Smart heater control system with built-in flow meter

Abstract

The application discloses an intelligent heater control system with a built-in flowmeter, and particularly relates to the technical field of heater control, which predicts the irrigation water temperature of crops in a region through a BP neural network, realizes accurate temperature control, obtains a heat loss coefficient according to the distance from the water outlet of the heater to the target region and the deviation between the ambient temperature and the water temperature in the heater, and sorts the irrigation priorities of different regions in combination with the prediction result of the irrigation water temperature of crops in the region, so that the energy consumption is minimized and the energy utilization efficiency is improved; the flow rate control module dynamically adjusts the flow rate of the water outlet of the heater according to the actual irrigation water temperature monitored to reach the target region, so that the irrigation effect is stable and consistent; and the control evaluation module analyzes the frequency change of the flow rate collected by the flowmeter at the water outlet and the valve adjustment delay, evaluates the stability of the flow rate control of the water outlet of the heater, discovers abnormal conditions of the flow rate control in time, and gives early warning.

Description

Technical Field

[0001] This invention relates to the field of heater control technology, and more specifically, to an intelligent heater control system with a built-in flow meter. Background Technology

[0002] The intelligent heater control system with a built-in flow meter is an intelligent automated control system that integrates flow measurement and water temperature control functions. The system mainly consists of a flow meter, heater, temperature sensor, controller, and communication module. The flow meter monitors the water flow rate in real time, the temperature sensor detects the water temperature, the controller controls the heater to adjust the water temperature according to preset parameters, and the data is transmitted to a remote monitoring system.

[0003] In agricultural irrigation, the intelligent heater control system with built-in flow meter can significantly optimize the temperature and flow of irrigation water, realize automated control to prevent crop roots from being cold or overheated, promote healthy crop growth, and improve crop growth conditions.

[0004] However, the initial investment in equipment such as intelligent control systems, flow meters, temperature sensors, and heating elements is relatively high. For some individual farmers who lack funds and professional knowledge, in order to save investment costs, they may use a single heater to heat irrigation water for crops in multiple different areas. However, the growth status of crops in different areas may vary, and the required irrigation water temperature should also be different. If the same heater heats irrigation water at the same time, the temperature tends to be uniform, which may lead to failure to meet the actual irrigation needs of crops in different areas, resulting in reduced crop yields. How to optimize the intelligent heater control system based on the limitations of the number of existing heater equipment to meet the actual irrigation needs of crops in different areas remains a technical challenge worth paying attention to.

[0005] To address the aforementioned shortcomings, a technical solution is provided. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent heater control system with a built-in flow meter to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] The intelligent heater control system with built-in flow meter includes a regional temperature prediction module, which acquires multiple index data for predicting the irrigation water temperature of crops in the region, constructs a BP neural network, and outputs the prediction results of the irrigation water temperature of crops in the region.

[0009] The irrigation route planning module obtains the heat loss coefficient based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. It also sorts the irrigation priorities of different areas based on the predicted irrigation water temperature of crops in the area.

[0010] The flow rate control module monitors the actual irrigation water temperature reaching the target area and controls the flow rate at the heater outlet based on the actual irrigation water temperature in the target area.

[0011] The control evaluation module analyzes the frequency changes of the outlet flow velocity collected by the flow meter and the adjustment delay of the outlet valve to evaluate the stability of the heater outlet flow velocity control.

[0012] In a preferred embodiment, multiple index data for predicting crop irrigation water temperature within a region are acquired, a BP neural network is constructed, and the predicted results of crop irrigation water temperature within the region are output, as follows:

[0013] Step A1: Determine multiple indicators for predicting crop irrigation water temperature in the region, including but not limited to air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area. Use air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area as inputs to the BP neural network, and crop irrigation water temperature as output.

[0014] A2, Construct a BP neural network for predicting irrigation water temperature for crops in the region;

[0015] A3 trains a BP neural network based on standardized multi-indicator sample data to obtain a BP neural network for predicting irrigation water temperature of crops in the region, and predicts irrigation water temperature of crops in the region.

[0016] In a preferred embodiment, the heat loss coefficient is obtained based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. Combined with the predicted irrigation water temperature for crops within the area, the irrigation priorities for different areas are ranked, as follows:

[0017] Obtain the distance from the heater outlet to the target area and mark it as JL. Use a temperature sensor to obtain the ambient temperature of the target area and the water temperature inside the heater, and mark the ambient temperature of the target area as t1 and the water temperature inside the heater as t2.

[0018] The heat loss coefficient SXS is calculated using the following formula based on the distance from the heater outlet to the target area, the ambient temperature of the target area, and the water temperature inside the heater:

[0019] The obtained heat loss coefficient and the predicted irrigation water temperature for crops in the region are used to calculate the regional irrigation priority ranking value PXZ using the following formula: [Expression follows] In the formula, YCS represents the predicted irrigation water temperature of crops in the region, α and β represent the heat loss coefficient and the proportionality coefficient of the predicted irrigation water temperature of crops in the region, respectively, and both α and β are greater than 0.

[0020] The irrigation regions are sorted from largest to smallest according to their irrigation priority ranking values ​​to obtain an irrigation region priority ranking table, and the different regions are irrigated according to the order in the irrigation priority ranking table.

[0021] In a preferred embodiment, the actual irrigation water temperature reaching the target area is monitored, and the flow rate at the heater outlet is controlled based on the actual irrigation water temperature in the target area, as follows:

[0022] The actual irrigation water temperature T reaching the target area is obtained by installing temperature sensors in different target areas. actual The irrigation water temperature error wc(t) is obtained by calculating the difference between the actual irrigation water temperature reaching the target area and the predicted water temperature, as shown in the following expression. The flow velocity at the heater outlet is obtained by using a flow meter built into the heater, and the outlet flow velocity is denoted as V. base ;

[0023] The flow velocity at the heater outlet is dynamically controlled using a PID control algorithm. The PID control formula is as follows: In the formula, V flow (t) represents the corrected outlet velocity, K p K represents the proportionality coefficient. i K represents the integral coefficient. d Represents the differential coefficient;

[0024] The flow rate at the heater outlet is dynamically controlled based on the corrected outlet flow rate.

[0025] In a preferred embodiment, the acquisition status of the flow meter is monitored to determine the change in the acquisition frequency of the flow velocity at the outlet, and the frequency acquisition jitter anomaly coefficient is obtained. The logic for obtaining the frequency acquisition jitter anomaly coefficient is as follows:

[0026] Acquire the flow velocity time series data collected by the flow meter, including timestamps and corresponding flow velocity values;

[0027] Calculate the mean flow velocity value based on the flow velocity time series data. The expression is as follows In the formula, x(t) represents the flow velocity value at time t in the flow velocity time series data;

[0028] The autocorrelation function R(δ) is calculated as follows: In the formula, δ represents the time delay, δ={0,1,2,...,N-1}, and N is a positive integer;

[0029] The maximum value of the autocorrelation function R(δ) is obtained by using a filtering function. max The filtering function is as follows: R(δ) max ) = MAX(R(δ));

[0030] Find the autocorrelation function decay to The time delay δ1, the lookup function is as follows

[0031] The frequency acquisition jitter anomaly coefficient cjd is calculated using the following expression: In the formula, T represents the sampling time period.

[0032] In a preferred embodiment, the adjustment status of the outlet valve is monitored to determine the adjustment delay of the outlet valve and obtain the valve adjustment delay coefficient. The logic for obtaining the valve adjustment delay coefficient is as follows:

[0033] Obtain the command reception time and actual response time of the outlet valve each time, and label the command reception time and actual response time as zl and xy respectively. Calculate the response time difference xc, as shown in the following expression: xc = xy - zl;

[0034] The average response time difference, xcp, is calculated using the following expression: In the formula xc m This represents the response time difference obtained in the m-th calculation, where m = {1, 2, ..., M}, and M is a positive integer;

[0035] Compare the response time difference calculated each time with the average response time difference, and mark the response time difference that is greater than the average response time difference as the delayed response time difference ycx;

[0036] The standard deviation of the delay response time difference, xyb, is calculated using the following expression: In the formula ycx u Let u represent the time difference of the u-th delayed response, where u = {1, 2, ..., v}, and v is a positive integer. The average delay response time difference is expressed as follows:

[0037] The valve adjustment delay coefficient fyc is calculated using the following expression:

[0038] In a preferred embodiment, the acquired frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient are normalized. Based on the normalized frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient, a flow velocity control stability assessment model is constructed, generating a flow velocity control stability assessment index lsw. The model is based on the following formula: In the formula, a1 and a2 represent the preset proportional coefficients of the frequency acquisition jitter abnormality coefficient and the valve adjustment delay coefficient, respectively, and both a1 and a2 are greater than 0.

[0039] In a preferred embodiment, the flow rate control stability evaluation index is compared with a preset flow rate control stability evaluation index threshold. If the flow rate control stability evaluation index is greater than the flow rate control stability evaluation index threshold, a stability anomaly signal is generated. If the flow rate control stability evaluation index is less than or equal to the flow rate control stability evaluation index threshold, no stability anomaly signal needs to be generated.

[0040] The technical effects and advantages of this invention are as follows:

[0041] 1. This invention acquires multiple index data for predicting irrigation water temperature of crops within a region, constructs a BP neural network to predict the irrigation water temperature of crops within the region, and achieves precise temperature control to ensure that the growth needs of crops in different regions are met, avoiding the impact of excessively high or low temperatures on crop growth. The heat loss coefficient is obtained based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. Combined with the predicted irrigation water temperature of crops within the region, the irrigation priority of different areas is ranked to minimize energy consumption and improve energy utilization efficiency. The flow rate control module dynamically adjusts the flow rate at the heater outlet based on the monitored actual irrigation water temperature reaching the target area, ensuring that the actual irrigation water temperature is as close as possible to the predicted value, thereby ensuring stable and consistent irrigation effects. The control evaluation module analyzes the frequency changes of the flow rate collected by the flow meter at the outlet and the valve adjustment delay, evaluates the stability of the flow rate control at the heater outlet, promptly detects abnormalities in flow rate control, provides early warnings, and takes measures to ensure stable and reliable system operation. Attached Figure Description

[0042] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0043] Figure 1 This is a schematic diagram of the system structure according to an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example: The present invention provides, as follows Figure 1 The intelligent heater control system with built-in flow meter shown includes a regional temperature prediction module, which acquires multiple index data for predicting the irrigation water temperature of crops in the region, constructs a BP neural network, and outputs the prediction results of the irrigation water temperature of crops in the region.

[0046] Step A1: Determine multiple indicators for predicting crop irrigation water temperature in the region, including but not limited to air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area. Use air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area as inputs to the BP neural network, and crop irrigation water temperature as output.

[0047] Temperature deviation refers to the degree of deviation between the temperature required for the current growth stage of crops and the actual temperature of the area. When the actual temperature is lower than the ideal temperature required by crops, it may affect the photosynthesis and growth rate of crops. The irrigation water temperature should be appropriately increased to raise the temperature of the soil and roots and promote crop growth.

[0048] Soil moisture deviation refers to the degree of deviation between the soil moisture required for the current growth stage of crops and the actual soil moisture in the area. When the actual soil moisture is lower than the soil moisture required for the current growth stage of crops, irrigation is required, and the temperature of the irrigation water will directly affect the growth status of crops.

[0049] The average height deviation of crops refers to the deviation between the average growth height of crops in the current area and the expected growth height. When it is necessary to irrigate crops in the area, if the average growth height of crops does not reach the expected growth height, it is even more necessary to control the irrigation water temperature.

[0050] The average leaf area of ​​crops refers to the average leaf area of ​​crops in the current area. The larger the average leaf area of ​​crops, the easier it is to block sunlight. In areas with obvious shading effect, the irrigation water temperature can be adjusted to be slightly higher than the ambient temperature to ensure that the root system of the lower plants is at a suitable temperature and promote their growth.

[0051] The sample data of multiple indicators for predicting irrigation water temperature of crops in the region are obtained and preprocessed, including cleaning the data to remove or fill missing values, handling outliers, and standardizing the data so that the data of each indicator are in the range of 0-1.

[0052] A2, Construct a BP neural network for predicting irrigation water temperature for crops in the region;

[0053] Backpropagation (BP) neural networks are used to solve various machine learning problems, including classification and regression. BP stands for "backpropagation," which is the key algorithm for training this model.

[0054] A backpropagation (BP) neural network consists of multiple neurons, typically divided into an input layer, hidden layers, and an output layer. Each neuron is connected to every neuron in the previous layer and has weights used to adjust signal transmission and computation. The principle of a BP neural network is based on two key steps: forward propagation and backward propagation.

[0055] Forward propagation is the process where the input signal is passed from the input layer to the hidden and output layers. Each neuron multiplies its input by weights and applies an activation function to produce an output. This process continues until the output layer, generating the network's predictions.

[0056] In this embodiment, four indicators—temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area—are used as four neurons in the input layer of the BP neural network, and the output layer of the BP neural network is one neuron, namely, the irrigation water temperature of the crop.

[0057] A three-layer backpropagation (BP) neural network model with one hidden layer is adopted. The number of neurons in the hidden layer is determined by various empirical rules. Based on the results of multiple training sessions, the BP neural network is ensured to meet the convergence condition. The weights of each index in the BP neural network are randomly obtained and updated through backpropagation of error. The hidden layer uses the ReLU activation function, and the output layer uses the Sigmoid activation function to restrict the output to the range of 0-1.

[0058] A3. The BP neural network is trained based on standardized multi-indicator sample data to obtain a BP neural network for predicting the irrigation water temperature of crops in the region, and the irrigation water temperature of crops in the region is predicted.

[0059] The irrigation route planning module obtains the heat loss coefficient based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. It also sorts the irrigation priorities of different areas based on the predicted irrigation water temperature of crops in the area.

[0060] Obtain the distance from the heater outlet to the target area and mark it as JL. Use a temperature sensor to obtain the ambient temperature of the target area and the water temperature inside the heater, and mark the ambient temperature of the target area as t1 and the water temperature inside the heater as t2.

[0061] The heat loss coefficient SXS is calculated using the following formula based on the distance from the heater outlet to the target area, the ambient temperature of the target area, and the water temperature inside the heater:

[0062] The greater the distance from the heater outlet to the target area and the lower the ambient temperature, the greater the heat loss coefficient, indicating that the irrigation water suffers more severe heat loss during its journey from the heater outlet to the target area.

[0063] The obtained heat loss coefficient and the predicted irrigation water temperature for crops in the region are used to calculate the regional irrigation priority ranking value PXZ using the following formula: [Expression follows] In the formula, YCS represents the predicted irrigation water temperature of crops in the region, α and β represent the heat loss coefficient and the proportionality coefficient of the predicted irrigation water temperature of crops in the region, respectively, and both α and β are greater than 0.

[0064] Since the water temperature heated by the heater tends to be consistent during the same period, the highest value of the predicted irrigation water temperature for crops in the region is used as the heating standard for the water temperature inside the heater.

[0065] The higher the predicted water temperature for irrigation of crops in a region and the lower the heat loss, the higher the priority for irrigation.

[0066] Crops have specific requirements for irrigation water temperature at different growth stages. Prioritizing areas with higher predicted irrigation water temperatures ensures that crops in these areas receive the optimal water temperature needed for healthy growth. Heat loss is unavoidable during irrigation. By prioritizing irrigation of areas with less heat loss, thermal energy utilization efficiency can be improved. Crops in areas with lower required optimal water temperatures can naturally lower the irrigation water temperature through heat loss, maximizing resource utilization, avoiding waste, and improving overall irrigation efficiency.

[0067] The irrigation regions are sorted from largest to smallest according to their irrigation priority ranking values ​​to obtain an irrigation region priority ranking table, and the different regions are irrigated according to the order in the irrigation priority ranking table.

[0068] Based on the irrigation sequence of different areas, determine the direction of irrigation water flow, and construct simple, detachable pipelines according to the actual situation to ensure that irrigation water can achieve full coverage of different areas.

[0069] The flow rate control module monitors the actual irrigation water temperature reaching the target area and controls the flow rate at the heater outlet based on the actual irrigation water temperature in the target area.

[0070] The actual irrigation water temperature T reaching the target area is obtained by installing temperature sensors in different target areas. actual The irrigation water temperature error wc(t) is obtained by calculating the difference between the actual irrigation water temperature reaching the target area and the predicted water temperature, as shown in the following expression. The flow velocity at the heater outlet is obtained by using a flow meter built into the heater, and the outlet flow velocity is denoted as V. base ;

[0071] Since the flow rate at the outlet may cause the actual irrigation water temperature reaching the target area to fluctuate to varying degrees, for example, if the flow rate is too slow, the water temperature may be excessively dissipated during transmission, resulting in a lower water temperature. Therefore, by controlling the flow rate at the heater outlet, the actual irrigation water temperature reaching the target area can be optimized.

[0072] The flow velocity at the heater outlet is dynamically controlled using a PID control algorithm. The PID control formula is as follows: In the formula, V flow (t) represents the corrected outlet velocity, K p K represents the proportionality coefficient. i K represents the integral coefficient. d Represents the differential coefficient;

[0073] It should be noted that K p K i K d Determined through experimental debugging;

[0074] The flow rate at the heater outlet is dynamically controlled based on the corrected outlet flow rate.

[0075] The control evaluation module analyzes the frequency changes of the outlet flow velocity collected by the flow meter and the adjustment delay of the outlet valve to evaluate the stability of the heater outlet flow velocity control.

[0076] The flow meter's acquisition status is monitored to determine the frequency change of the flow meter's acquisition frequency of the outlet flow velocity. The frequency acquisition jitter anomaly coefficient is obtained, and the logic for obtaining the frequency acquisition jitter anomaly coefficient is as follows:

[0077] Acquire the flow velocity time series data collected by the flow meter, including timestamps and corresponding flow velocity values;

[0078] Calculate the mean flow velocity value based on the flow velocity time series data. The expression is as follows In the formula, x(t) represents the flow velocity value at time t in the flow velocity time series data;

[0079] The autocorrelation function R(δ) is calculated as follows: In the formula, δ represents the time delay, δ={0,1,2,...,N-1}, and N is a positive integer;

[0080] The correlation of the flow velocity value x(t) under different time delays can be measured by calculating the autocorrelation function, and the periodicity of the flow meter's sampling frequency can be identified.

[0081] The maximum value of the autocorrelation function R(δ) is obtained by using a filtering function. max The filtering function is as follows: R(δ) max ) = MAX(R(δ));

[0082] Find the autocorrelation function decay to The time delay δ1, the lookup function is as follows

[0083] The frequency acquisition jitter anomaly coefficient cjd is calculated using the following expression: In the formula, T represents the sampling time period;

[0084] The stability of the flow meter's sampling frequency can be evaluated by calculating parameters such as the half-life of the autocorrelation function. A rapidly decaying autocorrelation function indicates that the flow meter's sampling frequency is more stable, that is, the smaller the frequency sampling jitter anomaly coefficient, the more stable the flow meter's sampling frequency. On the other hand, a slow decay may indicate that the frequency jitter is larger, that is, the larger the frequency sampling jitter anomaly coefficient, the greater the flow meter's sampling frequency jitter.

[0085] The adjustment status of the outlet valve is monitored to determine the adjustment delay, and the valve adjustment delay coefficient is obtained. The logic for obtaining the valve adjustment delay coefficient is as follows:

[0086] Obtain the command reception time and actual response time of the outlet valve each time, and label the command reception time and actual response time as zl and xy respectively. Calculate the response time difference xc, as shown in the following expression: xc = xy - zl;

[0087] The average response time difference, xcp, is calculated using the following expression: In the formula xc m This represents the response time difference obtained in the m-th calculation, where m = {1, 2, ..., M}, and M is a positive integer;

[0088] Compare the response time difference calculated each time with the average response time difference, and mark the response time difference that is greater than the average response time difference as the delayed response time difference ycx;

[0089] The standard deviation of the delay response time difference, xyb, is calculated using the following expression: In the formula ycx u Let u represent the time difference of the u-th delayed response, where u = {1, 2, ..., v}, and v is a positive integer. The average delay response time difference is expressed as follows:

[0090] The valve adjustment delay coefficient fyc is calculated using the following expression:

[0091] By calculating the valve adjustment delay coefficient, it can be determined whether the adjustment response of the outlet valve is stable and timely. A lower valve adjustment delay coefficient indicates that the outlet valve responds relatively quickly and the control of the outlet flow rate is more timely, while a higher valve adjustment delay coefficient may lead to a decrease in the stability of the outlet flow rate control.

[0092] The acquired frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient are normalized. Based on the normalized frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient, a flow velocity control stability assessment model is constructed, generating the flow velocity control stability assessment index lsw. The formula used in the model is as follows: In the formula, a1 and a2 represent the preset proportional coefficients of the frequency acquisition jitter anomaly coefficient and the valve adjustment delay coefficient, respectively, and both a1 and a2 are greater than 0;

[0093] As can be seen from the above calculation expression, the larger the frequency acquisition jitter abnormality coefficient and the larger the valve adjustment delay coefficient, the larger the flow velocity control stability evaluation index. This indicates that the frequency jitter abnormality of the flow velocity collected by the flow meter at the outlet and the adjustment delay of the outlet valve have a greater impact on the stability of the flow velocity control at the heater outlet. Conversely, the smaller the frequency acquisition jitter abnormality coefficient and the smaller the valve adjustment delay coefficient, the smaller the flow velocity control stability evaluation index. This indicates that the frequency jitter abnormality of the flow velocity collected by the flow meter at the outlet and the adjustment delay of the outlet valve have a smaller impact on the stability of the flow velocity control at the heater outlet.

[0094] The flow rate control stability assessment index is compared with the preset flow rate control stability assessment index threshold. If the flow rate control stability assessment index is greater than the threshold, it indicates that the abnormal frequency fluctuation of the flow rate collected by the flow meter at the outlet and the adjustment delay of the outlet valve have exceeded the preset limit on the stability of the flow rate control at the heater outlet. A stability abnormality signal is generated, and individual farmers need to be reminded to repair or replace the flow meter or valve to ensure the stability of the flow rate control. If the flow rate control stability assessment index is less than or equal to the threshold, it indicates that the abnormal frequency fluctuation of the flow rate collected by the flow meter at the outlet and the adjustment delay of the outlet valve have little impact on the stability of the flow rate control at the heater outlet. No stability abnormality signal needs to be generated.

[0095] This invention acquires multiple index data for predicting irrigation water temperature for crops within a region, constructs a BP neural network to predict the irrigation water temperature for crops within that region, and achieves precise temperature control. This ensures that the growth needs of crops in different regions are met, avoiding the impact of excessively high or low temperatures on crop growth. The heat loss coefficient is obtained based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. Combined with the predicted irrigation water temperature for crops within the region, the irrigation priority for different areas is ranked to minimize energy consumption and improve energy utilization efficiency. The flow rate control module dynamically adjusts the flow rate at the heater outlet based on the monitored actual irrigation water temperature reaching the target area, ensuring that the actual irrigation water temperature is as close as possible to the predicted value, thereby guaranteeing stable and consistent irrigation results. The control evaluation module analyzes the frequency changes of the flow rate collected by the flow meter at the outlet and the valve adjustment delay, evaluates the stability of the flow rate control at the heater outlet, promptly detects abnormalities in flow rate control, provides early warnings, and takes measures to ensure stable and reliable system operation.

[0096] Through precise temperature control and optimized irrigation routes, energy consumption is effectively saved, operating costs are reduced, and crop growth quality and yield are improved, helping individual farmers to make more effective use of equipment and enhance agricultural production efficiency.

[0097] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0098] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0099] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0100] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A smart heater control system with a built-in flow meter, characterized in that: It includes a regional temperature prediction module, which acquires multiple index data for predicting irrigation water temperature of crops in the region, constructs a BP neural network, and outputs the prediction results of irrigation water temperature of crops in the region. The irrigation route planning module obtains the heat loss coefficient based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. It also sorts the irrigation priorities of different areas based on the predicted irrigation water temperature of crops in the area. The flow rate control module monitors the actual irrigation water temperature reaching the target area and controls the flow rate at the heater outlet based on the actual irrigation water temperature in the target area. The control evaluation module analyzes the frequency changes of the outlet flow velocity collected by the flow meter and the adjustment delay of the outlet valve to evaluate the stability of the heater outlet flow velocity control. The heat loss coefficient is obtained based on the distance from the heater outlet to the target area and the deviation between the ambient temperature and the water temperature inside the heater. Combined with the predicted irrigation water temperature for crops within the area, the irrigation priorities for different areas are ranked as follows: Obtain the distance from the heater outlet to the target area, and mark the distance from the heater outlet to the target area as... The ambient temperature of the target area and the water temperature in the heater are obtained through temperature sensors, and the ambient temperature of the target area is marked as... The water temperature inside the heater is marked as ; The heat loss coefficient is calculated using a formula based on the distance from the heater outlet to the target area, the ambient temperature of the target area, and the water temperature inside the heater. The expression is as follows ; The obtained heat loss coefficient and the predicted irrigation water temperature for crops in the region are used to calculate the regional irrigation priority ranking value using the following formula. The expression is as follows In the formula This indicates the predicted water temperature for irrigation of crops within the region. , These represent the heat loss coefficient and the proportionality coefficient of the predicted irrigation water temperature for crops within the region, respectively. , All are greater than 0; The irrigation regions are sorted from largest to smallest according to their irrigation priority ranking values ​​to obtain an irrigation region priority ranking table, and the different regions are irrigated according to the order in the irrigation priority ranking table.

2. The intelligent heater control system with built-in flow meter according to claim 1, characterized in that: Multiple indicator data for predicting crop irrigation water temperature within a region are obtained, a BP neural network is constructed, and the predicted crop irrigation water temperature within the region is output, as follows: Step A1: Determine multiple indicators for predicting crop irrigation water temperature in the region, including air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area. Use air temperature deviation, soil moisture deviation, average crop height deviation, and average crop leaf area as inputs to the BP neural network, and crop irrigation water temperature as output. A2, Construct a BP neural network for predicting irrigation water temperature for crops in the region; A3 trains a BP neural network based on standardized multi-indicator sample data to obtain a BP neural network for predicting irrigation water temperature of crops in the region, and predicts irrigation water temperature of crops in the region.

3. The intelligent heater control system with built-in flow meter according to claim 1, characterized in that: Monitor the actual irrigation water temperature reaching the target area, and control the flow rate at the heater outlet based on the actual irrigation water temperature in the target area, as follows: The actual irrigation water temperature reaching the target area is obtained by installing temperature sensors in different target areas. The difference between the actual irrigation water temperature reaching the target area and the predicted water temperature is calculated to obtain the irrigation water temperature error. The expression is as follows The flow velocity at the heater outlet is obtained through a flow meter built into the heater, and the outlet flow velocity is marked as... ; The flow velocity at the heater outlet is dynamically controlled using a PID control algorithm. The PID control formula is as follows: In the formula, This indicates the corrected outlet flow velocity. Represents the proportionality coefficient. Represents the integral coefficient. Represents the differential coefficient; The flow rate at the heater outlet is dynamically controlled based on the corrected outlet flow rate.

4. The intelligent heater control system with built-in flow meter according to claim 3, characterized in that: The flow meter's acquisition status is monitored to determine the frequency change of the flow meter's acquisition frequency of the outlet flow velocity. The frequency acquisition jitter anomaly coefficient is obtained, and the logic for obtaining the frequency acquisition jitter anomaly coefficient is as follows: Acquire the flow velocity time series data collected by the flow meter, including timestamps and corresponding flow velocity values; Calculate the mean flow velocity value based on the flow velocity time series data. The expression is as follows In the formula This represents the flow velocity value at time t in the flow velocity time series data; Calculate the autocorrelation function The expression is as follows In the formula Indicates time delay. ={0,1,2,...,N-1}, where N is a positive integer; Obtain the autocorrelation function using the filtering function. maximum value The filtering function is as follows: ; Find the autocorrelation function decay to Time delay The lookup function is as follows: ; Calculate the frequency acquisition jitter anomaly coefficient The expression is as follows In the formula Indicates the sampling time period.

5. The intelligent heater control system with built-in flow meter according to claim 4, characterized in that: The adjustment status of the outlet valve is monitored to determine the adjustment delay, and the valve adjustment delay coefficient is obtained. The logic for obtaining the valve adjustment delay coefficient is as follows: Obtain the command reception time and actual response time for each operation of the outlet valve, and mark the command reception time and actual response time as follows: , Calculate the response time difference The expression is as follows ; Calculate the average response time difference The expression is as follows In the formula This represents the response time difference obtained in the m-th calculation, where m = {1, 2, ..., M}, and M is a positive integer; The calculated response time difference is compared with the average response time difference. Response time differences that are greater than the average response time difference are marked as delayed response time differences. ; Calculate the standard deviation of the delay response time difference The expression is as follows In the formula Let u represent the time difference of the u-th delayed response, where u = {1, 2, ..., v}, and v is a positive integer. The average delay response time difference is expressed as follows: ; Calculate the valve adjustment delay coefficient The expression is as follows .

6. The intelligent heater control system with built-in flow meter according to claim 5, characterized in that: The acquired frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient are normalized. Based on the normalized frequency acquisition jitter anomaly coefficient and valve adjustment delay coefficient, a flow velocity control stability assessment model is constructed, and a flow velocity control stability assessment index is generated. The model is based on the following formula: In the formula , These represent the preset proportional coefficients for the frequency acquisition jitter anomaly coefficient and the valve adjustment delay coefficient, respectively. , All are greater than 0.

7. The intelligent heater control system with built-in flow meter according to claim 6, characterized in that: The flow rate control stability assessment index is compared with the preset flow rate control stability assessment index threshold. If the flow rate control stability assessment index is greater than the flow rate control stability assessment index threshold, a stability anomaly signal is generated; if the flow rate control stability assessment index is less than or equal to the flow rate control stability assessment index threshold, no stability anomaly signal needs to be generated.

Images