Fault early warning method and system for electric pump

Abstract

The invention discloses a fault early warning method and system for an electric pump, and relates to the technical field of fault early warning methods, and the method comprises the steps: determining an emergency floating parameter combination of the electric pump based on a plurality of working parameters and corresponding working stages of the electric pump; according to the emergency floating parameter combination of the electric pump, the multiple fault parts of the electric pump and the service life of the electric pump, the multiple abnormal fault parts and the conventional fault parts are determined, and the accuracy of the multiple abnormal fault parts and the conventional fault parts is improved. Therefore, a corresponding fault maintenance plan is determined based on each fault maintenance combination, the current working node of the electric pump and the working plan of the electric pump; according to the invention, the plurality of sub-fault maintenance items are determined based on the identification of the fault maintenance plan, and the dynamic maintenance events of the plurality of sub-fault maintenance items are determined according to the item content of each sub-fault maintenance item, the distribution positions of the plurality of fault parts and the fault correlation coefficient, so that the accuracy of the dynamic maintenance events of the plurality of sub-fault maintenance items is improved.

Description

Technical Field

[0001] This invention relates to the technical field of fault early warning methods, and more particularly to a fault early warning method and system for an electric pump. Background Technology

[0002] With the development of technology, electric pumps are devices that convert electrical energy into mechanical energy, mainly used for transporting or pressurizing fluids. They are widely used in various fields such as industry, agriculture, households, and urban infrastructure. In existing technologies, collecting multiple operating parameters of the electric pump and determining the pump's fault events based on these parameters only yields the conventional fault portion. It does not take into account the emergency floating parameter combinations of the electric pump or the multiple fault components of the pump, affecting the gradient fault management of multiple abnormal fault components and failing to achieve dynamic maintenance events for multiple sub-fault maintenance projects. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a method and system for early warning of electric pump failures.

[0004] This invention provides a fault early warning method for an electric pump, comprising: collecting multiple operating parameters of the electric pump; determining the current operating event of the electric pump based on the multiple operating parameters, operating mode, and surrounding operating environment; determining multiple abnormal operating nodes based on the detection of the current operating event of the electric pump; determining multiple fault parts of the electric pump based on each abnormal operating node, associated operating part, and thermal distribution map of the electric pump; determining an emergency floating parameter combination of the electric pump based on the multiple operating parameters and corresponding operating stages; determining multiple abnormal fault parts and regular fault parts based on the emergency floating parameter combination, multiple fault parts of the electric pump, and service life of the electric pump; and performing gradient fault control on the multiple abnormal fault parts; determining corresponding fault correlation coefficients based on the multiple abnormal fault parts and regular fault parts; determining multiple corresponding fault maintenance combinations based on the multiple abnormal fault parts, regular fault parts, and corresponding fault correlation coefficients; determining corresponding fault maintenance plans based on each fault maintenance combination, the current operating node of the electric pump, and the working plan of the electric pump; determining multiple sub-fault maintenance projects based on the identification of the fault maintenance plan; and determining dynamic maintenance events of the multiple sub-fault maintenance projects based on the project content of each sub-fault maintenance project, the distribution location of the multiple fault parts, and the fault correlation coefficient.

[0005] This invention provides a fault early warning system for an electric pump, which is applied to the aforementioned fault early warning method for an electric pump. The fault early warning system includes: The current working event module is used to collect multiple working parameters of the electric pump and determine the current working event of the electric pump based on the multiple working parameters, working mode and surrounding working environment. The fault section module is used to determine multiple abnormal operating nodes based on the detection of the current operating events of the electric pump, and to determine multiple fault sections of the electric pump based on each abnormal operating node, associated operating section, and the thermal distribution diagram of the electric pump. The abnormal fault module is used to determine the emergency floating parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages of the electric pump. Based on the emergency floating parameter combination of the electric pump, multiple fault parts of the electric pump and the service life of the electric pump, it determines multiple abnormal fault parts and regular fault parts, and performs gradient fault control on multiple abnormal fault parts. The fault maintenance plan module is used to determine the corresponding fault correlation coefficients based on multiple abnormal fault components and regular fault components, and to determine multiple corresponding fault maintenance combinations based on multiple abnormal fault components, regular fault components and corresponding fault correlation coefficients; and to determine the corresponding fault maintenance plan based on each fault maintenance combination, the current working node of the electric pump and the working plan of the electric pump. The dynamic maintenance event module is used to identify multiple sub-fault maintenance projects based on the identification of fault maintenance plans, and to determine the dynamic maintenance events of multiple sub-fault maintenance projects according to the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient.

[0006] Compared with the prior art, the beneficial effects of the present invention are: In this embodiment of the invention, the method of this embodiment determines the emergency floating parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages. Multiple abnormal and regular fault parts are determined according to the emergency floating parameter combination, multiple fault components of the electric pump, and the service life of the electric pump. Gradient fault control is then implemented for the multiple abnormal fault parts. The introduction of multiple fault parts accommodates the overall consideration of the emergency floating parameter combination, multiple fault components of the electric pump, and the service life of the electric pump, improving the accuracy of the multiple abnormal and regular fault parts and achieving gradient fault control for the multiple abnormal fault parts.

[0007] Therefore, based on multiple abnormal and regular fault components, corresponding fault correlation coefficients are determined, and multiple fault maintenance combinations are determined based on these components and their correlation coefficients. A corresponding fault maintenance plan is then determined based on each fault maintenance combination, the current operating node of the electric pump, and the pump's work schedule. Multiple sub-fault maintenance items are identified based on the fault maintenance plan. Dynamic maintenance events for these sub-fault maintenance items are determined based on their content, the distribution of multiple fault components, and the fault correlation coefficients. This process introduces a fault maintenance plan, fully considering each fault maintenance combination, the current operating node of the electric pump, and the pump's work schedule. This achieves a holistic consideration of the content, distribution of multiple fault components, and fault correlation coefficients for each sub-fault maintenance item, improving the accuracy of dynamic maintenance events for multiple sub-fault maintenance items. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating the fault early warning method for an electric pump in an embodiment of the present invention. Figure 2 This is a flowchart illustrating step S11 of the electric pump fault early warning method in this embodiment of the invention. Figure 3 This is a flowchart illustrating step S12 in the electric pump fault early warning method in this embodiment of the invention. Figure 4 This is a flowchart illustrating step S13 in the electric pump fault early warning method in this embodiment of the invention. Figure 5 This is a flowchart illustrating step S14 of the electric pump fault early warning method in an embodiment of the present invention. Figure 6 This is a flowchart illustrating step S15 of the electric pump fault early warning method in an embodiment of the present invention. Figure 7 This is a schematic diagram of the structural composition of the electric pump fault early warning system in an embodiment of the present invention. Detailed Implementation

[0009] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0010] Please see Figures 1 to 7 A fault early warning method for an electric pump, applied to fault early warning scenarios; the fault early warning method for the electric pump includes: Step S11: Collect multiple operating parameters of the electric pump, and determine the current operating event of the electric pump based on the multiple operating parameters, operating mode and surrounding working environment; Step S12: Based on the detection of the current working events of the electric pump, determine multiple abnormal working nodes, and based on each abnormal working node, associated working part, and the thermal distribution diagram of the electric pump, determine multiple fault parts of the electric pump. Step S13: Determine the emergency floating parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages. Determine multiple abnormal fault parts and regular fault parts based on the emergency floating parameter combination of the electric pump, multiple fault parts of the electric pump and the service life of the electric pump, and perform gradient fault control on multiple abnormal fault parts. Step S14: Determine the corresponding fault correlation coefficients based on multiple abnormal fault parts and regular fault parts; determine multiple corresponding fault maintenance combinations based on multiple abnormal fault parts, regular fault parts and corresponding fault correlation coefficients; determine the corresponding fault maintenance plan based on each fault maintenance combination, the current working node of the electric pump and the working plan of the electric pump. Step S15: Based on the identification of the fault maintenance plan, identify multiple sub-fault maintenance items, and determine the dynamic maintenance events of the multiple sub-fault maintenance items according to the project content of each sub-fault maintenance item, the distribution location of multiple fault parts and the fault correlation coefficient.

[0011] refer to Figure 2 In step S11, the specific steps are as follows: S111: Real-time monitoring of the electric pump's operation process, and collection of multiple operating parameters of the electric pump at different time periods. Based on the multiple operating parameters of the electric pump and the current operating mode of the electric pump, the corresponding combination of operating parameters is determined, and the current working content is determined based on the combination of operating parameters and the working state of the electric pump. S112: Collect the current position of the electric pump, determine the surrounding working environment based on the environmental detection of the current position of the electric pump, and determine the current working event of the electric pump based on the surrounding working environment, the current working content and the working signal of the electric pump.

[0012] In the embodiments of this application, real-time monitoring is achieved through various sensors installed on the electric pump, including current sensors, voltage sensors, vibration sensors, temperature sensors, pressure sensors, and flow sensors. The data acquisition frequency is set according to the operating characteristics of the electric pump. High-frequency acquisition (e.g., 10-100 times per second) is typically used during critical operating phases, while low-frequency acquisition (e.g., 1-10 times per minute) can be used during stable operation. The data acquisition strategy varies for different time periods, such as different acquisition frequencies and parameter combinations for the startup phase, stable operation phase, load change phase, and shutdown phase. The acquired operating parameters typically include: current, voltage, power, vibration frequency, vibration amplitude, temperature, pressure, flow rate, speed, torque, etc.

[0013] Operating mode refers to the pump's running state, such as start-up mode, normal operation mode, high load mode, low load mode, and fault mode. Different operating modes focus on different combinations of operating parameters. For example, the start-up mode focuses on current and vibration, while the normal operation mode focuses more on temperature and efficiency. The combination of operating parameters is determined through historical data analysis and expert experience. Each operating mode corresponds to a set of key parameters and their normal range. The system will automatically select the appropriate parameter combination for analysis based on the current operating mode, reducing unnecessary data processing.

[0014] Furthermore, the electric pump's position is primarily acquired through position sensors, including photoelectric encoders, magnetic sensors, and Hall effect encoders. These position sensors need to be integrated with the electric pump's control system to provide real-time feedback on the pump's physical position, offering fundamental data for environmental monitoring. Environmental monitoring is achieved through a network of environmental sensors deployed around the pump, including temperature sensors, humidity sensors, gas sensors, and water quality sensors. Environmental monitoring parameters are determined based on the pump's operating environment; for example, in underground environments, parameters such as methane concentration, dust concentration, water temperature, and water pressure need to be monitored. The system compares the acquired environmental parameters with preset environmental models to determine the characteristics and state of the current operating environment. The environmental monitoring results affect the pump's operating parameter thresholds and fault diagnosis criteria; different criteria are used under different environments.

[0015] The system determines the current working event of the electric pump based on the surrounding working environment, current working content, and the pump's working signals. A working event is a comprehensive description of the pump's state when performing specific tasks under specific environmental conditions. The system comprehensively analyzes the surrounding working environment, current working content, and working signals, and determines the current working event through multi-dimensional data fusion. Working signals include dynamic parameters such as the pump's operating sound, vibration characteristics, current waveform, and temperature change trend. Working events are typically classified as: normal operation events, minor abnormal events, serious abnormal events, and emergency fault events. The system uses a pattern recognition algorithm to match the current multi-dimensional features with preset working event patterns to determine the most similar working event type.

[0016] refer to Figure 3 In step S12, the specific steps are as follows: S121: Collect the current working events of the electric pump, determine multiple abnormal working contents based on the detection of the current working events of the electric pump, and determine multiple corresponding abnormal key factors based on the identification of each abnormal working content. S122: Determine the abnormal working node corresponding to the abnormal working content based on multiple abnormal key factors, corresponding time nodes and the working status of the electric pump. At this time, the current working event of the electric pump has multiple abnormal working nodes. S123: In each abnormal working node, the relevant working part of the electric pump in China is determined by tracing the abnormal working node. At the same time, multiple temperature parameters of the electric pump are collected. Based on the multiple temperature parameters, the corresponding temperature detection location and the overall shape of the electric pump, a thermal distribution map of the electric pump is constructed. Based on the thermal distribution map of the electric pump, multiple abnormal working nodes and the corresponding relevant working parts, multiple fault parts of the electric pump are determined.

[0017] In the embodiments of this application, the current working event acquisition is a continuation of step S112. The system has determined the current working event of the electric pump through location information, environmental conditions, and working signals. The working event data is stored in the system's event database, containing information such as event type, occurrence time, duration, and related parameters. The system retrieves the complete data of the current working event through the event ID, including event description, environmental conditions, working parameters, and preliminary evaluation results. Working events are usually stored in structured data format for easy subsequent analysis and processing. The system verifies the completeness and validity of the working event data to ensure data quality.

[0018] Multiple abnormal operating conditions are identified based on the detection of current operating events of the electric pump. Abnormal operating condition detection is achieved by comparing current operating parameters with preset normal operating parameter threshold ranges. The system calls upon the corresponding parameter threshold standard according to the type of the current operating event; different operating events may have different normal parameter ranges. Parameter comparison employs multi-dimensional analysis, including absolute value comparison, rate of change comparison, and trend analysis. Abnormal operating conditions are typically categorized as follows: vibration abnormalities, temperature abnormalities, current abnormalities, pressure abnormalities, flow abnormalities, and noise abnormalities. The system assigns an abnormality level to each detected abnormality, such as minor, moderate, or severe. Abnormal operating conditions are stored in a list format, containing information such as abnormality type, abnormal value, normal range, abnormality level, and detection time.

[0019] In each abnormal work content, multiple corresponding critical factors are identified based on the identification of the abnormal work content. Identification of critical factors involves analyzing the characteristic parameters of the abnormal work content to determine the root cause or key influencing factors leading to the abnormality. The system establishes a mapping relationship between abnormal work content and critical factors, typically based on an expert knowledge base and historical data analysis. Critical factor identification employs multi-dimensional analysis methods, including spectrum analysis, time-domain analysis, trend analysis, and correlation analysis. Each abnormal work content may correspond to multiple critical factors, and the system needs to calculate the weight or degree of influence of each factor. Critical factors typically include: mechanical factors (such as bearing wear, imbalance, misalignment), electrical factors (such as winding short circuits, insulation aging), fluid factors (such as cavitation, blockage), and environmental factors (such as excessively high temperature, excessively high humidity), etc. The system assigns an influence coefficient to each critical factor, representing its contribution to the abnormal work content.

[0020] Furthermore, the system performs time series analysis on each critical abnormal factor, recording its occurrence time, duration, and trend. The time node accuracy is typically at the millisecond level, ensuring that the instantaneous changes of the abnormal factors can be captured. The system establishes a time distribution map of the critical abnormal factors, visually displaying the distribution of each factor on the time axis. For periodically occurring abnormal factors, the system analyzes their periodic characteristics and phase relationships. The time series analysis uses a sliding window technique, with the window size dynamically adjusted according to the working characteristics of the electric pump.

[0021] The system performs correlation analysis between critical abnormal factors and the operating status of the electric pump to determine the performance characteristics of each factor under different operating states. Operating states include start-up, normal operation, load change, and shutdown. The correlation analysis uses correlation calculation methods to quantify the strength of the relationship between abnormal factors and operating states. The system establishes an abnormal factor-operating state correlation matrix to intuitively display the sensitivity of each factor under different states. For highly correlated abnormal factors, the system will further analyze their causal relationship.

[0022] Based on time series analysis and correlation analysis results, the system identifies abnormal working nodes. An abnormal working node is defined as the combined manifestation of abnormal key factors at a specific time point and under a specific working state. Each abnormal working node includes information such as node ID, timestamp, working state, combination of abnormal factors, and severity. The system classifies abnormal working nodes into types such as instantaneous nodes, continuous nodes, and periodic nodes. The node classification results are stored in the abnormal node database, providing a basis for subsequent fault analysis.

[0023] Therefore, in each abnormal operating node, the relevant domestic operating parts of the electric pump are determined by tracing the abnormal operating node. At the same time, multiple temperature parameters of the electric pump are collected, and a thermal distribution map of the electric pump is constructed based on multiple temperature parameters, corresponding temperature detection locations, and the overall shape of the electric pump. Based on the thermal distribution map of the electric pump, multiple abnormal operating nodes, and corresponding relevant operating parts, multiple fault parts of the electric pump are determined. This approach takes into account the overall consideration of the electric pump's thermal distribution map, multiple abnormal operating nodes, and corresponding relevant operating parts, ensuring the accuracy of multiple fault parts of the electric pump.

[0024] At this point, based on each abnormal working node, the system traces back through signal propagation paths, physical connections, and functional logic to identify the working components or subsystems that may have caused the abnormality. Each abnormal node corresponds to one or more possible working parts, such as bearings, motor windings, impellers, seals, etc. These parts have direct physical or functional connections with the abnormal node. The system calculates the correlation between each working part and the abnormal node based on historical data, expert knowledge, and structural topology, which is used for priority ranking in subsequent fault location. The system summarizes all the associated working parts corresponding to the abnormal nodes, removes duplicates, and forms a complete list of associated working parts.

[0025] The system collects temperature data in real time through temperature sensors distributed in key parts of the electric pump (such as the motor end, bearing housing, pump casing, windings, etc.). Each temperature parameter is accompanied by precise installation location information for subsequent spatial mapping of the thermal distribution map. Thermal distribution map construction: The system performs three-dimensional modeling of the electric pump structure and maps the temperature data to the corresponding locations in the model. A visual temperature distribution map is generated using thermal map algorithms (such as interpolation and heat conduction models). The thermal distribution map can be updated in real time, showing the temperature field changes of the electric pump. The system compares the current temperature distribution with the historical normal distribution to identify abnormal temperature areas.

[0026] The system identifies the faulty component based on the thermal distribution map, abnormal operating nodes, and related operating parts. It integrates and analyzes this data, employing a weighted scoring mechanism to comprehensively determine the fault location. If a related operating part appears in multiple abnormal nodes and its temperature is abnormal in the thermal distribution map, it is classified as a high-probability faulty component. If a component appears only in a single abnormal node with a normal temperature, it is classified as a low-probability faulty component. The system assesses the severity of each faulty component based on the duration of the anomaly, the magnitude of the temperature deviation, and the node influence coefficient. Finally, the system outputs multiple faulty components, sorted by severity, along with the fault type, location, cause analysis, and recommended measures.

[0027] refer to Figure 4 In step S13, the specific steps are as follows: S131: Collect multiple operating parameters of the electric pump, determine the corresponding working stage based on the time nodes of the multiple operating parameters and the sub-working content corresponding to the electric pump, construct a dynamic diagram of operating parameters based on multiple operating parameters, the corresponding working stage and the working status of the electric pump; determine each emergency floating zone based on the identification of the dynamic diagram of operating parameters, and determine the combination of emergency floating parameters of the electric pump based on each emergency floating zone, the corresponding working status and multiple operating parameters. S132: Determine a first fault combination based on the emergency floating parameter combination of the electric pump and multiple fault parts of the electric pump; determine a second fault combination based on the multiple fault parts of the electric pump and the service life of the electric pump; determine multiple abnormal fault parts and regular fault parts based on the first fault combination, the second fault combination and the working environment of the electric pump. S133: Based on the identification of each abnormal fault part, the corresponding emergency fault level is determined. Based on the fault level of each abnormal fault part, the corresponding emergency fault level, and the fault level of the normal fault part, the gradient fault control measures are triggered, and gradient fault control is performed on multiple abnormal fault parts.

[0028] In the embodiments of this application, multiple operating parameters of the electric pump are collected, and the corresponding operating stages are determined based on the time nodes of the multiple operating parameters and the sub-operating content corresponding to the electric pump. A dynamic graph of operating parameters is constructed based on the multiple operating parameters, the corresponding operating stages, and the operating status of the electric pump. Each emergency floating zone is determined based on the identification of the dynamic graph of operating parameters. The combination of emergency floating parameters of the electric pump is determined based on each emergency floating zone, the corresponding operating status, and the multiple operating parameters. This approach takes into account the overall consideration of each emergency floating zone, the corresponding operating status, and the multiple operating parameters, ensuring the accuracy of the combination of emergency floating parameters of the electric pump.

[0029] At this time, the system collects multiple operating parameters in real time through various sensors installed on the electric pump, including: current (A): monitoring motor load; voltage (V): monitoring power supply stability; vibration (mm / s): monitoring mechanical operating status; temperature (°C): monitoring motor and bearing temperature; pressure (MPa): monitoring pump outlet pressure; flow rate (m³ / h): monitoring pump output flow rate; each parameter is accompanied by a precise timestamp, with an accuracy typically reaching the millisecond level.

[0030] The system identifies the current sub-work content based on the pump's operating status and control signals, including: Start-up phase: motor starts, current is relatively high; Loading phase: load gradually increases; Stable operation phase: parameters are relatively stable; Load change phase: flow or pressure is adjusted; Shutdown phase: motor stops running. Simultaneously, the system divides the pump's operation into multiple working phases based on the time nodes of the working parameters and the sub-work content. Each working phase has a characteristic parameter range, for example: Start-up phase: current is 150-200% of the rated value, vibration is relatively high; Stable operation phase: current is 90-110% of the rated value, vibration is relatively low.

[0031] Specifically, the parameter collection and working phase division of a certain model of electric pump during a day's operation are as follows: Parameter collection: 08:00:00 - Current: 220A (rated value 110A), Voltage: 380V, Vibration: 4.5mm / s, Temperature: 45℃, Pressure: 1.2MPa, Flow rate: 80m³ / h; 08:00:30 - Current: 150A, Voltage: 380V, Vibration: 3.2mm / s, Temperature: 48℃, Pressure: 1.5MPa, Flow rate: 100m³ / h; 08:01:00 - Current: 115A, Voltage: 380V, Vibration: 2.1mm / s, Temperature: 50℃, Pressure: 1.6MPa, Flow rate: 105m³ / h; 08:30:00 - Current: 108A, Voltage: 380V, Vibration: 2.0mm / s, Temperature: 52℃, Pressure: 1.6MPa, Flow rate: 105m³ / h; Working stages: 08:00:00 - 08:00:30: Start-up stage (current decreases from 220A to 150A); 08:00:30 - 08:01:00: Loading stage (current decreases from 150A to 115A); 08:01:00 - 08:30:00: Stable operation stage (current maintains around 108A).

[0032] The system constructs a dynamic graph of operating parameters based on multiple operating parameters, corresponding operating stages, and the operating status of the electric pump. Multiple operating parameters are plotted sequentially on the same time axis to form the dynamic graph. The dynamic graph typically uses a multi-curve format, with different parameters represented by different colors for easy comparison. The system also marks the dividing lines of operating stages on the dynamic graph, clearly defining the time range of each stage. Because different parameters have different units and dimensions, the system normalizes the parameters to ensure they vary within the range of 0-1. The normalization formula is: Parameter value = (Actual value - Minimum value) / (Maximum value - Minimum value). The system marks the operating status of the electric pump on the dynamic graph, such as normal operation, overload, and underload. The determination of the operating status is based on a comprehensive analysis of multiple parameters; for example, a current exceeding 120% of the rated value is considered an overload.

[0033] Specifically, the system's operational parameters are displayed in a dynamic graph: Graph characteristics: Horizontal axis: Time (08:00:00 - 08:30:00); Vertical axis: Normalized parameter value (0-1); Curve colors: Current: Red; Vibration: Blue; Temperature: Green; Pressure: Purple; Flow rate: Orange; Graph display content: 08:00:00 - 08:00:30: The current curve drops sharply (from 1.0 to 0.6), and the vibration curve drops from 0.8 to 0.5; 08:00:30 - 08:01:00: The current curve continues to drop to 0.5, and the vibration curve drops to 0.3; 08:01:00 - 08:30:00: All parameter curves remain relatively stable, with the current around 0.48 and the vibration around 0.28; Operational status label: 08:00:00 - 08:00:30: Labeled as "Startup Status"; 08:00:30 - 08:01:00: Marked as "Loading status"; 08:01:00 - 08:30:00: Marked as "Normal operation status".

[0034] The system analyzes the dynamic graph of operating parameters to identify areas where parameters exceed the normal range, termed emergency floating zones. The determination of emergency floating zones is based on parameter thresholds and rates of change, such as: vibration values ​​exceeding the normal range by 20%; temperature rise rate exceeding 5°C / minute; and current fluctuation amplitude exceeding the rated value by 10%. For each emergency floating zone, the system analyzes the following characteristics: duration: the length of time the abnormal state lasts; parameter rate of change: the speed at which parameter values ​​change; parameter correlation: whether multiple parameters are abnormal simultaneously; and operating state correlation: whether the abnormality is related to a specific operating state. Simultaneously, based on the characteristics of the emergency floating zones, the system determines the parameter combinations involved in the abnormality. The determination of parameter combinations is based on the correlation between parameters and their ability to indicate faults. The system assigns weights to each parameter combination to reflect its importance for fault diagnosis.

[0035] Specifically, assuming an anomaly occurs between 08:15:00 and 08:15:30: Emergency Floating Area Identification: The system detected that between 08:15:00 and 08:15:30: the vibration value suddenly increased from 2.0 mm / s to 3.5 mm / s (exceeding the normal range by 75%); the current increased from 108A to 125A (exceeding the normal range by 15%); and the temperature increased from 52℃ to 58℃ (at a rate of increase of 12℃ / minute).

[0036] Floating Area Feature Analysis: Duration: 30 seconds; Parameter Change Rate: Vibration: +1.5 mm / s / min; Current: +34 A / min; Temperature: +12℃ / min; Parameter Correlation: All three parameters are abnormal simultaneously and highly correlated; Operating Status Correlation: The anomaly occurs during normal operation and is an unexpected anomaly; Emergency Floating Parameter Combination Determination: The system determines the parameter combination involved in the anomaly as: {Vibration, Current, Temperature}; Parameter Combination Weights: Vibration: 0.5 (most sensitive to mechanical faults); Current: 0.3 (reflects load changes); Temperature: 0.2 (auxiliary verification parameter); The emergency floating parameter combination is represented as: {Vibration: 3.5 mm / s, Current: 125 A, Temperature: 58℃}, with weights {0.5, 0.3, 0.2}; The system records this emergency floating parameter combination as an important basis for subsequent fault diagnosis; In this way, the system can accurately capture the abnormal state of the electric pump during operation and provide accurate data support for fault early warning.

[0037] Furthermore, a first fault combination is determined based on the emergency floating parameter combination of the electric pump and multiple fault parts of the electric pump, and a second fault combination is determined based on the multiple fault parts of the electric pump and the service life of the electric pump; multiple abnormal fault parts and regular fault parts are determined based on the first fault combination, the second fault combination and the working environment of the electric pump, which takes into account the overall consideration of the first fault combination, the second fault combination and the working environment of the electric pump, and ensures the accuracy of multiple abnormal fault parts and regular fault parts.

[0038] At this point, the first fault combination is determined based on the emergency floating parameter combination of the electric pump and multiple faulty parts of the electric pump. The system obtains the identified emergency floating parameter combination from S131, such as: vibration: 3.5 mm / s (high); current: 125 A (high); temperature: 58°C (higher than normal operating temperature). These parameter combinations reflect the abnormal performance in the current operating state and are important basis for fault identification. At the same time, the system performs correlation analysis on these parameters with multiple identified faulty parts of the electric pump (such as bearings, motor windings, impellers, etc.). Each faulty part has its characteristic parameter response mode. For example: bearing fault: mainly manifested as abnormal vibration; motor winding fault: mainly manifested as abnormal current and temperature; impeller fault: mainly manifested as abnormal flow and pressure.

[0039] The system determines the most likely first fault combination based on the correlation between parameter combinations and fault components. Each fault component has a matching degree score, which is based on the consistency between the degree of parameter anomaly and the fault characteristics. The matching degree is usually calculated using a weighted scoring method, for example: bearing matching degree = vibration anomaly weight × vibration anomaly degree; motor winding matching degree = current anomaly weight × current anomaly degree + temperature anomaly weight × temperature anomaly degree. The system selects the fault component with the highest matching degree as the first fault combination.

[0040] Specifically, assuming the emergency floating parameter combination of a certain electric pump is: vibration: 3.5 mm / s (normal range: <2.0 mm / s); current: 125 A (normal range: 100-110 A); temperature: 58°C (normal range: 50-55°C); the system performs a fault correlation analysis: bearing fault analysis: vibration anomaly weight: 0.8; vibration anomaly degree: (3.5-2.0) / 2.0 = 0.75; bearing matching degree = 0.8 × 0.75 = 0.6; motor winding fault analysis: current anomaly weight: 0.5; current anomaly degree: (125-110) / 110 = 0.136; temperature anomaly weight: 0.5; temperature anomaly degree: (58-55) / 55 = 0.055; motor winding matching degree = 0.5 × 0.136 + 0.5 × 0.055 = 0.0955; Impeller fault analysis: No directly related parameters, matching degree is 0; The system determines the first fault combination as: bearing (matching degree 0.6), motor winding (matching degree 0.0955).

[0041] The second fault combination is determined based on multiple faulty parts of the electric pump and the pump's service life. The system collects service life data for each faulty part of the pump, including: design life: the theoretical life provided by the manufacturer; actual operating time: the cumulative operating time of the pump; maintenance history: maintenance and replacement records of each component; fault history: fault records of each component; life assessment model: the system uses a life assessment model to calculate the percentage of remaining life of each faulty part; commonly used models include: linear decay model: remaining life = (design life - actual operating time) / design life; nonlinear decay model: considers the impact of actual operating conditions on life; reliability-based model: considers the failure probability distribution.

[0042] Second fault combination determination: The system determines the second fault combination based on the percentage of remaining life of each fault component; usually, fault components with remaining life below a certain threshold (such as 20%) are included in the second fault combination; the second fault combination reflects the potential failure risk of the electric pump.

[0043] Specifically, assuming the following are the lifespan data for the faulty components of a certain electric pump: Bearing: Design life: 20,000 hours; Actual operating time: 18,000 hours; Remaining life percentage: (20,000-18,000) / 20,000 = 10%; Motor winding: Design life: 30,000 hours; Actual operating time: 15,000 hours; Remaining life percentage: (30,000-15,000) / 30,000 = 50%; Impeller: Design life: 25,000 hours; Actual operating time: 22,000 hours; Remaining life percentage: (25,000-22,000) / 25,000 = 12%; The system is set to a remaining lifespan threshold of 20%, then the second fault combination is: bearing (10%), impeller (12%).

[0044] Based on the first fault combination, the second fault combination, and the operating environment of the electric pump, multiple abnormal and regular fault components are identified. The system performs a comprehensive analysis of the first fault combination (based on current parameter anomalies) and the second fault combination (based on lifespan assessment). The analysis methods include: intersection analysis (fault components appearing in both combinations); union analysis (fault components appearing in either combination); and weighted analysis (calculating a comprehensive risk score based on the degree of parameter anomaly and remaining lifespan). The system considers the impact of the electric pump's operating environment on faults, including: ambient temperature (high temperatures accelerate equipment aging); ambient humidity (high humidity may cause electrical component failures); environmental corrosivity (corrosive environments accelerate mechanical component wear); and workload (long-term high-load operation shortens equipment lifespan). Based on the comprehensive analysis results, the system categorizes fault components into: abnormal fault components (current parameters are abnormal and remaining lifespan is short, requiring immediate attention); and regular fault components (parameters are normal but remaining lifespan is short, or parameters are abnormal but remaining lifespan is long, requiring planned maintenance).

[0045] Specifically, the first fault combination is: bearing (abnormal parameters) and motor winding (abnormal parameters); the second fault combination is: bearing (10% remaining life) and impeller (12% remaining life); the operating environment is: high temperature (35°C) and high humidity (80%); the system undergoes comprehensive analysis: intersection analysis: the bearing appears in both combinations, indicating a high-risk fault; union analysis: all faulty parts are: bearing, motor winding, and impeller; weighting analysis: bearing comprehensive risk = parameter abnormality score 0.6 + life risk score 0.9 = 1.5; motor winding comprehensive risk = parameter abnormality score 0.0955 + life risk score 0.2 = 0.2955; impeller comprehensive risk = parameter abnormality score 0 + life risk score 0.88 = 0.88; environmental factor adjustments: high temperature increases the risk of all faulty parts by 20%; high humidity increases the risk of motor winding by 30%.

[0046] Adjusted overall risk: Bearing: 1.5 × 1.2 = 1.8; Motor winding: 0.2955 × 1.2 × 1.3 = 0.46; Impeller: 0.88 × 1.2 = 1.056; The system risk threshold is set to 1.0, then: Abnormal fault parts: Bearing (1.8), Impeller (1.056); Regular fault parts: Motor winding (0.46); Final result: Abnormal fault parts: Bearing, Impeller; Regular fault parts: Motor winding.

[0047] Therefore, based on the identification of each abnormal fault component, the corresponding emergency fault level is determined. Based on the fault levels of each abnormal fault component, the corresponding emergency fault level, and the fault level of the regular fault component, gradient fault control measures are triggered. Gradient fault control is implemented for multiple abnormal fault components, which takes into account the overall consideration of the identification of each abnormal fault component and ensures the accuracy of the corresponding emergency fault level. At the same time, multiple fault components are introduced, which takes into account the emergency floating parameter combination of the electric pump, multiple fault components of the electric pump, and the overall consideration of the electric pump's service life. This improves the accuracy of multiple abnormal fault components and regular fault components and realizes gradient fault control for multiple abnormal fault components.

[0048] At this point, the system obtains a list of identified abnormal fault components from step S132, such as bearings and impellers. Each abnormal fault component is accompanied by its risk score and key parameter information. Emergency fault level determination: The system determines the emergency fault level for each abnormal fault component based on its risk score, parameter abnormality, and potential consequences. Emergency fault levels are typically divided into 5 levels: Level 1: Catastrophic fault, immediate shutdown; Level 2: Severe fault, shutdown as soon as possible; Level 3: Moderate fault, planned shutdown; Level 4: Minor fault, reduced load operation; Level 5: Warning fault, continued monitoring. The level determination criteria are: the higher the risk score, the more urgent the fault level; the greater the parameter abnormality, the more urgent the fault level; the more severe the potential consequences, the more urgent the fault level.

[0049] Specifically, assuming the abnormal faults in the electric pump are in the bearings and impeller: Bearing analysis: Risk score: 1.8 (high); Parameter anomaly: Vibration 3.5 mm / s (normal value <2.0 mm / s); Potential consequences: Bearing damage may cause the motor to seize up, resulting in equipment damage; Emergency fault level: Level 2 (serious fault, stop the machine as soon as possible); Impeller analysis: Risk score: 1.056 (medium); Parameter anomaly: Slight flow fluctuation (normal value ±5%, actual fluctuation ±8%); Potential consequences: Impeller wear may lead to a decrease in efficiency, but will not cause immediate equipment damage; Emergency fault level: Level 4 (minor fault, reduce load operation); Level determination result: Bearing: Level 2; Impeller: Level 4.

[0050] Based on the various abnormal fault components, their corresponding emergency fault levels, and the fault levels of the regular fault components, gradient fault control measures are triggered. The gradient fault control measures are designed as follows: the system pre-sets control measures corresponding to different fault levels, forming a gradient control strategy; control measures include operational adjustments, maintenance suggestions, and shutdown requirements; control measures are triggered based on the emergency fault level of the abnormal fault component; regular fault components also have their own fault levels (usually levels 4-5), which also trigger corresponding control measures; the system ensures that control measures do not conflict with each other, prioritizing the execution of control measures for higher-level faults; control measures include: Level 1: Immediate shutdown, emergency repair; Level 2: Shutdown as soon as possible (within 24 hours), prepare for repair; Level 3: Planned shutdown (within 1 week), arrange repair; Level 4: Reduce load operation, strengthen monitoring; Level 5: Continue monitoring, record anomalies.

[0051] The system executes control measures sequentially according to the fault level, from highest to lowest. After the control measures for high-level faults are completed, the control measures for lower-level faults are executed. The system monitors the execution and effectiveness of the control measures in real time. Control effectiveness evaluation: The system continuously monitors parameter changes in the abnormal fault portion and assesses whether the control measures have effectively reduced the fault risk. If the control measures are ineffective, the system automatically upgrades the control level. Dynamic adjustment: Based on the control effectiveness and new monitoring data, the system dynamically adjusts the control measures. If the fault situation worsens, the system increases the fault level and control intensity; if the fault situation improves, the system decreases the fault level and control intensity.

[0052] Specifically, taking the bearing (level 2) and impeller (level 4) as examples, assuming the common fault is in the motor winding (level 5): Control measures triggered: Bearing (level 2): ​​"Stop as soon as possible" measure is triggered; Impeller (level 4): "Reduced load operation" measure is triggered; Motor winding (level 5): "Continued monitoring" measure is triggered; Priority handling of measures: The system identifies the bearing's level 2 fault as having the highest priority, so the "Stop as soon as possible" measure is executed first; The impeller's level 4 fault is executed after the bearing fault is handled; The motor winding's level 5 fault is continuously monitored.

[0053] Specific control measures: Bearing (Level 2): ​​Immediately issue a "stop as soon as possible" alarm to the operator; recommend stopping the machine within 24 hours to check the bearing; prepare maintenance tools and spare parts; Impeller (Level 4): recommend reducing the electric pump load to 80% operation; increase the flow monitoring frequency to once every 5 minutes; record flow fluctuation data; Motor winding (Level 5): continue normal operation; maintain the regular monitoring frequency; record temperature and current data.

[0054] Gradient control execution sequence: Phase 1: Implement control measures for bearings (Level 2); Phase 2: Implement control measures for impellers (Level 4); Phase 3: Implement control measures for motor windings (Level 5); Phase 1: Bearing control (Level 2): ​​The system issues an "Immediate shutdown" alarm, and the operator receives a notification; the operator arranges shutdown 4 hours later (within the 24-hour requirement); after shutdown, inspection reveals severe bearing wear, which is immediately replaced; after replacement, the system restarts, and the vibration drops to 1.2. mm / s (normal); the system reduced the bearing fault level to level 5 (resolved); Second stage: Impeller control (level 4): After the bearing problem was resolved, the system implemented impeller control measures; the electric pump load was reduced to 80% operation; the system monitored flow fluctuations from ±8% to ±6%; although there was improvement, it was still not completely normal, so level 4 control was maintained; the system suggested checking the impeller during the next planned maintenance; Third stage: Motor winding control (level 5): the system continuously monitored the motor winding temperature and current; the data showed that the temperature was stable at 55℃ (within the normal range); the current fluctuation was within the normal range; the system maintained level 5 control and continued monitoring; Control effect evaluation: Bearing: control measures were effective, and the fault was resolved; Impeller: control measures were partially effective, and further observation is needed; Motor winding: no special control is needed, and monitoring is maintained; Dynamic adjustment: the bearing fault has been resolved and removed from the monitoring list; the impeller fault is maintained at level 4 control and is continuously observed; the motor winding is maintained at level 5 control and is continuously monitored.

[0055] refer to Figure 5 In step S14, the specific steps are as follows: S141: Collect multiple abnormal fault sections and regular fault sections, and determine the corresponding fault correlation coefficients based on the fault content of multiple abnormal fault sections, the fault content of regular fault sections, and the working content of the electric pump. S142: Determine the first sub-fault maintenance combination based on multiple abnormal fault components and fault correlation coefficients, determine the second sub-fault maintenance combination based on the regular fault components and fault correlation coefficients, and determine the corresponding multiple fault maintenance combinations based on the first sub-fault maintenance combination, the second sub-fault maintenance combination, and the abnormal signal of the electric pump. S143: Determine the first fault maintenance coefficient based on the current working node of each fault maintenance combination and electric pump, determine the second fault maintenance coefficient based on the working plan of each fault maintenance combination and electric pump, and determine the corresponding fault maintenance plan according to the mapping relationship between the first fault maintenance coefficient, the second fault maintenance coefficient and the fault maintenance plan.

[0056] In the embodiments of this application, multiple abnormal fault components and regular fault components are collected. Based on the fault content of the multiple abnormal fault components, the fault content of the regular fault components, and the working content of the electric pump, the corresponding fault correlation coefficients are determined. This approach takes into account the overall consideration of the fault content of the multiple abnormal fault components, the fault content of the regular fault components, and the working content of the electric pump, thus ensuring the accuracy of the corresponding fault correlation coefficients.

[0057] At this point, the system retrieves a list of identified faulty parts from step S133; Abnormal faulty parts: typically emergency faulty parts identified in the current work event; Regular faulty parts: typically non-emergency faulty parts that require attention; Data format: JSON format, containing faulty part ID, name, type, location, etc.; For each faulty part, the system collects the following attributes: Fault type (mechanical, electrical, performance, etc.); Fault location (specifically, which component of the electric pump); Fault severity (minor, moderate, severe); Fault duration (first detection time, duration); Fault development trend (stable, worsening, improving); Fault status verification: The system verifies the current status of each faulty part through sensor data; compares with historical data to confirm whether the fault persists; and eliminates false alarms or temporary anomalies.

[0058] The system performs a detailed analysis of each fault, including: fault mechanism analysis (why this fault occurs); fault impact analysis (the impact on the performance of the electric pump); fault propagation analysis (whether it will affect other components); the system obtains the current working content of the electric pump (such as high-load drainage, low-load circulation, etc.); and analyzes the characteristics of the working content: load size (high load, medium load, low load); operating mode (continuous operation, intermittent operation); and working environment (temperature, humidity, corrosiveness, etc.).

[0059] The system establishes a fault correlation assessment model, considering the following factors: the degree of impact of the fault on the current work content; the impact of the current work content on the development of the fault; the mutual influence relationship between faults; fault correlation coefficient calculation: the system uses a weighted scoring method to calculate the correlation coefficient of each fault component; scoring dimensions include: work impact (0-1 point): the degree of impact of the fault on the current work; environmental sensitivity (0-1 point): the sensitivity of the fault to the work environment; development risk (0-1 point): the risk level of the fault development; calculation formula: correlation coefficient = (work impact x 0.4) + (environmental sensitivity x 0.3) + (development risk x 0.3); coefficient range: 0-1, the larger the value, the stronger the correlation.

[0060] Specifically, assuming the system obtains the following fault components from step S133: Abnormal fault component: Bearing (ID: F001); Type: Mechanical fault; Location: Drive end bearing; Severity: Severe; Duration: 2 hours; Trend: Deteriorating; Impeller (ID: F002); Type: Performance fault; Location: Main impeller; Severity: Moderate; Duration: 4 hours; Trend: Stable; Regular fault component: Motor winding (ID: F003); Type: Electrical fault; Location: Stator winding; Severity: Slight; Duration: 24 hours; Trend: Stable; The system confirms the bearing vibration is continuously high through vibration sensors, the impeller efficiency is reduced through flow meters, and the motor winding temperature is slightly high through temperature sensors, thus verifying the authenticity of all fault components.

[0061] The electric pump is currently operating under "high-load drainage". The system is analyzed as follows: Bearing (F001) analysis: Failure mechanism: poor lubrication leads to bearing wear; Failure impact: increased vibration, affecting sealing performance; Failure propagation: may cause shaft seal damage; Operational impact: 0.9 (vibration has a serious impact under high load); Environmental sensitivity: 0.7 (sensitive to temperature changes); Development risk: 0.8 (high risk of accelerated wear); Correlation coefficient: (0.9×0.4)+(0.7×0.3)+(0.8×0.3) = 0.81.

[0062] Impeller (F002) Analysis: Failure Mechanism: Cavitation causes damage to the impeller surface; Failure Impact: Reduced efficiency and flow rate; Failure Propagation: May affect pump balance; Operational Impact: 0.7 (significant impact on efficiency under high load); Environmental Sensitivity: 0.5 (sensitive to changes in water quality); Development Risk: 0.4 (cavitation development is relatively slow); Correlation Coefficient: (0.7×0.4)+(0.5×0.3)+(0.4×0.3) = 0.55.

[0063] Analysis of motor winding (F003): Fault mechanism: local overheating caused by insulation aging; Fault impact: slight decrease in efficiency, increased energy consumption; Fault propagation: may lead to winding burnout; Operational impact: 0.3 (small impact under high load); Environmental sensitivity: 0.6 (sensitive to ambient temperature); Development risk: 0.5 (long-term aging risk); Correlation coefficient: (0.3×0.4)+(0.6×0.3)+(0.5×0.3) = 0.45; Finally, the system obtained the following fault correlation coefficients: bearing (F001): 0.81; impeller (F002): 0.55; motor winding (F003): 0.45; These correlation coefficients will serve as an important basis for determining the subsequent fault maintenance combination, reflecting the degree of correlation between each fault part and the current work content; fault parts with high correlation coefficients need to be dealt with first, reflecting the system's scientific assessment of the severity and urgency of the fault.

[0064] Furthermore, a first sub-fault maintenance combination is determined based on multiple abnormal fault components and fault correlation coefficients, and a second sub-fault maintenance combination is determined based on regular fault components and fault correlation coefficients. Based on the first sub-fault maintenance combination, the second sub-fault maintenance combination, and the abnormal signals of the electric pump, multiple corresponding fault maintenance combinations are determined. This approach takes into account the overall consideration of the first sub-fault maintenance combination, the second sub-fault maintenance combination, and the abnormal signals of the electric pump, ensuring the accuracy of the corresponding multiple fault maintenance combinations.

[0065] At this point, the system obtains a list of abnormal fault parts and their correlation coefficients from step S141; sets a threshold for the correlation coefficient of abnormal fault parts (e.g., 0.6); filters out abnormal fault parts with correlation coefficients exceeding the threshold; and sorts the maintenance priorities: abnormal fault parts are sorted in descending order according to their correlation coefficients; the higher the correlation coefficient, the higher the maintenance priority; and fault parts with the same correlation coefficient are sorted according to the degree of fault.

[0066] The sorted abnormal faults are grouped into the first sub-fault maintenance group; each fault part is accompanied by the following information: fault part ID and name; correlation coefficient; suggested maintenance method; estimated maintenance time; required resources; maintenance method matching: the system matches the best maintenance method from the maintenance knowledge base according to the fault type and severity; maintenance methods include: immediate shutdown maintenance, planned maintenance, status monitoring, etc.

[0067] Specifically, assuming the system obtains the following abnormal fault components from step S141: bearing (F001); correlation coefficient: 0.81; fault severity: severe; fault type: mechanical fault; impeller (F002); correlation coefficient: 0.55; fault severity: moderate; fault type: mechanical fault; and sets the threshold for the correlation coefficient of the abnormal fault components to 0.6, then: only the correlation coefficient (0.81) of bearing (F001) exceeds the threshold; the correlation coefficient (0.55) of impeller (F002) is lower than the threshold and is not included in the first sub-fault maintenance combination.

[0068] In the first sub-fault maintenance package, we identified a critical fault item with the following details: Fault Part ID: F001; Fault Name: Bearing; Correlation Coefficient: 0.81; Fault Severity: Critical; Recommended Maintenance Method: Immediate shutdown for repair; Estimated Maintenance Time: 4 hours; Required Resources: Repair team, spare bearing.

[0069] The system determines the second sub-fault maintenance combination based on the common fault components and their correlation coefficients. Step S141 retrieves a list of common fault components and their correlation coefficients; a correlation coefficient threshold (e.g., 0.3) is set for the common fault components; common fault components with correlation coefficients exceeding the threshold are filtered out; maintenance priority is ranked: common fault components are sorted in descending order based on their correlation coefficients; the higher the correlation coefficient, the higher the maintenance priority; fault components with the same correlation coefficient are ranked according to their fault development trend; the ranked common fault components are combined into the second sub-fault maintenance combination; each fault component includes the following information: fault component ID and name; correlation coefficient; suggested maintenance method; estimated maintenance time; required resources; maintenance method matching: the system matches the best maintenance method from the maintenance knowledge base based on the fault type and severity; maintenance methods include: planned maintenance, status monitoring, periodic inspection, etc.

[0070] Specifically, assuming the system obtains the following routine fault section from step S141: motor winding (F003); correlation coefficient: 0.45; fault severity: minor; fault type: electrical fault; and sets the correlation coefficient threshold for routine fault sections to 0.3, then: the correlation coefficient (0.45) of motor winding (F003) exceeds the threshold and is included in the second sub-fault maintenance group; in the second sub-fault maintenance group, we identify a medium-priority fault item with the following details: fault section ID: F003; fault name: motor winding; correlation coefficient: 0.45; fault severity: minor; recommended maintenance method: planned maintenance; estimated maintenance time: at the next downtime; required resources: electrical engineer, insulation testing equipment.

[0071] Based on the abnormal signals of the first sub-fault maintenance combination, the second sub-fault maintenance combination, and the electric pump, multiple corresponding fault maintenance combinations are determined. The system collects the current abnormal signal data of the electric pump. The abnormal signals include vibration signals, current signals, temperature signals, noise signals, etc. Each signal is accompanied by a timestamp and amplitude information. The correlation between the abnormal signals and each fault maintenance combination is analyzed. The influence weight of each signal on the maintenance combination is calculated. It is determined which signals have a significant impact on which fault maintenance combinations.

[0072] Based on the correlation analysis of abnormal signals, the first and second sub-fault maintenance combinations are optimized. Possible optimization directions include: adjusting maintenance priorities; merging related maintenance tasks; adding or reducing maintenance content. Multiple fault maintenance combinations are determined: the system generates multiple fault maintenance combination schemes. Each scheme includes: maintenance combination number; the fault part included; maintenance time window; required resources; expected results; and risk assessment.

[0073] Specifically, assuming the system collects the following abnormal signals: vibration signal: amplitude 12 mm / s, frequency range 10-1000 Hz; current signal: three-phase imbalance 3.5%; temperature signal: bearing temperature 85℃; signal correlation analysis results: vibration signal is highly correlated with bearing fault (weight 0.9); current signal is moderately correlated with motor winding fault (weight 0.6); temperature signal is highly correlated with bearing fault (weight 0.8); based on these analyses, the system generates the following fault maintenance combination: Fault Maintenance Package 1 (Immediate Execution): Package Number: MC001; Faulty Component: Bearing (F001); Maintenance Time Window: Immediate; Required Resources: Maintenance Team, Spare Bearing, Vibration Analyzer; Expected Outcome: Eliminate abnormal vibration and prevent equipment damage; Risk Assessment: Medium Risk (Requires Downtime) Fault Maintenance Package 2 (Planned Execution): Package Number: MC002; Faulty Component: Motor Winding (F003); Maintenance Time Window: Next Planned Shutdown; Required Resources: Electrical Engineer, Insulation Testing Equipment; Expected Outcome: Improved Motor Efficiency, Prevention of Insulation Aging; Risk Assessment: Low Risk (Planned Execution Required); Fault Maintenance Package 3 (Comprehensive Execution): Package Number: MC003; Faulty Components Included: Bearing (F001); Motor Winding (F003); Maintenance Time Window: Next planned downtime (if bearing condition permits); Required Resources: Maintenance team, electrical engineer, full set of testing equipment; Expected Outcome: Comprehensive resolution of the current fault; Risk Assessment: Medium risk (requires reasonable scheduling of downtime).

[0074] Therefore, a first fault maintenance coefficient is determined based on the current working node of each fault maintenance combination and electric pump, a second fault maintenance coefficient is determined based on the working plan of each fault maintenance combination and electric pump, and a corresponding fault maintenance plan is determined according to the mapping relationship between the first fault maintenance coefficient, the second fault maintenance coefficient and the fault maintenance plan. This approach takes into account the overall consideration of the mapping relationship between the first fault maintenance coefficient, the second fault maintenance coefficient and the fault maintenance plan, and ensures the accuracy of the corresponding fault maintenance plan.

[0075] At this point, the system obtains the current working node list of the electric pump from step S122; the working nodes include: normal operation nodes, load change nodes, start-stop nodes, etc.; each working node has a corresponding timestamp and duration; fault maintenance combination matching with working nodes: matching each fault maintenance combination with the current working node in terms of time; analyzing the impact of the maintenance combination execution on the working node; assessing the degree of conflict between the maintenance operation and the working node; calculating coefficients based on the following factors: time conflict degree: the degree of overlap between the maintenance time and the critical working node; impact severity: the degree of impact of the maintenance operation on the working node; resource availability: the current availability of resources required to perform maintenance; calculation formula: first coefficient = (time conflict degree × 0.4) + (impact severity × 0.4) + (resource availability × 0.2); coefficient normalization: normalizing the calculation result to the range of 0-1; the closer the coefficient is to 1, the worse the matching degree between the maintenance combination and the current working node.

[0076] The system acquires short-term (1 week) and long-term (1 month) work plans for electric pumps; the plans include: production tasks, planned downtime, maintenance windows, etc.; each plan item has priority and time constraints; maintenance combination matching with work plan: analyze the compatibility of each maintenance combination with the work plan; assess the impact of maintenance operations on planned tasks; identify available maintenance time windows; calculate coefficients based on the following factors: plan compatibility: the degree of matching between maintenance and work plans; time window suitability: the rationality of maintenance time windows; resource scheduling difficulty: the complexity of scheduling maintenance resources; calculation formula: second coefficient = (plan compatibility × 0.5) + (time window suitability × 0.3) + (resource scheduling difficulty × 0.2); coefficient optimization: optimize and adjust the coefficients; consider the urgency of maintenance and the flexibility of the plan.

[0077] Based on the first fault maintenance coefficient, the second fault maintenance coefficient, and the fault maintenance plan mapping relationship, the corresponding fault maintenance plan is determined. The system summarizes the first and second fault maintenance coefficients; calculates the comprehensive maintenance coefficient: Comprehensive coefficient = (first coefficient × 0.6) + (second coefficient × 0.4); sets coefficient thresholds for decision-making on maintenance plans; the system maintains a fault maintenance plan mapping table; the mapping relationship includes: comprehensive coefficient range → maintenance plan type; fault type → specific maintenance measures; resource requirements → resource allocation scheme; based on the comprehensive coefficient and maintenance plan mapping relationship; generates a specific maintenance plan, including: maintenance time arrangement; resource allocation scheme; execution step description; risk control measures; plan optimization and adjustment: optimizes the generated maintenance plan; considers factors such as resource balance and time conflicts; outputs the final maintenance plan; comprehensively considers the current state of the equipment (first coefficient) and future work plan (second coefficient), and generates the optimal maintenance plan through a systematic mapping relationship, which not only ensures timely handling of faults, but also minimizes the impact on production, demonstrating the practical value and scientific nature of the intelligent fault early warning system.

[0078] refer to Figure 6 In step S15, the specific steps are as follows: S151: Collect the fault maintenance plan, identify multiple sub-fault maintenance items based on the fault maintenance plan, and mark the corresponding fault maintenance operation methods; at the same time, collect the distribution location of multiple fault parts, mark the corresponding location importance coefficient, and determine the first sub-maintenance event based on the distribution location of multiple fault parts, location importance coefficient and corresponding sub-fault maintenance items. S152: Determine the second sub-maintenance event based on the project content of the sub-fault maintenance project, the corresponding fault maintenance operation method, and the fault correlation coefficient; determine the dynamic maintenance events of multiple sub-fault maintenance projects based on the first sub-maintenance event, the second sub-maintenance event, and the service life of the electric pump.

[0079] In the embodiments of this application, a fault maintenance plan is collected, and multiple sub-fault maintenance items are determined based on the identification of the fault maintenance plan, and the corresponding fault maintenance operation methods are marked. At the same time, the distribution locations of multiple fault parts are collected, and the corresponding location importance coefficients are marked. The first sub-maintenance event is determined based on the distribution locations of multiple fault parts, the location importance coefficients, and the corresponding sub-fault maintenance items. This approach takes into account the overall consideration of the distribution locations of multiple fault parts, the location importance coefficients, and the corresponding sub-fault maintenance items, ensuring the accuracy of the first sub-maintenance event.

[0080] At this point, the system obtains the determined fault maintenance plan from step S143; the maintenance plan contains multiple fault maintenance combinations and their detailed information; data format: JSON format, including maintenance project ID, type, time, etc.; each fault maintenance combination is decomposed into specific sub-fault maintenance projects; sub-projects usually correspond to specific faulty parts or maintenance operations; each sub-project is assigned a unique identifier and description information; fault maintenance operation means marking: each sub-fault maintenance project is marked with the corresponding operation means; operation means types include: replacement, repair, detection, adjustment, etc.; marking format: operation type + specific method (e.g., "replace - overall replacement").

[0081] Obtain the location information of the faulty part from the equipment BOM (Bill of Materials) or CAD drawings; location information includes: X / Y / Z coordinates, system to which it belongs, installation location, etc.; establish a location database to store the location information of all faulty parts; location importance coefficient marking: determine the importance coefficient of the faulty part based on its location in the equipment; importance coefficient evaluation factors: functional importance: the degree of impact of the location on equipment operation; accessibility: the ease with which maintenance personnel can reach the location; safety risk: the level of safety risk of operating at the location; coefficient range: 0.1-1.0, 1.0 indicates the most important; comprehensively analyze the following factors: type and complexity of sub-fault maintenance project; location information of the faulty part; location importance coefficient; generate the first sub-maintenance event, including: event ID, maintenance project, location information, importance coefficient, priority.

[0082] Specifically, the sub-fault maintenance project identification is as follows: Sub-project 1 (SP001): Project ID: SP001; Faulty part: Bearing (F001); Project description: Bearing replacement and maintenance; Sub-project 2 (SP002): Project ID: SP002; Faulty part: Impeller (F002); Project description: Impeller repair and maintenance; Fault maintenance operation method marking: SP001 operation method: Replacement - Overall replacement; SP002 operation method: Repair - Welding repair; Faulty part distribution location acquisition: Bearing (F001) location: Coordinates: X1200 / Y800 / Z500; System: Drive system; Installation location: Pump body front end; Impeller (F002) location: ; Coordinates: X1200 / Y800 / Z600; System: Hydraulic system; Installation location: Inside the pump body.

[0083] Location Importance Coefficient Markings: Bearing (F001): Functional Importance: 0.9 (Critical Drive Component); Accessibility: 0.7 (Requires Housing Disassembly); Safety Risk: 0.6 (Medium Risk); Location Importance Coefficient: (0.9 x 0.4) + (0.7 x 0.3) + (0.6 x 0.3) = 0.75; Impeller (F002): Functional Importance: 0.8 (Core Working Component); Accessibility: 0.4 (Difficult to Directly Access); Safety Risk: 0.7 (High Risk); Location Importance Coefficient: (0.8 x 0.4) + (0.4 x 0.3) + (0.7 x 0.3) =0.65; First sub-maintenance event determined: Event 1 (SE001): Event ID: SE001; Maintenance item: SP001 (bearing replacement); Location information: X1200 / Y800 / Z500; Location importance coefficient: 0.75; Priority: High; Event 2 (SE002): Event ID: SE002; Maintenance item: SP002 (impeller repair); Location information: X1200 / Y800 / Z600; Location importance coefficient: 0.65; Priority: Medium.

[0084] Furthermore, a second sub-maintenance event is determined based on the project content, corresponding maintenance operation methods, and fault correlation coefficient of the sub-fault maintenance project. Dynamic maintenance events for multiple sub-fault maintenance projects are determined based on the first and second sub-maintenance events and the service life of the electric pump. This approach considers the overall factors of the first and second sub-maintenance events and the service life of the electric pump, ensuring the accuracy of the dynamic maintenance events for multiple sub-fault maintenance projects. Simultaneously, a fault maintenance plan is introduced, fully considering each fault maintenance combination, the current working node of the electric pump, and the pump's work plan. This achieves a holistic consideration of the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient, thereby improving the accuracy of the dynamic maintenance events for multiple sub-fault maintenance projects.

[0085] At this point, extract the detailed content of each sub-fault maintenance project; the analysis content includes: maintenance objectives, technical requirements, resource requirements, etc.; assess the technical complexity and execution difficulty of the project; analyze the fault maintenance operation methods: analyze the following for each operation method: technical maturity: the reliability and effectiveness of the operation method; resource consumption: the manpower, material resources, and time required to perform the operation; risk level: the risks that may occur during the operation; establish an operation method evaluation matrix.

[0086] Obtain the correlation coefficients of each fault component from step S141; associate the correlation coefficients with maintenance items and operating methods; analyze the impact of the correlation coefficients on the maintenance strategy; determine the second sub-maintenance event: generate the second sub-maintenance event by considering the following factors: project complexity; technical maturity and resource consumption of operating methods; fault correlation coefficient; the event includes: technical assessment, resource requirements, and time estimation; service life analysis: obtain the service life information of the electric pump; analyze the impact of service life on the maintenance strategy: new equipment (<3 years): preventive maintenance is the main approach; mid-term equipment (3-7 years): balanced maintenance strategy; old equipment (>7 years): intensive maintenance strategy.

[0087] Dynamic maintenance event determination: Integrate the first and second sub-maintenance events; dynamically adjust them based on the service life factor; generate the final dynamic maintenance event, which includes: optimized maintenance strategy; dynamically adjusted maintenance time; resource allocation optimization plan; and risk control measures.

[0088] Specifically, the project content analysis is as follows: SP001 (Bearing Replacement): Maintenance Goal: Restore the normal function of the bearing; Technical Requirements: Precision grade P6, clearance C3; Resource Requirements: Special tools, measuring instruments; Complexity: Medium; SP002 (Impeller Repair): Maintenance Goal: Repair impeller damage; Technical Requirements: Dynamic balance grade G2.5; Resource Requirements: Welding equipment, dynamic balancing machine; Complexity: High.

[0089] Fault Maintenance Operation Method Analysis: SP001 Operation Method (Replacement - Complete Replacement): Technology Maturity: 0.9 (Mature Technology); Resource Consumption: 0.6 (Medium Consumption); Risk Level: 0.3 (Low Risk); SP002 Operation Method (Repair - Welding Repair): Technology Maturity: 0.7 (Relatively Mature); Resource Consumption: 0.8 (High Consumption); Risk Level: 0.6 (Medium Risk); Fault Correlation Coefficient Integration: SP001 Correlation Coefficient: 0.81 (Bearing); SP002 Correlation Coefficient: 0.55 (Impeller); Second Sub-Maintenance Event Determination: Event 1 (TE001): Item: SP001; Technology Assessment: Mature and Reliable; Resource Requirement: Medium; Time Estimation: 4 Hours; Event 2 (TE002): Item: SP002; Technology Assessment: Requires Professional Skills; Resource Requirement: High; Time Estimation: 8 Hours; Service Life Analysis: Electric Pump Service Life: 5 Years (Mid-Term Equipment); Maintenance Strategy: Balanced Maintenance Strategy.

[0090] Adjustment principles: Prioritize high-correlation faults; rationally schedule maintenance time; optimize resource allocation; Dynamic maintenance event determination: Dynamic event 1 (DE001): Maintenance item: Bearing replacement (SP001); Optimization strategy: Prioritize execution; Maintenance time: Saturday morning; Resource allocation: Main maintenance team; Risk control: Standard operating procedure; Dynamic event 2 (DE002): Maintenance item: Impeller repair (SP002); Optimization strategy: Execute when conditions permit; Maintenance time: Next Tuesday; Resource allocation: Professional welding team; Risk control: Full monitoring.

[0091] Please see Figure 7 , Figure 7 This is a schematic diagram of the structural composition of the electric pump fault early warning system in an embodiment of the present invention; the electric pump fault early warning system includes: The current working event module 21 is used to collect multiple working parameters of the electric pump and determine the current working event of the electric pump based on the multiple working parameters, working mode and surrounding working environment. The fault section module 22 is used to determine multiple abnormal working nodes based on the detection of the current working events of the electric pump, and to determine multiple fault sections of the electric pump based on each abnormal working node, associated working section and the thermal distribution diagram of the electric pump. The abnormal fault module 23 is used to determine the emergency floating parameter combination of the electric pump based on multiple operating parameters of the electric pump and the corresponding operating stage, determine multiple abnormal fault parts and regular fault parts according to the emergency floating parameter combination of the electric pump, multiple fault parts of the electric pump and the service life of the electric pump, and perform gradient fault control on multiple abnormal fault parts. The fault maintenance plan module 24 is used to determine the corresponding fault correlation coefficients based on multiple abnormal fault parts and regular fault parts, and to determine multiple corresponding fault maintenance combinations based on multiple abnormal fault parts, regular fault parts and corresponding fault correlation coefficients; and to determine the corresponding fault maintenance plan based on each fault maintenance combination, the current working node of the electric pump and the working plan of the electric pump. The dynamic maintenance event module 25 is used to identify multiple sub-fault maintenance items based on the identification of the fault maintenance plan, and to determine the dynamic maintenance events of multiple sub-fault maintenance items according to the project content of each sub-fault maintenance item, the distribution location of multiple fault parts and the fault correlation coefficient.

[0092] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A fault early warning method for an electric pump, characterized in that, include: Collect multiple operating parameters of the electric pump, and determine the current operating event of the electric pump based on the multiple operating parameters, operating mode and surrounding working environment; Multiple abnormal operating nodes are identified based on the detection of current operating events of the electric pump, and multiple faulty parts of the electric pump are identified based on each abnormal operating node, associated operating parts, and the thermal distribution diagram of the electric pump. Based on multiple operating parameters and corresponding operating stages of the electric pump, the emergency floating parameter combination of the electric pump is determined. Based on the emergency floating parameter combination of the electric pump, multiple fault parts of the electric pump, and the service life of the electric pump, multiple abnormal fault parts and regular fault parts are determined, and gradient fault control is performed on multiple abnormal fault parts. Based on multiple abnormal fault components and regular fault components, determine the corresponding fault correlation coefficients, and based on multiple abnormal fault components, regular fault components, and corresponding fault correlation coefficients, determine the corresponding multiple fault maintenance combinations. The corresponding fault maintenance plan is determined based on each fault maintenance combination, the current working node of the electric pump, and the working plan of the electric pump. Based on the identification of fault maintenance plans, multiple sub-fault maintenance projects are determined. Dynamic maintenance events for multiple sub-fault maintenance projects are determined according to the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient.

2. The fault early warning method for electric pumps according to claim 1, characterized in that, The system collects multiple operating parameters of the electric pump and determines the current operating event of the pump based on these parameters, its operating mode, and the surrounding working environment. This includes: The system monitors the operation of the electric pump in real time and collects multiple operating parameters of the electric pump at different time periods. Based on the multiple operating parameters of the electric pump and the current operating mode of the electric pump, the system determines the corresponding combination of operating parameters and the current working content based on the combination of operating parameters and the working state of the electric pump. The current position of the electric pump is collected, and the surrounding working environment is determined based on the environmental detection of the current position of the electric pump. Based on the surrounding working environment, the current working content, and the working signals of the electric pump, the current working event of the electric pump is determined.

3. The fault early warning method for electric pumps according to claim 1, characterized in that, The process involves identifying multiple abnormal operating nodes based on the detection of current operating events of the electric pump, and determining multiple faulty parts of the electric pump based on each abnormal operating node, associated operating parts, and the thermal distribution diagram of the electric pump, including: The current working events of the electric pump are collected, and multiple abnormal working contents are identified based on the detection of the current working events of the electric pump. In each abnormal working content, multiple corresponding key abnormal factors are identified based on the identification of the abnormal working content. Based on multiple key abnormal factors, corresponding time points, and the working status of the electric pump, the abnormal working node corresponding to the abnormal working content is determined. At this time, the current working event of the electric pump has multiple abnormal working nodes. In each abnormal working node, the relevant working part of the electric pump in China is determined by tracing the abnormal working node. At the same time, multiple temperature parameters of the electric pump are collected. Based on the multiple temperature parameters, the corresponding temperature detection locations and the overall shape of the electric pump, a thermal distribution map of the electric pump is constructed. Based on the thermal distribution map of the electric pump, multiple abnormal working nodes and the corresponding relevant working parts, multiple fault parts of the electric pump are determined.

4. The fault early warning method for electric pumps according to claim 1, characterized in that, The method involves determining the emergency float parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages, identifying multiple abnormal and regular fault components based on the emergency float parameter combination, multiple fault parts of the electric pump, and the service life of the electric pump, and implementing gradient fault control for the multiple abnormal fault parts, including: Multiple operating parameters of the electric pump are collected. The corresponding working stage is determined based on the time nodes of the multiple operating parameters and the sub-working content of the electric pump. A dynamic diagram of operating parameters is constructed based on the multiple operating parameters, the corresponding working stage, and the working status of the electric pump. Each emergency floating zone is determined based on the identification of the dynamic diagram of operating parameters. The combination of emergency floating parameters of the electric pump is determined based on each emergency floating zone, the corresponding working status, and the multiple operating parameters.

5. The fault early warning method for electric pumps according to claim 4, characterized in that, The method involves determining the emergency float parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages, identifying multiple abnormal and regular fault components based on the emergency float parameter combination, multiple fault components of the electric pump, and the service life of the electric pump, and implementing gradient fault control for the multiple abnormal fault components. The method also includes: The first fault combination is determined based on the emergency floating parameter combination of the electric pump and multiple fault parts of the electric pump; the second fault combination is determined based on the multiple fault parts of the electric pump and the service life of the electric pump; multiple abnormal fault parts and normal fault parts are determined based on the first fault combination, the second fault combination and the working environment of the electric pump. Based on the identification of each abnormal fault component, the corresponding emergency fault level is determined. Based on the fault level of each abnormal fault component, the corresponding emergency fault level, and the fault level of the regular fault component, gradient fault control measures are triggered, and gradient fault control is performed on multiple abnormal fault components.

6. The fault early warning method for electric pumps according to claim 1, characterized in that, The process involves determining the corresponding fault correlation coefficients based on multiple abnormal fault components and regular fault components, and then determining multiple corresponding fault maintenance combinations based on the multiple abnormal fault components, regular fault components, and the corresponding fault correlation coefficients. Based on each fault maintenance combination, the current operating node of the electric pump, and the electric pump's operating schedule, a corresponding fault maintenance plan is determined, including: Collect data on multiple abnormal faults and regular faults, and determine the corresponding fault correlation coefficients based on the fault content of the multiple abnormal faults, the fault content of the regular faults, and the operation of the electric pump. The first sub-fault maintenance combination is determined based on multiple abnormal fault components and fault correlation coefficients. The second sub-fault maintenance combination is determined based on the regular fault components and fault correlation coefficients. Based on the first sub-fault maintenance combination, the second sub-fault maintenance combination, and the abnormal signal of the electric pump, multiple corresponding fault maintenance combinations are determined.

7. The fault early warning method for electric pumps according to claim 6, characterized in that, The process involves determining the corresponding fault correlation coefficients based on multiple abnormal fault components and regular fault components, and then determining multiple corresponding fault maintenance combinations based on the multiple abnormal fault components, regular fault components, and the corresponding fault correlation coefficients. Based on each fault maintenance combination, the current operating node of the electric pump, and the electric pump's operating schedule, the corresponding fault maintenance plan is determined, which also includes: The first fault maintenance coefficient is determined based on the current working node of each fault maintenance combination and the electric pump. The second fault maintenance coefficient is determined based on the working plan of each fault maintenance combination and the electric pump. The corresponding fault maintenance plan is determined according to the mapping relationship between the first fault maintenance coefficient, the second fault maintenance coefficient and the fault maintenance plan.

8. The fault early warning method for electric pumps according to claim 1, characterized in that, The identification of multiple sub-fault maintenance projects based on the fault maintenance plan, and the determination of dynamic maintenance events for multiple sub-fault maintenance projects based on the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient, including: Collect fault maintenance plans, identify multiple sub-fault maintenance items based on the fault maintenance plans, and mark the corresponding fault maintenance operation methods; at the same time, collect the distribution locations of multiple fault parts, mark the corresponding location importance coefficients, and determine the first sub-maintenance event based on the distribution locations of multiple fault parts, location importance coefficients, and corresponding sub-fault maintenance items.

9. The fault early warning method for an electric pump according to claim 8, characterized in that, The process of identifying multiple sub-fault maintenance projects based on fault maintenance plan identification, and determining dynamic maintenance events for multiple sub-fault maintenance projects according to the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient, further includes: The second sub-maintenance event is determined based on the project content of the sub-fault maintenance project, the corresponding fault maintenance operation method, and the fault correlation coefficient; the dynamic maintenance events of multiple sub-fault maintenance projects are determined based on the first sub-maintenance event, the second sub-maintenance event, and the service life of the electric pump.

10. A fault early warning system for an electric pump, characterized in that, The fault early warning system for the electric pump is applied to the fault early warning method for the electric pump as described in any one of claims 1-9, and the fault early warning system for the electric pump includes: The current working event module is used to collect multiple working parameters of the electric pump and determine the current working event of the electric pump based on the multiple working parameters, working mode and surrounding working environment. The fault section module is used to determine multiple abnormal operating nodes based on the detection of the current operating events of the electric pump, and to determine multiple fault sections of the electric pump based on each abnormal operating node, associated operating section, and the thermal distribution diagram of the electric pump. The abnormal fault module is used to determine the emergency floating parameter combination of the electric pump based on multiple operating parameters and corresponding operating stages of the electric pump. Based on the emergency floating parameter combination of the electric pump, multiple fault parts of the electric pump and the service life of the electric pump, it determines multiple abnormal fault parts and regular fault parts, and performs gradient fault control on multiple abnormal fault parts. The fault maintenance plan module is used to determine the corresponding fault correlation coefficients based on multiple abnormal fault components and regular fault components, and to determine multiple corresponding fault maintenance combinations based on multiple abnormal fault components, regular fault components and corresponding fault correlation coefficients; and to determine the corresponding fault maintenance plan based on each fault maintenance combination, the current working node of the electric pump and the working plan of the electric pump. The dynamic maintenance event module is used to identify multiple sub-fault maintenance projects based on the identification of fault maintenance plans, and to determine the dynamic maintenance events of multiple sub-fault maintenance projects according to the project content of each sub-fault maintenance project, the distribution location of multiple fault parts, and the fault correlation coefficient.

Images