Dragon fruit growth state evaluation method based on fuzzy logic

Abstract

The invention discloses a dragon fruit growth state evaluation method based on fuzzy logic, and the method comprises the following steps: dynamically adjusting imaging parameters through a variable spectrum sensor, and collecting the multi-dimensional data and growth health condition image data of dragon fruits in real time; preprocessing the collected data to generate a standardized data set; defining a fuzzy set for each evaluation index, and representing the fuzzy sets of different grades by using membership functions; storing and managing the preprocessed data by using a holographic storage medium, and performing preliminary analysis; processing and calculating data through a topological insulator calculation technology, and constructing and optimizing a fuzzy rule base; the standardized data set and the image data are input into a fuzzy rule base, and the membership degree of the growth state is calculated through fuzzy reasoning; carrying out defuzzification on the fuzzy reasoning result by adopting a self-adaptive gravity center method based on clustering, and converting the fuzzy reasoning result into a specific growth state evaluation result; and generating a comprehensive evaluation result of the growth state of the pitaya in combination with comprehensive analysis of the membership degree of each evaluation index.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural production and management, and in particular to a method for evaluating the growth state of pitaya based on fuzzy logic. Background Art

[0002] With the development of modern agricultural technology, refined management and intelligent monitoring are increasingly being used in agricultural production. Especially in the planting process of high value-added crops such as pitaya, real-time monitoring and evaluation of its growth status are of great significance for improving yield and quality. As a tropical and subtropical fruit tree, pitaya has certain requirements for temperature and light. For example, a day / night temperature difference of 30 / 20℃ is conducive to the net photosynthesis of pitaya stems and vines. When the ambient temperature is higher than 40℃, the pitaya plant will enter a dormant state. When the ambient temperature is lower than 8℃, the young stems and vines are susceptible to cold damage. Pitaya is a long-day plant, and the daylight hours usually need to meet 12 hours to bloom and bear fruit normally, but high light intensity will cause the pitaya stems and vines to burn, whiten, or even dry up. Traditional methods for evaluating the growth status of pitaya mainly rely on manual observation and simple numerical statistical analysis, which have many shortcomings.

[0003] Manual observation methods are time-consuming and laborious, highly subjective, and difficult to ensure the accuracy and consistency of data. At the same time, manual observation is difficult to achieve real-time monitoring, and problems in the growth process cannot be discovered and handled in a timely manner, which may lead to a decrease in yield and quality. Secondly, although simple numerical statistical analysis methods can quantify the growth status to a certain extent, due to the lack of comprehensive consideration of complex environments and multiple growth factors, the evaluation results are often not comprehensive and accurate.

[0004] Existing pitaya growth status monitoring technologies mainly focus on the application of sensor technology and data processing technology. Spectral imaging technology and sensor networks can be used to collect multi-dimensional data during the growth of pitaya. Although sensor networks and spectral imaging technologies in existing technologies can collect multi-dimensional data, the accuracy and consistency of data are difficult to guarantee under different growth stages and environmental conditions. In addition, existing sensor technologies have poor adaptability to environmental changes, resulting in large fluctuations in data quality.

[0005] Existing methods for evaluating the growth status of pitaya usually rely on simple data statistics and analysis methods, which are difficult to handle complex, multi-dimensional data. These methods have deficiencies in data preprocessing, outlier detection and noise removal, resulting in low accuracy and reliability of data analysis. In the prior art, the evaluation of the growth status of pitaya is often limited to the analysis of a single indicator, and lacks a comprehensive evaluation model for multi-dimensional data. This leads to one-sided evaluation results that cannot fully reflect the actual growth status of pitaya. Existing pitaya growth status monitoring systems are difficult to achieve real-time monitoring and dynamic decision-making. This is because existing systems usually lack efficient data processing and computing capabilities, and cannot respond and adjust planting strategies in a timely manner.

[0006] Therefore, how to provide a method for evaluating the growth status of pitaya based on fuzzy logic is an urgent problem that technicians in this field need to solve. Summary of the invention

[0007] One object of the present invention is to propose a method for evaluating the growth status of pitaya based on fuzzy logic. The present invention makes full use of variable spectrum sensors, holographic storage media, holographic computing technology and topological insulator computing technology, and describes in detail a method for realizing real-time, high-precision monitoring and evaluation of the growth status of pitaya. The method has the advantages of high accuracy and adaptability of data acquisition, strong data processing and analysis capabilities, a comprehensive evaluation model, and strong real-time monitoring and dynamic decision-making capabilities.

[0008] The method for evaluating the growth status of pitaya based on fuzzy logic according to an embodiment of the present invention comprises the following steps: S1. Use variable spectrum sensors to dynamically adjust imaging parameters to adapt to different growth stages and environmental conditions, collect multi-dimensional data during the growth of pitaya in real time, and obtain image data on growth health status; S2, preprocess the collected multi-dimensional data, remove outliers and noise, and generate a standardized data set; S3, define the corresponding fuzzy set for each evaluation index, and use membership functions to represent fuzzy sets of different levels; S4, using holographic storage media to store and manage the pre-processed dragon fruit growth status data, and combining holographic computing technology to perform preliminary analysis on the data; S5. Using topological insulator computing technology, data processing and calculation are performed through the edge states of topological insulators to build and optimize the fuzzy rule base to achieve real-time monitoring and dynamic decision-making of the growth status of pitaya; S6, inputting the standardized data set and the growth health status image data into the fuzzy rule base, calculating the output of each fuzzy rule through fuzzy reasoning, and obtaining the membership degree of each growth status; S7, defuzzifying the fuzzy reasoning results through the clustering-based adaptive centroid method and converting them into specific growth status evaluation results; S8. Combine the membership degree of each evaluation index to conduct a comprehensive analysis and generate a comprehensive evaluation result of the growth status of pitaya.

[0009] Optionally, the S1 specifically includes: S11, using a variable spectrum sensor to adjust the spectrum imaging parameters in real time to adapt to different growth stages and environmental conditions of pitaya to obtain the best imaging effect; S12. Collect multi-dimensional data of dragon fruit in real time through sensor network, including the number of fruits and quality , and environmental factors; S13. Using imaging equipment to obtain image data of the growth and health status of pitaya ,The image data can reflect the health status and growth of pitaya stems and fruits; S14, multi-dimensional data and image data through wireless sensor networks Real-time transmission to the central database for storage and processing; S15. During the data collection process, the frequency and accuracy of the data collected by the sensor are adjusted dynamically according to the actual situation.

[0010] Optionally, the S3 specifically includes: S31. Define the fuzzy set of each evaluation index, including the number of fruits , fruit quality ,temperature ,humidity , light intensity , soil nutrients and image data ; S32. Set a membership function for each evaluation index. The membership function is used to represent fuzzy sets of different levels. The membership function of is defined as low, medium, and high; S33. Use biologically inspired evolutionary algorithms to optimize the specific form of membership functions. By simulating the biological evolution process, including selection, crossover, and mutation operations, the membership function parameters are optimized. , , and Dynamic adjustments are made so that the membership function can adapt to changes in different growth states and environmental conditions: ; Among them, the parameters , , and In the evolutionary algorithm, the optimization effect is evaluated by the fitness function; S34. Combining the membership functions of the evaluation indicators, a comprehensive fuzzy evaluation index of the growth status of pitaya is generated through a multi-objective optimization algorithm.

[0011] Optionally, the S4 specifically includes: S41, storing and managing the pre-processed pitaya growth status data through a holographic storage medium, wherein the data includes standardized multi-dimensional data and growth health status image data , define the storage function of the storage medium as , which means in three-dimensional space coordinates the data storage situation at the location; S42, using the storage characteristics of the holographic storage technology to store the pitaya growth status data on a holographic storage medium; S43. Perform a preliminary analysis on the stored data by combining holographic computing technology, and use the parallel processing capability of holographic computing to quickly process and analyze the data. The processing function is ; S44. Through the holographic computing model, the growth status data of the pitaya is processed in blocks to achieve rapid data processing. The block function is: , Number the chunks: ; in, Represents the holographic block processing operator, Indicates The volume of the block; S45. Use holographic Fourier transform to quickly process data: ; in, , , is the frequency variable of Fourier transform; S46. The data after preliminary analysis are merged and processed comprehensively to generate a data set that can be used for fuzzy reasoning and decision-making.

[0012] Optionally, the S5 specifically includes: S51. Using topological insulator computing technology, the edge states of topological insulators are used to process and calculate the pitaya growth status data set that can be used for fuzzy reasoning and decision-making, and a fuzzy rule base is constructed. The calculation function of the topological insulator is defined as: , which means in three-dimensional space coordinates the data processing situation at the relevant department; S52. Based on the high-dimensional topological protection characteristics of topological insulators, the processed pitaya growth status data is further optimized to make the rules in the fuzzy rule base stable when processing complex data. The optimization function is : ; in, Represents an optimization operator, represents the rule function, is the edge state function, is the topological protection factor, is the integration variable; S53, parallel processing of the optimized pitaya growth state data is performed through the edge state of the topological insulator, using the parallel processing function Optimize data processing speed and system real-time performance: ; in, represents the parallel processing coefficient, Indicates processing units; S54. Using the nonlinear edge state effect of topological insulators, the complexity of the pitaya growth state data after parallel processing is optimized to process high-complexity data. The nonlinear edge state effect function is: : ; in, represents a nonlinear operator, represents the complexity function; S55. Through the anti-interference characteristics of topological insulators, the fuzzy rule base in the complex environment after processing and management is formed to form an optimized fuzzy rule base to adapt to the real-time performance and accuracy of the system.

[0013] Optionally, the S6 specifically includes: S61. Standardized data sets and growth health status image data Input fuzzy rule base, define the set of input data as And the image data set is ; S62, through the adaptive fuzzy inference algorithm, dynamically adjust the inference rules and parameters according to the input data and environmental changes, and calculate the output membership of each fuzzy rule: ; in, represents the output membership, Represents input data The membership degree of Represents image data The degree of membership; S63. Using the evolutionary fuzzy reasoning algorithm and combining it with the optimization mechanism of the genetic algorithm, the membership functions and rules in the fuzzy reasoning process are optimized by evolution: ; in, represents the optimized output membership, Represents the optimized input data The membership degree of Represents optimized image data The degree of membership; S64. Using the hybrid defuzzification method, the results of the evolutionary fuzzy reasoning algorithm are converted into specific growth status evaluation results. The calculation formula of the centroid method is: ; The calculation formula of fuzzy entropy method is: ; in, is the specific evaluation value after defuzzification, is the fuzzy entropy; S65. Provide real-time management suggestions based on the evaluation results of the specific growth status of pitaya, and implement dynamic adjustment measures through automation.

[0014] Optionally, the S7 specifically includes: S71. The fuzzy reasoning results are converted into specific growth status evaluation results through the defuzzification method, and the set of fuzzy reasoning outputs is defined as ,in Indicates The output membership of each fuzzy inference rule represents the evaluation of the growth status of pitaya by different fuzzy rules under various input conditions. S72, using a clustering-based adaptive centroid method to defuzzify the fuzzy reasoning output, performing cluster analysis on the fuzzy reasoning output, identifying similar membership patterns, and grouping fuzzy reasoning results with similar membership patterns: ; in, Indicates clusters, represents the distance function between membership degrees, is the clustering threshold; S73, calculating the centroid of the membership degree in each cluster, and determining the representative growth state evaluation value of each cluster: ; in, Indicates The centroid value of each cluster; S74, combining the centroid values ​​of all clusters, and obtaining the final growth status evaluation value by weighted average method, wherein the weight is dynamically adjusted according to the size of the cluster and the membership distribution; S75. The fuzzy reasoning results are comprehensively analyzed through the clustering-based adaptive centroid method to provide a comprehensive evaluation of the growth status of pitaya.

[0015] The beneficial effects of the present invention are: The present invention utilizes a variable spectrum sensor to dynamically adjust imaging parameters, adapt to different growth stages and environmental conditions, and can collect multi-dimensional data and growth health status image data of pitaya in real time. This innovation improves the accuracy and consistency of data acquisition, and can obtain the best imaging effect under different environmental conditions, thereby more accurately reflecting the actual growth status of pitaya. Specifically, the variable spectrum sensor can dynamically adjust imaging parameters according to the growth stage and environmental conditions of pitaya to ensure that the collected data has high resolution and accuracy. By preprocessing the collected multi-dimensional data, removing outliers and noise, and generating a standardized data set, the data quality is ensured. This preprocessing step improves the accuracy and reliability of subsequent analysis by filtering out interfering data. The standardized data set includes multi-dimensional data such as the number and quality of pitaya fruits, as well as environmental factors. After preprocessing, the outliers and noise are removed from these data, and they are converted into a unified format and dimension, which is convenient for subsequent analysis and processing.

[0016] The present invention utilizes holographic storage media and holographic computing technology to achieve efficient storage, management and preliminary analysis of data, and improves data processing speed and accuracy. Holographic storage media can efficiently store large-scale data in three-dimensional space, and holographic computing technology achieves rapid analysis of data through parallel processing capabilities. This innovation solves the bottleneck of efficiency and accuracy of traditional storage and processing technologies. Holographic storage media stores the growth data of pitaya in three-dimensional space through holographic optical principles, which greatly increases storage capacity and speeds up access. Holographic computing technology utilizes the characteristics of holographic storage to perform preliminary analysis of data through parallel processing, such as data classification, clustering and feature extraction, thereby providing a high-quality data foundation for subsequent fuzzy reasoning.

[0017] The present invention utilizes topological insulator computing technology, performs data processing and calculation through the edge state of the topological insulator, and constructs and optimizes the fuzzy rule base. The topological insulator computing technology simulates the quantum state of the topological insulator, utilizes the anti-interference characteristics of its edge state when processing data, performs high-precision calculation and processing on the growth data of the dragon fruit, constructs and optimizes the fuzzy rule base, and enables the rule base to maintain high accuracy and robustness when facing complex and changeable data. The fuzzy reasoning results are defuzzified by using the clustering-based adaptive centroid method and converted into specific growth state evaluation results. This method identifies similar membership patterns through cluster analysis to improve the accuracy and robustness of defuzzification. The CACM method first clusters the fuzzy reasoning results, divides the results with similar membership patterns into one category, and then calculates the centroid of each category to improve the accuracy of defuzzification. Finally, the centroid results of each category are integrated to obtain the growth state evaluation value of the dragon fruit. This method combines the advantages of cluster analysis and centroid method, and can maintain high computational efficiency and robustness while improving the accuracy of defuzzification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of the method for evaluating the growth status of pitaya based on fuzzy logic proposed by the present invention; Figure 2 A flow chart of the present invention for dynamically adjusting imaging parameters using a variable spectrum sensor, collecting multi-dimensional data of pitaya and image data of growth and health status in real time, storing and managing pre-processed data using a holographic storage medium, and performing preliminary analysis; Figure 3 The present invention processes and calculates data through topological insulator computing technology, constructs and optimizes a fuzzy rule base, and uses a clustering-based adaptive centroid method to defuzzify the fuzzy reasoning results and convert them into a schematic diagram of specific growth status evaluation results. DETAILED DESCRIPTION

[0019] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0020] refer to Figure 1-3 , a method for evaluating the growth status of pitaya based on fuzzy logic includes the following steps: S1. Use variable spectrum sensors to dynamically adjust imaging parameters to adapt to different growth stages and environmental conditions, collect multi-dimensional data during the growth of pitaya in real time, including fruit quantity and quality, as well as environmental factors, and obtain image data on growth health status; S2, preprocess the collected multi-dimensional data, remove outliers and noise, and generate a standardized data set; S3, define the corresponding fuzzy set for each evaluation index, and use membership functions to represent fuzzy sets of different levels; S4, using holographic storage media to store and manage the pre-processed dragon fruit growth status data, and combining holographic computing technology to perform preliminary analysis on the data; S5. Using topological insulator computing technology, data processing and calculation are performed through the edge states of topological insulators to build and optimize the fuzzy rule base to achieve real-time monitoring and dynamic decision-making of the growth status of pitaya; S6, inputting the standardized data set and the growth health status image data into the fuzzy rule base, calculating the output of each fuzzy rule through fuzzy reasoning, and obtaining the membership degree of each growth status; S7, defuzzifying the fuzzy reasoning results through the clustering-based adaptive centroid method and converting them into specific growth status evaluation results; S8. Combine the membership degree of each evaluation index to conduct a comprehensive analysis and generate a comprehensive evaluation result of the growth status of pitaya.

[0021] In this implementation, S1 specifically includes: S11, using a variable spectrum sensor to adjust the spectrum imaging parameters in real time to adapt to different growth stages and environmental conditions of pitaya to obtain the best imaging effect; S12. Collect multi-dimensional data of dragon fruit in real time through sensor network, including the number of fruits and quality , and environmental factors; S13. Using imaging equipment to obtain image data of the growth and health status of pitaya ,The image data can reflect the health status and growth of the stems and fruits of pitaya plants; S14, multi-dimensional data and image data through wireless sensor networks Real-time transmission to the central database for storage and processing; S15. During the data collection process, the frequency and accuracy of the data collected by the sensor are adjusted dynamically according to the actual situation.

[0022] In this implementation, S3 specifically includes: S31. Define the fuzzy set of each evaluation index, including the number of fruits , fruit quality ,temperature ,humidity , light intensity , soil nutrients and image data ; S32. Set a membership function for each evaluation index. The membership function is used to represent fuzzy sets of different levels. The membership function of is defined as low, medium, and high; S33. Use biologically inspired evolutionary algorithms to optimize the specific form of membership functions. By simulating the biological evolution process, including selection, crossover, and mutation operations, the membership function parameters are optimized. , , and Dynamic adjustments are made so that the membership function can adapt to changes in different growth states and environmental conditions: ; Among them, the parameters , , and In the evolutionary algorithm, the optimization effect is evaluated by the fitness function; S34. Combining the membership functions of the evaluation indicators, a comprehensive fuzzy evaluation index of the growth status of pitaya is generated through a multi-objective optimization algorithm.

[0023] In this implementation manner, the S4 specifically includes: S41, storing and managing the pre-processed pitaya growth status data through a holographic storage medium, wherein the data includes standardized multi-dimensional data and growth health status image data , define the storage function of the storage medium as , which means in three-dimensional space coordinates the data storage situation at the location; S42, using the storage characteristics of the holographic storage technology to store the pitaya growth status data on a holographic storage medium; S43. Perform a preliminary analysis on the stored data by combining holographic computing technology, and use the parallel processing capability of holographic computing to quickly process and analyze the data. The processing function is ; S44. Through the holographic computing model, the growth status data of the pitaya is processed in blocks to achieve rapid data processing. The block function is: , Number the chunks: ; in, Represents the holographic block processing operator, Indicates The volume of the block; S45. Use holographic Fourier transform to quickly process data: ; in, , , is the frequency variable of Fourier transform; S46. The data after preliminary analysis are merged and processed comprehensively to generate a data set that can be used for fuzzy reasoning and decision-making.

[0024] In this implementation manner, S5 specifically includes: S51. Using topological insulator computing technology, the edge states of topological insulators are used to process and calculate the pitaya growth status data set that can be used for fuzzy reasoning and decision-making, and a fuzzy rule base is constructed. The calculation function of the topological insulator is defined as: , which means in three-dimensional space coordinates the data processing situation at the place where the S52. Based on the high-dimensional topological protection characteristics of topological insulators, the processed pitaya growth status data is further optimized to make the rules in the fuzzy rule base stable when processing complex data. The optimization function is : ; in, Represents an optimization operator, represents the rule function, is the edge state function, is the topological protection factor, is the integration variable; S53, parallel processing of the optimized pitaya growth state data is performed through the edge state of the topological insulator, using the parallel processing function Optimize data processing speed and system real-time performance: ; in, represents the parallel processing coefficient, Indicates processing units; S54. Using the nonlinear edge state effect of topological insulators, the complexity of the pitaya growth state data after parallel processing is optimized to process high-complexity data. The nonlinear edge state effect function is: : ; in, represents a nonlinear operator, represents the complexity function; S55. Through the anti-interference characteristics of topological insulators, the fuzzy rule base in the complex environment after processing and management is formed to form an optimized fuzzy rule base to adapt to the real-time performance and accuracy of the system.

[0025] In this implementation manner, S6 specifically includes: S61. Standardized data sets and growth health status image data Input fuzzy rule base, define the set of input data as And the image data set is ; S62, through the adaptive fuzzy inference algorithm, dynamically adjust the inference rules and parameters according to the input data and environmental changes, and calculate the output membership of each fuzzy rule: ; in, represents the output membership, Represents input data The membership degree of Represents image data The degree of membership; S63. Using the evolutionary fuzzy reasoning algorithm and combining it with the optimization mechanism of the genetic algorithm, the membership functions and rules in the fuzzy reasoning process are optimized by evolution: ; in, represents the optimized output membership, Represents the optimized input data The membership degree of Represents optimized image data The degree of membership; S64. Using the hybrid defuzzification method, the results of the evolutionary fuzzy reasoning algorithm are converted into specific growth status evaluation results. The calculation formula of the centroid method is: ; The calculation formula of fuzzy entropy method is: ; in, is the specific evaluation value after defuzzification, is the fuzzy entropy; S65. Provide real-time management suggestions based on the evaluation results of the specific growth status of pitaya, and implement dynamic adjustment measures through automation.

[0026] In this implementation manner, the S7 specifically includes: S71. The fuzzy reasoning results are converted into specific growth status evaluation results through the defuzzification method, and the set of fuzzy reasoning outputs is defined as ,in Indicates The output membership of each fuzzy inference rule represents the evaluation of the growth status of pitaya by different fuzzy rules under various input conditions. S72, using a clustering-based adaptive centroid method to defuzzify the fuzzy reasoning output, performing cluster analysis on the fuzzy reasoning output, identifying similar membership patterns, and grouping fuzzy reasoning results with similar membership patterns: ; in, Indicates clusters, represents the distance function between membership degrees, is the clustering threshold; S73, calculating the centroid of the membership degree in each cluster, and determining the representative growth state evaluation value of each cluster: ; in, Indicates The centroid value of each cluster; S74, combining the centroid values ​​of all clusters, and obtaining the final growth status evaluation value by weighted average method, wherein the weight is dynamically adjusted according to the size of the cluster and the membership distribution; S75. The fuzzy reasoning results are comprehensively analyzed through the clustering-based adaptive centroid method to provide a comprehensive evaluation of the growth status of pitaya.

[0027] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for evaluating the growth status of pitaya based on fuzzy logic, characterized in that: The steps include: S1. Use variable spectrum sensors to dynamically adjust imaging parameters to adapt to different growth stages and environmental conditions, collect multi-dimensional data during the growth of pitaya in real time, and obtain image data on growth health status; S2, preprocess the collected multi-dimensional data, remove outliers and noise, and generate a standardized data set; S3, define the corresponding fuzzy set for each evaluation index, and use membership functions to represent fuzzy sets of different levels; S4, using holographic storage media to store and manage the pre-processed dragon fruit growth status data, and combining holographic computing technology to perform preliminary analysis on the data; S5. Using topological insulator computing technology, data processing and calculation are performed through the edge states of topological insulators to build and optimize the fuzzy rule base to achieve real-time monitoring and dynamic decision-making of the growth status of pitaya; S6, inputting the standardized data set and the growth health status image data into the fuzzy rule base, calculating the output of each fuzzy rule through fuzzy reasoning, and obtaining the membership degree of each growth status; S7, defuzzifying the fuzzy reasoning results through the clustering-based adaptive centroid method and converting them into specific growth status evaluation results; S8. Combine the membership degree of each evaluation index to conduct a comprehensive analysis and generate a comprehensive evaluation result of the growth status of pitaya.

2. The method for evaluating the growth state of pitaya based on fuzzy logic according to claim 1, characterized in that: The S1 specifically includes: S11, using a variable spectrum sensor to adjust the spectrum imaging parameters in real time to adapt to different growth stages and environmental conditions of pitaya to obtain the best imaging effect; S12, collecting multi-dimensional data of pitaya in real time through a sensor network; S13. Using imaging equipment to obtain image data of the growth and health status of pitaya ,The image data can reflect the health status and growth of pitaya stems and fruits; S14, multi-dimensional data and image data through wireless sensor networks Real-time transmission to the central database for storage and processing; S15. During the data collection process, the frequency and accuracy of the data collected by the sensor are adjusted dynamically according to the actual situation.

3. The method for evaluating the growth state of pitaya based on fuzzy logic according to claim 1, characterized in that, The S3 specifically includes: S31. Define the fuzzy set of each evaluation index, including the number of fruits , fruit quality ,temperature ,humidity , light intensity , soil nutrients and image data ; S32. Set a membership function for each evaluation index. The membership function is used to represent fuzzy sets of different levels. The membership function of is defined as low, medium, and high; S33. Use biologically inspired evolutionary algorithms to optimize the specific form of membership functions. By simulating the biological evolution process, including selection, crossover, and mutation operations, the membership function parameters are optimized. , , and Dynamic adjustments are made so that the membership function can adapt to changes in different growth states and environmental conditions: ； Among them, the parameters , , and In the evolutionary algorithm, the optimization effect is evaluated by the fitness function; S34. Combining the membership functions of the evaluation indicators, a comprehensive fuzzy evaluation index of the growth status of pitaya is generated through a multi-objective optimization algorithm.

4. The method for evaluating the growth state of pitaya based on fuzzy logic according to claim 1, characterized in that: The S4 specifically includes: S41, storing and managing the pre-processed pitaya growth status data through a holographic storage medium, wherein the data includes standardized multi-dimensional data and growth health status image data , define the storage function of the storage medium as , which means in three-dimensional space coordinates the data storage situation at the location; S42, using the storage characteristics of the holographic storage technology to store the pitaya growth status data on a holographic storage medium; S43. Combine holographic computing technology to perform preliminary analysis on the stored data, and use the parallel processing capability of holographic computing to quickly process and analyze the data. The processing function is ; S44. Through the holographic computing model, the growth status data of the pitaya is processed in blocks to achieve rapid data processing. The block function is: , Number the chunks: ； in, Represents the holographic block processing operator, Indicates The volume of the block; S45. Use holographic Fourier transform to quickly process data: ； in, , , is the frequency variable of Fourier transform; S46. The data after preliminary analysis are merged and processed comprehensively to generate a data set that can be used for fuzzy reasoning and decision-making.

5. The method for evaluating the growth state of pitaya based on fuzzy logic according to claim 1, characterized in that: The S5 specifically includes: S51. Using topological insulator computing technology, the generated pitaya growth status data set that can be used for fuzzy reasoning and decision-making is processed and calculated through the edge state of the topological insulator, a fuzzy rule base is constructed, and the calculation function of the topological insulator is defined as: , which means in three-dimensional space coordinates the data processing situation at the relevant department; S52. Based on the high-dimensional topological protection characteristics of topological insulators, the processed pitaya growth status data is further optimized to make the rules in the fuzzy rule base stable when processing complex data. The optimization function is : ； in, Represents an optimization operator, represents the rule function, is the edge state function, is the topological protection factor, is the integration variable; S53, parallel processing of the optimized pitaya growth state data is performed through the edge state of the topological insulator, using the parallel processing function Optimize data processing speed and system real-time performance: ； in, represents the parallel processing coefficient, Indicates processing units; S54. Using the nonlinear edge state effect of topological insulators, the complexity of the pitaya growth state data after parallel processing is optimized to process high-complexity data. The nonlinear edge state effect function is: : ； in, represents a nonlinear operator, represents the complexity function; S55. Through the anti-interference characteristics of topological insulators, the fuzzy rule base in the complex environment after processing and management is formed to form an optimized fuzzy rule base to adapt to the real-time and accuracy of the system.

6. The method for evaluating the growth state of pitaya based on fuzzy logic according to claim 1, characterized in that: The S6 specifically includes: S61. Standardized data sets and growth health status image data Input fuzzy rule base, define the set of input data as And the image data set is ; S62, through the adaptive fuzzy inference algorithm, dynamically adjust the inference rules and parameters according to the input data and environmental changes, and calculate the output membership of each fuzzy rule: ； in, represents the output membership, Represents input data The membership degree of Represents image data The degree of membership; S63. Using the evolutionary fuzzy reasoning algorithm and combining it with the optimization mechanism of the genetic algorithm, the membership functions and rules in the fuzzy reasoning process are optimized by evolution: ； in, represents the optimized output membership, Represents the optimized input data The membership degree of Represents optimized image data The degree of membership; S64. Using the hybrid defuzzification method, the results of the evolutionary fuzzy reasoning algorithm are converted into specific growth status evaluation results. The calculation formula of the centroid method is: ； The calculation formula of fuzzy entropy method is: ； in, is the specific evaluation value after defuzzification, is the fuzzy entropy; S65. Provide real-time management suggestions based on the evaluation results of the specific growth status of pitaya, and implement dynamic adjustment measures through automation.

7. The method for evaluating the growth status of pitaya based on fuzzy logic according to claim 1, characterized in that: The S7 specifically includes: S71. The fuzzy reasoning results are converted into specific growth status evaluation results through the defuzzification method, and the set of fuzzy reasoning outputs is defined as ,in Indicates The output membership of each fuzzy inference rule represents the evaluation of the growth status of pitaya by different fuzzy rules under various input conditions. S72, using a clustering-based adaptive centroid method to defuzzify the fuzzy reasoning output, performing cluster analysis on the fuzzy reasoning output, identifying similar membership patterns, and grouping fuzzy reasoning results with similar membership patterns: ； in, Indicates clusters, represents the distance function between membership degrees, is the clustering threshold; S73, calculating the centroid of the membership degree in each cluster, and determining the representative growth state evaluation value of each cluster: ； in, Indicates The centroid value of each cluster; S74, combining the centroid values ​​of all clusters, and obtaining the final growth status evaluation value by weighted average method, wherein the weight is dynamically adjusted according to the size of the cluster and the membership distribution; S75. The fuzzy reasoning results are comprehensively analyzed through the clustering-based adaptive centroid method to provide a comprehensive evaluation of the growth status of pitaya.

Images