A temperature intelligent control method in cold chain transportation

Abstract

The present invention relates to the technical field of cold chain transportation, and specifically to a method for intelligent temperature control in the process of cold chain transportation, comprising the following steps: S1: real-time monitoring of the temperature distribution of each cargo unit and outputting temperature data; S2: calculating the thermal conductivity and thermal radiation characteristics of each cargo unit and predicting the trend of temperature change; S3: adjusting the working parameters of the refrigeration equipment according to the temperature change trend predicted in S2; S4: monitoring based on the temperature control result of S3, and automatically enhancing the refrigeration intensity of the cargo unit; S5: predicting the factors causing temperature abnormality and issuing an early warning to the transportation management personnel; S6: automatically generating a temperature control report after the transportation is completed. The present invention significantly improves the temperature management accuracy and response speed of cold chain transportation by real-time monitoring and automatic adjustment of temperature control parameters, while enhancing the energy efficiency of the system and the safety during transportation.

Description

Technical Field

[0001] The present invention relates to the field of cold chain transportation technology, and in particular to a temperature intelligent control method in a cold chain transportation process. Background Art

[0002] With the development of global trade and the pursuit of quality, the demand for cold chain logistics is increasing. Cold chain transportation means that during the transportation process, temperature-sensitive products (such as food, medicine, etc.) need to be transported in a specific low-temperature environment to ensure product quality. However, traditional temperature monitoring methods mostly rely on preset fixed modes, which are difficult to cope with the changing external environment and internal cargo status changes during actual transportation, resulting in inaccurate temperature control and easily affecting cargo quality. In addition, temperature data recording and exception handling in existing technologies are usually not automated and intelligent enough, and require manual intervention, which increases the management difficulty and cost during transportation.

[0003] Current cold chain transportation temperature control systems usually lack real-time data analysis and prediction functions, and cannot respond promptly to the impact of changes in the external environment and the heat changes of the goods themselves. This results in a long response time in the actual operation of the system once a temperature abnormality occurs, and the treatment measures may not be accurate or timely enough, thereby increasing the risk of damage to the goods. Therefore, it is particularly important to develop a system that can monitor and automatically adjust temperature control parameters in real time. Summary of the invention

[0004] Based on the above objectives, the present invention provides a method for intelligent temperature control during cold chain transportation.

[0005] A method for intelligent temperature control in a cold chain transportation process comprises the following steps:

[0006] S1: Install a machine vision-based temperature sensing device in the transport vehicle. The device uses infrared camera technology to continuously scan the cargo stacking area, monitor the temperature distribution of each cargo unit in real time, and output temperature data;

[0007] S2: Based on the temperature data output by S1, the adaptive temperature model algorithm is applied to analyze the type, size and stacking method of the cargo, calculate the thermal conductivity and thermal radiation characteristics of each cargo unit, and predict the trend of temperature change;

[0008] S3: Based on the temperature change trend predicted in S2, the central processor automatically adjusts the operating parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, to control the temperature of each cargo unit in the compartment;

[0009] S4: Deploy a temperature anomaly detection algorithm to monitor the temperature control results based on S3. When the temperature of a cargo unit deviates from the preset safe temperature range, the central processor will automatically increase the refrigeration intensity of the cargo unit to ensure that the temperature returns to the preset range.

[0010] S5: Based on the abnormal detection results in S4 and the historical data trend, predict the factors that cause temperature abnormalities, including changes in the external environment or increased self-heating of the cargo, and issue an early warning to the transportation management personnel;

[0011] S6: Based on all the data from S1 to S5, a temperature control report including a temperature distribution diagram, a refrigeration equipment work log and temperature abnormality records is automatically generated after the transportation is completed.

[0012] Optionally, the S1 specifically includes:

[0013] S11: Install infrared cameras at the top center and four corners of the transport vehicle to cover the entire cargo stacking area to capture temperature information from multiple angles and avoid visual blind spots;

[0014] S12: Each infrared camera is connected to a central processing unit in the vehicle via a data line, and the central processing unit is used to receive data input from each camera;

[0015] S13: An image processing algorithm is embedded in the central processing unit to interpret the temperature image captured by the infrared camera and convert the image into a digital temperature reading;

[0016] S14: Set the data collection frequency and adjust the scanning interval of the infrared camera according to the cargo type and transportation environment to adapt to different monitoring needs.

[0017] Optionally, the S13 specifically includes:

[0018] S131: preprocessing the original temperature image received from the infrared camera, including noise reduction and image enhancement;

[0019] S132: Apply image processing algorithm to calculate the temperature value of each pixel point, the formula is:

[0020] T=T ref +γ·(II ref ), where T represents the temperature of the pixel; T ref represents the reference temperature; γ represents the temperature calibration coefficient; I represents the intensity value of the current pixel; I ref Indicates the reference intensity value;

[0021] S133: Use a two-dimensional cubic interpolation method to smooth the temperature reading of a single pixel to eliminate local temperature anomalies. The formula is: T(x, y) = ∑ i，j T(x i ,y j )·k(xx i ,yy j ), where T(x, y) represents the temperature value at the position (x, y) after interpolation, in degrees Celsius; T(x i ,y j ) represents the temperature value of the surrounding pixels; k(xx i ,yy j ) represents the kernel function used for interpolation; x, y represent the position coordinates of the target pixel;

[0022] S134: Reformatting the interpolated temperature data into a digital temperature reading.

[0023] Optionally, the S2 specifically includes:

[0024] S21: Installing the adaptive temperature model algorithm software in the central processing unit, which receives the temperature data output from S1 as input;

[0025] S22: Analyze the input temperature data, identify the boundaries and positions of different cargo units, and determine the geometric size and relative position of each cargo unit using image analysis technology;

[0026] S23: The appearance characteristics of the goods are compared with the known types through the preset database, the type of goods is identified, and its thermal conductivity and thermal radiation characteristics are calculated. The thermal conductivity formula is: Where k is the thermal conductivity, Q is the heat flow through the cargo unit, ΔT is the temperature difference, and A conduction is the area of ​​heat transfer, Δx is the distance of heat transfer;

[0027] S24: Calculate the radiation exchange of each cargo unit using a thermal radiation model based on the Stefan-Boltzmann law, as follows: Among them, Q radiation is the radiative heat flux, ∈ is the emissivity, σ is the Stefan-Boltzmann constant, A radiation is the radiative surface area, T is the temperature of the cargo unit, T env is the ambient temperature;

[0028] S25: Based on historical data and real-time calculated thermal characteristics, predict the temperature change trend of each cargo unit and the temperature distribution of the entire cargo stacking area.

[0029] Optionally, the S25 specifically includes:

[0030] S251: collect and store the historical temperature data of each cargo unit to form a time series data set; and use the real-time temperature data and calculated thermal conductivity and thermal radiation characteristic data obtained from S2 as real-time input data;

[0031] S252: Use the Fourier heat conduction equation to establish the thermal conductivity model of the cargo unit. The formula is:

[0032] Where T is temperature, t is time, and α is thermal diffusivity. represents the Laplace operator, which is used to describe the variation of temperature over time and space;

[0033] S253: Perform time series analysis on historical temperature data, and specifically use an autoregressive integrated moving average model for prediction. The autoregressive integrated moving average model is defined as: Where T(t) is the temperature at time t; c is a constant term; represents the autoregressive coefficient of the i-th order;

[0034] θ j is the moving average coefficient, the coefficient of the jth order; ∈(t) is the random error term at time t; p is the order of autoregression; q is the order of moving average;

[0035] S254: Predict the temperature change trend, combine the real-time calculated thermal conductivity and thermal radiation characteristic data with the prediction results of the autoregressive integral moving average model, and use the Kalman filter to optimize the prediction accuracy. The formula is: in, is the temperature predicted at time t based on the information at t-1; is the predicted temperature at time t-1; K(t) is the Kalman gain at time t; T real-time (t) is the real-time temperature data at time t;

[0036] S255: The finite element method is used to simulate the temperature distribution of the entire cargo stacking area. Based on the thermal conductivity and thermal radiation characteristics of each cargo unit and the ambient temperature conditions, the temperature distribution equation is solved as follows:

[0037] Where Ω represents the area under consideration; δT represents the test function used in the finite element analysis; α represents the thermal diffusivity; Represents the gradient of temperature T, describing the rate of change of temperature in space; · represents the dot product operator.

[0038] Optionally, the S3 specifically includes:

[0039] S31: The central processor receives and analyzes the temperature change trend data from step S2, identifies the temperature change curve of each cargo unit in the future time period, and determines the temperature control parameters that need to be adjusted;

[0040] S32: Calculate the required refrigerant flow rate F according to the temperature change trend and the heat load demand of each cargo unit. The formula is: Where F is the refrigerant flow rate in kilograms per second, Q required is the required cooling capacity in Watts, ΔH is the change in specific enthalpy of the refrigerant in Joules per kilogram; the central processor will adjust the refrigerant flow by controlling the opening of the valve;

[0041] S33: According to the temperature change trend, determine the cooling air flow rate v that the fan needs to provide, the formula is:

[0042] Where v is the fan speed in meters per second; Q air is the heat flow of air in Watts; ρ is the air density in kilograms per cubic meter; A radiation is the cross-sectional area of ​​the fan in square meters; C p is the specific heat capacity of air in joules per kilogram per degree Celsius; ΔT is the change in air temperature in degrees Celsius;

[0043] S34: By analyzing the temperature change trend, determine the working and shutdown cycle τ of the refrigeration equipment, the formula is:

[0044] Where τ is the cooling cycle in seconds; ΔT set is the set temperature range in degrees Celsius; ΔT curent is the current temperature change in degrees Celsius; R is the cooling rate of the refrigeration equipment in degrees Celsius per second; the central processor will automatically adjust the start and stop time of the refrigeration equipment based on the calculation results.

[0045] Optionally, the S4 specifically includes:

[0046] S41: A temperature anomaly detection algorithm is embedded in the central processor. The anomaly detection algorithm first defines a preset safe temperature range T min To T max ;

[0047] S42: The temperature anomaly detection algorithm regularly receives the adjusted temperature data from S3 and monitors the current temperature T of each cargo unit in real time. current ;

[0048] S43: Temperature anomaly detection algorithm compares the T of each cargo unit current Compared with the preset safe temperature range, abnormality judgment is made. current Falling on T min and T max If it is outside the range, it is identified as temperature abnormality;

[0049] S44: When a temperature anomaly is detected, the central processor will calculate the additional cooling capacity required to correct the deviation;

[0050] S45: Automatically increase the operating intensity of the cooling equipment in the affected area based on the calculated additional cooling capacity, including increasing the refrigerant flow and fan speed.

[0051] Optionally, the additional cooling capacity is calculated as follows: Q extra =C·(T desired -T current ), where Q extra is the additional cooling capacity, C is the specific heat adjustment factor, T desired is the target temperature, T current is the current temperature.

[0052] Optionally, the S5 specifically includes:

[0053] S51: Collect and store the temperature anomaly detection results in S4, including the abnormal temperature data and its timestamp of each detection cycle; synchronously collect and store environmental data and cargo self-heating history data;

[0054] S52: Using historical data and temperature anomaly detection results, a regression analysis model is applied to determine the relationship between external environment changes and temperature anomalies. The regression model formula is:

[0055] T anomaly =β0+β1T emv +β2H env +β3Q self-heat +∈, where T anomaly is the abnormal temperature value, T env is the external ambient temperature, H env is the external ambient humidity, Q self-heat is the spontaneous heat of the cargo, β0, β1, β2, β3 are regression coefficients, and ∈ is the error term;

[0056] S53: Apply machine learning algorithms to establish a temperature anomaly prediction model based on historical data and train the model to identify the impact of different factors on temperature anomalies;

[0057] S54: Analyze the current external environment data and cargo temperature data in real time, input into the prediction model, and predict the factors causing temperature abnormality;

[0058] S55: Compare real-time data with historical trends and use a logistic regression model to estimate the probability of temperature anomalies: Among them, β0, β1, β2, β3 are regression coefficients; T env is the external ambient temperature; H env is the external environment humidity; Q self-heat is the spontaneous heat of the cargo; e is the base of the natural logarithm; this model takes the real-time monitored ambient temperature, humidity and spontaneous heat of the cargo as input and outputs a value between 0 and 1, indicating the probability of temperature anomaly. anomaly If the temperature exceeds the preset threshold, it will be judged as abnormal temperature;

[0059] S56: When P anomaly When the temperature is determined to be abnormal, warning information is generated, including the abnormal temperature prediction value, the factors causing the abnormality and the recommended measures; and a warning notification is sent to transportation management personnel via mobile applications, SMS or email.

[0060] Optionally, the S6 specifically includes:

[0061] S61: During the entire transportation process, collect and store the temperature data obtained from S1, the refrigeration equipment operating parameters obtained from S3, the temperature anomaly detection results obtained from S4, and the warning data obtained from S5, and store all the collected data in the internal database of the central processor, and back it up regularly during the transportation process;

[0062] S62: After the transportation is completed, the stored data is sorted and processed, including the integration of temperature data on the time axis, statistical analysis of refrigeration equipment working parameters, and classification of abnormal temperature records; and data processing software is used to convert all data into visual charts and text information;

[0063] S63: Based on the time axis, the temperature data of the entire transportation process is plotted into a temperature distribution diagram to show the temperature change at each time point and indicate the temperature curves of different cargo units; temperature abnormal points are marked in the temperature distribution diagram to show the time and location of the abnormality;

[0064] S64: extracting data from the stored operating parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, and arranging the data into a working log in chronological order;

[0065] S65: sorting out the temperature anomaly detection results and warning data, generating temperature anomaly records, and recording the information of each anomaly detection, including the abnormal temperature value, detection time, abnormal duration, and the response measures taken;

[0066] S66: Integrate the generated temperature distribution graph, refrigeration equipment work log and temperature anomaly record into a comprehensive temperature control report.

[0067] Beneficial effects of the present invention:

[0068] The present invention, by introducing advanced temperature anomaly detection algorithms and adaptive temperature control technology, can monitor temperature data in real time and automatically adjust the working parameters of refrigeration equipment to adapt to the influence of external environmental changes and self-heating of goods. This real-time and dynamic temperature control method not only reduces the risk of cargo damage caused by temperature anomalies, but also optimizes energy use and reduces transportation costs.

[0069] The present invention, through the intelligent early warning system, promptly issues early warning to transportation management personnel, enabling the management personnel to quickly take corresponding measures, thereby further improving the safety and reliability of cold chain transportation. Through the automatically generated temperature distribution map, refrigeration equipment work log and temperature abnormality record report, the present invention also provides detailed data analysis and recording functions, which are helpful for transportation management personnel to track quality and optimize the process, and improve the management efficiency and transparency of the entire cold chain system. This comprehensive temperature control solution significantly improves the quality assurance level of cargo transportation, and ensures product quality and customer satisfaction during transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0071] Figure 1 A schematic diagram of an intelligent temperature control method according to an embodiment of the present invention;

[0072] Figure 2 This is a schematic diagram of a process for real-time monitoring of the temperature distribution of each cargo unit according to an embodiment of the present invention;

[0073] Figure 3 It is a temperature change curve diagram in a future time period of an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0075] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0076] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0077] like Figure 1-Figure 2 As shown, a method for intelligent temperature control in a cold chain transportation process includes the following steps:

[0078] S1: Install a machine vision-based temperature sensing device in the transport vehicle. The device uses infrared camera technology to continuously scan the cargo stacking area, monitor the temperature distribution of each cargo unit in real time, and output temperature data;

[0079] S2: Based on the temperature data output by S1, the adaptive temperature model algorithm is applied to analyze the type, size and stacking method of the cargo, calculate the thermal conductivity and thermal radiation characteristics of each cargo unit, and predict the trend of temperature change;

[0080] S3: Based on the temperature change trend predicted in S2, the central processor automatically adjusts the operating parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, to control the temperature of each cargo unit in the compartment;

[0081] S4: Deploy a temperature anomaly detection algorithm to monitor the temperature control results based on S3. When the temperature of a cargo unit deviates from the preset safe temperature range, the central processor will automatically increase the refrigeration intensity of the cargo unit to ensure that the temperature returns to the preset range.

[0082] S5: Based on the abnormal detection results in S4 and the historical data trend, predict the factors that cause temperature abnormalities, including changes in the external environment or increased self-heating of the cargo, and issue an early warning to the transportation management personnel;

[0083] S6: Based on all the data from S1 to S5, a temperature control report with a temperature distribution diagram, refrigeration equipment work log and temperature abnormality record is automatically generated after the transportation is completed for quality assessment and process optimization.

[0084] S1 specifically includes:

[0085] S11: Install infrared cameras at the top center and four corners of the transport vehicle to cover the entire cargo stacking area to capture temperature information from multiple angles and avoid visual blind spots;

[0086] S12: Each infrared camera is connected to a central processing unit in the vehicle via a data line, and the central processing unit is used to receive data input from each camera;

[0087] S13: An image processing algorithm is embedded in the central processing unit to interpret the temperature image captured by the infrared camera and convert the image into a digital temperature reading;

[0088] S14: Setting the data collection frequency, adjusting the scanning interval of the infrared camera according to the type of goods and the transportation environment changes to adapt to different monitoring needs, such as increasing the scanning frequency in areas with high temperatures or frequent changes during transportation; the temperature data collected by the infrared camera is processed by the central processing unit and transmitted to the remote monitoring center in real time through the on-board wireless network module for further data analysis and recording; installing multiple infrared cameras in the transport vehicle through the above method to ensure coverage of every corner of the cargo stacking area, and capturing temperature image data in real time, and converting these image data into specific temperature values ​​through the image processing algorithm of the central processing unit, and storing and transmitting them, thereby achieving high-precision and real-time temperature monitoring. This method enhances the response capability to temperature changes in cold chain transportation and ensures the quality stability of goods during transportation.

[0089] The image processing algorithms in S13 specifically include:

[0090] S131: preprocessing the raw temperature image received from the infrared camera, including noise reduction and image enhancement, to improve image quality;

[0091] S132: Apply image processing algorithm to calculate the temperature value of each pixel point, the formula is:

[0092] T=T ref +γ·(II ref ), where T represents the temperature of the pixel in degrees Celsius (℃); T refrepresents the reference temperature, which is the base temperature value determined by the calibration process under specific conditions, in degrees Celsius; γ represents the temperature calibration coefficient, which is an experimentally determined coefficient used to adjust the relationship between the pixel intensity and the actual temperature; I represents the intensity value of the current pixel, which is the brightness or grayscale value of the pixel in the image captured by the infrared camera; I ref It represents the reference intensity value, which is the base intensity value determined by calibration under a predetermined environment;

[0093] S133: Use a two-dimensional cubic interpolation method to smooth the temperature reading of a single pixel to eliminate local temperature anomalies. The formula is: T(x, y) = ∑ i，j T(x i ,y j )·k(xx i ,yy j ), where T(x, y) represents the temperature value at the position (x, y) after interpolation, in degrees Celsius; T(x i ,y j ) represents the temperature value of the surrounding pixels, in degrees Celsius; k(xx i ,yy j ) represents a kernel function used for interpolation, which adjusts the weight according to the relative position of different pixels, and is used for smoothing and uniform distribution of temperature values; x, y represent the position coordinates of the target pixel, where x and y are the pixel position indexes on the image, which are integers;

[0094] S134: Reformatting the interpolated temperature data into digital temperature readings and outputting them into a standard digital format suitable for further data analysis and monitoring.

[0095] S2 specifically includes:

[0096] S21: installing an adaptive temperature model algorithm software in the central processing unit, which receives the temperature data output from S1 as input;

[0097] S22: Analyze the input temperature data, identify the boundaries and positions of different cargo units, and determine the geometric size and relative position of each cargo unit using image analysis technology;

[0098] The steps to determine the geometric dimensions and relative position of each cargo unit are as follows:

[0099] S221: Perform image preprocessing, first denoise the image received from the infrared camera, use a Gaussian filter to reduce image noise; then apply histogram equalization to enhance image contrast so as to more clearly distinguish different cargo units.

[0100] S222: Use the Canny edge detection algorithm to identify the edges in the image. This algorithm first uses a set of Gaussian filters to smooth the image, then calculates the gradient magnitude and direction of the image, and finally detects and connects the edges using a double threshold method. The formula is: Where G is the gradient magnitude, G x and G y is the gradient of the image in the x and y directions;

[0101] S223: Perform image segmentation using a region growing algorithm, starting from the identified edge pixel points, add adjacent pixel points to the corresponding cargo unit if their pixel point intensities are similar and are not marked as the boundaries of other cargo units; perform connected component analysis on the region growing results to identify independent cargo units, each connected component representing a cargo unit;

[0102] S224: Geometric size and position measurement: for each independent cargo unit, calculate its minimum circumscribed rectangle to determine the size (length and width) of the cargo unit; then calculate the geometric center of the circumscribed rectangle of each cargo unit and use it as the position coordinate of the cargo unit.

[0103] S23: The appearance characteristics of the goods are compared with the known types through the preset database, the type of goods is identified, and its thermal conductivity and thermal radiation characteristics are calculated. The thermal conductivity formula is: Where k is the thermal conductivity, Q is the heat flow through the cargo unit, ΔT is the temperature difference, and A conduction is the area of ​​heat transfer, Δx is the distance of heat transfer;

[0104] S24: Apply the thermal radiation model to calculate the radiation exchange of each cargo unit. The thermal radiation model is based on the Stefan-Boltzmann law and the formula is: Among them, Q radiation is the radiative heat flux, ∈ is the emissivity, σ is the Stefan-Boltzmann constant, A radiation is the radiative surface area, T is the temperature of the cargo unit, T env is the ambient temperature;

[0105] S25: Based on historical data and real-time calculated thermal characteristics, predict the temperature change trend of each cargo unit and the temperature distribution of the entire cargo stacking area; through the above steps, the adaptive temperature model algorithm can accurately analyze and predict the thermal characteristics and temperature changes of the cargo unit, providing a scientific basis and support for temperature control in cold chain transportation. This method enhances the accuracy and response speed of temperature control, thereby ensuring the quality and safety of the goods during transportation.

[0106] S25 specifically includes:

[0107] S251: collect and store the historical temperature data of each cargo unit to form a time series data set; and use the real-time temperature data and calculated thermal conductivity and thermal radiation characteristic data obtained from S2 as real-time input data;

[0108] S252: Use the Fourier heat conduction equation to establish a thermal conductivity model for the cargo unit. This equation is based on physical principles and describes how heat is transferred inside an object over time and space. The formula is:

[0109] Where T is temperature, t is time, and α is thermal diffusivity. represents the Laplace operator, which is used to describe the variation of temperature over time and space;

[0110] S253: Perform time series analysis on historical temperature data, specifically using an autoregressive integrated moving average model (ARIMA) for prediction. The autoregressive integrated moving average model is defined as: Where T(t) is the temperature at time t; c is a constant term; represents the autoregressive coefficient of the i-th order;

[0111] θ j is the moving average coefficient, the coefficient of the jth order; ∈(t) is the random error term at time t; p is the order of autoregression, indicating the number of lag terms included in the model; q is the order of moving average, indicating the number of sliding average terms included in the model;

[0112] S254: Predict the temperature change trend, combine the real-time calculated thermal conductivity and thermal radiation characteristic data with the prediction results of the autoregressive integral moving average model, and use the Kalman filter to optimize the prediction accuracy. The formula is: in, is the temperature predicted at time t based on the information at t-1; is the predicted temperature at time t-1; K(t) is the Kalman gain at time t, which is used to adjust the weight between the predicted value and the actual observed value; T real-time (t) is the real-time temperature data at time t;

[0113] S255: The finite element method (FEM) is used to simulate the temperature distribution of the entire cargo stacking area. Based on the thermal conductivity and thermal radiation characteristics of each cargo unit and the ambient temperature conditions, the temperature distribution equation is solved as follows:

[0114] Where Ω represents the area under consideration, which is the cargo stacking area in this case; δT represents the test function used in the finite element analysis, which is associated with the main temperature function T; α represents the thermal diffusivity; Represents the gradient of temperature T, describing the rate of change of temperature in space, in degrees Celsius per meter; · represents the dot product operator, which is used to calculate the dot product of two vectors; Through the above steps, based on historical data and real-time calculated thermal characteristics, the temperature change trend of each cargo unit can be accurately predicted, and the temperature distribution of the entire cargo stacking area can be simulated. This method improves the accuracy and response speed of temperature control, thereby ensuring the quality and safety of the cargo during transportation.

[0115] S3 specifically includes:

[0116] S31: The central processor receives and analyzes the temperature change trend data from step S2, identifies the temperature change curve of each cargo unit in the future time period, and determines the temperature control parameters that need to be adjusted;

[0117] Figure 3 It is the temperature change curve in the future time period, where the horizontal axis represents time (unit: hour) and the vertical axis represents temperature (unit: Celsius). The curve combines the basic temperature, temperature fluctuation amplitude and the temperature rising trend over time. In this way, the central processor can predict the temperature change trend of each cargo unit, thereby adjusting the working parameters of the refrigeration equipment to achieve precise temperature control.

[0118] S32: Calculate the required refrigerant flow rate F according to the temperature change trend and the heat load demand of each cargo unit. The formula is: Where F is the refrigerant flow rate in kilograms per second, Q required is the required cooling capacity in Watts, ΔH is the change in specific enthalpy of the refrigerant in Joules per kilogram; the central processor will adjust the refrigerant flow by controlling the opening of the valve to ensure that the cooling needs of each cargo unit are met;

[0119] S33: According to the temperature change trend, determine the cooling air flow rate v that the fan needs to provide, the formula is:

[0120] Where v is the fan speed in meters per second; Q air is the heat flow of air in Watts; ρ is the air density in kilograms per cubic meter; A radiation is the cross-sectional area of ​​the fan in square meters; C p is the specific heat capacity of the air, in joules per kilogram per degree Celsius; ΔT is the change in air temperature, in degrees Celsius; The central processor adjusts the fan motor speed to achieve the required fan speed to ensure that the air flow in the car meets the temperature control requirements;

[0121] S34: By analyzing the temperature change trend, determine the working and shutdown cycle τ of the refrigeration equipment, the formula is:

[0122] Where τ is the cooling cycle in seconds; ΔT set is the set temperature range in degrees Celsius; ΔT current is the current temperature change in degrees Celsius; R is the cooling rate of the refrigeration equipment in degrees Celsius per second; the central processor will automatically adjust the start and stop time of the refrigeration equipment based on the calculation results to ensure that the temperature in the car is stable within the predetermined range;

[0123] Through the above steps, the central processor can automatically adjust the working parameters of the refrigeration equipment according to the predicted temperature change trend, including refrigerant flow, fan speed and refrigeration cycle, so as to effectively control the temperature of each cargo unit in the carriage. This method ensures the accuracy and real-time performance of temperature control and ensures the quality and safety of the goods during cold chain transportation.

[0124] S4 specifically includes:

[0125] S41: A temperature anomaly detection algorithm is embedded in the central processor. The anomaly detection algorithm first defines a preset safe temperature range T min To T max ;

[0126] S42: The temperature anomaly detection algorithm regularly receives the adjusted temperature data from S3 and monitors the current temperature T of each cargo unit in real time. current ;

[0127] S43: Temperature anomaly detection algorithm compares the T of each cargo unit current Compared with the preset safe temperature range, abnormality judgment is made. current Falling on T min and T max If it is outside the range, it is identified as temperature abnormality;

[0128] S44: When a temperature anomaly is detected, the central processor will calculate the additional cooling capacity required to correct the deviation;

[0129] S45: Automatically increase the working intensity of the refrigeration equipment in the affected area based on the calculated additional cooling capacity, including increasing the refrigerant flow and fan speed;

[0130] Through the above steps, the central processor can effectively monitor and adjust the temperature of the cargo unit through the deployed temperature anomaly detection algorithm. When the temperature deviates from the preset safety range, the system can respond quickly, automatically enhance the refrigeration intensity, ensure temperature stability, and thus maintain the quality and safety of the goods during cold chain transportation.

[0131] The additional cooling capacity is calculated as: Q extra =C·(T desired -T current ), where Q extra is the additional cooling capacity, C is the specific heat adjustment factor, T desired is the target temperature, T current is the current temperature.

[0132] S5 specifically includes:

[0133] S51: Collect and store the temperature anomaly detection results in S4, including the abnormal temperature data and its timestamp for each detection cycle; synchronously collect and store environmental data (such as external temperature and humidity) and cargo self-heating history data;

[0134] S52: Using historical data and temperature anomaly detection results, a regression analysis model is applied to determine the relationship between external environment changes and temperature anomalies. The regression model formula is:

[0135] T anomaly =β0+β1T env +β2H emv +β3Q self-heat +∈, where T anomaly is the abnormal temperature value, T env is the external ambient temperature, H env is the external ambient humidity, Q self-heat is the spontaneous heat of the cargo, β0, β1, β2, β3 are regression coefficients, and ∈ is the error term;

[0136] S53: Apply machine learning algorithms (such as support vector machines (SVM) or random forests (RF)) to establish a temperature anomaly prediction model based on historical data, and train the model to identify the impact of different factors on temperature anomalies;

[0137] S54: Analyze the current external environment data and cargo temperature data in real time, input into the prediction model, and predict the factors causing temperature abnormality;

[0138] S55: Compare real-time data with historical trends and use a logistic regression model to estimate the probability of temperature anomalies: Among them, β0, β1, β2, β3 are regression coefficients, which are determined by training with historical data; T env is the external ambient temperature; Henv is the external environment humidity; Q self-heat is the spontaneous heat of the cargo; e is the base of the natural logarithm, approximately equal to 2.71828; this model takes the real-time monitored ambient temperature, humidity and spontaneous heat of the cargo as input, and outputs a value between 0 and 1, indicating the probability of temperature anomaly. anomaly If the temperature exceeds the preset threshold (e.g. 0.5), it will be judged as abnormal temperature;

[0139] S56: When P anomaly When the temperature is determined to be abnormal, warning information is generated, including the abnormal temperature prediction value, the factors causing the abnormality and the recommended measures; and a warning notification is sent to the transportation management personnel via mobile applications, text messages or emails; through the above steps, based on the temperature abnormality detection results and historical data trends, the factors causing the temperature abnormality can be predicted, and warnings can be issued to the transportation management personnel in real time to ensure that the temperature control during the cold chain transportation process is more accurate and reliable. This method makes temperature abnormality detection more accurate and automated, and can effectively identify potential risks in advance, thereby protecting the goods from inappropriate temperatures.

[0140] S6 specifically includes:

[0141] S61: During the entire transportation process, collect and store the temperature data obtained from S1, the refrigeration equipment operating parameters obtained from S3, the temperature anomaly detection results obtained from S4, and the warning data obtained from S5, and store all the collected data in the internal database of the central processor, and back it up regularly during the transportation process;

[0142] S62: After transportation, the stored data is sorted and processed, including the integration of temperature data on the time axis, statistical analysis of refrigeration equipment operating parameters, and classification of abnormal temperature records; and data processing software is used to convert all data into visual charts and text information to prepare the content of the temperature control report;

[0143] S63: Based on the time axis, the temperature data of the entire transportation process is plotted into a temperature distribution diagram to show the temperature change at each time point and indicate the temperature curves of different cargo units; temperature abnormal points are marked in the temperature distribution diagram to show the time and location of the abnormality for subsequent analysis;

[0144] S64: extracting data from the stored working parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, and arranging the data into a work log in chronological order; marking the time point and reason for each parameter adjustment in the work log, and providing a detailed equipment operation record;

[0145] S65: Organize the temperature anomaly detection results and warning data, generate temperature anomaly records, and record the information of each anomaly detection, including the abnormal temperature value, detection time, abnormal duration, and the response measures taken; summarize the possible causes of the temperature anomaly in the anomaly record, and provide relevant data support, such as external environment changes and cargo self-heating data;

[0146] S66: The generated temperature distribution map, refrigeration equipment work log and temperature abnormality record are integrated into a comprehensive temperature control report. The temperature control report is saved in the form of an electronic document and uploaded to the central management system via a wireless network for transportation management personnel to view and analyze.

[0147] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0148] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for intelligent temperature control in cold chain transportation, characterized in that: The following steps are involved: S1: Install a machine vision-based temperature sensing device in the transport vehicle. The device uses infrared camera technology to continuously scan the cargo stacking area, monitor the temperature distribution of each cargo unit in real time, and output temperature data; S2: Based on the temperature data output by S1, the adaptive temperature model algorithm is applied to analyze the type, size and stacking method of the cargo, calculate the thermal conductivity and thermal radiation characteristics of each cargo unit, and predict the trend of temperature change; The S2 specifically includes: S21: Installing the adaptive temperature model algorithm software in the central processing unit, which receives the temperature data output from S1 as input; S22: Analyze the input temperature data, identify the boundaries and positions of different cargo units, and determine the geometric size and relative position of each cargo unit using image analysis technology; S23: The appearance characteristics of the goods are compared with the known types through the preset database, the type of goods is identified, and its thermal conductivity and thermal radiation characteristics are calculated. The thermal conductivity formula is: Where k is the thermal conductivity, Q is the heat flow through the cargo unit, ΔT is the temperature difference, and A conduction is the area of ​​heat transfer, Δx is the distance of heat transfer; S24: Apply the thermal radiation model to calculate the radiation exchange of each cargo unit. The thermal radiation model is based on the Stefan-Boltzmann law and the formula is: Among them, Q radiation is the radiative heat flux, ∈ is the emissivity, σ is the Stefan-Boltzmann constant, A radiation is the radiative surface area, T is the temperature of the cargo unit, T env is the ambient temperature; S25: Predict the temperature trend of each cargo unit and the temperature distribution of the entire cargo stacking area based on historical data and real-time calculated thermal characteristics; S3: Based on the temperature change trend predicted in S2, the central processor automatically adjusts the operating parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, to control the temperature of each cargo unit in the compartment; S4: Deploy a temperature anomaly detection algorithm to monitor the temperature control results based on S3. When the temperature of a cargo unit deviates from the preset safe temperature range, the central processor will automatically increase the refrigeration intensity of the cargo unit to ensure that the temperature returns to the preset range. S5: Based on the abnormal detection results in S4 and the historical data trend, predict the factors that cause temperature abnormalities, including changes in the external environment or increased self-heating of the cargo, and issue an early warning to the transportation management personnel; S6: Based on all the data from S1 to S5, a temperature control report including a temperature distribution diagram, a refrigeration equipment work log and temperature abnormality records is automatically generated after the transportation is completed.

2. According to claim 1, a temperature intelligent control method in a cold chain transportation process is characterized in that: The S1 specifically includes: S11: Install infrared cameras at the top center and four corners of the transport vehicle to cover the entire cargo stacking area to capture temperature information from multiple angles; S12: Each infrared camera is connected to a central processing unit in the vehicle via a data line, and the central processing unit is used to receive data input from each camera; S13: An image processing algorithm is embedded in the central processing unit to interpret the temperature image captured by the infrared camera and convert the image into a digital temperature reading; S14: Set the data collection frequency and adjust the scanning interval of the infrared camera according to the cargo type and transportation environment to adapt to different monitoring needs.

3. The method for intelligent temperature control in cold chain transportation according to claim 2, characterized in that: The S13 specifically includes: S131: preprocessing the original temperature image received from the infrared camera, including noise reduction and image enhancement; S132: Apply image processing algorithm to calculate the temperature value of each pixel point, the formula is: T=T ref +γ·(II ref ), where T represents the temperature of the pixel; T ref represents the reference temperature; γ represents the temperature calibration coefficient; I represents the intensity value of the current pixel; I ref Indicates the reference intensity value; S133: Use a two-dimensional cubic interpolation method to smooth the temperature reading of a single pixel to eliminate local temperature anomalies. The formula is: T(x, y) = ∑ i，j T(x i ,y j )·k(xx i ,yy j ), where T(x, y) represents the temperature value at the position (x, y) after interpolation, in degrees Celsius; T(x i ,y j ) represents the temperature value of the surrounding pixels; k(xx i ,yy j ) represents the kernel function used for interpolation; x, y represent the position coordinates of the target pixel; S134: Reformatting the interpolated temperature data into a digital temperature reading.

4. The method for intelligent temperature control in cold chain transportation according to claim 1, characterized in that: The S25 specifically includes: S251: collect and store the historical temperature data of each cargo unit to form a time series data set; and use the real-time temperature data and calculated thermal conductivity and thermal radiation characteristic data obtained from S2 as real-time input data; S252: Use the Fourier heat conduction equation to establish the thermal conductivity model of the cargo unit. The formula is: Where T is temperature, t is time, and α is thermal diffusivity. represents the Laplace operator, which is used to describe the variation of temperature over time and space; S253: Perform time series analysis on historical temperature data, and specifically use an autoregressive integrated moving average model for prediction. The autoregressive integrated moving average model is defined as: Where T(t) is the temperature at time t; c is a constant term; represents the autoregressive coefficient of the i-th order; θ j is the moving average coefficient, the coefficient of the jth order; ∈(t) is the random error term at time t; p is the order of autoregression; q is the order of moving average; S254: Predict the temperature change trend, combine the real-time calculated thermal conductivity and thermal radiation characteristic data with the prediction results of the autoregressive integral moving average model, and use the Kalman filter to optimize the prediction accuracy. The formula is: in, is the temperature predicted at time t based on the information at t-1; is the predicted temperature at time t-1; K(t) is the Kalman gain at time t; T real-time (t) is the real-time temperature data at time t; S255: The finite element method is used to simulate the temperature distribution of the entire cargo stacking area. Based on the thermal conductivity and thermal radiation characteristics of each cargo unit and the ambient temperature conditions, the temperature distribution equation is solved as follows: Where Ω represents the area under consideration; δT represents the test function used in the finite element analysis; α represents the thermal diffusivity; Represents the gradient of temperature T, describing the rate of change of temperature in space; · represents the dot product operator.

5. The method for intelligent temperature control in cold chain transportation according to claim 1, characterized in that: The S3 specifically includes: S31: The central processor receives and analyzes the temperature change trend data from step S2, identifies the temperature change curve of each cargo unit in the future time period, and determines the temperature control parameters that need to be adjusted; S32: Calculate the required refrigerant flow rate F according to the temperature change trend and the heat load demand of each cargo unit. The formula is: Where F is the refrigerant flow rate in kilograms per second, Q required is the required cooling capacity in Watts, ΔH is the change in specific enthalpy of the refrigerant in Joules per kilogram; the central processor will adjust the refrigerant flow by controlling the opening of the valve; S33: According to the temperature change trend, determine the cooling air flow rate v that the fan needs to provide, the formula is: Where v is the fan speed in meters per second; Q air is the heat flow of air in Watts; ρ is the air density in kilograms per cubic meter; A radiation is the cross-sectional area of ​​the fan in square meters; C p is the specific heat capacity of air in joules per kilogram per degree Celsius; ΔT is the change in air temperature in degrees Celsius; S34: By analyzing the temperature change trend, determine the working and shutdown cycle τ of the refrigeration equipment, the formula is: Where τ is the cooling cycle in seconds; ΔT set is the set temperature range in degrees Celsius; ΔT current is the current temperature change in degrees Celsius; R is the cooling rate of the refrigeration equipment in degrees Celsius per second; the central processor will automatically adjust the start and stop time of the refrigeration equipment based on the calculation results.

6. The method for intelligent temperature control in cold chain transportation according to claim 1, characterized in that: The S4 specifically includes: S41: A temperature anomaly detection algorithm is embedded in the central processor. The anomaly detection algorithm first defines a preset safe temperature range T min To T max ; S42: The temperature anomaly detection algorithm regularly receives the adjusted temperature data from S3 and monitors the current temperature T of each cargo unit in real time. current ; S43: Temperature anomaly detection algorithm compares the T of each cargo unit current Compared with the preset safe temperature range, abnormality judgment is made. current Falling on T min and T max If it is outside the range, it is identified as temperature abnormality; S44: When a temperature anomaly is detected, the central processor will calculate the additional cooling capacity required to correct the deviation; S45: Automatically increase the operating intensity of the cooling equipment in the affected area based on the calculated additional cooling capacity, including increasing the refrigerant flow and fan speed.

7. The method for intelligent temperature control in cold chain transportation according to claim 6, characterized in that: The additional cooling capacity is calculated as: Q extra =C·(T desired -T current ), where Q extra is the additional cooling capacity, C is the specific heat adjustment factor, T desired is the target temperature, T current is the current temperature.

8. The method for intelligent temperature control in cold chain transportation according to claim 1, characterized in that: The S5 specifically includes: S51: Collect and store the temperature anomaly detection results in S4, including the abnormal temperature data and its timestamp of each detection cycle; synchronously collect and store environmental data and cargo self-heating history data; S52: Using historical data and temperature anomaly detection results, a regression analysis model is applied to determine the relationship between external environment changes and temperature anomalies. The regression model formula is: T anomaly =β0+β1T env +β2H env +β3Q self-heat +∈, where T anomaly is the abnormal temperature value, T env is the external ambient temperature, H env is the external ambient humidity, Q self-heat is the spontaneous heat of the cargo, β0, β1, β2, β3 are regression coefficients, and ∈ is the error term; S53: Apply machine learning algorithms to establish a temperature anomaly prediction model based on historical data and train the model to identify the impact of different factors on temperature anomalies; S54: Analyze the current external environment data and cargo temperature data in real time, input into the prediction model, and predict the factors causing temperature abnormality; S55: Compare real-time data with historical trends and use a logistic regression model to estimate the probability of temperature anomalies: Among them, β0, β1, β2, β3 are regression coefficients; T env is the external ambient temperature; H env is the external environment humidity; Q self-heat is the spontaneous heat of the cargo; e is the base of the natural logarithm; this model takes the real-time monitored ambient temperature, humidity and spontaneous heat of the cargo as input and outputs a value between 0 and 1, indicating the probability of temperature anomaly. anomaly If the temperature exceeds the preset threshold, it will be judged as abnormal temperature; S56: When P anomaly When the temperature is determined to be abnormal, warning information is generated, including the abnormal temperature prediction value, the factors causing the abnormality and the recommended measures; and a warning notification is sent to transportation management personnel via mobile applications, SMS or email.

9. The method for intelligent temperature control in cold chain transportation according to claim 1, characterized in that: The S6 specifically includes: S61: During the entire transportation process, collect and store the temperature data obtained from S1, the refrigeration equipment operating parameters obtained from S3, the temperature anomaly detection results obtained from S4, and the warning data obtained from S5, and store all the collected data in the internal database of the central processor, and back it up regularly during the transportation process; S62: After the transportation is completed, the stored data is sorted and processed, including the integration of temperature data on the time axis, statistical analysis of refrigeration equipment working parameters, and classification of abnormal temperature records; and data processing software is used to convert all data into visual charts and text information; S63: Based on the time axis, the temperature data of the entire transportation process is plotted into a temperature distribution diagram to show the temperature change at each time point and indicate the temperature curves of different cargo units; temperature abnormal points are marked in the temperature distribution diagram to show the time and location of the abnormality; S64: extracting data from the stored operating parameters of the refrigeration equipment, including refrigerant flow, fan speed, and refrigeration cycle, and arranging the data into a working log in chronological order; S65: sorting out the temperature anomaly detection results and warning data, generating temperature anomaly records, and recording the information of each anomaly detection, including the abnormal temperature value, detection time, abnormal duration, and the response measures taken; S66: Integrate the generated temperature distribution graph, refrigeration equipment work log and temperature anomaly record into a comprehensive temperature control report.

Images