Intelligent pallet cold chain transportation monitoring system based on Internet of Things technology

Abstract

The present invention relates to the field of data processing technology, and specifically to an intelligent pallet cold chain transportation monitoring system based on Internet of Things technology. The system screens out abnormal segments and abnormal areas from all curve segments of the temperature-time curve of each area according to several curve segments with similar temperature changes in each area; screens out several areas that need maintenance according to the temperature abnormality degree of each curve segment before the abnormal segment of the temperature-time curve of each abnormal area and each temperature data; obtains the intelligent pallet cold chain transportation monitoring results according to the abnormal degree of the refrigeration effect of each area that needs maintenance and the temperature abnormality degree of each curve segment. The present invention screens out temperature abnormal areas by comparing the differences in temperature changes in different areas in a cold chain transport vehicle, and judges whether the abnormal area needs maintenance according to the degree to which the abnormal area returns to normal after temperature control, thereby improving the accuracy of identifying abnormal refrigeration effect areas.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent pallet cold chain transportation monitoring system based on Internet of Things technology. Background Art

[0002] At present, the market scale of cold chain logistics is constantly expanding, and the cold chain transportation process needs to meet high-efficiency and high-standard temperature control. Therefore, it is very important to monitor the temperature in the transport box during transportation. The monitoring system needs to promptly determine whether the temperature is abnormal in the current state and perform corresponding maintenance processing for different abnormal situations. However, the current informatization supervision of cold chain transportation is relatively weak. During transportation, there may be unsatisfactory sealing effect of the cold chain transport vehicle or high stacking density of items in the transport vehicle, resulting in uneven temperature distribution in the transport vehicle, and there are areas with poor refrigeration effect, which leads to increased burden on refrigeration equipment, increased refrigeration costs, and deterioration of goods in the cold chain transport vehicle. In severe cases, it may even cause damage to the quality of the equipment. Therefore, it is very necessary to accurately and timely monitor the temperature in the cold chain transport vehicle. During cold chain transportation, there may be uneven temperature distribution in the refrigeration box, resulting in poor refrigeration effect in a certain area. The existing technology sets a temperature sensor for a single pallet and sets a fixed threshold to determine whether the temperature of a single pallet area meets the standard. If it does not meet the standard, an alarm is issued and the corresponding area is maintained. However, in actual operation, the existing technology method for obtaining abnormal areas that need maintenance is not accurate enough. When the temperature of each area is abnormal, it often interferes with the temperature of the surrounding areas. Therefore, if only a fixed threshold is set to determine whether the temperature of a single pallet area meets the standard, abnormal temperatures in other areas may not be detected, thereby reducing the accuracy of temperature monitoring during the cold chain transportation of smart pallets. Summary of the invention

[0003] The present invention provides an intelligent pallet cold chain transportation monitoring system based on Internet of Things technology to solve the existing problems.

[0004] The intelligent pallet cold chain transportation monitoring system based on Internet of Things technology of the present invention adopts the following technical solutions:

[0005] An embodiment of the present invention provides an intelligent pallet cold chain transportation monitoring system based on Internet of Things technology, which includes the following modules:

[0006] Data acquisition module: used to obtain the original output power in the cold chain transport vehicle and the temperature data of each area in the cold chain transport vehicle at each moment, construct the temperature-time curve of each area, segment the temperature-time curve of each area, obtain several curve segments and the approximate temperature value of each curve segment;

[0007] Abnormal degree acquisition module of cooling effect: used to obtain the abnormal degree of temperature of each curve segment in the temperature-time curve of each area according to each temperature data in each curve segment in the temperature-time curve of each area and the approximate temperature value of each curve segment; select several abnormal areas from all areas according to the abnormal degree of temperature of each curve segment in the temperature-time curve of each area; obtain the abnormal degree of cooling effect of each abnormal area according to the abnormal degree of temperature of each curve segment in the temperature-time curve of each abnormal area and each temperature data in each curve segment;

[0008] Monitoring result acquisition module: used to obtain the updated temperature-time curve of each abnormal area according to the abnormal degree of the refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle; obtain the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area according to the method of obtaining the temperature abnormality of each curve segment in the temperature-time curve of each area; obtain the pallet cold chain transportation monitoring result according to the abnormal degree of the refrigeration effect of each abnormal area, the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area and each temperature data in each curve segment.

[0009] Further, obtaining the temperature anomaly degree of each curve segment in the temperature-time curve of each region according to each temperature data in each curve segment in the temperature-time curve of each region and the approximate temperature value of each curve segment includes:

[0010] The approximate temperature value of each curve segment is obtained by an adaptive piecewise constant approximation algorithm;

[0011] According to each temperature data in each curve segment in the temperature-time curve of each region, the approximate temperature value of each curve segment and the duration, the fluctuation index of the last curve segment in the temperature-time curve of each region is obtained;

[0012] According to the fluctuation index of each curve segment in the temperature-time curve of each area and each temperature data in each curve segment, the temperature anomaly degree of the last curve segment in the temperature-time curve of each area is obtained.

[0013] Furthermore, the specific calculation formula for obtaining the fluctuation index of the last curve segment in the temperature-time curve of each region according to each temperature data in each curve segment in the temperature-time curve of each region, the approximate temperature value of each curve segment and the duration is:

[0014]

[0015] in, Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates The average duration of all curve segments in the temperature-time curve of a region, Indicates The duration of the last curve segment in the temperature-time curve of a region, Indicates The approximate temperature value of the last curve segment in the temperature-time curve of the region, Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, represents the absolute value function.

[0016] Furthermore, according to the fluctuation index of each curve segment in the temperature-time curve of each region and each temperature data in each curve segment, the specific calculation formula for obtaining the temperature anomaly degree of the last curve segment in the temperature-time curve of each region is:

[0017]

[0018] in, Indicates The temperature anomaly degree of the last curve segment in the temperature-time curve of a region is Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates that except The average value of the fluctuation index of the last curve segment in the temperature-time curve of all regions other than the region, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, Indicates the number of regions. Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates that except The temperature-time curve of the region The last curve segment of the temperature-time curve of the area Temperature data, represents the absolute value function, represents the linear normalization function.

[0019] Furthermore, the method of screening out a number of abnormal areas from all areas according to the temperature anomaly degree of each curve segment in the temperature-time curve of each area includes:

[0020] When When the temperature anomaly degree of the last curve segment in the temperature-time curve of the region is greater than the first judgment threshold, it is determined that the The area is an abnormal area.

[0021] Further, the abnormal degree of the refrigeration effect of each abnormal area is obtained according to the temperature abnormal degree of each curve segment of the temperature-time curve of each abnormal area and each temperature data in each curve segment, including:

[0022] The first The curve segment with the positive corresponding data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the temperature-time curve of the abnormal area is recorded as The main reference curve segment of the abnormal area;

[0023] The first The ordinal value of the last curve segment in the temperature-time curve of the abnormal area is recorded as the target ordinal value;

[0024] According to the number of main reference curve segments in the temperature-time curve of each abnormal area, the temperature abnormality degree of each curve segment and each temperature data in each curve segment, the specific calculation formula for the abnormality degree of the cooling effect of each abnormal area is obtained as follows:

[0025]

[0026] in, Indicates The abnormal degree of cooling effect in each abnormal area, Indicates The number of main reference curve segments in the temperature-time curve of the abnormal area, Indicates The mean of all data in the first-order difference series of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, Indicates The average value of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, It represents the average of the temperature anomaly degree of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions. Indicates The mean of all temperature data of all curve segments of the temperature-time curve of the abnormal area, Represents the mean of all temperature data of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions, represents the linear normalization function.

[0027] Furthermore, obtaining an updated temperature-time curve of each abnormal area according to the abnormal degree of the refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle includes:

[0028] Calculate the sum of the average of the abnormal degrees of the refrigeration effects of all abnormal areas plus 1, and multiply the sum by the original output power in the cold chain transport vehicle to record it as the adjusted output power;

[0029] Continue to collect temperature data of each area at each moment in the preset time period after the adjusted output power, and construct an updated temperature-time curve.

[0030] Further, the monitoring result of the cold chain transportation of the pallet is obtained according to the abnormal degree of the refrigeration effect of each abnormal area, the abnormal degree of the temperature of each curve segment in the updated temperature-time curve of each abnormal area, and each temperature data in each curve segment, including:

[0031] According to the distance between each abnormal area and the abnormal degree of the cooling effect of each abnormal area, several abnormal groups are obtained;

[0032] The first The curve segment corresponding to the negative data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the updated temperature-time curve of the abnormal area is recorded as A reference curve segment for the abnormal area;

[0033] According to the number of reference curve segments in the updated temperature-time curve of each abnormal area, the abnormal degree of the cooling effect of each abnormal area in the abnormal group to which each abnormal area belongs, and each temperature data, the degree to which the last curve segment in the updated temperature-time curve of each abnormal area needs maintenance is obtained;

[0034] The last curve segment in the updated temperature-time curve of each abnormal area, whose maintenance requirement is greater than a preset second judgment threshold, is recorded as a curve segment requiring maintenance;

[0035] The abnormal area corresponding to the updated temperature-time curve of the curve segment requiring maintenance is recorded as the area requiring maintenance;

[0036] Calculate the The degree of maintenance required for the last curve segment in the updated temperature-time curve of the area requiring maintenance is the same as that of the first The product of the mean of all temperature data in the last curve segment of the updated temperature-time curve of the area to be maintained, and the normalized value of the ratio of the product to the mean of all temperature data in the last curve segment of the updated temperature-time curve in all areas is recorded as the first The maintenance factor of the area that needs maintenance;

[0037] An alarm is issued for an area where the maintenance coefficient is greater than the preset third judgment threshold, and no alarm is issued for an area where the maintenance coefficient is less than or equal to the preset third judgment threshold.

[0038] Furthermore, according to the distance between each abnormal area and the abnormal degree of the cooling effect of each abnormal area, several abnormal groups are obtained, including:

[0039] The product of the distance between any two abnormal areas and the absolute value of the difference in the abnormal degree of the cooling effect of any two abnormal areas is taken as the clustering distance between any two abnormal areas. The K-means clustering algorithm is used to cluster all abnormal areas to obtain several final clusters.

[0040] All abnormal regions in each final cluster are grouped into an abnormal group, and several abnormal groups are obtained.

[0041] Furthermore, according to the number of reference curve segments in the updated temperature-time curve of each abnormal area, the abnormal degree of the refrigeration effect of each abnormal area in the abnormal group to which each abnormal area belongs, and each temperature data, a specific calculation formula for obtaining the degree to which the last curve segment in the updated temperature-time curve of each abnormal area needs maintenance is obtained:

[0042]

[0043] in, Indicates The degree to which the last curve segment in the updated temperature-time curve of the abnormal area needs maintenance, Indicates The average value of all temperature data in the last curve segment of the updated temperature-time curve of the abnormal area, Represents the mean value of all temperature data in the last curve segment of the updated temperature-time curve of all regions. For the The number of reference curve segments in the updated temperature-time curve of the abnormal area, For the The abnormal degree of cooling effect of all abnormal areas in the abnormal group where the abnormal area belongs is the same as that of the first abnormal area. The average of the absolute values ​​of the differences in the abnormal degree of cooling effect in the abnormal areas, For the The abnormal degree of cooling effect in each abnormal area, Indicated in Among all the abnormal areas in the abnormal group where the abnormal area belongs, the abnormal degree of cooling effect is higher than that of the abnormal area. The number of areas with small abnormal cooling effect in abnormal areas, Indicates The mean of all temperature data in the updated temperature-time curves of all abnormal regions in the abnormal group where the abnormal region belongs, represents the mean of all temperature data in the updated temperature-time curves of all abnormal areas in all abnormal groups, represents the linear normalization function, represents the normalization function, represents the absolute value function.

[0044] The beneficial effects of the technical solution of the present invention are:

[0045] In the embodiment of the present invention, the temperature anomaly degree of each curve segment in the temperature-time curve of each area is obtained; according to the temperature anomaly degree of each curve segment in the temperature-time curve of each area, the abnormal segment is screened out from all the curve segments of the temperature-time curve of each area, and the abnormal degree of the refrigeration effect of each abnormal area is obtained. According to the segmentation of the temperature-time curve of each area, the comprehensive analysis of the temperature data is guaranteed, and the accuracy of the abnormal detection is improved; the fine segmentation of the temperature curve is realized, and the ability to capture the temperature change characteristics is improved; by calculating the temperature anomaly degree, the efficiency of the abnormal area identification is improved; the temperature data before and after the abnormal segment is comprehensively considered, and the comprehensiveness and accuracy of the evaluation of the abnormal degree of the refrigeration effect are improved. According to the abnormal degree of the refrigeration effect of each abnormal area, the temperature anomaly degree of each curve segment in the temperature-time curve of each abnormal area, and each temperature data in each curve segment, the monitoring result of the cold chain transportation of the intelligent pallet is obtained. So far, the present invention screens the temperature abnormal area by comparing the difference in temperature changes in different areas in the cold chain transport vehicle, and judges whether the abnormal area needs maintenance according to the degree to which the abnormal area returns to normal after temperature regulation, thereby improving the accuracy of the identification of the abnormal refrigeration effect area. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1This is a module flow chart of the intelligent pallet cold chain transportation monitoring system based on the Internet of Things technology of the present invention;

[0048] Figure 2 This is a flow chart for obtaining the monitoring results of cold chain transportation of pallets in this embodiment. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of the intelligent pallet cold chain transportation monitoring system based on the Internet of Things technology proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] 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.

[0051] The specific scheme of the intelligent pallet cold chain transportation monitoring system based on Internet of Things technology provided by the present invention is described in detail below with reference to the accompanying drawings.

[0052] See also Figure 1 , which shows a module flow chart of an intelligent pallet cold chain transportation monitoring system based on Internet of Things technology provided by an embodiment of the present invention, the system includes the following modules:

[0053] Module 101: Data acquisition module.

[0054] This module is used to obtain the original output power in the cold chain transport vehicle and the temperature data of each area in the cold chain transport vehicle at each moment, construct the temperature-time curve of each area, segment the temperature-time curve of each area, and obtain several curve segments and the approximate temperature value of each curve segment.

[0055] A temperature sensor is set at the position of each pallet in the cold chain transport vehicle. The temperature sensor is used to obtain the original output power in the cold chain transport vehicle, the temperature data of each area in the cold chain transport vehicle at each moment, and the distance between each area. A rectangular coordinate system is constructed with the direction of temperature rise as the vertical axis and time as the horizontal axis. The temperature data collected in each area are arranged in the rectangular coordinate system according to the time sequence, and the temperature-time curve of each area is obtained by connecting them point by point according to the time sequence.

[0056] What needs to be explained is: In the actual transportation process, the temperature in different areas may be different due to the density of cargo stacking hindering air circulation or the poor sealing effect of the cold chain transport vehicle. In order to analyze the temperature changes at a certain location during transportation, the temperature changes at different locations in the transport box during the cold chain transportation process are recorded from the moment the cargo is loaded. The power adjustment judgment is performed every hour, and the collection frequency is once every 5 seconds. This is used as an example for description.

[0057] Since the temperature in different areas of the cold chain transport vehicle may be different, and since the heat dissipation capabilities of different areas are different, the degree of temperature change in different areas will also vary over time. Therefore, in order to obtain the temperature change trend of the area where a single pallet is located at different times, the temperature-time curve of a single area is segmented.

[0058] The Adaptive Piecewise Constant Approximation (APCA) algorithm is used to The temperature-time curve of each region is segmented to obtain a number of curve segments, and the approximate temperature value of each curve segment is obtained by an adaptive piecewise constant approximation algorithm.

[0059] It should be noted that the adaptive piecewise constant approximation algorithm is a well-known technology and the specific method will not be introduced here.

[0060] According to the obtained The time periods corresponding to the several curve segments of the temperature-time curve of the region will be The temperature-time curves of all areas except the area are segmented.

[0061] At this point, the number of curve segments in the temperature-time curve of each region is the same, and the number of temperature data in the same time period is also the same.

[0062] Module 102: Module for obtaining the abnormal degree of cooling effect.

[0063] This module is used to obtain the degree of temperature anomaly of each curve segment in the temperature-time curve of each area according to each temperature data in each curve segment in the temperature-time curve of each area and the approximate temperature value of each curve segment; according to the degree of temperature anomaly of each curve segment in the temperature-time curve of each area, screen out several abnormal areas from all areas; according to the degree of temperature anomaly of each curve segment of the temperature-time curve of each abnormal area and each temperature data in each curve segment, obtain the degree of abnormality of the cooling effect of each abnormal area.

[0064] First Take the last curve segment of the temperature-time curve of a region as an example, then The calculation formula for the fluctuation index of the last curve segment in the temperature-time curve of a region is:

[0065]

[0066] in, Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates The average duration of all curve segments in the temperature-time curve of a region, Indicates The duration of the last curve segment in the temperature-time curve of a region, Indicates The approximate temperature value of the last curve segment in the temperature-time curve of the region, Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, represents the absolute value function.

[0067] According to the above method, the fluctuation index of all curve segments in the temperature-time curve of each region can be obtained.

[0068] Since the temperature inside the transport box is affected by internal and external factors, the temperature distribution in different locations is uneven. Internal factors: Due to the attenuation of temperature transfer in space, the temperature of the area close to the air outlet drops faster during refrigeration, and vice versa. In addition, the accumulation of items in the transport box hinders the circulation of cold air, resulting in uneven temperature distribution in different areas; External factors: There are external factors such as poor sealing effect of the cold chain transport box, which leads to leakage of cold air in the transport box, resulting in uneven temperature distribution in the cold chain transport box. The refrigeration effect may be poor in a certain area (temperature abnormality). Therefore, by comparing the curves of different areas, the curve segments with abnormal temperatures are screened.

[0069] First Take the last curve segment of the temperature-time curve of a region as an example. The last curve segment of the temperature-time curve of the region is The greater the temperature difference in the last curve segment of the temperature-time curve of all regions other than the first region, the greater the difference in fluctuation degree, indicating that the The more abnormal the last curve segment in the temperature-time curve of a region is.

[0070] First Take the last curve segment of the temperature-time curve of a region as an example, then The calculation formula for the temperature anomaly degree of the last curve segment in the temperature-time curve of a region is:

[0071]

[0072] in, Indicates The temperature anomaly degree of the last curve segment in the temperature-time curve of a region is Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates that except The average value of the fluctuation index of the last curve segment in the temperature-time curve of all regions other than the region, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, Indicates the number of regions. Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates that except The temperature-time curve of the region The last curve segment of the temperature-time curve of the area Temperature data, represents the absolute value function, represents the linear normalization function.

[0073] What needs to be explained is: Indicates The last curve segment of the temperature-time curve of the region is The difference in the mean of the fluctuation index of the last curve segment in the temperature-time curve of all other regions outside the first region is greater than that of the second region. The greater the degree of fluctuation of the last curve segment in the temperature-time curve of a region deviates from the whole, the greater the abnormality of the curve segment. It indicates the mean temperature difference between different areas in the same period. The larger the mean, the higher the The greater the difference between the last curve segment in the temperature-time curve of a region and the overall temperature, the greater the abnormality of the curve segment.

[0074] According to the method of obtaining the temperature anomaly degree of the last curve segment in the temperature-time curve of each region, the temperature anomaly degree of each curve segment in the temperature-time curve of each region is obtained.

[0075] Preset the first judgment threshold, when the When the temperature anomaly degree of the last curve segment in the temperature-time curve of the region is greater than the first judgment threshold, it is determined that the The first area is the abnormal area, and the last curve segment is the abnormal segment.

[0076] It should be noted that: the preset judgment threshold in this embodiment is 0.5, and this is taken as an example for description.

[0077] Ideally, the refrigeration system in cold chain transport vehicles can cool different locations in the vehicle to the same degree and with good effect, but in actual operation, some areas have poor cooling effect. The greater the degree of interference with the cooling effect of a certain area (interference caused by factors such as the distance of the area from the air-conditioning outlet, the density of goods, and poor sealing effect), the faster the temperature changes, and the period before the temperature abnormality occurs has a gradually increasing degree of abnormality (that is, although the cooling effect of the curve segment before the abnormal segment is qualified, as the time sequence increases, its cooling effect continues to approach the abnormal process).

[0078] Therefore, the abnormal degree of the refrigeration effect of each abnormal area is obtained by analyzing the changing trend of the abnormal degree in the abnormal section and the time period before the abnormal section in the temperature-time curve of each abnormal area.

[0079] First Take the temperature-time curve of an abnormal area as an example. The temperature anomaly degree of each curve segment in the temperature-time curve of the abnormal area gradually increases. The greater the degree to which the temperature of an abnormal area is affected by interference factors, the greater the degree of cooling abnormality in the abnormal area in the current state.

[0080] The first The curve segment with the positive corresponding data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the temperature-time curve of the abnormal area is recorded as The main reference curve segment of the abnormal area;

[0081] The first The ordinal value of the last curve segment in the temperature-time curve of the abnormal area is recorded as the target ordinal value.

[0082] First For example, the abnormal area The calculation formula for the abnormal degree of the cooling effect of each abnormal area is:

[0083]

[0084] in, Indicates The abnormal degree of cooling effect in each abnormal area, Indicates The number of main reference curve segments in the temperature-time curve of the abnormal area, Indicates The mean of all data in the first-order difference series of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, Indicates The average value of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, It represents the average of the temperature anomaly degree of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions. Indicates The mean of all temperature data of all curve segments of the temperature-time curve of the abnormal area, Represents the mean of all temperature data of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions, represents the linear normalization function.

[0085] Module 103: Monitoring result acquisition module.

[0086] This module is used to obtain the updated temperature-time curve of each abnormal area according to the abnormal degree of the refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle; obtain the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area according to the method of obtaining the temperature abnormality of each curve segment in the temperature-time curve of each area; obtain the pallet cold chain transportation monitoring results according to the abnormal degree of the refrigeration effect of each abnormal area, the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area and each temperature data in each curve segment.

[0087] Since temperature is conducted in space, the abnormal area will also affect the temperature of the surrounding area. In order to accurately obtain the abnormal area, the obtained abnormal areas are grouped, that is, the areas with adjacent positions and similar abnormal degrees of cooling effects are grouped together and the abnormal degrees of the corresponding groups are obtained.

[0088] The product of the distance between any two abnormal areas and the absolute value of the difference in the abnormal degree of the cooling effect of any two abnormal areas is taken as the clustering distance between any two abnormal areas. The K-means clustering algorithm is used to cluster all abnormal areas to obtain several final clusters.

[0089] All abnormal regions in each final cluster are grouped into an abnormal group, and several abnormal groups are obtained.

[0090] It should be noted that the number of clusters when performing clustering operations on all abnormal regions is obtained using the elbow method. Both the K-means clustering algorithm and the elbow method are well-known technologies, and the specific methods are not introduced here.

[0091] Calculate the sum of the average of the abnormal degrees of refrigeration effects of all abnormal areas plus 1, and multiply the sum by the original output power in the cold chain transport vehicle, which is recorded as the adjusted output power.

[0092] According to the above method, the temperature data of each area at each moment in the preset time period after the adjusted output power is continuously collected to construct an updated temperature-time curve (which does not include the original temperature-time curve).

[0093] It should be noted that: in this embodiment, the preset time period is 1 hour, and this is used as an example for description.

[0094] At this point, according to the abnormal degree of the refrigeration effect, the output power of the refrigeration equipment is adjusted through the automatic temperature adjustment system in the cold chain transport vehicle to achieve temperature control.

[0095] Since there are some areas where the cooling effect is significantly improved after temperature control (the area may be an area with poor heat dissipation due to occasional factors such as excessive cargo stacking density, and the temperature of the area can gradually return to normal after temperature control with sequential growth, and it will be relatively stable), there may be areas in the abnormal areas obtained in the above steps that do not require maintenance, and the cooling effect can be restored to normal after intervention by the automatic temperature control system. There is no need to alarm for these abnormalities. Areas where the cooling effect cannot be restored to normal after temperature control require human intervention (timely maintenance, etc.).

[0096] Therefore, by detecting the temperature change in the period after the output power is adjusted, that is, according to whether there is a trend of gradually improving the cooling effect in a certain abnormal area relative to the abnormal period, it is further analyzed whether the area is an abnormal area that needs maintenance.

[0097] According to the method of obtaining the temperature anomaly degree of each curve segment in the temperature-time curve of each region, the temperature anomaly degree of each curve segment in the updated temperature-time curve of each abnormal region is obtained.

[0098] The first The curve segment corresponding to the negative data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the updated temperature-time curve of the abnormal area is recorded as The reference curve segment of the abnormal area.

[0099] First Take the last curve segment of the updated temperature-time curve of the abnormal area as an example, then The calculation formula for the degree of maintenance required for the last curve segment in the updated temperature-time curve of an abnormal area is:

[0100]

[0101] in, Indicates The degree to which the last curve segment in the updated temperature-time curve of the abnormal area needs maintenance, Indicates The average value of all temperature data in the last curve segment of the updated temperature-time curve of the abnormal area, Represents the mean value of all temperature data in the last curve segment of the updated temperature-time curve of all regions. For the The number of reference curve segments in the updated temperature-time curve of the abnormal area, For the The abnormal degree of cooling effect of all abnormal areas in the abnormal group where the abnormal area belongs is the same as that of the first abnormal area. The average of the absolute values ​​of the differences in the abnormal degree of cooling effect in the abnormal areas, For the The abnormal degree of cooling effect in each abnormal area, Indicated in Among all the abnormal areas in the abnormal group where the abnormal area belongs, the abnormal degree of cooling effect is higher than that of the abnormal area. The number of areas with small abnormal cooling effect in abnormal areas, Indicates The mean of all temperature data in the updated temperature-time curves of all abnormal regions in the abnormal group where the abnormal region belongs, represents the mean of all temperature data in the updated temperature-time curves of all abnormal areas in all abnormal groups, represents the linear normalization function, represents the normalization function, represents the absolute value function.

[0102] What needs to be explained is: Indicates The number of areas in the updated temperature-time curves of all abnormal areas in the abnormal group where the abnormal area is located, where the abnormal degree of the cooling effect of the last curve segment is smaller than the abnormal degree of the cooling effect of the abnormal segment, the greater the number, the higher the number. The more effective the temperature control of the abnormal group in which the abnormal area belongs, Indicates The greater the difference between the temperature of each area and the average temperature of all areas in the car, the more it deviates from the normal state. Represents the mean of all temperature data in the updated temperature-time curves of all anomaly areas in all anomaly groups. The larger the The lower the temperature of the abnormal group where the abnormal area is located relative to all abnormal groups, that is, the better the corresponding degree of temperature control is, the less maintenance is required.

[0103] According to the above method, the degree to which the last curve segment in the updated temperature-time curve of each abnormal area needs maintenance can be obtained.

[0104] A second judgment threshold is preset, and the curve segment whose maintenance requirement of the last curve segment in the updated temperature-time curve of each abnormal area is greater than the preset second judgment threshold is recorded as the curve segment requiring maintenance.

[0105] The abnormal area corresponding to the updated temperature-time curve where there is a curve segment requiring maintenance is recorded as the area requiring maintenance.

[0106] It should be noted that: the second judgment threshold preset in this embodiment is 0.5, and this is taken as an example for description.

[0107] The maintenance coefficient is set according to the degree of maintenance required for the last curve segment in the updated temperature-time curve of each abnormal area, and the area where the alarm information needs to be set is screened. That is, the greater the degree of maintenance required, the greater the maintenance coefficient, and the greater the difference between the current temperature and the average temperature, the more abnormal the area is, and the greater the maintenance coefficient.

[0108] First For example, if the area to be maintained The calculation formula for the maintenance factor of an area that needs maintenance is:

[0109]

[0110] in, For the The maintenance factor of the area that needs maintenance, Indicates The average value of all temperature data in the last curve segment of the updated temperature-time curve of the area that needs maintenance, Represents the mean value of all temperature data in the last curve segment of the updated temperature-time curve in all regions. Indicates The degree to which the last curve segment in the updated temperature-time curve of the area requiring maintenance needs maintenance. represents the linear normalization function.

[0111] A third judgment threshold is preset, and an alarm is issued for areas where the maintenance coefficient is greater than the preset third judgment threshold. For areas where the maintenance coefficient is less than or equal to the preset third judgment threshold, only the temperature and maintenance coefficient value of the current area are displayed on the monitoring device, and no alarm is issued.

[0112] It should be noted that: alarms are issued for areas with a large maintenance coefficient, which facilitates timely maintenance by staff and enables efficient operation of cold chain transportation. In this embodiment, the third judgment threshold is preset to 0.5, which is used as an example for description. Among them, the acquisition process of the pallet cold chain transportation monitoring results is as follows Figure 2 shown.

[0113] So far, the present invention is completed.

[0114] In summary, in an embodiment of the present invention, the original output power in the cold chain transport vehicle and the temperature data of each area in the cold chain transport vehicle at each moment are obtained, a temperature-time curve of each area is constructed, and the temperature-time curve of each area is segmented to obtain a plurality of curve segments and an approximate temperature value of each curve segment; according to each temperature data in each curve segment in the temperature-time curve of each area and the approximate temperature value of each curve segment, the temperature anomaly degree of each curve segment in the temperature-time curve of each area is obtained; according to the temperature anomaly degree of each curve segment in the temperature-time curve of each area, a plurality of abnormal areas are screened out from all areas; according to each temperature data in the temperature-time curve of each abnormal area, the temperature anomaly degree of each curve segment in the temperature-time curve of each area is obtained. The abnormal degree of temperature of each curve segment and each temperature data in each curve segment are used to obtain the abnormal degree of refrigeration effect of each abnormal area; according to the abnormal degree of refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle, the updated temperature-time curve of each abnormal area is obtained; according to the acquisition method of the temperature abnormality of each curve segment in the temperature-time curve of each area, the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area is obtained; according to the abnormal degree of refrigeration effect of each abnormal area, the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area, and each temperature data in each curve segment, the cold chain transport monitoring result of the pallet is obtained. The present invention screens the temperature abnormal area by comparing the difference in temperature changes in different areas in the cold chain transport vehicle, and judges whether the abnormal area needs maintenance according to the degree to which the abnormal area returns to normal after temperature regulation, thereby improving the accuracy of identifying the abnormal refrigeration effect area.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Intelligent pallet cold chain transportation monitoring system based on Internet of Things technology, characterized by: The system includes the following modules: Data acquisition module: used to obtain the original output power in the cold chain transport vehicle and the temperature data of each area in the cold chain transport vehicle at each moment, construct the temperature-time curve of each area, segment the temperature-time curve of each area, obtain several curve segments and the approximate temperature value of each curve segment; Abnormal degree acquisition module of cooling effect: used to obtain the abnormal degree of temperature of each curve segment in the temperature-time curve of each area according to each temperature data in each curve segment in the temperature-time curve of each area and the approximate temperature value of each curve segment; select several abnormal areas from all areas according to the abnormal degree of temperature of each curve segment in the temperature-time curve of each area; obtain the abnormal degree of cooling effect of each abnormal area according to the abnormal degree of temperature of each curve segment in the temperature-time curve of each abnormal area and each temperature data in each curve segment; Monitoring result acquisition module: used to obtain the updated temperature-time curve of each abnormal area according to the abnormal degree of the refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle; obtain the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area according to the acquisition method of the temperature abnormality of each curve segment in the temperature-time curve of each area; obtain the cold chain transport monitoring result of the pallet according to the abnormal degree of the refrigeration effect of each abnormal area, the temperature abnormality of each curve segment in the updated temperature-time curve of each abnormal area, and each temperature data in each curve segment; The step of obtaining the temperature anomaly degree of each curve segment in the temperature-time curve of each region according to each temperature data in each curve segment in the temperature-time curve of each region and the approximate temperature value of each curve segment comprises: The approximate temperature value of each curve segment is obtained by an adaptive piecewise constant approximation algorithm; According to each temperature data in each curve segment in the temperature-time curve of each region, the approximate temperature value of each curve segment and the duration, the fluctuation index of the last curve segment in the temperature-time curve of each region is obtained; According to the fluctuation index of each curve segment in the temperature-time curve of each area and each temperature data in each curve segment, the temperature anomaly degree of the last curve segment in the temperature-time curve of each area is obtained; The specific calculation formula for obtaining the fluctuation index of the last curve segment in the temperature-time curve of each region according to each temperature data in each curve segment in the temperature-time curve of each region, the approximate temperature value of each curve segment and the duration is: in, Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates The average duration of all curve segments in the temperature-time curve of a region, Indicates The duration of the last curve segment in the temperature-time curve of a region, Indicates The approximate temperature value of the last curve segment in the temperature-time curve of the region, Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, represents the absolute value function; The specific calculation formula for obtaining the temperature anomaly degree of the last curve segment in the temperature-time curve of each region according to the fluctuation index of each curve segment in the temperature-time curve of each region and each temperature data in each curve segment is: in, Indicates The temperature anomaly degree of the last curve segment in the temperature-time curve of a region is Indicates The fluctuation index of the last curve segment in the temperature-time curve of a region, Indicates that except The average value of the fluctuation index of the last curve segment in the temperature-time curve of all regions other than the region, Indicates The number of temperature data of the last curve segment in the temperature-time curve of the region, Indicates the number of regions. Indicates The last curve segment of the temperature-time curve of the area Temperature data, Indicates that except The temperature-time curve of the region The last curve segment of the temperature-time curve of the area Temperature data, represents the absolute value function, represents the linear normalization function; The monitoring result of the cold chain transportation of the pallet is obtained according to the abnormal degree of the refrigeration effect of each abnormal area, the abnormal degree of the temperature of each curve segment in the updated temperature-time curve of each abnormal area, and each temperature data in each curve segment, including: According to the distance between each abnormal area and the abnormal degree of the cooling effect of each abnormal area, several abnormal groups are obtained; The first The curve segment corresponding to the negative data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the updated temperature-time curve of the abnormal area is recorded as A reference curve segment for the abnormal area; According to the number of reference curve segments in the updated temperature-time curve of each abnormal area, the abnormal degree of the cooling effect of each abnormal area in the abnormal group to which each abnormal area belongs, and each temperature data, the degree to which the last curve segment in the updated temperature-time curve of each abnormal area needs maintenance is obtained; The last curve segment in the updated temperature-time curve of each abnormal area, whose maintenance requirement is greater than a preset second judgment threshold, is recorded as a curve segment requiring maintenance; The abnormal area corresponding to the updated temperature-time curve of the curve segment requiring maintenance is recorded as the area requiring maintenance; Calculate the The degree of maintenance required for the last curve segment in the updated temperature-time curve of the area requiring maintenance is the same as that of the first The product of the mean of all temperature data in the last curve segment of the updated temperature-time curve of the area to be maintained, and the normalized value of the ratio of the product to the mean of all temperature data in the last curve segment of the updated temperature-time curve in all areas is recorded as the first The maintenance factor of the area that needs maintenance; An alarm is issued for an area where the maintenance coefficient is greater than a preset third judgment threshold, and no alarm is issued for an area where the maintenance coefficient is less than or equal to the preset third judgment threshold; According to the distance between each abnormal area and the abnormal degree of the cooling effect of each abnormal area, several abnormal groups are obtained, including: The product of the distance between any two abnormal areas and the absolute value of the difference in the abnormal degree of the cooling effect of any two abnormal areas is taken as the clustering distance between any two abnormal areas. The K-means clustering algorithm is used to cluster all abnormal areas to obtain several final clusters. All abnormal regions in each final cluster are grouped into an abnormal group, and several abnormal groups are obtained; The specific calculation formula for obtaining the degree to which the last curve segment in the updated temperature-time curve of each abnormal area needs maintenance is obtained according to the number of reference curve segments in the updated temperature-time curve of each abnormal area, the abnormal degree of the refrigeration effect of each abnormal area in the abnormal group to which each abnormal area belongs, and each temperature data: in, Indicates The degree to which the last curve segment in the updated temperature-time curve of the abnormal area needs maintenance, Indicates The average value of all temperature data in the last curve segment of the updated temperature-time curve of the abnormal area, Represents the mean value of all temperature data in the last curve segment of the updated temperature-time curve of all regions. For the The number of reference curve segments in the updated temperature-time curve of the abnormal area, For the The abnormal degree of cooling effect of all abnormal areas in the abnormal group where the abnormal area belongs is the same as that of the first abnormal area. The average of the absolute values ​​of the differences in the abnormal degree of cooling effect in the abnormal areas, For the The abnormal degree of cooling effect in each abnormal area, Indicated in Among all the abnormal areas in the abnormal group where the abnormal area belongs, the abnormal degree of cooling effect is higher than that of the abnormal area. The number of areas with small abnormal cooling effect in abnormal areas, Indicates The mean of all temperature data in the updated temperature-time curves of all abnormal regions in the abnormal group where the abnormal region belongs, represents the mean of all temperature data in the updated temperature-time curves of all abnormal areas in all abnormal groups, represents the linear normalization function, represents the normalization function, represents the absolute value function.

2. According to claim 1, the intelligent pallet cold chain transportation monitoring system based on Internet of Things technology is characterized in that: According to the temperature anomaly degree of each curve segment in the temperature-time curve of each region, a number of abnormal regions are screened out from all regions, including: When When the temperature anomaly degree of the last curve segment in the temperature-time curve of the region is greater than the first judgment threshold, it is determined that the The area is an abnormal area.

3. According to claim 1, the intelligent pallet cold chain transportation monitoring system based on Internet of Things technology is characterized in that: The abnormal degree of the refrigeration effect of each abnormal area is obtained according to the temperature abnormal degree of each curve segment of the temperature-time curve of each abnormal area and each temperature data in each curve segment, including: The first The curve segment with the positive corresponding data in the first-order difference sequence of the temperature anomaly degree of all curve segments in the temperature-time curve of the abnormal area is recorded as The main reference curve segment of the abnormal area; The first The ordinal value of the last curve segment in the temperature-time curve of the abnormal area is recorded as the target ordinal value; According to the number of main reference curve segments in the temperature-time curve of each abnormal area, the temperature abnormality degree of each curve segment and each temperature data in each curve segment, the specific calculation formula for the abnormality degree of the cooling effect of each abnormal area is obtained as follows: in, Indicates The abnormal degree of cooling effect in each abnormal area, Indicates The number of main reference curve segments in the temperature-time curve of the abnormal area, Indicates The mean of all data in the first-order difference series of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, Indicates The average value of the temperature anomaly degree of all curve segments of the temperature-time curve of the abnormal area, It represents the average of the temperature anomaly degree of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions. Indicates The mean of all temperature data of all curve segments of the temperature-time curve of the abnormal area, Represents the mean of all temperature data of all curve segments whose ordinal values ​​are before the target ordinal value in the temperature-time curve of all regions, represents the linear normalization function.

4. According to claim 1, the intelligent pallet cold chain transportation monitoring system based on Internet of Things technology is characterized in that: The obtaining of an updated temperature-time curve of each abnormal area according to the abnormal degree of the refrigeration effect of each abnormal area and the original output power in the cold chain transport vehicle includes: Calculate the sum of the average of the abnormal degrees of the refrigeration effects of all abnormal areas plus 1, and multiply the sum by the original output power in the cold chain transport vehicle to record it as the adjusted output power; Continue to collect temperature data of each area at each moment in the preset time period after the adjusted output power, and construct an updated temperature-time curve.

Images