Accurate cold storage and temperature control method for multi-temperature-zone cold chain distribution of fruits and vegetables

Abstract

The invention relates to the technical field of cold-chain logistics intelligent temperature control, and particularly discloses a fruit and vegetable multi-temperature-zone cold-chain distribution accurate cold storage and temperature control method, a transportation space is divided into a plurality of independent temperature control zones, each temperature control zone is specially used for storing specific types of fruits and vegetables, and temperature and power supply data in each zone are monitored in real time; a temperature abnormal fluctuation characteristic value and a power supply fluctuation characteristic value are respectively calculated by using fast Fourier transform and Haar wavelet transform, the stability of temperature and power supply is evaluated, and the influence degree of power supply on the temperature stability is further analyzed by using a gradient boosting tree model. And calculating a power supply regulation value based on the support vector regression model, and dynamically adjusting the power supply of the corresponding region to maintain the optimal temperature condition.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent temperature control in cold chain logistics, and particularly relates to a precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables. Background Art

[0002] With the continuous improvement of people's requirements for food safety and quality, the multi-temperature zone cold chain distribution system for fruits and vegetables plays a crucial role in modern agricultural logistics. Traditional cold chain distribution mainly relies on refrigeration equipment with single-temperature control. However, different types of fruits and vegetables have different requirements for storage environments, including optimal temperature, humidity, and other conditions. To meet these diverse needs, modern cold chain logistics has gradually shifted to using multi-temperature zone control systems, which can maintain multiple different temperature ranges within the same transportation vehicle or storage space to adapt to the optimal preservation conditions of different types of fruits and vegetables.

[0003] The existing technology has the following problems:

[0004] When precisely controlling the cold storage temperature in the multi-temperature zone cold chain distribution of fruits and vegetables, the stability of the power supply is directly related to the efficiency of the refrigeration system, which in turn affects the accuracy of temperature control. However, current cold chain management systems rarely have the ability to monitor and analyze power supply fluctuations in real time, making it difficult to detect and solve problems caused by unstable power supply in a timely manner. Summary of the Invention

[0005] The purpose of the present invention is to provide a precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables to solve the problems in the above background.

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

[0007] A precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables, comprising the following steps:

[0008] S1: Divide the transportation space into multiple independent temperature control zones, and each zone is dedicated to storing one type of fruit or vegetable;

[0009] S2: Real-time monitor the temperature data in each independent temperature control zone, and evaluate the temperature stability in each temperature control zone according to the degree of fluctuation of the temperature data;

[0010] S3: Real-time monitor the power supply during the transportation of fruits and vegetables, and evaluate the power supply stability in each temperature control zone according to the degree of power supply fluctuation;

[0011] S4: Analyze the degree of influence of power supply stability on temperature stability, and dynamically regulate the power supply according to the analysis results.

[0012] As a further solution of the present invention: The evaluation of the temperature stability in each temperature control area specifically includes:

[0013] During the transportation cycle of fruits and vegetables, in time series, the temperature data in each independent temperature control area is acquired in real time. According to the fluctuation amplitude of the temperature data in each independent temperature control area, the temperature abnormal fluctuation eigenvalue is calculated, and it is judged whether the temperature abnormal fluctuation eigenvalue is greater than or equal to the preset threshold. If so, the temperature in the corresponding temperature control area is unstable and is recorded as a temperature abnormal area. If not, the temperature in the corresponding temperature control area is stable and is recorded as a temperature normal area.

[0014] As a further solution of the present invention: The process of obtaining the temperature abnormal fluctuation eigenvalue is as follows:

[0015] In time series, the temperature data in each independent temperature control area is acquired in real time. The fast Fourier transform is applied to the temperature data in each independent temperature control area to convert it from the time domain to the frequency domain. After the fast Fourier transform, a set of frequency components is obtained, and the amplitude and phase information of the frequency components are recorded. In the frequency domain, the frequency domain components are divided into two parts: the low-frequency band and the high-frequency band, and only the frequency components corresponding to the high-frequency band are retained. The sum of the squares of the amplitudes of each frequency component in the high-frequency band is calculated to obtain the energy density of the high-frequency band. The ratio of the energy density of the high-frequency band to the total energy density of all frequency bands is calculated to obtain the temperature abnormal fluctuation eigenvalue.

[0016] As a further solution of the present invention: The evaluation of the power supply stability in each temperature control area specifically includes:

[0017] During the transportation cycle of fruits and vegetables, in time series, the power supply data in each independent temperature control area is acquired in real time. According to the power supply fluctuation degree in each transportation cycle of each fruit and vegetable, in each independent temperature control area, the power supply fluctuation eigenvalue is calculated, and it is judged whether the power supply fluctuation eigenvalue is greater than or equal to the preset threshold. If so, the power supply in the corresponding temperature control area is unstable. If not, the power supply in the corresponding temperature control area is stable.

[0018] As a further solution of the present invention: The process of obtaining the power supply fluctuation eigenvalue is as follows:

[0019] During the transportation cycle of fruits and vegetables, for each independent temperature control area, the power supply data is continuously collected at a fixed time interval; the Haar wavelet transform is applied to the collected power supply data for decomposition, and the Haar wavelet transform decomposes the power supply data into two parts: the approximation coefficient and the detail coefficient;

[0020] Filter the detail coefficients. Calculate the energy of the detail coefficients by squaring them, sum up the energies of all detail coefficients to obtain the total energy of the detail coefficients, and calculate the ratio of the total energy of the detail coefficients to the total energy of the approximation coefficients and the detail coefficients to obtain the power supply fluctuation eigenvalue.

[0021] As a further solution of the present invention: Analyzing the influence degree of the power supply stability on the temperature stability specifically includes:

[0022] Based on the temperature anomaly region, obtain the temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue in each temperature regulation region, and construct a machine learning model. According to the model output, judge the influence degree of the power supply stability on the temperature stability.

[0023] As a further solution of the present invention: Obtain the temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue in each temperature regulation region, construct the temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue into a comprehensive feature vector as the input of the machine learning model, the output of the model is the influence eigenvalue, take minimizing the error between the predicted influence eigenvalue and the actual influence eigenvalue as the training objective of the model, according to the trained model, output the influence eigenvalue, and judge the influence degree of the power supply stability on the temperature stability. The machine learning model is a gradient boosting tree model.

[0024] As a further solution of the present invention: Judging the influence degree of the power supply stability on the temperature stability specifically includes:

[0025] Judge whether the influence eigenvalue is greater than or equal to a preset threshold. If so, there is a serious influence. If not, there is a slight influence.

[0026] As a further solution of the present invention: Dynamically regulating the power supply according to the analysis result specifically includes:

[0027] Based on the temperature anomaly region with serious influence, calculate the power supply regulation value according to the temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue in the corresponding region, and dynamically regulate the power supply in the temperature anomaly region according to the power supply regulation value.

[0028] As a further solution of the present invention: The process of obtaining the power supply regulation value is as follows:

[0029] Obtain the temperature anomaly fluctuation eigenvalue and power supply fluctuation eigenvalue of the temperature anomaly area with serious influence, take the temperature anomaly fluctuation eigenvalue and power supply fluctuation eigenvalue in the temperature anomaly area as the input of the support vector regression model, use minimizing the error between the predicted power supply regulation value and the actual power supply regulation value as the training objective of the support vector regression model, and output the power supply regulation value according to the trained model.

[0030] Advantages of the present invention:

[0031] (1) By real-time monitoring the temperature data in each independent temperature regulation area and using the fast Fourier transform (FFT) technology to convert the time-domain data to the frequency domain, the present invention can accurately identify and quantify the energy density in the high-frequency band as the temperature anomaly fluctuation eigenvalue, thus significantly improving the sensitivity to sudden and transient temperature fluctuations. This method can not only detect potential problems at an early stage, but also provide a scientific basis for taking corrective measures in a timely manner. Further, by combining the support vector regression (SVR) model to calculate the power supply regulation value and dynamically adjusting the power supply of the corresponding area according to this value, the precise response and optimized regulation of the power supply fluctuation are realized. This method of comprehensively applying advanced signal processing technology and machine learning models not only avoids over-compensation or under-compensation, but also ensures that each independent temperature regulation area always maintains the best temperature conditions, greatly improving the stability and efficiency of the cold chain logistics system. Through this innovative solution, the present invention not only solves the problems of low temperature control accuracy and slow response speed in the traditional cold chain management system, but also effectively reduces the loss of goods caused by unstable power supply, ensuring the freshness and quality of fruits and vegetables during the whole transportation process, and providing a more intelligent, efficient and reliable solution for modern cold chain logistics.

[0032] (2) Existing cold chain management systems generally lack the ability to monitor and deeply analyze power supply fluctuations in real time. This results in difficulty in promptly detecting and effectively solving potential problems when the power supply is unstable, thereby affecting the accuracy and stability of temperature control. The present invention innovatively uses Haar wavelet transform to decompose power supply data, and quantifies the power supply fluctuation eigenvalue by focusing on the energy calculation of the detail coefficients. It can accurately capture the instantaneous fluctuations and local changes in the power supply, significantly improving the evaluation accuracy of power supply stability. In addition, combined with the Gradient Boosting Tree (GBT) model, the present invention can comprehensively evaluate the impact of power supply stability on temperature stability, early warning potential power supply problems, and providing a scientific basis for dynamic regulation. Through the deep integration and application of this advanced signal processing technology and machine learning model, the present invention not only solves the problem of insufficient power supply monitoring in traditional cold chain management systems, but also effectively reduces the loss of goods caused by unstable power supply, ensuring the freshness and quality of fruits and vegetables throughout the transportation process. This method provides a more reliable and efficient power management strategy for cold chain logistics, especially suitable for complex scenarios that require highly accurate temperature control, thus significantly improving the overall performance and reliability of the cold chain logistics system. This innovative solution marks the entry of cold chain logistics management into a new intelligent stage, providing strong technical support for ensuring food safety and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below with reference to the accompanying drawings.

[0034] Figure 1 It is a mind map of the precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] Please refer to Figure 1 As shown, the present invention is a precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables, including the following steps:

[0037] S1: Divide the transportation space into multiple independent temperature control regions, and each region is dedicated to storing a type of fruit and vegetable;

[0038] S2: Real-time monitor the temperature data in each independent temperature control region, and evaluate the temperature stability in each temperature control region according to the fluctuation degree of the temperature data;

[0039] S3: Monitor the power supply during the transportation of fruits and vegetables in real time, and evaluate the power supply stability in each temperature control area according to the degree of power supply fluctuation.

[0040] S4: Analyze the influence degree of power supply stability on temperature stability, and dynamically regulate the power supply according to the analysis results.

[0041] In S1, divide the transportation space into multiple independent temperature control areas, and each area is dedicated to storing one type of fruit and vegetable, specifically including:

[0042] First, conduct a comprehensive analysis of all types of fruits and vegetables to be transported to determine the optimal storage temperature range and humidity conditions for each type of fruit and vegetable. According to the actual size and structural characteristics of the vehicle or storage space, design a reasonable layout plan to ensure that each independent temperature control area can meet the storage requirements of specific fruits and vegetables while maximizing the use of available space. Exemplarily: Use heat insulation boards or other isolation materials to create several closed small environments in the refrigerated compartment, and each small environment is equipped with an independent temperature and humidity control system, thereby forming multiple independent temperature control areas dedicated to storing different types of fruits and vegetables. In this way, not only can the precise control of temperature and humidity in each area be maintained, but also the influence of heat conduction between different temperature zones can be effectively prevented, ensuring the freshness and quality of fruits and vegetables during the entire transportation process.

[0043] In S2, monitor the temperature data in each independent temperature control area in real time, and evaluate the temperature stability in each temperature control area according to the degree of temperature data fluctuation, specifically including:

[0044] During the transportation cycle of fruits and vegetables, obtain the temperature data in each independent temperature control area in real time according to the time series. According to the fluctuation range of the temperature data in each independent temperature control area, calculate the temperature abnormal fluctuation characteristic value, and judge whether the temperature abnormal fluctuation characteristic value is greater than or equal to the preset threshold. If so, the temperature in the corresponding temperature control area is unstable and is recorded as a temperature abnormal area. If not, the temperature in the corresponding temperature control area is stable and is recorded as a temperature normal area.

[0045] The process of obtaining the characteristic value of abnormal temperature fluctuation is as follows: According to the time series, the temperature data in each independent temperature control area is obtained in real time. The fast Fourier transform is applied to the temperature data in each independent temperature control area to transform it from the time domain to the frequency domain. After the fast Fourier transform, a set of frequency components are obtained, and the amplitude and phase information of the frequency components are recorded. In the frequency domain, the frequency domain components are divided into two parts: the low-frequency band and the high-frequency band, and only the frequency components corresponding to the high-frequency band are retained. The sum of the squares of the amplitudes of each frequency component in the high-frequency band is calculated to obtain the energy density of the high-frequency band. The ratio of the energy density of the high-frequency band to the total energy density of all frequency bands is calculated to obtain the characteristic value of abnormal temperature fluctuation.

[0046] It should be noted that: By real-time monitoring and analyzing the temperature data in each independent temperature control area, and using the fast Fourier transform technology to convert the time-domain data to the frequency domain, it is possible to accurately identify the energy density of the high-frequency band, and quantify the characteristic value of abnormal temperature fluctuation by calculating the ratio of the energy density of the high-frequency band to the total energy density. This method can not only effectively distinguish the normal temperature area and the abnormal temperature area, but also improve the sensitivity to sudden and transient temperature fluctuations by specifically focusing on the high-frequency components, enabling the system to detect potential problems earlier and take measures in a timely manner. Its technical effects are mainly reflected in significantly improving the accuracy and response speed of temperature control in the cold chain logistics process, reducing the loss of goods caused by temperature fluctuations, ensuring the freshness and quality of fruits and vegetables during transportation, and providing a more scientific and efficient temperature monitoring solution compared with traditional methods.

[0047] In S3, the power supply during the transportation of fruits and vegetables is monitored in real time, and the power supply stability in each temperature control area is evaluated according to the degree of power supply fluctuation, specifically including:

[0048] During the transportation cycle of fruits and vegetables, according to the time series, the power supply data in each independent temperature control area is obtained in real time. According to the degree of power supply fluctuation in each independent temperature control area during the transportation cycle of each fruit and vegetable, the power supply fluctuation characteristic value is calculated, and it is judged whether the power supply fluctuation characteristic value is greater than or equal to the preset threshold. If so, the power supply in the corresponding temperature control area is unstable; if not, the power supply in the corresponding temperature control area is stable.

[0049] The process of obtaining the power supply fluctuation characteristic value is as follows:

[0050] During the transportation cycle of fruits and vegetables, for each independent temperature control area, the power supply data is continuously collected at a fixed time interval; the collected power supply data is decomposed by applying the Haar wavelet transform. The Haar wavelet transform decomposes the power supply data into two parts: the approximation coefficient and the detail coefficient.

[0051] Filter the detail coefficients. Calculate the energy of the detail coefficients by squaring them, sum up the energies of all the detail coefficients to obtain the total energy of the detail coefficients, and calculate the ratio of the total energy of the detail coefficients to the sum of the energies of the approximation coefficients and the detail coefficients to obtain the power supply fluctuation eigenvalue.

[0052] It should be noted that: The Haar wavelet transform is used to monitor and analyze the power supply data in each independent temperature control area during the fruit and vegetable transportation process in real time. By decomposing the power supply data into approximation coefficients and detail coefficients, the energy calculation of the detail coefficients is focused on to quantify the power supply fluctuation eigenvalue. This method can accurately capture the instantaneous fluctuations and local changes in the power supply, and is especially good at identifying small and rapid fluctuations that may cause unstable temperature control. Its technical effect is reflected in significantly improving the evaluation accuracy of the power supply stability, enabling the system to detect potential power supply problems at an early stage and take timely measures to adjust, thus ensuring the stability of the cold chain logistics environment. Compared with traditional monitoring methods, this solution not only improves the response speed and sensitivity of the system, but also effectively reduces the cargo losses caused by unstable power supply, ensuring the freshness and quality of fruits and vegetables during transportation. This solution based on advanced signal processing technology provides a more reliable and efficient power management strategy for cold chain logistics.

[0053] In S3, the power supply during the fruit and vegetable transportation process is monitored in real time, and the power supply stability in each temperature control area is evaluated according to the degree of power supply fluctuation, specifically including:

[0054] Based on the temperature anomaly area, obtain the temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue in each temperature control area, and construct a machine learning model. According to the model output, judge the influence degree of the power supply stability on the temperature stability;

[0055] The temperature anomaly fluctuation eigenvalue and the power supply fluctuation eigenvalue in each temperature control area are obtained and constructed into a comprehensive feature vector as the input of the machine learning model. The output of the model is the influence eigenvalue. The training objective of the model is to minimize the error between the predicted influence eigenvalue and the actual influence eigenvalue. According to the trained model, the influence eigenvalue is output to judge the influence degree of the power supply stability on the temperature stability. The machine learning model is a gradient boosting tree model;

[0056] The training process of the gradient boosting tree model is as follows: Calculate the residuals of the current model on each sample (i.e., the difference between the predicted value and the actual value), use these residuals as the target variable, fit a new regression tree, which minimizes the residuals as the goal, and learn how to adjust the prediction to better match the actual impact feature values. Determine the optimal step size, which is the weight of the new tree, to minimize the total loss function, and then update the model. Divide the dataset into a training set and a validation set. After each iteration, use the validation set to evaluate the model performance. Adjust the model parameters (such as the number of trees, the depth of the trees, the learning rate, etc.) according to the performance of the validation set to ensure that the model has good generalization ability.

[0057] Judge whether the impact feature value is greater than or equal to the preset threshold. If so, there is a serious impact. If not, there is a slight impact.

[0058] In S4, analyze the degree of influence of power supply stability on temperature stability. According to the analysis results, dynamically regulate the power supply, specifically including:

[0059] Based on the temperature anomaly regions with serious impacts, calculate the power supply regulation value according to the temperature anomaly fluctuation feature values and power supply fluctuation feature values in the corresponding regions, and dynamically regulate the power supply in the temperature anomaly regions according to the power supply regulation value;

[0060] The process of obtaining the power supply regulation value is as follows:

[0061] Obtain the temperature anomaly fluctuation feature values and power supply fluctuation feature values of the temperature anomaly regions with serious impacts. Use the temperature anomaly fluctuation feature values and power supply fluctuation feature values in the temperature anomaly regions as the input of the support vector regression model. Take minimizing the error between the predicted power supply regulation value and the actual power supply regulation value as the training goal of the support vector regression model. According to the trained model, output the power supply regulation value;

[0062] The training process of the support vector regression model is as follows: Set the regularization parameter, kernel width parameter, and insensitive loss interval, and adjust these hyperparameters according to experience or the grid search method to ensure that the model performance reaches the best. Use the quadratic programming algorithm to obtain the optimal weight vector and bias term. Map the input feature vectors in the training set to a high-dimensional space through the kernel function, and use the obtained weight vector and bias term to construct a regression function. For the new input feature vectors, the model outputs the predicted values.

[0063] The specific dynamic regulation includes: According to the calculated power supply regulation value, if the power supply regulation value is less than the preset threshold, increase the power supply and adjust the power management system to increase the power supply power of the corresponding region. If the power supply regulation value is greater than or equal to the preset threshold, reduce the power supply and adjust the power management system to reduce the power supply power of the corresponding region.

[0064] It should be noted that: the dynamic regulation of power supply through the power supply regulation value can not only quickly respond to the impact brought by power supply fluctuations, but also effectively avoid over-compensation or under-compensation, so as to ensure that each independent temperature regulation area always maintains the best temperature conditions, significantly improving the stability and efficiency of the cold chain logistics system. This method is particularly suitable for scenarios that require highly precise temperature control, helping to maximize the freshness and quality of fruits and vegetables.

[0065] The working principle of the present invention: According to the optimal storage temperature and humidity requirements of each type of fruit and vegetable, multiple independent temperature regulation areas are created in the refrigerated compartment using heat-insulating materials. Each area is dedicated to storing a specific type of fruit and vegetable to achieve optimal temperature control and prevent the influence of heat conduction between different temperature ranges. The temperature data in each independent temperature regulation area is monitored in real time. The fast Fourier transform is used to convert the temperature data from the time domain to the frequency domain, and the characteristic value of abnormal temperature fluctuation is calculated to evaluate the temperature stability, distinguishing normal and abnormal temperature areas. The Haar wavelet transform is applied to the power supply data, and the characteristic value of power supply fluctuation is calculated by analyzing the ratio of the energy density of the detail coefficients to the total energy density to evaluate the stability of the power supply. Based on the obtained characteristic values of abnormal temperature fluctuation and power supply fluctuation, a gradient boosting tree model is constructed, and the influence characteristic value is output to judge the degree of influence of power supply stability on temperature stability. For the temperature abnormal areas with serious influence, the support vector regression model is used to calculate the power supply regulation value, and the power supply of the corresponding area is dynamically adjusted according to this value: if the regulation value is less than the preset threshold, the power supply power is increased; otherwise, the power supply power is decreased. This method not only significantly improves the stability and response speed of the cold chain logistics system, but also effectively avoids the loss of goods caused by unstable power supply, ensuring the best storage conditions for fruits and vegetables throughout the transportation cycle, providing a more scientific and efficient solution compared with traditional methods, and is particularly suitable for logistics scenarios that require highly precise temperature control.

[0066] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0067] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of 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, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. 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 by wire or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0068] It should be understood that the term "and / or" in this document is merely an association relationship describing associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0069] It should be understood that in various embodiments of the present application, the order numbers of the above processes do 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 to the implementation process of the embodiments of the present application.

[0070] The above has described in detail one embodiment of the present invention, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. Any equal changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A precise cold storage temperature control method for cold chain distribution of fruits and vegetables in multiple temperature zones, characterized in that, It includes the following steps: S1: Divide the transportation space into multiple independent temperature control regions, and each region is dedicated to storing a type of fruit and vegetable; S2: Monitor the temperature data in each independent temperature control region in real time, and evaluate the temperature stability in each temperature control region according to the fluctuation degree of the temperature data; S3: Monitor the power supply during the transportation of fruits and vegetables in real time, and evaluate the power supply stability in each temperature control region according to the fluctuation degree of the power supply; S4: Analyze the influence degree of power supply stability on temperature stability, and dynamically regulate the power supply according to the analysis result.

2. The precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables according to claim 1, wherein The evaluation of the temperature stability in each temperature control region specifically includes: During the transportation cycle of fruits and vegetables, obtain the temperature data in each independent temperature control region in real time according to the time series. According to the fluctuation amplitude of the temperature data in each independent temperature control region, calculate the temperature abnormal fluctuation characteristic value, and judge whether the temperature abnormal fluctuation characteristic value is greater than or equal to the preset threshold. If so, the temperature in the corresponding temperature control region is unstable and is recorded as a temperature abnormal region. If not, the temperature in the corresponding temperature control region is stable and is recorded as a temperature normal region.

3. The precise cold storage temperature control method for cold chain distribution of fruits and vegetables in multiple temperature zones according to claim 2, characterized in that The process of obtaining the temperature abnormal fluctuation characteristic value is: Obtain the temperature data in each independent temperature control region in real time according to the time series, apply the fast Fourier transform to the temperature data in each independent temperature control region, convert it from the time domain to the frequency domain. After the fast Fourier transform, a set of frequency components are obtained, record the amplitude and phase information of the frequency components. In the frequency domain, divide the frequency domain components into two parts: the low-frequency band and the high-frequency band, and only retain the frequency components corresponding to the high-frequency band. Calculate the sum of the squares of the amplitudes of each frequency component in the high-frequency band to obtain the energy density of the high-frequency band. Calculate the ratio of the energy density of the high-frequency band to the total energy density of all frequency bands to obtain the temperature abnormal fluctuation characteristic value.

4. The precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables according to claim 1, characterized in that The evaluation of the power supply stability in each temperature control region specifically includes: During the transportation cycle of fruits and vegetables, obtain the power supply data in each independent temperature control region in real time according to the time series. According to the power supply fluctuation degree in each transportation cycle of each fruit and vegetable, calculate the power supply fluctuation characteristic value, and judge whether the power supply fluctuation characteristic value is greater than or equal to the preset threshold. If so, the power supply in the corresponding temperature control region is unstable. If not, the power supply in the corresponding temperature control region is stable.

5. The precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables according to claim 4, characterized in that, The process of obtaining the power supply fluctuation characteristic value is: During the transportation cycle of fruits and vegetables, for each independent temperature control region, continuously collect power supply data at a fixed time interval; Apply the Haar wavelet transform to decompose the collected power supply data. The Haar wavelet transform decomposes the power supply data into two parts: the approximation coefficient and the detail coefficient; Screen the detail coefficients. Calculate the energy of the detail coefficients by calculating the squares of the detail coefficients, sum up the energies of all the detail coefficients to obtain the total energy of the detail coefficients, and calculate the ratio of the total energy of the detail coefficients to the sum of the energies of the approximation coefficient and the detail coefficients to obtain the power supply fluctuation characteristic value.

6. The precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables according to claim 1, wherein Analyzing the degree of influence of power supply stability on temperature stability specifically includes: Based on the temperature anomaly regions, obtaining the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values within each temperature regulation region, constructing a machine learning model, and judging the degree of influence of power supply stability on temperature stability according to the model output.

7. The precise cold storage temperature control method for cold chain distribution of fruits and vegetables in multiple temperature zones according to claim 6, characterized in that, Obtaining the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values within each temperature regulation region, constructing the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values into a comprehensive characteristic vector as the input of the machine learning model, with the output of the model being the influence characteristic value, taking minimizing the error between the predicted influence characteristic value and the actual influence characteristic value as the training objective of the model, and judging the degree of influence of power supply stability on temperature stability according to the trained model. The machine learning model is a gradient boosting tree model.

8. The precise cold storage temperature control method for cold chain distribution of fruits and vegetables in multiple temperature zones according to claim 6, characterized in that, Judging the degree of influence of power supply stability on temperature stability specifically includes: Judging whether the influence characteristic value is greater than or equal to a preset threshold. If so, there is a serious influence; if not, there is a slight influence.

9. The precise cold storage temperature control method for cold chain distribution of fruits and vegetables in multiple temperature zones according to claim 1, characterized in that, Performing dynamic regulation on the power supply according to the analysis result specifically includes: Based on the temperature anomaly regions with serious influence, calculating the power supply regulation value according to the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values within the corresponding regions, and performing dynamic regulation of the power supply on the temperature anomaly regions according to the power supply regulation value.

10. The precise cold storage temperature control method for multi-temperature zone cold chain distribution of fruits and vegetables according to claim 9, wherein, The process of obtaining the power supply regulation value is as follows: obtaining the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values of the temperature anomaly regions with serious influence, taking the temperature anomaly fluctuation characteristic values and power supply fluctuation characteristic values within the temperature anomaly regions as the input of the support vector regression model, taking minimizing the error between the predicted power supply regulation value and the actual power supply regulation value as the training objective of the support vector regression model, and outputting the power supply regulation value according to the trained model.

Images