CN116701983A - Cold-chain logistics real-time monitoring data processing method and system - Google Patents
Cold-chain logistics real-time monitoring data processing method and system Download PDFInfo
- Publication number
- CN116701983A CN116701983A CN202310966456.2A CN202310966456A CN116701983A CN 116701983 A CN116701983 A CN 116701983A CN 202310966456 A CN202310966456 A CN 202310966456A CN 116701983 A CN116701983 A CN 116701983A
- Authority
- CN
- China
- Prior art keywords
- temperature
- internal temperature
- external
- real
- internal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000003672 processing method Methods 0.000 title claims description 3
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 59
- 230000008859 change Effects 0.000 claims description 54
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 abstract description 12
- 238000003064 k means clustering Methods 0.000 description 5
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000017525 heat dissipation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for processing real-time monitoring data of a cold chain logistics. The method comprises the steps of obtaining the internal temperature and the external temperature of a transport vehicle of a cold chain logistics; screening out the adjacent external temperature corresponding to the internal temperature according to the variation fluctuation degree of the internal temperature and the historical external temperature; determining the degree of external environmental influence according to the difference between the internal temperature and the corresponding adjacent external temperature; according to the difference of the real-time external environment influence degree and the influence degree standard, the loss function in the clustering algorithm is adjusted to obtain a target loss function, the internal temperature of the transport vehicle of the cold chain logistics is clustered by using the clustering algorithm to obtain the category of the real-time internal temperature of the transport vehicle of the cold chain logistics, and the transport vehicle of the cold chain logistics is monitored based on the category. The method improves the accuracy of judging the temperature abnormality in the transportation carriage of the cold-chain logistics.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for processing real-time monitoring data of a cold chain logistics.
Background
With the perfection and development of global supply chain systems, the cold chain logistics market demand is increasing. Various parameters such as temperature, humidity, air pressure and the like need to be detected and monitored in the cold chain logistics transportation process so as to ensure the safety and quality of goods. Monitoring of temperature is critical in cold chain transportation because temperature can affect humidity and air pressure within the transport vehicle, typically by sensing temperature parameters during cold chain transportation.
At present, the data in the transport vehicle is monitored through a temperature sensor, and the temperature abnormality of the transport vehicle is judged when the temperature exceeding the range of the preset temperature interval occurs through setting the temperature interval. However, the fixed temperature interval is set, and the anti-noise capability corresponding to the fixed temperature interval is poor, because the influence of different external environments on the temperature when the transport vehicle is at different positions at different times is not considered, and the judgment accuracy of the abnormal temperature in the transport vehicle compartment of the cold chain logistics is lower.
Disclosure of Invention
In order to solve the technical problem of low accuracy in judging temperature abnormality in a transportation carriage of a cold-chain logistics, the invention aims to provide a method and a system for processing real-time monitoring data of the cold-chain logistics, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for processing real-time monitoring data of a cold chain stream, including the steps of:
acquiring the internal temperature and the external temperature of a transport vehicle of the cold chain logistics;
screening adjacent external temperatures corresponding to the internal temperature from the historical external temperatures according to the variation fluctuation degree of the internal temperature and the historical external temperature;
determining the degree of external environmental influence according to the difference between the internal temperature and the corresponding adjacent external temperature;
according to the real-time external environment influence degree and the difference of the influence degree standard, the loss function in the clustering algorithm is adjusted to obtain a target loss function; based on the target loss function, clustering the internal temperature of the transport vehicle of the cold chain logistics by using a clustering algorithm to obtain the category of the real-time internal temperature of the transport vehicle of the cold chain logistics, and monitoring the transport vehicle of the cold chain logistics based on the category.
Preferably, the step of screening the adjacent external temperature corresponding to the internal temperature from the historical external temperature according to the variation fluctuation degree of the internal temperature and the historical external temperature includes:
constructing an internal temperature sequence section corresponding to the real-time internal temperature by the real-time internal temperature and the preset first number of internal temperatures; constructing an external temperature sequence segment corresponding to each historical external temperature according to each historical external temperature and the corresponding preset first number of historical external temperatures;
determining the fluctuation similarity of the internal temperature curve section and the external temperature curve section according to the slope difference corresponding to the data at the same position on the internal temperature sequence section and the external temperature sequence section;
and taking the historical external temperature corresponding to the maximum value of the fluctuation similarity of the internal temperature sequence section and all the corresponding external temperature sequence sections as the real-time adjacent external temperature of the internal temperature.
Preferably, the determining the fluctuation similarity of the internal temperature sequence segment and the external temperature sequence segment according to the slope difference corresponding to the data at the same position on the internal temperature sequence segment and the external temperature sequence segment comprises:
calculating the square of the difference value of slope change values corresponding to any two temperature data with the same positions on the internal temperature sequence section and the external temperature sequence section as a first square; and carrying out negative correlation normalization processing on the average value of all the first squares corresponding to the internal temperature sequence section and the external temperature sequence section to obtain the fluctuation similarity of the internal temperature sequence section and the external temperature sequence section.
Preferably, the method for obtaining the slope change value of the internal temperature comprises the following steps:
selecting any internal temperature as a target temperature, and fitting an internal temperature sequence segment corresponding to the target temperature to obtain an internal temperature curve segment; calculating the difference between the slope of the target temperature and the slope of the internal temperature at the next moment corresponding to the target temperature; the slope of the target temperature is the slope of a data point corresponding to the target temperature on the internal temperature curve segment, the horizontal axis of the internal temperature curve segment is time, and the vertical axis is internal temperature.
Preferably, the determining the external environment influence degree according to the difference between the internal temperature and the corresponding adjacent external temperature includes:
calculating the difference between the internal temperature and the corresponding adjacent external temperature to be used as the difference between the internal temperature and the external temperature; and taking the normalized value of the product of the internal and external temperature difference and the adjacent external temperature as the external environment influence degree.
Preferably, the method for obtaining the influence degree reference comprises the following steps:
taking the average value of the historic internal temperature and the corresponding external environment influence degree close to the external temperature as an influence degree standard.
Preferably, the adjusting the loss function in the clustering algorithm according to the real-time external environment influence degree and the difference of the influence degree standard to obtain the target loss function includes:
taking the difference value between the real-time external environment influence degree and the influence degree standard as an influence difference; and taking the sum value of the preset influence threshold value and the influence difference as the weight of the loss function in the clustering algorithm, and adjusting the loss function in the clustering algorithm to obtain the target loss function.
Preferably, the clustering the internal temperature by using a clustering algorithm based on the target loss function to obtain the category of the real-time internal temperature includes:
based on the target loss function, clustering the real-time internal temperature and the historical internal temperature by using a clustering algorithm to obtain at least two clustering categories, and obtaining the category of the real-time internal temperature.
Preferably, the monitoring the transport vehicle for the cold chain logistics based on the category comprises:
taking the clustering type with the largest number of internal temperatures as a normal type; when the category of the second number of real-time internal temperatures is not in the normal category, the monitoring result of the transport vehicle of the cold chain logistics is judged to be abnormal.
In a second aspect, an embodiment of the present invention provides a system for real-time monitoring and data processing of a cold-chain stream, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method for real-time monitoring and data processing of a cold-chain stream when executing the computer program.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, the internal temperature and the external temperature of the transport vehicle of the cold chain logistics are firstly obtained, and the temperature change in the carriage and the external temperature change condition are hysteresis because the temperature transmission is time-consuming, so that the influence degree of the temperature cannot be calculated through the external temperature and the internal temperature at the same time, the adjacent external temperature corresponding to the internal temperature is screened out from the historical external temperature according to the change fluctuation degree of the internal temperature and the historical external temperature, and the adjacent external temperature corresponding to the internal temperature can more accurately reflect the external environment corresponding to the current moment of the internal temperature. Further, the external environment influence degree is determined according to the difference between the internal temperature and the corresponding adjacent external temperature, the larger the difference between the internal temperature and the corresponding adjacent external temperature is, the larger the influence degree of the internal temperature on the external environment is, and when the internal temperature and the external temperature are consistent, the smaller the influence degree of the internal temperature on the external environment is. Finally, the loss function in the clustering algorithm is adjusted according to the external environment influence degree, so that when the difference between the external environment influence degree and the reference is larger, the loss function is enlarged, the range self-adaption of the clustering result is enlarged, the interference of the external environment on the internal temperature is eliminated, and misjudgment on the condition of abnormal internal temperature caused by the larger influence of the external environment on the internal temperature is avoided. And finally, obtaining the category of the internal temperature in real time according to the clustering result, and further realizing the monitoring of the transport vehicle of the cold chain logistics based on the category. The method and the system enable the clustering result obtained according to the clustering algorithm to be more accurate, further enable the monitoring result of the transport vehicle of the cold chain logistics to be more accurate based on the clustering result, and improve the judgment accuracy of temperature abnormality in the transport vehicle of the cold chain logistics.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for processing real-time monitoring data of a cold-chain stream according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of a method and a system for processing real-time monitoring data of cold-chain logistics according to the invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment of the invention provides a method and a system for processing real-time monitoring data of a cold-chain logistics, and the method is suitable for a cold-chain logistics transportation scene. When the cold chain logistics transportation is carried out in this scene, temperature information is acquired through the temperature sensor, the temperature information is uploaded to the data processing center, whether the temperature in the vehicle is abnormal or not is judged by the data processing center, and a logistics driver is timely informed to process, so that the problem of transportation products is prevented. In order to solve the problem of low judgment accuracy of temperature abnormality. According to the invention, the temperature abnormality caused by the equipment acquisition problem is removed through the clustering algorithm, and the accuracy of the system in judging the temperature abnormality is improved. The method has the advantages that the historical external temperature and the real-time internal temperature are analyzed, the degree of the external environment influence of the external environment on the internal temperature acquired by the temperature sensor is obtained, the loss function in the clustering algorithm is adjusted according to the degree of the external environment influence, the clustering result is more accurate, the monitoring result of the transport vehicle of the cold chain logistics is more accurate based on the clustering result, and the judgment accuracy of temperature abnormality is improved.
The invention provides a method and a system for processing real-time monitoring data of a cold-chain logistics, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of steps of a method for processing real-time monitoring data of a cold chain stream according to an embodiment of the invention is shown, the method includes the following steps:
step S100, obtaining an internal temperature and an external temperature of a transport vehicle of the cold chain stream.
When the instantaneous internal temperature value in the transport carriage of the cold-chain logistics is abnormal, the situation that the internal temperature of the transport carriage of the cold-chain logistics exceeds a set temperature threshold value due to the fact that the acquisition equipment acquires information or data transmission errors occur may occur, and the situation that false alarm occurs may be serious. Analyzing the historical temperature data of the cold-chain logistics monitoring system draws the condition of temperature change along with time into a temperature change curve, and further analyzes the temperature change curve to monitor the cold-chain logistics.
Firstly, the temperature sensor is used for collecting the internal temperature in a transport carriage of the cold-chain logistics, the internal temperature is transmitted to a computer of the transport vehicle through a wired interface, and equipment in the vehicle performs operations such as analysis and analysis on the transmitted data. The position of the vehicle is generally to be positioned during cold chain logistics transportation, a positioner is necessarily arranged on the vehicle, and the temperature information of the environment where the vehicle is located is acquired from a network according to the position information of the vehicle and is recorded as the external temperature of the transport vehicle. And judging the temperature in the carriage according to the data returned by the temperature sensor, and judging whether the abnormal temperature occurs in the transportation carriage. The data processing center of the automobile is provided with networking equipment, and the equipment is used for acquiring the change conditions of the internal temperature and the external temperature of the transport vehicle of the cold chain logistics during the previous transport. The real-time internal temperature and the real-time external temperature, the historical external temperature and the historical internal temperature are acquired through the temperature sensor, wherein the historical external temperature is the external temperature in the historical data, and the historical internal temperature is the internal temperature in the historical data.
Step S200, selecting the adjacent external temperature corresponding to the internal temperature from the historical external temperatures according to the variation fluctuation degree of the internal temperature and the historical external temperature.
Temperature data collected by the sensor can be classified into three categories based on a priori knowledge: normal data, abnormal data and noise data, wherein data distribution disorder regularity in the noise data is poor, the collected temperature data is judged to be the normal data and the abnormal data, and the temperature is not the normal data and the noise data, namely the abnormal data. The normal data is normal data by manually setting a threshold value as long as the acquired temperature data is within a normal range. Only need judge whether the data is unusual data can, when cold chain transportation, because the environment that the external world is located is different, the external influence degree in the carriage is different, and the strict degree of the loss function when clustering the inside temperature when adopting cluster analysis is different. The greater the external influence degree is, the more loose the definition of the loss function is, and the lesser the external influence degree is, the more strict the definition of the loss function is. The definition strictness of the loss function in the K-means clustering algorithm is changed by adjusting the loss function in the K-means clustering algorithm, and the convergence degree of the K-means clustering algorithm is changed.
In the transportation process of cold chain logistics, the temperature in the carriage can be influenced by the external temperature, and according to Newton's law of cooling, the larger the temperature difference between the carriage and the external environment is, the larger the influence degree is. When the temperature difference is the same, the influence degree of different external temperatures on the temperature in the carriage is also different, and the influence degree of higher external temperature on the temperature in the carriage is also increased. It should be noted that, the thermodynamic definition is that under ideal conditions, the energy absorbed by the same object at the same temperature is the same, but in reality, the thermal conductivity of the object will change with the change of temperature, and the higher the temperature, the faster the molecular movement rate of the object, the energy absorbed by the increased temperature will decrease.
Judging the abnormal condition of the collected temperature information, judging whether the abnormal condition of the temperature exceeds the influence degree of the external temperature, and when the abnormal condition of the collected temperature information is overlarge, the abnormal condition may be the abnormal condition of the temperature information collected by equipment, and the abnormal condition of the temperature in the carriage can not be judged by the data.
The position of the vehicle is generally positioned during logistics transportation, a positioner is arranged on the vehicle, and the temperature information of the environment where the vehicle is located is acquired from the network according to the position information of the vehicle. And judging the influence degree of the external temperature according to the external temperature information of the outside and the internal temperature information of the carriage acquired by the sensor.
Due to the heat transfer effect, the temperature change outside the vehicle can influence the temperature change in the carriage, and although the carriage contains the heat insulation layer, the existence of the heat insulation layer only reduces the interference of the external environment and can not completely remove the interference of the external environment.
And analyzing the condition that the temperature change in the transport vehicle is influenced by the external temperature, and observing whether the change condition of the temperature information acquired in each time period exceeds the influence of the external environment temperature. The temperature change in the transportation carriage is influenced by the temperature of the refrigerating equipment and the external environment in the carriage, and when the temperature change condition in the transportation carriage exceeds the influence degree of the external environment, the acquired temperature information is error information with high probability and noise information with high probability. The temperature transmission is time-consuming, and the temperature change in the compartment and the temperature change in the outside are hysteresis, but the temperature change curve in the compartment and the temperature change curve in the outside environment show similar trends. And acquiring which time period each time period is affected by according to the trend of temperature change.
And acquiring the external temperature of the external environment of the current position according to the position information, drawing an external temperature sequence according to the change of the external temperature along with time, and updating the external temperature sequence and the internal temperature sequence in the carriage along with the change of time.
Since the temperature is affected by hysteresis, the degree of influence of the temperature cannot be calculated from the external temperature and the internal temperature at the same time. When the working efficiency of the refrigerating equipment in the carriage is the same as that of the refrigerating equipment in all time periods, the temperature change in the carriage is caused by the change of the external temperature, and the temperature change trend in the carriage is similar to the change trend of the external environment. And judging the fluctuation similarity of the two sequences, and obtaining the temperature influenced by the external temperature of the acquired temperature information according to the similarity, wherein the temperature influenced by the external temperature is called as the adjacent external temperature of the internal temperature.
Wherein, according to the fluctuation degree of the change of the internal temperature and the historical external temperature, the adjacent external temperature corresponding to the internal temperature is screened out from the historical external temperature, and the method is specific: constructing an internal temperature sequence section corresponding to the real-time internal temperature by the real-time internal temperature and the preset first number of internal temperatures; constructing an external temperature sequence segment corresponding to each historical external temperature according to each historical external temperature and the corresponding preset first number of historical external temperatures; determining the fluctuation similarity of the internal temperature curve section and the external temperature curve section according to the slope difference corresponding to the data at the same position on the internal temperature sequence section and the external temperature sequence section; and taking the historical external temperature corresponding to the maximum value of the fluctuation similarity of the internal temperature sequence section and all the corresponding external temperature sequence sections as the real-time adjacent external temperature of the internal temperature. In the embodiment of the invention, the first number of experience values is preset to be 9, and in other embodiments, the value is adjusted by an implementer according to actual conditions.
Namely, 10 pieces of data are empirically set as a judging sequence section, and the first 9 internal temperatures of the internal temperature in the current carriage and the current internal temperature are combined into a judging sequence section, which is called an internal temperature sequence section. And calculating the similarity of the fluctuation of the internal temperature sequence section and the external temperature sequence section.
The fluctuation similarity of the internal temperature sequence section and the external temperature sequence section is determined according to the slope difference corresponding to the data at the same position on the internal temperature sequence section and the external temperature sequence section, and the fluctuation similarity is specifically: calculating the square of the difference value of slope change values corresponding to any two temperature data with the same positions on the internal temperature sequence section and the external temperature sequence section as a first square; and carrying out negative correlation normalization processing on the average value of all the first squares corresponding to the internal temperature sequence section and the external temperature sequence section to obtain the fluctuation similarity of the internal temperature sequence section and the external temperature sequence section.
The calculation formula of the fluctuation similarity is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,the fluctuation similarity of the internal temperature sequence section and the corresponding c-th external temperature sequence section; exp is an exponential function based on a natural constant; />Slope change value of the ith internal temperature of the internal temperature sequence segment; />Slope change value of the ith external temperature of the c-th external temperature sequence segment corresponding to the internal temperature sequence segment; n is the number of internal temperatures in the internal temperature sequence segment, and in the embodiment of the invention, the number of internal temperatures in the internal temperature sequence segment is consistent with the number of external temperatures in the external temperature sequence segment, so n is the number of external temperatures in the external temperature sequence segment;is the first square of the i-th internal temperature of the internal temperature sequence segment and the corresponding i-th external temperature of the c-th external temperature sequence segment.
In the embodiment of the invention, the negative correlation normalization processing of the average value of all the first squares corresponding to the internal temperature sequence section and the external temperature sequence section is realized by taking the natural constant as a base number and taking the average value of all the first squares corresponding to the negative internal temperature sequence section and the external temperature sequence section as an exponential function of an index, so that the fluctuation similarity of the internal temperature sequence section and the external temperature sequence section is obtained. The smaller the difference between the slope change corresponding to the internal temperature in the internal temperature sequence segment and the slope change corresponding to the external temperature in the external temperature sequence segment, the greater the similarity of the short fluctuations of the two internal temperature sequence segments and the external temperature sequence.
Wherein, the temperature change in the carriage is influenced by external temperature and the refrigerating equipment in the carriage, and when the efficiency of the refrigerating equipment is unchanged, the temperature change in the carriage only has the influence of external environment change. The change trend of the temperature in the carriage should be the same as the change trend of the temperature of the external environment. Only the trend of the temperature change is calculated, and the size of the temperature change is not considered. The temperature change trend can be changed according to the slope of each temperature data, and the slope of each acquired temperature data can be obtained according to the information of the front data and the back data.
For the internal temperature, the method for acquiring the slope change value of the internal temperature comprises the following steps: selecting any internal temperature as a target temperature, and fitting an internal temperature sequence segment corresponding to the target temperature to obtain an internal temperature curve segment; calculating the difference between the slope of the target temperature and the slope of the internal temperature at the next moment corresponding to the target temperature; the slope of the target temperature is the slope of a data point corresponding to the target temperature on the internal temperature curve segment, the horizontal axis of the internal temperature curve segment is time, and the vertical axis is internal temperature.
Similarly, for the external temperature, the method for acquiring the slope change value of the external temperature is as follows: selecting any external temperature as a temperature to be selected, and fitting an external temperature sequence section corresponding to the temperature to be selected to obtain an external temperature curve section; calculating the difference value between the slope of the temperature to be selected and the slope of the external temperature at the next moment corresponding to the temperature to be selected; the slope of the temperature to be selected is the slope of a data point corresponding to the temperature to be selected on the external temperature curve segment, the horizontal axis of the external temperature curve segment is time, and the vertical axis is external temperature.
The slope change value is the length of the slope change value compared with the time change, and in the embodiment of the invention, the sampling time and the sampling frequency are the same, so that the corresponding time intervals are the same, the slope change value is directly taken as the slope change value without dividing the slope change value by the time change length.
And finally, taking the historical external temperature corresponding to the maximum value of the fluctuation similarity of the internal temperature sequence section and all the corresponding external temperature sequence sections as the real-time adjacent external temperature of the internal temperature. The fluctuation of the historical external temperature corresponding to the maximum value of the fluctuation similarity is the influencing factor for causing the temperature change in the transportation carriage.
Step S300, determining the external environment influence degree according to the difference between the internal temperature and the corresponding adjacent external temperature.
The external environment temperature can influence the judgment of the clustering result, because the data are larger due to the interference of the external environment, the clustering is carried out by taking the difference between the temperatures as the Euclidean distance between the temperatures for judgment, and the data with normal temperature can be divided into abnormal data due to the external interference, so that the clustering accuracy is influenced.
The interference of the external environment can cause data migration, and when the clustering center is calculated through the loss function in an iterative mode, the data migration causes inaccurate selection result of the clustering center. The greater the interference to the temperature, the greater the degree of offset, and the greater the degree of offset of the clustering result.
And clustering the collected temperatures to judge the category of the internal temperature in real time, and adjusting a loss function in a clustering algorithm according to the degree of influence of the temperatures and the degree of abnormality of temperature data by calculating the degree of abnormality and the degree of influence, wherein the larger the loss function is, the larger the range of a clustering result is, and the smaller the loss function is, the smaller the range of the clustering result is. The severity of the clustering result is adjusted by adjusting the loss function of the clusters.
Determining the degree of external environmental influence according to the difference between the internal temperature and the corresponding adjacent external temperature, specifically: calculating the difference between the internal temperature and the corresponding adjacent external temperature to be used as the difference between the internal temperature and the external temperature; and taking the normalized value of the product of the internal and external temperature difference and the adjacent external temperature as the external environment influence degree.
The calculation formula of the external environment influence degree is as follows:
wherein D is the external environment influence degree; norm is a normalization function;is the internal temperature; />Is the internal temperature->A corresponding external temperature; />Is the difference between the internal temperature and the corresponding adjacent external temperature.
The larger the temperature difference between the internal temperature and the external temperature is, the faster the heat dissipation speed is reflected, and the larger the temperature difference between the interior and the exterior of the carriage is, the larger the influence degree of the external environment on the temperature in the carriage is. When the temperature difference between the inner environment and the outer environment is the same at different time points, the higher the external temperature is, the higher the heat dissipation efficiency of the temperature is, and the greater the influence degree of the heat dissipation efficiency on the carriage is. The influence degree of different external temperatures on the temperature in the carriage is obtained.
Step S400, according to the real-time external environment influence degree and the difference of influence degree references, the loss function in the clustering algorithm is adjusted to obtain a target loss function; based on the target loss function, clustering the internal temperature by using a clustering algorithm to obtain the real-time belonging category of the internal temperature, and monitoring the transport vehicle of the cold chain logistics based on the belonging category.
Firstly, determining an influence degree standard corresponding to the real-time external environment influence degree according to the influence degrees corresponding to the internal temperature and the external temperature in the historical data, wherein the acquisition method of the influence degree standard comprises the following steps: taking the average value of the historic internal temperature and the corresponding external environment influence degree close to the external temperature as an influence degree standard. The influence level reference reflects the normal influence level of the real-time temperature data.
And taking the difference value between the internal temperatures as the Euclidean distance between the internal temperatures, and calculating a loss function of each cluster center by selecting the cluster center and iterating the selection of the cluster center. Because the temperature is interfered by the external environment, the external interference is removed to obtain a more accurate clustering center when the loss function is calculated. In the embodiment of the invention, the value of K in the K-means clustering algorithm is 3, and in other embodiments, the value is adjusted by an implementer according to actual conditions, but the value is required to be a positive integer greater than or equal to 2.
Therefore, further, after obtaining the influence degree standard, according to the real-time external environment influence degree and the difference of the influence degree standard, the loss function in the clustering algorithm is adjusted to obtain the target loss function, and the method is specific: taking the difference value between the real-time external environment influence degree and the influence degree standard as an influence difference; and taking the sum value of the preset influence threshold value and the influence difference as the weight of the loss function in the clustering algorithm, and adjusting the loss function in the clustering algorithm to obtain the target loss function.
The calculation formula of the target loss function is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,is a target loss function; />As a reference for the degree of influence; d is the real-time external environment influence degree; e is the loss function of the original K-means cluster. In the embodiment of the present invention, the value of the preset influence threshold is 1, and in other embodiments, the value can be adjusted by an implementer according to the actual situation.
When the difference between the external environment influence degree and the influence height reference is larger, the corresponding influence degree is more unstable, so that when the target loss function is adjusted, the target loss function with smaller difference between the external environment influence degree and the influence degree reference is larger. Because the larger the loss function is, the larger the range of the clustering result is, the smaller the loss function is, and because the larger the external environment influence degree is different from the reference, the larger the range of the corresponding clustering result is, so as to adapt to the influence of the external environment.
Based on the obtained target loss function, clustering the internal temperature of the transport vehicle of the cold-chain logistics by using a clustering algorithm to obtain the category of the internal temperature of the transport vehicle of the cold-chain logistics in real time. The data to be clustered by the clustering algorithm is a real-time internal temperature and a historical internal temperature in the historical data. The method is that based on a target loss function, a clustering algorithm is utilized to cluster the real-time internal temperature and the historical internal temperature to obtain at least two clustering categories, and the category of the real-time internal temperature is obtained. Since the value of K in the embodiment of the invention is 3, the clustering result is three categories.
When cold chain logistics transportation is carried out, the temperature in a transportation carriage is generally kept at 10-15 ℃, and under normal conditions, the temperature in the transportation carriage is kept in a normal temperature range, so that the data in normal categories in a clustering result is the most, the denser the data distribution is, and the greater the clustering center density is. Therefore, the cluster type with the largest number of internal temperatures is further defined as the normal type. When the category of the second number of real-time internal temperatures is not in the normal category, judging that the monitoring result of the transport vehicle of the cold chain logistics is abnormal. In the embodiment of the invention, the second number of experience values is preset to be 3, and in other embodiments, the value is adjusted by an implementer according to actual conditions. Therefore, it can be said that when all of the 3 continuously collected internal temperatures do not belong to the normal category, the monitoring result of the transport vehicle of the cold chain logistics is considered to be abnormal, otherwise, the monitoring result of the transport vehicle of the cold chain logistics is judged to be normal.
According to the invention, the temperature abnormality caused by the equipment acquisition problem is removed through the K-means clustering algorithm, and the accuracy of the system in judging the temperature abnormality is improved. And analyzing the interference influence degree of the external environment on the information acquired by the temperature sensor through the route passed by the transportation equipment and the time and history information of the equipment passing by the route, and adjusting the clustered loss function according to the influence degree. And according to the collected information which is not in accordance with the logic through clustering, whether abnormal information exists or not is judged again for the denoised information, so that the conventional misjudgment degree of judging whether abnormal conditions occur or not by setting a temperature threshold value is avoided, and the accuracy of abnormal temperature judgment is improved.
In summary, the present invention relates to the field of data processing technology. The method comprises the steps of obtaining the internal temperature and the external temperature of a transport vehicle of a cold chain logistics; screening adjacent external temperatures corresponding to the internal temperature from the historical external temperatures according to the variation fluctuation degree of the internal temperature and the historical external temperature; determining the degree of external environmental influence according to the difference between the internal temperature and the corresponding adjacent external temperature; according to the real-time external environment influence degree and the difference of the influence degree standard, the loss function in the clustering algorithm is adjusted to obtain a target loss function; based on the target loss function, clustering the internal temperature of the transport vehicle of the cold chain logistics by using a clustering algorithm to obtain the category of the real-time internal temperature of the transport vehicle of the cold chain logistics, and monitoring the transport vehicle of the cold chain logistics based on the category.
The embodiment of the invention also provides a cold chain logistics real-time monitoring data processing system which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the method when executing the computer program. Because a detailed description is given above for a method for processing real-time monitoring data of a cold chain logistics, the detailed description is omitted.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. The method for processing the real-time monitoring data of the cold chain logistics is characterized by comprising the following steps of:
acquiring the internal temperature and the external temperature of a transport vehicle of the cold chain logistics;
screening adjacent external temperatures corresponding to the internal temperature from the historical external temperatures according to the variation fluctuation degree of the internal temperature and the historical external temperature;
determining the degree of external environmental influence according to the difference between the internal temperature and the corresponding adjacent external temperature;
according to the real-time external environment influence degree and the difference of the influence degree standard, the loss function in the clustering algorithm is adjusted to obtain a target loss function; based on the target loss function, clustering the internal temperature of the transport vehicle of the cold chain logistics by using a clustering algorithm to obtain the category of the real-time internal temperature of the transport vehicle of the cold chain logistics, and monitoring the transport vehicle of the cold chain logistics based on the category.
2. The method for processing real-time monitoring data of cold-chain logistics according to claim 1, wherein the step of screening the adjacent external temperature corresponding to the internal temperature from the historical external temperatures according to the fluctuation degree of the internal temperature and the historical external temperature comprises the steps of:
constructing an internal temperature sequence section corresponding to the real-time internal temperature by the real-time internal temperature and the preset first number of internal temperatures; constructing an external temperature sequence segment corresponding to each historical external temperature according to each historical external temperature and the corresponding preset first number of historical external temperatures;
determining the fluctuation similarity of the internal temperature curve section and the external temperature curve section according to the slope difference corresponding to the data at the same position on the internal temperature sequence section and the external temperature sequence section;
and taking the historical external temperature corresponding to the maximum value of the fluctuation similarity of the internal temperature sequence section and all the corresponding external temperature sequence sections as the real-time adjacent external temperature of the internal temperature.
3. The method for processing real-time monitoring data of cold-chain logistics according to claim 2, wherein determining the fluctuation similarity of the internal temperature sequence segment and the external temperature sequence segment according to the slope difference corresponding to the data at the same position on the internal temperature sequence segment and the external temperature sequence segment comprises:
calculating the square of the difference value of slope change values corresponding to any two temperature data with the same positions on the internal temperature sequence section and the external temperature sequence section as a first square; and carrying out negative correlation normalization processing on the average value of all the first squares corresponding to the internal temperature sequence section and the external temperature sequence section to obtain the fluctuation similarity of the internal temperature sequence section and the external temperature sequence section.
4. The method for processing real-time monitoring data of cold-chain logistics according to claim 3, wherein the method for acquiring the slope change value of the internal temperature is as follows:
selecting any internal temperature as a target temperature, and fitting an internal temperature sequence segment corresponding to the target temperature to obtain an internal temperature curve segment; calculating the difference between the slope of the target temperature and the slope of the internal temperature at the next moment corresponding to the target temperature; the slope of the target temperature is the slope of a data point corresponding to the target temperature on the internal temperature curve segment, the horizontal axis of the internal temperature curve segment is time, and the vertical axis is internal temperature.
5. The method for real-time monitoring data processing of a cold chain stream according to claim 1, wherein said determining the degree of external environmental influence based on the difference between the internal temperature and the corresponding adjacent external temperature comprises:
calculating the difference between the internal temperature and the corresponding adjacent external temperature to be used as the difference between the internal temperature and the external temperature; and taking the normalized value of the product of the internal and external temperature difference and the adjacent external temperature as the external environment influence degree.
6. The method for processing real-time monitoring data of cold-chain logistics according to claim 1, wherein the method for obtaining the influence degree standard is as follows:
taking the average value of the historic internal temperature and the corresponding external environment influence degree close to the external temperature as an influence degree standard.
7. The method for processing real-time monitoring data of cold-chain logistics according to claim 1, wherein the step of adjusting the loss function in the clustering algorithm according to the real-time external environment influence degree and the difference of the influence degree standard to obtain the target loss function comprises the following steps:
taking the difference value between the real-time external environment influence degree and the influence degree standard as an influence difference; and taking the sum value of the preset influence threshold value and the influence difference as the weight of the loss function in the clustering algorithm, and adjusting the loss function in the clustering algorithm to obtain the target loss function.
8. The method for processing real-time monitoring data of cold-chain logistics according to claim 1, wherein the clustering the internal temperatures by using a clustering algorithm based on the objective loss function to obtain the real-time belonging categories of the internal temperatures comprises:
based on the target loss function, clustering the real-time internal temperature and the historical internal temperature by using a clustering algorithm to obtain at least two clustering categories, and obtaining the category of the real-time internal temperature.
9. The method for processing real-time monitoring data of cold-chain logistics according to claim 8, wherein the monitoring of the transport vehicle of the cold-chain logistics based on the category comprises:
taking the clustering type with the largest number of internal temperatures as a normal type; when the category of the second number of real-time internal temperatures is not in the normal category, the monitoring result of the transport vehicle of the cold chain logistics is judged to be abnormal.
10. A cold chain logistics real-time monitoring data processing system, comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of the cold chain logistics real-time monitoring data processing method according to any one of claims 1-9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310966456.2A CN116701983B (en) | 2023-08-03 | 2023-08-03 | Cold-chain logistics real-time monitoring data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310966456.2A CN116701983B (en) | 2023-08-03 | 2023-08-03 | Cold-chain logistics real-time monitoring data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116701983A true CN116701983A (en) | 2023-09-05 |
| CN116701983B CN116701983B (en) | 2023-10-20 |
Family
ID=87843629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310966456.2A Active CN116701983B (en) | 2023-08-03 | 2023-08-03 | Cold-chain logistics real-time monitoring data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116701983B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117474427A (en) * | 2023-12-27 | 2024-01-30 | 大连金马衡器有限公司 | Intelligent pallet cold chain tracing method based on Internet of things technology |
| CN117611031A (en) * | 2023-12-04 | 2024-02-27 | 冻冻(北京)网络科技有限公司 | Real-time monitoring method and system for logistics temperature of cold chain Internet of things |
| CN117873838A (en) * | 2024-03-12 | 2024-04-12 | 武汉众诚华鑫科技有限公司 | Method and system for monitoring ambient temperature of telecommunication equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529881A (en) * | 2016-11-21 | 2017-03-22 | 山东省计算中心（国家超级计算济南中心） | Logistics cargo tracking monitoring device and method |
| US20210240156A1 (en) * | 2020-02-03 | 2021-08-05 | Samsung Electronics Co., Ltd. | Methods and systems for ascertaining factors contributing to the temperature of a device |
| US20210293651A1 (en) * | 2018-09-11 | 2021-09-23 | Hefei Institute For Public Safety Research, Tsinghua University | Method and device for detecting fault of monitoring device |
| CN114020064A (en) * | 2021-11-05 | 2022-02-08 | 江苏北联国芯技术有限公司 | Self-adaptive environment temperature adjusting system of intelligent equipment |
| CN114838767A (en) * | 2022-05-06 | 2022-08-02 | 徐州工程学院 | Temperature and humidity intelligent monitoring system and method for cold-chain logistics |
| CN114992926A (en) * | 2022-05-26 | 2022-09-02 | 西安交通大学 | For trans-critical CO 2 Control method and control system of air conditioning system |
| CN114996661A (en) * | 2022-08-04 | 2022-09-02 | 山东佳力通汽车有限公司 | Refrigerator car temperature monitoring method and system |
| CN115882463A (en) * | 2022-12-07 | 2023-03-31 | 国网河南省电力公司经济技术研究院 | Commercial building air conditioner load schedulable potential evaluation method |
| CN116205556A (en) * | 2023-05-06 | 2023-06-02 | 成都运荔枝科技有限公司 | Cold chain food logistics warehouse management system based on internet |
| CN116418120A (en) * | 2023-06-08 | 2023-07-11 | 深圳市联明电源有限公司 | Intelligent early warning method applied to water-cooled power supply |
-
2023
- 2023-08-03 CN CN202310966456.2A patent/CN116701983B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529881A (en) * | 2016-11-21 | 2017-03-22 | 山东省计算中心（国家超级计算济南中心） | Logistics cargo tracking monitoring device and method |
| US20210293651A1 (en) * | 2018-09-11 | 2021-09-23 | Hefei Institute For Public Safety Research, Tsinghua University | Method and device for detecting fault of monitoring device |
| US20210240156A1 (en) * | 2020-02-03 | 2021-08-05 | Samsung Electronics Co., Ltd. | Methods and systems for ascertaining factors contributing to the temperature of a device |
| CN114020064A (en) * | 2021-11-05 | 2022-02-08 | 江苏北联国芯技术有限公司 | Self-adaptive environment temperature adjusting system of intelligent equipment |
| CN114838767A (en) * | 2022-05-06 | 2022-08-02 | 徐州工程学院 | Temperature and humidity intelligent monitoring system and method for cold-chain logistics |
| CN114992926A (en) * | 2022-05-26 | 2022-09-02 | 西安交通大学 | For trans-critical CO 2 Control method and control system of air conditioning system |
| CN114996661A (en) * | 2022-08-04 | 2022-09-02 | 山东佳力通汽车有限公司 | Refrigerator car temperature monitoring method and system |
| CN115882463A (en) * | 2022-12-07 | 2023-03-31 | 国网河南省电力公司经济技术研究院 | Commercial building air conditioner load schedulable potential evaluation method |
| CN116205556A (en) * | 2023-05-06 | 2023-06-02 | 成都运荔枝科技有限公司 | Cold chain food logistics warehouse management system based on internet |
| CN116418120A (en) * | 2023-06-08 | 2023-07-11 | 深圳市联明电源有限公司 | Intelligent early warning method applied to water-cooled power supply |
Non-Patent Citations (4)
| Title |
|---|
| WANG TINGMAN等: "Fish product quality evaluation based on temperature monitoring in cold chain", 《AFRICAN JOURNAL OF BIOTECHNOLOGY》, vol. 9 * |
| 张明利;李杰;黄培;: "农产品冷链物流车载智能监控系统的应用", 现代农业科技, no. 18 * |
| 范蓓蕾: "基于多尺度环境分析的设施奶牛场精细化管理研究", 《中国优秀硕士学位论文全文数据库（农业科技辑）》, no. 8 * |
| 马骏;: "蔬菜大棚温度电控系统的模糊控制研究", 中国农机化学报, no. 01 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611031A (en) * | 2023-12-04 | 2024-02-27 | 冻冻(北京)网络科技有限公司 | Real-time monitoring method and system for logistics temperature of cold chain Internet of things |
| CN117611031B (en) * | 2023-12-04 | 2024-05-28 | 冻冻(北京)网络科技有限公司 | Real-time monitoring method and system for logistics temperature of cold chain Internet of things |
| CN117474427A (en) * | 2023-12-27 | 2024-01-30 | 大连金马衡器有限公司 | Intelligent pallet cold chain tracing method based on Internet of things technology |
| CN117474427B (en) * | 2023-12-27 | 2024-03-26 | 大连金马衡器有限公司 | Intelligent pallet cold chain tracing method based on Internet of things technology |
| CN117873838A (en) * | 2024-03-12 | 2024-04-12 | 武汉众诚华鑫科技有限公司 | Method and system for monitoring ambient temperature of telecommunication equipment |
| CN117873838B (en) * | 2024-03-12 | 2024-05-24 | 武汉众诚华鑫科技有限公司 | Method and system for monitoring ambient temperature of telecommunication equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116701983B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116701983B (en) | Cold-chain logistics real-time monitoring data processing method and system | |
| CN109542740B (en) | Abnormality detection method and apparatus | |
| US20200355524A1 (en) | Internet of things based conveyance having predictive maintenance | |
| CN114912852B (en) | Abnormity monitoring and early warning system for storage tank of refrigeration bin | |
| CN116383450B (en) | Railway and highway logistics transportation information comprehensive management system | |
| TWI578257B (en) | Method, apparatus, system, and non-transitory computer-readable storage medium for monitoring manufacturing apparatus | |
| CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
| WO2023044770A1 (en) | Dry pump downtime early warning method and apparatus, electronic device, storage medium, and program | |
| CN114996661B (en) | Refrigerator car temperature monitoring method and system | |
| CN117196353A (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN116909339B (en) | Intelligent household safety early warning method and system based on artificial intelligence | |
| CN116066343A (en) | Intelligent early warning method and system for fault model of oil delivery pump unit | |
| CN115290316B (en) | Fault diagnosis method for eccentric rotary valve | |
| CN117708748B (en) | Operation monitoring system and method for centrifugal fan | |
| CN116881745A (en) | Pressure transmitter abnormality monitoring method based on big data | |
| CN110737975B (en) | Wind power plant wind speed and power prediction and abnormality correction method based on empirical mode decomposition and autoregressive model | |
| CN116594446B (en) | Temperature control method and system for big data center | |
| CN117349711A (en) | Electronic tag data processing method and system for railway locomotive parts | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| CN117611031B (en) | Real-time monitoring method and system for logistics temperature of cold chain Internet of things | |
| CN117367023B (en) | Energy consumption control method, system, equipment and storage medium for refrigerated cabinet | |
| CN118013323B (en) | Driving motor state analysis method and system for large-caliber electric half ball valve | |
| CN117874445B (en) | Enzyme preparation production monitoring method for real-time online monitoring data analysis | |
| CN118094449B (en) | Intelligent production monitoring method, system and device based on industrial Internet | |
| CN117829381B (en) | Agricultural greenhouse data optimization acquisition system based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |