A reservoir pump station water pump automatic control system and control method thereof

Abstract

The present invention provides a reservoir pump station water pump automatic control system and a control method thereof, which relate to the field of water pump control, wherein the system comprises: an information acquisition module, which is used to acquire relevant information of a to-be-irrigated area; a pipeline planning module, which is used to determine an optimal pipeline distribution scheme based on the relevant information of the to-be-irrigated area; a pipeline setting module, which is used to set a plurality of main pipelines, branch pipelines and emergency pipelines based on the optimal pipeline distribution scheme; a state monitoring module, which is used to acquire real-time state information of a water pump on a main pipeline, real-time state information of each main pipeline, real-time state information of each branch pipeline and real-time soil moisture information of the to-be-irrigated area; and a water pump control module, which is used to generate an optimal control scheme to control irrigation work based on the real-time state information of the water pump on the main pipeline, real-time state information of each main pipeline, real-time state information of each branch pipeline and real-time soil moisture information of the to-be-irrigated area, and has the advantage of improving the control accuracy of a water pump in a reservoir pump station.

Description

Technical Field

[0001] The invention relates to the field of water pump control, and in particular to an automatic control system for water pumps in a reservoir pump station and a control method thereof. Background Art

[0002] At present, the uneven temporal and spatial distribution of water resources has restricted the economic and social development of many regions. For areas without sufficient irrigation, when the total annual available water resources are insufficient, the goal is to maximize the comprehensive benefits of water use, strengthen the unified scheduling and management of regional water resources, and use and adjust the water conservancy projects of the irrigation system as a unified whole. The use of existing projects, such as joint scheduling and operation of reservoirs and pumping stations, to enable them to play a greater role is the main way to solve the water shortage problem in irrigation areas.

[0003] The existing irrigation method mainly leads multiple main pipes from the reservoir, and then leads multiple branch pipes from each main pipe, and uses the branch pipes to lead irrigation water to the farmland. In order to facilitate control, a water pump is generally installed on each main pipe, and then the water supply of the pipeline is controlled by wireless transmission to achieve automatic irrigation. Generally, there are more than a dozen main pipes leading from a small reservoir, and more than dozens of main pipes leading from a large reservoir. The control of the water pump is only to control the amount of water required for irrigation, and the satisfaction of crop irrigation needs is relatively low.

[0004] Therefore, it is necessary to provide a reservoir booster water pump automatic control system and a control method thereof, so as to improve the control accuracy of the reservoir pump station water pump and improve the intelligence and effectiveness of crop irrigation. Summary of the invention

[0005] The present invention provides a reservoir pump station water pump automatic control system, comprising: an information acquisition module, used for acquiring relevant information of an area to be irrigated; a pipeline planning module, used for determining an optimal pipeline distribution scheme based on the relevant information of the area to be irrigated, wherein the optimal pipeline distribution scheme includes pipeline topological structure information; a pipeline setting module, used for setting a plurality of main pipelines, a plurality of branch pipelines and a plurality of emergency pipelines in the area to be irrigated based on the optimal pipeline distribution scheme, wherein a water pump is installed on the main pipeline, and the emergency pipeline is used to connect two main pipelines; a state monitoring module, used for acquiring real-time state information of the water pump on the main pipeline, real-time state information of each main pipeline, real-time state information of each branch pipeline and real-time soil moisture information of the area to be irrigated; a water pump control module, used for generating an optimal control scheme based on the real-time state information of the water pump on the main pipeline, real-time state information of each main pipeline, real-time state information of each branch pipeline and real-time soil moisture information of the area to be irrigated, and controlling the water pump on the main pipeline to perform irrigation based on the optimal control scheme.

[0006] Furthermore, the relevant information of the area to be irrigated includes at least historical irrigation records of multiple locations; the pipeline planning module determines the optimal pipeline distribution plan based on the relevant information of the area to be irrigated, including: determining the irrigation correlation between any two locations based on the historical irrigation records of the multiple locations; clustering the multiple locations based on the irrigation correlation between any two locations to determine the multiple sub-irrigation areas included in the area to be irrigated; determining a plurality of candidate pipeline distribution plans based on the multiple sub-irrigation areas included in the area to be irrigated through a plan generation model; establishing an irrigation simulation model; and screening the multiple candidate pipeline distribution plans based on the irrigation simulation model to determine the optimal pipeline distribution plan.

[0007] Furthermore, the pipeline planning module determines the irrigation relevance between any two locations based on the historical irrigation records of the multiple locations, including: determining the irrigation relevance between any two locations according to the following formula: Among them, C (i,j) is the irrigation correlation between the i-th position and the j-th position, K is the preset normalization parameter, K>0, R (i,t) is the irrigation amount of the i-th location at the t-th time point, R (j,t) is the irrigation amount of the jth position at the tth time point, and T is the total number of historical time points; the pipeline planning module clusters the multiple positions based on the irrigation correlation between any two positions to determine the multiple sub-irrigation areas included in the area to be irrigated, including: performing a first clustering of the multiple positions based on the distance between any two positions using the k-means clustering algorithm to determine a plurality of position clustering clusters; for each of the position clustering clusters, performing a second clustering of the multiple positions included in the position clustering cluster using the k-means clustering algorithm based on the irrigation correlation between any two positions included in the position clustering cluster to determine the sub-irrigation area corresponding to the position clustering cluster.

[0008] Furthermore, the pipeline planning module screens the multiple candidate pipeline distribution schemes based on the irrigation simulation model to determine the optimal pipeline distribution scheme, including: determining the irrigation demand of each of the sub-irrigation areas at different time nodes based on the historical irrigation records of the multiple locations; determining multiple irrigation simulation demand scenarios based on the irrigation demand of each of the sub-irrigation areas at different time nodes; for each of the candidate pipeline distribution schemes, determining the water pump operating parameters under each of the irrigation simulation demand scenarios based on the irrigation simulation model, and determining the scheme matching score corresponding to the candidate pipeline distribution scheme based on the water pump operating parameters under each of the irrigation simulation demand scenarios and multiple evaluation indicators; based on the scheme matching score corresponding to each of the candidate pipeline distribution schemes, screening the multiple candidate pipeline distribution schemes to determine the optimal pipeline distribution scheme.

[0009] Furthermore, the pipeline planning module determines the scheme matching score corresponding to the candidate pipeline distribution scheme based on the water pump operating parameters and multiple evaluation indicators in each of the irrigation simulation demand scenarios, including: determining the weights corresponding to the multiple evaluation indicators based on the entropy method; determining the scores of the candidate pipeline distribution scheme in the multiple evaluation indicators based on the water pump operating parameters in each of the irrigation simulation demand scenarios; determining the scheme matching score corresponding to the candidate pipeline distribution scheme based on the scores of the candidate pipeline distribution scheme in the multiple evaluation indicators and the weights corresponding to the multiple evaluation indicators.

[0010] Furthermore, the status monitoring module includes a water pump monitoring unit, a main pipeline monitoring unit, a branch pipeline monitoring unit, a soil moisture detection unit and an edge computing unit, wherein the water pump monitoring unit is used to collect real-time operation information of the water pump on the main pipeline, the main pipeline monitoring unit is used to collect real-time operation information of the main pipeline, the branch pipeline monitoring unit is used to collect real-time operation information of the branch pipeline, and the soil moisture detection unit is used to collect soil moisture information of the multiple sub-irrigation areas; the edge computing unit is used to determine the real-time status information of the water pump on the main pipeline based on the collected real-time operation information of the water pump on the main pipeline; the edge computing unit is also used to determine the real-time status information of each of the main pipelines based on the collected real-time operation information of the main pipeline; the edge computing unit is also used to determine the real-time status information of each of the branch pipelines based on the collected real-time operation information of the branch pipelines; the edge computing unit is also used to determine the real-time soil moisture information of the area to be irrigated based on the collected soil moisture information of the multiple sub-irrigation areas.

[0011] Further, the water pump monitoring unit includes multiple water pump monitoring devices, one water pump corresponds to one water pump, and the water pump monitoring device at least includes an inlet flow rate monitoring component, an outlet flow rate monitoring component, a vibration monitoring component, a sound monitoring component and a temperature monitoring component; the main pipeline monitoring unit includes multiple main pipeline monitoring devices, one main pipeline corresponds to one main pipeline, and the main pipeline monitoring device includes multiple main pipeline flow rate monitoring components; the branch pipeline monitoring unit includes multiple branch pipeline monitoring devices, one branch pipeline corresponds to one branch pipeline, and the branch pipeline monitoring device includes multiple branch pipeline flow rate monitoring components; the soil moisture detection unit includes at least one soil moisture detection device, one soil moisture detection device corresponds to one sub-irrigation area, and the soil moisture detection device includes multiple soil moisture sensors.

[0012] Furthermore, a first valve is provided on the main pipeline, a second valve is provided on the branch pipeline, and a third valve is provided on the emergency pipeline; the water pump control module generates an optimal control scheme based on the real-time status information of the water pump on the main pipeline, the real-time status information of each of the main pipelines, the real-time status information of each of the branch pipelines and the real-time soil moisture information of the area to be irrigated, including: judging whether to irrigate based on the irrigation demand of each of the sub-irrigation areas corresponding to different time nodes and the real-time soil moisture information of the area to be irrigated; when it is judged to irrigate, determining the real-time operating parameters of multiple water pumps, the status of the first valve, the status of the second valve and the status of the third valve based on the real-time status information of the water pump on the main pipeline, the real-time status information of each of the main pipelines and the real-time status information of each of the branch pipelines.

[0013] Furthermore, the water pump control module determines the real-time operating parameters of multiple water pumps, the state of the first valve, the state of the second valve, and the state of the third valve based on the real-time status information of the water pumps on the main pipeline, the real-time status information of each of the main pipelines, and the real-time status information of each of the branch pipelines, including: determining multiple preset operating states based on the optimal pipeline distribution plan; determining the optimal control plan corresponding to each of the preset operating states based on the irrigation simulation model; determining the current operating state based on the real-time status information of the water pumps on the main pipeline, the real-time status information of each of the main pipelines, and the real-time status information of each of the branch pipelines; calculating the state similarity between the current operating state and each of the preset operating states, determining the target preset operating state from the multiple preset operating states, and determining the real-time operating parameters of multiple water pumps, the state of the first valve, the state of the second valve, and the state of the third valve based on the optimal control plan corresponding to the target preset operating state.

[0014] The present invention provides a method for automatically controlling a water pump in a reservoir pump station, comprising: obtaining relevant information of an area to be irrigated; determining an optimal pipeline distribution scheme based on the relevant information of the area to be irrigated, wherein the optimal pipeline distribution scheme includes pipeline topological structure information; arranging a plurality of main pipelines, a plurality of branch pipelines and a plurality of emergency pipelines in the area to be irrigated based on the optimal pipeline distribution scheme, wherein a water pump is installed on the main pipeline, and the emergency pipeline is used to connect two main pipelines; obtaining real-time status information of the water pump on the main pipeline, real-time status information of each main pipeline, real-time status information of each branch pipeline and real-time soil moisture information of the area to be irrigated; generating an optimal control scheme based on the real-time status information of the water pump on the main pipeline, real-time status information of each main pipeline, real-time status information of each branch pipeline and real-time soil moisture information of the area to be irrigated; and controlling the water pump on the main pipeline to perform irrigation based on the optimal control scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0016] Figure 1 It is a module schematic diagram of a reservoir pump station water pump automatic control system according to some embodiments of this specification;

[0017] Figure 2 is a schematic diagram of a process for determining an optimal pipeline distribution scheme according to some embodiments of this specification;

[0018] Figure 3 It is a flow chart of a method for automatically controlling a water pump in a reservoir pump station according to some embodiments of this specification. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0020] Figure 1 is a schematic diagram of a module of a reservoir pump station water pump automatic control system according to some embodiments of this specification, such as Figure 1 As shown, a reservoir pump station water pump automatic control system may include an information acquisition module, a pipeline planning module, a pipeline setting module, a status monitoring module and a water pump control module.

[0021] The information acquisition module can be used to obtain relevant information of the area to be irrigated.

[0022] In some embodiments, the relevant information of the area to be irrigated includes at least historical irrigation records of multiple locations, including the varieties of crops planted at different locations in the area to be irrigated and the irrigation amounts corresponding to different growth states.

[0023] The pipeline planning module can be used to determine the optimal pipeline distribution plan based on relevant information of the area to be irrigated.

[0024] Among them, the optimal pipeline distribution plan includes pipeline topology information, specifically including the number and location of main pipelines, the number and location of branch pipelines, the number and location of emergency pipelines, the connection relationship between branch pipelines and main pipelines, and the connection relationship between emergency pipelines and main pipelines.

[0025] Figure 2 is a flow chart of determining the optimal pipeline distribution scheme according to some embodiments of this specification, such as Figure 2 As shown, in some embodiments, the pipeline planning module determines the optimal pipeline distribution plan based on relevant information of the area to be irrigated, including:

[0026] Determine the irrigation correlation between any two locations based on historical irrigation records at multiple locations;

[0027] Based on the irrigation correlation between any two locations, multiple locations are clustered to determine multiple sub-irrigation areas included in the area to be irrigated;

[0028] Determine multiple candidate pipeline distribution schemes based on multiple sub-irrigation areas included in the area to be irrigated through a scheme generation model;

[0029] Establishing an irrigation simulation model, wherein the irrigation simulation model may be a mathematical model;

[0030] Based on the irrigation simulation model, multiple candidate pipeline distribution schemes are screened to determine the optimal pipeline distribution scheme.

[0031] In some embodiments, the pipeline planning module can determine the irrigation relevance between any two locations according to the following formula:

[0032]

[0033] Among them, C (i,j) is the irrigation correlation between the i-th position and the j-th position, K is the preset normalization parameter, K>0, R (i,t) is the irrigation amount of the i-th location at the t-th time point, R (j,t) is the irrigation amount of the jth location at the tth time point, and T is the total number of historical time points.

[0034] The pipeline planning module can build an irrigation simulation model through the following process:

[0035] (1) Select variables. Variables refer to quantities that need to be selected or determined to establish an irrigation simulation model. In the linear and nonlinear programming mathematical models of irrigation systems, they are called decision (design) variables. In planning and design problems, irrigation area, irrigation reservoir capacity, percentage of crop types, channel water delivery capacity, installed capacity of irrigation stations, inner diameter of sprinkler and drip irrigation pipes, etc. are often used as variables; in management and operation problems, the amount of water released by the reservoir during a period, the amount of water delivered by branch and ditches during a period, the area of ​​crop planted in the irrigation area, the percentage of crop planted, etc. are often used as variables. In the dynamic programming mathematical model of the irrigation system, since the irrigation problem under study needs to be transformed into a multi-stage decision-making process, there are three types of variables in the model: stage variables, state variables, and decision variables. In irrigation planning and design projects, the project types, such as reservoirs, pumping stations, water intake gates or irrigation areas, and crop varieties can generally be used as stage variables, reservoir water level, water storage capacity, effective water supply to crops, number of pumping station units in operation, etc. can be used as state variables, and flow or water volume can be used as decision variables; in irrigation management and operation projects, years, months or ten days are often used as stage variables, and the selection of state variables and decision variables is related to the planning and design types.

[0036] (2) The objective function can be to maximize the average operating energy efficiency of each water supply pump station or minimize the total power consumption of the pump station during the scheduling period.

[0037] (3) Constraints, including: water balance constraints of irrigation reservoirs (including surface reservoirs or underground reservoirs); reservoir discharge volume (or downstream flood control conditions); irrigation area boundary constraints; channel water delivery capacity constraints; irrigation water volume or crop water use time constraints; groundwater balance constraints in well irrigation areas; policy constraints; construction funds and labor constraints, etc.

[0038] (4) Write the expression of the objective function using the optimization criterion proposed by RE Bellman, and write the boundary conditions such as the system method, constraints and recursive equations. The system equation can often be reflected based on the mutual constraints between state variables and decision variables and hydraulic conditions, for example, the water balance equation.

[0039] In some embodiments, the pipeline planning module clusters multiple locations based on the irrigation association between any two locations, and determines multiple sub-irrigation areas included in the area to be irrigated, including:

[0040] Using the k-means clustering algorithm, multiple locations are clustered for the first time based on the distance between any two locations to determine multiple location clusters;

[0041] For each location cluster, a k-means clustering algorithm is used to perform a second clustering on multiple locations included in the location cluster based on the irrigation association between any two locations included in the location cluster, and the sub-irrigation area corresponding to the location cluster is determined.

[0042] The pipeline setting module can be used to set up multiple main pipelines, multiple branch pipelines and multiple emergency pipelines in the area to be irrigated based on the optimal pipeline distribution plan, wherein a water pump is installed on the main pipeline, and the emergency pipeline is used to connect two main pipelines. A first valve is set on the main pipeline, a second valve is set on the branch pipeline, and a third valve is set on the emergency pipeline.

[0043] In some embodiments, the pipeline planning module screens multiple candidate pipeline distribution schemes based on the irrigation simulation model to determine the optimal pipeline distribution scheme, including:

[0044] Based on historical irrigation records at multiple locations, determine the irrigation needs of each sub-irrigation area at different time points;

[0045] Based on the irrigation demand of each sub-irrigation area corresponding to different time nodes, multiple irrigation simulation demand scenarios are determined, wherein the irrigation simulation demand scenario may include the irrigation demand of each sub-irrigation area within the same simulation time period. It can be understood that the irrigation demand of the same sub-irrigation area may be different under different irrigation simulation demand scenarios;

[0046] For each candidate pipeline distribution scheme, based on the irrigation simulation model, the water pump operating parameters under each irrigation simulation demand scenario are determined, and based on the water pump operating parameters under each irrigation simulation demand scenario and multiple evaluation indicators, the scheme matching score corresponding to the candidate pipeline distribution scheme is determined;

[0047] Based on the scheme matching score corresponding to each candidate pipeline distribution scheme, multiple candidate pipeline distribution schemes are screened to determine the optimal pipeline distribution scheme. For example, the candidate pipeline distribution scheme with the largest scheme matching score is taken as the optimal pipeline distribution scheme.

[0048] Evaluation indicators may include water pump operating load indicators, energy consumption indicators, irrigation coverage indicators, etc.

[0049] In some embodiments, the pipeline planning module determines the scheme matching score corresponding to the candidate pipeline distribution scheme based on the water pump operating parameters and multiple evaluation indicators in each irrigation simulation demand scenario, including:

[0050] Based on the entropy method, the weights corresponding to multiple evaluation indicators are determined;

[0051] Based on the pump operating parameters under each irrigation simulation demand scenario, determine the scores of candidate pipeline distribution schemes in multiple evaluation indicators;

[0052] Based on the scores of the candidate pipeline distribution scheme in multiple evaluation indicators and the weights corresponding to the multiple evaluation indicators, a scheme matching score corresponding to the candidate pipeline distribution scheme is determined.

[0053] In some embodiments, the pipeline planning module may calculate the score of the candidate pipeline distribution scheme in the operating load index based on the following formula:

[0054]

[0055] Among them, S (g,load) is the score of the g-th candidate pipeline distribution scheme in the operating load index, K2 is the preset normalization parameter, K2>0, L (e,f) is the operating load of the f-th water pump under the e-th irrigation simulation demand scenario corresponding to the g-th candidate pipeline distribution scheme, L presets is the preset operating load, F is the total number of irrigation simulation demand scenarios, and F is the total number of water pumps corresponding to the g-th candidate pipeline distribution scheme.

[0056] The pipeline planning module can calculate the energy consumption index score of the candidate pipeline distribution scheme based on the following formula:

[0057]

[0058] Among them, S (g,energy) is the score of the g-th candidate pipeline distribution scheme in the energy consumption index, K3 is the preset normalization parameter, K3>0, C (e,f) is the energy consumption of the f-th water pump under the e-th irrigation simulation demand scenario corresponding to the g-th candidate pipeline distribution scheme.

[0059] The pipeline planning module can calculate the score of the candidate pipeline distribution scheme in the irrigation coverage index based on the following formula:

[0060]

[0061] Among them, S (g,coverage) is the score of the g-th candidate pipeline distribution scheme in the irrigation coverage index, R e is the irrigation coverage rate of the g-th candidate pipeline distribution scheme under the e-th irrigation simulation demand scenario, K4 is the preset normalization parameter, K4>0.

[0062] The pipeline planning module can perform weighted summation of the scores of the candidate pipeline distribution schemes in multiple evaluation indicators based on the weights corresponding to the multiple evaluation indicators, and determine the scheme matching score corresponding to the candidate pipeline distribution scheme.

[0063] The status monitoring module can be used to obtain the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline, the real-time status information of each branch pipeline and the real-time soil moisture information of the area to be irrigated.

[0064] In some embodiments, the state monitoring module includes a water pump monitoring unit, a main pipeline monitoring unit, a branch pipeline monitoring unit, a soil moisture detection unit and an edge computing unit, wherein the water pump monitoring unit is used to collect real-time operation information of the water pump on the main pipeline, the main pipeline monitoring unit is used to collect real-time operation information of the main pipeline, the branch pipeline monitoring unit is used to collect real-time operation information of the branch pipeline, and the soil moisture detection unit is used to collect soil moisture information of multiple sub-irrigation areas;

[0065] The edge computing unit is used to determine the real-time status information of the water pump on the main pipeline based on the real-time operation information of the water pump on the main pipeline. The edge computing unit is also used to determine the real-time status information of each main pipeline based on the real-time operation information of the main pipeline. The edge computing unit is also used to determine the real-time status information of each branch pipeline based on the real-time operation information of the branch pipeline. The edge computing unit is also used to determine the real-time soil moisture information of the area to be irrigated based on the soil moisture information of multiple sub-irrigation areas collected.

[0066] In some embodiments, the water pump monitoring unit includes a plurality of water pump monitoring devices, one water pump corresponds to one water pump monitoring device, and the water pump monitoring device includes at least a water inlet flow rate monitoring component, a water outlet flow rate monitoring component, a vibration monitoring component, a sound monitoring component, and a temperature monitoring component;

[0067] The main pipeline monitoring unit includes a plurality of main pipeline monitoring devices, one main pipeline corresponds to one main pipeline monitoring device, and the main pipeline monitoring device includes a plurality of main pipeline flow rate monitoring components;

[0068] The branch pipeline monitoring unit includes a plurality of branch pipeline monitoring devices, one branch pipeline corresponds to one branch pipeline monitoring device, and the branch pipeline monitoring device includes a plurality of branch pipeline flow rate monitoring components;

[0069] The soil moisture detection unit includes at least one soil moisture detection device, one sub-irrigation area corresponds to one soil moisture detection device, and the soil moisture detection device includes a plurality of soil moisture sensors.

[0070] Specifically, the edge computing unit can determine the real-time status information of the water pump on the main pipeline based on the collected real-time operation information of the water pump on the main pipeline through a long time series prediction algorithm, determine the real-time status information of each main pipeline based on the collected real-time operation information of the main pipeline, determine the real-time status information of each branch pipeline based on the collected real-time operation information of the branch pipeline, and determine the real-time soil moisture information of the area to be irrigated based on the collected soil moisture information of multiple sub-irrigation areas.

[0071] Taking the determination of the real-time status information of the water pump on the main pipeline as an example, the real-time status information of the water pump on the main pipeline can be determined based on the collected real-time operation information of the water pump on the main pipeline by using a long time series prediction algorithm, which can include the following steps:

[0072] S1: Acquire the real-time status information of the water pump on the sample main pipeline to form an original data set, wherein the real-time status information may include the water inlet flow rate, water outlet flow rate, vibration amplitude, sound intensity and temperature of the water pump.

[0073] S2: Perform data integration and data preprocessing on the original data set according to the time series characteristics to construct a time series data set. Data integration and processing include: arranging data in time series order, deduplication, data supplementation, data normalization and other processing.

[0074] S3: Divide the time series dataset into training dataset, validation dataset and test dataset.

[0075] S4: The real-time status information of the water pump within a certain historical time series range corresponding to the training data set is used as input information, and the real-time status of the water pump within a certain future time series is used as output information to train the long time series prediction model.

[0076] Long time series prediction model training includes: building a long time series prediction model, setting multiple feature variable inputs to predict a single feature output mode, setting the number of encoders and decoders, setting the number of input sequences, label sequences, and output sequences, setting the number of iterations, the number of batches, the conditions for ending training early, setting the time series interval, and selecting the loss function.

[0077] S5: The real-time status information of the water pump corresponding to the verification data set is input into the trained model, and the loss function of the verification data set is calculated. The loss function is used as a measurement standard, and the optimal model is obtained through repeated iterations.

[0078] S6: Input the real-time status information of the water pump corresponding to the test data set into the long time series prediction model to obtain the test result, that is, the prediction result of the water pump on the main pipeline within a certain time series range in the future.

[0079] The water pump control module can be used to generate an optimal control plan based on the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline, the real-time status information of each branch pipeline and the real-time soil moisture information of the area to be irrigated, and control the water pump on the main pipeline to perform irrigation work based on the optimal control plan.

[0080] In some embodiments, the water pump control module generates an optimal control scheme based on the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline, the real-time status information of each branch pipeline, and the real-time soil moisture information of the area to be irrigated, including:

[0081] Based on the irrigation demand of each sub-irrigation area at different time nodes and the real-time soil moisture information of the area to be irrigated, it is determined whether irrigation should be carried out. For example, if the current soil moisture of a sub-area or the predicted soil moisture in the future target time period is less than the soil moisture threshold corresponding to the current crop growth state of the sub-area and there will be no rainfall in the area to be irrigated in the future target time period, it is determined that irrigation is needed;

[0082] When it is determined to carry out irrigation, the real-time operating parameters of multiple water pumps, the status of the first valve, the status of the second valve and the status of the third valve are determined based on the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline and the real-time status information of each branch pipeline.

[0083] In some embodiments, the water pump control module determines the real-time operating parameters of the plurality of water pumps, the state of the first valve, the state of the second valve, and the state of the third valve based on the real-time state information of the water pump on the main pipeline, the real-time state information of each main pipeline, and the real-time state information of each branch pipeline, including:

[0084] Based on the optimal pipeline distribution plan, a plurality of preset operating states are determined, wherein the preset operating states may include the state of the water pump (e.g., normal, faulty, etc.), the state of the main pipeline (e.g., normal, damaged, etc.), and the state of the branch pipeline (e.g., normal, damaged, etc.);

[0085] Based on the irrigation simulation model, determining an optimal control scheme corresponding to each preset operating state, wherein the optimal control scheme may include real-time operating parameters of multiple water pumps, a state of a first valve, a state of a second valve, and a state of a third valve;

[0086] Determine the current operation status based on the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline and the real-time status information of each branch pipeline;

[0087] The state similarity between the current operating state and each preset operating state is calculated, a target preset operating state is determined from multiple preset operating states, and the real-time operating parameters of multiple water pumps, the state of the first valve, the state of the second valve, and the state of the third valve are determined based on the optimal control scheme corresponding to the target preset operating state.

[0088] Specifically, for each preset operating state, multiple valve control schemes can be determined, wherein the valve control scheme may include the state of the first valve, the state of the second valve and the state of the third valve. Through the irrigation simulation model, the operating parameters of the water pump under each valve control scheme are determined. According to the operating parameters of the water pump, the score of the valve control scheme in the operating load index, energy consumption index and irrigation coverage index of the water pump is determined, and the priority score of the valve control scheme is calculated. The valve control scheme with the largest priority score is taken as the optimal valve control scheme. According to the optimal valve control scheme and the operating parameters of the water pump corresponding to the optimal valve control scheme, the optimal control scheme corresponding to the preset operating state is generated.

[0089] The cosine similarity between the current operating state and each preset operating state may be calculated as the state similarity between the current operating state and each preset operating state, and the preset operating state with the greatest state similarity may be used as the target preset operating state.

[0090] Figure 3 is a flow chart of a reservoir pump station water pump automatic control method according to some embodiments of this specification, such as Figure 3 As shown, a method for automatic control of water pumps in a reservoir pumping station may include the following steps.

[0091] Step 310, obtaining relevant information of the area to be irrigated;

[0092] Step 320, determining an optimal pipeline distribution plan based on relevant information of the area to be irrigated;

[0093] Step 330, setting a plurality of main pipelines, a plurality of branch pipelines and a plurality of emergency pipelines in the area to be irrigated based on the optimal pipeline distribution plan;

[0094] Step 340, obtaining real-time status information of the water pump on the main pipeline, real-time status information of each main pipeline, real-time status information of each branch pipeline, and real-time soil moisture information of the area to be irrigated;

[0095] Step 350, generating an optimal control plan based on the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline, the real-time status information of each branch pipeline, and the real-time soil moisture information of the area to be irrigated;

[0096] Step 360, based on the optimal control solution, control the water pump on the main pipeline to perform irrigation work.

[0097] A reservoir pump station water pump automatic control system can be used to execute a reservoir pump station water pump automatic control method. For more descriptions of a reservoir pump station water pump automatic control method, please refer to the relevant description of a reservoir pump station water pump automatic control system, which will not be repeated here.

[0098] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A reservoir pump station water pump automatic control system, characterized in that: include: An information acquisition module is used to acquire relevant information of the area to be irrigated, wherein the relevant information of the area to be irrigated includes the varieties of crops planted at different locations in the area to be irrigated and the irrigation amounts corresponding to different growth states; A pipeline planning module, used to determine a pipeline distribution plan based on the relevant information of the area to be irrigated, wherein the pipeline distribution plan includes the number and position of main pipelines, the number and position of branch pipelines, the number and position of emergency pipelines, the connection relationship between branch pipelines and main pipelines, and the connection relationship between emergency pipelines and main pipelines; A pipeline setting module, used for setting a plurality of main pipelines, a plurality of branch pipelines and a plurality of emergency pipelines in the area to be irrigated based on the pipeline distribution plan, wherein a water pump is installed on the main pipeline, and the emergency pipeline is used to connect two main pipelines; A status monitoring module, used to obtain real-time status information of the water pump on the main pipeline, real-time status information of each of the main pipelines, real-time status information of each of the branch pipelines, and real-time soil moisture information of the area to be irrigated, wherein the real-time status information of the water pump includes the water inlet flow rate, water outlet flow rate, vibration amplitude, sound intensity and temperature of the water pump, the real-time status information of the main pipeline includes the main pipeline flow rate, and the real-time status information of the branch pipeline includes the branch pipeline flow rate; A water pump control module is used to generate an optimal control scheme based on the real-time status information of the water pump on the main pipeline, the real-time status information of each of the main pipelines, the real-time status information of each of the branch pipelines, and the real-time soil moisture information of the area to be irrigated, including: Based on the irrigation demand of each sub-region at different time nodes and the real-time soil moisture information of the area to be irrigated, it is determined whether irrigation should be performed. If the current soil moisture of a sub-region or the predicted soil moisture in the future target time period is less than the soil moisture threshold corresponding to the current crop growth state of the sub-region and there will be no rainfall in the area to be irrigated in the future target time period, it is determined that irrigation is required; When it is determined that irrigation is to be performed, a plurality of preset operating states are determined based on the pipeline distribution scheme; the current operating state is determined based on the real-time state information of the water pump on the main pipeline, the real-time state information of each main pipeline and the real-time state information of each branch pipeline; the cosine similarity between the current operating state and each preset operating state is calculated as the state similarity between the current operating state and each preset operating state, and the preset operating state with the largest state similarity is used as the target preset operating state. For each preset operating state, a plurality of valve control schemes are determined, wherein the valve control scheme includes the state of the first valve, the state of the second valve, and the state of the second valve. state and the state of the third valve, determine the operating parameters of the water pump under each valve control scheme through the irrigation simulation model, determine the score of the valve control scheme in the water pump's operating load index, energy consumption index, and irrigation coverage index according to the operating parameters of the water pump, calculate the priority score of the valve control scheme, and take the valve control scheme with the largest priority score as the optimal valve control scheme, and generate the optimal control scheme corresponding to the preset operating state according to the optimal valve control scheme and the operating parameters of the water pump corresponding to the optimal valve control scheme, wherein the main pipeline is provided with a first valve, the branch pipeline is provided with a second valve, and the emergency pipeline is provided with a third valve; The scores of the candidate pipeline distribution schemes in the operating load index are calculated based on the following formula: in, is the score of the g-th candidate pipeline distribution scheme in the operating load index, To preset the normalization parameters, , is the operating load of the f-th water pump under the e-th irrigation simulation demand scenario corresponding to the g-th candidate pipeline distribution scheme, For the preset operating load, is the total number of irrigation simulation demand scenarios, is the total number of water pumps corresponding to the g-th candidate pipeline distribution scheme; The energy consumption score of the candidate pipeline distribution scheme is calculated based on the following formula: in, is the score of the g-th candidate pipeline distribution scheme in terms of energy consumption index, To preset the normalization parameters, , is the energy consumption of the f-th water pump under the e-th irrigation simulation demand scenario corresponding to the g-th candidate pipeline distribution scheme; The scores of the candidate pipeline distribution schemes in the irrigation coverage index are calculated based on the following formula: in, is the score of the g-th candidate pipeline distribution scheme in the irrigation coverage index, is the irrigation coverage rate of the g-th candidate pipeline distribution scheme under the e-th irrigation simulation demand scenario, To preset the normalization parameters, .

2. A reservoir pump station water pump automatic control method, characterized in that: A reservoir pump station water pump automatic control system applied to claim 1, comprising: Acquire relevant information of the area to be irrigated, wherein the relevant information of the area to be irrigated includes the varieties of crops planted at different locations in the area to be irrigated and the irrigation amounts corresponding to different growth states; Based on the relevant information of the area to be irrigated, a pipeline distribution plan is determined, wherein the pipeline distribution plan includes the number and position of main pipelines, the number and position of branch pipelines, the number and position of emergency pipelines, the connection relationship between branch pipelines and main pipelines, and the connection relationship between emergency pipelines and main pipelines; Based on the pipeline distribution scheme, multiple main pipelines, multiple branch pipelines and multiple emergency pipelines are arranged in the area to be irrigated, wherein a water pump is installed on the main pipeline, and the emergency pipeline is used to connect two main pipelines; Acquire the real-time status information of the water pump on the main pipeline, the real-time status information of each main pipeline, the real-time status information of each branch pipeline and the real-time soil moisture information of the area to be irrigated, wherein the real-time status information includes the water inlet flow rate, water outlet flow rate, vibration amplitude, sound intensity and temperature of the water pump; Generate an optimal control plan based on the real-time status information of the water pump on the main pipeline, the real-time status information of each of the main pipelines, the real-time status information of each of the branch pipelines, and the real-time soil moisture information of the area to be irrigated; Based on the optimal control scheme, the water pump on the main pipeline is controlled to perform irrigation work.

Images