Water pump operation efficiency monitoring and abnormity early warning threshold value self-adaptive setting method

Abstract

The invention relates to the technical field of water pump operation monitoring, and discloses a water pump operation efficiency monitoring and abnormity early warning threshold value self-adaptive setting method. The method comprises the steps of firstly collecting operation parameters of a target water pump in a preset period, and determining the real-time operation state; forming a to-be-analyzed monitoring point set by combining environment interference monitoring points based on the divided efficiency dominant and secondary acquisition points; then calculating parameter influence coefficients of associated monitoring points in the set, and constructing a parameter association network taking the monitoring points as nodes and the influence coefficients as weights; then determining a network core path, and performing priority ranking on the monitoring points; and finally, processing the data according to the priority to realize the self-adaptive setting of the abnormal early warning threshold. According to the method, through dynamic division of the monitoring points, analysis of parameter association and sorting processing, threshold setting better fits the actual running state of the water pump, and the pertinence and adaptability of monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water pump operation monitoring, and in particular to a method for adaptively setting a water pump operation efficiency monitoring and abnormality warning threshold. Background Art

[0002] In many fields, including industrial production, municipal water supply, and agricultural irrigation, water pumps are core fluid transport equipment. Their operating efficiency is directly related to energy consumption, system stability, and operating costs. With the development of intelligent technology, real-time monitoring of water pump operating status and abnormal warnings have become an important part of equipment management. Currently, monitoring water pump efficiency relies heavily on fixed parameter collection points, typically including flow rate, head, power, speed, and temperature. These parameters are used to assess the real-time efficiency of water pumps. However, in practice, due to the complex and changing operating environment of water pumps, such as changes in water quality, fluctuations in pipeline pressure, and ambient temperature variations, monitoring data from fixed collection points often fails to fully reflect the actual operating status of the water pumps. Existing abnormality warning threshold settings often rely on empirical values ​​or fixed thresholds, which lack adaptability to dynamic changes in the pump's operating status. When a pump is in different operating conditions (such as startup, shutdown, and load changes), the range of its normal operating parameters changes significantly. Fixed thresholds can easily lead to inaccurate warnings, false alarms, or missed alarms. For example, during the pump's startup phase, power and speed increase dramatically within a short period of time. If the thresholds used for normal operation are used, false alarms are likely to be triggered. During long-term low-load operation, the gradual deviation of some parameters may be overlooked by the fixed thresholds, resulting in potential faults not being detected in a timely manner. Existing monitoring methods fail to adequately consider the correlations between parameters, often analyzing each parameter as an independent entity and ignoring their mutual influence. For example, a change in flow rate may cause corresponding changes in head and power. Setting thresholds for individual parameters makes it difficult to accurately identify the root cause of the anomaly, increasing the difficulty of troubleshooting. These issues reduce the accuracy and reliability of pump efficiency monitoring, impacting the timeliness and effectiveness of equipment maintenance. Summary of the Invention

[0003] The object of the present invention is to provide a method for monitoring the operating efficiency of a water pump and adaptively setting an abnormality warning threshold, so as to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above objectives, the present invention provides a method for monitoring pump operation efficiency and adaptively setting abnormality warning thresholds, the method comprising: Collecting various operating parameters of a currently running target water pump within a preset period, and determining the real-time operating status of the target water pump based on the operating parameters; Based on the real-time operating status, the operating parameter collection points are divided into efficiency-dominant collection points and efficiency-secondary collection points, and environmental interference monitoring points are determined among the auxiliary monitoring points other than the operating parameter collection points, wherein the efficiency-dominant collection points, the efficiency-secondary collection points, and the environmental interference monitoring points constitute a set of monitoring points to be analyzed; Determine the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed, and construct a parameter association network of the set of monitoring points to be analyzed using the monitoring points in the set of monitoring points to be analyzed as nodes and the parameter influence coefficient as weights connecting the nodes; Determining a core path of the parameter association network, and determining a priority ranking of each monitoring point in the set of monitoring points to be analyzed based on the core path; The data of each monitoring point in the set of monitoring points to be analyzed are processed in sequence according to the priority order to achieve adaptive setting of abnormal warning thresholds.

[0005] Preferably, determining the real-time operating status of the target water pump according to the operating parameters includes: Calculating, based on the operating parameters, an efficiency benchmark value of the target water pump over multiple historical cycles; According to the fluctuation range of the operating parameters corresponding to each efficiency benchmark value, the calculated efficiency benchmark values ​​are grouped to form one or more efficiency status groups; A target efficiency state group that matches the current operating parameters of the target water pump is determined in the efficiency state group, and a state identifier corresponding to the target efficiency state group is used as the real-time operating state of the target water pump.

[0006] Preferably, grouping the calculated efficiency reference values ​​according to the fluctuation range of the operating parameters corresponding to the efficiency reference values ​​includes: Obtaining a preset parameter fluctuation range in the water pump monitoring system; For any calculated efficiency reference value, the parameter fluctuation interval to which the operating parameter fluctuation range corresponding to the efficiency reference value belongs is identified, and the efficiency reference value is divided into the efficiency state group corresponding to the identified parameter fluctuation interval.

[0007] Preferably, based on the real-time operating status, dividing the operating parameter collection points into efficiency-dominant collection points and efficiency-secondary collection points includes: Determine the key influencing parameters and non-key influencing parameters corresponding to the real-time operating status; Determining a first monitoring range of the key influencing parameter at the operating parameter collection point, and determining a second monitoring range of the non-key influencing parameter at the operating parameter collection point; The operating parameter collection points covered by the first monitoring range are determined as efficiency-dominant collection points, and the operating parameter collection points covered by the second monitoring range are determined as efficiency-secondary collection points.

[0008] Preferably, determining the environmental interference monitoring point among the auxiliary monitoring points other than the operating parameter collection point includes: Setting a first influence radius for an efficiency-dominant collection point among the operating parameter collection points, and setting a second influence radius for an efficiency-secondary collection point among the operating parameter collection points; For auxiliary monitoring points other than the operating parameter collection points, if the distance to the efficiency dominant collection point is within the first influence radius, the auxiliary monitoring point is selected as the environmental interference monitoring point; if the distance to the efficiency secondary collection point is within the second influence radius, the auxiliary monitoring point is selected as the environmental interference monitoring point.

[0009] Preferably, determining the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed includes: For a first monitoring point and a second monitoring point associated with the set of monitoring points to be analyzed, identifying a parameter type of each of the first monitoring point and the second monitoring point, wherein the parameter type includes one of an efficiency dominant parameter, an efficiency secondary parameter, and an environmental interference parameter; determining a first influence weight of the first monitoring point and a second influence weight of the second monitoring point according to the identified parameter type; The correlation between the first impact weight and the historical data of the second monitoring point is calculated, and the parameter impact coefficient between the first monitoring point and the second monitoring point is determined according to the correlation.

[0010] Preferably, determining the parameter influence coefficient between the first monitoring point and the second monitoring point according to the correlation includes: Collecting historical operating data of each monitoring point in the set of monitoring points to be analyzed, and determining the fluctuation variance of the collected historical operating data; Dividing the volatility variance into multiple correlation levels, and determining a target correlation level for the calculated first impact weight and historical data correlation; A preset coefficient value corresponding to the target correlation level is determined as a parameter influence coefficient between the first monitoring point and the second monitoring point.

[0011] Preferably, processing the data of each monitoring point in the set of monitoring points to be analyzed in sequence according to the priority order to achieve adaptive setting of the abnormal warning threshold includes: Extracting real-time parameter data of each monitoring point in the priority sorting, and constructing a time series feature sequence based on the extracted real-time parameter data, wherein the arrangement order of each feature in the time series feature sequence is consistent with the priority sorting; Inputting the time series feature sequence into an adaptive threshold model to generate an abnormal warning threshold for each of the monitoring points through the adaptive threshold model; The corresponding monitoring points are monitored according to the generated abnormal warning thresholds to achieve abnormal warning.

[0012] Preferably, the method further comprises: After the abnormal warning threshold is set, continuously monitoring the parameter change rate of each monitoring point in the set of monitoring points to be analyzed; When the parameter change rate exceeds a preset fluctuation threshold for multiple consecutive periods, the step of determining the core path of the parameter association network is re-executed, and the priority sorting is adjusted according to the new core path.

[0013] Preferably, determining the key influencing parameters and non-key influencing parameters corresponding to the real-time operating status includes: Obtaining a design parameter table of the target water pump, wherein the design parameter table includes rated flow, rated head, and rated power; Comparing the actual operating parameters in the real-time operating state with the rated parameters in the design parameter table to calculate the parameter deviation percentage; The operating parameters whose parameter deviation percentage is greater than the preset deviation threshold are determined as key influencing parameters, and the operating parameters whose parameter deviation percentage is less than or equal to the preset deviation threshold are determined as non-key influencing parameters.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By dynamically dividing operating parameter collection points into efficiency-dominant and efficiency-secondary collection points, and combining them with environmental interference monitoring points, a set of monitoring points to be analyzed is formed, making the monitoring range more closely aligned with the actual operating status of the pump. This division is not fixed but adjusted based on real-time operating status. It can focus on parameters that have a more significant impact on efficiency according to the characteristics of the pump under different operating conditions, while also taking into account environmental factors that may cause interference, making monitoring more targeted. In the process of building a parameter association network, by calculating the parameter influence coefficient between any two related monitoring points and using this coefficient as the weight to connect the nodes, the inherent connections between the parameters can be clearly demonstrated. This network structure no longer views parameters in isolation, but rather analyzes their interactions from a holistic perspective. For example, when the ambient temperature changes, it may affect the power parameters of the water pump, and the power change may be related to the fluctuation of flow rate and head. The network can intuitively reflect these chain reactions, providing a more comprehensive perspective for subsequent analysis. Identifying the core paths of the parameter association network and prioritizing monitoring points makes data processing more logical and structured. Processing data sequentially according to priority allows us to focus on parameters that are most critical to efficiency and anomaly warnings, reducing interference from irrelevant data. This organized approach avoids analytical confusion caused by information overload and streamlines the process of setting anomaly warning thresholds. The adaptive setting of abnormal warning thresholds dynamically adjusts to changes in the pump's operating status. When the pump is in different operating conditions, such as startup, high load, and low load, the threshold changes accordingly to better match the normal parameter range under each operating condition. This adaptability enables warnings to more accurately identify true abnormalities, reducing misjudgments caused by fixed thresholds. It also promptly detects potential problems under different operating conditions and improves awareness of the pump's operating status. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a working principle diagram of the method for adaptively setting the water pump operating efficiency monitoring and abnormal warning threshold according to the present invention; Figure 2 Flowcharts determined for real-time operational status; Figure 3 Flowchart for parameter influence coefficient determination; Figure 4 A flow chart for calculating the refined parameter influence coefficient; Figure 5 Flowchart for determining key influencing parameters and non-key influencing parameters. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] See also Figure 1 The present invention provides a method for monitoring the operation efficiency of a water pump and adaptively setting an abnormality warning threshold, the method comprising: Various operating parameters of a currently running target water pump within a preset period are collected, and a real-time operating state of the target water pump is determined based on the operating parameters.

[0018] The preset cycle can be set based on the operating characteristics of the pump, for example, 30 minutes. Operating parameters include but are not limited to flow rate, head, power, speed, inlet and outlet pressures, medium temperature, etc. Sensors deployed at different locations on the pump collect these parameters. After collection, the parameters are pre-processed to remove outliers and noise data. The real-time operating status of the pump is then determined based on the processed parameters.

[0019] Based on the real-time operating status, the operating parameter collection points are divided into efficiency-dominant collection points and efficiency-secondary collection points, and environmental interference monitoring points are determined among the auxiliary monitoring points other than the operating parameter collection points. The efficiency-dominant collection points, efficiency-secondary collection points, and environmental interference monitoring points constitute a set of monitoring points to be analyzed.

[0020] The real-time operating status reflects the pump's current efficiency level and operating mode. Based on this classification, the primary efficiency collection points are those that have a significant impact on pump efficiency, such as the power sensor installation points and flow sensor installation points. Secondary efficiency collection points are those that have a smaller impact on efficiency, such as the medium temperature sensor installation point. Auxiliary monitoring points include those for the pump's surrounding environment, such as temperature, humidity, and vibration. These monitoring points are then screened for environmental interference monitoring points that may interfere with the pump's operating parameters, such as the ambient temperature monitoring point close to the pump. Together, these three monitoring points form the set of monitoring points to be analyzed.

[0021] Determine the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed, and construct a parameter association network of the set of monitoring points to be analyzed using the monitoring points in the set of monitoring points to be analyzed as nodes and the parameter influence coefficient as the weight between the connecting nodes.

[0022] Associated monitoring points are those where parameters influence each other. For example, power and flow collection points are associated, and ambient temperature and medium temperature collection points are associated. By calculating the parameter influence coefficients between these associated monitoring points, the degree of influence between the parameters is quantified. Using the monitoring points as nodes and the influence coefficients as weights, a parameter association network is constructed using graph theory. The weight of each edge in the network represents the corresponding parameter influence coefficient.

[0023] A core path of the parameter association network is determined, and a priority ranking of each monitoring point in the set of monitoring points to be analyzed is determined based on the core path.

[0024] The core path is the path in the parameter association network that has the greatest impact on pump efficiency. This can be determined by analyzing the connection strength and weight values ​​of the nodes in the network. For example, a maximum weight path algorithm can be used to select the core path. Based on the importance of the monitoring points on the core path and the degree of association between other monitoring points and the core path, all monitoring points to be analyzed are prioritized. Key nodes on the core path have higher priority, while nodes with weaker associations with the core path have lower priority.

[0025] The data of each monitoring point in the set of monitoring points to be analyzed are processed in sequence according to the priority order to achieve adaptive setting of abnormal warning thresholds.

[0026] The data of each monitoring point is analyzed and processed in order of priority from high to low, with priority given to the data of high-priority monitoring points. Then, based on the correlation between the processing results and the parameters, the abnormal warning threshold of each monitoring point is dynamically adjusted so that the threshold can adapt to changes in the operating status of the water pump.

[0027] Example 1: See Figure 2 When determining the target pump's real-time operating status based on operating parameters, the target pump's efficiency baseline is calculated over multiple historical periods based on the operating parameters. The efficiency baseline is derived from the ratio of the effective power generated during pump operation to the input power. The effective power is calculated based on real-time data collected regarding flow rate, head, and the density of the conveying medium. The input power can be directly obtained using a power sensor installed on the pump motor or derived from collected current and voltage data. The historical periods selected must cover different pump operating conditions. The number of historical periods can be set based on actual monitoring needs. For example, the most recent 60 periods, each corresponding to one hour of continuous operating data, are selected to ensure that the calculated efficiency baseline reflects the pump's operating efficiency characteristics over different time periods. During the calculation process, the collected operating parameters are preprocessed to remove abnormal data caused by sensor failure or transient interference. Missing data is supplemented using interpolation to ensure data integrity and continuity, thereby improving the accuracy of the efficiency baseline calculation.

[0028] According to the fluctuation range of the operating parameters corresponding to each efficiency benchmark value, the calculated efficiency benchmark values ​​are grouped to form one or more efficiency status groups. During the specific operation, the parameter fluctuation ranges pre-set in the water pump monitoring system are first obtained. These ranges are based on the design parameters of the water pump, industry standards, and empirical data accumulated from long-term operation. Different operating parameters correspond to different fluctuation ranges. For example, the fluctuation range of flow parameters can be divided into multiple levels, and parameters such as head, power, and speed are also set with corresponding fluctuation ranges based on the degree of their influence on the efficiency of the water pump. The division of these intervals needs to take into account the natural fluctuation range of the parameters during normal operation of the water pump, while taking into account the reasonable variation range of the parameters under different working conditions, to ensure that the grouping results can accurately reflect the efficiency status of the water pump.

[0029] For any calculated efficiency benchmark value, identify the parameter fluctuation interval to which the operating parameter fluctuation range corresponding to that efficiency benchmark value belongs, and assign that efficiency benchmark value to the efficiency state group corresponding to the identified parameter fluctuation interval. Each efficiency benchmark value corresponds to a set of operating parameter fluctuation data, and each of these parameter fluctuation ranges must be analyzed individually to determine which preset fluctuation interval it belongs to. For example, if the flow fluctuation range corresponding to a certain efficiency benchmark value is ±4%, and the system's preset flow fluctuation intervals are within ±5%, then that flow fluctuation range is assigned to this interval. Similarly, if the head fluctuation range corresponding to that efficiency benchmark value is ±7%, then if the head fluctuation intervals are within ±10%, then that head fluctuation range is assigned to that interval. If the combination of the ±5% flow fluctuation interval and the ±10% head fluctuation interval in the system corresponds to an efficiency state group, then that efficiency benchmark value is assigned to that group. For situations with multiple operating parameters, the fluctuation intervals of all parameters must be comprehensively considered to determine the efficiency state group to which the efficiency benchmark value belongs, ensuring that each efficiency benchmark value is accurately assigned to the corresponding group.

[0030] A target efficiency state group matching the target pump's current operating parameters is identified within the efficiency state group, and the state identifier corresponding to the target efficiency state group is used as the target pump's real-time operating state. Real-time operating parameters are collected and processed in the same manner as historical parameters, requiring similar preprocessing to remove interference. The fluctuation range of the current operating parameters is compared with the parameter fluctuation ranges corresponding to each efficiency state group. When the current parameter fluctuation range fully matches all parameter fluctuation ranges corresponding to a particular efficiency state group, that group is identified as the target efficiency state group. The state identifier characterizes the efficiency state group, such as "high-efficiency stable operation," "medium-efficiency fluctuating operation," or "low-efficiency operation." These identifiers provide a visual representation of the pump's current operating state and provide a basis for subsequent parameter collection point allocation and abnormal warning threshold setting. During the matching process, if the fluctuation range of the current operating parameters simultaneously meets the range requirements of multiple efficiency state groups, the efficiency state group that best matches the current operating conditions is selected as the target group based on parameter change trends and historical matching records to ensure accurate real-time operating state determination.

[0031] Example 2: See Figure 5 When dividing the operating parameter collection points into efficiency-dominant and efficiency-secondary collection points based on the real-time operating status, first determine the key and non-key influencing parameters corresponding to the real-time operating status. Obtain the design parameter table of the target water pump. This table is provided by the water pump manufacturer and contains the rated parameters of the water pump under standard operating conditions. In addition to the rated flow, rated head, and rated power, it may also include parameters such as rated speed and rated inlet and outlet pressures. These parameters together constitute the benchmark reference for the normal operation of the water pump.

[0032] Compare the actual operating parameters in real-time operation with the rated parameters in the design parameter table to analyze any discrepancies. Actual operating parameters are collected in real time by sensors deployed at key locations on the pump, covering data corresponding to the rated parameters, such as flow rate, head, and power. During the comparison process, ensure that the actual operating parameters are collected under the same conditions as the rated parameters. For example, environmental conditions such as medium temperature and density must conform to the standard conditions indicated in the design parameter table. If any discrepancies exist, the actual operating parameters must be corrected to ensure the reliability of the comparison results.

[0033] After comparing the differences between the parameters, operating parameters with a parameter deviation percentage greater than a preset deviation threshold are identified as key influencing parameters, while operating parameters with a parameter deviation percentage less than or equal to the preset deviation threshold are identified as non-key influencing parameters. The preset deviation threshold is determined based on the pump type, application scenario, and operating requirements. The deviation thresholds for different parameters may vary. For example, for a pump used in a precision water supply system, the deviation threshold for the flow parameter may be set lower, while for a pump used in general irrigation, the deviation threshold for the power parameter may be set relatively higher.

[0034] After determining the key influencing parameters and non-key influencing parameters, determine the first monitoring range of the key influencing parameters in the operating parameter collection points, and determine the second monitoring range of the non-key influencing parameters in the operating parameter collection points. The first monitoring range refers to the installation positions and coverage areas of all sensors that can collect key influencing parameters. These locations are usually distributed in key parts that have a greater impact on the efficiency of the water pump. For example, the sensor that collects flow parameters may be installed on the outlet pipe of the water pump, and the sensor that collects power parameters may be integrated into the control circuit of the motor. The installation positions of these sensors together constitute the first monitoring range. The second monitoring range is the location and coverage area of ​​the sensors that collect non-key influencing parameters. For example, the sensor for monitoring the medium temperature may be installed on the inlet pipe of the water pump, and the sensor for monitoring the ambient humidity may be installed in the water pump room. These locations form the second monitoring range.

[0035] The operating parameter collection points covered by the first monitoring range are identified as efficiency-dominant collection points, and the operating parameter collection points covered by the second monitoring range are identified as efficiency-secondary collection points. The data collected by the efficiency-dominant collection points directly reflects the core influencing factors of water pump efficiency, and its data quality and real-time performance are crucial for subsequent efficiency monitoring and abnormality warnings. During the data processing process, the data from these collection points will be prioritized and analyzed to ensure that abnormal conditions that may affect water pump efficiency can be discovered in a timely manner. The data collected by the efficiency-secondary collection points has a relatively small impact on water pump efficiency, and its data processing priority is lower than that of the efficiency-dominant collection points, but it cannot be ignored. This data can provide supplementary information for a comprehensive assessment of the water pump's operating status and help more accurately judge the overall operating status of the water pump. Through this division method, the water pump monitoring system can process various types of monitoring data more targetedly, improving the system's operating efficiency and monitoring accuracy.

[0036] Example 3: See Figure 3When determining the environmental interference monitoring points among the auxiliary monitoring points other than the operating parameter collection points, first set the first influence radius for the efficiency-dominant collection points among the operating parameter collection points, and set the second influence radius for the efficiency-secondary collection points among the operating parameter collection points. The values ​​of the first influence radius and the second influence radius need to be determined in combination with the physical characteristics of the parameters and the actual monitoring scenario. For example, for collection points that collect efficiency-dominant parameters such as power and flow that are more sensitive to environmental vibrations, the first influence radius can be appropriately set larger to cover areas that may produce significant vibration interference; and for collection points that collect efficiency-secondary parameters such as medium temperature that are relatively less affected by the environment, the second influence radius can be set smaller. The setting of these radii requires an on-site investigation of the water pump operating environment, taking into account factors such as the distribution of surrounding equipment and wall obstructions, to ensure that environmental factors that may interfere with the corresponding parameters can be accurately captured.

[0037] For auxiliary monitoring points other than operating parameter collection points, if their distance from the dominant efficiency collection point is within the first influence radius, they are selected as environmental interference monitoring points; if their distance from the secondary efficiency collection point is within the second influence radius, they are selected as environmental interference monitoring points. Auxiliary monitoring points can be of various types, including ambient temperature and humidity sensors installed in the pump room, vibration sensors installed near equipment, and noise sensors installed on pipe supports. During the screening process, the straight-line distance between each auxiliary monitoring point and each dominant efficiency collection point and secondary efficiency collection point is measured one by one. Distance measurements are calculated using spatial distance calculation methods using the location coordinates recorded during installation. If the distance between an auxiliary monitoring point and any dominant efficiency collection point is less than or equal to the first influence radius, it is included in the environmental interference monitoring points. Similarly, if the distance from any secondary efficiency collection point is less than or equal to the second influence radius, it is also designated as an environmental interference monitoring point. This approach ensures that all environmental factors that may interfere with operating parameters are monitored.

[0038] When determining the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed, for the first monitoring point and the second monitoring point associated in the set of monitoring points to be analyzed, the parameter types of the first monitoring point and the second monitoring point are respectively identified, and the parameter types include one of the efficiency dominant parameter, the efficiency secondary parameter, and the environmental interference parameter. The identification of the parameter type is based on the attributes of the monitoring point and the nature of the collected parameters. For example, the flow parameter collected by the flow sensor installed on the outlet pipe of the water pump is an efficiency dominant parameter; the medium temperature parameter collected by the temperature sensor installed on the inlet pipe is an efficiency secondary parameter; and the parameter collected by the ambient temperature sensor installed in the machine room is an environmental interference parameter. During the identification process, it is necessary to compare with the preset parameter type classification table to ensure that the parameter type of each monitoring point is accurately divided, providing a basis for the subsequent determination of the impact weight.

[0039] Based on the identified parameter type, the first impact weight of the first monitoring point is determined, and the second impact weight of the second monitoring point is determined. The numerical settings of the first impact weight and the second impact weight are based on the physical impact mechanism of the monitoring point parameter type on the pump operation efficiency and the industry-recognized parameter importance classification rules. The specific correlation relationship is as follows: If the monitoring point parameter type is an efficiency-dominant parameter (such as power, flow rate, or head), its corresponding impact weight (including the first or second impact weight) is set to the highest level. This type of parameter directly determines the ratio between the effective power and input power of the pump and is a core indicator of pump efficiency. For example, the power parameter is directly related to the conversion efficiency between motor energy consumption and output power, and the flow parameter directly affects fluid delivery efficiency. Therefore, it should be given the highest weight to reflect its dominant role in efficiency.

[0040] If the monitoring point parameter type is a secondary efficiency parameter (such as medium temperature or inlet and outlet pressure), its corresponding influence weight is set to a medium level. This type of parameter affects pump efficiency indirectly. For example, changes in medium temperature will cause changes in fluid density, which in turn affects the effective power calculation result. However, compared with parameters such as power and flow, its impact on efficiency is weaker, so its weight level is lower than that of the dominant efficiency parameter.

[0041] If the monitoring point parameter type is an environmental interference parameter (such as ambient temperature, room humidity, and ambient vibration), its corresponding impact weight is set to the lowest level. This type of parameter indirectly interferes with the pump's operating status through external environmental factors. For example, excessively high ambient temperature can reduce the motor's heat dissipation efficiency, indirectly affecting power consumption. However, this effect on efficiency requires transmission through multiple links, resulting in a long and weak impact. Therefore, the weight is the lowest.

[0042] Weight value association rules: The impact weight values ​​corresponding to the same parameter type remain consistent, and the weight values ​​of different types of parameters meet the relationship of "efficiency-dominant parameter weight > efficiency-secondary parameter weight > environmental interference parameter weight". The specific value of the weight value needs to be determined in combination with the equipment type of the target water pump (such as centrifugal pump, axial flow pump), application scenario (such as industrial water supply, agricultural irrigation) and design standards, through the following methods: Refer to the markings on parameter importance in the pump design manual. For example, the design manual of a certain type of centrifugal pump clearly states that "flow rate and head are the core influencing parameters of efficiency, and medium temperature is a secondary influencing parameter." Then, the corresponding matching weight level should be based on this marking; Combined with the requirements of the parameter monitoring priority in the industry technical specifications, the weight level is reversely deduced according to the monitoring priority, and high-frequency monitoring parameters are assigned higher weights; Based on the historical operation data verification of similar water pumps, if the historical data shows that the change of a certain type of parameter (such as power) has the highest correlation frequency and the largest amplitude with the change of efficiency, the rationality of the corresponding weight level of this type of parameter is confirmed.

[0043] The numerical value of the impact weight reflects the degree of influence of the parameter type on the pump efficiency. The determination of these weights requires reference to the pump design manual, industry specifications and the correlation between each parameter and efficiency changes in historical operating data. They are set after comprehensive analysis, and the impact weights of parameters of the same type remain consistent to ensure the uniformity of the analysis.

[0044] Calculate the correlation between the first impact weight and the historical data of the second monitoring point, and based on this correlation, determine the parameter influence coefficient between the first and second monitoring points. The historical data correlation is calculated based on the parameter data of the two monitoring points over multiple historical periods, using statistical analysis to determine the degree of correlation between their changing trends. During the calculation process, the historical data must first be standardized to eliminate the influence of different parameter units and magnitudes, making the correlation analysis more comparable.

[0045] The parameter influence coefficient can be determined by the following formula:

[0046] in, represents the parameter influence coefficient between the first monitoring point and the second monitoring point, represents the first impact weight of the first monitoring point, Represents the correlation value between the first impact weight and the historical data of the second monitoring point.

[0047] Correlation values ​​range from 0 to 1, with larger values ​​indicating stronger correlation. In actual calculations, sufficient historical data, typically the most recent 100 cycles of operating data, is required to ensure the reliability of the correlation analysis. The parameter influence coefficient calculated in this way comprehensively reflects the strength of the parameter influence between two monitoring points, providing a quantitative basis for the subsequent construction of a parameter association network.

[0048] Example 4: See Figure 4 When determining the parameter influence coefficient between the first monitoring point and the second monitoring point based on the correlation, it is necessary to first collect the historical operating data of each monitoring point in the set of monitoring points to be analyzed. These data cover parameter records in multiple operating cycles in the past, including efficiency-dominant parameters such as power and flow, efficiency-minor parameters such as medium temperature, and environmental interference parameters such as ambient humidity. During the data collection process, it is necessary to cover the operation of the water pump under different loads and different environmental conditions, such as full-load operation periods on weekdays, low-load operation periods on weekends, and operation data in special environments such as high temperature and humidity. After the collection is completed, the data is sorted to remove jump values ​​caused by temporary sensor failures and abnormal interruption data caused by external factors such as sudden power outages, to ensure that the historical operation data can truly reflect the normal operating status of the water pump.

[0049] The fluctuation variance of the collected historical operating data is then determined. The fluctuation variance can reflect the degree of dispersion of the parameters within the historical period. By analyzing the fluctuation variance, the stability of different parameters can be understood. For example, the fluctuation variance of a certain flow monitoring point is small, indicating that its numerical changes in historical operation are relatively stable; while the fluctuation variance of a certain ambient temperature monitoring point is large, indicating that it is more significantly affected by the external environment. According to the size of the fluctuation variance, multiple correlation levels are divided, and different correlation levels correspond to different intervals of parameter influence. For example, the interval with the smallest fluctuation variance corresponds to an extremely strong correlation between parameters, the interval with a slightly larger fluctuation variance corresponds to a strong correlation, and so on, until the interval with the largest fluctuation variance corresponds to an extremely weak correlation.

[0050] After determining the target correlation level for the calculated first impact weight and the historical data correlation, the preset coefficient value corresponding to that level is used as the parameter influence coefficient between the first monitoring point and the second monitoring point. For example, if the historical data correlation between the power monitoring point (efficiency-dominant parameter) and the flow monitoring point (efficiency-dominant parameter) is at an extremely strong correlation level, and the preset coefficient value corresponding to that level is 0.9, then the parameter influence coefficient between the two is 0.9; if the correlation between the ambient temperature monitoring point (environmental interference parameter) and the medium temperature monitoring point (efficiency-secondary parameter) is at a weak correlation level, and the corresponding preset coefficient value is 0.3, then their parameter influence coefficient is 0.3.

[0051] When processing the data of each monitoring point in the set of monitoring points to be analyzed in sequence according to the priority sorting, the real-time parameter data of each monitoring point in the priority sorting is first extracted. Assuming that the priority sorting is power monitoring point, flow monitoring point, ambient temperature monitoring point, and medium temperature monitoring point, the real-time data of these monitoring points in the current and recent cycles are extracted in sequence. The extraction of real-time data must ensure timeliness, and is usually collected every few minutes to ensure that the latest changes in parameters can be reflected in a timely manner. After extraction, a time series feature sequence is constructed based on these real-time parameter data. The features of each position in the sequence correspond one-to-one to the monitoring points in the priority sorting. For example, the first feature of the sequence is power data, the second is flow data, and the subsequent features are ambient temperature and medium temperature data. Each feature contains corresponding time information, forming a sequence arranged in chronological order.

[0052] The time series feature sequence is input into the adaptive threshold model, which generates abnormal warning thresholds for each monitoring point based on the data variation patterns in the sequence. The model analyzes the changing trends of the parameters in the time series feature sequence. For example, the power parameter will rise rapidly during the pump startup phase and then remain relatively stable during the stable operation phase. Based on this trend, the model sets dynamic thresholds for the power monitoring point during the startup phase and static thresholds during the stable phase. For parameters that are significantly affected by the environment, such as ambient temperature, the model adjusts the thresholds based on seasonal variations. The warning threshold in summer is higher than that in winter to accommodate seasonal environmental differences.

[0053] When monitoring the corresponding monitoring points according to the generated abnormal warning threshold, the current parameters of the monitoring points are compared with the warning threshold in real time. When the parameters of a monitoring point exceed the threshold range, the system will trigger an abnormal warning. For example, if the real-time data of the power monitoring point suddenly exceeds the upper warning threshold, the system will immediately issue a warning signal; if the value of the flow monitoring point continuously falls below the lower warning threshold, the system will also trigger a warning after several cycles of confirmation. Warning information will be transmitted through various means, such as displaying a red alarm icon on the monitoring center screen and sending prompt information to the maintenance personnel's terminal devices, so that relevant personnel will be aware of it in a timely manner and take corresponding measures.

[0054] Throughout the entire process, the adaptive threshold model will continuously learn new operating data. When the water pump enters a new operating stage, such as long-term low-load operation, the model will gradually adjust the warning threshold to match the new operating status, ensuring the accuracy and applicability of abnormal warnings.

[0055] Example 5: After the abnormal warning threshold is set, it is necessary to continuously monitor the parameter change rate of each monitoring point in the set of monitoring points to be analyzed. The parameter change rate reflects the magnitude of the change in the parameters of the monitoring point in adjacent cycles. By tracking this indicator in real time, potential changes in the operating status of the water pump can be captured in a timely manner. The monitoring process covers all monitoring points to be analyzed, including efficiency-dominant collection points such as power sensors and flow sensors, efficiency-secondary collection points such as medium temperature sensors, and environmental interference monitoring points such as ambient humidity sensors. The monitoring frequency is consistent with the parameter collection cycle. For example, the parameter change rate is calculated every 30 minutes to ensure that abnormal fluctuations in parameters can be detected in a timely manner.

[0056] To calculate the parameter rate of change, the parameter values ​​for the current cycle and the previous cycle must be obtained. The magnitude of the change is calculated by dividing the difference between the two by the ratio of the previous cycle's value. For example, if the parameter value for a power monitoring point was 100kW in the previous cycle and 105kW in the current cycle, the corresponding rate of change is 5%. If the parameter value drops to 98kW in the next cycle, the rate of change is -6.67%. During the calculation process, it is important to ensure consistency in parameter units. For parameters with different units, such as flow rate and head, the rate of change is expressed as a percentage to facilitate consistent comparison and analysis.

[0057] When the parameter change rate exceeds the preset fluctuation threshold for multiple consecutive cycles, it indicates that the operating state of the pump may have changed significantly, and the step of determining the core path of the parameter association network needs to be re-executed. The number of consecutive cycles is set according to the operational stability of the pump. For example, for a relatively stable industrial pump, it can be set to 5 cycles; for a small pump that starts and stops frequently, it can be set to 3 cycles. The preset fluctuation threshold varies depending on the parameter type. For example, the fluctuation threshold of the power parameter is set relatively large, while the fluctuation threshold of the ambient temperature parameter is set relatively small to accommodate the inherent characteristics of each parameter.

[0058] When re-determining the core path, the parameter influence coefficients between each monitoring point must be recalculated based on the latest parameter data, and a new parameter association network must be constructed. For example, if the rate of change of the ambient temperature continuously exceeds the fluctuation threshold, the influence coefficient between it and the medium temperature monitoring point may increase. The ambient temperature monitoring point, which was originally in a secondary position, may form strong associations with more nodes in the new network. By analyzing the connection strength and weight distribution of nodes in the new network, the core path with the greatest impact on the current operating status is identified. The monitoring points on the core path are generally those with large parameter change rates and significant influence on other parameters.

[0059] Priority rankings are adjusted based on the new core path, increasing the priority of monitoring points along the core path and decreasing the priority of monitoring points further away from the core path. For example, if a flow monitoring point is found to be a key node on the core path after reanalysis, its priority will be adjusted from third to first. Meanwhile, the priority of an ambient humidity monitoring point, which previously had a higher priority but now has a reduced impact, may be lowered accordingly. This adjusted priority ranking will affect the order of subsequent data processing, ensuring that data from high-priority monitoring points is analyzed and processed first.

[0060] After the priority ranking is adjusted, the adaptive threshold model regenerates the anomaly warning threshold based on the new time series feature sequence, allowing the threshold to adapt to the changed operating status. For example, if the priority of a flow monitoring point is increased, the model will pay more attention to subtle changes in its parameters and generate a more sensitive warning threshold. For monitoring points with lowered priority, the threshold may be appropriately relaxed to reduce unnecessary warnings. This dynamic adjustment mechanism ensures that the anomaly warning system always stays synchronized with the actual operating status of the water pump and can promptly respond to various changes during operation.

[0061] Throughout the adjustment process, the system records the time periods when the parameter change rate exceeded the standard, changes in the core paths, and the details of the priority adjustments, creating an adjustment log. This log can be used to trace the evolution of the pump's operating status, providing reference information for subsequent maintenance and optimization. Furthermore, the system continues to monitor the adjusted parameter change rate. If the parameter exceeds the standard again, the adjustment process will be repeated, forming a continuous dynamic adaptation mechanism.

[0062] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0063] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold, characterized in that: The method is applied to a water pump monitoring system, wherein the water pump monitoring system is pre-deployed with multiple operating parameter collection points, and the method includes: Collecting various operating parameters of a currently running target water pump within a preset period, and determining the real-time operating status of the target water pump based on the operating parameters; Based on the real-time operating status, the operating parameter collection points are divided into efficiency-dominant collection points and efficiency-secondary collection points, and environmental interference monitoring points are determined among the auxiliary monitoring points other than the operating parameter collection points, wherein the efficiency-dominant collection points, the efficiency-secondary collection points, and the environmental interference monitoring points constitute a set of monitoring points to be analyzed; Determine the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed, and construct a parameter association network of the set of monitoring points to be analyzed using the monitoring points in the set of monitoring points to be analyzed as nodes and the parameter influence coefficient as weights connecting the nodes; Determining a core path of the parameter association network, and determining a priority ranking of each monitoring point in the set of monitoring points to be analyzed based on the core path; The data of each monitoring point in the set of monitoring points to be analyzed are processed in sequence according to the priority order to achieve adaptive setting of abnormal warning thresholds.

2. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1, characterized in that: Determining the real-time operating status of the target water pump according to the operating parameters includes: Calculating, based on the operating parameters, an efficiency benchmark value of the target water pump over multiple historical cycles; According to the fluctuation range of the operating parameters corresponding to each efficiency benchmark value, the calculated efficiency benchmark values ​​are grouped to form one or more efficiency status groups; A target efficiency state group that matches the current operating parameters of the target water pump is determined in the efficiency state group, and a state identifier corresponding to the target efficiency state group is used as the real-time operating state of the target water pump.

3. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 2, characterized in that: According to the fluctuation range of the operating parameters corresponding to each efficiency benchmark value, the calculated efficiency benchmark values ​​are grouped as follows: Obtaining a preset parameter fluctuation range in the water pump monitoring system; For any calculated efficiency reference value, the parameter fluctuation interval to which the operating parameter fluctuation range corresponding to the efficiency reference value belongs is identified, and the efficiency reference value is divided into the efficiency state group corresponding to the identified parameter fluctuation interval.

4. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1, characterized in that: Based on the real-time operating status, the operating parameter collection points are divided into efficiency-dominant collection points and efficiency-secondary collection points, including: Determine the key influencing parameters and non-key influencing parameters corresponding to the real-time operating status; Determining a first monitoring range of the key influencing parameter at the operating parameter collection point, and determining a second monitoring range of the non-key influencing parameter at the operating parameter collection point; The operating parameter collection points covered by the first monitoring range are determined as efficiency-dominant collection points, and the operating parameter collection points covered by the second monitoring range are determined as efficiency-secondary collection points.

5. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1, characterized in that: Determining the environmental interference monitoring point among the auxiliary monitoring points other than the operating parameter collection point includes: Setting a first influence radius for an efficiency-dominant collection point among the operating parameter collection points, and setting a second influence radius for an efficiency-secondary collection point among the operating parameter collection points; For auxiliary monitoring points other than the operating parameter collection points, if the distance to the efficiency dominant collection point is within the first influence radius, the auxiliary monitoring point is selected as the environmental interference monitoring point; if the distance to the efficiency secondary collection point is within the second influence radius, the auxiliary monitoring point is selected as the environmental interference monitoring point.

6. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1, characterized in that: Determining the parameter influence coefficient between any two associated monitoring points in the set of monitoring points to be analyzed includes: For a first monitoring point and a second monitoring point associated with the set of monitoring points to be analyzed, identifying a parameter type of each of the first monitoring point and the second monitoring point, wherein the parameter type includes one of an efficiency dominant parameter, an efficiency secondary parameter, and an environmental interference parameter; determining a first influence weight of the first monitoring point and a second influence weight of the second monitoring point according to the identified parameter type; The correlation between the first impact weight and the historical data of the second monitoring point is calculated, and the parameter impact coefficient between the first monitoring point and the second monitoring point is determined according to the correlation.

7. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 6, characterized in that: Determining the parameter influence coefficient between the first monitoring point and the second monitoring point according to the correlation includes: Collecting historical operating data of each monitoring point in the set of monitoring points to be analyzed, and determining the fluctuation variance of the collected historical operating data; Dividing the volatility variance into multiple correlation levels, and determining a target correlation level for the calculated first impact weight and historical data correlation; A preset coefficient value corresponding to the target correlation level is determined as a parameter influence coefficient between the first monitoring point and the second monitoring point.

8. The method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1 is characterized in that: Processing the data of each monitoring point in the set of monitoring points to be analyzed in sequence according to the priority order to achieve adaptive setting of abnormal warning thresholds includes: Extracting real-time parameter data of each monitoring point in the priority sorting, and constructing a time series feature sequence based on the extracted real-time parameter data, wherein the arrangement order of each feature in the time series feature sequence is consistent with the priority sorting; Inputting the time series feature sequence into an adaptive threshold model to generate an abnormal warning threshold for each of the monitoring points through the adaptive threshold model; The corresponding monitoring points are monitored according to the generated abnormal warning thresholds to achieve abnormal warning.

9. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 1, characterized in that: The method further comprises: After the abnormal warning threshold is set, continuously monitoring the parameter change rate of each monitoring point in the set of monitoring points to be analyzed; When the parameter change rate exceeds a preset fluctuation threshold for multiple consecutive periods, the step of determining the core path of the parameter association network is re-executed, and the priority sorting is adjusted according to the new core path.

10. A method for adaptively setting a water pump operating efficiency monitoring and abnormal warning threshold according to claim 4, characterized in that: Determining the key influencing parameters and non-key influencing parameters corresponding to the real-time operating status includes: Obtaining a design parameter table of the target water pump, wherein the design parameter table includes rated flow, rated head, and rated power; Comparing the actual operating parameters in the real-time operating state with the rated parameters in the design parameter table to calculate the parameter deviation percentage; The operating parameters whose parameter deviation percentage is greater than the preset deviation threshold are determined as key influencing parameters, and the operating parameters whose parameter deviation percentage is less than or equal to the preset deviation threshold are determined as non-key influencing parameters.

Images