Cold chain equipment control method and system

Abstract

The invention relates to a cold chain equipment control method and system, and relates to the field of cold chain equipment control, and the method comprises the steps: obtaining a historical cold chain transportation data record, extracting a cold chain temperature parameter recorded when the product quality changes, and extracting a historical temperature floating parameter set; randomly generating a first cold chain control parameter, and performing equipment control prediction in combination with the environment parameter and the aging parameter to obtain a first cold chain temperature sequence; and performing retrieval in the first cold chain temperature sequence by adopting the historical temperature floating parameter set, calculating to obtain first control fitness in combination with the fluctuation characteristic parameter of the first cold chain temperature sequence, continuing to perform parameter optimization, and obtaining an optimal cold chain control parameter for control. According to the invention, the technical problem that the quality of transported products is affected due to large temperature fluctuation in the transportation process caused by the fact that a traditional method cannot dynamically adjust a cold chain control strategy according to an actual transportation scene can be solved; the adverse effect of temperature fluctuation on product quality can be effectively reduced, and product safety and quality stability are ensured.

Description

Technical Field

[0001] The present invention relates to the field of cold chain equipment control, and in particular to a cold chain equipment control method and system. Background Art

[0002] Cold chain transportation refers to the control of temperature, humidity and other environmental factors during the transportation, storage and distribution process to ensure that goods are maintained under specific temperature control conditions throughout the entire transportation cycle to maintain their quality and safety. Cold chain transportation is widely used in temperature-sensitive goods such as medicines, food (especially fresh food, frozen food), biological samples, etc.

[0003] Traditional cold chain equipment usually operates based on preset temperature ranges and control parameters. It lacks a flexible dynamic adjustment mechanism and is unable to dynamically optimize according to real-time environmental changes, transportation time, external conditions and cargo characteristics, resulting in temperature fluctuations during transportation, which in turn affects the quality of the transported products. Summary of the invention

[0004] The present invention provides a cold chain equipment control method and system to solve the technical problem that traditional cold chain equipment control methods are unable to dynamically adjust the cold chain control strategy according to the actual transportation scenario, resulting in temperature fluctuations during transportation, which in turn affects the quality of the transported products.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a cold chain equipment control method, comprising: during the operation of the cold chain equipment, obtaining a target product for cold chain transportation, obtaining a cold chain control parameter space of the cold chain equipment, and collecting environmental parameters and aging parameters for the operation of the cold chain equipment; obtaining historical cold chain transportation data records of the target product, extracting cold chain temperature parameters recorded when product quality changes occur, and extracting a set of historical temperature floating parameters; randomly generating a first cold chain control parameter in the cold chain control parameter space, and performing cold chain equipment control prediction in combination with the environmental parameters and aging parameters to obtain a first cold chain temperature sequence; using the set of historical temperature floating parameters to search in the first cold chain temperature sequence, and combining the fluctuation characteristic parameters of the first cold chain temperature sequence to calculate a first control fitness, continue to optimize the cold chain control parameters, obtain optimal cold chain control parameters, and control the cold chain equipment.

[0006] In a second aspect, the present invention provides a cold chain equipment control system, including: a cold chain transportation information acquisition module, which is used to obtain the target product for cold chain transportation during the operation of the cold chain equipment, and obtain the cold chain control parameter space of the cold chain equipment, and collect the environmental parameters and aging parameters of the cold chain equipment operation; a historical transportation data extraction module, which is used to obtain the historical cold chain transportation data records of the target product, extract the cold chain temperature parameters recorded when the product quality changes, and extract the historical temperature floating parameter set; a cold chain equipment control prediction module, which is used to randomly generate a first cold chain control parameter in the cold chain control parameter space, and perform cold chain equipment control prediction in combination with the environmental parameters and aging parameters to obtain a first cold chain temperature sequence; a cold chain control parameter optimization module, which is used to use the historical temperature floating parameter set to search in the first cold chain temperature sequence, and in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, calculate and obtain the first control fitness, continue to optimize the cold chain control parameters, obtain the optimal cold chain control parameters, and control the cold chain equipment.

[0007] In a third aspect, the present invention further provides an electronic device, comprising: At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of the method described in the first aspect above.

[0008] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method described in the first aspect are implemented.

[0009] The beneficial effects of the present invention are as follows: during the operation of the cold chain equipment, the target product for cold chain transportation is obtained, the cold chain control parameter space of the cold chain equipment is obtained, and the environmental parameters and aging parameters of the cold chain equipment operation are collected; then the historical cold chain transportation data records of the target product are obtained, the cold chain temperature parameters recorded when the product quality changes, and the historical temperature floating parameter set are extracted; then the first cold chain control parameter is randomly generated in the cold chain control parameter space, and the cold chain equipment control prediction is performed in combination with the environmental parameters and aging parameters to obtain the first cold chain temperature sequence; the historical temperature floating parameter set is further used to search in the first cold chain temperature sequence, and the first control fitness is calculated in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, and the cold chain control parameters are continuously optimized to obtain the optimal cold chain control parameters; finally, the cold chain equipment is controlled according to the optimal cold chain control parameters; that is, through the above steps, matching cold chain control parameters can be set after comprehensive analysis of product feature differences, external environmental fluctuations and equipment operation status, which significantly improves the accuracy and stability of cold chain control, thereby effectively reducing the adverse effects of temperature fluctuations on product quality and ensuring the safety and quality stability of products during transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a cold chain equipment control method provided by the present invention; Figure 2 A schematic diagram of the structure of a cold chain equipment control system provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are described as follows: Cold chain transportation information collection module 01, historical transportation data extraction module 02, cold chain equipment control prediction module 03, cold chain control parameter optimization module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a cold chain equipment control method, which specifically includes the following steps: S100: During the operation of the cold chain equipment, the target product for cold chain transportation is obtained, the cold chain control parameter space of the cold chain equipment is obtained, and the environmental parameters and aging parameters of the cold chain equipment operation are collected.

[0016] Furthermore, step S100 of the present invention further includes: S110: During the operation of the cold chain equipment, the product category for cold chain transportation is obtained as the target product; S120: The cold chain control parameter space for controlling and adjusting the cold chain equipment is obtained; S130: The temperature parameters and humidity parameters of the current external environment are collected as environmental parameters, and the accumulated operating time of the cold chain equipment is collected as an aging parameter.

[0017] Specifically, first, during the cold chain transportation process, it is necessary to clearly define the target product categories to be transported, such as medicines, food, vaccines, etc. These products have different temperature and humidity requirements, so different temperature control strategies need to be set according to the characteristics of the products. For example, vaccines and insulin are extremely sensitive to temperature changes and need to be maintained within a narrow temperature control range; fresh and frozen foods are usually required to be transported at lower temperatures to avoid deterioration caused by temperature fluctuations; blood samples, cells, etc. require specific temperature and humidity conditions.

[0018] Next, the cold chain control parameter space for controlling and adjusting the cold chain equipment is obtained, wherein the cold chain control parameters include various parameters that affect the temperature regulation of the equipment, such as compressor control parameters (including operating frequency, power, operating mode, etc.); the cold chain control parameter space refers to a set of multiple cold chain control parameters. By adjusting these parameters, dynamic optimization of the performance of the cold chain equipment can be achieved, thereby ensuring temperature control accuracy and stable product quality.

[0019] Then, the temperature and humidity parameters of the current external environment are collected. Changes in ambient temperature will directly affect the cooling efficiency of the equipment, especially when encountering high temperature weather during transportation. The cold chain equipment needs to be adaptively adjusted according to the external environment; humidity has an important impact on some specific products (such as biological samples). Too high or too low humidity may have a negative impact on product quality. Therefore, it is necessary to monitor the ambient humidity and adjust the humidity control function of the equipment; and set the temperature and humidity parameters as environmental parameters.

[0020] On the other hand, the accumulated running time of the cold chain equipment is collected and used as an aging parameter. As the equipment ages, the refrigeration efficiency may decrease, which may lead to inaccurate temperature control. Therefore, the aging degree of the equipment needs to be taken into consideration and the equipment performance needs to be evaluated regularly. By obtaining the target product category, environmental parameters and equipment aging parameters, data support is provided for the subsequent dynamic adjustment analysis of cold chain control parameters.

[0021] S200: Obtain historical cold chain transportation data records of the target product, extract cold chain temperature parameters recorded when product quality changes occur, and extract a set of historical temperature floating parameters.

[0022] Furthermore, step S200 of the present invention further includes: S210: Obtain historical cold chain transportation data records of similar products of the target product, screen the abnormal cold chain temperature parameter sequences and product quality change parameters recorded when the target product undergoes quality changes, and obtain an abnormal cold chain temperature parameter sequence set and a product quality change parameter set; S220: Extract the maximum temperature fluctuation amplitude from multiple abnormal cold chain temperature parameter sequences in the abnormal cold chain temperature parameter sequence set to obtain an abnormal temperature floating parameter set.

[0023] Specifically, first, collect historical cold chain transportation data records of similar products of the target product during cold chain transportation, including cold chain temperature data, product quality data, etc.; then, screen the abnormal cold chain temperature parameter sequence and product quality change parameters recorded when the target product undergoes quality changes (for example, at least one product is damaged, such as corruption) in the historical cold chain transportation data records, where the abnormal cold chain temperature parameter sequence includes temperature parameters under multiple consecutive timestamps; the product quality change parameter refers to the damage rate of the product, such as a 3% damage rate for fresh food; obtain a set of abnormal cold chain temperature parameter sequences and a set of product quality change parameters, where the abnormal cold chain temperature parameter sequences and the product quality change parameters correspond one to one.

[0024] Then, the maximum temperature fluctuation amplitudes in multiple abnormal cold chain temperature parameter sequences in the abnormal cold chain temperature parameter sequence set are calculated respectively, the maximum temperature fluctuation amplitude refers to the temperature difference between the maximum temperature and the minimum temperature in each abnormal cold chain temperature parameter sequence, and the maximum temperature fluctuation amplitude is set as the abnormal temperature floating parameter. For example, within a certain time period, the temperature records are 4 degrees Celsius, 6 degrees Celsius, 3 degrees Celsius, 5 degrees Celsius and 7 degrees Celsius, then the maximum temperature is 7 degrees Celsius, the minimum temperature is 3 degrees Celsius, the maximum temperature fluctuation amplitude is 7 minus 3 equals 4 degrees Celsius, then the normal temperature floating parameter is 4 degrees Celsius, and the abnormal temperature floating parameter set is obtained, wherein the abnormal temperature floating parameters and the abnormal cold chain temperature parameter sequences correspond one to one.

[0025] S300: Randomly generate a first cold chain control parameter in the cold chain control parameter space, perform cold chain equipment control prediction in combination with the environmental parameter and the aging parameter, and obtain a first cold chain temperature sequence.

[0026] Furthermore, step S300 of the present invention further includes: S310: Pre-training a cold chain equipment control prediction path based on historical operation data of the cold chain equipment, wherein the cold chain equipment control prediction path includes multiple cold chain equipment control prediction branches.

[0027] Furthermore, step S310 of the present invention further includes: S311: Based on the historical operation data of cold chain equipment of the same model, collect sample cold chain control parameter set, sample environmental parameter set, sample aging parameter set, and collect the control temperature of the cold chain equipment, and mark the sample cold chain temperature set; S312: Combine the sample cold chain control parameter set, sample environmental parameter set, sample aging parameter set and sample cold chain temperature set as cold chain supervision training data, and perform K-fold division to obtain K cold chain supervision training data sets, where K is an integer greater than 1; S313: Use the K cold chain supervision training data sets respectively, use machine learning to train K cold chain equipment control prediction branches, and combine them to obtain the cold chain equipment control prediction path after the training is completed.

[0028] Specifically, first, based on the historical operation data of cold chain equipment of the same model, a set of sample cold chain control parameters (compressor power, operating frequency, etc.), a set of sample environmental parameters (ambient temperature, ambient humidity), and a set of sample aging parameters (cumulative operating time) are collected, and the control temperature of the cold chain equipment under different sample cold chain control parameters, sample environmental parameters, and sample aging parameters are collected, marked as sample cold chain temperature, and a sample cold chain temperature set is obtained. Then, the sample cold chain control parameter set, sample environmental parameter set, sample aging parameter set, and sample cold chain temperature set are combined as cold chain supervision training data, and the cold chain supervision training data is K-folded, that is, the above-mentioned cold chain supervision training data set is randomly divided into K non-overlapping subsets (each subset contains different sample data), K is an integer greater than 1, and the value of K can be set according to actual needs, such as setting K to 10 to obtain K cold chain supervision training data sets.

[0029] K cold chain equipment control prediction branches are constructed based on the BP network, wherein the cold chain equipment control prediction branch is a BP neural network model that can be iteratively optimized in machine learning, and is used to output the predicted cold chain temperature by inputting cold chain equipment control parameters, environmental conditions and aging parameters. The model includes an input layer, multiple hidden layers and an output layer, wherein the input layer is used to receive various input data of the cold chain equipment, including cold chain control parameters, environmental parameters and aging parameters, and the output layer is responsible for generating prediction results, and the output data is the cold chain temperature. Then, taking the sample cold chain control parameters, sample environmental parameters and sample aging parameters as input and the sample cold chain temperature as supervision, the K cold chain supervised training data sets are used to perform supervised training on the K cold chain equipment control prediction branches respectively. First, the input data (cold chain control parameters, environmental parameters, aging parameters) are passed into the network, and the output result is finally obtained after calculation of the input layer and the hidden layer; then, according to the difference between the predicted result and the actual result (real cold chain temperature data or target temperature), the error (such as mean square error MSE) is calculated; further, the error is used to calculate the weight update of each layer through the back propagation algorithm, and the weight value is adjusted to reduce the prediction error. The purpose of back propagation is to optimize the model parameters through multiple iterations to minimize the prediction error of the model; finally, the gradient descent method or its variants (such as Adam optimizer) are used to update the network parameters to minimize the loss function, and the iterative optimization is continued until the loss function converges to obtain the trained K cold chain equipment control prediction branches.

[0030] Finally, the K cold chain equipment control prediction branches are combined in parallel to construct a cold chain equipment control prediction path. The cold chain equipment control prediction path is constructed by using an integrated learning method of multiple BP neural network branches. Since the training data of each cold chain equipment control prediction branch is different, multiple predictions can be made to obtain multiple predicted temperature results, so that temperature fluctuations under different circumstances can be predicted more accurately.

[0031] S320: randomly generate a first cold chain control parameter in the cold chain control parameter space; S330: input the first cold chain control parameter, environmental parameter and aging parameter into multiple cold chain equipment control prediction branches in the cold chain equipment control prediction path, perform cold chain equipment control prediction, and output multiple first cold chain temperatures; S340: construct a first cold chain temperature sequence based on the multiple first cold chain temperatures.

[0032] Specifically, first, any cold chain control parameter is randomly selected in the cold chain control parameter space as the first cold chain control parameter; then the first cold chain control parameter, environmental parameters and aging parameters are input into multiple cold chain equipment control prediction branches in the cold chain equipment control prediction path to perform cold chain equipment control prediction and output multiple first cold chain temperatures, wherein each BP neural network branch performs temperature prediction through forward propagation combined with the input control parameters, environmental conditions and equipment aging status, and each branch outputs a predicted temperature (first cold chain temperature). By integrating the prediction results of multiple branches, it is possible to better consider the equipment operating status and environmental changes, and predict the temperature fluctuations of cold chain equipment in different scenarios.

[0033] Finally, the multiple first cold chain temperatures are arranged to construct a first cold chain temperature sequence, which represents the fluctuation range of the cold chain temperature under the first cold chain control parameters, environmental factors and equipment aging. For example, the temperature sequence that may be obtained under multiple predictions of the first cold chain control parameters is: [4.5 degrees Celsius, 4.6 degrees Celsius, 4.4 degrees Celsius]. These values ​​represent the various possibilities of the cold chain temperature under the same control strategy, affected by factors such as the environment and equipment aging.

[0034] S400: Use the historical temperature floating parameter set to search within the first cold chain temperature sequence, and combine the fluctuation characteristic parameters of the first cold chain temperature sequence to calculate and obtain the first control fitness, continue to optimize the cold chain control parameters, obtain the optimal cold chain control parameters, and control the cold chain equipment.

[0035] Furthermore, step S400 of the present invention further includes: S410: Calculate and obtain the first maximum cold chain temperature fluctuation amplitude in the first cold chain temperature sequence; S420: Traverse and search whether multiple historical temperature floating parameters in the historical temperature floating parameter set fall into the first maximum cold chain temperature fluctuation amplitude, and obtain a floating search result set, where the floating search result is 1 or 0, if it falls into, it is 1, and if it does not fall into, it is 0.

[0036] Specifically, first, calculate and obtain the first maximum cold chain temperature fluctuation amplitude in the first cold chain temperature sequence, and the first maximum cold chain temperature fluctuation amplitude is the temperature difference of the maximum temperature in the first cold chain temperature sequence minus the minimum temperature. Then, traverse and search whether multiple historical temperature floating parameters in the historical temperature floating parameter set fall within the first maximum cold chain temperature fluctuation amplitude, wherein, if the historical temperature floating amplitude is less than or equal to the first maximum cold chain temperature fluctuation amplitude, it is recorded as "1", indicating that the historical temperature floating parameter falls within the first cold chain temperature fluctuation range; if the historical temperature floating amplitude is greater than the first maximum cold chain temperature fluctuation amplitude, it is recorded as "0", indicating that the historical temperature floating parameter does not fall within the first cold chain temperature fluctuation range; and obtain a floating search result set. By analyzing the floating search result set, we can evaluate whether the temperature fluctuation under the first cold chain control parameter is consistent with the temperature control performance in the historical data. If most of the historical temperature floating parameters fall within the first cold chain temperature fluctuation amplitude range, that is, most of the search results are "1", it indicates that the current control strategy may cause excessive temperature fluctuations and the control parameters need to be further optimized; if most of the search results are "0", it means that the temperature fluctuations under the control strategy are reasonable.

[0037] S430: Analyze and obtain the fluctuation characteristic parameters of the first cold chain temperature sequence, combine the floating search result set and the product quality change parameter set, and calculate and obtain the first control fitness of the first cold chain control parameter.

[0038] Further, step S430 of the present invention further includes: S431: randomly select multiple groups of first cold chain temperatures in the first cold chain temperature sequence, wherein each group of first cold chain temperatures includes two first cold chain temperatures; S432: calculate the temperature fluctuation amplitudes of the multiple groups of first cold chain temperatures, obtain multiple temperature fluctuation amplitudes, and calculate the average to obtain a first average temperature fluctuation amplitude; S433: calculate and obtain the first control fitness of the first cold chain control parameter according to the first average temperature fluctuation amplitude, the floating search result set and the product quality change parameter set, as shown in the following formula: ; Among them, CTFIT is the control fitness, is the average temperature fluctuation amplitude, M is the number of floating search results in the floating search result set, is the i-th floating search result, each floating search result is 1 or 0, is the product quality change parameter corresponding to the i-th floating retrieval result.

[0039] Specifically, first, any two first cold chain temperatures in the first cold chain temperature sequence are randomly selected as a group of cold chain temperatures, and multiple groups of first cold chain temperatures are randomly selected multiple times to obtain multiple groups of first cold chain temperatures, wherein the number of selections can be set according to the calculation accuracy, and the more the number of selections, the higher the calculation accuracy. Then, the temperature fluctuation amplitudes of the multiple groups of first cold chain temperatures are calculated respectively, wherein the temperature fluctuation amplitude is the absolute value of the temperature difference between the two first cold chain temperatures, to obtain multiple temperature fluctuation amplitudes; further, the average of the multiple temperature fluctuation amplitudes is calculated to obtain the first average temperature fluctuation amplitude.

[0040] Construct a control fitness evaluation function: ; In the control fitness evaluation function, CTFIT is the control fitness. The greater the control fitness, the more stable the temperature control effect is, and the more conducive to maintaining product quality; is the average temperature fluctuation amplitude, which is negatively correlated with the control fitness, that is, the larger the average temperature fluctuation amplitude, the smaller the control fitness, and the smaller the average temperature fluctuation amplitude, the smaller the control fitness; M is the number of floating search results in the floating search result set, is the i-th floating search result, each floating search result is 1 or 0, where the more “1” there are in the floating search result, the smaller the control fitness is, and the more “0” there are, the larger the control fitness is; is the product quality change parameter corresponding to the i-th floating search result. The larger the product quality change parameter, the smaller the control fitness. Conversely, the smaller the product quality change parameter, the greater the control fitness. By constructing a control fitness evaluation function, we can quantify the impact of each cold chain control parameter on temperature control stability, accurately evaluate the control fitness of each cold chain control parameter, and intuitively reflect the pros and cons of the cold chain control parameters.

[0041] The fitness evaluation function is further used to calculate the first control fitness of the first cold chain control parameter according to the first average temperature fluctuation amplitude, the floating search result set and the product quality change parameter set.

[0042] S440: Continue to optimize the cold chain control parameters in the cold chain control parameter space until convergence, output the cold chain control parameters with the maximum control fitness, and obtain the optimal cold chain control parameters.

[0043] Specifically, a second cold chain control parameter is then randomly selected in the cold chain control parameter space, and a second control fitness of the second cold chain control parameter is calculated; the same method is used to iteratively select and evaluate the fitness of the cold chain control parameter in the cold chain control parameter space until a predetermined number of selections is reached (which can be set according to the optimization accuracy, the more selections, the higher the optimization accuracy), and multiple cold chain control parameters and multiple control fitness are output; then the cold chain control parameter with the largest control fitness is output as the optimal cold chain control parameter, and the cold chain equipment is controlled according to the optimal cold chain control parameter.

[0044] A cold chain equipment control method provided by an embodiment of the present invention has at least the following technical effects: During the operation of the cold chain equipment, the target product for cold chain transportation is obtained, the cold chain control parameter space of the cold chain equipment is obtained, and the environmental parameters and aging parameters of the cold chain equipment operation are collected; then the historical cold chain transportation data records of the target product are obtained, the cold chain temperature parameters recorded when the product quality changes, and the historical temperature floating parameter set are extracted; then the first cold chain control parameter is randomly generated in the cold chain control parameter space, and the cold chain equipment control prediction is performed in combination with the environmental parameters and aging parameters to obtain the first cold chain temperature sequence; further, the historical temperature floating parameter set is used to search in the first cold chain temperature sequence, and the first control fitness is calculated in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, and the cold chain control parameters are continuously optimized to obtain the optimal cold chain control parameters; finally, the cold chain equipment is controlled according to the optimal cold chain control parameters; that is, through the above steps, matching cold chain control parameters can be set after comprehensive analysis based on product feature differences, external environmental fluctuations and equipment operation status, which significantly improves the accuracy and stability of cold chain control, thereby effectively reducing the adverse effects of temperature fluctuations on product quality and ensuring the safety and quality stability of products during transportation.

[0045] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the cold chain equipment control method provided in Embodiment 1, the embodiment of the present invention further provides a cold chain equipment control system, including: The cold chain transportation information acquisition module 01 is used to obtain the target product for cold chain transportation during the operation of the cold chain equipment, as well as the cold chain control parameter space of the cold chain equipment, and collect the environmental parameters and aging parameters of the cold chain equipment operation; the historical transportation data extraction module 02 is used to obtain the historical cold chain transportation data records of the target product, extract the cold chain temperature parameters recorded when the product quality changes, and extract the historical temperature floating parameter set; the cold chain equipment control prediction module 03 is used to randomly generate the first cold chain control parameter in the cold chain control parameter space, and perform cold chain equipment control prediction in combination with the environmental parameters and aging parameters to obtain the first cold chain temperature sequence; the cold chain control parameter optimization module 04 is used to use the historical temperature floating parameter set to search in the first cold chain temperature sequence, and in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, calculate and obtain the first control fitness, continue to optimize the cold chain control parameters, obtain the optimal cold chain control parameters, and control the cold chain equipment.

[0046] Furthermore, the cold chain equipment control system is also used to: during the operation of the cold chain equipment, obtain the product category for cold chain transportation as the target product; obtain the cold chain control parameter space for controlling and adjusting the cold chain equipment; collect the temperature parameters and humidity parameters of the current external environment as environmental parameters, and collect the cumulative operating time of the cold chain equipment as an aging parameter.

[0047] Furthermore, the cold chain equipment control system is also used to: obtain historical cold chain transportation data records of similar products to the target product, screen the abnormal cold chain temperature parameter sequences and product quality change parameters recorded when the target product undergoes quality changes, and obtain an abnormal cold chain temperature parameter sequence set and a product quality change parameter set; extract the maximum temperature fluctuation amplitude from multiple abnormal cold chain temperature parameter sequences in the abnormal cold chain temperature parameter sequence set, and obtain an abnormal temperature floating parameter set.

[0048] Furthermore, the cold chain equipment control system is also used to: pre-train a cold chain equipment control prediction path based on historical operation data of the cold chain equipment, wherein the cold chain equipment control prediction path includes multiple cold chain equipment control prediction branches; randomly generate a first cold chain control parameter in the cold chain control parameter space; input the first cold chain control parameter, environmental parameter and aging parameter into multiple cold chain equipment control prediction branches in the cold chain equipment control prediction path, perform cold chain equipment control prediction, and output multiple first cold chain temperatures; and construct a first cold chain temperature sequence based on the multiple first cold chain temperatures.

[0049] Furthermore, the cold chain equipment control system is also used to: collect sample cold chain control parameter sets, sample environmental parameter sets, and sample aging parameter sets based on historical operating data of cold chain equipment of the same model, and collect the control temperature of the cold chain equipment, and mark the sample cold chain temperature set; combine the sample cold chain control parameter set, sample environmental parameter set, sample aging parameter set, and sample cold chain temperature set as cold chain supervision training data, and perform K-fold division to obtain K cold chain supervision training data sets, where K is an integer greater than 1; respectively use the K cold chain supervision training data sets and use machine learning to train K cold chain equipment control prediction branches, and after the training is completed, combine them to obtain the cold chain equipment control prediction path.

[0050] Furthermore, the cold chain equipment control system is also used to: calculate and obtain the first maximum cold chain temperature fluctuation amplitude in the first cold chain temperature sequence; traverse and search whether multiple historical temperature floating parameters in the historical temperature floating parameter set fall into the first maximum cold chain temperature fluctuation amplitude, and obtain a floating search result set, wherein the floating search result is 1 or 0, falls into 1, and does not fall into 0; analyze and obtain the fluctuation characteristic parameters of the first cold chain temperature sequence, and calculate and obtain the first control fitness of the first cold chain control parameter by combining the floating search result set and the product quality change parameter set; continue to optimize the cold chain control parameters in the cold chain control parameter space until convergence, output the cold chain control parameters with the largest control fitness, and obtain the optimal cold chain control parameters.

[0051] Furthermore, the cold chain equipment control system is also used to: randomly select multiple groups of first cold chain temperatures in the first cold chain temperature sequence, wherein each group of first cold chain temperatures includes two first cold chain temperatures; calculate the temperature fluctuation amplitudes of the multiple groups of first cold chain temperatures to obtain multiple temperature fluctuation amplitudes, and calculate the average to obtain a first average temperature fluctuation amplitude; calculate and obtain a first control fitness of the first cold chain control parameter according to the first average temperature fluctuation amplitude, the floating search result set and the product quality change parameter set, as shown in the following formula: ; Among them, CTFIT is the control fitness, is the average temperature fluctuation amplitude, M is the number of floating search results in the floating search result set, is the i-th floating search result, each floating search result is 1 or 0, is the product quality change parameter corresponding to the i-th floating retrieval result.

[0052] For example 3, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: during the operation of the cold chain equipment, a target product for cold chain transportation is obtained, as well as a cold chain control parameter space of the cold chain equipment, and environmental parameters and aging parameters for the operation of the cold chain equipment are collected; historical cold chain transportation data records of the target product are obtained, cold chain temperature parameters recorded when product quality changes occur are extracted, and a historical temperature floating parameter set is extracted; a first cold chain control parameter is randomly generated in the cold chain control parameter space, and a cold chain equipment control prediction is performed in combination with the environmental parameters and aging parameters to obtain a first cold chain temperature sequence; the historical temperature floating parameter set is used to search in the first cold chain temperature sequence, and a first control fitness is calculated in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, and the cold chain control parameter optimization is continued to obtain the optimal cold chain control parameter to control the cold chain equipment.

[0053] Example 4, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a second computer program 611 is stored. When the second computer program 611 is executed by the processor, the following steps are implemented: during the operation of the cold chain equipment, a target product for cold chain transportation is obtained, as well as a cold chain control parameter space of the cold chain equipment, and environmental parameters and aging parameters for the operation of the cold chain equipment are collected; historical cold chain transportation data records of the target product are obtained, cold chain temperature parameters recorded when product quality changes occur are extracted, and a historical temperature floating parameter set is extracted; a first cold chain control parameter is randomly generated in the cold chain control parameter space, and a cold chain equipment control prediction is performed in combination with the environmental parameters and aging parameters to obtain a first cold chain temperature sequence; the historical temperature floating parameter set is used to search in the first cold chain temperature sequence, and a first control fitness is calculated in combination with the fluctuation characteristic parameters of the first cold chain temperature sequence, and the cold chain control parameter optimization is continued to obtain the optimal cold chain control parameter to control the cold chain equipment.

[0054] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0055] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0059] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0060] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A cold chain equipment control method, characterized in that: Methods include: During the operation of the cold chain equipment, the target products for cold chain transportation are obtained, the cold chain control parameter space of the cold chain equipment is obtained, and the environmental parameters and aging parameters of the cold chain equipment operation are collected; Obtain historical cold chain transportation data records of the target product, extract cold chain temperature parameters recorded when product quality changes occur, and extract a set of historical temperature floating parameters; Randomly generate a first cold chain control parameter in the cold chain control parameter space, perform cold chain equipment control prediction in combination with the environmental parameter and the aging parameter, and obtain a first cold chain temperature sequence; The historical temperature floating parameter set is used to search within the first cold chain temperature sequence, and combined with the fluctuation characteristic parameters of the first cold chain temperature sequence, the first control fitness is calculated and obtained, and the cold chain control parameters are continuously optimized to obtain the optimal cold chain control parameters and control the cold chain equipment.

2. The cold chain equipment control method according to claim 1, characterized in that: During the operation of the cold chain equipment, the target products for cold chain transportation are obtained, the cold chain control parameter space of the cold chain equipment is obtained, and the environmental parameters and aging parameters of the cold chain equipment operation are collected, including: During the operation of the cold chain equipment, the product categories for cold chain transportation are obtained as target products; Obtaining a cold chain control parameter space for controlling and adjusting the cold chain equipment; The temperature parameters and humidity parameters of the current external environment are collected as environmental parameters, and the accumulated operating time of the cold chain equipment is collected as aging parameters.

3. The cold chain equipment control method according to claim 1, characterized in that: During the operation of the cold chain equipment, the historical cold chain transportation data records of the target product are obtained, the cold chain temperature parameters when the product quality changes, and the historical temperature floating parameter set are extracted, including: Obtain historical cold chain transportation data records of similar products of the target product, screen abnormal cold chain temperature parameter sequences and product quality change parameters recorded when the target product undergoes quality changes, and obtain abnormal cold chain temperature parameter sequence sets and product quality change parameter sets; The maximum temperature fluctuation amplitude among multiple abnormal cold chain temperature parameter sequences in the abnormal cold chain temperature parameter sequence set is extracted to obtain an abnormal temperature floating parameter set.

4. The cold chain equipment control method according to claim 1, characterized in that: Randomly generating a first cold chain control parameter in the cold chain control parameter space, combining the environmental parameter and the aging parameter, performing cold chain equipment control prediction, and obtaining a first cold chain temperature sequence, including: Pre-training a cold chain equipment control prediction path according to historical operation data of the cold chain equipment, wherein the cold chain equipment control prediction path includes a plurality of cold chain equipment control prediction branches; Randomly generating a first cold chain control parameter in the cold chain control parameter space; Inputting the first cold chain control parameter, environmental parameter and aging parameter into a plurality of cold chain equipment control prediction branches in the cold chain equipment control prediction path, performing cold chain equipment control prediction, and outputting a plurality of first cold chain temperatures; A first cold chain temperature sequence is constructed based on the multiple first cold chain temperatures.

5. The cold chain equipment control method according to claim 4, characterized in that: Based on the historical operation data of cold chain equipment, the cold chain equipment control prediction path is pre-trained, including: According to the historical operation data of the same type of cold chain equipment, collect the sample cold chain control parameter set, sample environmental parameter set, sample aging parameter set, and collect the control temperature of the cold chain equipment, and mark the sample cold chain temperature set; The sample cold chain control parameter set, the sample environment parameter set, the sample aging parameter set and the sample cold chain temperature set are combined as cold chain supervision training data, and K-fold division is performed to obtain K cold chain supervision training data sets, where K is an integer greater than 1; The K cold chain supervision training data sets are respectively used to train K cold chain equipment control prediction branches using machine learning. After the training is completed, the cold chain equipment control prediction path is obtained by combining them.

6. The cold chain equipment control method according to claim 3, characterized in that: The historical temperature floating parameter set is used to search in the first cold chain temperature sequence, and combined with the fluctuation characteristic parameter of the first cold chain temperature sequence, a first control fitness is calculated, including: Calculate and obtain a first maximum cold chain temperature fluctuation amplitude in the first cold chain temperature sequence; Traverse and search whether multiple historical temperature floating parameters in the historical temperature floating parameter set fall within the first maximum cold chain temperature fluctuation amplitude, and obtain a floating search result set, wherein the floating search result is 1 or 0, and the value is 1 if it falls within the range, and 0 if it does not fall within the range; Analyze and obtain the fluctuation characteristic parameters of the first cold chain temperature sequence, combine the floating search result set and the product quality change parameter set, and calculate and obtain the first control fitness of the first cold chain control parameter; Continue to optimize the cold chain control parameters in the cold chain control parameter space until convergence, output the cold chain control parameters with the maximum control fitness, and obtain the optimal cold chain control parameters.

7. The cold chain equipment control method according to claim 6, characterized in that: Analyzing and obtaining the fluctuation characteristic parameters of the first cold chain temperature sequence, combining the floating search result set and the product quality change parameter set, and calculating and obtaining the first control fitness of the first cold chain control parameter, including: Randomly selecting multiple groups of first cold chain temperatures within the first cold chain temperature sequence, wherein each group of first cold chain temperatures includes two first cold chain temperatures; Calculating the temperature fluctuation amplitudes of the multiple groups of first cold chain temperatures to obtain multiple temperature fluctuation amplitudes, and calculating the average to obtain a first average temperature fluctuation amplitude; According to the first average temperature fluctuation amplitude, the floating search result set and the product quality change parameter set, the first control fitness of the first cold chain control parameter is calculated and obtained as follows: ； Among them, CTFIT is the control fitness, is the average temperature fluctuation amplitude, M is the number of floating search results in the floating search result set, is the i-th floating search result, each floating search result is 1 or 0, is the product quality change parameter corresponding to the i-th floating retrieval result.

8. A cold chain equipment control system, characterized in that: The steps for implementing a cold chain equipment control method according to any one of claims 1 to 7 include: The cold chain transportation information collection module is used to obtain the target products for cold chain transportation during the operation of the cold chain equipment, obtain the cold chain control parameter space of the cold chain equipment, and collect the environmental parameters and aging parameters of the cold chain equipment operation; A historical transportation data extraction module is used to obtain the historical cold chain transportation data records of the target product, extract the cold chain temperature parameters recorded when the product quality changes, and extract the historical temperature floating parameter set; A cold chain equipment control prediction module, used to randomly generate a first cold chain control parameter in the cold chain control parameter space, and perform cold chain equipment control prediction in combination with the environmental parameter and the aging parameter to obtain a first cold chain temperature sequence; The cold chain control parameter optimization module is used to use the historical temperature floating parameter set to search within the first cold chain temperature sequence, and combine the fluctuation characteristic parameters of the first cold chain temperature sequence to calculate and obtain the first control fitness, continue to optimize the cold chain control parameters, obtain the optimal cold chain control parameters, and control the cold chain equipment.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of a cold chain equipment control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of a cold chain equipment control method as described in any one of claims 1 to 7.

Images