Aquaculture water quality monitoring control method based on fuzzy logic and dynamic weight adjustment

Abstract

The invention relates to an aquaculture water quality monitoring control method based on fuzzy logic and dynamic weight adjustment, which comprises the following steps: collecting real-time water quality data of a fishery according to a plurality of water quality parameters; carrying out data preprocessing and standardization processing on the collected water quality data; performing fuzzification processing on the water quality data according to membership functions respectively defined for each water quality parameter in advance; the initial weight of each water quality parameter is determined based on an entropy weight method, the real-time data entropy of each water quality parameter is dynamically updated and calculated according to the water quality data collected in real time, and the corresponding data entropy change rate is determined, so that the weight of each water quality parameter is adjusted; and according to the fuzzified water quality data and the dynamically adjusted weight of each water quality parameter, performing fuzzy reasoning through a fuzzy rule base to obtain a fuzzy control strategy of the corresponding electrical equipment. Compared with the prior art, the system achieves the real-time monitoring and optimal control of complex environment data, and improves the efficiency and effect of breeding management.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring and control, and in particular to an aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment. Background Art

[0002] The core of modern aquaculture is to maintain the best water quality and environmental conditions to ensure the healthy growth of aquaculture objects (such as fish, shrimp, etc.). Water quality parameters such as water temperature, dissolved oxygen, ammonia nitrogen concentration, turbidity, etc. play a vital role in aquaculture. Changes in these parameters will directly affect the growth rate, health status and survival rate of aquaculture objects.

[0003] Traditional water quality monitoring and control methods usually rely on manual testing and regular adjustments. However, with the expansion of aquaculture scale and the complexity of aquaculture environment, manual methods can no longer meet the needs of efficient management. Automated and intelligent monitoring and control systems have emerged, among which real-time data collection, analysis and processing, and control optimization are key technical links.

[0004] In practical applications, there is a complex nonlinear relationship between water quality parameters and the operating status of electrical equipment. It is difficult to accurately capture this complexity by relying solely on traditional statistical analysis methods, and it is impossible to accurately and effectively achieve intelligent monitoring and optimization control of the aquaculture environment. Summary of the invention

[0005] The purpose of the present invention is to overcome the defect that there is a complex nonlinear relationship between water quality parameters and the operating status of electrical equipment in the above-mentioned prior art, and that it is difficult to accurately capture this complexity by relying solely on traditional statistical analysis methods, and to provide an aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment comprises the following steps:

[0008] Collect real-time water quality data of fisheries based on multiple water quality parameters;

[0009] Preprocess the collected water quality data and standardize them to make the data have consistent dimensions;

[0010] According to the membership functions pre-defined for each water quality parameter, the standardized water quality data is fuzzy processed;

[0011] Based on the entropy weight method, the initial weight of each water quality parameter is determined, and the real-time data entropy of each water quality parameter is dynamically updated and calculated according to the real-time collected water quality data, and the corresponding data entropy change rate is determined, so as to dynamically adjust the weight of each water quality parameter;

[0012] According to the fuzzy processed water quality data and the dynamically adjusted weights of various water quality parameters, fuzzy reasoning is performed through a pre-built fuzzy rule library to obtain the corresponding fuzzy control strategy for electrical equipment.

[0013] Furthermore, the multiple water quality parameters include temperature, dissolved oxygen, ammonia nitrogen concentration and turbidity.

[0014] Furthermore, the membership function corresponding to the temperature is an intermediate distribution, which is optimal in the medium range; the membership function corresponding to the dissolved oxygen content is a large-sized distribution in the trapezoidal type, and the larger the value, the better the result; the membership functions corresponding to the ammonia nitrogen concentration and turbidity are both small-sized distributions, and the smaller the value, the better the result.

[0015] Furthermore, the expression of the membership function corresponding to the temperature is:

[0016]

[0017] In the formula, μ Medium (T′) is the membership function corresponding to temperature, and T′ is the temperature after standardization;

[0018] The expression of the membership function corresponding to the dissolved oxygen content is:

[0019]

[0020] In the formula, μ High (DO′) is the membership function corresponding to the dissolved oxygen content, and DO′ is the dissolved oxygen content after standardized treatment;

[0021] The expression of the membership function corresponding to the ammonia nitrogen concentration is:

[0022]

[0023] In the formula, μ Low (NH3-N′) is the membership function corresponding to the ammonia nitrogen concentration, and NH3-N′ is the ammonia nitrogen concentration after standardization;

[0024] The expression of the membership function corresponding to the turbidity is:

[0025]

[0026] In the formula, μ Low (Turb′) is the membership function corresponding to turbidity, and Turb′ is the turbidity after normalization.

[0027] Furthermore, the data preprocessing includes cleaning the collected water quality data to remove outliers and sensor noise, and then processing missing data through interpolation and averaging methods.

[0028] Furthermore, the data standardization process includes:

[0029] According to the data after data preprocessing, an evaluation matrix of m monitoring sections and n evaluation indicators is constructed. The expression of the evaluation matrix is:

[0030]

[0031] In the formula, R ij It represents the measured data of the jth evaluation index corresponding to the i-th monitoring section;

[0032] Positive normalization is used for the positive indicators in the evaluation matrix, and reverse normalization is used for the negative indicators. The corresponding expressions are:

[0033]

[0034] In the formula, R ij ' is the data after standardization.

[0035] Furthermore, the calculation expression for determining the initial weight of each water quality parameter based on the entropy weight method is:

[0036]

[0037] In the formula, R i ' j is the data after standardization, m is the number of monitoring sections, q ij is the proportion of the i-th sample value under the j-th indicator to the indicator, S j is the entropy value of the jth indicator, w j (0) is the initial weight of each indicator;

[0038] The calculation expression of the real-time data entropy of each water quality parameter is:

[0039]

[0040] In the formula, S j (t) is the real-time data entropy of the jth parameter at time t, p ij (t) is the normalized probability distribution of the jth parameter at time t.

[0041] Furthermore, the data entropy change rate is calculated based on the comparison of the information entropy at the current time point t and the previous time point t-1, and the corresponding calculation expression is:

[0042] ΔS j (t) = S j (t)-S j (t-1)

[0043] In the formula, ΔS j (t) is the data entropy change rate of the jth parameter at time t, S j (t-1) is the real-time data entropy of the jth parameter at time t-1.

[0044] Furthermore, the weight adjustment formula of the water quality parameters is:

[0045]

[0046] In the formula, w j (t) is the weight of the jth parameter at time t, w j (t-1) is the weight of the jth parameter at time t-1, α is the adjustment coefficient, ΔS j (t) is the data entropy change rate of the jth parameter at time t.

[0047] Furthermore, the fuzzy rule base V = {v1, v2, v3, ..., v m}, including at least one of the following rules:

[0048]

[0049] The fuzzy control strategy of the electrical equipment corresponding to rule V1 is to reduce the operating power of the aerator by 30% and increase the operating power of the irrigation and drainage system by 30%; the fuzzy control strategy of the electrical equipment corresponding to rule V2 is to reduce the operating power of the aerator by 15% and increase the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V3 is to maintain the operating power of the aerator and the operating power of the irrigation and drainage system unchanged; the fuzzy control strategy of the electrical equipment corresponding to rule V4 is to increase the operating power of the aerator by 15% and reduce the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V5 is to increase the operating power of the aerator by 30% and reduce the operating power of the irrigation and drainage system by 30%;

[0050] After the fuzzy processed water quality data is multiplied by the weights of the dynamically adjusted water quality parameters, the most suitable rule is obtained through the fuzzy rule library, and the corresponding fuzzy control strategy is selected to control the electrical equipment.

[0051] Compared with the prior art, the present invention has the following advantages:

[0052] (1) The present invention collects water quality parameters of typical fisheries, such as temperature, dissolved oxygen, ammonia nitrogen concentration and turbidity, uses fuzzy logic to process and infer data, and adjusts weights in real time according to data changes to establish fuzzy rules between water quality parameters and the operating status of electrical equipment, thereby achieving real-time monitoring and optimal control of the aquaculture environment. Fuzzy logic can effectively describe and process the complex and uncertain nonlinear relationship between water quality parameters and the operating status of electrical equipment, thereby improving the accuracy of aquaculture environment monitoring and thus improving the efficiency and effectiveness of aquaculture management.

[0053] (2) The present invention recalculates the real-time data entropy of each parameter each time new data is received, and obtains the data entropy change rate of each parameter, which can reflect the uncertainty and volatility of the parameter in the recent time period. If the entropy change rate of a parameter is large, it means that its importance has increased at the current moment; according to the size of the entropy change rate, it can be identified which parameters have changed significantly at the current time point; thus affecting the direction and magnitude of the weight adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 The present invention provides a flow chart of an aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0058] Example 1

[0059] like Figure 1 As shown, this embodiment provides a method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment, comprising the following steps:

[0060] S1: Collect real-time water quality data of the fishery based on multiple water quality parameters;

[0061] S2: pre-process the collected water quality data and perform standardization to make the data have consistent dimensions;

[0062] S3: fuzzy processing is performed on the standardized water quality data according to the membership functions pre-defined for each water quality parameter;

[0063] S4: Determine the initial weight of each water quality parameter based on the entropy weight method, dynamically update and calculate the real-time data entropy of each water quality parameter according to the real-time collected water quality data, and determine the corresponding data entropy change rate, so as to dynamically adjust the weight of each water quality parameter;

[0064] S5: According to the fuzzy processed water quality data and the weights of each water quality parameter after dynamic adjustment, fuzzy reasoning is performed through a pre-built fuzzy rule library to obtain the corresponding fuzzy control strategy of the electrical equipment.

[0065] Specifically, in step S1, this embodiment collects real-time water quality data of fisheries in typical periods of the fishery-solar-energy-storage system, considers the typical fishery aquaculture operation mode, selects four important typical parameters of temperature (T), dissolved oxygen (DO), ammonia nitrogen concentration (NH3-N), and turbidity (Turb) to construct a typical aquaculture water quality model of the "fishery-solar-energy-storage" system, and sets the evaluation index factor set U = {u1, u2, u3, u4}. Among them, u1 is temperature, u2 is dissolved oxygen, u3 is ammonia nitrogen concentration, and u4 is turbidity.

[0066] In step S2, the collected data are cleaned, missing values ​​are processed, and standardized through linear transformation so that each parameter has a consistent dimension;

[0067] The initial data to be acquired is cleaned to remove outliers and sensor noise, and then the missing data is processed through interpolation and averaging methods. Finally, the data is standardized to meet the input requirements of the fuzzy logic system.

[0068] The data standardization process includes:

[0069] First, an evaluation matrix R with n evaluation indicators in m monitoring sections is constructed. The evaluation indicator matrix is ​​composed of the measured data of the evaluation indicators of each section, as shown in the following formula:

[0070]

[0071] In the formula, R ij Represents the measured data of the jth evaluation index corresponding to the ith monitoring section.

[0072] Secondly, positive normalization is used for positive indicators (such as dissolved oxygen), and reverse normalization is used for negative indicators (such as ammonia nitrogen concentration). The specific normalization formula is as follows:

[0073]

[0074] In the formula, R ij ′ represents the standardized data, R ij is the original data.

[0075] In step S3, an appropriate membership function is defined for each water quality parameter. The membership function can be a triangular, trapezoidal or Gaussian function, and its shape is determined according to the characteristics of the data; the standardized water quality data is fuzzified through the membership function to generate a fuzzy set representation, and the obtained fuzzy set will be used as the input of subsequent fuzzy reasoning.

[0076] The specific process is:

[0077] Establish a single factor evaluation matrix. Since the water quality data standard is a vague concept, it is more reasonable to use membership to characterize the classification boundaries. Water quality evaluation is more suitable for a trapezoidal membership function, in which the larger the DO evaluation index value, the better the result, the T evaluation index value is medium, and the other evaluation indicators are the opposite. Therefore, the DO index adopts a large distribution in the trapezoidal type, the T index adopts an intermediate distribution, and the other indicators adopt a small distribution. The membership functions of standardized water quality parameters include:

[0078] 1) Membership function of temperature T:

[0079]

[0080] In the formula, μ Medium (T′) is the membership function corresponding to temperature, and T′ is the temperature after standardization;

[0081] 2) Membership function of dissolved oxygen:

[0082]

[0083] In the formula, μ High (DO′) is the membership function corresponding to the dissolved oxygen content, and DO′ is the dissolved oxygen content after standardized treatment;

[0084] 3) Membership function of ammonia nitrogen:

[0085]

[0086] In the formula, μ Low (NH3-N′) is the membership function corresponding to the ammonia nitrogen concentration, and NH3-N′ is the ammonia nitrogen concentration after standardization;

[0087] 4) Membership function of turbidity:

[0088]

[0089] In the formula, μ Low (Turb′) is the membership function corresponding to turbidity, and Turb′ is the turbidity after normalization.

[0090] In step S4, the initial weight of each parameter is determined based on the entropy weight method, and the data entropy (S j (t)), which is used to reflect the dispersion and volatility of data; the rate of change of data entropy (S j (t)), and dynamically adjust the weights of each parameter accordingly.

[0091] Specifically, the steps of dynamic weight adjustment include:

[0092] 1) Calculate the information entropy value of the indicator and the weight of each indicator. The calculation formula is as follows:

[0093]

[0094] In the formula, R′ ij is the data after standardization, m is the number of monitoring sections, q ij is the proportion of the i-th sample value under the j-th indicator to the indicator, S j is the entropy value of the jth indicator, w j (0) is the initial weight of each indicator;

[0095] 2) Update data entropy in real time and calculate the entropy change rate

[0096] Whenever new data is received, the real-time data entropy S of each parameter is recalculated j (t) to reflect the uncertainty and information content of the current parameters. The calculation formula of real-time data entropy is similar to the entropy calculation in the initial weight calculation process:

[0097]

[0098] In the formula, S j (t) is the real-time data entropy of the jth parameter at time t, p ij (t) is the normalized probability distribution of the jth parameter at time t, which is calculated in the same way as q ij same.

[0099] Compare the information entropy at the current time point t with the information entropy at the previous time point t-1, and calculate the data entropy change rate ΔS of each parameter j (t):

[0100] ΔS j(t) = S j (t)-S j (t-1)

[0101] In the formula, ΔS j (t) is the data entropy change rate of the jth parameter at time t, S j (t-1) is the real-time data entropy of the jth parameter at time t-1. Entropy change rate ΔS j (t) reflects the uncertainty and volatility of the parameter in the recent time period. If the entropy change rate of a parameter is large, it means that its importance has increased at the current moment. According to the size of the entropy change rate, it is possible to identify which parameters have changed significantly at the current point in time. These parameters will affect the direction and magnitude of the weight adjustment.

[0102] 3) According to the real-time data entropy change rate, adjust the weight w of each parameter j (t). The adjustment formula is as follows:

[0103]

[0104] In the formula, w j (t) is the weight of the jth parameter at time t, w j (t-1) is the weight of the jth parameter at time t-1, and α is the adjustment coefficient, which controls the sensitivity of weight adjustment. Through the appropriate α value, the system can balance the response speed to real-time changes and the stability of decision-making. α is assigned by expert experience.

[0105] In step S5, the fuzzy processed water quality data and the dynamically adjusted weights are input into the fuzzy reasoning system; according to the pre-built fuzzy rule base, fuzzy reasoning is performed on the input data to obtain the fuzzy control strategy of the electrical equipment.

[0106] Set the fuzzy association rule V = {v1,v2,v3,...,v m}, including at least one of the following rules:

[0107]

[0108] The above table shows the standard after the aquaculture water quality data is normalized, among which the fuzzy control strategy of the electrical equipment corresponding to rule V1 is to reduce the operating power of the aerator by 30% and increase the operating power of the irrigation and drainage system by 30%; the fuzzy control strategy of the electrical equipment corresponding to rule V2 is to reduce the operating power of the aerator by 15% and increase the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V3 is to maintain the operating power of the aerator and the operating power of the irrigation and drainage system unchanged; the fuzzy control strategy of the electrical equipment corresponding to rule V4 is to increase the operating power of the aerator by 15% and reduce the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V5 is to increase the operating power of the aerator by 30% and reduce the operating power of the irrigation and drainage system by 30%;

[0109] Based on the above five fuzzy association set matrices, the fuzzy comprehensive evaluation matrix R can be established. 4ⅹ5 , specifically:

[0110]

[0111] The real-time electrical equipment control results output by the final model are:

[0112] E=w·R=[e1,e2,e3,e4,e5]

[0113] In the formula, w 1×4 is the real-time weight vector.

[0114] The model output is analyzed based on the maximum membership principle, that is, the electrical equipment control to which the largest element in vector E belongs is obtained by comparison. When e1 is the largest, the operating power of the aerator decreases by 30%, and the operating power of the irrigation and drainage system increases by 30%; when e2 is the largest, the operating power of the aerator decreases by 15%, and the operating power of the irrigation and drainage system increases by 15%; when e3 is the largest, the operating power of the aerator and the operating power of the irrigation and drainage system remain basically unchanged; when e4 is the largest, the operating power of the aerator increases by 15%, and the operating power of the irrigation and drainage system decreases by 15%; when e5 is the largest, the operating power of the aerator increases by 30%, and the operating power of the irrigation and drainage system decreases by 30%.

[0115] Example 2

[0116] This embodiment also provides an aquaculture water quality monitoring and control device based on fuzzy logic and dynamic weight adjustment, including a memory and a processor, the memory stores a computer program, and the processor calls the computer program to execute the steps of the aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment as described in the embodiment.

[0117] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment, characterized in that: The following steps are involved: Collect real-time water quality data of fisheries based on multiple water quality parameters; Preprocess the collected water quality data and standardize them to make the data have consistent dimensions; According to the membership functions pre-defined for each water quality parameter, the standardized water quality data is fuzzy processed; Based on the entropy weight method, the initial weight of each water quality parameter is determined, and the real-time data entropy of each water quality parameter is dynamically updated and calculated according to the real-time collected water quality data, and the corresponding data entropy change rate is determined, so as to dynamically adjust the weight of each water quality parameter; According to the fuzzy processed water quality data and the dynamically adjusted weights of various water quality parameters, fuzzy reasoning is performed through a pre-built fuzzy rule library to obtain the corresponding fuzzy control strategy for electrical equipment.

2. A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment according to claim 1, characterized in that: The multiple water quality parameters include temperature, dissolved oxygen, ammonia nitrogen concentration and turbidity.

3. A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment according to claim 2, characterized in that: The membership function corresponding to the temperature is an intermediate distribution, which is optimal in the medium range; the membership function corresponding to the dissolved oxygen content is a trapezoidal distribution that is biased towards the large, and the larger the value, the better the result; the membership functions corresponding to the ammonia nitrogen concentration and turbidity are both biased towards the small distribution, and the smaller the value, the better the result.

4. A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment according to claim 3, characterized in that: The expression of the membership function corresponding to the temperature is: In the formula, μ Medium (T′) is the membership function corresponding to temperature, and T′ is the temperature after standardization; The expression of the membership function corresponding to the dissolved oxygen content is: In the formula, μ High (DO′) is the membership function corresponding to the dissolved oxygen content, and DO′ is the dissolved oxygen content after standardized treatment; The expression of the membership function corresponding to the ammonia nitrogen concentration is: In the formula, μ Low (NH3-N′) is the membership function corresponding to the ammonia nitrogen concentration, and NH3-N′ is the ammonia nitrogen concentration after standardization; The expression of the membership function corresponding to the turbidity is: In the formula, μ Low (Turb′) is the membership function corresponding to turbidity, and Turb′ is the turbidity after normalization.

5. The aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment according to claim 1 is characterized in that: The data preprocessing includes cleaning the collected water quality data to remove outliers and sensor noise, and then processing missing data through interpolation and averaging methods.

6. The aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment according to claim 1 is characterized in that: The data standardization process includes: According to the data after data preprocessing, an evaluation matrix of m monitoring sections and n evaluation indicators is constructed. The expression of the evaluation matrix is: In the formula, R ij It represents the measured data of the jth evaluation index corresponding to the i-th monitoring section; Positive normalization is used for the positive indicators in the evaluation matrix, and reverse normalization is used for the negative indicators. The corresponding expressions are: In the formula, R ij ' is the data after standardization.

7. The aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment according to claim 1 is characterized in that: The calculation expression for determining the initial weight of each water quality parameter based on the entropy weight method is: In the formula, R′ ij is the data after standardization, m is the number of monitoring sections, q ij is the proportion of the i-th sample value under the j-th indicator to the indicator, S j is the entropy value of the jth indicator, w j (0) is the initial weight of each indicator; The calculation expression of the real-time data entropy of each water quality parameter is: In the formula, S j (t) is the real-time data entropy of the jth parameter at time t, p ij (t) is the normalized probability distribution of the jth parameter at time t.

8. A method for monitoring and controlling aquaculture water quality based on fuzzy logic and dynamic weight adjustment according to claim 7, characterized in that: The data entropy change rate is calculated based on the comparison of the information entropy at the current time point t and the previous time point t-1, and the corresponding calculation expression is: ΔS j (t)=S j (t)-S j (t-1) In the formula, ΔS j (t) is the data entropy change rate of the jth parameter at time t, S j (t-1) is the real-time data entropy of the jth parameter at time t-1.

9. The aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment according to claim 1 is characterized in that: The weight adjustment formula of the water quality parameters is: In the formula, w j (t) is the weight of the jth parameter at time t, w j (t-1) is the weight of the jth parameter at time t-1, α is the adjustment coefficient, ΔS j (t) is the data entropy change rate of the jth parameter at time t.

10. The aquaculture water quality monitoring and control method based on fuzzy logic and dynamic weight adjustment according to claim 1, characterized in that: The fuzzy rule base V = {v1, v2, v3, ..., v m }, including at least one of the following rules: The fuzzy control strategy of the electrical equipment corresponding to rule V1 is to reduce the operating power of the aerator by 30% and increase the operating power of the irrigation and drainage system by 30%; the fuzzy control strategy of the electrical equipment corresponding to rule V2 is to reduce the operating power of the aerator by 15% and increase the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V3 is to maintain the operating power of the aerator and the operating power of the irrigation and drainage system unchanged; the fuzzy control strategy of the electrical equipment corresponding to rule V4 is to increase the operating power of the aerator by 15% and reduce the operating power of the irrigation and drainage system by 15%; the fuzzy control strategy of the electrical equipment corresponding to rule V5 is to increase the operating power of the aerator by 30% and reduce the operating power of the irrigation and drainage system by 30%; After the fuzzy processed water quality data is multiplied by the weights of the dynamically adjusted water quality parameters, the most suitable rule is obtained through the fuzzy rule library, and the corresponding fuzzy control strategy is selected to control the electrical equipment.

Images