Multi-pump collaborative variable-frequency energy-saving water supply equipment and control method

Abstract

The invention discloses multi-pump collaborative variable-frequency energy-saving water supply equipment and a control method, belongs to the technical field of intelligent control of water supply equipment, and aims to solve the problems of high energy consumption and poor adaptability of traditional water supply equipment. The method comprises the following steps: collecting water consumption data, extracting features through a sliding window, screening parameters through principal component analysis to construct a feature parameter set, dividing feature clustering groups in combination with time attribute clustering, and associating water consumption time periods and demand intensity grades to construct a typical water consumption mode; according to the water pump performance curve and the attenuation index, constructing an updated dynamic capability matrix; matching a target water consumption mode, screening water pumps to construct an execution pump set, decomposing a flow demand and distributing a load to generate a regulation and control instruction; and executing the instruction and counting the deviation accumulated duration, and judging whether to update the instruction. Dynamic adaptation of the water pump set and the water demand is achieved, and the water supply stability and the energy saving performance are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control of water supply equipment, and more particularly to a multi-pump cooperative variable frequency energy-saving water supply equipment and a control method. BACKGROUND

[0002] In the modern water supply field, in order to meet the water demand of different scales, multi-pump combination operation has become the mainstream configuration. However, the current water supply system still faces a series of problems to be solved in actual operation.

[0003] From the water consumption end, the water consumption is not constant, but is affected by many factors such as seasonal change, daily work and rest, sudden activity, and shows a complex fluctuation state. This fluctuation includes not only the water consumption difference in fixed time period every day, but also the periodic change every week and every month, and occasionally irregular sudden water consumption increase. When dealing with these changes, the existing water supply scheme often appears to be not flexible enough, and it is difficult to accurately predict the water consumption trend, resulting in that the water supply state is often out of touch with the actual demand, or the water supply quantity exceeds the actual need causing waste, or the water supply quantity is insufficient affecting normal water consumption. In terms of equipment operation, as the core component of the water supply system, the performance of the water pump will gradually change with the increase of the use time and the change of the running environment. For example, long-term high-load operation will aggravate mechanical wear, and water temperature changes in different seasons may affect the efficiency of the water pump, and frequent start-stop operation will also cause equipment performance degradation. However, the current management and control mode mostly relies on the performance parameters of the water pump when it leaves the factory, and lacks dynamic evaluation of the real-time state of the equipment, so that the running parameter setting of the water pump does not match the actual performance, which not only reduces the water supply efficiency, but also shortens the service life of the equipment and increases the operation cost. At the system control level, how to reasonably allocate the running state of multiple water pumps is the key to guarantee the efficient operation of the water supply system. The existing mode often adopts a relatively fixed mode in the selection of water pumps and the distribution of loads, and it is difficult to flexibly adjust according to the real-time water consumption and equipment state. At the same time, for the running instructions already issued, there is a lack of effective tracking and evaluation mechanism, and the deviation between the instructions and the actual demand cannot be found and corrected in time, which makes it difficult for the water supply system to maintain stable and efficient operation state when facing complex and changeable conditions. Therefore, in order to overcome these limitations, the present application provides a multi-pump cooperative variable frequency energy-saving water supply equipment and a control method. SUMMARY

[0004] In view of the deficiencies in the prior art, the purpose of the present application is to provide a multi-pump cooperative variable frequency energy-saving water supply equipment and a control method, which solves the problem of how to realize accurate adaptation of the water supply equipment to the dynamically changing water demand, and at the same time guarantees the long-term stable and efficient operation of the water supply system in the case of equipment performance degradation with running.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0006] The control method of the multi-pump cooperative variable frequency energy-saving water supply equipment comprises the following steps:

[0007] Collect water consumption data, extract water consumption features of the water consumption data through a sliding window, perform principal component analysis on quantitative indexes of the water consumption features, screen feature parameters to construct a feature parameter set, cluster feature clusters based on time interval attributes of the feature parameter set, and associate with water consumption periods and demand intensity levels to construct typical water consumption modes;

[0008] According to the performance curves and performance attenuation quantitative indexes of each water pump of the water pump group of the water supply equipment, a dynamic capability matrix of each water pump is constructed and updated;

[0009] According to real-time water consumption data, water consumption features are extracted for similarity matching of typical water consumption modes, positioning of a target water consumption mode, screening of target water pumps in the water pump group for water supply in combination with the dynamic capability matrix of the water pump, construction of an execution pump group, decomposition of flow demand of the target water consumption mode into basic load and dynamic adjustment load, load distribution, and generation of control instructions of the water pump group;

[0010] The control instructions are executed, and the deviation cumulative duration of the target water consumption mode, the dynamic capability matrix, and the load distribution is counted to determine whether to trigger water pump group control instruction updating.

[0011] Specifically, the specific steps of clustering and dividing the feature cluster group include:

[0012] Collect water consumption data, and based on the collection time stamp of the water consumption data, perform alignment processing on the water consumption data through a time synchronization mechanism to construct a basic water consumption data set;

[0013] Set a sliding window, and based on the basic water consumption data set, extract water consumption features of the water consumption data in the sliding window; the water consumption features include trend features, periodic features, and random features;

[0014] The trend features are used to reflect the change rule features of the water consumption data within the time range of the sliding window; the periodic features are used to reflect the regular fluctuation features of the water consumption data within a fixed period; and the random features are used to capture irregular water consumption change features caused by sudden water consumption;

[0015] According to the time stamp of the sliding window, the water consumption features are marked with time interval attributes, which refer to time range information corresponding to the sliding window, including a start time and an end time;

[0016] For the extracted water consumption features, perform principal component analysis on the quantitative indexes contained therein, configure parameter filtering thresholds, screen feature parameters, classify and integrate the feature parameters according to feature types, and form a feature parameter set;

[0017] Based on the feature parameter set, a clustering algorithm is used to cluster and analyze the feature parameters of different time interval attributes, and the feature clustering groups are divided.

[0018] Specifically, the specific steps of constructing the typical water use mode include:

[0019] The time interval clustering parameters are configured, and the time interval clustering algorithm is used to divide the water use period, which is used to clarify the distribution range of different feature clustering groups in the time dimension;

[0020] The demand intensity related parameters are configured, and the corresponding demand intensity level is divided for each feature clustering group, which is used to quantify the urgency and scale of the water demand represented by different feature clustering groups;

[0021] The feature clustering groups are associated and integrated with the divided water use period and the divided demand intensity level to form a typical water use mode.

[0022] Specifically, the dynamic capability matrix is a two-dimensional structured data table, the horizontal dimension is the running frequency interval division, and the vertical dimension is the core parameter category representing the performance of the water pump, including the basic performance parameter and the state correction parameter. The basic performance parameter is used to reflect the inherent performance characteristics of the water pump at different running frequencies, and embodies the basic running capability of the water pump under standard conditions; the state correction parameter is used to reflect the performance deviation and boundary change of the water pump in the actual running process, and reflects the dynamic characteristics of the water pump performance with the change of running conditions.

[0023] Specifically, the specific steps of constructing and updating the dynamic capability matrix of each water pump include:

[0024] Based on the factory rated performance curve of the water pump, the key performance parameters of the water pump are discretized according to the preset frequency interval, the key performance parameter values at the end points of each frequency interval are recorded as the basic performance parameter values, and the state correction parameters of each type are initialized and set according to the factory performance of the water pump, to construct an initial dynamic capability matrix;

[0025] An off-line full working condition test platform is built to carry out off-line full working condition test, and the basic performance parameter data under different running frequencies are collected, which are used to correct the basic performance parameter values of the initial dynamic capability matrix through data calibration algorithm;

[0026] In the running stage, real-time running data of the water pump are collected and current typical water use mode data are extracted as correction data to construct a correction data set;

[0027] Based on the correction data set, the deviation analysis algorithm is used to calculate the basic performance parameter deviation value, which is mapped to the corresponding dimension of the basic performance parameter in proportion for point-by-point correction, and the basic performance parameter is dynamically updated;

[0028] A multi-factor coupled performance degradation quantification model is constructed to calculate mechanical loss amount, efficiency degradation correction value and load fluctuation influence factor, and update state correction parameters.

[0029] Specifically, the specific steps of positioning the target water mode include:

[0030] Real-time water consumption data of the current pipe network is collected, and real-time water consumption features are extracted for quantitative processing. The real-time water consumption features are converted into real-time feature parameter sets consistent with the structure of the feature parameter sets in the typical water consumption modes through a standardization parameter conversion algorithm.

[0031] The cosine similarity of the real-time feature parameter set and the feature parameter sets in each typical water consumption mode is calculated, a similarity threshold is set, and the cosine similarity of the real-time feature parameter set and the feature parameter sets in each typical water consumption mode is compared with the similarity threshold. The typical water consumption mode with a cosine similarity greater than the similarity threshold is marked as a potential target water consumption mode.

[0032] If the number of potential target water consumption modes is greater than 1, the time matching degree of each potential target water consumption mode and the current actual time is calculated, and the potential target water consumption mode is selected as the target water consumption mode according to the time matching degree.

[0033] If the number of potential target water consumption modes is 1, the potential target water consumption mode is taken as the target water consumption mode.

[0034] If the number of potential target water consumption modes is less than 1, a reference mode is selected according to the cosine similarity, and a temporary water consumption mode is generated using a linear interpolation algorithm as the target water consumption mode.

[0035] Specifically, the specific steps of constructing the candidate pump group include:

[0036] The target water consumption mode is obtained, and the feature parameter set, time interval attribute and demand intensity level are extracted.

[0037] The dynamic capability matrix of each water pump of the water pump group is called, and the basic performance parameters and state correction parameters of each water pump are extracted to construct a water pump performance parameter library.

[0038] Based on the water pump performance parameter library, a correspondence matrix of the target water consumption mode and the water pump operating state is constructed to establish a quantitative association framework between water consumption demand and water pump performance. The deviation rate of the correspondence matrix is calculated, and a dynamic weight is set in combination with the demand intensity level. The initial water pump adaptation score is calculated by weighted summation, and the water pump adaptation score of each water pump is obtained by correction according to the state correction parameters of each water pump.

[0039] According to the flow demand value of the target water mode and the rated flow of the water pump, the target number of required water pumps is calculated; all water pumps are sorted in descending order based on the water pump adaptation degree score, and the initial candidate pump group is constructed by selecting water pumps based on the target number;

[0040] The performance of the initial candidate pump group is verified, and in response to not passing the performance verification, the number of water pumps of the candidate pump group is increased according to the adaptation degree score to construct an execution pump group.

[0041] Specifically, the specific steps of generating the control instruction of the water pump group include:

[0042] Obtain the candidate pump group and the target water mode, and decompose the flow demand value of the target water mode to divide the basic load and the dynamic adjustment load;

[0043] Based on the dynamic capability matrix of each water pump in the candidate pump group, the target operating frequency interval of each water pump is determined;

[0044] According to the target operating frequency interval and the rated flow ratio of each water pump, the basic load component that each water pump needs to bear is calculated, and the target operating frequency required by each basic load component is determined;

[0045] If the target operating frequency of the water pump is within its target operating frequency interval, it is marked as a basic load bearing pump, and the basic load is allocated to it according to the calculated target operating frequency; if the target operating frequency of the water pump exceeds its target operating frequency interval, the allocation ratio of the basic load component is adjusted again, and the target operating frequency of the water pump is updated;

[0046] The state correction parameter in the dynamic capability matrix of the water pump is standardized, the dynamic adjustment adaptation index is calculated, the number of dynamic adjustment load bearing pumps is set, the dynamic adjustment load bearing pumps are selected and marked according to the dynamic adjustment adaptation index, and the frequency adjustment interval of each dynamic adjustment load bearing pump is determined;

[0047] According to the fluctuation amplitude and frequency of the flow in the real-time water data, the dynamic adjustment load is allocated to each dynamic adjustment load bearing pump according to the dynamic adjustment adaptation index proportion;

[0048] According to the allocation results of the basic load and the dynamic adjustment load, the control instruction of the water pump group is generated, and the control instruction includes the water pump start-stop instruction, the basic operating frequency instruction, and the dynamic adjustment parameter instruction.

[0049] Specifically, the specific steps of determining whether to trigger the water pump group control instruction update include:

[0050] The extracted water feature updates the real-time feature parameter set, and similarity measurement is performed with the current target water mode feature parameter set, a mode matching degree is calculated, a similarity judgment threshold is set, a mode deviation cumulative duration when the mode matching degree is less than the similarity judgment threshold is counted, and if the mode deviation cumulative duration is greater than a preset mode deviation duration, a water pump group regulation instruction update is triggered;

[0051] The water pump operation state parameters are compared with the corresponding parameters in the dynamic capability matrix, a parameter deviation rate is calculated, and if the parameter deviation rate is greater than a preset parameter deviation threshold, the parameter deviation cumulative duration is greater than a preset parameter deviation duration, a water pump group regulation instruction update is triggered;

[0052] For the basic load bearing pump, the load deviation cumulative duration when the actual operation frequency deviates from the target operation frequency interval is monitored, and if the load deviation cumulative duration is greater than a preset load deviation duration, a water pump group regulation instruction update is triggered;

[0053] For the dynamic load bearing pump, the adjustment deviation cumulative duration when the actual adjustment amount deviates from the load tolerance range adjustment amount is monitored, and if the adjustment deviation cumulative duration is greater than a preset adjustment deviation duration, a water pump group regulation instruction update is triggered.

[0054] The multi-pump cooperative variable frequency energy-saving water supply equipment comprises a sensor sensing network, a data processing module, a control module and an instruction update judgment module.

[0055] The sensor sensing network is used for collecting water use data and water pump operation data at key nodes of the pipe network; the data processing module is used for constructing typical water use modes and a dynamic capability matrix; the control module is used for positioning a target water use mode, screening water pumps and generating regulation instructions; and the instruction update judgment module is used for monitoring data and comprehensively judging whether to update the regulation instructions.

[0056] The application has the following advantages:

[0057] The application can accurately capture the trend, cycle and random characteristics of water use demand by constructing typical water use modes, and can make the water supply scheme more suitable for actual water use changes by combining time intervals and demand intensity levels, so as to avoid waste or deficiency caused by disconnection between water supply and demand; the construction and update of the dynamic capability matrix can reflect changes in water pumps caused by performance degradation and the like in real time, so that the water pump operation parameter setting is consistent with the actual performance, the water supply efficiency is improved, and the equipment life is prolonged; the target water use mode is positioned by similarity matching, the water pumps are screened by combining the dynamic capability matrix, the regulation instructions are generated by distributing loads, and the operation state of the water pump group is flexibly adjusted; and the deviation cumulative duration is counted and the instruction update judgment mechanism can timely correct the instruction deviation, so that the water supply system can maintain stable and efficient operation under complex conditions, and the adaptability, energy saving and reliability of the water supply system are improved as a whole. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 Flow chart for the control method of the multi-pump cooperative variable frequency energy-saving water supply device of the present application;

[0059] Figure 2 Flow chart for the cluster division feature cluster group of the present application;

[0060] Figure 3 Flow chart for the dynamic capability matrix construction of the present application;

[0061] Figure 4 Flow chart for the positioning target water mode of the present application;

[0062] Figure 5 Flow chart for the construction of the pump group of the present application. DETAILED DESCRIPTION

[0063] Please refer to Figure 1 The embodiment introduces the control method of the multi-pump cooperative variable frequency energy-saving water supply device, which includes:

[0064] Step S1: Deploy a sensor perception network at key nodes of the pipeline network, collect water use data including pressure, flow, etc. through the sensor perception network, construct a basic water use data set through time synchronization processing, set a sliding window and use the time series analysis algorithm to extract water use characteristics, and mark its time interval attributes; then use principal component analysis to screen key feature parameters to form a feature parameter set, based on this clustering to divide feature cluster groups, combine periodic characteristics and feature cluster group time interval attributes to divide water use time periods, and define demand intensity levels based on feature parameters and other indicators. Finally, associate and integrate the feature cluster groups with water use time periods and demand intensity levels to form a typical water use pattern that can provide a standardized reference for water pump group control. Specifically, pressure transmitters, electromagnetic flowmeters and smart water meters are installed at the risers, branch nodes and user terminals at the end of the pipeline network to form a sensor perception network, which collects water use data such as pressure, flow, water use duration and water use start and end time in real time. The water use data are correlated and integrated according to the timestamps at the time of collection to form a basic water use data set with time series tags; using the time series analysis algorithm, the flow data in the basic water use data set is calculated using a sliding window for multiple consecutive days to obtain trend characteristics reflecting long-term change trends; at the same time, spectrum analysis is performed on daily and weekly flow fluctuations to extract periodic characteristics that reflect periodic laws, and statistical identification is performed on flow anomalies that deviate from the periodic trend to obtain identification bursts. Random characteristics of water use; then a clustering algorithm is used to analyze the three types of water use characteristics extracted, and the key quantitative indicators in trend characteristics, periodic characteristics, and random characteristics are screened to form a characteristic parameter set. Combined with the statistical laws of water use start and end time, the time interval clustering is used to determine the peak, flat, and valley period boundaries to construct a time distribution model. According to the flow peak value and pressure fluctuation range in the characteristic parameter set and combined with the pipeline design standards, the demand intensity level is defined, and finally a typical water use pattern containing these three parts is generated, thereby converting the scattered water use data into a structured demand template, providing a standardized reference for the subsequent water pump group to match the control strategy according to the real-time water use status, and realizing dynamic adaptation of water pump operation and water demand.

[0065] In this embodiment, by constructing a perception network covering the entire pipe network and a systematic data analysis process, the accurate transformation of water demand from raw data to structured mode is realized. On the one hand, the multi-dimensional water use data collected in real time is associated through a time synchronization mechanism to form a complete and time clear basic data set, providing high-quality data support for subsequent analysis; on the other hand, by setting a sliding window and using a time series analysis algorithm to extract three types of water use features, the change rule, periodic rule and burst characteristics of water demand are fully captured, and the typical water use mode generated through clustering and other steps is presented in a structured form of feature parameter set, time distribution model and demand intensity level, which intuitively presents the water use rule and demand magnitude in different scenarios. This transformation makes the originally scattered water use data become a standardized template with clear guiding significance, not only providing a direct reference demand benchmark for subsequent water pump group regulation, but also ensuring that the water pump operation state can respond accurately to the dynamic changes of water demand through the deep integration of time interval attributes, laying a key foundation for the stable operation and energy saving optimization of the water supply system.

[0066] Please refer to Figure 2 , preferably, the specific steps of clustering and dividing the feature cluster group include:

[0067] Through the sensor perception network, water use data is collected in real time, including pressure data, flow data, water use duration data and water use start and end time data. Based on the collection time stamp of the water use data, the water use data is aligned through a time synchronization mechanism to build a basic water use data set, providing continuous and reliable raw data support for subsequent feature extraction.

[0068] A sliding window is set, and based on the basic water use data set, a time series analysis algorithm is used to extract water use features from the water use data in the sliding window. The water use features include trend features, periodic features and random features. Trend features are used to reflect the change rule characteristics of water use data within the time range of the sliding window; periodic features are used to reflect the regular fluctuation characteristics of water use data within a fixed period; random features are used to capture the irregular water use change characteristics caused by sudden water use;

[0069] According to the time stamp of the sliding window, the extracted water use features are marked with time interval attributes. Time interval attributes refer to the time range information corresponding to the sliding window, including the start time and end time, which are used to establish a clear association between the extracted water use features and the actual time dimension, so that the feature data can be corresponded to a specific period, providing a time sequence reference for subsequent steps such as feature clustering and time distribution model construction according to the time dimension;

[0070] For the extracted water feature, principal component analysis is performed on the quantitative indicators contained therein, parameter threshold is configured, redundant parameters are removed, and feature parameters that can significantly reflect the original properties of water demand are selected. The feature parameters are classified and integrated according to the feature types to form a feature parameter set. The numerical values of the feature parameter set are directly derived from the quantitative results of the basic water data set after feature extraction, objectively reflect the essential properties of water demand, and include flow demand values and pressure demand values;

[0071] Based on the generated feature parameter set, a clustering algorithm is used to perform clustering analysis on the feature parameters with different time interval attributes. The clustering number and similarity threshold are configured, and the feature clustering groups are divided according to the similarity of the feature parameters, the correlation of the time interval attributes, and the consistency of the water features. Water features with similar feature parameters, similar time distribution rules, and matching demand intensity levels are classified into the same category to form several feature clustering groups. Each clustering group represents a feature set with similar water rules, providing a clustering basis for the generation of typical water patterns.

[0072] Based on the division of the cycle period in the cycle feature, combined with the time interval attributes corresponding to the feature clustering groups, time interval clustering parameters are configured, and a time interval clustering algorithm is used to divide the water period. This is used to determine the distribution range of different feature clustering groups in the time dimension, so that each feature clustering group can correspond to a specific water period, providing a time dimension division basis for the subsequent integration to form a typical water pattern.

[0073] According to the core indicators such as flow demand values and pressure demand values in the feature parameter set, combined with the feature parameter performance of the feature clustering groups, demand intensity related parameters are configured to determine the corresponding demand intensity level for each feature clustering group. This is used to quantify the urgency and scale of water demand represented by different feature clustering groups, so that the feature clustering groups have more explicit demand attributes.

[0074] The feature clustering groups are associated and integrated with the divided water periods and the determined demand intensity levels, so that each feature clustering group corresponds to a specific water period and demand intensity level, forming a complete typical water pattern. This integration organically combines the feature parameter set, time interval attributes, and demand intensity levels, and completely reflects the water rules in different scenarios, providing a standardized reference template for subsequent pump groups to match and control strategies according to real-time water conditions.

[0075] Step S2: Obtain the water pump set configured by the water supply equipment, discretize the key parameters based on the performance curve of each water pump out of the factory, and construct a dynamic capability matrix framework containing basic performance parameters and state correction parameters; calibrate the data collected through offline full-condition testing, and construct a dynamic capability matrix; after the equipment is running, integrate real-time data and typical water use mode information to form a correction data set, update the basic performance parameters and determine the state correction parameters, and finally construct a dynamic capability matrix that can reflect the actual performance of the water pump in real time. Specifically, the dynamic capability matrix is a two-dimensional structured data table, the horizontal dimension is the division of the running frequency interval, the vertical dimension is the core parameter category representing the performance of the water pump, and it contains two levels of basic performance parameters and state correction parameters. The basic performance parameters are used to reflect the inherent performance characteristics of the water pump under different running frequencies, including core indicators such as rated flow, rated head, and running efficiency, which reflect the basic running capability of the water pump under standard conditions; the state correction parameters are used to reflect the performance deviation and boundary changes of the water pump caused by factors such as mechanical loss, running time, and load fluctuation during actual operation, including indicators such as response speed attenuation, load tolerance range adjustment, and health state quantification, which reflect the dynamic characteristics of the water pump performance changes with running conditions. The two together constitute a structured parameter set that can reflect the performance and change law of the water pump under different running conditions in real time, and provide accurate quantitative basis for the collaborative control of the water pump set. When constructing, first discretize the benchmark value according to the rated performance curve of the water pump out of the factory to form an initial matrix framework, and then complete the initial construction by calibrating the benchmark value through offline full-condition testing data collection; during the equipment running stage, combined with the real-time running data collected by the sensor and the load characteristics of the typical water use mode, the performance attenuation algorithm is used to dynamically correct the matrix parameters, so that the two together constitute a structured parameter set that can reflect the performance and change law of the water pump in real time, and provide accurate quantitative basis for the collaborative control of the water pump set.

[0076] In this embodiment, through the technical path combining full-condition testing and real-time correction, the performance of the water pump from static benchmark to dynamic change is fully described. The initial matrix constructed based on the factory parameters and offline testing provides a standardized quantitative benchmark, combined with real-time monitoring data and dynamic correction of the performance attenuation algorithm, which can accurately capture the performance deviation of the water pump during operation, and ensure that the parameter set is consistent with the actual state in real time. This structured dynamic capability matrix clearly presents the core performance and state boundary under different running conditions, providing a directly callable quantitative basis for load distribution of the water pump set, and through the dynamic update of the state correction parameters, the collaborative control strategy adapts to the performance attenuation process of the water pump, laying a core technical support for long-term stable and energy-saving operation of the water supply system.

[0077] Please refer to Figure 3 , preferably, the specific steps of constructing the dynamic capability matrix include:

[0078] Based on the factory rated performance curve of the water pump, the key performance parameters such as rated flow, rated head, and operating efficiency are discretized at preset frequency intervals, and the performance parameter values corresponding to the end points of each frequency interval are recorded as the basic performance parameter values. At the same time, according to the mechanical performance parameters, design service life, and load tolerance threshold under standard working conditions of the water pump at the time of factory delivery, and according to the optimal operating state and rated load characteristics of the water pump without performance degradation, the initial reference values of various state correction parameters are determined, and the state correction parameters are initialized based on this, to construct the initial dynamic capability matrix.

[0079] A test platform covering different flow, head, and pressure working conditions is built to carry out offline full-condition testing to simulate the working state of the water pump under various possible operating scenarios. For each water pump, the basic performance parameter data is collected at different operating frequencies, and the measured data is compared and corrected with the discretized reference values of the basic performance parameters in the initial framework through data calibration algorithms such as least squares method, overcoming the defect that the static parameters in the prior art are difficult to match the actual working conditions, and completing the initial construction of the dynamic capability matrix.

[0080] When the device enters the actual running stage, the sensors installed at the inlet and outlet of the water pump, the motor, and other parts are used to collect the operating data of the water pump in real time, including actual flow, pressure, operating frequency, motor current, and operating time length; at the same time, the correction data such as the feature parameter set corresponding to the current period, time interval attribute, and demand intensity level are extracted from the current typical water use mode, and the correction data are associated and integrated to form a correction data set for correction calculation.

[0081] Based on the correction data set, the deviation analysis algorithm is used to calculate the deviation value of the actual operating data and the corresponding basic performance parameters in the initial dynamic capability matrix, and the deviation value is mapped to the corresponding dimension of the basic performance parameter in proportion, and the discretized reference values of the flow, head, and efficiency parameters are corrected point by point. At the same time, the sliding window algorithm is used to smooth the deviation trend of continuous multiple periods, and the deviation interference caused by instantaneous abnormal fluctuations is eliminated, to dynamically update the basic performance parameters in the dynamic capability matrix, overcoming the defect of parameter fixation in the prior art;

[0082] Meanwhile, a multi-factor coupled performance degradation quantification model is constructed, taking the running frequency, flow deviation value and running time length as input parameters, calculating the mechanical loss amount per unit time through a preset loss coefficient formula, quantifying the performance degradation caused by mechanical wear; according to the interval corresponding to the degradation coefficient table divided by the running time length, the degradation coefficient matched with the current running time length is determined, multiplied by the efficiency parameter in the basic performance parameter to obtain the efficiency degradation correction value, reflecting the cumulative influence of the running time length on the efficiency; combined with the deviation amplitude of the actual flow and the characteristic parameter set flow reference value and the demand intensity level, the load fluctuation influence factor is calculated by weighting according to the weight corresponding to the demand intensity level, which is used for dynamically adjusting the load tolerance range parameter.

[0083] According to the mechanical loss amount, efficiency degradation correction value and load fluctuation influence factor calculated above, the state correction parameters of various types in the dynamic capability matrix are updated respectively, so that the dynamic updating of the state correction parameters and the basic performance parameters forms a coordinated linkage. For example, when it is detected that the flow continuously exceeds the normal range and the running frequency is high, combined with the demand intensity level of the corresponding period, the specific value of the state correction parameter is derived through the performance degradation quantification model and filled into the matrix, realizing the real-time and accurate mapping of the dynamic capability matrix to the actual running state of the water pump, solving the problem that the existing technology cannot dynamically adapt to the change of equipment performance, and improving the support accuracy of the matrix for water pump operation regulation.

[0084] Step S3: extracting water use features according to real-time water use data, for similarity matching of typical water use modes, positioning the target water use mode, and screening the target water pump for water supply in the water pump group in combination with the dynamic capability matrix of the water pump, constructing an execution pump group, and dividing the flow demand of the target water use mode into basic load and dynamic adjustment load for load distribution, generating the regulation instruction of the water pump group. Specifically, similarity matching refers to the process of determining the typical water use mode corresponding to the current water use state by calculating the similarity of the real-time water use features and the feature parameter set in the typical water use mode, and using the cosine similarity algorithm to quantify the similarity between the current water use state and each typical water use mode; the target water use mode refers to the typical water use mode with the highest similarity to the real-time water use features, which is used as the demand reference for current water supply regulation; the execution pump group refers to a set of several water pumps selected from the water pump group, which have the ability to meet the current water demand and have the optimal energy consumption; the basic load refers to the relatively stable flow demand part in the target water use mode, which is borne by the fixed water pump in the execution pump group; the dynamic adjustment load refers to the flow demand part that changes with the real-time water use fluctuation, which is dynamically borne by the adjustable water pump in the execution pump group according to the actual situation.

[0085] In this embodiment, by dynamically matching real-time water use characteristics with typical water use patterns, combined with water pump performance state screening to perform pump group and optimize load distribution, the precise adaptation of water demand and water pump operation is realized. On the one hand, the similarity matching mechanism can quickly locate the target water use pattern, providing a clear demand benchmark for regulation and control, and when no match is found, an interim water use pattern can be generated through interpolation algorithm to ensure the continuity of regulation and control; on the other hand, the water pump screening and load decomposition strategy based on dynamic capability matrix can flexibly determine the number of target water pumps according to the demand size, and through reasonable allocation of basic load and dynamic adjustment load, the water pump can run in the high efficiency interval, maximizing energy saving, providing support for energy saving and stable operation of the water supply system.

[0086] Please refer to Figure 4 , preferably, the specific steps of locating the target water use pattern include:

[0087] The current water use data of the pipe network is collected in real time by sensors, including real-time pressure value, real-time flow value, real-time water use time and real-time water use start and end time, etc. These data will be used as the basis for extracting real-time water use characteristics.

[0088] Based on the collected real-time water use data, set a sliding window with the same window size as when constructing the typical water use pattern in step S1, and use time series analysis algorithm to process the real-time water use data in the sliding window to extract real-time water use characteristics, including real-time trend characteristics, real-time periodic characteristics and real-time random characteristics.

[0089] Quantitative processing of the extracted real-time water use characteristics, converting the real-time water use characteristics into real-time feature parameter set consistent with the structure of the feature parameter set in the typical water use pattern through standardization parameter conversion algorithm. The standardization parameter conversion algorithm refers to an algorithm that normalizes the numerical range and dimension division of real-time water use characteristics according to the parameter type, dimension definition and quantization scale of the feature parameter set in the typical water use pattern, ensuring that the two are completely matched in parameter structure and quantization standard, providing the basis for direct comparison.

[0090] Calculate the cosine similarity of the real-time feature parameter set and the feature parameter set in each typical water use pattern. Cosine similarity refers to measuring the similarity of two vectors by calculating the cosine of the angle between them, with a value range of [-1, 1], and the closer the value is to 1, the higher the similarity.

[0091] Set the similarity threshold, which is the critical value for determining whether the real-time water use characteristics match the typical water use pattern, and set it according to the stability requirements of the water supply system and historical matching data.

[0092] The cosine similarity of the real-time feature parameter set and the feature parameter set in each typical water use mode is compared with the similarity threshold value, and the typical water use mode with a cosine similarity greater than the similarity threshold value is marked as a potential target water use mode.

[0093] If the number of potential target water use modes is greater than 1, the time matching degree of each potential target water use mode and the current actual time is calculated, the time matching degree refers to the degree of coincidence between the time interval attribute of the potential target water use mode and the current actual time, and the value range is between [0, 1], the value closer to 1 indicates a higher time matching degree, and the potential target water use mode with the highest time matching degree is selected as the final target water use mode.

[0094] If the number of potential target water use modes is equal to 1, the potential target water use mode is directly determined as the final target water use mode.

[0095] If the number of potential target water use modes is less than 1, the two typical water use modes with the highest cosine similarity are selected as reference modes, a temporary water use mode is generated by using a linear interpolation algorithm, the linear interpolation algorithm refers to a method of connecting two known data points by a straight line to calculate the value of the intermediate point, in this case, the corresponding parameters of the temporary water use mode are calculated according to the feature parameter set, time interval attribute and demand intensity level of the two reference modes, and the temporary water use mode is determined as the final target water use mode.

[0096] Please refer to Figure 5 , preferably, the specific steps of constructing the pump group include:

[0097] The target water use mode obtained by positioning is acquired, and the feature parameter set, time interval attribute and demand intensity level thereof are extracted, the feature parameter set including flow demand value and pressure demand value.

[0098] The dynamic capability matrix of each water pump of the water pump group is called, and the basic performance parameters and state correction parameters of each water pump are extracted therefrom, the basic performance parameters including rated flow, rated head and operating efficiency under different operating frequencies, the state correction parameters including response speed decay value, load tolerance range adjustment amount and health state quantitative value, forming a water pump performance parameter library.

[0099] Based on the water pump performance parameter library, a corresponding relationship matrix of the target water mode and the water pump running state is constructed. The corresponding relationship matrix refers to a two-dimensional data matrix arranged in a one-to-one correspondence relationship between the key parameters representing the water demand scale and characteristics in the target water mode and the key parameters representing the output capacity and performance level of the water pump in the high-efficiency running interval. Each element in the matrix represents a matching node of a set of demand parameters and performance parameters, and is used to establish a quantitative correlation framework between water demand and water pump performance, so that the matching degree of the two can be calculated and analyzed through the numerical relationship of the matrix elements. The deviation rate of the corresponding relationship matrix is calculated, and a dynamic weight is set in combination with the demand intensity level. The initial water pump adaptation degree score is calculated by weighted summation, and the water pump adaptation degree score of each water pump is obtained by modification according to the state correction parameters. The specific steps are as follows:

[0100] The flow demand value and the pressure demand value of the target water mode are taken as the column vectors of the matrix, and the rated flow and the rated head of a single water pump at the high-efficiency running frequency are taken as the row vectors of the matrix to form the demand-performance corresponding relationship matrix.

[0101] For each corresponding element in the corresponding relationship matrix, the flow deviation rate and the pressure deviation rate are obtained by calculating the absolute difference between the water pump parameters and the demand parameters relative to the proportion of the demand parameters. The smaller the deviation rate is, the higher the matching degree of the water pump parameters and the demand parameters is.

[0102] The weights of the flow deviation rate and the pressure deviation rate are set according to the demand intensity level of the target water mode. The demand intensity level is divided into three levels: high, medium and low. The flow deviation rate weight is higher than the pressure deviation rate weight at high demand intensity, so as to prioritize the flow matching accuracy. The pressure deviation rate weight is higher than the flow deviation rate weight at low demand intensity, so as to focus on the pressure stability. The weights of the two are balanced at medium demand intensity.

[0103] The product of the flow deviation rate and the corresponding weight, and the product of the pressure deviation rate and the corresponding weight are added, and then the sum is subtracted by 1 to obtain the basic matching score. The basic matching score has a value range of [0, 1], and the value closer to 1 indicates better basic performance matching.

[0104] The health state quantitative value in the state correction parameter is taken as the health correction coefficient, and 1 is subtracted from the response speed attenuation value to obtain the response correction coefficient. The two are multiplied to obtain the comprehensive correction coefficient, which reflects the influence of the current health status and response ability of the water pump on the adaptability.

[0105] The basic matching score is multiplied by the comprehensive correction coefficient to obtain a final water pump matching degree score, which is used to comprehensively integrate the matching degree of the water pump performance and water demand and the state of the water pump itself, to provide accurate and dynamic quantitative basis for water pump screening and sorting, and to ensure that the screened water pump can meet the current water demand and adapt to the actual running state.

[0106] According to the flow demand value of the target water mode and the rated flow of the water pump, the target number of the required water pump is calculated to ensure that the total flow output capacity of the candidate pump group is not lower than the current demand, and the number is determined by using the upward rounding method during calculation.

[0107] Based on the water pump matching degree score, all water pumps are sorted in descending order, and water pumps with high scores are preferentially selected into the candidate range. During the sorting process, for water pumps with the same score, an operation time length balancing factor is introduced to preferentially select water pumps with shorter cumulative operation time length to balance the use frequency of each water pump.

[0108] From the sorted water pumps, water pumps are selected in sequence to form an initial candidate pump group, and the number of water pumps in the initial candidate pump group is the target number calculated.

[0109] The performance of the initial candidate pump group is verified, and the verification content includes whether the total flow output range of the candidate pump group covers the flow demand value of the target water mode, whether the total head output range covers the pressure demand value of the target water mode, and whether the load tolerance range adjustment of each water pump can adapt to the load fluctuation range corresponding to the demand intensity level.

[0110] If the initial candidate pump group passes the performance verification, it is determined as the final execution pump group; if it does not pass the verification, one water pump is added, the second highest matching degree score is selected to re-establish a candidate pump group, and the performance verification is performed again, and the process is repeated until the execution pump group passes the verification.

[0111] Preferably, the specific steps of generating the control instruction of the water pump group include:

[0112] The candidate pump group and the target water mode are obtained, and the flow demand value of the target water mode is decomposed to divide the basic load and the dynamic adjustment load. The basic load is the relatively stable part of the flow demand value, and the dynamic adjustment load is the part that changes with the real-time water fluctuation. The proportion of the two is determined according to the demand intensity level, and the higher the demand intensity level, the greater the proportion of the basic load, so as to ensure the stability of water supply.

[0113] Based on the dynamic capability matrix of each water pump in the candidate pump group, the basic performance parameters of each water pump at different operating frequencies are extracted, and the target operating frequency interval of each water pump is determined. The target operating frequency interval refers to the frequency range corresponding to the high level of water pump operating efficiency, which provides energy efficiency reference for load distribution.

[0114] According to the target operation frequency interval and the rated flow ratio of each water pump, the basic load component borne by each water pump is calculated and distributed, and the target operation frequency required by each basic load component is determined according to the flow-frequency correspondence of the water pump, and then the target operation frequency is compared with the target operation frequency interval of each water pump;

[0115] If the target operation frequency of the water pump is within its target operation frequency interval, it is marked as a basic load bearing pump, and the basic load is allocated according to the calculated target operation frequency; if the target operation frequency of the water pump exceeds its target operation frequency interval, the distribution ratio of the basic load component is adjusted again, and the basic load component borne by the water pump exceeding the target operation frequency interval is reduced, and the reduced component is allocated to other water pumps with target operation frequency within the interval according to the rated flow ratio;

[0116] The state correction parameters in the dynamic capacity matrix of the water pump are standardized, the dynamic adjustment adaptation index is calculated according to the preset weight, the number of dynamic adjustment load bearing pumps is set according to the ratio of the total dynamic adjustment load to the maximum dynamic adjustment capacity of a single pump and the upward rounding rule, and the dynamic adjustment load bearing pumps are screened and marked according to the dynamic adjustment adaptation index;

[0117] The frequency adjustment interval of each dynamic adjustment load bearing pump is determined by combining the fluctuation range of the dynamic adjustment load and the load tolerance range adjustment amount of the dynamic adjustment load bearing pump, the frequency adjustment interval needs to be located within the safe operation frequency range of the water pump, and needs to be connected with the target operation frequency interval to form a continuous frequency adjustment range.

[0118] According to the fluctuation amplitude and frequency of the flow in the real-time water consumption data, the dynamic adjustment load is allocated to each dynamic adjustment load bearing pump according to the dynamic adjustment adaptation index proportion, that is, according to the proportion of the dynamic adjustment adaptation index of each dynamic adjustment load bearing pump in the total dynamic adjustment adaptation index of all dynamic adjustment load bearing pumps, the corresponding proportion of the dynamic adjustment load is allocated, and in the allocation process, it is necessary to ensure that the adjustment amount of each pump does not exceed the load tolerance range adjustment amount, and the output of the basic load bearing pump is complementary, and together meet the flow demand of the target water mode;

[0119] According to the basic load and dynamic load distribution results, the control instructions of the water pump group are generated, and the control instructions include water pump start-stop instructions, basic operation frequency instructions, and dynamic adjustment parameter instructions: the water pump start-stop instructions are instructions for specifying the water pumps in the candidate pump group that need to be started to participate in water supply, including basic load bearing pumps and dynamic adjustment load bearing pumps, which are used to control the input and idling of the water pumps, avoid invalid energy consumption, and ensure that the number of water pumps participating in water supply meets the current load demand; the basic operation frequency instructions are instructions for setting fixed operation frequency values for each basic load bearing pump, which are used to ensure that the basic load bearing pump runs in an efficient and stable state and continuously outputs the flow corresponding to the basic load; the dynamic adjustment parameter instructions are instructions for setting the upper and lower limits of the frequency adjustment, the step size of each adjustment, and the response delay time for each dynamic adjustment load bearing pump, which are used to guide the dynamic adjustment load bearing pump to flexibly adjust the operation frequency according to the real-time water fluctuation, meet the dynamic adjustment load demand, and avoid the intensification of equipment wear caused by frequent adjustment.

[0120] Step S4: In the process of implementing coordinated control according to the water pump group control instructions, the pipe network water data and the water pump operation state are continuously monitored, the real-time water features are extracted and similarity calculation is performed with the feature parameter set of the current target water mode, and the matching degree of the actual operation state parameters of each water pump in the pump group and the corresponding parameters in the dynamic capability matrix is evaluated, to comprehensively determine whether the control instructions of the water pump group need to be updated. Specifically, the pressure, flow, and other water data of the pipe network and the operation frequency, output flow, head, and other operation parameters of the water pump are collected in real time; the real-time trend, period, and random features are extracted based on the water data and converted into a real-time feature parameter set, and the cosine similarity is calculated with the feature parameter set of the current target water mode to measure the matching degree of the water demand; the actual operation parameters of the water pump are compared with the basic performance parameters and state correction parameters in the dynamic capability matrix corresponding to the frequency interval, and the deviation rate is calculated to evaluate the equipment operation adaptability; if the similarity is lower than the set threshold, the deviation rate exceeds the allowed range, or the operation frequency of the basic load bearing pump deviates from the target interval or the adjustment amount of the dynamic adjustment load bearing pump exceeds the limit, it is determined that the control instructions need to be updated, otherwise the current instructions are maintained.

[0121] In this embodiment, dynamic adaptation of the water pump group control is achieved. On the one hand, continuous monitoring of the water consumption data of the pipeline network and the operating status of the water pump ensures the immediate capture of water demand fluctuations and equipment performance changes, providing comprehensive and real-time data support for subsequent judgments; on the other hand, the matching degree of water demand is quantified by cosine similarity calculation, and the adaptability of equipment operation and dynamic capacity matrix is ​​evaluated by deviation rate. At the same time, combined with multi-dimensional indicators such as the frequency range compliance of the basic load-bearing pump and the rationality of the adjustment amount of the dynamic load-bearing pump, a scientific basis for judgment is formed. This multi-dimensional comprehensive judgment method not only avoids the unstable water supply caused by the failure to respond in time to the sudden change of water demand, but also prevents the energy efficiency reduction or increased loss caused by the deviation of equipment performance. At the same time, it reduces unnecessary instruction adjustments, while ensuring the efficient and stable operation of the water supply system, extending the service life of the equipment, and providing key closed-loop feedback support for the intelligent and refined control of the entire water supply system.

[0122] Preferably, the specific steps of determining whether to update the water pump group control instruction include:

[0123] When the water pump group control instruction is implemented, the real-time feature parameter set is updated according to the extracted water use characteristics, and the similarity is measured with the current target water use pattern feature parameter set to calculate the pattern matching degree, and the similarity judgment threshold is set according to the demand intensity level of the target water use pattern and the historical matching accuracy. During the implementation of the current water pump group control instruction, the cumulative time of the pattern deviation in which the pattern matching degree is lower than the similarity judgment threshold is counted; if the cumulative time exceeds the preset pattern deviation time, the update of the water pump group control instruction is triggered;

[0124] The water pump operating status parameters are monitored synchronously, compared with the corresponding parameters in the dynamic capacity matrix, and the parameter deviation rate is calculated. If the parameter deviation rate is greater than the preset parameter deviation threshold and the cumulative parameter deviation duration is greater than the preset parameter deviation duration, the water pump group control instruction update is triggered;

[0125] For the base load bearing pump, the accumulated load deviation duration of the actual operating frequency from the target operating frequency range is monitored. If it is greater than the preset load deviation duration, the water pump group control instruction update is triggered;

[0126] For the dynamically regulated load-bearing pump, the accumulated time of the regulation deviation of the actual regulation amount from the load tolerance range adjustment amount is monitored. If it is greater than the preset regulation deviation time, the water pump group control instruction update is triggered.

[0127] This embodiment also introduces a multi-pump coordinated variable frequency energy-saving water supply device, including: a sensor perception network, a data processing module, a control module and an instruction update determination module;

[0128] The sensor perception network is used to collect water consumption and water pump operation data at key nodes of the pipe network; the data processing module is used to construct typical water consumption patterns and dynamic capability matrices; the control module is used to locate target water consumption patterns, screen water pumps and generate control instructions; the instruction update determination module is used to monitor data and comprehensively determine whether to update the control instructions;

[0129] The sensor perception network is laid out at key nodes of the pipe network, specifically, pressure transmitters, electromagnetic flowmeters and intelligent water meters are installed at the standpipe, branch nodes and user terminals at the end of the pipe network. These devices work together to collect water consumption data and water pump operation data of the pipe network. Among them, the water consumption data covers pressure data, flow data, water consumption duration data and water consumption start and end time data; the operation data includes the actual operation frequency, actual output flow, actual lift, motor current and cumulative operation duration of the water pump.

[0130] The data processing module is connected with the sensor perception network, receives water consumption data and operation data from the sensors and processes them. It will construct a basic water consumption data set and a real-time monitoring data set, extract water consumption features from them and form a feature parameter set. Based on the feature parameter set, feature cluster groups, water consumption time periods and demand intensity levels are divided, and these contents are associated and integrated to form typical water consumption patterns. At the same time, the module is also responsible for constructing and dynamically updating the dynamic capability matrix of the water pump. This matrix is a two-dimensional structured data table, the horizontal dimension is the operation frequency interval division, and the vertical dimension is the core parameter category representing the performance of the water pump, including basic performance parameters and state correction parameters.

[0131] The control module is connected with the data processing module, its main function is to locate the target water consumption pattern based on the similarity matching of real-time water consumption features and typical water consumption patterns. Then combined with the dynamic capability matrix, the target water pump is selected from the water pump group to construct the execution pump group. Then the flow demand of the target water consumption pattern is decomposed into basic load and dynamic adjustment load and allocated, and finally the control instructions of the water pump group are generated, including water pump start-stop instructions, basic operation frequency instructions and dynamic adjustment parameter instructions. When generating the control instructions, the control module will determine the proportion of the basic load and the dynamic adjustment load according to the demand intensity level, the higher the demand intensity level, the greater the proportion of the basic load.

[0132] The instruction updating determination module is connected with the sensor sensing network, the data processing module and the control module respectively, and continuously monitors the water consumption data and the operation data. By calculating the mode matching similarity and the parameter deviation rate, the operation state of the basic load bearing pump and the dynamic adjustment load bearing pump is monitored, and it is comprehensively determined whether the control instruction needs to be updated. The determination basis includes the cumulative time length of the mode matching similarity being less than the set threshold, the continuous number of the parameter deviation rate being greater than the set threshold, the cumulative time length of the operation frequency of the basic load bearing pump deviating from the target interval, the cumulative time length of the adjustment amount of the dynamic adjustment load bearing pump exceeding the tolerance range, and the situation that the current target water mode is invalid due to the update of the typical water mode.

[0133] Working principle and effects:

[0134] The present application realizes multi-pump collaborative variable frequency energy-saving water supply, and the core is to accurately match the dynamic water demand with the real-time performance of the water pump, which not only guarantees the stability of water supply, but also improves the energy-saving performance of the system.

[0135] Firstly, water consumption data and water pump operation data are collected at key nodes of the pipe network, and water consumption characteristics such as trend, period and randomness are extracted therefrom, and typical water modes are constructed in combination with time interval attributes and demand intensity levels. Meanwhile, a dynamic capability matrix reflecting the actual performance of the water pump is constructed according to the factory performance and real-time attenuation data of the water pump. This process not only converts scattered water consumption data into structured reference modes to provide accurate basis for control, but also dynamically tracks the performance change of the water pump to ensure that the relevant parameters meet the actual state, solving the problems of inaccurate grasp of water consumption law and static evaluation of water pump performance in traditional water supply systems. Secondly, the current corresponding target water mode is determined through similarity matching, and appropriate water pumps are selected to form an execution pump group in combination with the dynamic capability matrix, the flow demand is decomposed into basic load and dynamic adjustment load and reasonably allocated, and corresponding control instructions are generated. At the same time, the cumulative time length of various deviations is continuously monitored, and the control instructions are updated in time. This dynamic control mode can flexibly respond to water consumption fluctuations, and the water pump can run in the efficient interval, avoiding energy waste and unstable water supply under the fixed control mode, and through multi-dimensional monitoring of deviations, the long-term stable operation of the system is guaranteed.

[0136] In summary, through systematic water mode construction, dynamic water pump performance evaluation and precise load allocation and control, the present application realizes real-time adaptation of water demand and water pump operation, improves the stability and reliability of water supply, significantly reduces energy consumption, prolongs the service life of equipment, and provides an effective solution for the intelligentization and energy saving of multi-pump collaborative water supply system.

[0137] The above merely describes the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-described embodiments. Any technical solution falling within the concept of the present application shall fall within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A control method for a multi-pump coordinated frequency conversion energy-saving water supply equipment, characterized in that: include: Collect water consumption data and extract water consumption characteristics of the water consumption data through a sliding window; The principal component analysis of the quantitative indicators of the water use characteristics is performed to screen the characteristic parameters and construct a characteristic parameter set; based on the time interval attributes of the characteristic parameter set, the characteristic cluster groups are clustered and divided, and the typical water use pattern is constructed by associating with the water use period and demand intensity level; Based on the performance curves and performance degradation quantitative indicators of each pump in the water supply equipment's pump group, a dynamic capacity matrix of each pump is constructed and updated; Extract water usage characteristics based on real-time water usage data to perform similarity matching on typical water usage patterns, locate the target water usage pattern, and, combined with the dynamic capacity matrix of the water pumps, select the target water pumps for water supply in the water pump group. Build an execution pump group, and perform load distribution by decomposing the flow demand of the target water usage pattern into a base load and a dynamically adjusted load, generating control instructions for the water pump group. Execute the control instruction, and count the cumulative time of deviation from the target water usage pattern, the dynamic capacity matrix, and the load distribution to determine whether to trigger the update of the water pump group control instruction.

2. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 1, characterized in that: The specific steps of clustering the feature cluster groups include: Collect water usage data and align the data based on the collection timestamp through a time synchronization mechanism to build a basic water usage dataset. Setting a sliding window, and extracting water use features from the water use data within the sliding window based on the basic water use data set; the water use features include trend features, periodic features, and random features; The trend feature is used to reflect the regularity of changes in water use data within the time range of the sliding window; the period feature is used to reflect the regular fluctuation characteristics of water use data within a fixed period; and the random feature is used to capture the irregular water use change characteristics caused by sudden water use situations. According to the timestamp of the sliding window, the water usage characteristics are marked with time interval attributes. The time interval attribute refers to the time range information corresponding to the sliding window, including the start time and end time; For the extracted water use characteristics, principal component analysis is performed on the quantitative indicators contained therein, parameter screening thresholds are configured, characteristic parameters are screened, and characteristic parameters are classified and integrated according to characteristic types to form a characteristic parameter set; Based on the characteristic parameter set, a clustering algorithm is used to perform cluster analysis on the characteristic parameters of different time interval attributes and divide the characteristic cluster groups.

3. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 2, characterized in that: The specific steps of constructing a typical water use pattern include: Configure time interval clustering parameters and use the time interval clustering algorithm to divide water use periods to clarify the distribution range of different feature cluster groups in the time dimension; Configure demand intensity related parameters and assign corresponding demand intensity levels to each characteristic cluster group to quantify the urgency and scale of water demand represented by different characteristic cluster groups; The characteristic clustering groups are associated and integrated with the divided water use periods and the designated demand intensity levels to form a typical water use pattern.

4. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 1, characterized in that: The dynamic capability matrix is ​​a two-dimensional structured data table. The horizontal dimension is the operating frequency interval division, and the vertical dimension is the core parameter category characterizing the performance of the water pump, which includes basic performance parameters and state correction parameters. The basic performance parameters are used to reflect the inherent performance characteristics of the water pump at different operating frequencies and reflect the basic operating capability of the water pump under standard conditions; the state correction parameters are used to reflect the performance deviation and boundary changes of the water pump during actual operation and reflect the dynamic characteristics of the water pump performance as the operating conditions change.

5. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 4, characterized in that: The specific steps of constructing and updating the dynamic capacity matrix of each water pump include: Based on the factory rated performance curve of the water pump, the key performance parameters of the water pump are discretized according to the preset frequency intervals. The key performance parameter values ​​at the endpoints of each frequency interval are recorded as the basic performance parameter values. Various state correction parameters are initialized and set according to the factory performance of the water pump to construct the initial dynamic capacity matrix. Build a full-operation test platform to conduct offline full-operation test, collect basic performance parameter data at different operating frequencies, and use the data calibration algorithm to correct the basic performance parameter values ​​of the initial dynamic capability matrix; During the operation phase, real-time operation data of the water pumps is collected and the current typical water usage pattern data is extracted as correction data to construct a correction data set; Based on the corrected data set, the deviation analysis algorithm is used to calculate the deviation value of the basic performance parameters, which are proportionally mapped to the corresponding dimensions of the basic performance parameters for point-by-point correction, and the basic performance parameters are dynamically updated; Construct a multi-factor coupled performance degradation quantification model, calculate the mechanical loss, efficiency degradation correction value and load fluctuation influencing factor, and update the state correction parameters.

6. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 1, characterized in that: The specific steps of locating the target water use pattern include: Collect water usage data of the current pipe network in real time, extract real-time water usage characteristics for quantitative processing, and convert the real-time water usage characteristics into a real-time feature parameter set consistent with the feature parameter set structure in the typical water usage pattern through a standardized parameter conversion algorithm; Calculate the cosine similarity between the real-time feature parameter set and the feature parameter set in each typical water use pattern, set a similarity threshold, compare the cosine similarity between the real-time feature parameter set and the feature parameter set in each typical water use pattern with the similarity threshold, and mark the typical water use pattern with a cosine similarity greater than the similarity threshold as a potential target water use pattern; If the number of potential target water use patterns is greater than 1, the time matching degree between each potential target water use pattern and the current actual time is calculated, and the potential target water use pattern is selected as the target water use pattern according to the time matching degree; If the number of potential target water use patterns is 1, then the potential target water use pattern is used as the target water use pattern; If the number of potential target water use patterns is less than 1, a reference pattern is selected based on cosine similarity, and a linear interpolation algorithm is used to generate a temporary water use pattern as the target water use pattern.

7. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 1, characterized in that: The specific steps of constructing the execution pump group include: Obtain target water use patterns, extract characteristic parameter sets, time interval attributes, and demand intensity levels; Retrieve the dynamic capacity matrix of each pump in the pump group, extract the basic performance parameters and state correction parameters of each pump, and build a pump performance parameter library; Based on the water pump performance parameter library, a correspondence matrix between the target water use pattern and the water pump operating status is constructed to establish a quantitative correlation framework between water demand and water pump performance. The deviation rate of the correspondence matrix is ​​calculated, and dynamic weights are set in combination with the demand intensity level. The initial water pump fitness score is calculated through weighted summation, and then corrected according to the status correction parameters of each water pump to obtain the water pump fitness score of each water pump. Calculate the target number of required pumps based on the flow demand value of the target water use pattern and the rated flow rate of the pumps; sort all pumps in descending order based on the pump suitability scores, and select pumps based on the target number to form the initial candidate pump group; The performance of the initial candidate pump group is verified. In response to failing the performance verification, the number of water pumps in the candidate pump group is increased according to the fitness score to construct the execution pump group.

8. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 7, characterized in that: The specific steps of generating the control instruction of the water pump group include: Obtain candidate pump groups and target water use patterns, decompose the flow demand value of the target water use pattern, and divide it into basic load and dynamic adjustment load; Based on the dynamic capability matrix of each water pump in the candidate pump group, determine the target operating frequency range of each water pump; Based on the target operating frequency range and the rated flow ratio of each pump, calculate the basic load component that each pump needs to bear, and determine the target operating frequency required for each basic load component; If the target operating frequency of the water pump is within its target operating frequency range, it is marked as a base load bearing pump, and the base load is allocated to it according to the calculated target operating frequency; if the target operating frequency of the water pump exceeds its target operating frequency range, the allocation ratio of the base load component is readjusted and the target operating frequency of the water pump is updated; Standardize the state correction parameters in the water pump dynamic capacity matrix, calculate the dynamic adjustment adaptation index, set the number of dynamic adjustment load-bearing pumps, screen and mark the dynamic adjustment load-bearing pumps according to the dynamic adjustment adaptation index, and determine the frequency adjustment range of each dynamic adjustment load-bearing pump; Based on the fluctuation amplitude and frequency of flow in real-time water consumption data, the dynamic adjustment load is allocated to each dynamic adjustment load-bearing pump according to the proportion of dynamic adjustment adaptation index; According to the basic load and dynamic load adjustment distribution results, the control instructions of the water pump group are generated. The control instructions include water pump start and stop instructions, basic operating frequency instructions, and dynamic adjustment parameter instructions.

9. The control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to claim 1, characterized in that: The specific steps of determining whether to trigger the update of the water pump group control instruction include: Extract water usage characteristics to update the real-time feature parameter set, measure the similarity with the current target water usage pattern feature parameter set, calculate the pattern matching degree, set the similarity judgment threshold, and count the cumulative pattern deviation time when the pattern matching degree is less than the similarity judgment threshold. If it is greater than the preset pattern deviation time, the water pump group control instruction update is triggered; Compare the water pump operating status parameters with the corresponding parameters in the dynamic capacity matrix and calculate the parameter deviation rate. If the parameter deviation rate is greater than the preset parameter deviation threshold and the cumulative parameter deviation duration is greater than the preset parameter deviation duration, the water pump group control instruction update is triggered; For the base load bearing pump, the accumulated load deviation duration of the actual operating frequency from the target operating frequency range is monitored. If it is greater than the preset load deviation duration, the water pump group control instruction update is triggered; For the dynamically regulated load-bearing pump, the accumulated time of the regulation deviation of the actual regulation amount from the load tolerance range adjustment amount is monitored. If it is greater than the preset regulation deviation time, the water pump group control instruction update is triggered.

10. Multi-pump coordinated frequency conversion energy-saving water supply equipment, which is implemented based on the control method of multi-pump coordinated frequency conversion energy-saving water supply equipment according to any one of claims 1 to 9, characterized in that: include: Sensor perception network, data processing module, control module and instruction update determination module; The sensor perception network is used to collect water use data and water pump operation data at key nodes of the pipeline network; the data processing module is used to construct typical water use patterns and dynamic capacity matrices; the control module is used to locate target water use patterns, screen water pumps and generate control instructions; the instruction update determination module is used to monitor data and comprehensively determine whether to update the control instructions.

Images