CN114996661B - Refrigerator car temperature monitoring method and system - Google Patents
Refrigerator car temperature monitoring method and system Download PDFInfo
- Publication number
- CN114996661B CN114996661B CN202210929645.8A CN202210929645A CN114996661B CN 114996661 B CN114996661 B CN 114996661B CN 202210929645 A CN202210929645 A CN 202210929645A CN 114996661 B CN114996661 B CN 114996661B
- Authority
- CN
- China
- Prior art keywords
- temperature
- distance
- internal
- difference
- surface temperature
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 121
- 230000007613 environmental effect Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 35
- 238000013528 artificial neural network Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005057 refrigeration Methods 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 192
- 238000003062 neural network model Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention relates to the technical field of refrigeration control, in particular to a method and a system for monitoring the temperature of a refrigerator car, wherein the method comprises the following steps: collecting the internal temperature, the distance to transported articles and the ambient temperature of each set position in the refrigerator car at each detection time in a historical period; obtaining a plurality of distance grades according to the distance; calculating the internal and external temperature difference according to the internal temperature and the environmental temperature to obtain a plurality of temperature difference grades; calculating a second surface temperature of the transported item according to the internal temperature, and calculating temperature influence values of all temperature difference levels based on the first surface temperature and the second surface temperature; calculating distance accurate values of all distance grades and the correlation and credibility of all set positions according to the internal temperature and the first surface temperature; and calculating the actual surface temperature of the transported goods according to the correlation, the credibility, the accurate distance value and the temperature influence value, thereby realizing the monitoring of the temperature of the refrigerated truck. The invention can accurately acquire the actual surface temperature and realize the control of the temperature of the refrigerated truck.
Description
Technical Field
The invention relates to the technical field of refrigeration control, in particular to a method and a system for monitoring the temperature of a refrigerator car.
Background
In recent years, cold chain transportation is gradually popularized and rapidly developed in China, and a refrigerator car serving as key equipment of cold chain logistics has heat preservation and refrigeration functions and can meet the requirement of short-distance refrigeration transportation of refrigerated goods. The internal temperature of maintenance refrigerator carriage is invariable, keeps the inside less difference in temperature everywhere of box, plays important role to the quality of guaranteeing article in the transportation. Therefore, the temperature in the refrigerator compartment is required to be guaranteed to be within the refrigeration temperature range of transported goods at all times in the transportation process, and the temperature in the refrigerator compartment is required to be monitored and regulated in real time.
The traditional refrigerated vehicle monitoring system directly utilizes the temperature sensor to obtain the temperature inside the refrigerated vehicle, and does not consider that the distribution of the temperature inside the refrigerated vehicle is not uniform, namely, the distance from the temperature sensor to the transported goods is different, so that the influence on the surface temperature of the transported goods is different, and the traditional refrigerated vehicle monitoring system has a plurality of defects, such as simple and crude control, incapability of monitoring the actual state inside the vehicle in real time, scientific and representative control strategy and low monitoring precision; therefore, how to reasonably and accurately acquire the actual state of the interior of the carriage so as to control the temperature distribution in the refrigerated vehicle within a reasonable range is a technical problem which needs to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a refrigerator car temperature monitoring method, which adopts the following technical scheme:
collecting the internal temperature and the distance from each set position in the refrigerator van to the transported object at each detection time in the historical period, and collecting the environmental temperature corresponding to each detection time in the historical period; and dividing the distance into a plurality of distance levels; setting a first surface temperature corresponding to each detection time of the transported object in a historical time period;
calculating the internal and external temperature difference corresponding to each detection time in the historical time period according to the internal temperature and the environmental temperature; dividing the internal and external temperature difference into a plurality of temperature difference grades; the temperature difference grade at least comprises a detection moment;
calculating a second surface temperature corresponding to each detection time of the transported object in a historical period according to the internal temperature, and calculating a temperature influence value corresponding to each temperature difference grade based on a first surface temperature and a second surface temperature corresponding to each detection time of the transported object in each temperature difference grade;
calculating distance accurate values corresponding to the distance grades according to the internal temperature corresponding to the distance grades and the first surface temperature;
calculating the absolute value of the difference between each internal temperature and the corresponding first surface temperature, and calculating the correlation and credibility corresponding to each set position according to the absolute value of the difference;
and calculating the actual surface temperature of the transported object at the current detection moment according to the weight, the internal temperature corresponding to the current detection moment of each set position and the temperature influence value, so as to realize the monitoring of the temperature of the refrigerated truck.
Further, the calculation method of the internal and external temperature difference comprises the following steps: and calculating the average value corresponding to each internal temperature, and recording the difference value between the environmental temperature and the average value as the internal and external temperature difference.
Further, the method for acquiring the second surface temperature comprises the following steps: and according to the distance corresponding to each internal temperature, obtaining the temperature weight corresponding to each internal temperature, and carrying out weighted summation on the internal temperature and the temperature weight corresponding to the internal temperature to obtain the second surface temperature.
Further, the temperature influence value is:
whereinIs the temperature influence value corresponding to the temperature difference grade o,the number of detection moments in the temperature difference grade o;for the first surface temperature of the transported item at the jth detection moment in the temperature difference level o,and the corresponding second surface temperature of the transported object at the jth detection time in the temperature difference grade o.
Further, the method for obtaining the accurate distance value comprises the following steps: all internal temperatures corresponding to the distance grade; calculating the difference value of each internal temperature and the first surface temperature corresponding to the internal temperature; obtaining an accurate distance value according to the difference value, wherein the calculation formula is as follows:
in the formula,for the distance accuracy value corresponding to the distance level y,for the distance class y to correspond to the number of internal temperatures,for the ith internal temperature in the distance class y,a first surface temperature corresponding to the ith internal temperature in the distance class y;to adjust the coefficient;
the method for acquiring the first surface temperature corresponding to the internal temperature comprises the following steps: and acquiring the detection time corresponding to the internal temperature in the historical time period, and recording the first surface temperature corresponding to the transported article at the detection time as the first surface temperature corresponding to the internal temperature.
Further, the correlation corresponding to each setting position is as follows:
wherein,for the correlation corresponding to the kth setting position,the absolute value of the difference value between the internal temperature corresponding to the kth set position at the e-th detection moment and the first surface temperature corresponding to the transported object at the e-th detection moment is obtained;the number of detected time instants within the history period,is the number of the set positions;
the credibility corresponding to each set position is as follows:
wherein,for the correlation corresponding to the kth setting position,the absolute value of the difference value between the internal temperature corresponding to the kth set position at the e-th detection moment and the first surface temperature corresponding to the transported object at the e-th detection moment is obtained;the number of detected time instants within the history period,is an exponential function with e as the base.
Further, the method for obtaining the weight comprises the following steps: forming all distance levels in the historical time period into a distance level set, obtaining the distance from each set position to the transported object at the current detection time, searching the distance level corresponding to each distance in the distance level set and obtaining a corresponding distance accurate value, calculating the product of the relevance, the credibility and the distance accurate value corresponding to each set position, and taking the value after the normalization of the product as the weight corresponding to each set position.
Further, the method for calculating the actual surface temperature of the transportation object corresponding to the current detection time comprises the following steps:
forming all temperature difference levels in a historical period into a temperature difference level set, calculating the internal and external temperature difference corresponding to the current detection moment, searching the temperature difference level corresponding to the internal and external temperature difference in the temperature difference level set and obtaining a corresponding temperature influence value; and weighting and summing the internal temperature corresponding to each set position at the current detection moment and the weight corresponding to each set position, and adding the obtained temperature influence value to obtain the actual surface temperature of the transported goods.
Further, the method further comprises the steps of obtaining the actual surface temperature of the transported object corresponding to the current detection time through an FC neural network; the specific process is as follows:
calculating actual surface temperature corresponding to each detection time of the transported object in a historical period, obtaining volume and heat conductivity corresponding to each detection time of the transported object in the historical period, obtaining a vector corresponding to each detection time in the historical period by using the volume, the heat conductivity, the internal temperature, the environmental temperature and the distance as data sets, training an FC neural network by using the vector corresponding to each detection time in the historical period and the actual surface temperature corresponding to each detection time of the transported object in the historical period as the data sets, obtaining the trained FC neural network, obtaining the vector corresponding to the current detection time, inputting the vector into the trained FC neural network, and outputting the actual surface temperature corresponding to the current detection time of the transported object;
the corresponding loss function of the FC neural network during training is as follows:
in the formula,as a corresponding loss function of the FC neural network during training,in order to be a function of the cross-entropy loss,is a difference lossA loss function;
the difference loss function is:
in the formula,in order to be a function of the difference loss,for the corresponding actual surface temperature in the data set,actual surface temperature output for the FC neural network;in order to take the function of the minimum value,is an exponential function with e as the base.
The invention also provides a refrigerator car temperature monitoring system which comprises a processor and a memory, wherein the processor executes a program of the refrigerator car temperature monitoring method stored in the memory.
The embodiment of the invention at least has the following beneficial effects:
according to the method, the temperature influence value of each temperature difference grade is calculated through the first surface temperature and the second surface temperature of the transported object at each detection time in the temperature difference grade, the different influences of the different temperature difference grades inside and outside the refrigerator car on the actual surface temperature of the transported object are considered, the temperature influence value of each temperature difference grade on the actual surface temperature of the transported object is calculated, and the calculation result is more accurate; according to the method, the distance is divided into a plurality of distance grades according to different distances from each set position to the transported articles, and the distance accurate value corresponding to each distance grade is calculated; considering that the distances from the set positions to the transported objects are different, the contribution of the internal temperature corresponding to the set positions to the actual surface temperature of the transported objects is different; calculating the correlation and credibility corresponding to each set position based on the absolute value of the difference value between the internal temperature of each set position and the corresponding first surface temperature in the historical time period; and calculating the actual surface temperature of the transported goods at the current detection time according to the weight, the internal temperature of each set position in the refrigerator car at the current detection time and the temperature influence value, so as to realize the monitoring of the refrigerator car temperature. According to the method, the influence of the distance and the temperature difference grade of the internal environment and the external environment of the refrigerator compartment on the actual surface temperature of the transported goods is considered, the relevance and the credibility corresponding to each set position are also considered, the weight corresponding to each set position is calculated according to the relevance and the credibility, and the actual surface temperature of the transported goods is further obtained. The invention analyzes the influence of different reference factors on the actual surface temperature from multiple angles, so that the obtained actual surface temperature is more accurate, the precision of monitoring the temperature of the refrigerator car is improved, the quality of transported goods is ensured to the greatest extent, and the damage rate of the transported goods is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a method for monitoring the temperature of a refrigerated vehicle according to an embodiment of the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the proposed solution, its specific implementation, structure, features and effects will be made with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 specific scenes aimed by the invention are as follows: in the cold chain logistics industry, a refrigerator car is used as important equipment of cold chain logistics, and whether the temperature in the refrigerator car can be in a fresh-keeping temperature range corresponding to transported goods all the time in the transportation process is a key factor for guaranteeing the quality of the transported goods. Therefore, the actual surface temperature of the transported goods should be monitored in real time and adjusted in the transportation process, so that the transported goods are kept fresh to the maximum extent, and the damage rate of the transported goods is reduced.
Referring to fig. 1, a flow chart illustrating steps of a method for monitoring a temperature of a refrigerator car according to an embodiment of the present invention is shown, the method including the steps of:
step 1, collecting the internal temperature and the distance from each set position in the refrigerator van to a transported object at each detection time in a historical period, and collecting the environmental temperature corresponding to each detection time in the historical period; dividing the distance into a plurality of distance grades; and setting a first surface temperature corresponding to each detection time of the transported object in the historical time.
Specifically, because the distribution of the inside temperature of the refrigerator car is not uniform, corresponding set positions are uniformly arranged on two sides of the inside car body of the refrigerator car, namely, the distance between two adjacent set positions in the set positions corresponding to the same side of the car body is equal, a temperature sensor is respectively arranged at each set position and used for collecting the inside temperature corresponding to each set position at each detection moment in the historical time period, and a temperature sensor is arranged outside the refrigerator car and used for collecting the environment temperature corresponding to each detection moment in the historical time period.
The distance from each set position to the transported object is obtained according to the neural network model, and the specific process is as follows: the method comprises the following steps of installing a camera right above the interior of a refrigerator van, shooting the interior of the refrigerator van by using a wide-angle camera to obtain a corresponding image, inputting the image into a neural network model trained in advance to obtain the distance from each set position to a transported object, further dividing the distance into a plurality of distance grades, and setting the number of the distance grades by an implementer according to actual conditions; wherein the distance is the closest distance of each set position to the transported item, i.e. the vertical distance of each set position to the transported item. The selection of the neural network model is determined by an implementer, and the training process of the neural network model is a known technology and is not described in detail.
It should be noted that the refrigerator car in this embodiment is specially used for transporting single articles, and the articles are placed in the storage box or the storage frame, so that the placement is not neat, and the articles are placed from inside to outside when placed, that is, when the articles are placed well at the innermost position of the carriage and cannot be placed, the articles are placed outwards in sequence; the distance from each set position to the transported article is the distance from each set position to the placed article.
The first surface temperature corresponding to the transported object is set by relevant workers according to human experience based on the collected internal temperature and the collected environmental temperature corresponding to each set position and the distance from each set position to the transported object.
The embodiment is directed to multiple transportation of a plurality of refrigerated vehicles in a historical time period, namely, one refrigerated vehicle completes one transportation from a starting place to a destination, and in the route from the starting place to the destination, the transported goods in the refrigerated vehicle are not increased or reduced; the quantity of transported goods which can be contained by different refrigerated vehicles is different, and the quantity of the corresponding transported goods is also different during each transportation, although the capacities of the different refrigerated vehicles are different, the quantity of the set positions in each refrigerated vehicle is consistent; the distance from each set position to the transported item varies over the history of time. Because the transported goods in the refrigerated truck can not be increased or reduced in the route from the starting place to the destination, when the distance from each set position to the transported goods is obtained, only one time of obtaining is needed in each transportation process, the repeated obtaining of data is avoided, the complexity of the subsequent analysis process is increased, and the accuracy of the analysis result is reduced.
The time interval between two adjacent detection moments is 10 minutes, the implementer can adjust the time interval according to specific conditions, and the specific time length of the historical time period is set by the implementer according to actual conditions.
Step 2, calculating the internal and external temperature difference corresponding to each detection moment according to the internal temperature and the environmental temperature; dividing the internal and external temperature difference into a plurality of temperature difference grades; at least one detection moment is included in one temperature difference grade.
The method for acquiring the internal and external temperature difference comprises the following steps: calculating the average value corresponding to each internal temperature, and recording the difference value between the environment temperature and the average value as the internal and external temperature difference, wherein the calculation formula is as follows:
wherein,the temperature difference between the inside and the outside corresponding to the e-th detection moment,is the ambient temperature corresponding to the e-th detection moment,for the internal temperature corresponding to the kth set position at the e-th detection time,to set the number of positions.
The difference between the temperature in the refrigerator compartment and the external environment temperature is reflected by the internal and external temperature difference, namely, the internal and external temperature difference of the refrigerator car, the temperature difference can influence the temperature in the refrigerator compartment, the influence degree generated by different temperature differences is different, the greater the internal and external temperature difference is, the greater the influence degree on the temperature in the refrigerator compartment is, and therefore the internal and external temperature difference corresponding to each detection moment is calculated according to the environment temperature and the internal temperature, and the influence degree on the temperature in the refrigerator compartment is reflected. The smaller the difference between the average value of the internal temperatures at each set position at a certain detection time and the ambient temperature at that detection time, the smaller the internal-external temperature difference, and the smaller the influence on the temperature in the refrigerator compartment.
Further, dividing all internal and external differences in the historical period into a plurality of temperature difference levels, wherein one temperature difference level at least comprises one internal and external difference, namely one temperature difference level at least comprises one detection moment; the number of temperature difference levels is set by an implementer according to actual conditions.
And 3, calculating second surface temperatures corresponding to the transported articles at all detection moments according to the internal temperatures, and calculating temperature influence values corresponding to all temperature difference grades based on the first surface temperatures and the second surface temperatures corresponding to all detection moments of the transported articles in all temperature difference grades.
The method for calculating the second surface temperature of the transported article at each detection time comprises the following steps: and according to the distance from each set position to the transported object at any detection moment, obtaining the temperature weight corresponding to each internal temperature at the detection moment, and performing weighted summation on the internal temperature and the corresponding temperature weight to obtain a second surface temperature.
The specific method for acquiring the temperature weight comprises the following steps: calculating the distance accumulation sum of the distances corresponding to the detection moment, normalizing the distances according to the distance accumulation sum to ensure that the value of each normalized distance is between 0 and 1, ensuring that the sum of all normalized distances is 1, then calculating the difference value between 1 and each normalized distance, and normalizing the difference value to obtain the temperature weight corresponding to each internal temperature. The calculation formula of the temperature weight is as follows:in the formula (I), the reaction is carried out,the temperature weight of the internal temperature corresponding to the kth set position at the detection moment;is the difference between 1 and the corresponding normalized distance from the k-th set position to the transported item at the detection moment,is the number of the set positions;in the formula (I), wherein,for the distance of the kth set position to the transported item at the moment of detection,is the number of set positions.
The distribution of the internal temperature of the refrigerator compartment is not uniform, the distance from each set position to the transported item at the detection time determines the degree of contribution of the corresponding internal temperature to the calculation of the second surface temperature, and the closer the distance from the set position to the transported item, the closer the internal temperature corresponding to the set position is to the surface temperature of the transported item, the greater the contribution of the internal temperature corresponding to the set position to the calculation of the second surface temperature, the greater the corresponding temperature weight, and conversely, the smaller the contribution of the internal temperature corresponding to the set position to the calculation of the second surface temperature, the smaller the corresponding temperature weight.
Specifically, the temperature influence value is:
whereinIs the temperature influence value corresponding to the temperature difference grade o,the number of detection moments in the temperature difference grade o;for the first surface temperature of the transported item at the jth detection moment in the temperature difference level o,and the corresponding second surface temperature of the transported object at the jth detection time in the temperature difference grade o.
The difference between the first surface temperature and the second surface temperature corresponding to the jth detection time of the transported object in the temperature difference grade o represents the setting accuracy of the first surface temperature corresponding to the transported object, and the larger the difference is, the lower the setting accuracy of the first surface temperature is; the setting accuracy of the first surface temperature corresponding to different detection moments in the same temperature difference grade is approximately the same, and the influence degrees of the different temperature difference grades on the setting accuracy of the first surface temperature are different, so that the average value of the corresponding difference of all the detection moments in the same temperature difference grade is calculated and used as the temperature influence value corresponding to the temperature difference grade, and the acquired data are more accurate when the actual surface temperature of the transported object is subsequently calculated.
And 4, calculating distance accurate values corresponding to the distance grades according to the internal temperature corresponding to each distance grade and the first surface temperature, wherein one distance grade at least comprises one internal temperature.
The method for acquiring the accurate distance value comprises the following steps: all internal temperatures corresponding to the distance grade; calculating the difference value of each internal temperature and the first surface temperature corresponding to the internal temperature; obtaining an accurate distance value according to the difference value, wherein the calculation formula is as follows:
in the formula,for the distance accuracy value corresponding to the distance level y,for the distance class y to correspond to the number of internal temperatures,for the ith internal temperature in the distance class y,a first surface temperature corresponding to the ith internal temperature in the distance class y;is an adjustment factor; the value of the adjustment coefficient in this embodiment is 100, which ensures thatIs sufficiently large thatThe value of (2) is less than 1, and an implementer can set the value of the adjustment coefficient according to specific conditions.
The method for acquiring the first surface temperature corresponding to the internal temperature comprises the following steps: and acquiring the detection time corresponding to the internal temperature in the historical time period, and recording the first surface temperature corresponding to the transported article at the detection time as the first surface temperature corresponding to the internal temperature.
It should be noted that the distance accuracy value represents the accuracy of the corresponding internal temperature representing the surface temperature of the transported object at the distance grade,the difference between the ith internal temperature and the corresponding first surface temperature in the distance grade y is represented, and the smaller the difference is, the higher the accuracy is; conversely, the lower the accuracy; generally, the accuracy of representing the surface temperature of the corresponding transported object by a plurality of internal temperatures in the same distance grade is approximately the same, so the embodiment calculates the average value of the differences in the distance grade to reflect the accurate distance value corresponding to the distance grade.
And 5, calculating the absolute value of the difference between each internal temperature and the corresponding first surface temperature, and calculating the correlation and credibility corresponding to each set position according to the absolute value of the difference.
The correlation corresponding to each set position is as follows:
wherein,for the correlation corresponding to the kth setting position,the absolute value of the difference value between the internal temperature corresponding to the kth set position at the e-th detection moment and the first surface temperature corresponding to the transported object at the e-th detection moment is obtained;the number of detected time instants within the history period,to set the number of positions, the denominator is increased by 1 in order to avoid the case where the denominator is 0 in the formula.
Is a firstThe difference absolute value between the internal temperature corresponding to the k set positions at the e-th detection time and the first surface temperature corresponding to the transported object at the e-th detection time represents the difference between the internal temperature corresponding to the k-th set positions and the first surface temperature corresponding to the transported object, and the larger the difference is, the smaller the correlation between the internal temperature corresponding to the set positions is, namely, the larger the difference between the internal temperature corresponding to the set positions and the first surface temperature of the transported object is; if the difference between the internal temperature corresponding to any one set position and the first surface temperature of the transported object is smaller than the difference between the internal temperature corresponding to other set positions and the first surface temperature of the transported object, the smaller the difference between the internal temperature corresponding to the set position and the first surface temperature of the transported object is, the greater the correlation between the internal temperature corresponding to the set position and the first surface temperature of the transported object is.
The credibility corresponding to each set position is as follows:
wherein,for the reliability of the correspondence of the kth setting position,the absolute value of the difference value between the internal temperature corresponding to the kth set position at the e-th detection moment and the first surface temperature corresponding to the transported object at the e-th detection moment is obtained;the number of detected time instants within the history period,is an exponential function with e as the base.
In the same way as above, the first and second,for the absolute value of the difference between the internal temperature corresponding to the kth set position at the e-th detection time and the first surface temperature corresponding to the transported object at the e-th detection time, obtaining the change condition of the difference between the internal temperature corresponding to the set position and the first surface temperature of the transported object through the absolute value of the difference between all the internal temperatures corresponding to one set position in the historical period and the corresponding first surface temperatures, wherein the smaller the change is, the smaller the difference between the internal temperature corresponding to the set position and the first surface temperature of the transported object is represented, the more accurate the data of the internal temperature corresponding to the set position is obtained, and the greater the credibility corresponding to the set position is; since the absolute value of the difference between the internal temperature corresponding to the set position and the first surface temperature corresponding to the transported object is in a negative correlation with the reliability corresponding to the set position, the present embodiment adoptsThe function determines the reliability corresponding to each set position.
And 6, obtaining weights corresponding to all set positions according to the correlation, the credibility and the accurate distance values, and calculating the actual surface temperature of the transported object corresponding to the current detection time according to the weights, the internal temperature of all the set positions in the refrigerator car corresponding to the current detection time and the temperature influence value to realize the monitoring of the refrigerator car temperature.
Specifically, the method for obtaining the weight includes: forming all distance levels in the historical time period into a distance level set, obtaining the distance from each set position to the transported object at the current detection time, searching the distance level corresponding to each distance in the distance level set and obtaining a corresponding distance accurate value, calculating the product of the relevance, the credibility and the distance accurate value corresponding to each set position, and taking the value after the normalization of the product as the weight corresponding to each set position. For example, the weight corresponding to the kth setting position is:
in the formula,the weight corresponding to the kth setting position,the product of the correlation, the credibility and the accurate value of the distance corresponding to the kth set position;is the number of set positions.Whereinfor the correlation corresponding to the kth setting position,for the reliability of the correspondence of the kth setting position,and when the distance from the kth set position to the transported article is the distance grade x, obtaining the accurate distance value corresponding to the distance grade x.
It should be noted that, in the following description,when the distance from the kth set position to the transported object is the distance grade x, calculating the accurate distance value corresponding to the distance grade x according to the accurate distance value, the correlation and the credibility, and considering the distance from each set position to the transported object to obtain the accuracy rate of the internal temperature of the set position corresponding to the distance, namely the accurate distance value corresponding to the distance, wherein if the accurate distance value is larger, the weight corresponding to the set position is larger; if the correlation corresponding to one set position is larger, calculatingThe weighting of the internal temperature corresponding to the set position is larger when the actual surface temperature of the transport object is measured, and the weighting of the internal temperature corresponding to the set position when the actual surface temperature of the transport object is calculated is larger when the reliability of the corresponding set position is larger. The weight setting is considered from multiple angles, so that the weight is more convincing to obtain, and meanwhile, the actual surface temperature of the transported goods calculated subsequently is more accurate.
The method for calculating the actual surface temperature of the transported goods comprises the following steps: forming all temperature difference levels in a historical period into a temperature difference level set, calculating the internal and external temperature difference corresponding to the current detection moment, searching the temperature difference level corresponding to the internal and external temperature difference in the temperature difference level set and obtaining a corresponding temperature influence value; weighting and summing the internal temperature corresponding to each set position at the current detection time and the weight corresponding to each set position, and adding the obtained temperature influence value to obtain the actual surface temperature of the transported object, wherein the calculation formula is as follows:
wherein,the actual surface temperature of the transported goods at the current detection moment when the corresponding temperature difference grade is the temperature difference grade o,the weight corresponding to the kth setting position,for the internal temperature corresponding to the current detection time at the kth set position,is the temperature influence value corresponding to the temperature difference grade o.
The actual surface temperature of the transported object at the current detection moment is obtained by calculating the weighted sum of the internal temperature corresponding to each set position and the weighted sum of the temperature influence values corresponding to the temperature difference grade of the current detection moment and the weighted sum of the weighted sum and the temperature influence value corresponding to the temperature difference grade of the current detection moment, the influence of different temperature differences of the internal environment and the external environment of the refrigerator compartment on the surface temperature of the transported object is also considered, the obtained actual surface temperature is more accurate, and the quality of the transported object can be guaranteed to the greatest extent.
And further, acquiring the actual surface temperature of the transported objects in the refrigerator van in real time, judging whether the actual surface temperature is in the temperature range for keeping the transported objects fresh, and if not, giving an alarm by the system to remind related workers of adjusting the temperature in the refrigerator van.
As other embodiments, the actual surface temperature of the transported object can also be obtained through the FC neural network; the specific process is as follows:
calculating the actual surface temperature of the transported object corresponding to each detection time in the historical period, obtaining the volume and the heat conductivity of the transported object corresponding to each detection time in the historical period, obtaining the vector corresponding to each detection time in the historical period by using the volume, the heat conductivity, the internal temperature, the environmental temperature and the distance as the multi-dimensional vector, training the FC neural network by using the vector corresponding to each detection time in the historical period and the actual surface temperature of the transported object corresponding to each detection time in the historical period as a data set to obtain the trained FC neural network, obtaining the vector corresponding to the current detection time, inputting the vector into the trained FC neural network, and outputting the actual surface temperature of the transported object corresponding to the current detection time.
Specifically, the volume and the thermal conductivity corresponding to the transported goods are obtained through a neural network model, namely, the image obtained in the step 1 is input into the neural network model trained in advance, and the corresponding volume and the corresponding thermal conductivity are output; wherein the thermal conductivity is not described in detail in the prior art; the loss function of the neural network model is a cross entropy loss function, and the training process of the neural network model is a known technology and is not described in detail. The neural network model is the neural network model in the step 1, namely, the images are input into the neural network model trained in advance, the distance from each set position to the transported object is output, the volume and the heat conductivity corresponding to the transported object are obtained, and only the distance needs to be selected in the step 1 for subsequent analysis, namely, only one neural network model needs to be trained in the embodiment, so that the complexity of operation is reduced.
The corresponding loss function of the FC neural network is:
in the formula,as a function of the loss of the FC neural network,in order to be a function of the cross-entropy loss,as a function of the difference loss.
The difference loss function is:
in the formula,in order to be a function of the difference loss,for the corresponding actual surface temperature in the data set,actual surface temperature output for the FC neural network;in order to take the function of the minimum value,is an exponential function with e as the base.
The difference between the corresponding actual surface temperature in the data set and the actual surface temperature output by the FC neural network is smaller, which indicates that the better the training result of the FC neural network is, and the difference and the loss of the FC neural network present a positive correlation relationship, namely, the smaller the difference is, the smaller the loss of the FC neural network is, the better the training result is; otherwise the worse the training result. Thus, calculated in this embodimentIn the step (1), the first step,andthe result of the calculation of (a) exhibits a negative correlation,is in the range of 0 to 1, and therefore is useful in this embodimentAs a function of the differential loss of the FC neural network, such that the differenceThe loss of the FC neural network is positively correlated.
It should be noted that the loss function corresponding to the FC neural network is obtained through the difference loss function and the cross entropy loss function, so that the training time of the FC neural network is shorter, the training speed is faster, the efficiency of the FC neural network in the training process is improved, and the convergence of the FC neural network is accelerated; the training process of the FC neural network is well known in the art and will not be described in detail.
The invention also provides a refrigerator car temperature monitoring system, which comprises a processor and a memory, wherein the processor executes a program of a refrigerator car temperature monitoring method stored in the memory, and the specific implementation mode of the refrigerator car temperature monitoring method is given in detail in the steps 1 to 6 and is not described in detail.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; the modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application, and are included in the protection scope of the present application.
Claims (7)
1. A method of monitoring the temperature of a refrigerated vehicle, the method comprising the steps of:
collecting the internal temperature and the distance from each set position in the refrigerator van to the transported object at each detection time in the historical period, and collecting the environmental temperature corresponding to each detection time in the historical period; and dividing the distance into a plurality of distance levels; artificially setting a first surface temperature corresponding to each detection time of the transported object in a historical period;
calculating the internal and external temperature difference corresponding to each detection time in the historical time period according to the internal temperature and the environmental temperature; dividing the internal and external temperature difference into a plurality of temperature difference grades; the temperature difference grade at least comprises a detection moment;
calculating a second surface temperature corresponding to each detection time of the transported object in a historical period according to the internal temperature, and calculating a temperature influence value corresponding to each temperature difference grade based on a first surface temperature and a second surface temperature corresponding to each detection time of the transported object in each temperature difference grade;
the second surface temperature obtaining method comprises the following steps: according to the distance corresponding to each internal temperature, obtaining a temperature weight corresponding to each internal temperature, and carrying out weighted summation on the internal temperature and the temperature weight corresponding to the internal temperature to obtain a second surface temperature;
the temperature influence values are:
whereinIs the temperature influence value corresponding to the temperature difference grade o,the number of detection moments in the temperature difference grade o;for the first surface temperature of the transported item at the jth detection moment in the temperature difference level o,a second surface temperature corresponding to the j detection time of the transported object in the temperature difference grade o;
calculating distance accurate values corresponding to the distance grades according to the internal temperature corresponding to the distance grades and the first surface temperature;
the method for acquiring the accurate distance value comprises the following steps: all internal temperatures corresponding to the distance grade; calculating the difference value of each internal temperature and the first surface temperature corresponding to the internal temperature; obtaining an accurate distance value according to the difference value, wherein the calculation formula is as follows:
in the formula,for the distance accuracy value corresponding to the distance level y,the distance level y corresponds to the number of internal temperatures,for the ith internal temperature in the distance class y,a first surface temperature corresponding to the ith internal temperature in the distance grade y;is an adjustment factor;
the method for acquiring the first surface temperature corresponding to the internal temperature comprises the following steps: acquiring the detection time corresponding to the internal temperature in a historical period, and recording the first surface temperature of the transported article corresponding to the detection time as the first surface temperature corresponding to the internal temperature;
calculating the absolute value of the difference between each internal temperature and the corresponding first surface temperature, and calculating the correlation and credibility corresponding to each set position according to the absolute value of the difference;
and according to the correlation, the credibility and the accurate distance value, obtaining the weight corresponding to each set position, and according to the weight, the internal temperature corresponding to each set position at the current detection time and the temperature influence value, calculating the actual surface temperature corresponding to the transported object at the current detection time to realize the monitoring of the temperature of the refrigerated truck.
2. A refrigerator car temperature monitoring method as claimed in claim 1, wherein the calculation method of the difference between the internal and external temperatures is: and calculating the average value corresponding to each internal temperature, and recording the difference value between the environmental temperature and the average value as the internal and external temperature difference.
3. A refrigerator car temperature monitoring method according to claim 1,
the corresponding correlation of each set position is as follows:
wherein,for the correlation corresponding to the kth setting position,the absolute value of the difference value between the internal temperature corresponding to the kth set position at the e-th detection moment and the first surface temperature corresponding to the transported article at the e-th detection moment;the number of detected time instants within the history period,is the number of the set positions;
the credibility corresponding to each set position is as follows:
wherein,for the correlation corresponding to the kth set position,set the position for the kth at the e-th testThe absolute value of the difference value between the internal temperature corresponding to the measuring moment and the first surface temperature corresponding to the transported object at the e-th detecting moment;the number of detected time instants within the history period,is an exponential function with e as the base.
4. A refrigerator car temperature monitoring method as claimed in claim 1, wherein the weight is obtained by: forming all distance levels in the historical time period into a distance level set, obtaining the distance from each set position to the transported object at the current detection time, searching the distance level corresponding to each distance in the distance level set and obtaining a corresponding distance accurate value, calculating the product of the relevance, the credibility and the distance accurate value corresponding to each set position, and taking the value after the normalization of the product as the weight corresponding to each set position.
5. A refrigerator car temperature monitoring method as claimed in claim 1, wherein the method of calculating the actual surface temperature of the transported object at the current detection time is:
forming all temperature difference levels in a historical period into a temperature difference level set, calculating the internal and external temperature difference corresponding to the current detection moment, searching the temperature difference level corresponding to the internal and external temperature difference in the temperature difference level set and obtaining a corresponding temperature influence value; and weighting and summing the internal temperature corresponding to each set position at the current detection time and the weight corresponding to each set position, and adding the obtained temperature influence value to obtain the actual surface temperature corresponding to the transported article at the current detection time.
6. A refrigerator car temperature monitoring method as claimed in claim 1, further comprising obtaining an actual surface temperature of the transported object at a current detection time through an FC neural network; the specific process is as follows:
calculating actual surface temperature corresponding to each detection time of the transported object in a historical period, obtaining volume and heat conductivity corresponding to each detection time of the transported object in the historical period, obtaining a vector corresponding to each detection time in the historical period by using the volume, the heat conductivity, the internal temperature, the environmental temperature and the distance as data sets, training an FC neural network by using the vector corresponding to each detection time in the historical period and the actual surface temperature corresponding to each detection time of the transported object in the historical period as the data sets, obtaining the trained FC neural network, obtaining the vector corresponding to the current detection time, inputting the vector into the trained FC neural network, and outputting the actual surface temperature corresponding to the current detection time of the transported object;
the corresponding loss function of the FC neural network during training is as follows:
in the formula,for the corresponding loss function of the FC neural network during training,in order to be a function of the cross-entropy loss,is a difference loss function;
the difference loss function is:
7. A refrigerator car temperature monitoring system comprising a processor and a memory, wherein the processor executes a program of a refrigerator car temperature monitoring method as claimed in any one of claims 1 to 6 stored in the memory.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210929645.8A CN114996661B (en) | 2022-08-04 | 2022-08-04 | Refrigerator car temperature monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210929645.8A CN114996661B (en) | 2022-08-04 | 2022-08-04 | Refrigerator car temperature monitoring method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114996661A CN114996661A (en) | 2022-09-02 |
CN114996661B true CN114996661B (en) | 2022-11-01 |
Family
ID=83021184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210929645.8A Active CN114996661B (en) | 2022-08-04 | 2022-08-04 | Refrigerator car temperature monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114996661B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116757534B (en) * | 2023-06-15 | 2024-03-15 | 中国标准化研究院 | Intelligent refrigerator reliability analysis method based on neural training network |
CN116701983B (en) * | 2023-08-03 | 2023-10-20 | 青岛冠成软件有限公司 | Cold-chain logistics real-time monitoring data processing method and system |
CN118032395B (en) * | 2024-04-15 | 2024-06-07 | 江苏星星冷链科技有限公司 | Ultralow temperature refrigerator storage effect evaluation method and system based on temperature detection |
CN118428841A (en) * | 2024-07-05 | 2024-08-02 | 浪潮智慧供应链科技(山东)有限公司 | Cargo state early warning method and system for cold chain logistics |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107146050A (en) * | 2017-04-24 | 2017-09-08 | 南京农业大学 | A kind of cold chain transportation environmental forecasting method and system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9384458B2 (en) * | 2011-10-13 | 2016-07-05 | Thermo King Corporation | Auto configuration of refrigeration systems in cold chain |
CN107826027B (en) * | 2017-09-21 | 2019-09-03 | 山东大学 | Refrigerator car temprature control method and system based on big data analysis |
CN111157898A (en) * | 2020-01-07 | 2020-05-15 | 清华大学深圳国际研究生院 | New energy vehicle online battery fault detection and analysis method and device |
US20210312261A1 (en) * | 2020-04-02 | 2021-10-07 | Huawei Technologies Co., Ltd. | Neural network search method and related apparatus |
CN113988262A (en) * | 2021-10-28 | 2022-01-28 | 重庆大学 | Cold-chain logistics temperature prediction method and temperature regulation and control method |
-
2022
- 2022-08-04 CN CN202210929645.8A patent/CN114996661B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107146050A (en) * | 2017-04-24 | 2017-09-08 | 南京农业大学 | A kind of cold chain transportation environmental forecasting method and system |
Also Published As
Publication number | Publication date |
---|---|
CN114996661A (en) | 2022-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114996661B (en) | Refrigerator car temperature monitoring method and system | |
CN116383450B (en) | Railway and highway logistics transportation information comprehensive management system | |
KR100277219B1 (en) | System for monitoring refrigerant charge | |
CN113378890B (en) | Lightweight pedestrian vehicle detection method based on improved YOLO v4 | |
CN114912852A (en) | Abnormity monitoring and early warning system for storage tank of refrigeration bin | |
CN116701983B (en) | Cold-chain logistics real-time monitoring data processing method and system | |
CN112985494A (en) | Cold chain wisdom logistics transportation on-line real-time supervision cloud platform based on big data and artificial intelligence | |
CN118014166B (en) | Load prediction method and system of heating system based on big data | |
CN115713162A (en) | Distributed low-carbon energy station health state early warning prediction method | |
CN114590329A (en) | Multi-temperature-zone cold chain transport carriage system | |
CN116972913B (en) | On-line monitoring method and system for running state of cold chain equipment | |
CN116717938B (en) | Method and system for detecting and controlling internal environment of refrigerator | |
CN110657836B (en) | Monitoring system and monitoring method for fresh food transportation intelligent logistics box | |
CN116090939B (en) | Artificial intelligence-based method for identifying and tracking problem products in supply chain | |
CN117217667A (en) | Intelligent dispatching platform for refrigeration house based on Internet of things | |
CN113253275B (en) | Rainfall estimation method based on improved RBF neural network | |
CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
CN115049996B (en) | Double-sensor target detection fusion method and system based on evidence reasoning rule | |
CN113780462A (en) | Vehicle detection network establishment method based on unmanned aerial vehicle aerial image and application thereof | |
JPH0875437A (en) | Device and method for judgment of the same target | |
CN117993589B (en) | Intelligent cold chain logistics scheduling method and system based on Internet of things | |
CN117893121B (en) | System and method for monitoring article transportation state by utilizing artificial intelligence | |
CN116993010B (en) | Fixed wing unmanned aerial vehicle situation prediction method based on Bayesian neural network | |
CN116663753B (en) | Cold chain food distribution prediction method and system | |
CN117635009B (en) | Intelligent monitoring method, system, equipment and storage medium for cold chain transportation |
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 |