Parallel water pump performance monitoring method, device, computing equipment and system

Abstract

The invention discloses a parallel water pump performance monitoring method, device, computing equipment and system. According to the technical scheme provided by the invention, the parallel circulating water pumps are monitored, and historical operation data of the parallel circulating water pumps are collected; data cleaning is conducted on the collected historical operation data, and restored historical data after restoration is obtained; wherein the data cleaning comprises abnormal data detection, abnormal data screening and / or data restoration; generating a water pump characteristic curve according to the repaired historical data, and constructing a parallel circulating water pump performance model; and based on the current operation data of the parallel circulating water pump, the parallel circulating water pump performance model is used for monitoring and optimizing the operation state of the parallel circulating water pump. According to the method, the parallel circulating water pump performance model is generated through the fitting of the performance curve based on the historical operation data of the parallel water pump, so that the real-time monitoring and analysis of the water pump performance are realized, the operation condition of the water pump is scientifically predicted, and a reasonable optimization mode is obtained.

Description

Technical Field

[0001] The present invention relates to the field of industrial power generation, and in particular to a method, device, computing equipment and system for monitoring the performance of parallel water pumps. Background Art

[0002] As energy security, ecological environment, climate change and other issues become increasingly prominent, building a clean energy supply system and promoting green energy transformation and development have become a general consensus of the international community. In this context, as the main power source for my country's electricity supply, the progress of its low-carbon transformation is related to the implementation of my country's overall "dual carbon" goals. As one of the important auxiliary machines of thermal power plants and thermal power plants, the circulating water pump accounts for a high proportion of the power consumption rate of thermal power plants. Therefore, real-time monitoring of the operating performance of the circulating water pump and rational use of the circulating water pump to ensure that it operates in the high-efficiency zone are important measures for energy conservation and consumption reduction in thermal power plants.

[0003] In this regard, the existing circulating water pump monitoring technologies mostly rely on traditional sensors and control systems, lacking in-depth analysis and optimization of water pump performance. These technologies usually only focus on the real-time response of heat supply and demand, but ignore the operating performance of each water pump during the response process. This makes the operating data of each water pump usually obtained relatively simple, and the data collection is not comprehensive, resulting in the inability to calculate the water pump efficiency based on the operating parameters, and the inability to achieve real-time monitoring of the water pump operating performance. In addition, in actual work, due to factors such as site restrictions and connection installation, the installation layout of parallel circulating water pumps is different, resulting in obvious differences in operating parameters under the same working conditions even for the same model of water pumps. This difference leads to higher operating pressures for some water pumps, while the performance of other water pumps cannot be fully utilized, making the overall working efficiency of parallel circulating water pumps low and increasing their overall power consumption. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a parallel water pump performance monitoring method and a corresponding parallel water pump performance monitoring device, computing equipment and system.

[0005] According to one aspect of the present invention, a method for monitoring the performance of parallel water pumps is provided, the method comprising:

[0006] Monitor the parallel circulating water pumps and collect historical operation data of the parallel circulating water pumps;

[0007] Performing data cleaning on the collected historical operation data to obtain repaired historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair;

[0008] Generate water pump characteristic curve based on historical repair data and build parallel circulation water pump performance model;

[0009] Based on the current operating data of the parallel circulating water pump, the parallel circulating water pump performance model is used to monitor and optimize the operating status of the parallel circulating water pump.

[0010] In the above scheme, the monitoring of the parallel circulating water pump and the collection of historical operation data of the parallel circulating water pump further include:

[0011] The historical operation data at least include the main pipe inlet pressure, each pump outlet pressure, the total amount of circulating water, each hydraulic coupling scoop pipe opening and / or each motor current.

[0012] In the above scheme, data cleaning is performed on the collected historical operation data to obtain the repaired repair historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair, and further includes:

[0013] Generate structured monitoring data of circulating water pumps based on historical operation data with the same sampling frequency;

[0014] Use the 3σ criterion to detect abnormal data for structured monitoring data;

[0015] Based on the abnormal data detection results, the abnormal data set is screened and obtained;

[0016] Based on LSTM neural network and SVR algorithm, data repair is performed for abnormal data sets;

[0017] The data repair at least includes: redundant data elimination, erroneous data correction and / or missing data filling.

[0018] In the above scheme, generating a water pump characteristic curve based on the repair history data and constructing a parallel circulation water pump performance model further includes:

[0019] Determine the local resistance coefficient based on the historical repair data and the structural parameters of the parallel circulating water pump, and determine the head of the parallel circulating water pump based on the dynamic head and static head;

[0020] Based on the head of the parallel circulating water pump, the flow rate, input power and speed corresponding thereto are determined, and a characteristic curve of the parallel circulating water pump is generated; wherein the characteristic curve at least includes a QH curve, a QP curve and a Q-η curve;

[0021] Establish water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model;

[0022] Polynomial fitting is performed on each characteristic curve of the parallel circulating water pump, and a performance model of the parallel circulating water pump is constructed based on it.

[0023] In the above scheme, the operation status of the parallel circulating water pump is monitored and optimized by using the performance model of the parallel circulating water pump based on the current operation data of the parallel circulating water pump, further comprising:

[0024] Obtain the current operating data of the parallel circulating water pump and determine the actual performance data;

[0025] Input the current operation data of the parallel circulating water pump into the performance model of the parallel circulating water pump to calculate and obtain the predicted performance data;

[0026] Compare the actual performance data with the predicted performance data to obtain a comparison result;

[0027] Adjust the operating status of the parallel circulating water pump according to the comparison results.

[0028] In the above scheme, the actual performance data is compared with the predicted performance data to obtain a comparison result, further comprising:

[0029] Based on a preset number of historical repair data, a corresponding preset number of predicted performance data is calculated as an initial data set;

[0030] Perform data filtering on the initial data set, and obtain a filtered data set after filtering is completed;

[0031] Calculate upper and lower limit parameters based on the filtered data set;

[0032] Based on the upper limit parameter and the lower limit parameter, a threshold range for comparing the actual performance data with the predicted performance data is determined.

[0033] In the above scheme, the method further comprises:

[0034] Based on the initial data set, calculate the average value of all actual performance data in it and the upper quartile and lower quartile Based on this, the upper limit up1 and lower limit down1 of filtering the initial data set are determined.

[0035]

[0036] Filter the initial data set according to the filter upper limit up1 and the filter lower limit down1 to obtain the filtered data set, and calculate the average value of the filtered data set

[0037]

[0038] Where n′ is the number of actual performance data in the filtered data set, X′ i To filter the actual performance data in the data set;

[0039] Upper limit parameter and lower limit parameters for

[0040]

[0041] in, The number of filtered data sets that is greater than the average value of the filtered data sets The amount of data; The number of filtered data sets that is greater than the average value of the filtered data sets data; The number of filtered data sets that is less than the average value of the filtered data sets The amount of data; The number of filtered data sets that is less than the average value of the filtered data sets data;

[0042] The upper and lower thresholds in the threshold range are

[0043]

[0044] According to another aspect of the present invention, a parallel water pump performance monitoring device is provided, comprising: a collection module, a data cleaning module, a model generation module and an operation optimization module; wherein,

[0045] The acquisition module is used to monitor the parallel circulating water pump and collect historical operation data of the parallel circulating water pump;

[0046] The data cleaning module is used to clean the collected historical operation data to obtain the repaired historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair;

[0047] The model generation module is used to generate a water pump characteristic curve and construct a parallel circulation water pump performance model based on the repair history data;

[0048] The operation optimization module is used to monitor and optimize the operation status of the parallel circulating water pump based on the current operation data of the parallel circulating water pump and using the parallel circulating water pump performance model.

[0049] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0050] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned method for monitoring the performance of parallel water pumps.

[0051] According to another aspect of the present invention, a system is provided, which can perform operations corresponding to the above-mentioned method for monitoring the performance of parallel water pumps, and at least includes: a data import unit, a performance calculation unit and a result display unit; wherein,

[0052] The data import unit is used to respond to a data import instruction of a user and import the historical operation data and / or current operation data corresponding to the data import instruction into the system;

[0053] The performance calculation unit is used to calculate corresponding predicted performance data based on the imported current operation data using the parallel circulating water pump performance model;

[0054] The result display unit is used to display the obtained predicted performance data to the user terminal and provide a corresponding water pump operation status adjustment method.

[0055] According to the technical solution provided by the present invention, the parallel circulating water pump is monitored and the historical operating data of the parallel circulating water pump is collected; data cleaning is performed on the collected historical operating data to obtain repaired repair historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair; based on the repair historical data, a water pump characteristic curve is generated and a parallel circulating water pump performance model is constructed; based on the current operating data of the parallel circulating water pump, the parallel circulating water pump performance model is used to monitor and optimize the operating status of the parallel circulating water pump. By monitoring the parallel circulating water pumps and collecting various operating parameters corresponding to each water pump, comprehensive monitoring and collection of the operating parameters of the parallel circulating water pumps can be achieved, which is conducive to scientifically and comprehensively determining the operating conditions of the water pumps; by cleaning the collected historical operating data, the abnormal data can be detected and screened for the data used for model construction, and then the abnormal part can be repaired based on the LSTM neural network and SVR algorithm, which greatly improves the integrity and credibility of the data, and further improves the accuracy of model construction and water pump performance prediction; based on the repaired historical operating data and the installation structure of each water pump, the local resistance coefficient is determined, and according to the calculation formula of the head, the dynamic and static head of the water pump can be more accurately determined, and thus according to the flow, power and speed , accurately obtain the corresponding flow-head, power-head and speed-head characteristic curves, further determine the water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model, perform polynomial fitting, and scientifically construct the parallel circulating water pump performance model based on this; based on the parallel circulating water pump performance model, the corresponding predicted performance data is obtained based on the current operating data, the parallel circulating water pump is monitored, and compared with the actual performance data monitored, and the operating status of each water pump is scientifically adjusted according to the results, and the operating parameters of the water pump are optimized, so that the overall operation mode of each water pump and the parallel circulating water pump is more reasonable, while ensuring the working performance, the working efficiency of the parallel circulating water pump is greatly improved, and the overall energy consumption is reduced. In addition, in the process of comparing the actual performance data with the predicted performance data, the corresponding actual performance data is determined based on the repair history data of a preset number of water pumps, and is filtered according to the upper and lower filter limits to remove invalid data. Subsequently, the average value, upper and lower limit parameters of the filtered data set are determined, and finally the threshold range of the comparison results of the actual performance data and the predicted performance data is scientifically determined, so as to accurately judge whether the actual performance is higher or lower than the predicted data, and then reasonably determine the adjustment method of the water pump operation.

[0056] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 A schematic flow chart of a method for monitoring the performance of parallel water pumps according to an embodiment of the present invention is shown;

[0060] Figure 2 A schematic flow chart of a method for cleaning historical operating data of a parallel circulating water pump according to the present invention is shown;

[0061] Figure 3 A schematic flow chart of a method for constructing a performance model of a parallel circulating water pump according to an embodiment of the present invention is shown;

[0062] Figure 4 It shows an empty view of a circulating water pipeline of a thermal power station according to an embodiment of the present invention;

[0063] Figure 5 It shows an axonometric view of a circulating water pump and a circulating water pipeline according to an embodiment of the present invention;

[0064] Figure 6 It shows a layout diagram of some circulating water pipelines in a thermal power station according to one embodiment of the present invention;

[0065] Figure 7 A schematic diagram of QH curve fitting of a parallel circulating water pump according to an embodiment of the present invention is shown;

[0066] Figure 8 A schematic diagram of QP curve fitting of a parallel circulating water pump according to an embodiment of the present invention is shown;

[0067] Fig. 9 A schematic diagram of Q-η curve fitting of a parallel circulating water pump according to an embodiment of the present invention is shown;

[0068] Fig.10 A schematic flow chart of an operation monitoring and optimization method based on a parallel circulating water pump performance model according to an embodiment of the present invention is shown;

[0069] Fig.11 A structural block diagram of a parallel water pump performance monitoring device according to an embodiment of the present invention is shown;

[0070] Fig.12 A schematic structural diagram of a parallel water pump performance monitoring system according to an embodiment of the present invention is shown;

[0071] Fig.13 A schematic diagram of data import of a parallel water pump performance monitoring system according to an embodiment of the present invention is shown;

[0072] Fig.14 A schematic diagram showing results of a parallel water pump performance monitoring system according to an embodiment of the present invention is shown;

[0073] Fig.15 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0074] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0075] Figure 1 A schematic flow chart of a method for monitoring the performance of parallel water pumps according to an embodiment of the present invention is shown, and the method comprises the following steps:

[0076] Step S101, monitoring the parallel circulating water pumps and collecting historical operating data of the parallel circulating water pumps.

[0077] Preferably, the historical operation data at least includes the main pipe inlet pressure, each pump outlet pressure, the total amount of circulating water, each hydraulic coupling scoop pipe opening and / or each motor current.

[0078] Step S102, cleaning the collected historical operation data to obtain repaired historical data.

[0079] Preferably, the data cleaning includes at least: abnormal data detection, abnormal data screening and / or data repair.

[0080] Furthermore, the data repair at least includes: redundant data elimination, erroneous data correction and / or missing data filling.

[0081] Step S103, generating a water pump characteristic curve based on the repair history data, and constructing a parallel circulation water pump performance model.

[0082] Step S104: Based on the current operation data of the parallel circulating water pump, the operation status of the parallel circulating water pump is monitored and optimized using the performance model of the parallel circulating water pump.

[0083] According to the parallel water pump performance monitoring method provided in this embodiment, the parallel circulating water pump is monitored and the historical operation data of the parallel circulating water pump is collected; data cleaning is performed on the collected historical operation data to obtain repaired repair historical data; wherein the data cleaning at least includes: abnormal data detection, data screening and / or data repair; based on the repair historical data, a water pump characteristic curve is generated and a parallel circulating water pump performance model is constructed; based on the current operation data of the parallel circulating water pump, the parallel circulating water pump performance model is used to monitor and optimize the operation status of the parallel circulating water pump. The parallel water pump performance monitoring method provided by the present embodiment monitors the parallel circulating water pumps and collects various operating parameters corresponding to each water pump, thereby realizing comprehensive monitoring and collection of the operating parameters of the parallel circulating water pumps, which is conducive to scientifically and comprehensively determining the operating conditions of the water pumps; by cleaning the collected historical operating data, abnormal data therein is detected and screened for the data used for model construction, and data repair is performed on the abnormal part, which greatly improves the integrity and credibility of the data, and further improves the accuracy of model construction and water pump performance prediction; based on the repaired historical operating data and the installation structure of each water pump, the local resistance coefficient is determined, and according to the calculation formula of the head, a more accurate Determine the dynamic and static head of the water pump, and thus accurately obtain the corresponding characteristic curve according to the flow, power and speed, and then determine the water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model, and scientifically construct the parallel circulating water pump performance model based on this; based on the parallel circulating water pump performance model, monitor and predict the performance of the parallel circulating water pump, and according to the comparison results of the monitoring and predicted data, scientifically adjust the operating status of each water pump, optimize the operating parameters of the water pump, make the overall operation mode of each water pump and the parallel circulating water pump more reasonable, while ensuring the working performance, greatly improve the working efficiency of the parallel circulating water pump, and reduce the overall energy consumption.

[0084] Figure 2 A schematic flow chart of a method for cleaning historical operating data of a parallel circulating water pump according to the present invention is shown;

[0085] like Figure 2 As shown, the method comprises the following steps:

[0086] Step S201: Generate structured monitoring data of a circulating water pump based on historical operation data with the same sampling frequency.

[0087] Preferably, based on the same sampling frequency, each time-series monitoring parameter of the circulating water pump is sampled from the historical operation data z to obtain structured monitoring data of each monitoring parameter within the monitoring period.

[0088]

[0089] Where N is the number of monitoring parameters; T is the length of the monitoring time series; is the monitoring data of each Nth monitoring parameter at time T.

[0090] Step S202: using the 3σ criterion to perform abnormal data detection on the structured monitoring data.

[0091] Specifically, the 3σ criterion for judging abnormal data is based on

[0092] P(|x-μ|>3s)≤0.003

[0093] Among them, x is a certain type of monitoring data; μ is the mean of the corresponding structured monitoring data set; s is the standard deviation of the corresponding structured monitoring data set.

[0094] Step S203: based on the abnormal data detection result, filter and obtain the abnormal data set.

[0095] Preferably, in the structured monitoring data set of monitoring data, data with monitoring sequences at at least both ends that are completely identical or overly similar are treated as redundant data; data caused by interference in sensing, transmission or storage, such as special words or blanks such as null, N / A or 0, are treated as missing data; data that seriously deviates from the sample distribution law or isolated points or clusters in time series are treated as erroneous data.

[0096] Step S204: Based on the LSTM neural network and the SVR algorithm, data repair is performed on the abnormal data set.

[0097] Specifically, the data repair at least includes: redundant data elimination, erroneous data correction and / or missing data filling.

[0098] Preferably, the LSTM neural network determines whether data is retained based on the sigmoid function; updates the cell state through the sigmoid function and the tanh function; after completing the update, based on the weight matrix and bias term of the output gate, combined with the tanh function, determines the next hidden state; and transmits the new cell state and the hidden state.

[0099] According to the above method, the collected historical operating data can be cleaned to detect and screen the abnormal data used for model construction, and then the abnormal part can be repaired based on the LSTM neural network and SVR algorithm, which greatly improves the integrity and credibility of the data, and further improves the accuracy of model construction and water pump performance prediction.

[0100] Figure 3A schematic flow chart of a method for constructing a performance model of a parallel circulating water pump according to an embodiment of the present invention is shown;

[0101] like Figure 3 As shown, the method comprises the following steps:

[0102] Step S301, determining the local resistance coefficient according to the repair history data and the structural parameters of the parallel circulating water pump, and determining the head of the parallel circulating water pump based on the dynamic head and the static head.

[0103] Specifically, the basic expression of lift is

[0104]

[0105] Where, H is the head; H geo is the elevation difference head; ρ is the density; g is the acceleration of gravity; p1 is the inlet pressure; p2 is the outlet pressure; v1 is the inlet flow rate; v2 is the outlet flow rate; H r For friction loss.

[0106] The static head H st for

[0107]

[0108] Dynamic head H dyn for

[0109]

[0110] When the inlet and outlet diameters of the water pump are the same, the dynamic pressure difference between the inlet and outlet can be ignored, and the dynamic head is the friction loss.

[0111]

[0112] Among them, λ is the friction coefficient; l is the length of the pipe section; d is the diameter of the pipe section; v is the flow velocity in the pipe; ξ is the local resistance coefficient.

[0113] According to the structural parameters of the water pump, determine the various structures included in it, such as Figure 4 , 5 , 6 as shown: Figure 4 An empty view of a circulating water pipeline of a thermal power station according to an embodiment of the present invention is shown. Figure 5 The figure shows an axonometric view of a circulating water pump and a circulating water pipeline according to an embodiment of the present invention. Figure 6 The diagram shows the layout of some circulating water pipes in a thermal power station according to an embodiment of the present invention. Further, according to the local resistance coefficient table corresponding to various structures, the corresponding local resistance coefficient is selected according to the structural parameters.

[0114] Preferably, the structure included in the water pump includes at least: curved pipes and elbows, lateral reflux tees, lateral diversion tees, converging or diverting fork tees, straight pipes or lateral branches of converging or diverting oblique tees, reducers, butterfly valves and / or check valves, etc.

[0115] For example, the local resistance coefficient table of a butterfly valve is as follows:

[0116]

[0117] Step S302, based on the head of the parallel circulating water pump, determine the flow rate, input power and rotation speed corresponding thereto, and generate a characteristic curve of the parallel circulating water pump.

[0118] Specifically, the characteristic curve includes at least a QH curve, a QP curve and a Q-η curve.

[0119] Specifically, the flow rate, head and input power corresponding to the target speed are determined according to the proportional relationship between the target speed and the rated speed, combined with the flow rate, head and input power corresponding to the rated speed.

[0120] Based on the obtained flow rate Q, head H, input power P and efficiency η, the corresponding QH curve, QP curve and Q-η curve are obtained;

[0121] Since the operating point of a single water pump is the intersection of the water pump's QH curve and the system resistance curve, it is determined that the operating point of the parallel circulating water pump is located at the intersection of the system resistance curve and the combined QH curve of all operating pumps;

[0122] Among them, for parallel pumps composed of water pumps of the same model, based on the principle of equal head and added flow, the QH curve of the parallel water pumps is obtained;

[0123] For the parallel pumps composed of different types of water pumps, take the parallel pump composed of two water pumps as an example, draw the QH curves of the two water pumps, namely (QH)1 and (QH)2 respectively; then based on the folding characteristic curve method, deduct the inlet and outlet resistance loss curves of the corresponding water pumps from (QωH)1 and (QH)2 to obtain the folding characteristic curves (QH)1′ and (QH)2′; finally, according to the principle of equal head and addition of flow, draw the (QH) of the parallel pump operation 12 Curve, that is, the QH curve of a single equal-duty water pump.

[0124] Step S303, establishing a water pump efficiency model, a water pump power model, a motor efficiency model and a fluid coupling efficiency model.

[0125] Preferably, the pump efficiency is expressed as

[0126]

[0127] Among them, K 机 is the mechanical loss coefficient; K 摩 is the friction loss coefficient; K 冲 is the impact resistance loss coefficient; K 泄 is the leakage loss coefficient; Q0 is the flow rate at the optimal operating point;

[0128] Based on this, a water pump efficiency model is constructed.

[0129] The motor power factor is

[0130]

[0131] in, is the motor power factor; P EM-in is the motor input power; U EM-in is the input voltage; I EM-in is the input current;

[0132] According to the similar characteristics of power factor and motor efficiency change rate, the motor efficiency curve is obtained and the motor efficiency model is constructed.

[0133] The efficiency of the hydraulic coupling is

[0134]

[0135] Among them, η 偶 is the efficiency of the hydraulic coupling; P 出 is the output power of the hydraulic coupling; P 入 is the fluid coupling input power; η 容 is the volumetric efficiency; η 机 is the mechanical efficiency; η 液 is hydraulic efficiency;

[0136] Since, in actual operation, the volume loss and mechanical loss of the hydraulic coupling are very small and can be ignored, the corresponding volumetric efficiency and mechanical efficiency can both be taken as 1;

[0137] Moreover, hydraulic efficiency can be expressed as the ratio of turbine speed to pump speed (i.e., the ratio of output shaft speed to input shaft speed);

[0138] Therefore, the fluid coupling efficiency can be simplified to

[0139]

[0140] Among them, n 出 is the turbine speed; n 入 is the pump impeller speed;

[0141] The efficiency model of the fluid coupling is thus determined.

[0142] The pump power is

[0143]

[0144] The water pump power model is determined accordingly.

[0145] Step S304: Perform polynomial fitting on each characteristic curve of the parallel circulating water pump, and construct a performance model of the parallel circulating water pump accordingly.

[0146] Specifically, based on the degree of the fitting polynomial, a fitting equation of the characteristic curve is determined.

[0147] Preferably, taking the QH curve as an example, the QH curve fitting equation of the water pump is H=Z0+Z1Q+Z2Q 2 +…+Z j Q m

[0148] Wherein, Z is the coefficient; m is the degree of the fitting polynomial; j=1, 2,…, m.

[0149] The matrix form of the fitting equation is

[0150] AZ=B

[0151]

[0152] Solve based on the least squares method to make the fitting equation satisfy

[0153] δ 2 =min|B-AZ| 2

[0154] Where δ is the distance between the fitted curves.

[0155] It follows that

[0156] Z=(A′A) -1 (A′B).

[0157] According to the same principle, polynomial fitting is performed for other characteristic curves, such as Figure 7 , 8 , as shown in 9, Figure 7 A schematic diagram of QH curve fitting of a parallel circulating water pump according to an embodiment of the present invention is shown. Figure 8 A schematic diagram of QP curve fitting of a parallel circulating water pump according to an embodiment of the present invention is shown. Fig. 9 A Q-η curve fitting schematic diagram of a parallel circulating water pump according to an embodiment of the present invention is shown, which will not be described in detail here. Based on the polynomial fitting results, a performance model of a parallel circulating water pump is constructed.

[0158] According to the above method, the local resistance coefficient can be determined based on the historical operating data after repair and the installation structure of each water pump, and the dynamic and static heads of the water pump can be determined more accurately based on the head calculation formula. Therefore, according to the flow rate, power and speed, the corresponding flow-head, power-head and speed-head characteristic curves can be accurately obtained. After further determining the water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model, polynomial fitting is performed, and a parallel circulating water pump performance model is scientifically constructed based on this. The model can be used to accurately predict the performance of the parallel circulating water pump, so as to monitor and reasonably adjust the water pump in the future.

[0159] Fig.10 A schematic flow chart of an operation monitoring and optimization method based on a parallel circulating water pump performance model according to an embodiment of the present invention is shown;

[0160] like Fig.10 As shown, the method comprises the following steps:

[0161] Step S1001, obtaining current operation data of the parallel circulating water pump and determining actual performance data.

[0162] Step S1002: input the current operation data of the parallel circulating water pump into the performance model of the parallel circulating water pump to calculate and obtain predicted performance data.

[0163] Specifically, a preset number of predicted performance data is calculated based on a preset number of repair history data to be used as an initial data set;

[0164] Perform data filtering on the initial data set, and obtain a filtered data set after filtering is completed;

[0165] Calculate upper and lower limit parameters based on the filtered data set;

[0166] Based on the upper limit parameter and the lower limit parameter, a threshold range for comparing the actual performance data with the predicted performance data is determined.

[0167] Preferably, based on the initial data set, the average value of all actual performance data therein is calculated and the upper quartile and lower quartile Based on this, the upper limit up1 and lower limit down1 of filtering the initial data set are determined.

[0168]

[0169] According to the filter upper limit up i Filter the initial data set with the filter lower limit down1 to obtain the filtered data set, and calculate the average value of the filtered data set

[0170]

[0171] Where n′ is the number of actual performance data in the filtered data set, X′ i To filter the actual performance data in the data set;

[0172] Upper limit parameter and lower limit parameters for

[0173]

[0174] in, The number of filtered data sets that is greater than the average value of the filtered data sets The amount of data; The number of filtered data sets that is greater than the average value of the filtered data sets data; The number of filtered data sets that is less than the average value of the filtered data sets The amount of data; The number of filtered data sets that is less than the average value of the filtered data sets data;

[0175] The upper and lower thresholds in the threshold range are

[0176]

[0177] Step S1003, comparing the actual performance data with the predicted performance data to obtain a comparison result.

[0178] Specifically, the threshold range is used as a selection range for predicted performance data, which is then compared with the actual performance data.

[0179] Step S1004: adjusting the operating state of the parallel circulating water pump according to the comparison result.

[0180] Specifically, when the actual performance data is within the threshold range, it is determined that the operation status of the parallel circulating water pump meets the requirements and does not need to be adjusted;

[0181] When the actual performance data is not within the threshold range, it is determined that the operating condition of the parallel circulating water pump meets the requirements and the current performance is poor; based on this, the operating parameters of each water pump are further obtained and the operating parameters of the water pump are adjusted to improve the overall performance of the parallel circulating water pump.

[0182] Preferably, the specific adjustment method can be selected according to actual conditions and is not limited here; for example, the adjustment method is to reduce the flow rate of the single water pump with the highest power by 20%, and correspondingly increase the flow rate of the water pump with a power lower than the overall power of the parallel circulating water pump by 20%.

[0183] According to the above method, the corresponding predicted performance data can be obtained based on the performance model of the parallel circulating water pump and the current operating data, so as to realize the monitoring of the parallel circulating water pump, and compare it with the actual performance data monitored, and adjust the operating state of each water pump scientifically according to the result, optimize the operating parameters of the water pump, make the operation mode of each water pump and the parallel circulating water pump as a whole more reasonable, and greatly improve the working efficiency of the parallel circulating water pump while ensuring the working performance, and reduce the overall power consumption. In addition, in the process of comparing the actual performance data with the predicted performance data, the corresponding actual performance data is determined based on the repair history data of a preset number of water pumps, and filtered according to the upper and lower filter limits to remove invalid data, and then by determining the average value, upper limit parameter and lower limit parameter of the filtered data set, the threshold range of the comparison result of the actual performance data and the predicted performance data is finally scientifically determined, so as to accurately judge whether the actual performance is higher or lower than the predicted data, and then reasonably determine the adjustment method of the water pump operation.

[0184] Fig.11 FIG. 4 shows a structural block diagram of a parallel water pump performance monitoring device according to an embodiment of the present invention. Fig.11 As shown, the device includes: a collection module 1101, a data cleaning module 1102, a model generation module 1103 and an operation optimization module 1104; wherein,

[0185] The acquisition module 1101 is used to monitor the parallel circulating water pump and collect historical operation data of the parallel circulating water pump.

[0186] Preferably, the historical operation data at least includes the main pipe inlet pressure, each pump outlet pressure, the total amount of circulating water, each hydraulic coupling scoop pipe opening and / or each motor current.

[0187] The data cleaning module 1102 is used to clean the collected historical operation data to obtain repaired repair history data.

[0188] Specifically, the data cleaning includes at least: abnormal data detection, abnormal data screening and / or data repair.

[0189] Specifically, the data cleaning module 1102 is further used to:

[0190] Generate structured monitoring data of circulating water pumps based on historical operation data with the same sampling frequency;

[0191] Use the 3σ criterion to detect abnormal data for structured monitoring data;

[0192] Based on the abnormal data detection results, the abnormal data set is screened and obtained;

[0193] Based on LSTM neural network and SVR algorithm, data repair is performed for abnormal data sets;

[0194] The data repair at least includes: redundant data elimination, erroneous data correction and / or missing data filling.

[0195] The model generation module 1103 is used to generate a water pump characteristic curve and construct a parallel circulation water pump performance model based on the repair history data.

[0196] Specifically, the model generation module 1103 is further used to:

[0197] Determine the local resistance coefficient based on the historical repair data and the structural parameters of the parallel circulating water pump, and determine the head of the parallel circulating water pump based on the dynamic head and static head;

[0198] Based on the head of the parallel circulating water pump, the flow rate, input power and speed corresponding thereto are determined, and a characteristic curve of the parallel circulating water pump is generated; wherein the characteristic curve at least includes a QH curve, a QP curve and a Q-η curve;

[0199] Establish water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model;

[0200] Polynomial fitting is performed on each characteristic curve of the parallel circulating water pump, and a performance model of the parallel circulating water pump is constructed based on it.

[0201] The operation optimization module 1104 is used to monitor and optimize the operation status of the parallel circulating water pump based on the current operation data of the parallel circulating water pump and using the performance model of the parallel circulating water pump.

[0202] Specifically, the operation optimization module 1104 is further used to:

[0203] Obtain the current operating data of the parallel circulating water pump and determine the actual performance data;

[0204] Input the current operation data of the parallel circulating water pump into the performance model of the parallel circulating water pump to calculate and obtain the predicted performance data;

[0205] Compare the actual performance data with the predicted performance data to obtain a comparison result;

[0206] Adjust the operating status of the parallel circulating water pump according to the comparison results.

[0207] Preferably, the operation optimization module 1104 is further used to:

[0208] Based on a preset number of historical repair data, a corresponding preset number of predicted performance data is calculated as an initial data set;

[0209] Perform data filtering on the initial data set, and obtain a filtered data set after filtering is completed;

[0210] Calculate upper and lower limit parameters based on the filtered data set;

[0211] Based on the upper limit parameter and the lower limit parameter, a threshold range for comparing the actual performance data with the predicted performance data is determined.

[0212] Preferably, based on the initial data set, the average value of all actual performance data therein is calculated and the upper quartile and lower quartile Based on this, the upper limit up1 and lower limit down1 of filtering the initial data set are determined.

[0213]

[0214] Filter the initial data set according to the filter upper limit up1 and the filter lower limit down1 to obtain the filtered data set, and calculate the average value of the filtered data set

[0215]

[0216] Where n′ is the number of actual performance data in the filtered data set, and X′i is the actual performance data in the filtered data set;

[0217] Upper limit parameter and lower limit parameters for

[0218]

[0219] in, The number of filtered data sets that is greater than the average value of the filtered data sets The amount of data; The number of filtered data sets that is greater than the average value of the filtered data sets data; The number of filtered data sets that is less than the average value of the filtered data sets The amount of data; The number of filtered data sets that is less than the average value of the filtered data sets data;

[0220] The upper and lower thresholds in the threshold range are

[0221]

[0222] The parallel water pump performance monitoring device provided in this embodiment includes:

[0223] An acquisition module, a data cleaning module, a model generation module and an operation optimization module; wherein the acquisition module is used to monitor the parallel circulating water pump and collect the historical operation data of the parallel circulating water pump; the data cleaning module is used to perform data cleaning on the collected historical operation data to obtain the repaired repair history data; wherein data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair; the model generation module is used to generate a water pump characteristic curve based on the repair history data and construct a parallel circulating water pump performance model; the operation optimization module is used to monitor and optimize the operation status of the parallel circulating water pump based on the current operation data of the parallel circulating water pump and using the parallel circulating water pump performance model. The parallel water pump performance monitoring device provided in this embodiment monitors the parallel circulating water pumps and collects various operating parameters corresponding to each water pump, thereby realizing comprehensive monitoring and collection of the operating parameters of the parallel circulating water pumps, which is conducive to scientifically and comprehensively determining the operating conditions of the water pumps; by cleaning the collected historical operating data, the abnormal data therein is detected and screened for the data used for model construction, and then the abnormal part is repaired based on the LSTM neural network and SVR algorithm, which greatly improves the integrity and credibility of the data, and further improves the accuracy of model construction and water pump performance prediction; based on the repaired historical operating data and the installation structure of each water pump, the local resistance coefficient is determined, and according to the calculation formula of the head, the dynamic and static head of the water pump is more accurately determined, and thereby According to the flow rate, power and speed, the corresponding flow-head, power-head and speed-head characteristic curves are accurately obtained. After further determining the water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model, polynomial fitting is performed, and the parallel circulating water pump performance model is scientifically constructed based on this. Based on the parallel circulating water pump performance model, the corresponding predicted performance data is obtained based on the current operating data, and the parallel circulating water pump is monitored. The data is compared with the actual performance data monitored, and the operating status of each water pump is scientifically adjusted according to the results, and the operating parameters of the water pump are optimized, so that the overall operation mode of each water pump and the parallel circulating water pump is more reasonable. While ensuring the working performance, the working efficiency of the parallel circulating water pump is greatly improved and the overall energy consumption is reduced. In addition, in the process of comparing the actual performance data with the predicted performance data, the corresponding actual performance data is determined based on the repair history data of a preset number of water pumps, and is filtered according to the upper and lower filter limits to remove invalid data. Subsequently, the average value, upper and lower limit parameters of the filtered data set are determined, and finally the threshold range of the comparison results of the actual performance data and the predicted performance data is scientifically determined, so as to accurately judge whether the actual performance is higher or lower than the predicted data, and then reasonably determine the adjustment method of the water pump operation.

[0224] The present invention also provides a parallel water pump performance monitoring system, wherein the system executable instructions can execute the parallel water pump performance monitoring method in any of the above method embodiments, such as Fig.12 As shown, Fig.12 The schematic diagram of the structure of a parallel pump performance monitoring system according to an embodiment of the present invention is shown. The system comprises: a data import unit 1201, a performance calculation unit 1202 and a result display unit 1203;

[0225] The data import unit 1202 is used to import historical operation data and / or current operation data corresponding to the data import instruction into the system in response to the user's data import instruction.

[0226] The performance calculation unit 1202 is used to calculate corresponding predicted performance data based on the imported current operation data using the parallel circulating water pump performance model.

[0227] Preferably, the program for calculating various performance parameters of the water pump in the performance calculation unit 1202 is written by modularly compiling a program in Python.

[0228] The result display unit 1203 is used to display the obtained predicted performance data to the user terminal and provide a corresponding water pump operation status adjustment method.

[0229] The parallel water pump performance monitoring system further includes a control unit 1204;

[0230] The control unit 1204 is used to select a system function in response to a user's control signal.

[0231] The user's control signal may be different signals for various terminals, such as click, touch, etc., which are not limited here.

[0232] Furthermore, the parallel pump performance monitoring system has the following styles when importing data and outputting results: Fig.13 , 14 shown. Fig.13 A schematic diagram of data import of a parallel water pump performance monitoring system according to an embodiment of the present invention is shown; Fig.14 A schematic diagram showing results of a parallel water pump performance monitoring system according to an embodiment of the present invention is shown.

[0233] Fig.15 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0234] like Fig.15As shown, the computing device may include: a processor (processor) 1502 , a communication interface (Communications Interface) 1504 , a memory (memory) 1506 , and a communication bus 1508 .

[0235] in:

[0236] The processor 1502 , the communication interface 1504 , and the memory 1506 communicate with each other via a communication bus 1508 .

[0237] The communication interface 1504 is used to communicate with other devices such as clients or other servers.

[0238] The processor 1502 is used to execute the program 1510, and specifically can execute the relevant steps in the above-mentioned embodiment of the parallel water pump performance monitoring method.

[0239] Specifically, the program 1510 may include program code, which includes computer operation instructions.

[0240] The processor 1502 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0241] The memory 1506 is used to store the program 1510. The memory 1506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0242] Program 1510 can be specifically used to enable processor 1502 to execute a parallel water pump performance monitoring method in any of the above method embodiments. The specific implementation of each step in program 1510 can refer to the corresponding descriptions in the corresponding steps and units in the above parallel water pump performance monitoring method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described equipment and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0243] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0244] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0245] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0246] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0247] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0248] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0249] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring the performance of parallel water pumps, comprising: Monitor the parallel circulating water pumps and collect historical operation data of the parallel circulating water pumps; Performing data cleaning on the collected historical operation data to obtain repaired historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair; Generate water pump characteristic curve based on historical repair data and build parallel circulation water pump performance model; Based on the current operating data of the parallel circulating water pump, the parallel circulating water pump performance model is used to monitor and optimize the operating status of the parallel circulating water pump.

2. The method according to claim 1, characterized in that The monitoring of the parallel circulating water pumps and the collection of historical operating data of the parallel circulating water pumps further include: The historical operation data at least include the main pipe inlet pressure, each pump outlet pressure, the total amount of circulating water, each hydraulic coupling scoop pipe opening and / or each motor current.

3. The method according to claim 1, characterized in that The data cleaning is performed on the collected historical operation data to obtain the repaired repair historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair, and further includes: Generate structured monitoring data of circulating water pumps based on historical operation data with the same sampling frequency; Use the 3σ criterion to detect abnormal data for structured monitoring data; Based on the abnormal data detection results, the abnormal data set is screened and obtained; Based on LSTM neural network and SVR algorithm, data repair is performed for abnormal data sets; The data repair at least includes: redundant data elimination, erroneous data correction and / or missing data filling.

4. The method according to claim 1, characterized in that: The method of generating a water pump characteristic curve and constructing a parallel circulating water pump performance model based on the repair history data further includes: Determine the local resistance coefficient based on the historical repair data and the structural parameters of the parallel circulating water pump, and determine the head of the parallel circulating water pump based on the dynamic head and static head; Based on the head of the parallel circulating water pump, the flow rate, input power and speed corresponding thereto are determined, and a characteristic curve of the parallel circulating water pump is generated; wherein the characteristic curve at least includes a QH curve, a QP curve and a Q-η curve; Establish water pump efficiency model, water pump power model, motor efficiency model and hydraulic coupling efficiency model; Polynomial fitting is performed on each characteristic curve of the parallel circulating water pump, and a performance model of the parallel circulating water pump is constructed based on it.

5. The method according to claim 1, characterized in that The method of monitoring and optimizing the operating state of the parallel circulating water pump using the parallel circulating water pump performance model based on the current operating data of the parallel circulating water pump further includes: Obtain the current operating data of the parallel circulating water pump and determine the actual performance data; Input the current operation data of the parallel circulating water pump into the performance model of the parallel circulating water pump to calculate and obtain the predicted performance data; Compare the actual performance data with the predicted performance data to obtain a comparison result; Adjust the operating status of the parallel circulating water pump according to the comparison results.

6. The method according to claim 5, characterized in that The comparing the actual performance data with the predicted performance data to obtain a comparison result further includes: Based on a preset number of historical repair data, a corresponding preset number of predicted performance data is calculated as an initial data set; Perform data filtering on the initial data set, and obtain a filtered data set after filtering is completed; Calculate upper and lower limit parameters based on the filtered data set; Based on the upper limit parameter and the lower limit parameter, a threshold range for comparing the actual performance data with the predicted performance data is determined.

7. The method according to claim 6, characterized in that The method further comprises: Based on the initial data set, calculate the average value of all actual performance data in it and the upper quartile and lower quartile Based on this, the upper limit up1 and lower limit down1 of filtering the initial data set are determined. Filter the initial data set according to the filter upper limit up1 and the filter lower limit down1 to obtain the filtered data set, and calculate the average value of the filtered data set Where n′ is the number of actual performance data in the filtered data set, X′ i To filter the actual performance data in the data set; Upper limit parameter and lower limit parameters for in, The number of filtered data sets that is greater than the average value of the filtered data sets The amount of data; The number of filtered data sets that is greater than the average value of the filtered data sets data; The number of filtered data sets that is less than the average value of the filtered data sets The amount of data; The number of filtered data sets that is less than the average value of the filtered data sets data; The upper and lower thresholds in the threshold range are 8. A parallel water pump performance monitoring device, comprising: Acquisition module, data cleaning module, model generation module and operation optimization module; among them, The acquisition module is used to monitor the parallel circulating water pump and collect historical operation data of the parallel circulating water pump; The data cleaning module is used to clean the collected historical operation data to obtain the repaired historical data; wherein the data cleaning at least includes: abnormal data detection, abnormal data screening and / or data repair; The model generation module is used to generate a water pump characteristic curve and construct a parallel circulation water pump performance model based on the repair history data; The operation optimization module is used to monitor and optimize the operation status of the parallel circulating water pump based on the current operation data of the parallel circulating water pump and using the parallel circulating water pump performance model.

9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to a parallel water pump performance monitoring method as described in any one of claims 1-7.

10. A parallel water pump performance monitoring system, the system performing operations corresponding to a parallel water pump performance monitoring method according to any one of claims 1 to 7, at least comprising: Data import unit, performance calculation unit and result display unit; among them, The data import unit is used to respond to a data import instruction of a user and import the historical operation data and / or current operation data corresponding to the data import instruction into the system; The performance calculation unit is used to calculate corresponding predicted performance data based on the imported current operation data using the parallel circulating water pump performance model; The result display unit is used to display the obtained predicted performance data to the user terminal and provide a corresponding water pump operation status adjustment method.

Images