Cold-chain logistics information management method and management system

Abstract

The invention provides a cold-chain logistics information management method and management system, and relates to the technical field of equipment information management. According to the invention, by integrating the collection and analysis of historical fault data, the construction of an equipment safety pre-estimation model, the identification of fault relevance, the implementation of safety scores and the establishment of a real-time alarm mechanism, the fault early warning capability of the cold chain equipment is remarkably improved, and the identification precision of fault relevance between the equipment is enhanced; the method optimizes the assessment and alarm response process of the equipment safety state, thereby greatly improving the management efficiency and response speed of cold-chain logistics, reducing the operation cost and risk, and promoting the sustainable development of the cold-chain logistics industry and the safety guarantee of the goods quality.

Description

Technical Field

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

[0002] Cold chain logistics, as an important part of the modern supply chain and logistics system, focuses on the entire process of perishable food from the place of production to the hands of consumers, ensuring that each link is carried out in a low temperature environment required by the product to ensure food quality and safety, reduce losses and prevent pollution. The operation modes of cold chain logistics mainly include warehousing cold chain logistics mode, transportation cold chain logistics mode and comprehensive cold chain logistics mode.

[0003] In the warehousing-type cold chain logistics model, cold chain logistics equipment such as refrigerated trucks and cold storages are prone to failures during operation, and traditional fault warning methods often rely on manual inspections and empirical judgments, which have large lags and uncertainties. This deficiency makes it difficult to detect and handle equipment failures in a timely manner, which in turn affects the continuity and stability of cold chain logistics; there are often complex correlations between cold chain logistics equipment, and the failure of one device may affect the normal operation of other equipment. However, traditional management methods often ignore this correlation, resulting in the inability to quickly locate the root cause of the problem when equipment failure occurs; due to information asymmetry, data silos, and insufficient equipment fault warning and correlation identification capabilities, the management efficiency of cold chain logistics is generally low, which not only increases management costs, but also reduces the flexibility and response speed of overall operations.

[0004] Therefore, it is necessary to provide a cold chain logistics information management method and management system to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a cold chain logistics information management method and management system for solving the problems that it is difficult to provide early warning for potential failures, failures in various equipment in the cold chain line may trigger a chain reaction, resulting in a lack of global vision when handling failures and high operating costs.

[0006] The present invention provides a cold chain logistics information management method and management system, the management method comprising the following steps:

[0007] S100, collecting historical fault data of each cold chain equipment on the same cold chain line, including but not limited to the fault type, occurrence time, and parameters before and after the equipment failure;

[0008] S200, based on the collected historical failure data, using time series analysis method, identify the change trend of parameters of each cold chain equipment before and after the failure and build an equipment safety prediction model based on this;

[0009] S300, establishing an equipment failure mode library based on the collected historical failure data, and identifying the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library;

[0010] S400, based on the fault correlation between the cold chain equipment on the same cold chain line, build an equipment correlation prediction model;

[0011] S500, collecting parameter information of each cold chain device in the same cold chain line in real time, and judging whether each cold chain device exceeds a preset safety alarm threshold according to the collected parameter information through the equipment safety estimation model;

[0012] S600: In response to the judgment result of the cold chain device exceeding the preset safety alarm threshold, the safety score of other cold chain devices associated with the cold chain device on the same cold chain line is performed through the device association estimation model;

[0013] S700. Based on the obtained safety score, control each cold chain device in turn to issue an alarm mark of a corresponding level.

[0014] Preferably, the step S01 specifically includes the following steps:

[0015] S101. Extract historical failure data of cold chain equipment from a data storage source using a data acquisition tool, including but not limited to failure type, occurrence time, and parameters before and after the equipment failure;

[0016] S102, sorting the collected historical fault data, specifically including removing duplicate or invalid information, and storing it in a database in a unified format.

[0017] Preferably, the step S200 specifically includes the following steps:

[0018] S201, preprocessing the collected historical fault data to obtain preprocessed data, wherein the preprocessing specifically includes data cleaning, data conversion and data normalization;

[0019] S202, using a trend fitting method in a time series analysis method to analyze the parameter change trend of each cold chain equipment before and after the failure occurs, and obtaining an analysis result;

[0020] S203. Based on the analysis results, a mapping relationship is established between the parameter change trend of the cold chain equipment and the corresponding fault type to form a training set;

[0021] S204. The selected neural network model is used as the model architecture, and the neural network model is trained through the training set to obtain a device safety prediction model.

[0022] Preferably, the step S300 specifically includes:

[0023] S301, extracting all relevant fault information from historical fault data, wherein there are n different fault events i, and each fault event i is represented by a vector xi;

[0024] S302, different fault modes are identified by using a k-means clustering algorithm, specifically, k is selected as the number of clusters. The goal of k-means is to minimize the sum of the squares of the distances from all points to the centroids of the clusters to which they belong, expressed as:

[0025]

[0026] In the formula, C i is the set of all data points in the ith cluster, μ i is the centroid of the ith cluster, i.e., the average vector, x j It belongs to C i A data point of

[0027] S303, after different fault modes are identified by the k-means clustering algorithm, a fault mode library is constructed, specifically: each fault mode M i With a center of mass μ i To indicate, all fault events belonging to this mode are recorded at the same time;

[0028] S304. Identify the fault correlation between cold chain equipment by comparing the commonalities and differences between different fault modes, specifically:

[0029] For cold chain equipment A, failure mode M occurs i After that, the cold chain equipment B has a failure mode M j The probability P(M j ∣M i ), calculated by the conditional probability formula:

[0030]

[0031] In the formula, P(M i ,M j ) is the cold chain equipment A occurs M i At the same time as the failure, cold chain equipment B has M j The probability of failure, P(M i ) is the cold chain equipment A occurs M i Probability of failure.

[0032] Preferably, the step S400 specifically includes:

[0033] S401. There are n cold chain devices in the same cold chain line. Each cold chain device has k different failure modes. Define the device association matrix A to represent the association between cold chain devices. Aij Indicates the intensity of the impact on the equipment when a cold chain equipment fails;

[0034] S402: Based on the conditional probability formula in step S304, the association strength of the cold chain equipment is quantified, and the association strength A of the cold chain equipment i to the cold chain equipment j is specifically defined. ij , whose expression is:

[0035] Ai j =P(M j ∣M i )-P(M j )

[0036] In the formula, P(M j ) is the marginal probability of any failure mode occurring in cold chain equipment j;

[0037] S403, based on the association strength A ij , build a device association estimation model:

[0038] Assume that the cold chain equipment i has a failure mode M i , then the cold chain equipment j has a failure mode M j The probability P′(M j ∣M i ) is:

[0039] P′(M j ∣M i )=P(M j )+A ij

[0040] In the formula, P(M j ) is the failure mode M of cold chain equipment j j The baseline probability of A ij is the association strength of cold chain equipment i to cold chain equipment j;

[0041] In addition, considering the impact of the severity of cold chain equipment failure on the association strength, a weight factor w is introduced i To reflect the severity of the equipment i failure, the equipment association prediction model is determined as:

[0042] P′(M j ∣M i )=P(M j )+A ij ·w i .

[0043] Preferably, the step S500 specifically includes the following steps:

[0044] 501. Use sensor tools to collect operating parameter information of each cold chain device on the same cold chain line in real time, and clean and convert it to obtain a collated data set;

[0045] 502. Input the sorted data set into the equipment safety estimation model to determine whether each cold chain equipment exceeds a preset safety alarm threshold and obtain a judgment result.

[0046] Preferably, the step S600 specifically includes the following steps:

[0047] 601. Based on the judgment result, when a cold chain device exceeding a preset safety alarm threshold is identified, the device association estimation model is triggered;

[0048] 602. The equipment association estimation model responds, performs safety scoring on other cold chain equipment associated with the cold chain equipment on the same cold chain line, and obtains scoring results of other cold chain equipment.

[0049] Preferably, the step S700 specifically includes the following steps:

[0050] 701. Compare the scoring results of other cold chain equipment according to the preset score threshold and classify them into low, medium and high grades;

[0051] 702. According to the grade classification of the scoring results, instructions are sent to other cold chain equipment through the control system to control them to issue alarm signs of corresponding levels, where the alarm signs of corresponding levels specifically include flashing green alarm lights, flashing yellow alarm lights, and flashing red alarm lights with a buzzer.

[0052] A cold chain logistics information management system, the management system comprising:

[0053] The data collection module is used to collect the historical fault data of each cold chain equipment on the same cold chain line, including but not limited to the fault type, occurrence time, and parameters before and after the equipment failure;

[0054] The first model building module is used to identify the change trend of the parameters of each cold chain equipment before and after the failure based on the collected historical failure data and to build an equipment safety prediction model based on this using a time series analysis method;

[0055] The analysis module is used to establish an equipment failure mode library based on the collected historical failure data, and to identify the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library;

[0056] The second model building module is used to build an equipment correlation prediction model based on the fault correlation between the cold chain equipment on the same cold chain line;

[0057] The collection and judgment module is used to collect the parameter information of each cold chain equipment on the same cold chain line in real time, and judge whether each cold chain equipment exceeds the preset safety alarm threshold according to the collected parameter information through the equipment safety estimation model;

[0058] The scoring module is used to respond to the judgment result of the cold chain equipment that exceeds the preset safety alarm threshold, and to perform safety scoring on other cold chain equipment associated with the cold chain equipment on the same cold chain line through the equipment association estimation model;

[0059] The warning module is used to control each cold chain device to issue an alarm mark of the corresponding level according to the safety score obtained.

[0060] Compared with the related art, the cold chain logistics information management method and management system provided by the present invention have the following beneficial effects:

[0061] The present invention significantly improves the fault warning capability of cold chain equipment by integrating the collection and analysis of historical fault data, the construction of equipment safety prediction model, the identification of fault correlation, the implementation of safety scoring and the establishment of real-time alarm mechanism, enhances the identification accuracy of fault correlation between equipment, optimizes the assessment of equipment safety status and alarm response process, thereby greatly improving the management efficiency and response speed of cold chain logistics, reducing operating costs and risks, and promoting the sustainable development of the cold chain logistics industry and the safety assurance of cargo quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of a cold chain logistics information management method provided by the present invention;

[0063] Figure 2 A system block diagram of a cold chain logistics information management system provided by the present invention. DETAILED DESCRIPTION

[0064] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0065] Embodiment 1

[0066] like Figure 1 As shown, a cold chain logistics information management method includes the following steps:

[0067] S100. Collect historical failure data of each cold chain device on the same cold chain line, including but not limited to failure type, occurrence time, and parameters before and after the equipment failure.

[0068] Specifically, determine the scope of historical fault data to be collected, that is, the historical fault data of all cold chain equipment on the same cold chain line, and then collect historical fault data for a period of time, specifically half a month, from the data storage source of the sensor network, including but not limited to mechanical failures, electrical failures, software errors and other fault types, the specific time of the failure, and the operating parameters of the equipment before and after the failure, including but not limited to temperature, pressure, current, speed, etc., and organize and store them in the database for subsequent analysis. By analyzing the historical failure data, we can understand the performance of cold chain equipment under different operating conditions and identify the patterns of failure occurrence.

[0069] S200. Based on the collected historical failure data, a time series analysis method is used to identify the change trend of the parameters of each cold chain equipment before and after the failure and to build an equipment safety prediction model based on this.

[0070] Specifically, the collected historical failure data are preprocessed, and the trend fitting method in the time series analysis method is used to identify the changing trends of the parameters of each cold chain equipment before and after the failure. The selected neural network model is used as the model architecture to train and construct the equipment safety prediction model.

[0071] S300: Establish an equipment failure mode library based on the collected historical failure data, and identify the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library.

[0072] Specifically, the collected historical fault data is organized into a fault mode library. Each fault mode contains information such as fault type, fault description, occurrence conditions, and impact range. By comparing and analyzing the commonalities and differences of different fault modes, the fault correlations between the equipment on the same cold chain line are identified. Identifying the fault correlations between equipment helps to more comprehensively understand the overall health status of the cold chain line, thereby taking more effective prevention and response measures.

[0073] For example, on a cold chain line, it was found that when a delivery pump failed, insufficient supply often caused subsequent filling machines to also malfunction, thus identifying the fault correlation between the two devices.

[0074] S400: Based on the fault correlation between the cold chain equipment on the same cold chain line, an equipment correlation prediction model is constructed.

[0075] Specifically, based on the fault correlation between the cold chain equipment on the same cold chain line, the intensity of the impact on the equipment when a cold chain equipment failure occurs is defined, the correlation strength of the cold chain equipment is quantified, and an equipment correlation estimation model is constructed.

[0076] S500, collect parameter information of each cold chain device on the same cold chain line during operation in real time, and determine whether each cold chain device exceeds a preset safety alarm threshold based on the collected parameter information through an equipment safety estimation model.

[0077] Specifically, the operating parameters of each cold chain equipment are collected in real time through the equipment monitoring system, and these parameters are input into the equipment safety prediction model. The equipment safety prediction model determines the safety status of the equipment based on the input parameter information and whether it exceeds the preset safety alarm threshold. If it exceeds the preset safety alarm threshold, the cold chain equipment operates normally. In this embodiment, the preset safety alarm threshold is the safety threshold of each parameter set based on expert advice.

[0078] S600: In response to the judgment result of the cold chain device exceeding the preset safety alarm threshold, the safety score of other cold chain devices associated with the cold chain device on the same cold chain line is performed through the device association estimation model.

[0079] Specifically, when a cold chain device is judged to exceed the safety alarm threshold, the system triggers feedback information. The feedback information allows the device-associated prediction model to receive a response, and then a safety score is given to other devices associated with the same cold chain line of the device, which helps to determine which equipment requires urgent attention or maintenance to avoid more serious consequences.

[0080] S700. Based on the obtained safety score, control each cold chain device in turn to issue an alarm mark of a corresponding level.

[0081] Specifically, the obtained safety scores are divided into low, medium and high levels. According to the low, medium and high levels, each cold chain device is controlled to issue an alarm mark of the corresponding level in sequence, wherein the alarm marks of the corresponding level specifically include a flashing green alarm light, a flashing yellow alarm light and a flashing red alarm light with a buzzer.

[0082] In the specific implementation process, step S01 specifically includes the following steps:

[0083] S101. Use a data acquisition tool to extract historical failure data of cold chain equipment from a data storage source, including but not limited to failure type, occurrence time, and parameters before and after the equipment failure.

[0084] S102, sorting the collected historical fault data, specifically including removing duplicate or invalid information, and storing it in a database in a unified format.

[0085] In the specific implementation process, step S200 specifically includes the following steps:

[0086] S201 . Preprocess the collected historical fault data to obtain preprocessed data, wherein the preprocessing specifically includes data cleaning, data conversion, and data normalization.

[0087] S202. Use the trend fitting method in the time series analysis method to analyze the parameter change trend of each cold chain equipment before and after the failure occurs to obtain the analysis result.

[0088] Specifically, the collected historical fault data, in this embodiment, is the equipment parameter data before and after the fault occurs, and the trend fitting is performed on the parameters of each cold chain equipment. Specifically, time is used as the independent variable and the equipment parameter is used as the dependent variable, and the trend fitting model is substituted. The model parameters are solved by mathematical methods to obtain the trend curve of the parameter changes over time, and on the basis of the trend curve, the key change points in the parameter change trend are further identified to obtain the analysis results.

[0089] S203. Based on the analysis results, a mapping relationship is established between the parameter change trend of the cold chain equipment and the corresponding fault type to form a training set.

[0090] S204. The selected neural network model is used as the model architecture, and the neural network model is trained through the training set to obtain a device safety prediction model.

[0091] In the specific implementation process, step S300 specifically includes:

[0092] S301. Extract all relevant fault information from historical fault data, wherein there are n different fault events i, and each fault event i is represented by a vector xi.

[0093] S302, different fault modes are identified by using a k-means clustering algorithm, specifically, k is selected as the number of clusters. The goal of k-means is to minimize the sum of the squares of the distances from all points to the centroids of the clusters to which they belong, expressed as:

[0094]

[0095] In the formula, C i is the set of all data points in the ith cluster, μ i is the centroid of the ith cluster, i.e., the average vector, x j It belongs to C i A data point of .

[0096] S303, after different fault modes are identified by the k-means clustering algorithm, a fault mode library is constructed, specifically: each fault mode M i With a center of mass μ i To indicate, all fault events belonging to this mode are recorded at the same time.

[0097] S304. Identify the fault correlation between cold chain equipment by comparing the commonalities and differences between different fault modes, specifically:

[0098] For cold chain equipment A, failure mode M occurs i After that, the cold chain equipment B has a failure mode M j The probability P(M j ∣M i ), calculated by the conditional probability formula:

[0099]

[0100] In the formula, P(M i ,M j ) is the cold chain equipment A occurs M i At the same time as the failure, cold chain equipment B has M j The probability of failure, P(M i ) is the cold chain equipment A occurs M i Probability of failure.

[0101] In the specific implementation process, step S400 specifically includes:

[0102] S401. There are n cold chain devices in the same cold chain line. Each cold chain device has k different failure modes. Define the device association matrix A to represent the association between cold chain devices. A ij Indicates the intensity of the impact on the cold chain equipment when a failure occurs.

[0103] S402: Based on the conditional probability formula in step S304, the association strength of the cold chain equipment is quantified, and the association strength A of the cold chain equipment i to the cold chain equipment j is specifically defined. ij , whose expression is:

[0104] Ai j =P(M j ∣M i )-P(M j )

[0105] In the formula, P(M j ) is the marginal probability of any failure mode occurring in cold chain equipment j.

[0106] S403, based on the association strength A ij , build a device association estimation model:

[0107] Assume that the cold chain equipment i has a failure mode M i , then the cold chain equipment j has a failure mode M j The probability P′(M j ∣M i ) is:

[0108] P′(M j ∣M i )=P(M j )+A ij

[0109] In the formula, P(M j ) is the failure mode M of cold chain equipment j j The baseline probability of A ij is the association strength of cold chain equipment i to cold chain equipment j;

[0110] In addition, considering the impact of the severity of cold chain equipment failure on the association strength, a weight factor w is introduced i To reflect the severity of the equipment i failure, the equipment association prediction model is determined as:

[0111] P′(M j ∣M i )=P(M j )+A ij ·w i .

[0112] In the specific implementation process, step S500 specifically includes the following steps:

[0113] 501. The operating parameter information of each cold chain equipment on the same cold chain line is collected in real time through sensor tools, and then cleaned and converted to obtain a collated data set.

[0114] 502. Input the sorted data set into the equipment safety estimation model to determine whether each cold chain equipment exceeds a preset safety alarm threshold and obtain a judgment result.

[0115] In the specific implementation process, step S600 specifically includes the following steps:

[0116] 601. Based on the judgment result, when a cold chain device exceeding a preset safety alarm threshold is identified, the device association prediction model is triggered.

[0117] 602. The equipment association estimation model responds, performs safety scoring on other cold chain equipment associated with the cold chain equipment on the same cold chain line, and obtains scoring results of other cold chain equipment.

[0118] In the specific implementation process, step S700 specifically includes the following steps:

[0119] 701. Compare the scoring results of other cold chain equipment according to the preset score threshold and classify them into levels, wherein the levels are specifically divided into low level, medium level and high level.

[0120] 702. According to the grade classification of the scoring results, instructions are sent to other cold chain equipment through the control system to control them to issue alarm signs of corresponding levels, where the alarm signs of corresponding levels specifically include flashing green alarm lights, flashing yellow alarm lights, and flashing red alarm lights with a buzzer.

[0121] Embodiment 2

[0122] like Figure 2 As shown, a cold chain logistics information management system applied to a cold chain logistics information management method includes:

[0123] The data collection module is used to collect the historical fault data of each cold chain equipment on the same cold chain line, including but not limited to the fault type, occurrence time, and parameters before and after the equipment failure.

[0124] Specifically, the data collection module is used to determine the scope of historical fault data to be collected, that is, the historical fault data of all cold chain equipment on the same cold chain line, and then collect historical fault data for a period of time, specifically half a month, from the data storage source of the sensor network, including: mechanical failure, electrical failure, software error and other fault types, the specific time of the failure, and the operating parameters of the equipment before and after the failure, specifically temperature, pressure, current, speed, etc., and organize and store them in the database for subsequent analysis. By analyzing the historical failure data, we can understand the performance of cold chain equipment under different operating conditions and identify the patterns of failure occurrence.

[0125] The first model building module is used to identify the changing trends of the parameters of each cold chain equipment before and after the failure based on the collected historical failure data and to build an equipment safety prediction model based on this using a time series analysis method.

[0126] Specifically, the first model building module is used to preprocess the collected historical fault data, and use the trend fitting method in the time series analysis method to identify the changing trends of the parameters of each cold chain equipment before and after the failure, and use the selected neural network model as the model architecture to train and build the equipment safety prediction model.

[0127] The analysis module is used to establish an equipment failure mode library based on the collected historical failure data, and to identify the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library.

[0128] Specifically, the analysis module is used to organize the collected historical fault data into a fault mode library. Each fault mode contains information such as fault type, fault description, occurrence conditions, and impact range. By comparing and analyzing the commonalities and differences of different fault modes, the fault correlation between the devices on the same cold chain line can be identified. Identifying the fault correlation between devices helps to more fully understand the overall health of the cold chain line, so as to take more effective prevention and response measures.

[0129] The second model building module is used to build an equipment correlation prediction model based on the fault correlation between the cold chain equipment on the same cold chain line.

[0130] Specifically, the second model building module is used to define the intensity of the impact on the equipment when a cold chain equipment fails based on the fault correlation between the cold chain equipment on the same cold chain line, quantify the correlation strength of the cold chain equipment, and build an equipment correlation estimation model.

[0131] The collection and judgment module is used to collect the parameter information of each cold chain equipment on the same cold chain line in real time during operation, and judge whether each cold chain equipment exceeds the preset safety alarm threshold based on the collected parameter information through the equipment safety estimation model.

[0132] Specifically, the collection and judgment module is used to collect the operating parameters of each cold chain equipment in real time through the equipment monitoring system, and input these parameters into the equipment safety estimation model. The equipment safety estimation model determines the safety status of the equipment based on the input parameter information and whether it exceeds the preset safety alarm threshold. If it exceeds the preset safety alarm threshold, the cold chain equipment operates normally. In this embodiment, the preset safety alarm threshold is the safety threshold of each parameter set based on expert advice.

[0133] The scoring module is used to respond to the judgment results of cold chain equipment that exceeds the preset safety alarm threshold, and to perform safety scores on other cold chain equipment associated with the cold chain equipment on the same cold chain line through the equipment association prediction model.

[0134] Specifically, the scoring module is used to trigger feedback information when a certain cold chain equipment is judged to have exceeded the safety alarm threshold, and the equipment association prediction model receives a response through the feedback information, and then the safety score of other equipment associated with the same cold chain line of the equipment is calculated. This helps to determine which equipment needs urgent attention or maintenance to avoid more serious consequences.

[0135] The warning module is used to control each cold chain device to issue an alarm mark of the corresponding level according to the safety score obtained.

[0136] Specifically, the obtained safety scores are divided into low, medium and high levels. According to the low, medium and high levels, each cold chain device is controlled to issue an alarm mark of the corresponding level in sequence, wherein the alarm marks of the corresponding level specifically include a flashing green alarm light, a flashing yellow alarm light and a flashing red alarm light with a buzzer.

[0137] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0139] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A cold chain logistics information management method, characterized in that: The management method comprises the following steps: S100, collecting historical fault data of each cold chain equipment on the same cold chain line, including but not limited to the fault type, occurrence time, and parameters before and after the equipment failure; S200, based on the collected historical failure data, using time series analysis method, identify the change trend of parameters of each cold chain equipment before and after the failure and build an equipment safety prediction model based on this; S300, establishing an equipment failure mode library based on the collected historical failure data, and identifying the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library; S400, based on the fault correlation between the cold chain equipment on the same cold chain line, build an equipment correlation prediction model; S500, collecting parameter information of each cold chain device in the same cold chain line in real time, and judging whether each cold chain device exceeds a preset safety alarm threshold according to the collected parameter information through the equipment safety estimation model; S600: In response to the judgment result of the cold chain device exceeding the preset safety alarm threshold, the safety score of other cold chain devices associated with the cold chain device on the same cold chain line is performed through the device association estimation model; S700. Based on the obtained safety score, control each cold chain device in turn to issue an alarm mark of a corresponding level.

2. A cold chain logistics information management method according to claim 1, characterized in that: The step S01 specifically includes the following steps: S101. Extract historical failure data of cold chain equipment from a data storage source using a data acquisition tool, including but not limited to failure type, occurrence time, and parameters before and after the equipment failure; S102, sorting the collected historical fault data, specifically including removing duplicate or invalid information, and storing it in a database in a unified format.

3. A cold chain logistics information management method according to claim 1, characterized in that: The step S200 specifically includes the following steps: S201, preprocessing the collected historical fault data to obtain preprocessed data, wherein the preprocessing specifically includes data cleaning, data conversion and data normalization; S202, using a trend fitting method in a time series analysis method to analyze the parameter change trend of each cold chain equipment before and after the failure occurs, and obtaining an analysis result; S203. Based on the analysis results, a mapping relationship is established between the parameter change trend of the cold chain equipment and the corresponding fault type to form a training set; S204. The selected neural network model is used as the model architecture, and the neural network model is trained through the training set to obtain a device safety prediction model.

4. A cold chain logistics information management method according to claim 1, characterized in that: The step S300 specifically includes: S301, extract all relevant fault information from historical fault data, where there are n different fault events i, and each fault event i is represented by a vector x i express; S302, different fault modes are identified by using a k-means clustering algorithm, specifically, k is selected as the number of clusters. The goal of k-means is to minimize the sum of the squares of the distances from all points to the centroids of the clusters to which they belong, expressed as: In the formula, C i is the set of all data points in the ith cluster, μ i is the centroid of the ith cluster, i.e., the average vector, x j It belongs to C i A data point of . S303, after different fault modes are identified by the k-means clustering algorithm, a fault mode library is constructed, specifically: each fault mode M i With a center of mass μ i To indicate, all fault events belonging to this mode are recorded at the same time; S304. Identify the fault correlation between the cold chain equipment by comparing the commonalities and differences between different fault modes, specifically: For cold chain equipment A, failure mode M occurs i After that, the cold chain equipment B has a failure mode M j The probability P(M j ∣M i ), calculated by the conditional probability formula: In the formula, P(M i ,M j ) is the cold chain equipment A occurs M i At the same time as the failure, cold chain equipment B has M j The probability of failure, P(M i ) is the cold chain equipment A occurs M i Probability of failure.

5. A cold chain logistics information management method according to claim 4, characterized in that: The step S400 specifically includes: S401. There are n cold chain devices in the same cold chain line. Each cold chain device has k different failure modes. Define the device association matrix A to represent the association between cold chain devices. A ij Indicates the intensity of the impact on the equipment when a cold chain equipment fails; S402: Based on the conditional probability formula in step S304, the association strength of the cold chain equipment is quantified, and the association strength A of the cold chain equipment i to the cold chain equipment j is specifically defined. ij , whose expression is: you j =P(M j ∣M i )-P.M j ) In the formula, P(M j ) is the marginal probability of any failure mode occurring in cold chain equipment j; S403, based on the association strength A ij , build a device association estimation model: Assume that the cold chain equipment i has a failure mode M i , then the cold chain equipment j has a failure mode M j The probability P′(M j ∣M i ) is: P′(M j ∣M i )=P(M j )+A ij In the formula, P(M j ) is the failure mode M of cold chain equipment j j The baseline probability of A ij is the association strength of cold chain equipment i to cold chain equipment j; In addition, considering the impact of the severity of cold chain equipment failure on the association strength, a weight factor w is introduced i To reflect the severity of the equipment i failure, the equipment association prediction model is determined as: P′(M j ∣M i )=P(M j )+A ij ·w i 。 6. A cold chain logistics information management method according to claim 1, characterized in that: The step S500 specifically includes the following steps:

501. Use sensor tools to collect operating parameter information of each cold chain device on the same cold chain line in real time, and clean and convert it to obtain a collated data set; 502. Input the sorted data set into the equipment safety estimation model to determine whether each cold chain equipment exceeds a preset safety alarm threshold and obtain a judgment result.

7. A cold chain logistics information management method according to claim 1, characterized in that: The step S600 specifically includes the following steps:

601. Based on the judgment result, when a cold chain device exceeding a preset safety alarm threshold is identified, the device association estimation model is triggered; 602. The equipment association estimation model responds, performs safety scoring on other cold chain equipment associated with the cold chain equipment on the same cold chain line, and obtains scoring results of other cold chain equipment.

8. A cold chain logistics information management method according to claim 7, characterized in that: The step S700 specifically includes the following steps:

701. Compare the scoring results of other cold chain equipment according to the preset score threshold and classify them into low, medium and high grades; 702. According to the grade classification of the scoring results, instructions are sent to other cold chain equipment through the control system to control them to issue alarm signs of corresponding levels, where the alarm signs of corresponding levels specifically include flashing green alarm lights, flashing yellow alarm lights, and flashing red alarm lights with a buzzer.

9. A cold chain logistics information management system, applied to a cold chain logistics information management method according to any one of claims 1 to 8, characterized in that: The management system comprises: The data collection module is used to collect the historical fault data of each cold chain equipment on the same cold chain line, including but not limited to the fault type, occurrence time, and parameters before and after the equipment failure; The first model building module is used to identify the change trend of the parameters of each cold chain equipment before and after the failure based on the collected historical failure data and to build an equipment safety prediction model based on this using a time series analysis method; The analysis module is used to establish an equipment failure mode library based on the collected historical failure data, and to identify the failure correlation between the cold chain equipment on the same cold chain line by analyzing the commonalities and differences of different failure modes in the failure mode library; The second model building module is used to build an equipment correlation prediction model based on the fault correlation between the cold chain equipment on the same cold chain line; The collection and judgment module is used to collect the parameter information of each cold chain equipment on the same cold chain line in real time, and judge whether each cold chain equipment exceeds the preset safety alarm threshold according to the collected parameter information through the equipment safety estimation model; The scoring module is used to respond to the judgment result of the cold chain equipment that exceeds the preset safety alarm threshold, and to perform safety scoring on other cold chain equipment associated with the cold chain equipment on the same cold chain line through the equipment association estimation model; The warning module is used to control each cold chain device to issue an alarm mark of the corresponding level according to the safety score obtained.

Images