Water supply system energy consumption assessment and monitoring system and method based on data analysis

Abstract

The present invention discloses a water supply system energy consumption assessment and monitoring system and method based on data analysis, which relates to the technical field of water supply energy consumption assessment. The system obtains energy consumption data of water supply equipment and load data of the water supply system; divides a day into different time periods, extracts typical load data and target time periods of the water supply system; obtains and analyzes the energy consumption of the i-th water supply equipment in the target time period of the water supply system, and determines whether the i-th water supply equipment is in an abnormally high energy consumption state; obtains energy consumption distribution data of all water supply equipment in the target time period of the water supply system, and analyzes to obtain an energy consumption score of the i-th water supply equipment. The system is independent of the flow rate of the water supply equipment, analyzes the energy consumption status of the water supply equipment, and does not require manual inspection of the water supply equipment one by one, thereby realizing large-scale monitoring; reduces manual participation, can inspect the water supply equipment in real time, and improves the efficiency and timeliness of inspection.

Description

Technical Field

[0001] The present invention relates to the technical field of water supply energy consumption assessment, and in particular to a water supply system energy consumption assessment and monitoring system and method based on data analysis. Background Art

[0002] Water supply system energy consumption assessment aims to improve energy consumption management, water supply quality, and efficiency in water supply enterprises from an energy management perspective, with the goal of achieving energy conservation, emission reduction, and high-quality development. Based on basic data analysis and key equipment testing, a comprehensive scoring of water supply system energy consumption indicators is performed to quantitatively assess the current energy consumption of the water supply system. Water supply equipment, the facilities and equipment that provide water resources, consumes a certain amount of energy to operate, and its energy consumption is a significant factor influencing energy consumption. Energy consumption assessment of water supply equipment requires flow data, but many water supply equipment lack flow meters, making accurate flow data difficult to obtain, making energy consumption assessment difficult. Currently, energy consumption assessment of water supply equipment relies primarily on human resources. Assessment teams comprised of personnel with professional backgrounds in water supply production, electromechanical operations, and pipe network operations conduct biennial assessments of a large number of water supply equipment. However, limited human resources and long assessment cycles reduce the likelihood of timely detection of abnormally high energy consumption equipment. Summary of the Invention

[0003] The purpose of the present invention is to provide a water supply system energy consumption assessment and monitoring system and method based on data analysis to solve the problems raised in the prior art.

[0004] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: a water supply system energy consumption assessment and monitoring system based on data analysis, comprising a data acquisition module, a data analysis module, a data storage module, a data interaction module and an output module; the output end of the data acquisition module is connected to the input end of the data storage module, for obtaining energy consumption data of the water supply equipment; the output end of the data storage module is connected to the input end of the data analysis module, for storing energy consumption data of the water supply system and the water supply equipment; the output end of the data analysis module is connected to the input end of the output module, for analyzing the energy consumption of the water supply equipment, identifying the abnormally high energy consumption state of the water supply equipment, and generating an energy consumption score for the water supply equipment; the output end of the data interaction module is connected to the input end of the data storage module, for obtaining maintenance information of the water supply equipment; the output module is used to display the energy consumption score of the water supply equipment and the abnormally high energy consumption state identification results in the form of a list.

[0005] The data acquisition module also includes a flow measurement unit and an electrical parameter measurement unit; the flow measurement unit is used to obtain the flow of the water supply system and obtain the load data of the water supply system; the electrical parameter measurement unit is used to obtain the energy consumption information of the water supply equipment. The data analysis module also includes a target time period extraction unit, a box plot detection unit, a regression unit, and an energy consumption scoring unit; the target time period extraction unit is used to extract the typical load and target time period; the box plot detection unit generates the lower edge through the box plot method to detect anomalies in the data; the regression unit is used to train a multivariate linear regression model for the transfer energy efficiency of the target time period; the energy consumption scoring unit is used to calculate the energy consumption score of the water supply equipment. The energy consumption scoring unit obtains the weight of the target time period based on the number of time periods included in the classification cluster to which the target time period belongs, and obtains the energy consumption score of the water supply equipment based on the transfer energy efficiency of the water supply equipment in the target time period and the weight of the target time period.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a water supply system energy consumption assessment and monitoring method based on data analysis, comprising the following steps:

[0007] S11, obtaining energy consumption data of water supply equipment and load data of the water supply system; dividing a day into different time periods, extracting typical load data of the water supply system and target time periods;

[0008] S12: During the target time period of the water supply system, the energy consumption of the i-th water supply device is obtained and analyzed to determine whether the i-th water supply device is in an abnormally high energy consumption state. If not, the process proceeds to step S13; if so, the i-th water supply device is added to the maintenance target.

[0009] S13, obtaining energy consumption distribution data of all water supply equipment in the target time period of the water supply system, analyzing to obtain the energy consumption score of the i-th water supply equipment, and generating a maintenance target for the water supply equipment.

[0010] In step S11, dividing a day into different time periods and extracting typical load data and target time periods of the water supply system further comprises the following steps:

[0011] S21, dividing a day into n time periods, where n is a positive integer; obtaining historical load data of the water supply system in each time period, and calculating the average load of each time period based on the historical load data;

[0012] S22, randomly select the average load of k time periods as the initial centroid and form a classification cluster, where k is a positive integer and is set according to the load of the water supply system;

[0013] S23, calculating the absolute value of the error between the average load of the time period other than the centroid and the centroid, and assigning the average load of the unselected time period to the classification cluster of the centroid with the smallest Euclidean distance;

[0014] S24, calculating the average of all average loads in each classification cluster and taking the average as the new centroid; determining the time period to which the centroid belongs: calculating the absolute value of the error between the centroid and the average load in the classification cluster to which it belongs, and the time period corresponding to the average load with the smallest absolute value of the error between the centroid and the average load is the time period of the centroid;

[0015] S25, repeating steps S23 and S24 until the maximum number of iterations is reached, at which point the centroid of the classification cluster is the typical load of the water supply system, and the time period to which the centroid belongs is the target time period.

[0016] The efficiency of water supply equipment varies with load, with different efficiencies under different loads. Loads are affected by people's water demand and change periodically, so it is necessary to analyze the efficiency of water supply equipment under different loads.

[0017] In step S12, the energy consumption change trend of the i-th water supply device itself is analyzed to determine whether the i-th water supply device is in an abnormally high energy consumption state, and further includes the following steps:

[0018] S31, obtaining the energy consumption data of the i-th water supply equipment and the load data of the water supply system in n time periods in the historical data, calculating the ratio of load to energy consumption to obtain the first transfer energy efficiency; obtaining the j-th target time period, using the first transfer energy efficiencies of other time periods as input and the first transfer energy efficiency of the j-th target time period as output, and training a multivariate linear regression model for the transfer energy efficiency of the j-th target time period;

[0019] S32, obtaining energy consumption data of the i-th water supply device and load data of the water supply system in n time periods on different dates from historical data, calculating the ratio of load to energy consumption to obtain a first transfer energy efficiency; using a multiple linear regression model of the transfer energy efficiency of the j-th target time period, taking the transfer energy efficiencies of time periods other than the j-th target time period as input, to generate a second transfer energy efficiency; performing a weighted summation of the second transfer energy efficiency and the first transfer energy efficiency to obtain a target transfer energy efficiency, and generating a transfer energy efficiency curve for the i-th water supply device based on the target transfer energy efficiency, with the horizontal axis representing the date and the vertical axis representing the target transfer energy efficiency;

[0020] S33: Perform an outlier detection on the transfer energy efficiency curve of the i-th water supply device to determine whether there is an outlier: Calculate the mean μ and standard deviation σ of the transfer energy efficiency curve to generate a baseline μ-aσ, where a is a positive integer. If there is a portion of the transfer energy efficiency curve that is less than the baseline, the i-th water supply device is in an abnormally high energy consumption state, and the process ends; if there is no portion of the transfer energy efficiency curve that is less than the baseline, proceed to step S34.

[0021] S34, in the transfer energy efficiency curve of the i-th water supply equipment, calculate the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, and calculate the change value V of the target transfer energy efficiency of the i-th water supply equipment. where b1, b2, ..., b m is the weight, b1>b2>…>b m , e1 is the latest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, ..., e m is the oldest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency; compare the change value V of the target transfer energy efficiency of the i-th water supply equipment with the threshold. If V is less than the threshold, it is judged that the i-th water supply equipment is in an abnormally high energy consumption state; if V is not less than the threshold, continue to analyze the i-th water supply equipment.

[0022] The load of water supply equipment is affected by the water supply system. When the load of the water supply system increases, the load of the water supply equipment also increases. For the same water supply equipment, when carrying the same load, as the equipment ages and its efficiency decreases, the power consumption increases. First, the first transfer energy efficiency of each target time period is analyzed using the equipment's own data. If there is an abnormally low first transfer energy efficiency, it indicates that the water supply equipment is experiencing abnormally high energy consumption under the load of the target time period. Next, the change value V of the target transfer energy efficiency for each target time period is analyzed. People's water use fluctuates, and therefore the target transfer energy efficiency also fluctuates. For example, water supply equipment is efficient under low load and less efficient under high load. As water use changes, the target transfer energy efficiency of the water supply equipment also changes. However, water use does not always change in the same direction. The loss of water supply equipment will basically remain unchanged in a short period of time. Therefore, the target transfer energy efficiency of the water supply equipment should also fluctuate within a certain range. If the target transfer energy efficiency of the water supply equipment decreases significantly within the m+1 day, it indicates that the water supply equipment is experiencing abnormally high energy consumption.

[0023] The energy consumption of water supply equipment depends on the measurement of its electrical parameters. If the electrical parameter measurements are affected during the target time period, the energy consumption determination will be affected. To this end, the transfer energy efficiency for the target time period is obtained by using data from all time periods throughout the day. Within a single day, the losses of water supply equipment are essentially the same, and the efficiencies under high and low loads match. For example, if the loss is c1, the efficiencies under high and low loads are r1 and g1, respectively. If the loss is c2, the efficiencies under high and low loads are r2 and g2, respectively. Then, r1 and g1, and r2 and g2, match. When the transfer energy efficiency data for the water supply equipment for time periods other than the jth target time period are obtained, the losses of the water supply equipment can be reflected, and the transfer energy efficiency data for the jth target time period can be obtained. Taking a weighted sum of the second and first transfer energy efficiencies can reduce interference caused by electrical measurement errors.

[0024] In step S34, the threshold is determined by the following steps:

[0025] Obtain the change value of the target transfer energy efficiency of other water supply equipment, and assign weights according to the status of other water supply equipment. If there are test results for other water supply equipment and it is determined that there is no abnormally high energy consumption state, the weight is increased. If there are test results for other water supply equipment and it is determined that there is an abnormally high energy consumption state, the weight is set to 0; if there are no test results for other water supply equipment, the weight is reduced, and the change value of the transfer energy efficiency of other water supply equipment is weightedly summed according to the weight to obtain a reference value; calculate the difference between the change value of the target transfer energy efficiency of other water supply equipment without test results and the reference value, and determine the lower edge of the difference through the box plot method, and add the lower edge to the reference value to obtain the threshold.

[0026] Obtain the energy consumption of all water supply equipment and the load data of the water supply system in the j-th target time period on different dates from historical data, calculate the ratio of load to energy consumption to obtain the first transfer energy efficiency of all water supply equipment in the j-th target time period, obtain the second transfer energy efficiency of all water supply equipment in the j-th target time period through a multiple linear regression model, and obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period based on the first transfer energy efficiency and the second transfer energy efficiency;

[0027] Analyze whether the target transfer energy efficiency of the i-th water supply equipment is an outlier, obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period, and perform box plot analysis to obtain the lower edge. If the target transfer energy efficiency of the i-th water supply equipment does not have a part that is less than the lower edge, then the target transfer energy efficiency of the i-th water supply equipment is not an outlier. Otherwise, the target transfer energy efficiency of the i-th water supply equipment is an outlier, and an abnormally high energy consumption state exists.

[0028] In step S13, the following steps are specifically included:

[0029] Obtain the number of time periods Nj contained in the classification cluster to which the j-th target time period belongs, calculate the weight Wj of the j-th target time period, Wj = Nj / n; obtain the energy consumption score Pi of the i-th water supply equipment according to the transferred energy efficiency of the i-th water supply equipment, Where Fi j is the target transfer energy efficiency of the i-th water supply equipment in the j-th target time period.

[0030] Compared with the existing technology, the beneficial effects of the present invention are: it does not rely on the flow rate of the water supply equipment, analyzes the energy consumption status of the water supply equipment, does not need to manually test the water supply equipment one by one, and can achieve large-scale monitoring; it reduces manual participation, can test the water supply equipment in real time, and improves the efficiency and timeliness of the detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a structural diagram of the water supply system energy consumption assessment and monitoring system based on data analysis of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] Example: Figure 1 As shown, the present invention provides a technical solution, a water supply system energy consumption assessment and monitoring system based on data analysis, including a data acquisition module, a data analysis module, a data storage module, a data interaction module and an output module; the output end of the data acquisition module is connected to the input end of the data storage module, for obtaining energy consumption data of the water supply equipment; the output end of the data storage module is connected to the input end of the data analysis module, for storing energy consumption data of the water supply system and the water supply equipment; the output end of the data analysis module is connected to the input end of the output module, for analyzing the energy consumption of the water supply equipment, identifying the abnormally high energy consumption state of the water supply equipment, and generating an energy consumption score of the water supply equipment; the output end of the data interaction module is connected to the input end of the data storage module, for obtaining maintenance information of the water supply equipment; the output module is used to display the energy consumption score of the water supply equipment and the abnormally high energy consumption state identification result in the form of a list.

[0034] The data acquisition module also includes a flow measurement unit and an electrical parameter measurement unit; the flow measurement unit is used to obtain the flow of the water supply system and obtain the load data of the water supply system; the electrical parameter measurement unit is used to obtain the energy consumption information of the water supply equipment. The data analysis module also includes a target time period extraction unit, a box plot detection unit, a regression unit, and an energy consumption scoring unit; the target time period extraction unit is used to extract the typical load and target time period; the box plot detection unit generates the lower edge through the box plot method to detect anomalies in the data; the regression unit is used to train a multivariate linear regression model for the transfer energy efficiency of the target time period; the energy consumption scoring unit is used to calculate the energy consumption score of the water supply equipment. The energy consumption scoring unit obtains the weight of the target time period based on the number of time periods included in the classification cluster to which the target time period belongs, and obtains the energy consumption score of the water supply equipment based on the transfer energy efficiency of the water supply equipment in the target time period and the weight of the target time period.

[0035] Embodiment: The present invention provides a technical solution, a method for evaluating and monitoring energy consumption of a water supply system based on data analysis, comprising the following steps:

[0036] S11, obtaining energy consumption data of water supply equipment and load data of water supply system; dividing a day into different time periods, extracting typical load data of water supply system and target time period:

[0037] Divide a day into n time periods, where n is a positive integer. Obtain the historical load data of the water supply system in each time period and calculate the average load of each time period based on the historical load data. Randomly select the average load of k time periods as the initial centroid and form a classification cluster. k is a positive integer and is set according to the load of the water supply system.

[0038] S100, calculating the absolute value of the error between the average load of the time period other than the centroid and the centroid, and assigning the average load of the unselected time period to the classification cluster of the centroid with the smallest Euclidean distance;

[0039] S200, calculating the average of all average loads in each classification cluster and taking the average as the new centroid; determining the time period to which the centroid belongs: calculating the absolute value of the error between the centroid and the average load in the classification cluster to which it belongs, and the time period corresponding to the average load with the smallest absolute error between the centroid and the average load is the time period of the centroid;

[0040] Repeat steps S100 and S200 until the maximum number of iterations is reached, at which point the centroid of the classification cluster is the typical load of the water supply system, and the time period to which the centroid belongs is the target time period.

[0041] Optionally, n is set to 24 and k is set to 3, that is, a day is divided into 24 hours, and the load of the water supply system is divided into peak hours, off-peak hours, and normal hours. By analyzing the efficiency of the water supply equipment in the target time period containing the three typical loads, a comprehensive evaluation of the water supply equipment can be performed without analyzing all time periods.

[0042] S12: During the target time period of the water supply system, the energy consumption of the i-th water supply device is obtained and analyzed to determine whether the i-th water supply device is in an abnormally high energy consumption state. If not, the process proceeds to step S13; if so, the i-th water supply device is added to the maintenance target.

[0043] Determining whether the i-th water supply device is in an abnormally high energy consumption state further includes the following steps:

[0044] S31, obtaining the energy consumption data of the i-th water supply equipment and the load data of the water supply system in n time periods in the historical data, calculating the ratio of load to energy consumption to obtain the first transfer energy efficiency; obtaining the j-th target time period, using the first transfer energy efficiencies of other time periods as input and the first transfer energy efficiency of the j-th target time period as output, and training a multivariate linear regression model for the transfer energy efficiency of the j-th target time period;

[0045] S32, obtaining energy consumption data of the i-th water supply device and load data of the water supply system in n time periods on different dates from historical data, calculating the ratio of load to energy consumption to obtain a first transfer energy efficiency; using a multiple linear regression model of the transfer energy efficiency of the j-th target time period, taking the transfer energy efficiencies of time periods other than the j-th target time period as input, to generate a second transfer energy efficiency; performing a weighted summation of the second transfer energy efficiency and the first transfer energy efficiency to obtain a target transfer energy efficiency, and generating a transfer energy efficiency curve for the i-th water supply device based on the target transfer energy efficiency, with the horizontal axis representing the date and the vertical axis representing the target transfer energy efficiency;

[0046] In one day's data, the first transfer energy efficiency of 24 time periods can be obtained. When the first time period is the target time period, the regression model is trained by the data of the remaining 23 time periods. The data of one day is used as a set of input and output data, and the input and output data on different dates are input to obtain the regression model parameters.

[0047] S33: Perform an outlier detection on the transfer energy efficiency curve of the i-th water supply device to determine whether there is an outlier: Calculate the mean μ and standard deviation σ of the transfer energy efficiency curve to generate a baseline μ-aσ, where a is a positive integer. If there is a portion of the transfer energy efficiency curve that is less than the baseline, the i-th water supply device is in an abnormally high energy consumption state, and the process ends; if there is no portion of the transfer energy efficiency curve that is less than the baseline, proceed to step S34.

[0048] S34, in the transfer energy efficiency curve of the i-th water supply equipment, calculate the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, and calculate the change value V of the target transfer energy efficiency of the i-th water supply equipment. where b1, b2, ..., b m is the weight, b1>b2>…>b m , e1 is the latest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, ..., e m is the oldest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency; compare the change value V of the target transfer energy efficiency of the i-th water supply equipment with the threshold. If V is less than the threshold, it is judged that the i-th water supply equipment is in an abnormally high energy consumption state; if V is not less than the threshold, continue to analyze the i-th water supply equipment.

[0049] The threshold is determined by the following steps:

[0050] Obtain the change value of the target transfer energy efficiency of other water supply equipment, and assign weights according to the status of other water supply equipment. If there are test results for other water supply equipment and it is determined that there is no abnormally high energy consumption state, the weight is increased. If there are test results for other water supply equipment and it is determined that there is an abnormally high energy consumption state, the weight is set to 0; if there are no test results for other water supply equipment, the weight is reduced, and the change value of the transfer energy efficiency of other water supply equipment is weightedly summed according to the weight to obtain a reference value; calculate the difference between the change value of the target transfer energy efficiency of other water supply equipment without test results and the reference value, and determine the lower edge of the difference through the box plot method, and add the lower edge to the reference value to obtain the threshold.

[0051] S13, obtaining the energy consumption distribution data of all water supply equipment in the target time period of the water supply system, and analyzing to obtain the energy consumption score of the i-th water supply equipment:

[0052] Obtain the energy consumption of all water supply equipment and the load data of the water supply system in the j-th target time period on different dates from historical data, calculate the ratio of load to energy consumption to obtain the first transfer energy efficiency of all water supply equipment in the j-th target time period, obtain the second transfer energy efficiency of all water supply equipment in the j-th target time period through a multiple linear regression model, and obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period based on the first transfer energy efficiency and the second transfer energy efficiency;

[0053] The target transfer energy efficiency can be weightedly summed according to the first transfer energy efficiency and the second transfer energy efficiency, where the weight of the first transfer energy efficiency decreases as the number n increases. This is because the more time periods are divided, the shorter the target time period is, and the lower the probability of being discovered when the electrical measuring equipment fails within the target time period, and the higher the probability of using erroneous data when evaluating the energy consumption of water supply equipment.

[0054] Analyze whether the target transfer energy efficiency of the i-th water supply equipment is an outlier, obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period, and perform box plot analysis to obtain the lower edge. If the target transfer energy efficiency of the i-th water supply equipment does not have a part that is less than the lower edge, then the target transfer energy efficiency of the i-th water supply equipment is not an outlier. Otherwise, the target transfer energy efficiency of the i-th water supply equipment is an outlier, and an abnormally high energy consumption state exists.

[0055] Obtain the number of time periods Nj contained in the classification cluster to which the j-th target time period belongs, calculate the weight Wj of the j-th target time period, Wj = Nj / n; obtain the energy consumption score Pi of the i-th water supply equipment according to the transferred energy efficiency of the i-th water supply equipment, Where Fi j is the target transfer energy efficiency of the i-th water supply equipment in the j-th target time period.

[0056] Generate maintenance targets for water supply equipment, add all water supply equipment with abnormally high energy consumption to the maintenance targets, and for water supply equipment without abnormally high energy consumption, perform maintenance in ascending order based on energy consumption scores.

[0057] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A water supply system energy consumption assessment and monitoring method based on data analysis, characterized in that: The following steps are involved: S11, obtaining energy consumption data of water supply equipment and load data of the water supply system; dividing a day into different time periods, extracting typical load data of the water supply system and target time periods; In step S11, dividing a day into different time periods and extracting typical load data and target time periods of the water supply system further comprises the following steps: S21, dividing a day into n time periods, where n is a positive integer; obtaining historical load data of the water supply system in each time period, and calculating the average load of each time period based on the historical load data; S22, randomly select the average load of k time periods as the initial centroid and form a classification cluster, where k is a positive integer and is set according to the load of the water supply system; S23, calculating the absolute value of the error between the average load of the time period other than the centroid and the centroid, and assigning the average load of the unselected time period to the classification cluster of the centroid with the smallest Euclidean distance; S24, calculating the average of all average loads in each classification cluster and taking the average as the new centroid; determining the time period to which the centroid belongs: calculating the absolute value of the error between the centroid and the average load in the classification cluster to which it belongs, and the time period corresponding to the average load with the smallest absolute value of the error between the centroid and the average load is the time period of the centroid; S25, repeating steps S23 and S24 until the maximum number of iterations is reached, at which point the centroid of the classification cluster is the typical load of the water supply system, and the time period to which the centroid belongs is the target time period; S12: During the target time period of the water supply system, the energy consumption of the i-th water supply device is obtained and analyzed to determine whether the i-th water supply device is in an abnormally high energy consumption state. If not, the process proceeds to step S13; if so, the i-th water supply device is added to the maintenance target. In step S12, the energy consumption change trend of the i-th water supply device itself is analyzed to determine whether the i-th water supply device is in an abnormally high energy consumption state, and further includes the following steps: S31, obtaining the energy consumption data of the i-th water supply equipment and the load data of the water supply system in n time periods in the historical data, calculating the ratio of load to energy consumption to obtain the first transfer energy efficiency; obtaining the j-th target time period, using the first transfer energy efficiencies of other time periods as input and the first transfer energy efficiency of the j-th target time period as output, and training a multivariate linear regression model for the transfer energy efficiency of the j-th target time period; S32, obtaining energy consumption data of the i-th water supply device and load data of the water supply system in n time periods on different dates from historical data, calculating the ratio of load to energy consumption to obtain a first transfer energy efficiency; using a multiple linear regression model of the transfer energy efficiency of the j-th target time period, taking the transfer energy efficiencies of time periods other than the j-th target time period as input, to generate a second transfer energy efficiency; performing a weighted summation of the second transfer energy efficiency and the first transfer energy efficiency to obtain a target transfer energy efficiency, and generating a transfer energy efficiency curve for the i-th water supply device based on the target transfer energy efficiency, with the horizontal axis representing the date and the vertical axis representing the target transfer energy efficiency; S33: Perform an outlier detection on the transfer energy efficiency curve of the i-th water supply device to determine whether there is an outlier: Calculate the mean μ and standard deviation σ of the transfer energy efficiency curve to generate a baseline μ-aσ, where a is a positive integer. If there is a portion of the transfer energy efficiency curve that is less than the baseline, the i-th water supply device is in an abnormally high energy consumption state, and the process ends; if there is no portion of the transfer energy efficiency curve that is less than the baseline, proceed to step S34. S34, in the transfer energy efficiency curve of the i-th water supply equipment, calculate the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, and calculate the change value V of the target transfer energy efficiency of the i-th water supply equipment. where b1, b2, ..., b m is the weight, b1>b2>…>b m , e1 is the latest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency, ..., e m is the oldest value of the difference between the previous target transfer energy efficiency and the next target transfer energy efficiency; compare the change value V of the target transfer energy efficiency of the i-th water supply equipment with the threshold value. If V is less than the threshold value, it is judged that the i-th water supply equipment is in an abnormally high energy consumption state; if V is not less than the threshold value, continue to analyze the i-th water supply equipment; S13, obtaining energy consumption distribution data of all water supply equipment in the target time period of the water supply system, analyzing to obtain the energy consumption score of the i-th water supply equipment, and generating a maintenance target for the water supply equipment.

2. The water supply system energy consumption assessment and monitoring method based on data analysis according to claim 1 is characterized in that: In step S34, the threshold is determined by the following steps: Obtain the change value of the target transfer energy efficiency of other water supply equipment and assign weights according to the status of other water supply equipment. If the other water supply equipment has a test result and is determined to be in a non-abnormally high energy consumption state, increase the weight. If the other water supply equipment has a test result and is determined to be in an abnormally high energy consumption state, set the weight to 0. If there is no test result for other water supply equipment, the weight is reduced, and the change values ​​of the transfer energy efficiency of other water supply equipment are weighted and summed according to the weight to obtain the reference value; The difference between the change value of the target transfer energy efficiency of other water supply equipment without test results and the reference value is calculated, and the lower edge of the difference is determined by the box plot method, and the threshold is obtained by adding the lower edge to the reference value.

3. The water supply system energy consumption assessment and monitoring method based on data analysis according to claim 2 is characterized in that: In step S13, the following steps are also included: Obtain the energy consumption of all water supply equipment and the load data of the water supply system in the j-th target time period on different dates from historical data, calculate the ratio of load to energy consumption to obtain the first transfer energy efficiency of all water supply equipment in the j-th target time period, obtain the second transfer energy efficiency of all water supply equipment in the j-th target time period through a multiple linear regression model, and obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period based on the first transfer energy efficiency and the second transfer energy efficiency; Analyze whether the target transfer energy efficiency of the i-th water supply equipment is an outlier, obtain the target transfer energy efficiency of all water supply equipment in the j-th target time period, and perform box plot analysis to obtain the lower edge. If the target transfer energy efficiency of the i-th water supply equipment does not have a part that is less than the lower edge, then the target transfer energy efficiency of the i-th water supply equipment is not an outlier. Otherwise, the target transfer energy efficiency of the i-th water supply equipment is an outlier, and an abnormally high energy consumption state exists.

4. The water supply system energy consumption assessment and monitoring method based on data analysis according to claim 3 is characterized in that: In step S13, the following steps are specifically included: Obtain the number of time periods Nj contained in the classification cluster to which the j-th target time period belongs, calculate the weight Wj of the j-th target time period, Wj = Nj / n; obtain the energy consumption score Pi of the i-th water supply equipment according to the transferred energy efficiency of the i-th water supply equipment, Where Fij is the target transfer energy efficiency of the i-th water supply equipment in the j-th target time period.

5. A water supply system energy consumption evaluation and monitoring system based on data analysis, using the water supply system energy consumption evaluation and monitoring method based on data analysis according to any one of claims 1 to 4, characterized in that: It includes a data acquisition module, a data analysis module, a data storage module, a data interaction module and an output module; the output end of the data acquisition module is connected to the input end of the data storage module to obtain the energy consumption data of the water supply equipment; the output end of the data storage module is connected to the input end of the data analysis module to store the energy consumption data of the water supply system and the water supply equipment; the output end of the data analysis module is connected to the input end of the output module to analyze the energy consumption of the water supply equipment, identify the abnormally high energy consumption state of the water supply equipment, and generate an energy consumption score for the water supply equipment; the output end of the data interaction module is connected to the input end of the data storage module to obtain maintenance information of the water supply equipment; The output module is used to display the energy consumption score of the water supply equipment and the abnormally high energy consumption state identification result in a list form.

6. The water supply system energy consumption assessment and monitoring system based on data analysis according to claim 5 is characterized in that: The data acquisition module also includes a flow measurement unit and an electrical parameter measurement unit; the flow measurement unit is used to obtain the flow of the water supply system and obtain the load data of the water supply system; the electrical parameter measurement unit is used to obtain energy consumption information of the water supply equipment.

7. The water supply system energy consumption assessment and monitoring system based on data analysis according to claim 5 is characterized in that: The data analysis module also includes a target time period extraction unit, a box plot detection unit, a regression unit and an energy consumption scoring unit; the target time period extraction unit is used to extract typical loads and target time periods; the box plot detection unit generates a lower edge through a box plot method to perform anomaly detection on the data; the regression unit is used to train a multivariate linear regression model for target time period transfer energy efficiency; and the energy consumption scoring unit is used to calculate the energy consumption score of the water supply equipment.

8. The water supply system energy consumption assessment and monitoring system based on data analysis according to claim 7 is characterized in that: The energy consumption scoring unit obtains the weight of the target time period according to the number of time periods included in the classification cluster to which the target time period belongs, and obtains the energy consumption score of the water supply equipment according to the transfer energy efficiency of the water supply equipment in the target time period and the weight of the target time period.

Images