Method for determining performance of pump unit, computing device and storage medium

Abstract

The embodiment of the invention relates to a method for determining the performance of a pump unit, computing equipment and a storage medium. The method comprises the following steps: constructing an index network for pump performance evaluation, wherein the index network comprises a plurality of performance indexes related to the pump and a relationship among the performance indexes; on the basis of the constructed index network, atomic indexes of the pump unit and all single pumps in the pump unit are collected in real time, and values of derived indexes and composite indexes are predicted on the basis of the collected atomic indexes; feature extraction is carried out on each performance index, so that features of multiple performance indexes in deviation value features, deviation time sequence features, performance features, energy consumption features and fault features of the pump unit and single pumps in the pump unit are obtained; and evaluating the performance of the pump unit and each single pump in the pump unit based on the obtained characteristics of the plurality of performance indexes. Therefore, deep evaluation can be carried out on the pump unit and each single pump in the unit, and traceability and root cause analysis can be directly carried out on equipment performance degradation.

Description

Technical Field

[0001] Embodiments of the present invention generally relate to the field of industrial control, and more particularly to a method, computing device, and storage medium for determining performance of a pump unit. Background Art

[0002] A pump unit usually contains multiple pumps. Different types of pumps have different quantitative standards for performance parameters, and performance identification and judgment need to be made according to different quantitative standards. The performance parameters of the pumps and their relationship are the basis for pump selection and flow regulation. The performance differences of various types of pumps play a very important role in selection and use.

[0003] Traditional methods for online evaluation of pump unit performance, such as focusing on single pump equipment and systems with single pump equipment as the core, have some deficiencies in the comprehensive evaluation of pump unit systems, and it is difficult to form a close evaluation relationship between the performance evaluation of the entire unit and the single pump under the unit; for example, the performance evaluation of a single pump is performed through some general indicators, which cannot comprehensively analyze the performance of the equipment in terms of the breadth and depth of quantification. In addition, the traditional quantification and evaluation system cannot directly trace the source and root cause analysis of equipment performance degradation. Therefore, the industry as a whole lacks refined management of the performance of water pump equipment (and systems), and its performance monitoring and real-time evaluation are insufficient.

[0004] In summary, the traditional method for determining the performance of a pump unit has the following shortcomings: it can only evaluate a single pump, and the evaluation is insufficient in depth and breadth, making it difficult to accurately evaluate the performance of the pump unit, and unable to directly trace and analyze the root causes of equipment performance degradation. Summary of the invention

[0005] In response to the above problems, the present invention provides a method, a computing device and a storage medium for determining the performance of a pump unit, which can perform an in-depth evaluation of the pump unit and each individual pump in the unit, and directly trace the source and conduct root cause analysis of equipment performance degradation.

[0006] According to a first aspect of the present invention, a method for determining the performance of a pump unit is provided, comprising: constructing an indicator network for pump performance evaluation, the indicator network comprising a plurality of performance indicators about the pump and the relationship between the performance indicators, the plurality of performance indicators comprising atomic indicators, derived indicators and composite indicators; based on the constructed indicator network, collecting the atomic indicators of the pump unit and each single pump in the pump unit in real time, and predicting the values ​​of the derived indicators and the composite indicators based on the collected atomic indicators; performing feature extraction on each performance indicator to obtain characteristics of a plurality of performance indicators including deviation value characteristics, deviation timing characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit; and evaluating the performance of the pump unit and each single pump in the pump unit based on the characteristics of the plurality of performance indicators obtained.

[0007] According to a second aspect of the present invention, a computing device is provided, comprising: at least one processing unit; at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to the first aspect.

[0008] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a machine, the method according to the first aspect is implemented.

[0009] According to a fourth aspect of the present invention, there is further provided a computer program product, comprising a computer program, wherein when the computer program is executed by a machine, the method of the first aspect of the present invention is performed.

[0010] In some embodiments, atomic indicators include inlet pressure, outlet pressure, voltage, current, speed and / or frequency; derived indicators include instantaneous flow, cumulative flow, total energy consumption, head and / or unit pipe loss; composite indicators include pump operating conditions, energy utilization rate, motor power and / or unit energy consumption.

[0011] In some embodiments, the values ​​of derived indicators and composite indicators predicted based on the collected atomic indicators include: predicting instantaneous flow, head and unit pipe loss based on inlet pressure, outlet pressure, speed and / or frequency; predicting motor power based on voltage, current, speed and / or frequency; predicting pump operating conditions based on head, instantaneous flow and unit pipe loss; predicting energy utilization based on pump operating conditions and motor power; and predicting unit energy consumption based on cumulative flow and total energy consumption.

[0012] In some embodiments, feature extraction is performed for each performance indicator to obtain characteristics of multiple performance indicators including deviation value characteristics, deviation timing characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit, including: calculating a performance deviation value based on the predicted performance value and the actual performance value; performing calculations based on the performance deviation value to obtain a threshold quantile of the performance deviation; and calculating the proportion of performance deviations exceeding the threshold.

[0013] In some embodiments, feature extraction is performed for each performance indicator to obtain characteristics of multiple performance indicators including deviation value characteristics, deviation timing characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit, including: extracting original timing data of target performance indicators of the pump unit and / or each single pump in the pump unit based on a predetermined historical time range; and performing step-by-step processing on the original timing data of the target performance indicator to obtain trend characteristics, periodic characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original timing data of the target performance indicator.

[0014] In some embodiments, the original time series data of the target performance index is processed step by step to obtain the trend characteristics, period characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance index respectively, including: The original time series data of the target performance is filtered and denoised so as to generate the first time series data after the outliers in the original time series data are removed; the first time series data is decomposed by using the seasonal trend decomposition method to obtain the trend item data about the first time series data; the obtained trend item data is fitted and the goodness of fit is calculated so as to select the trend data that meets the goodness requirements; and based on the selected trend data, the trend change rate parameter is calculated to obtain the trend characteristics of the pump unit and / or each single pump in the pump unit about the target performance.

[0015] In some embodiments, the original time series data of the target performance indicator is processed in steps to obtain the trend characteristics, periodic characteristics and / or fluctuation characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance from the original time series data of the target performance indicator, and further includes: from the first time series data, the selected trend data is removed to generate the second time series data; for the second time series data, the seasonal trend decomposition method is used for decomposition, and the obtained second trend item data is subjected to Fourier transform to obtain multiple groups of amplitude data about the second time series data; from the multiple groups of amplitude data obtained, the amplitude data that meets the amplitude requirements is selected, and the time series lag order corresponding to the amplitude data is calculated as the prediction period; and the autocorrelation coefficient is calculated for the prediction period, so as to select at least one period that meets the autocorrelation coefficient requirements from the prediction period to obtain the periodic characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance.

[0016] In some embodiments, the original time series data of the target performance indicator is processed in steps to obtain the trend characteristics, periodic characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance indicator, and also includes: from the second time series data, eliminating data related to the obtained periodic characteristics to generate third time series data; and performing mean variance calculation on the third time series data to obtain the fluctuation characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance.

[0017] In some embodiments, the performance characteristics of the pump unit and / or each single pump in the pump unit include: actual performance curves of the pump unit, single pump, industrial frequency equipment and / or variable frequency equipment; the energy consumption characteristics of the pump unit and / or each single pump in the pump unit at least include the motor load level; the fault characteristics of the pump unit and / or each single pump in the pump unit include: the number of data of electrical faults, the proportion of data of electrical faults, the number of data of deviations from operating conditions and / or the proportion of data of deviations from operating conditions.

[0018] In some embodiments, based on the characteristics of the multiple performance indicators obtained, the performance of the pump unit and each single pump in the pump unit is evaluated, including: based on the deviation value characteristics, deviation timing characteristics, performance characteristics, energy consumption characteristics and / or fault characteristics, the performance degradation probability, performance degradation degree and performance degradation speed of the pump unit and each single pump in the pump unit are evaluated.

[0019] In some embodiments, evaluating the performance degradation probability, performance degradation degree and performance degradation rate of the pump group and each individual pump in the pump group includes: evaluating the degradation probability of the pump group and each individual pump in the pump group based on the threshold quantile of the performance deviation; and evaluating the degradation rate of the pump group and each individual pump in the pump group based on the trend indicator of the target performance.

[0020] In some embodiments, evaluating the degree of performance degradation of the pump unit and each individual pump in the pump unit includes: evaluating the operating condition indicators of the pump unit and each individual pump in the pump unit based on the actual performance curve; and evaluating the motor power indicator, energy utilization indicator and / or unit energy consumption indicator of the pump unit and each individual pump in the pump unit based on the over-threshold proportion and fault characteristics of the performance deviation.

[0021] In some embodiments, the method for determining the performance of a pump unit also includes: constructing a root cause analysis model based on at least multiple performance evaluation indicators, the hierarchical relationship between the pump unit and each individual pump in the pump unit, the product performance of each individual pump, the probability of performance degradation, the degree of performance degradation and the speed of performance degradation; performing a root cause analysis on the performance evaluation results of the pump unit and each individual pump in the pump unit through the constructed root cause analysis model; and determining the pump unit and potential and / or existing faults in the pump unit based on the root cause analysis results.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements.

[0024] Figure 1 A schematic diagram of a system for implementing a method for determining performance of a pump assembly according to an embodiment of the present invention is shown.

[0025] Figure 2 A flow chart of a method for evaluating performance of a pump unit according to an embodiment of the present invention is shown.

[0026] Figure 3 A flow chart of a method for obtaining deviation time series characteristics of a pump assembly and each individual pump in the pump assembly according to an embodiment of the present invention is shown.

[0027] Figure 4 A flow chart for obtaining trend characteristics of target performance according to an embodiment of the present invention is shown.

[0028] Figure 5 A flow chart of a method for acquiring periodic characteristics and / or fluctuation characteristics of target performance according to an embodiment of the present invention is shown.

[0029] Figure 6 A schematic diagram of an indicator network structure according to an embodiment of the present invention is shown.

[0030] Figure 7 A schematic diagram showing time series data features according to an embodiment of the present invention is shown.

[0031] Figure 8 A block diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0034] As described above, traditional methods for online evaluation of pump unit performance, such as focusing on single pump equipment and systems with single pump equipment as the core, have some deficiencies in the comprehensive evaluation of pump unit systems, and the performance evaluation of the entire unit is difficult to form a close evaluation relationship with the single pump under the unit; for example, the performance evaluation of a single pump is performed through some general indicators, which cannot comprehensively analyze the performance of the equipment in terms of the breadth and depth of quantification. In addition, the traditional quantification and evaluation system cannot directly trace the source and root cause analysis of equipment performance degradation.

[0035] Therefore, the traditional method for determining the performance of a pump unit has the following shortcomings: it can only evaluate a single pump, and the evaluation is insufficient in depth and breadth, making it difficult to accurately evaluate the performance of the pump unit, and unable to directly trace and analyze the root causes of equipment performance degradation.

[0036] In order to at least partially solve one or more of the above problems and other potential problems, an exemplary embodiment of the present invention proposes a scheme for determining the performance of a pump unit. In the scheme of the present invention, an index network for pump performance evaluation is constructed based on multiple performance indicators and the relationship between performance indicators; based on the constructed index network, the atomic indicators of the pump unit and each single pump in the pump unit are collected in real time, and the values ​​of the derived indicators and the composite indicators are predicted based on the collected atomic indicators. Thus, by constructing an index network containing multiple performance indicators, the present invention can achieve a more comprehensive and integrated performance evaluation system for the pump. The present invention also includes feature extraction for each performance indicator to obtain the characteristics of multiple performance indicators in the deviation value characteristics, deviation time series characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit; and based on the characteristics of the obtained multiple performance indicators, the performance of the pump unit and each single pump in the pump unit is evaluated; thus, the present invention can perform comprehensive quantification of indicators according to the order relationship and correlation between the performance indicators, and improve the accuracy and interpretability of the performance evaluation of the pump unit and the single pump.

[0037] Figure 1 FIG. 1 is a schematic diagram of a system 100 for implementing a method for determining the performance of a pump assembly according to an embodiment of the present invention. Figure 1 As shown in , the system 100 includes a computing device 110 and a pump unit 130 (the pump unit 130 includes multiple single pumps 130-1 to 130-n), an operating data acquisition device 150, and a network 140. The computing device 110, the pump unit 130, the multiple single pumps (130-1 to 130-n), and the operating data acquisition device 150 can exchange data through the network 140 (such as the Internet, industrial Ethernet, wide area network, etc.).

[0038] The pump unit 130 includes a plurality of single pumps 130 - 1 to 130 - n , wherein each single pump is, for example, not limited to a variable frequency or fixed frequency driven pump device, such as a pump, a water pump, etc.

[0039] Regarding the working condition data acquisition device 150, it includes, for example, a plurality of sensors, such as a pressure sensor, a flow meter, a speed sensor, an ammeter, a voltmeter, a power meter, a frequency meter, etc. The working condition data acquisition device 150 is configured based on the pump unit 130 and the plurality of single pumps 130-1 to 130-n contained in the pump unit 130, and the index network includes a plurality of performance indicators about the pump, thereby determining the number and type of sensors and the installation position, so as to collect various real-time working condition data about the pump unit 130 and each single pump. The working condition data acquisition device 150 can also send the collected various data to the computing device 110, so that the computing device 110 calculates the values ​​of each derived indicator and composite indicator based on the relationship between the plurality of performance indicators in the index network and the collected data of the atomic indicators.

[0040] In addition, the computing device 110 is capable of performing feature extraction for each performance indicator to obtain characteristics of multiple performance indicators including deviation value characteristics, deviation timing characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump group and each single pump in the pump group; and is capable of evaluating the performance of the pump group 130 and each single pump 130-1 to 130-n in the pump group 130 based on the characteristics of the obtained multiple performance indicators.

[0041] The computing device 110 may have one or more processing units, including dedicated processing units such as GPU, FPGA and ASIC, and general processing units such as CPU. In addition, one or more virtual machines may also be running on each computing device 110. In some embodiments, the computing device 110 and the working condition data acquisition device 150 may be integrated together or may be separately arranged.

[0042] In some embodiments, the computing device 110 includes, for example, an indicator network construction module 112 , an indicator value calculation module 114 , an indicator feature extraction module 116 , and a comprehensive performance evaluation module 118 .

[0043] The indicator network construction module 112 is used to construct an indicator network for pump performance evaluation. The indicator network includes multiple performance indicators about the pump and the relationship between the performance indicators. The multiple performance indicators include atomic indicators, derived indicators and composite indicators.

[0044] The index value calculation module 114 is used to collect the atomic indexes of the pump unit and each single pump in the pump unit in real time based on the constructed index network, and predict the values ​​of derived indexes and composite indexes based on the collected atomic indexes.

[0045] The indicator feature extraction module 116 is used to extract features for each performance indicator to obtain features of multiple performance indicators including deviation value features, deviation timing features, performance features, energy consumption features and fault features of the pump unit and each single pump in the pump unit.

[0046] The comprehensive performance evaluation module 118 is used to evaluate the performance of the pump assembly and each single pump in the pump assembly based on the characteristics of the acquired multiple performance indicators.

[0047] Figure 2 FIG. 2 is a flow chart of a method 200 for evaluating the performance of a pump unit according to an embodiment of the present invention. The method 200 may be performed as follows: Figure 1 The computing device 110 shown may also be executed in Figure 8 The method 200 is executed at the electronic device 800. It should be understood that the method 200 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0048] In step 202 , the computing device 110 constructs an indicator network for pump performance evaluation, wherein the indicator network includes multiple performance indicators about the pump and the relationship between the performance indicators, and the multiple performance indicators include atomic indicators, derived indicators, and composite indicators.

[0049] Regarding the relationship between performance indicators, such as the operational relationship between indicators and the method of obtaining them.

[0050] Regarding atomic indicators, derived indicators and composite indicators, they are three different types of indicators in the indicator system, and they play different roles in constructing and analyzing data.

[0051] Atomic indicators refer to the measurement values ​​based on the business process, which are the smallest units in the indicator system that cannot be further divided. For example, they are used to clarify the statistical caliber and calculation logic of the business. For example, in the present invention, atomic indicators include inlet pressure, outlet pressure, voltage, current, speed and / or frequency. In addition, in the present invention, atomic indicators are performance indicators that can be directly collected by sensor equipment.

[0052] Derived indicators refer to new indicators formed on the basis of atomic indicators in combination with additional conditions such as time period, dimension, business limitation, etc., which are used to express more specific business scenarios or trend changes. For example, in the present invention, derived indicators include instantaneous flow, cumulative flow, total energy consumption, head and / or unit pipe loss; in the present invention, derived indicators are obtained based on atomic indicator calculations.

[0053] A composite indicator is a complex indicator constructed by using two or more basic indicators (which may be atomic indicators or derived indicators) through specific mathematical operations, and is used to measure deeper business conditions or effects. The calculation of a composite indicator usually involves mathematical operations such as addition, subtraction, multiplication, division, and proportional calculation. For example, in the present invention, the composite indicator includes pump operating conditions, energy utilization rate, motor power, and / or unit energy consumption. In the present invention, the composite indicator is calculated based on the atomic indicator and / or derived indicator.

[0054] In step 204, the computing device 110 collects atomic indicators of the pump unit and each single pump in the pump unit in real time based on the constructed indicator network, and predicts the values ​​of derived indicators and composite indicators based on the collected atomic indicators.

[0055] In some embodiments, the values ​​of derived indicators and composite indicators predicted based on the collected atomic indicators include: predicting instantaneous flow, head and unit pipe loss based on inlet pressure, outlet pressure, speed and / or frequency; predicting motor power based on voltage, current, speed and / or frequency; predicting pump operating conditions based on head, instantaneous flow and unit pipe loss; predicting energy utilization based on pump operating conditions and motor power; and predicting unit energy consumption based on cumulative flow and total energy consumption.

[0056] For example, see Figure 6 , which illustrates a schematic diagram of an indicator network structure of an embodiment of the present invention, wherein arrows indicate the correlation between indicators, the bottom layer is atomic indicators (such as inlet pressure, outlet pressure, voltage, current, speed and / or frequency), and derived indicators (such as instantaneous flow, cumulative flow, total energy consumption, head and / or unit pipe loss) are obtained by calculation from the atomic indicators, and the top layer is composite indicators (pump operating conditions, energy consumption utilization rate, motor power and / or unit energy consumption (energy consumption per ton of water)); wherein unit energy consumption and energy consumption utilization rate are composite indicators used to measure energy consumption, and the two can replace each other. For example: the pump operating condition indicator (i.e., performance indicator) is calculated from the flow indicator and the head indicator, and the head indicator is calculated from the flow indicator and the inlet and outlet pressure indicators, and these indicators have strict functional relationships and correlations.

[0057] Therefore, based on Figure 6 The indicator network shown in can predict instantaneous flow and motor power based on real-time collected operation data only, and calculate the predicted values ​​of working condition indicators and energy consumption utilization rate indicators based on the predicted instantaneous flow data and motor power data. Therefore, it is possible to associate the performance indicators with each other, thereby obtaining a more accurate comprehensive performance prediction result. If these performance indicators are only analyzed independently, errors in functional relationships and correlations may occur.

[0058] For example, after building the indicator network, three composite indicators that ultimately point to the energy consumption of the pump, motor, and overall equipment are selected - pump operating condition, motor power, and energy utilization rate. These three composite indicators are used to comprehensively evaluate the performance of the pump unit and single pump. Other relevant performance indicators are used as derived indicators and atomic indicators of these three composite indicators to form an indicator network for analysis, avoiding calculation errors or data contradictions that may be caused by the independence analysis of all indicators. At the same time, data support and inference evidence sources are prepared for subsequent root cause analysis.

[0059] In step 206 , the computing device 110 performs feature extraction for each performance indicator to obtain features of multiple performance indicators including deviation value features, deviation timing features, performance features, energy consumption features, and fault features of the pump unit and each individual pump in the pump unit.

[0060] In some embodiments, obtaining deviation value characteristics about the pump group and each single pump in the pump group includes: calculating the performance deviation value based on the predicted performance value and the actual performance value; performing calculations based on the performance deviation value to obtain the threshold quantile of the performance deviation; and calculating the percentage of performance deviations exceeding the threshold.

[0061] Regarding the calculation of performance deviation values, in order to eliminate the influence of dimension, relative deviation is used for calculation. The calculation formula (1) is as follows: (1) Among them, true_value is the actual performance value of the performance indicator, and pred_value is the predicted performance value of the performance indicator.

[0062] For example, after obtaining the performance deviation value, the deviation distribution is further calculated for each performance indicator, so as to further calculate the threshold quantile of the performance deviation and the percentage of performance deviation exceeding the threshold value according to the deviation distribution. For example, the calculation result of the threshold quantile score of the deviation is: working condition performance indicator - 60 points; motor power performance indicator - 90 points; energy consumption utilization performance indicator - 70 points.

[0063] The percentage of performance deviation exceeding the threshold is used to count the percentage of data items with deviation exceeding the threshold in the total number of statistics within a certain period of time. For example, the calculation result of the characteristic of the percentage of deviation exceeding the threshold is: working condition performance index - this item is not calculated; motor power performance index - 5%; energy consumption utilization performance index - 30%.

[0064] Please refer to Figure 3, showing that the acquisition of deviation time series characteristics about the pump unit and each single pump in the pump unit in step 206 includes: step 302, extracting the original time series data of the target performance index of the pump unit and / or each single pump in the pump unit based on a predetermined historical time range; step 304, performing step-by-step processing on the original time series data of the target performance index, and (steps 306, 308 and 310) respectively acquiring the pump unit and / or each single pump in the pump unit about the target performance from the original time series data of the target performance index. Trend characteristics, periodic characteristics and / or fluctuation characteristics; specifically including: step 306, obtaining trend characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance from the original time series data of the target performance index; step 308, obtaining periodic characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance from the original time series data of the target performance index; step 310, obtaining fluctuation characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance from the original time series data of the target performance index.

[0065] The following will combine Figure 4 Describe in detail the method of obtaining the trend characteristics of the target performance, combined with Figure 5 The method of obtaining the periodic characteristics and / or fluctuation characteristics of the target performance is described in detail and will not be repeated here.

[0066] In step 208 , the computing device 110 evaluates the performance of the pump assembly and each individual pump in the pump assembly based on the characteristics of the acquired multiple performance indicators.

[0067] In some embodiments, based on the characteristics of the obtained multiple performance indicators, the performance of the pump unit and each single pump in the pump unit is evaluated, including: based on the deviation value characteristics, deviation time series characteristics, performance characteristics, energy consumption characteristics and / or fault characteristics, the performance degradation probability, performance degradation degree and performance degradation speed of the pump unit and each single pump in the pump unit are evaluated. In addition, the specific method of degradation evaluation is further described later.

[0068] Through the above scheme, the performance of the entire pump unit can be evaluated separately, and the performance of each single pump in the pump unit can be evaluated separately, so that the problems and potential problems in the pump system can be judged more accurately, so as to carry out fault prevention and performance optimization in advance. For example, pump unit A includes single pump A1 and single pump A2. The energy utilization rate of pump unit A is 75, which is good performance. However, the energy utilization rate of single pump A1 is 55, and the energy utilization rate of single pump A2 is 95. Obviously, in this case, there is a problem with the energy utilization rate of single pump A1, while the energy utilization rate of the entire pump unit A is normal; through the above method, even if the entire pump unit is operating normally, the single pump with problems can be found earlier to carry out risk prevention and control.

[0069] In the above scheme, the present invention constructs an indicator network based on the relationship between performance indicators, and performs more refined and targeted feature extraction on each performance indicator. In addition to quantifying the actual deviation of the performance indicator, it also adds characteristics of multiple performance indicators in deviation timing characteristics, performance characteristics, energy consumption characteristics and fault characteristics; and based on the characteristics of the multiple performance indicators obtained, the performance of the pump unit and each single pump in the pump unit is comprehensively evaluated from three angles: performance degradation probability, performance degradation degree and performance degradation speed, and an inference basis is provided for subsequent root cause analysis.

[0070] In addition, the above solution has the following advantages: 1) A series of business performance indicators of the pump unit and each single pump in the pump unit are constructed into an indicator network for analysis to avoid calculation errors or data contradictions that may be caused by the independent analysis of performance indicators; 2) Comprehensively consider the performance of the pump unit and each single pump in the pump unit, and conduct a comprehensive performance evaluation on each single pump based on the characteristics of multiple performance indicators, and also conduct a comprehensive performance evaluation on the entire pump unit.

[0071] Figure 4 4 is a flow chart showing a method 400 for obtaining trend characteristics of target performance according to an embodiment of the present invention. The method 400 may be performed as follows: Figure 1 The computing device 110 shown may also be executed in Figure 8 The method 400 is executed at the electronic device 800. It should be understood that the method 400 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0072] In step 402 , the computing device 110 performs filtering and noise reduction on the original time series data of the target performance, so as to generate first time series data after removing abnormal values ​​in the original time series data.

[0073] For example, after removing outliers, the original time series data of the target performance may be smoothed to generate first time series data, thereby eliminating the influence of extreme values.

[0074] In step 404 , the computing device 110 decomposes the first time series data using a seasonal trend decomposition method to obtain trend item data about the first time series data.

[0075] Regarding the seasonal trend analysis method, namely the STL decomposition (Seasonal and Trend decomposition using Loess) method, its basic principle is to represent the time series data as a linear combination of three components: trend (Trend) item data, periodic (Seasonal) item data and residual (Residual) item data. These three parts reflect the long-term trend of the data, periodic fluctuations, and random fluctuations or noise. STL decomposition uses Loess (local weighted regression) as a smoothing method to estimate the trend and seasonal components in an adaptive manner.

[0076] Therefore, by means of STL decomposition, trend item data can be decomposed from the first time series data to further determine trend data related to performance indicators, operating conditions, faults, etc. of the pump unit and single pump from the trend item data.

[0077] In step 406 , the computing device 110 performs fitting and goodness-of-fit calculation on the acquired trend item data, so as to select trend data that meets the goodness requirement.

[0078] For example, see Figure 7 , indicating that the first time series data can be decomposed by STL to obtain three layers of data: trend item data, period item data and residual item data, and trend extraction is performed on the obtained trend item data. Figure 7 The trend item data in the trend extraction calculation is performed in a variety of ways, and one or more of the trend data with more obvious trend performance is determined as the trend data that meets the requirements of excellence; for example Figure 7 The trend is extracted linearly (represented by ...) and nonlinearly (represented by . . --) respectively, and the one with a more obvious trend is selected.

[0079] In step 408 , the computing device 110 calculates a trend change rate parameter based on the selected trend data to obtain trend characteristics of the pump unit and / or each individual pump in the pump unit regarding the target performance.

[0080] For example, the pump operating performance index has a linear trend, and whether the degradation threshold has been reached can be calculated based on the trend slope; for example, the motor power performance index does not have trend characteristic data; for example, the energy consumption utilization performance index has a linear trend, and whether the trend slope has reached the degradation threshold can be determined based on calculation.

[0081] Therefore, based on the above scheme, trend data about the performance indicator can be obtained from the original data, so as to analyze whether there is a problem with the performance indicator based on the trend of the trend data, such as analyzing its degradation probability, degradation degree, degradation speed, etc.

[0082] Figure 51 is a flow chart of a method 500 for obtaining periodic characteristics and / or fluctuation characteristics of target performance according to an embodiment of the present invention. The method 500 may be performed as follows: Figure 1 The computing device 110 shown may also be executed in Figure 8 The method 500 is executed at the electronic device 800. It should be understood that the method 500 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0083] In step 502 , the computing device 110 removes selected trend data from the first time series data to generate second time series data.

[0084] In step 504 , the computing device 110 decomposes the second time series data using a seasonal trend decomposition method, and performs Fourier transform on the acquired second trend item data to obtain multiple groups of amplitude data about the second time series data.

[0085] In step 506, the computing device 110 selects amplitude data that meets the amplitude requirement from the acquired multiple sets of amplitude data, and calculates the time series lag order corresponding to the amplitude data as a prediction period.

[0086] In step 508, the computing device 110 calculates the autocorrelation coefficient for the prediction period so as to select at least one period that meets the autocorrelation coefficient requirement from the prediction period to obtain the periodic characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance.

[0087] For example, the second trend item data is used as input data for Fourier transform, the transformed amplitude data is extracted, and the amplitude that meets the amplitude requirements (for example, the top ranking) and the corresponding time series lag order are selected as the prediction period; the autocorrelation coefficient may be calculated for the selected prediction periodicity, and the period that meets the autocorrelation coefficient requirements is selected (for example, the largest autocorrelation coefficient, for example, the first two autocorrelation coefficients are selected), and the corresponding time series lag order is calculated, based on the above selection of the periodic characteristics of the output performance indicator.

[0088] For example, for the operating performance indicators, a 260-order lag cycle was found. According to the data collection frequency of once every 10 seconds, the degradation has a fluctuation period of about 43 minutes; for example, for the motor power performance indicators, no periodic characteristics were found; for example, for the energy consumption utilization performance indicators, no periodic characteristics were found.

[0089] In step 510 , the computing device 110 removes data related to the acquired periodic features from the second time series data to generate third time series data.

[0090] In step 512 , the computing device 110 performs mean-variance calculation on the third time series data to obtain fluctuation characteristics of the pump unit and / or each individual pump in the pump unit with respect to the target performance.

[0091] For example, continuing the above example, the amplitude data with the largest autocorrelation coefficient is removed from the second time series data to obtain the third time series data. The mean variance calculation is performed on the third time series data to obtain the fluctuation characteristics of the target performance (for example Figure 7 The fluctuation characteristic data is illustrated in Figure 3), the fluctuation characteristic can also be called noise characteristic.

[0092] Regarding noise characteristics (volatility characteristics), for example, based on the fluctuation characteristics of the operating condition performance indicators, it is determined that the fluctuation has not reached the fault threshold; for example, based on the fluctuation characteristics of the motor power performance indicators, it is determined that the fluctuation has not reached the fault threshold; for example, based on the fluctuation characteristics of the energy consumption utilization performance indicators, it is determined that the fluctuation has not reached the fault threshold.

[0093] Therefore, based on the above method, the original time series data of the performance indicators can be processed step by step, and the trend characteristics, periodic characteristics and / or fluctuation characteristics of the target performance indicators can be extracted from the original time series data respectively, and based on these time series characteristic data, further quantitative analysis can be performed to evaluate the comprehensive performance of the pump unit and each single pump.

[0094] In some embodiments, the performance characteristics of the pump unit and / or each individual pump in the pump unit include: actual performance curves of the pump unit, the individual pumps, the industrial frequency equipment and / or the variable frequency equipment.

[0095] Regarding the actual performance curve, for example, the actual performance curve of the working condition has a hump but the hump is not obvious, has a significant offset, and does not intersect with the theoretical working condition curve, and is located below the theoretical working condition curve; the actual performance curve can be used to analyze the status of the current pump system and the single pump. Regarding the acquisition of the performance curve, for example, by obtaining the operating data of the variable frequency unit and the historical frequency data of the water pump; based on the operating data, multiple working modes of the variable frequency unit are identified by a clustering algorithm to obtain the working condition data corresponding to each working mode; for the standard working condition data, the optimization algorithm is used to perform optimization calculation on the operating characteristic curve of the variable frequency unit within the preset rules to calculate the actual operating characteristic curve of the variable frequency unit (i.e., the actual performance curve). In order to facilitate further understanding of the acquisition of the actual performance curve, the entire content of another invention patent of the same applicant of this invention (application number: 202411984578.5; invention name: method, device and medium for determining the actual operating characteristics of the variable frequency unit) is introduced here. According to the scheme disclosed in the invention, it can be used to fit the actual performance curves of the pump unit and each single pump.

[0096] In some embodiments, the energy consumption characteristics of the pump unit and / or each single pump in the pump unit include at least the motor load level. For example, the motor load level is determined based on the motor load over a period of history and the comparison result between the motor load and a common threshold value in the industry; for example, within the statistical time range, the motor is running at low load, high load, or normal load. For example, the motor load level is the ratio of the actual power of the motor to the theoretical rated power of the motor.

[0097] In some embodiments, the fault characteristics of the pump unit and / or each single pump in the pump unit include: the number of data of electrical faults, the proportion of data of electrical faults, the number of data of deviation from the working condition and / or the proportion of data of deviation from the working condition. For example, with respect to electrical faults, within a period of time in the statistical history, the proportion of the number of data of electrical faults to the total number of data. For example, with respect to deviation from the working condition data, within a period of time in the statistical history, the proportion of the number of data of deviation from the working condition to the total number of data; for example, with respect to performance indicators such as head and flow rate, if they are not in the optimal working condition, it is considered that there is a deviation from the working condition.

[0098] In some embodiments, based on the threshold quantile of the performance deviation, the degradation probability of the pump unit and each single pump in the pump unit is evaluated. For example, for the operating condition performance index, if the degradation threshold is reached, it indicates that the pump may begin to degrade; for example, for the motor power performance index, if the degradation threshold is not reached, it indicates that no degradation signs are detected in the motor; for example, for the energy consumption utilization performance index, if the degradation threshold is reached, the energy consumption is high and the equipment has signs of degradation.

[0099] In some embodiments, based on the trend index of the target performance, the degradation rate of the pump unit and each single pump in the pump unit is evaluated. For example, for the working condition performance index, it is found that there is a further degradation trend according to the trend characteristics; for example, for the motor power performance index, it is found that the pump unit has no further degradation trend; for example, for the energy consumption utilization performance index, it is found that a single pump in the pump unit has a further degradation trend.

[0100] In some embodiments, evaluating the degree of performance degradation of the pump unit and each individual pump in the pump unit includes: evaluating the operating condition indicators of the pump unit and each individual pump in the pump unit based on the actual performance curve; and evaluating the motor power indicator, energy utilization indicator and / or unit energy consumption indicator of the pump unit and each individual pump in the pump unit based on the over-threshold proportion and fault characteristics of the performance deviation.

[0101] For example, for the operating condition performance index - the actual water pump performance curve characteristics are used for quantification, and it is found that the pump operation performance has degraded and the pump head has decreased overall; for the motor power performance index - the deviation over-threshold proportion characteristics are used for quantification, and it is found that a single pump has not reached the degradation threshold and the motor performance has not been detected to be degraded; for the energy consumption utilization performance index - the over-threshold proportion is used for quantification, and it is found that the pump unit has not reached the degradation threshold, but a single pump in the pump unit has reached the degradation threshold, and it is detected that the pump equipment has performance degradation.

[0102] Therefore, in the above scheme, the present invention can target multiple performance indicators in the indicator network, for example, split and calculate the characteristics of derived indicators and atomic indicators based on the selected three composite indicators, extract multiple characteristics of the target performance indicators, and more comprehensively evaluate the performance of performance indicators in terms of degradation probability, degradation degree, and degradation speed, which further corresponds to the performance evaluation of pump units and single pump equipment.

[0103] In some embodiments, the computing device 110 constructs a root cause analysis model based on at least multiple performance evaluation indicators, the hierarchical relationship of the pump unit and each individual pump in the pump unit, the product performance of each individual pump, the probability of performance degradation, the degree of performance degradation and the speed of performance degradation; performs root cause analysis on the performance evaluation results of the pump unit and each individual pump in the pump unit through the constructed root cause analysis model; and determines the pump unit and potential and / or existing faults in the pump unit based on the root cause analysis results.

[0104] For example, based on the evaluation level of the pump unit - single pump, the indicator network, the characteristics of each performance indicator and the quantitative analysis results of the degradation attributes (degradation probability, degradation degree and degradation rate), combined with expert experience and product manuals, a knowledge base is created and a root cause analysis model is constructed. This allows us to make relevant suggestions for the operation of the pump unit based on the results of the quantitative analysis and the characteristics of the performance indicators, and assist in related preventive maintenance and water pump operation optimization.

[0105] For example, in the current equipment, the operating performance of the pump has deteriorated, the pump head has decreased overall, and there is a trend of further deterioration; at the same time, the motor condition remains good; but due to the degradation of the pump performance, the overall energy consumption of the equipment has deteriorated, and has a synchronous deterioration trend as the pump performance deteriorates.

[0106] Continuing with the above example, based on the above quantitative analysis results, the possible causes analyzed based on the root cause analysis model are as follows: (1) Based on the actual pump performance curve characteristics, it is inferred that the impeller flow channel may be blocked, internal leakage may occur, and cavitation may occur at the inlet; (2) Based on the periodic characteristics, it is inferred that the water pump will experience short-term instantaneous periodic changes every 43 minutes. It is necessary to further track this time period to determine whether the pump equipment has mechanical operation changes or is subject to mechanical influences; (3) Based on the partial operating condition statistics and motor load level, it is inferred that the pump equipment motor is in a low-load state for a long time, causing the pump equipment to maintain a "big horse pulling a small cart" operating state, which in turn causes potential failures of the pump equipment and leads to performance degradation; (4) Based on the trend characteristics, it is inferred that the possible failures mentioned above have the risk of persisting and further deteriorating, and require attention and treatment.

[0107] Furthermore, in the above root cause analysis example, the remaining features not mentioned indicate that no usable anomaly information is present.

[0108] In the above scheme, the present invention, based on a single pump, formulates a unified evaluation system for single pumps in the associated unit for the performance evaluation needs of the equipment unit, and collects data from different units to conduct a comprehensive performance evaluation of the unit and the single pump under the unit. It is also possible to perform multi-dimensional comparisons of multiple performance indicators, and also provide an inference basis for subsequent root cause analysis. Specifically, this hierarchical division is also suitable for the above-mentioned performance indicator quantitative evaluation system: the performance indicators of the pump unit are selected in the same way as the single pump, and the three composite indicators of pump operating conditions, motor power, and energy consumption utilization rate can also be selected. At the same time, the indicator performance of the pump unit is evaluated from three perspectives: degradation probability, degradation degree, and degradation speed. However, since the unit operating conditions are more complex and changeable than those of a single pump (for example, the unit will turn on different numbers of pumps according to the water demand at different times), the feature extraction and calculation difficulty of the performance indicators is more complicated.

[0109] In addition, the above evaluation system can also provide rich data support for comprehensive evaluation and quantitative performance degradation, as well as root cause analysis of degradation. It can also provide relevant suggestions in combination with the user manual and fault database of the water pump, assist in related preventive maintenance and pump equipment operation optimization, and track and analyze the root causes of performance changes in pump units and pump equipment.

[0110] Figure 8 Schematic diagram of an example electronic device 800 that can be used to implement an embodiment of the present specification is shown. Figure 1The computing device 110 shown can be implemented by an electronic device 800. As shown, the electronic device 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or computer program instructions loaded from a storage unit 808 to a random access memory (RAM) 803. In the random access memory 803, various programs and data required for the operation of the electronic device 800 can also be stored. The central processing unit 801, the read-only memory 802, and the random access memory 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0111] Multiple components in the electronic device 800 are connected to the input / output interface 805, including: an input unit 806, such as a keyboard, a mouse, a microphone, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0112] The various processes and processing described above, such as methods 200 to 500, may be performed by the central processing unit 801. For example, in some embodiments, methods 200 to 500 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the read-only memory 802 and / or the communication unit 809. When the computer program is loaded into the random access memory 803 and executed by the central processing unit 801, one or more actions of the methods 200 to 500 described above may be performed.

[0113] The present invention relates to methods, apparatuses, systems, electronic devices, computer-readable storage media and / or computer program products. The computer program products may include computer-readable program instructions for executing various aspects of the present invention.

[0114] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0115] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge computing devices. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0116] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be executed by using the state information of the computer-readable program instructions to personalize and customize the electronic circuit, thereby implementing various aspects of the present invention.

[0117] Various aspects of the present invention are described herein with reference to flow charts and / or step diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each of the steps in the flow charts and / or step diagrams and the combination of the steps in the flow charts and / or step diagrams can be implemented by computer-readable program instructions.

[0118] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more steps in the flowchart and / or step diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more steps in the flowchart and / or step diagram.

[0119] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more steps in the flowchart and / or step diagram.

[0120] The flowchart and step diagram in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each square step in the flowchart or step diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square steps can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive square steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square step in the step diagram and / or the flowchart, and the combination of the square steps in the step diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining the performance of a pump unit, characterized in that include: Constructing an index network for pump performance evaluation, wherein the index network includes multiple performance indicators of the pump and the relationship between the performance indicators, and the multiple performance indicators include atomic indicators, derived indicators and composite indicators; Based on the constructed indicator network, the atomic indicators of the pump unit and each single pump in the pump unit are collected in real time, and the values ​​of the derived indicators and the composite indicators are predicted based on the collected atomic indicators; Perform feature extraction for each performance indicator to obtain features of multiple performance indicators including deviation value features, deviation time series features, performance features, energy consumption features, and fault features of the pump unit and each single pump in the pump unit; as well as Based on the characteristics of the obtained multiple performance indicators, the performance of the pump assembly and each single pump in the pump assembly is evaluated.

2. The method according to claim 1, characterized in that Atomic indicators include inlet pressure, outlet pressure, voltage, current, speed and / or frequency; Derived indicators include instantaneous flow, cumulative flow, total energy consumption, head and / or unit pipe loss; The composite index includes operating conditions, energy utilization, motor power and / or specific energy consumption.

3. The method according to claim 1, characterized in that The values ​​of derived and composite indicators predicted based on the collected atomic indicators include: Predict instantaneous flow, head and unit pipe loss based on inlet pressure, outlet pressure, speed and / or frequency; Predict motor power based on voltage, current, speed and / or frequency; Predict pump operating conditions based on head, instantaneous flow and unit pipe loss; Predict energy utilization based on pump operating conditions and motor power; and Based on the accumulated flow and total energy consumption, predict the unit energy consumption.

4. The method according to claim 1, characterized in that Feature extraction is performed for each performance indicator to obtain the characteristics of multiple performance indicators including deviation value characteristics, deviation time series characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit, including: Calculate the performance deviation value based on the predicted performance value and the actual performance value; Calculating based on the performance deviation value to obtain a threshold quantile of the performance deviation; and Calculate the percentage of performance deviations that exceed the threshold.

5. The method according to claim 1, characterized in that Feature extraction is performed for each performance indicator to obtain the characteristics of multiple performance indicators including deviation value characteristics, deviation time series characteristics, performance characteristics, energy consumption characteristics and fault characteristics of the pump unit and each single pump in the pump unit, including: Extracting original time series data of target performance indicators of the pump unit and / or each single pump in the pump unit based on a predetermined historical time range; and The original time series data of the target performance index is processed step by step to obtain the trend characteristics, period characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance index.

6. The method according to claim 5, characterized in that The original time series data of the target performance index is processed step by step to obtain the trend characteristics, period characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance index, including: Filtering and denoising the original time series data of the target performance, so as to generate first time series data after removing abnormal values ​​in the original time series data; Decomposing the first time series data by using the seasonal trend decomposition method to obtain trend item data about the first time series data; Performing fitting and goodness-of-fit calculation on the acquired trend item data so as to select trend data that meets goodness requirements; and Based on the selected trend data, a trend change rate parameter is calculated to obtain trend characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance.

7. The method according to claim 6, characterized in that The original time series data of the target performance index is processed step by step to obtain the trend characteristics, period characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance index respectively, and further includes: Selecting trend data from the first time series data to generate second time series data; The second time series data is decomposed by using a seasonal trend decomposition method, and the obtained second trend item data is subjected to Fourier transform to obtain multiple groups of amplitude data about the second time series data; Selecting amplitude data that meets the amplitude requirement from the acquired multiple sets of amplitude data, and calculating the time series lag order corresponding to the amplitude data as a prediction period; and The autocorrelation coefficient is calculated for the prediction period so as to select at least one period that meets the autocorrelation coefficient requirement from the prediction period to obtain the period characteristics of the pump unit and / or each single pump in the pump unit regarding the target performance.

8. The method according to claim 7, characterized in that The original time series data of the target performance index is processed step by step to obtain the trend characteristics, period characteristics and / or fluctuation characteristics of the target performance of the pump unit and / or each single pump in the pump unit from the original time series data of the target performance index respectively, and further includes: Eliminating data related to the acquired periodic feature from the second time series data to generate third time series data; and A mean-variance calculation is performed on the third time series data to obtain fluctuation characteristics of the pump unit and / or each single pump in the pump unit with respect to the target performance.

9. The method according to claim 1, characterized in that: The performance characteristics of the pump unit and / or each individual pump in the pump unit include: the actual performance curves of the pump unit, the individual pump, the power frequency equipment and / or the variable frequency equipment; The energy consumption characteristics of the pump unit and / or each individual pump in the pump unit include at least the motor load level; The fault characteristics of the pump unit and / or each single pump in the pump unit include: the number of data of electrical faults, the proportion of data of electrical faults, the number of data of abnormal working conditions and / or the proportion of data of abnormal working conditions.

10. The method according to claim 1, characterized in that Based on the characteristics of the obtained multiple performance indicators, the performance of the pump unit and each single pump in the pump unit is evaluated, including: Based on the deviation value characteristics, deviation time series characteristics, performance characteristics, energy consumption characteristics and / or fault characteristics, the performance degradation probability, performance degradation degree and performance degradation speed of the pump unit and each single pump in the pump unit are evaluated.

11. The method according to claim 10, characterized in that The performance degradation probability, degree and speed of the pump unit and each individual pump in the pump unit are evaluated, including: Assessing the degradation probability of the pump unit and each individual pump in the pump unit based on the threshold quantile of performance deviation; and Evaluate the degradation rate of the pump unit and each individual pump in the pump unit based on the trend indicator of the target performance.

12. The method according to claim 11, characterized in that The performance degradation of the pump unit and each individual pump in the pump unit is evaluated including: Evaluate the operating indicators of the pump unit and each pump in the pump unit based on the actual performance curve; and Based on the percentage of performance deviations exceeding the threshold and fault characteristics, the motor power index, energy utilization index and / or unit energy consumption index of the pump unit and each single pump in the pump unit are evaluated.

13. The method according to claim 1, characterized in that Also includes: Constructing a root cause analysis model based at least on the plurality of performance evaluation indicators, the hierarchical relationship between the pump unit and each individual pump in the pump unit, the product performance of each individual pump, the probability of performance degradation, the degree of performance degradation and the speed of performance degradation; Through the constructed root cause analysis model, the root cause analysis is performed on the performance evaluation results of the pump unit and each single pump in the pump unit; as well as Based on the root cause analysis results, potential and / or existing faults in the pump units and pump units are identified.

14. A computing device, characterized in that include: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to any one of claims 1 to 13.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a machine, the method according to any one of claims 1 to 13 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a machine, the method according to any one of claims 1 to 13 is performed.

Images