Cold-chain logistics real-time monitoring method and system

Abstract

The invention discloses a cold-chain logistics real-time monitoring method and system, and the method comprises the steps: setting temperature sensors and humidity sensors at all measurement points in a cold-chain logistics transportation carriage, and obtaining the temperature and humidity of each measurement point; the operation frequency and refrigeration power of a cold-chain logistics transportation compartment refrigerator are obtained, and meanwhile the ventilation quantity of a cold-chain logistics transportation compartment ventilation device is obtained; uploading all the acquired data to a monitoring server, calculating the average value and variance of the temperature and humidity of all the measurement points, and calculating a first characteristic value, a second characteristic value and a third characteristic value according to the operation frequency and the refrigeration power of the refrigerating machine of the cold-chain logistics transportation compartment and the ventilation quantity of the ventilation equipment, and inputting the logistic regression model of which the parameter training is completed, and generating an abnormal state confidence coefficient to judge whether the interior of the current cold-chain logistics transportation carriage is abnormal or not. According to the invention, fault prediction and health management in the cold-chain logistics transportation process based on each operation data of the cold-chain logistics transportation compartment are realized.

Description

Technical Field

[0001] The present invention relates to the field of logistics monitoring, and in particular to a method and system for real-time monitoring of cold chain logistics. Background Art

[0002] In cold chain logistics, timeliness and reliability are crucial. Timeliness determines the speed of cold chain logistics transportation, while reliability determines the transportation quality and the integrity of the goods. The reliability of cold chain logistics is determined by the robustness of the refrigeration system. If a refrigeration failure occurs during cold chain logistics transportation, it will cause irreversible damage to the goods and lead to irreparable economic losses. Therefore, real-time status monitoring of the refrigeration system of cold chain logistics transport vehicles is very important. When problems such as temperature anomalies and equipment failures occur, alarm signals can be issued in a timely manner so that timely measures can be taken.

[0003] However, the existing public technologies for monitoring cold chain logistics have the problem of a single monitoring process and cannot monitor the real-time status of the refrigeration system of cold chain logistics transport vehicles in multiple dimensions. In addition, simply judging whether the refrigeration system of the cold chain logistics transport vehicle is abnormal through threshold judgment cannot meet the requirements of unified abnormal status judgment for different refrigeration states in different transportation scenarios. Summary of the Invention

[0004] The purpose of the present invention is to provide a real-time monitoring method and system for cold chain logistics, aiming to solve the problem that the existing public technology for monitoring cold chain logistics has a single monitoring process and cannot monitor the real-time status of the refrigeration system of the cold chain logistics transport vehicle in multiple dimensions. It simply judges whether the refrigeration system of the cold chain logistics transport vehicle is abnormal through threshold judgment, which cannot meet the problem of unified abnormal status judgment for different refrigeration states in different transportation scenarios.

[0005] In view of the above problems, the present application provides a method and system for real-time monitoring of cold chain logistics.

[0006] The first aspect disclosed in the present application provides a method for real-time monitoring of cold chain logistics, the method comprising the following steps: Step 1: Install temperature sensors and humidity sensors at all measurement points inside the cold chain logistics transport carriage to obtain the temperature and humidity of each measurement point in real time. All measurement points inside the cold chain logistics transport carriage are evenly distributed. Step 2: Obtain the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment in real time, and simultaneously obtain the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time; Step 3: Upload all the data acquired in real time in steps 1 and 2 to the monitoring server. The monitoring server calculates the mean and variance of the temperature and humidity at all measurement points in real time, and calculates the first, second, and third eigenvalues in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment; Step 4: Input all the data calculated in real time by the monitoring server in step 3 into the trained logistic regression model to generate real-time abnormal state confidence. Step 5: Determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal status confidence exceeds a predetermined threshold.

[0007] Preferably, the step 3 specifically includes the following steps: Step 3.1: Upload all data obtained in steps 1 and 2 to the monitoring server in real time; Step 3.2: The monitoring server calculates the mean and variance of temperature and humidity in real time based on the temperature and humidity at all measurement points inside the cold chain logistics transport compartment. Step 3.3: According to the operating frequency of the refrigeration machine in the cold chain logistics transport compartment and cooling power , the first eigenvalue is calculated in real time using formula (1) and formula (2) respectively and the second eigenvalue : Formula (1) Formula (2) in, and They are the preset standard operating frequency and standard cooling power, and They are the allowable fluctuation ranges of standard operating frequency and standard cooling power respectively; Step 3.4: According to the ventilation volume of the cold chain logistics transport compartment ventilation equipment , use formula (3) to calculate the third eigenvalue in real time : Formula (3).

[0008] Preferably, step 4 specifically includes the following steps: Step 4.1: Collect the mean and variance of the temperature and humidity at all measurement points inside 1,000 historical cold chain logistics transport carriages, and calculate the first, second, and third eigenvalues corresponding to the 1,000 historical cold chain logistics transport carriages. Construct a sample dataset and label each sample in the sample dataset as abnormal using 1 or 0. Step 4.2: Establish a logistic regression model, initialize the parameters of the logistic regression model, perform binary classification training on the logistic regression model based on the sample data set, and iteratively train the parameters of the logistic regression model through maximum likelihood estimation. The output of the logistic regression model is the probability value of the abnormal state; Step 4.3: Input the mean and variance of the temperature and humidity of all measurement points calculated in real time in step 3, as well as the first eigenvalue, second eigenvalue, and third eigenvalue into the logistic regression monitoring model that has completed parameter training to generate a real-time abnormal state probability value as the real-time abnormal state confidence.

[0009] Preferably, the parameters of the logistic regression model are initialized in step 4.2 by randomly sampling values from a standard normal distribution with a mean of 0 and a standard deviation of 0.01, and assigning the values to the parameters of the logistic regression model respectively.

[0010] The second aspect disclosed in the present application provides a cold chain logistics real-time monitoring system, which is used in the above-mentioned cold chain logistics real-time monitoring method, and the system includes: A first acquisition module is configured to set temperature sensors and humidity sensors at all measurement points inside the cold chain logistics transport compartment to obtain the temperature and humidity of each measurement point in real time, wherein all measurement points inside the cold chain logistics transport compartment are evenly distributed; A second acquisition module, which is used to obtain the operating frequency and refrigeration power of the refrigeration machine in the cold chain logistics transport compartment in real time, and the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time; a first calculation module, which is used to upload all data acquired in real time by the first acquisition module and the second acquisition module to a monitoring server, and the monitoring server respectively calculates the average value and variance of the temperature and humidity of all measurement points in real time, and calculates the first eigenvalue, the second eigenvalue, and the third eigenvalue in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment; A second calculation module, which is used to input all the data calculated in real time by the monitoring server in the first calculation module into the logistic regression model with completed parameter training to generate real-time abnormal state confidence; The determination module is used to determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal state confidence exceeds a predetermined threshold.

[0011] The third aspect disclosed in the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for real-time monitoring of cold chain logistics when executing the computer program.

[0012] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for real-time monitoring of cold chain logistics.

[0013] The fifth aspect disclosed in the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the steps of the above-mentioned method for real-time monitoring of cold chain logistics.

[0014] The beneficial effects of the present invention are: (1) Based on the various operating data of the cold chain logistics transport compartments, fault prediction and health management of the cold chain logistics transport process are carried out, solving the problem that the existing technology cannot monitor the real-time status of the refrigeration system of the cold chain logistics transport vehicle in multiple dimensions; (2) By performing specific nonlinear transformations on the operating data of each cold chain logistics transport compartment to generate multiple eigenvalues, and inputting them into the logistic regression model to generate abnormal state probability values as confidence levels, it is possible to make unified abnormal state judgments for different refrigeration states in different transportation scenarios, thus achieving flexible fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 The figure is an overall flow chart of a real-time monitoring method for cold chain logistics.

[0017] Figure 2 This is an overall structural diagram of a real-time monitoring system for cold chain logistics. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Example 1: like Figure 1 As shown, the embodiment of the present application provides a method for real-time monitoring of cold chain logistics, the method comprising the following steps: Step 1: Set temperature sensors and humidity sensors at all measuring points inside the cold chain logistics transport compartment to obtain the temperature and humidity of each measuring point in real time. Among them, all measuring points inside the cold chain logistics transport compartment are evenly distributed.

[0020] Specifically, temperature and humidity are the most important operating data. It is necessary to ensure that the temperature and humidity in the carriage are always kept within the range required by the goods. Temperature sensors and humidity sensors are set at multiple evenly distributed measuring points to obtain the temperature at different locations in the carriage. The temperature inside the cold chain logistics transport carriage should remain relatively uniform. Generally, the temperature difference at each measuring point is required to not exceed 2℃-3℃ to prevent local overheating or overcooling from causing damage to the goods.

[0021] Step 2: Obtain the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment in real time, and obtain the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time.

[0022] Specifically, the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment should meet the cooling needs in the compartment. Different cold chain goods have different temperature requirements, and the corresponding refrigeration machine operating frequency and cooling power are also different. The ventilation equipment in the cold chain logistics transport compartment should also operate normally to ensure air circulation in the compartment to ensure the uniformity of temperature and humidity.

[0023] Step 3: Upload all the data obtained in real time in steps 1 and 2 to the monitoring server. The monitoring server calculates the mean and variance of the temperature and humidity of all measurement points in real time, and calculates the first eigenvalue, the second eigenvalue, and the third eigenvalue in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment.

[0024] Step 3 specifically includes the following steps: Step 3.1: Upload all data obtained in steps 1 and 2 to the monitoring server in real time; Step 3.2: The monitoring server calculates the mean and variance of temperature and humidity in real time based on the temperature and humidity at all measurement points inside the cold chain logistics transport compartment. Step 3.3: According to the operating frequency of the refrigeration machine in the cold chain logistics transport compartment and cooling power , the first eigenvalue is calculated in real time using formula (1) and formula (2) respectively and the second eigenvalue : Formula (1) Formula (2) in, and They are the preset standard operating frequency and standard cooling power, and They are the allowable fluctuation ranges of standard operating frequency and standard cooling power respectively; Specifically, equations (1) and (2) are calculated by the operating frequency of the refrigeration machine in the cold chain logistics transport compartment. and cooling power Perform nonlinear transformation to project the operating data of the refrigerator during normal operation into an interval close to a constant value, namely the first eigenvalue and the second eigenvalue , and when the refrigerator is abnormal and the operating data deviates from the normal range, the first characteristic value and the second eigenvalue The value of the temperature sensor changes dramatically, which enables a more sensitive response to abnormal conditions. In addition, it can be flexibly adjusted according to the different refrigeration conditions in different transportation scenarios, and can make unified abnormal condition judgments for different refrigeration conditions in different transportation scenarios. Step 3.4: According to the ventilation volume of the cold chain logistics transport compartment ventilation equipment , use formula (3) to calculate the third eigenvalue in real time : Formula (3); Specifically, the ventilation volume of the cold chain logistics transport compartment ventilation equipment and the cooling power of the refrigerator There is a linear relationship, and the function It has a high gradient in the domain of (0,1), and the independent variable x Small changes in the dependent variable y The rapid change of ventilation equipment can be captured more sensitively through the form of formula (3). and the cooling power of the refrigerator The relative relationship and change state between them can respond to abnormal conditions more sensitively, and can flexibly adapt to different refrigeration powers in different transportation scenarios, and can adaptively judge abnormal conditions in any scenario.

[0025] Step 4: Input all the data calculated in real time by the monitoring server in step 3 into the logistic regression model with completed parameter training to generate real-time abnormal state confidence.

[0026] Step 4 specifically includes the following steps: Step 4.1: Collect the mean and variance of the temperature and humidity at all measurement points inside 1,000 historical cold chain logistics transport carriages, and calculate the first, second, and third eigenvalues corresponding to the 1,000 historical cold chain logistics transport carriages. Construct a sample dataset and label each sample in the sample dataset as abnormal using 1 or 0. Step 4.2: Establish a logistic regression model, initialize the parameters of the logistic regression model, perform binary classification training on the logistic regression model based on the sample data set, and iteratively train the parameters of the logistic regression model through maximum likelihood estimation. The output of the logistic regression model is the probability value of the abnormal state; Step 4.3: Input the mean and variance of the temperature and humidity of all measurement points calculated in real time in step 3, as well as the first eigenvalue, second eigenvalue, and third eigenvalue into the logistic regression monitoring model that has completed parameter training to generate a real-time abnormal state probability value as the real-time abnormal state confidence.

[0027] The specific method of initializing the parameters of the logistic regression model in step 4.2 is: randomly sample values from the standard normal distribution with a mean of 0 and a standard deviation of 0.01, and assign them to the parameters of the logistic regression model respectively, thus completing the initialization of the parameters of the logistic regression model.

[0028] Step 5: Determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal status confidence exceeds a predetermined threshold; Under normal circumstances, the real-time abnormal state probability value generated by the logistic regression monitoring model is transformed by the sigmoid activation function. When the real-time abnormal state confidence exceeds 0.5, it is determined that an abnormality has occurred inside the current cold chain logistics transport compartment.

[0029] In summary, the cold chain logistics real-time monitoring method provided by the embodiments of the present application has the following technical effects: (1) Based on the various operating data of the cold chain logistics transport compartments, fault prediction and health management of the cold chain logistics transport process are carried out, solving the problem that the existing technology cannot monitor the real-time status of the refrigeration system of the cold chain logistics transport vehicle in multiple dimensions; (2) By performing specific nonlinear transformations on the operating data of each cold chain logistics transport compartment to generate multiple eigenvalues, and inputting them into the logistic regression model to generate abnormal state probability values as confidence levels, it is possible to make unified abnormal state judgments for different refrigeration states in different transportation scenarios, thus achieving flexible fault prediction.

[0030] Example 2: Based on the same inventive concept as the cold chain logistics real-time monitoring method in Example 1, Figure 2As shown, the present application provides a cold chain logistics real-time monitoring system, the system comprising: A first acquisition module is configured to set temperature sensors and humidity sensors at all measurement points inside the cold chain logistics transport compartment to obtain the temperature and humidity of each measurement point in real time, wherein all measurement points inside the cold chain logistics transport compartment are evenly distributed; A second acquisition module, which is used to obtain the operating frequency and refrigeration power of the refrigeration machine in the cold chain logistics transport compartment in real time, and the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time; a first calculation module, which is used to upload all data acquired in real time by the first acquisition module and the second acquisition module to a monitoring server, and the monitoring server respectively calculates the average value and variance of the temperature and humidity of all measurement points in real time, and calculates the first eigenvalue, the second eigenvalue, and the third eigenvalue in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment; A second calculation module, which is used to input all the data calculated in real time by the monitoring server in the first calculation module into the logistic regression model with completed parameter training to generate real-time abnormal state confidence; The determination module is used to determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal state confidence exceeds a predetermined threshold.

[0031] Through the above detailed description of a method for real-time monitoring of cold chain logistics in this specification, those skilled in the art can clearly understand a real-time monitoring system for cold chain logistics in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For relevant matters, please refer to the method part.

[0032] Example 3: In the third embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method for real-time monitoring of cold chain logistics when executing the computer program.

[0033] Example 4: In the fourth embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for real-time monitoring of cold chain logistics are implemented.

[0034] Embodiment 5: In the fifth embodiment, a computer program product is provided, including a computer program or instructions, which implement the steps of the above-mentioned method for real-time monitoring of cold chain logistics when executed by a processor.

[0035] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0036] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for real-time monitoring of cold chain logistics, characterized in that: The method comprises the following steps: Step 1: Install temperature sensors and humidity sensors at all measurement points inside the cold chain logistics transport carriage to obtain the temperature and humidity of each measurement point in real time. All measurement points inside the cold chain logistics transport carriage are evenly distributed. Step 2: Obtain the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment in real time, and simultaneously obtain the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time; Step 3: Upload all the data acquired in real time in steps 1 and 2 to the monitoring server. The monitoring server calculates the mean and variance of the temperature and humidity at all measurement points in real time, and calculates the first, second, and third eigenvalues in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment; Step 4: Input all the data calculated in real time by the monitoring server in step 3 into the trained logistic regression model to generate real-time abnormal state confidence. Step 5: Determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal status confidence exceeds a predetermined threshold.

2. A method for real-time monitoring of cold chain logistics according to claim 1, characterized in that: The step 3 specifically includes the following steps: Step 3.1: Upload all data obtained in steps 1 and 2 to the monitoring server in real time; Step 3.2: The monitoring server calculates the mean and variance of temperature and humidity in real time based on the temperature and humidity at all measurement points inside the cold chain logistics transport compartment. Step 3.3: According to the operating frequency of the refrigeration machine in the cold chain logistics transport compartment and cooling power , the first eigenvalue is calculated in real time using formula (1) and formula (2) respectively and the second eigenvalue : Formula (1) Formula (2) in, and They are the preset standard operating frequency and standard cooling power, and They are the allowable fluctuation ranges of standard operating frequency and standard cooling power respectively; Step 3.4: According to the ventilation volume of the cold chain logistics transport compartment ventilation equipment , use formula (3) to calculate the third eigenvalue in real time : Formula (3).

3. A method for real-time monitoring of cold chain logistics according to claim 1, characterized in that: The step 4 specifically includes the following steps: Step 4.1: Collect the mean and variance of the temperature and humidity at all measurement points inside 1,000 historical cold chain logistics transport carriages, and calculate the first, second, and third eigenvalues corresponding to the 1,000 historical cold chain logistics transport carriages. Construct a sample dataset and label each sample in the sample dataset as abnormal using 1 or 0. Step 4.2: Establish a logistic regression model, initialize the parameters of the logistic regression model, perform binary classification training on the logistic regression model based on the sample data set, and iteratively train the parameters of the logistic regression model through maximum likelihood estimation. The output of the logistic regression model is the probability value of the abnormal state; Step 4.3: Input the mean and variance of the temperature and humidity of all measurement points calculated in real time in step 3, as well as the first eigenvalue, second eigenvalue, and third eigenvalue into the logistic regression monitoring model that has completed parameter training to generate a real-time abnormal state probability value as the real-time abnormal state confidence.

4. A method for real-time monitoring of cold chain logistics according to claim 3, characterized in that: Initialize the parameters of the logistic regression model as described in step 4.2 by randomly sampling values from a standard normal distribution with a mean of 0 and a standard deviation of 0.01, and assigning them to the parameters of the logistic regression model respectively.

5. A cold chain logistics real-time monitoring system, comprising: A first acquisition module is configured to set temperature sensors and humidity sensors at all measurement points inside the cold chain logistics transport compartment to obtain the temperature and humidity of each measurement point in real time, wherein all measurement points inside the cold chain logistics transport compartment are evenly distributed; A second acquisition module, which is used to obtain the operating frequency and refrigeration power of the refrigeration machine in the cold chain logistics transport compartment in real time, and the ventilation volume of the ventilation equipment in the cold chain logistics transport compartment in real time; a first calculation module, which is used to upload all data acquired in real time by the first acquisition module and the second acquisition module to a monitoring server, and the monitoring server respectively calculates the average value and variance of the temperature and humidity of all measurement points in real time, and calculates the first eigenvalue, the second eigenvalue, and the third eigenvalue in real time based on the operating frequency and cooling power of the refrigeration machine in the cold chain logistics transport compartment and the ventilation volume of the ventilation equipment; A second calculation module, which is used to input all the data calculated in real time by the monitoring server in the first calculation module into the logistic regression model with completed parameter training to generate real-time abnormal state confidence; The determination module is used to determine whether an abnormality occurs inside the current cold chain logistics transport compartment based on whether the real-time abnormal state confidence exceeds a predetermined threshold.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for real-time monitoring of cold chain logistics according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for real-time monitoring of cold chain logistics according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of a method for real-time monitoring of cold chain logistics according to any one of claims 1 to 4 are implemented.

Images