pump failures.

[0067] It should be noted that the rule-based expert system can quickly judge and identify equipment failures by establishing and using an expert rule base, which is particularly suitable for scenarios with known failure modes. Its flexibility and scalability enable the system to continuously optimize and improve the accuracy and efficiency of diagnosis.

[0068] Example 3: The following is an embodiment of the present invention, which provides an intelligent fault prediction method for online monitoring of water pumps and oil pumps. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0069] First, in this embodiment, two water pump devices are selected as the first devices, numbered as device A and device B, respectively, wherein device A adopts the traditional fault monitoring and manual control system, and device B applies the online monitoring intelligent fault prediction system described in the present invention. The experiment is carried out in an environment where the auxiliary equipment of the hydropower station is operating normally, with the purpose of evaluating the advantages and innovation of the invented system. The experimental environment temperature is controlled at 20℃ to 25℃, and the relative humidity is 45% to 55%.

[0070] By building a data perception system, the relevant operating data of equipment B is collected, including current, voltage, temperature, vibration and flow parameters. The data acquisition device is connected to the programmable logic controller (PLC) through 4-20mA analog signals and Modbus communication protocol, and converted by the PLC into a standard format. Subsequently, the data is connected to the first diagnostic server through fieldbus and Ethernet. In the diagnostic server, the data is first cleaned and screened to remove abnormal and invalid data to ensure the authenticity and consistency of the data. The processed valid data is stored in the database, and real-time analysis and model calculation are performed.

[0071] Next, the diagnostic server built a fault diagnosis model based on machine learning to analyze and process the operating data of device B. The model includes overload fault detection, motor phase loss detection, turn-to-turn short circuit diagnosis, and phase imbalance detection. The system can identify fault conditions in real time and provide predictive warnings. Some of the results are shown in Table 1. According to the diagnosis results, the system starts and stops device B through the optimal start-stop control logic to reduce unnecessary load and energy consumption during equipment operation and improve the equipment's operating reliability.

[0072] Table 1 Test data record form

[0073]

[0074] By comparing the data in the above tables, it can be seen that the water pump and oil pump online monitoring intelligent fault prediction system of the present invention shows obvious advantages over device B. When device A is running in the traditional fault monitoring mode, when key parameters such as current, voltage and temperature fluctuate and exceed the normal range, it fails to predict and identify faults in advance. Its operating median current rises to 55A, voltage drops to 395V, and temperature rises to 35°C, resulting in reduced operating efficiency, increased energy consumption, and 7 fault shutdowns.

[0075] In contrast, device B can effectively identify the changing trend of the current through real-time monitoring and diagnosis by the fault prediction system of the present invention. When the current reaches 53A, the system provides a fault warning and restores the current to 51A through optimal start-stop control, thus avoiding the occurrence of overload faults. The voltage is controlled between 397-399V, the temperature fluctuates between 28°C and 32°C, and the vibration remains in a relatively stable range. Device B only experienced two fault shutdowns in 1200 hours of operation, and thanks to the system's intelligent diagnosis and optimal control strategy, the number of failures was further reduced to 1, significantly reducing the downtime and maintenance costs of the equipment.

[0076] Embodiment 4: The following is an embodiment of the present invention, which provides an intelligent fault prediction system for online monitoring of a water pump or oil pump, including:

[0077] Data perception module: used to obtain the operating data related to the first device. Through the sensors and data collectors installed on the device, a data perception system is built to obtain key data such as the device's operating status, pressure, temperature, and flow.

[0078] Data transmission module: used to connect the collected relevant operation data to the first diagnostic server. This module supports data transmission via field bus and Ethernet to ensure that the data is delivered to the diagnostic server efficiently and in real time.

[0079] Diagnostic analysis module: executed by the first diagnostic server, its main function is to analyze and process the acquired operating data and build a calculation model for fault diagnosis; the data is cleaned, filtered and classified in this module, stored in the database, and the model algorithm is used to diagnose the fault status of the equipment.

[0080] Control operation module: Based on the results of the diagnostic analysis, the first device is optimally started and stopped. This module analyzes and compares the data during the start and stop process of the device to help users identify and predict potential faults, providing support for the safe and efficient operation of the equipment.

[0081] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0082] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0083] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0084] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0085] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for online monitoring of water pumps and oil pumps for intelligent fault prediction, characterized in that: include: Acquiring relevant operation data of the first device; Connecting the relevant operation data to the first diagnostic server; The first diagnostic server performs analysis and processing, and constructs a calculation model for fault diagnosis; Optimal start / stop operation control is performed on the first device according to the diagnosis result.

2. The water pump and oil pump online monitoring intelligent fault prediction method according to claim 1, characterized in that: The obtaining of the first device related operating data includes obtaining the first device related operating data by constructing a data perception system.

3. The water pump and oil pump online monitoring intelligent fault prediction method according to claim 2, characterized in that: The accessing to the first diagnostic server includes accessing data to the first diagnostic server via a field bus and Ethernet.

4. The water pump and oil pump online monitoring intelligent fault prediction method as claimed in claim 3, characterized in that: The analysis and processing includes that the data is analyzed and processed by the first diagnostic server, and applied to construct an application system.

5. The water pump and oil pump online monitoring intelligent fault prediction method according to claim 4, characterized in that: The construction of the calculation model includes performing data cleaning and screening operations, storing valid data in a database and performing model calculations.

6. The water pump and oil pump online monitoring intelligent fault prediction method according to claim 5, characterized in that: The fault diagnosis includes analyzing the motor overload fault based on the operating voltage curve of general electrical equipment; using the refined current analysis method, the motor phase loss, turn-to-turn short circuit and phase imbalance faults can be obtained.

7. The water pump and oil pump online monitoring intelligent fault prediction method according to claim 6, characterized in that: The optimal start-stop operation control includes analyzing and comparing data at different times during the start-stop process of the equipment, and providing an analysis basis for the user to identify related faults.

8. A system using the water pump and oil pump online monitoring intelligent fault prediction method as claimed in any one of claims 1 to 7, characterized in that: Data perception module: used to obtain the operation data related to the first device, and to build a data perception system through sensors and data collectors installed on the device to obtain key data such as the device's operation status, pressure, temperature, and flow rate; Data transmission module: used to connect the collected relevant operation data to the first diagnostic server. This module supports data transmission via field bus and Ethernet to ensure that the data is delivered to the diagnostic server efficiently and in real time. Diagnostic analysis module: executed by the first diagnostic server, its main function is to analyze and process the acquired operation data and build a calculation model for fault diagnosis; the data is cleaned, filtered and classified in this module, stored in the database, and the model algorithm is used to diagnose the fault of the equipment status; Control operation module: Based on the results of the diagnostic analysis, the first device is optimally started and stopped. This module analyzes and compares the data during the start and stop process of the device to help users identify and predict potential faults, providing support for the safe and efficient operation of the equipment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the water pump and oil pump online monitoring intelligent fault prediction method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the water pump and oil pump online monitoring intelligent fault prediction method according to any one of claims 1 to 7 are implemented.

Images