Intelligent monitoring system and monitoring method for storage and transportation process of chilled fresh meat of livestock and poultry

Abstract

The invention provides an intelligent monitoring system and monitoring method for the storage and transportation process of chilled fresh meat of livestock and poultry, and relates to the technical field of data processing. The method comprises the steps that temperature data and smell data are collected through a temperature sensor and a smell sensor in a storage and transportation compartment; determining a risk point based on a relationship between temperature data in the temperature data sequence or smell data in the smell data sequence and a preset threshold value, or determining the risk point based on a temperature change degree and a smell concentration increase parameter; candidate hot spots are determined based on the temperature difference between the temperature data of all the points in the compartment temperature field and the overall temperature distribution, and first potential risk points in the candidate hot spots are determined; determining stacking concentration points in the candidate hot spots based on the odor concentration increasing parameters, and determining second potential risk points based on the temperature data of the stacking concentration points, the odor concentration increasing parameters, the odor concentration similarity between the stacking concentration points and adjacent points, the odor concentration increasing parameter similarity and the temperature difference; and sending risk early warning. The reliability of the monitoring result can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to an intelligent monitoring system and method for the storage and transportation of chilled livestock and poultry meat. Background Technology

[0002] In the production and distribution of chilled meat, the quality control during storage and transportation directly determines the safety and market value of the meat. Cold chain transportation is the core means to ensure the freshness of chilled meat. Therefore, real-time monitoring of the storage and transportation environment and the condition of the meat has become a key requirement for the industry.

[0003] In related technologies, traditional threshold judgment methods are typically used to monitor the storage and transportation process of chilled meat. Specifically, temperature sensors or odor sensors are deployed at single points to collect local temperature data or volatile gas concentration data released during meat spoilage inside the vehicle. Then, based on preset fixed thresholds (such as upper temperature limit or upper odor concentration limit), it is determined whether there are any abnormalities.

[0004] However, the traditional threshold determination method mentioned above only triggers an alarm when the temperature or odor concentration reaches a significantly abnormal threshold, resulting in a delayed monitoring response and an inability to provide early warnings. Fresh meat is usually stored in a stacked state in the storage and transportation compartment, and the heat dissipation conditions and gas diffusion efficiency of different stacking positions vary significantly. Single-point monitoring cannot reflect the true stacking state and may easily mask potential quality risks in the stack center. Without combining the temperature change trend with the dynamic change of odor concentration, relying solely on a single parameter threshold for judgment cannot accurately identify potential quality risks. Summary of the Invention

[0005] To address the problems of delayed monitoring response, blind spots, and low accuracy in risk identification inherent in related technologies, which lead to insufficient safety and controllability in cold chain transportation, this application provides an intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat. The specific technical solution adopted is as follows: Temperature and odor data are collected using temperature and odor sensors in the storage and transportation compartments. Risk points are determined based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensor and a first preset threshold or the relationship between the odor data in the odor data sequence collected by the odor sensor and a second preset threshold; or, risk points are determined based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence. The temperature field of the carriage is determined based on the temperature data sequence of each temperature sensor. Candidate hot spots are determined based on the temperature difference between the temperature data of each point in the temperature field and the overall temperature distribution. Candidate hot spots whose difference from the average temperature of the temperature field of the carriage is greater than a third preset threshold are identified as first potential risk points. Based on the odor concentration increase parameter, the accumulation concentration point in the candidate hotspot is determined, and based on its own temperature data and odor concentration increase parameter, as well as its odor concentration similarity, odor concentration increase parameter similarity and temperature difference with neighboring points, a second potential risk point is determined. If the risk point, the first potential risk point, or the second potential risk point exists in the storage and transportation compartment, an early warning will be sent.

[0006] For example, determining the risk point based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensor and a first preset threshold, or the relationship between the odor data in the odor data sequence collected by the odor sensor and a second preset threshold, includes: for each temperature sensor, constructing a temperature data sequence based on the temperature data collected by the temperature sensor, and denoting it as the temperature data sequence of the point to be determined at the location of the temperature sensor; for each odor sensor, constructing an odor data sequence based on the odor data collected by the odor sensor, and denoting it as the odor data sequence of the point to be determined at the location of the odor sensor; if there is temperature data in the temperature data sequence that is greater than the first preset threshold, or odor data in the odor data sequence that is greater than the second preset threshold, determining the corresponding point to be determined as the risk point.

[0007] For example, determining the risk point based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence includes: obtaining the highest and lowest temperature data in the temperature data sequence of the point to be determined, calculating the difference between the highest and lowest temperature data, and recording it as the degree of temperature change; performing time series fitting on the odor data sequence of the point to be determined, and determining the odor concentration increase parameter based on the fitting result; if the degree of temperature change is less than a fourth preset threshold and the odor concentration increase parameter is less than a fifth preset threshold, then the corresponding point to be determined is determined as a stable point; otherwise, the corresponding point to be determined is determined as the risk point.

[0008] For example, determining the temperature field of the carriage based on the temperature data sequence of each temperature sensor includes: calculating the average value of all temperature data in each temperature data sequence, and recording it as the point average temperature at the location of the corresponding temperature sensor; for a target point in the storage and transportation carriage where no temperature sensor is deployed, determining the reference temperature sensor adjacent to the target point and calculating the spatial distance between each reference temperature sensor and the target point; using a spatial interpolation algorithm to determine the temperature data of the target point based on the point average temperature of each reference temperature sensor and its spatial distance to the target point; and merging the temperature data of all the target points and the temperature data collected by all the temperature sensors to obtain the temperature field of the carriage.

[0009] For example, determining candidate hotspots based on the temperature difference between the temperature data at each point in the carriage temperature field and the overall temperature distribution includes: calculating the average value of the average temperature at each point corresponding to the temperature sensor in the carriage temperature field, denoted as the field average temperature of the carriage temperature field; obtaining the maximum value among the average temperatures at each point corresponding to the temperature sensor in the carriage temperature field, denoted as the maximum point average temperature; and determining the candidate hotspots at each location point in the carriage temperature field based on the temperature data at that location point, the field average temperature, and the maximum point average temperature.

[0010] For example, determining the accumulation concentration point among the candidate hotspots based on the odor concentration increase parameter includes: acquiring the odor data sequence of each location point in the temperature field of the carriage, performing time series fitting on the odor data sequence, and determining the odor concentration increase parameter of each location point based on the fitting result; calculating the average value of the odor concentration increase parameter of each location point in the temperature field of the carriage, and recording it as the average odor concentration increase parameter; and determining the candidate hotspots whose odor concentration increase parameter is greater than the average odor concentration increase parameter as the accumulation concentration point.

[0011] For example, determining a second potential risk point based on its own temperature data and odor concentration increase parameter, as well as its odor concentration similarity, odor concentration increase parameter similarity, and temperature difference with neighboring points, includes: obtaining the odor concentration increase parameter and the average temperature of the stacking point; determining the self-risk parameter of the stacking point based on the odor concentration increase parameter and the average temperature; determining the neighboring points of the stacking point, and determining the similarity between the odor data sequences of the stacking point and the neighboring points, denoted as the odor concentration similarity; determining the risk parameter of the stacking point and the... The similarity between the odor concentration increase parameters of neighboring points is denoted as the odor concentration increase parameter similarity; the difference between the average point temperature of the stacking concentration point and the neighboring points is determined and denoted as the temperature difference; the odor spread probability of the stacking concentration point is determined based on the odor concentration similarity, the odor concentration increase parameter similarity, and the temperature difference between the stacking concentration point and the neighboring points; the risk parameter of the stacking concentration point is determined based on its own risk parameter and the odor spread probability, and the stacking concentration point with the risk parameter greater than a sixth preset threshold is determined as the second potential risk point.

[0012] For example, determining the similarity between the odor data sequences of the stacking concentration point and the neighboring points, denoted as the odor concentration similarity, includes: determining the similarity between the odor data sequences of the stacking concentration point and the neighboring points through a dynamic time warping algorithm, denoted as the odor concentration similarity.

[0013] For example, determining the similarity between the odor concentration increase parameters of the stacking concentration point and the neighboring points, denoted as the odor concentration increase parameter similarity, includes: obtaining the smaller and larger values ​​of the odor concentration increase parameters of the stacking concentration point and the neighboring points, and recording the ratio of the smaller value to the larger value as the odor concentration increase parameter similarity.

[0014] Correspondingly, this application also provides an intelligent monitoring system for the storage and transportation of chilled livestock and poultry meat, including: The data acquisition module is used to collect temperature and odor data through temperature and odor sensors in the storage and transportation compartment; The risk assessment module is used to determine risk points based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensor and a first preset threshold or the relationship between the odor data in the odor data sequence collected by the odor sensor and a second preset threshold, or to determine the risk points based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence. The risk assessment module is further configured to determine the temperature field of the carriage based on the temperature data sequence of each of the temperature sensors, determine candidate hotspots based on the temperature difference between the temperature data of each point in the temperature field and the overall temperature distribution, and determine the candidate hotspots whose difference from the average temperature of the temperature field of the carriage is greater than a third preset threshold as the first potential risk point. The risk assessment module is also used to determine the concentrated accumulation point in the candidate hotspot based on the odor concentration increase parameter, and to determine the second potential risk point based on its own temperature data and odor concentration increase parameter, as well as the odor concentration similarity, odor concentration increase parameter similarity and temperature difference with the neighboring points. The risk warning module is used to send a warning if the risk point, the first potential risk point, or the second potential risk point exists in the storage and transportation compartment.

[0015] This application may have some or all of the following beneficial effects: In the intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat provided in this application, risk points are determined based on the relationship between temperature data and a first preset threshold in each temperature data sequence or the relationship between each odor data and a second preset threshold in each odor data sequence, or based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence. By identifying risk points through these two methods, not only can explicit risk points where the temperature or odor has exceeded the threshold be identified, but abnormal fluctuations can also be captured in advance through the temperature change trend and the dynamic increase characteristics of odor concentration. Risks can be determined before the meat has obviously deteriorated, thus achieving early warning. By constructing a temperature field in the carriage, analyzing the differences between each point in the temperature field and the overall temperature distribution, candidate hotspots are determined, and the first potential risk point with a temperature difference exceeding the threshold is selected from them. By capturing the temperature distribution differences in different areas within the cargo compartment under stacked conditions, the system accurately locates potential risks related to uneven heat dissipation caused by stacking, avoiding monitoring blind spots where risks at the stack center are masked by normal data from peripheral areas. For candidate hotspots, the system combines odor concentration elevation parameters to determine stacking concentration points. Based on the temperature and odor data of these concentration points, their similarity to neighboring points in odor concentration, similarity in odor concentration elevation parameters, and temperature differences, a second potential risk point is identified. This multi-dimensional analysis of its own parameters and their relationship with neighboring points avoids the limitations of single-parameter judgments, improves the accuracy of potential risk identification, and reduces misjudgments or omissions. Timely warnings are issued when risk points, first potential risk points, or second potential risk points are identified, allowing cold chain transport personnel to quickly identify abnormal areas and risk types within the cargo compartment. This facilitates timely inspection and handling of the transport environment or meat condition, effectively reducing the probability of meat spoilage due to unaddressed risks and significantly improving the safety and controllability of the storage and transportation of chilled livestock and poultry.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart is shown below illustrating an intelligent monitoring method for the storage and transportation of chilled meat from livestock and poultry, according to an exemplary embodiment of this application. Figure 2 A schematic block diagram of an intelligent monitoring system for the storage and transportation of chilled meat from livestock and poultry, according to an exemplary embodiment of this application, is shown. Detailed Implementation

[0019] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent monitoring system and method for the storage and transportation of chilled livestock and poultry meat proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, 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 application pertains.

[0021] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent monitoring system and monitoring method for the storage and transportation of chilled livestock and poultry meat provided in this application.

[0022] Please see Figure 1 It illustrates a flowchart of an intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat according to an embodiment of this application, as shown below. Figure 1 As shown, the intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat specifically includes the following steps: S110: Temperature and odor data are collected through temperature and odor sensors in the storage and transportation compartment; S120: Determine risk points based on the relationship between temperature data and a first preset threshold in the temperature data sequence collected by the temperature sensor or the relationship between each odor data and a second preset threshold in the odor data sequence collected by the odor sensor; or, determine risk points based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence. S130: Determine the temperature field of the carriage based on the temperature data sequence of each temperature sensor, determine candidate hot spots based on the temperature difference between the temperature data of each point in the temperature field and the overall temperature distribution, and determine the candidate hot spots whose difference from the average temperature of the temperature field of the carriage is greater than the third preset threshold as the first potential risk points. S140: Based on the odor concentration rise parameter, determine the concentrated point of the stacking in the candidate hotspot, and based on its own temperature data and odor concentration rise parameter, as well as its odor concentration similarity, odor concentration rise parameter similarity and temperature difference with the neighboring points, determine the second potential risk point. S150: If there is a risk point, a first potential risk point, or a second potential risk point in the storage and transportation compartment, send an early warning.

[0023] The following is a detailed explanation of each step in the above-mentioned intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat: In step S110, temperature data and odor data are collected by temperature sensors and odor sensors in the storage and transportation compartment.

[0024] In this embodiment, the aforementioned storage and transportation carriage is a special carriage used for cold chain transportation of chilled meat from livestock and poultry, which needs to maintain a low-temperature environment to ensure the freshness of the meat.

[0025] In this embodiment of the application, the temperature data mentioned above refers to the temperature values ​​collected by temperature sensors installed inside the storage and transportation compartment.

[0026] In the embodiments of this application, the aforementioned odor data refers to the concentration values ​​of volatile organic compounds (VOCs) released by odor sensors installed inside the storage and transportation compartments of chilled livestock and poultry meat during storage and transportation due to spoilage or microbial activity.

[0027] For example, the above-mentioned collection of temperature and odor data by temperature and odor sensors in the storage and transportation compartment can achieve the following: Temperature and odor sensors are evenly arranged inside the storage and transportation compartment, with some sensors directly placed in the gaps between stacks of chilled meat or attached to the surface of the meat, to ensure that the collected local temperature and odor concentration accurately reflect the surrounding environment of the meat; temperature and odor data are collected synchronously by the temperature and odor sensors, both at a frequency of once every 15 seconds, to ensure the timeliness and continuity of the data, forming preliminary temperature and odor data; the collected temperature and odor data are wirelessly transmitted to the risk assessment module of the monitoring system; the risk assessment module preprocesses the data uploaded by the sensors, including removing outliers, time synchronization, and mean / smoothing processing, to ensure the validity and accuracy of the data, providing a data foundation for subsequent risk point determination.

[0028] In step S120, risk points are determined based on the relationship between temperature data in the temperature data sequence collected by the temperature sensor and a first preset threshold or the relationship between each odor data in the odor data sequence collected by the odor sensor and a second preset threshold, or based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence.

[0029] In this embodiment of the application, the temperature data sequence is a continuous set of values ​​formed by preprocessing the temperature data collected by the corresponding temperature sensor; the first preset threshold is a pre-set critical value for judging temperature anomalies. When any temperature value in the temperature data sequence exceeds the threshold, it indicates that there is a temperature anomaly at the corresponding location.

[0030] In this embodiment of the application, the above-mentioned odor data sequence is a continuous set of values ​​formed by preprocessing the odor data collected by the corresponding odor sensor; the above-mentioned second preset threshold is a pre-set critical value for judging odor abnormality. When any concentration value in the odor data sequence exceeds the threshold, it indicates that there is an odor abnormality at the corresponding location.

[0031] In the embodiments of this application, the aforementioned degree of temperature change is used to reflect the temperature fluctuation range at the corresponding location, and can be used as a basis for judging whether the temperature is in a stable state.

[0032] In the embodiments of this application, the above-mentioned odor concentration increase parameter is used to reflect the rate of increase of odor concentration at the corresponding location over time, and can be used as a basis for judging whether there is an abnormal increase in odor concentration.

[0033] In this embodiment of the application, the aforementioned risk points are locations where abnormal temperature or odor may occur, potentially leading to deterioration of meat quality.

[0034] For example, the determination of risk points based on the relationship between temperature data and a first preset threshold in the temperature data sequence collected by the temperature sensor or the relationship between each odor data and a second preset threshold in the odor data sequence collected by the odor sensor can be achieved as follows: For each temperature sensor, a temperature data sequence is constructed based on the temperature data collected by the temperature sensor, and is denoted as the temperature data sequence of the point to be determined at the location of the temperature sensor; for each odor sensor, an odor data sequence is constructed based on the odor data collected by the odor sensor, and is denoted as the odor data sequence of the point to be determined at the location of the odor sensor; if there is temperature data in the temperature data sequence that is greater than the first preset threshold or odor data in the odor data sequence that is greater than the second preset threshold, the corresponding point to be determined is determined as a risk point.

[0035] In one specific implementation of this application embodiment, the process of determining risk points by threshold comparison can be achieved as follows: obtaining the temperature data sequence corresponding to the current point to be determined. and odor data sequences Comparison of temperature data sequences Each temperature data in the sequence is compared with a first preset threshold. There exists any temperature data. If the threshold (first preset threshold) is reached, it is determined that there is a temperature anomaly at the location of the point to be determined; compare with the odor data sequence. Each odor data in the sequence is compared with a second preset threshold. There exists any odor concentration value If the second preset threshold is met, it is determined that there is an abnormal odor at the location of the point to be judged; if either the temperature abnormality or the odor abnormality is met, the point to be judged can be identified as a risk point.

[0036] In addition to identifying obvious risk points where temperature or odor has exceeded thresholds using the methods described above, this application embodiment can also detect abnormal fluctuations in advance by observing temperature change trends and dynamic increases in odor concentration. For example, the above-mentioned determination of risk points based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence can be achieved as follows: obtain the highest and lowest temperature data in the temperature data sequence of the point to be determined, calculate the difference between the highest and lowest temperature data, and record it as the degree of temperature change; perform time series fitting on the odor data sequence of the point to be determined, and determine the odor concentration increase parameter based on the fitting result; if the degree of temperature change is less than a fourth preset threshold and the odor concentration increase parameter is less than a fifth preset threshold, then the corresponding point to be determined is determined as a stable point; otherwise, the corresponding point to be determined is determined as a risk point.

[0037] In one specific implementation of this application embodiment, the process of preemptively capturing abnormal fluctuations by observing temperature change trends and dynamic increases in odor concentration, and determining risk points based on these abnormal fluctuations, can be achieved as follows: obtaining the temperature data sequence corresponding to the current point to be determined. and odor data sequences From temperature data series Extract the maximum and minimum values, and record them as the highest temperature data. and minimum temperature data The degree of temperature change is calculated using the following formula: ; odor data sequence of the current point to be determined Time series fitting was performed to obtain the trend parameter of odor concentration increasing over time, which was denoted as the odor concentration increase parameter at the current point to be determined. For example, the above time series fitting can employ linear fitting, exponential fitting, or other fitting methods, the implementation of which is the same as existing technologies and will not be elaborated further here; if the degree of temperature change Not less than the fourth preset threshold (a pre-set critical value for the degree of temperature change), or, the odor concentration increase parameter. If the temperature is not less than the fifth preset threshold (the critical value of the preset odor concentration increase parameter), it reflects an abnormally high temperature or a significant increase in odor concentration at the current location of the point to be judged. This indicates that meat is densely piled up in the area or is showing signs of spoilage, resulting in an abnormal local environment due to uneven heat dissipation and the accumulation of volatile gases. The current location to be judged is therefore identified as a risk point. If the temperature change is significant... Parameters with odor concentration less than the fourth preset threshold and increasing If the temperature is less than the fifth preset threshold, it indicates that the temperature at the current location of the test point remains constant and the odor concentration changes slowly. This proves that the temperature is normal during meat transportation, the heat dissipation is uniform, and the release of volatile substances is within an acceptable range, which will not affect the quality of the meat. Therefore, the current test point is determined to be a stable point.

[0038] In step S130, the temperature field of the carriage is determined based on the temperature data sequence of each temperature sensor, and candidate hotspots are determined based on the temperature difference between the temperature data of each point in the temperature field and the overall temperature distribution. Candidate hotspots whose difference from the average temperature of the carriage temperature field is greater than a third preset threshold are identified as first potential risk points.

[0039] In meat storage projects, although the storage and transport compartments are kept at a constant temperature, the high density of meat may lead to uneven heat dissipation, resulting in slightly higher local temperatures and relatively higher concentrations of volatile gases in concentrated areas. Therefore, the temperature hotspots and gas concentrations obtained from sensors can accurately identify concentrated meat storage areas. However, due to the limited placement of sensors within the storage and transport compartments, areas with abnormal temperatures may not be directly detected. To address this, this application embodiment can perform spatial interpolation calculations based on temperature data collected from existing sensors to construct the overall temperature field of the compartment. Furthermore, by combining the overall temperature distribution of the compartment's temperature field, candidate hotspots with significantly higher local temperatures can be screened. This allows for further identification of potential risk points within these candidate hotspots, preventing monitoring blind spots caused by the risk at the stacking center being masked by normal data from the edge areas.

[0040] In this embodiment of the application, the above-mentioned temperature field of the carriage refers to a continuous temperature distribution set covering the entire carriage area, formed by supplementing the temperature values ​​of areas without sensor deployment in the carriage with the effective temperature data of all temperature sensors through a spatial interpolation algorithm. This set can intuitively reflect the spatial distribution differences of temperature in the carriage.

[0041] For example, the above-mentioned determination of the car body temperature field based on the temperature data sequence of each temperature sensor can be achieved as follows: calculate the average value of all temperature data in each temperature data sequence, and record it as the point average temperature at the location of the corresponding temperature sensor; for the target point to be supplemented in the storage and transportation car body where no temperature sensor is deployed, determine the reference temperature sensor near the target point to be supplemented, and calculate the spatial distance between each reference temperature sensor and the target point to be supplemented; use a spatial interpolation algorithm to determine the temperature data of the target point to be supplemented based on the point average temperature of each reference temperature sensor and its spatial distance from the target point to be supplemented; merge the temperature data of all target points to be supplemented and the temperature data collected by all temperature sensors to obtain the car body temperature field.

[0042] In one specific implementation of this application embodiment, the process of determining the temperature field of the carriage can be achieved as follows: For the i-th temperature sensor, calculate its temperature data sequence. The average value of all temperature data is denoted as the point average temperature at the location of the i-th temperature sensor. And construct an average temperature set Where m is the current number of temperature sensors; based on the dimensions of the carriage space and the sensor deployment density, target points within the carriage that are currently without temperature sensors are identified for replacement; for these target points... The temperature data was generated using the Inverse Distance Weighting Interpolation Algorithm (IDW) as follows: in, Points to be added for the above objectives Temperature data; For example, the number of reference temperature sensors mentioned above can be selected from all temperature sensors to match the target point to be supplemented. The nearest N are used as reference temperature sensors, and the specific number of N can be set according to the size of the carriage and the density of sensor deployment. For the i-th reference temperature sensor, the target point to be supplemented is... The contribution weight of temperature calculation is set in the embodiments of this application. ; The average temperature of the point corresponding to the i-th reference temperature sensor; For the i-th reference temperature sensor and the target point to be supplemented The distance between them.

[0043] After determining the temperature data of each target point to be supplemented using the above method, the interpolated temperature data of all target points to be supplemented are combined with the point average temperature data of all temperature sensors to form a temperature field covering the entire storage and transportation compartment. .

[0044] In this embodiment of the application, the aforementioned candidate hotspots are locations in the temperature field of the carriage where the local temperature is significantly higher, and are potential areas where there may be dense stacking and uneven heat dissipation.

[0045] For example, the above method of determining candidate hotspots based on the temperature difference between the temperature data of each point in the temperature field of the carriage and the overall temperature distribution can be achieved as follows: calculate the average value of the average temperature of each point corresponding to the temperature sensor in the temperature field of the carriage, and record it as the field average temperature of the temperature field of the carriage; obtain the maximum value of the average temperature of each point corresponding to the temperature sensor in the temperature field of the carriage, and record it as the maximum point average temperature; for each location point in the temperature field of the carriage, determine the candidate hotspots among the location points based on the temperature data of each location point, the field average temperature and the maximum point average temperature.

[0046] In one specific implementation of this application embodiment, the process of determining candidate hotspots described above can be achieved as follows: calculating the average temperature set. The average temperature of all points in the carriage is denoted as the field average temperature of the temperature field. ; obtain The maximum value in the range is denoted as the average temperature at the maximum point. For any point in the temperature field of the carriage, if its temperature is significantly higher than that of its surrounding points and higher than the average temperature of all sensor points, then... and If so, it is identified as a candidate hotspot.

[0047] In this embodiment of the application, the first potential risk point is a location with a higher degree of temperature anomaly selected from the candidate hotspots, corresponding to a potentially high-risk area in the storage and transportation compartment where the meat quality may deteriorate due to severe uneven heat dissipation caused by excessive stacking.

[0048] In one specific implementation of this application embodiment, the process of determining the first potential risk point can be implemented as follows: For each candidate hotspot, calculate its point average temperature. With field average temperature The difference: ;like If the temperature exceeds the third preset threshold, it indicates that the abnormal temperature of the candidate hot spot has exceeded the normal heat dissipation difference range, which may lead to local temperature rise and deterioration of the meat. The candidate hot spot is then identified as the first potential risk point.

[0049] In step S140, the concentrated points of the candidate hotspots are determined based on the odor concentration increase parameter, and the second potential risk points are determined based on their own temperature data and odor concentration increase parameter, as well as the similarity of their odor concentration, the similarity of their odor concentration increase parameter, and the temperature difference with those of their neighboring points.

[0050] In this embodiment of the application, the above-mentioned concentrated stacking points are locations with abnormal odor concentration growth selected from candidate hot spots. These correspond to densely stacked areas of meat in the storage and transportation compartment, which are prone to quality risks due to uneven heat dissipation and odor accumulation.

[0051] For example, the above method of determining the stacking concentration point among candidate hotspots based on the odor concentration increase parameter can be achieved as follows: obtain the odor data sequence of each location point in the temperature field of the carriage, perform time series fitting on the odor data sequence, and determine the odor concentration increase parameter of each location point based on the fitting result; calculate the average value of the odor concentration increase parameter of each location point in the temperature field of the carriage, and record it as the average odor concentration increase parameter; determine the candidate hotspots with odor concentration increase parameters greater than the average odor concentration increase parameter as the stacking concentration point.

[0052] In one specific implementation of this application embodiment, the process of determining the stacking concentration point can be implemented as follows: determine the odor concentration rise parameter of all candidate hotspots. Wherein, if a candidate hotspot is a target point to be replenished without an odor sensor, the odor data sequence of the target point to be replenished is similarly generated using the aforementioned inverse distance weighted interpolation algorithm, and its odor concentration rise parameter is obtained after time series fitting; the odor concentration rise parameters of all locations are statistically analyzed and their average value is calculated, denoted as the average odor concentration rise parameter. For any Odor concentration increase parameter The i-th candidate hotspot is determined as the stacking concentration point.

[0053] In this embodiment of the application, the aforementioned second potential risk point is a location that meets the anomaly level criteria selected from the concentrated stacking points by combining its own temperature and odor risk with the surrounding diffusion characteristics.

[0054] For example, the above-mentioned determination of the second potential risk point based on the temperature data and odor concentration rise parameters of the stacking concentration point itself, as well as the odor concentration similarity, odor concentration rise parameter similarity, and temperature difference with neighboring points can be achieved as follows: Obtain the odor concentration rise parameters and average temperature of the stacking concentration point; determine the self-risk parameters of the stacking concentration point based on the odor concentration rise parameters and average temperature; determine the neighboring points of the stacking concentration point, and determine the similarity between the odor data sequences of the stacking concentration point and the neighboring points, denoted as odor concentration similarity; determine the similarity between the odor concentration rise parameters of the stacking concentration point and the neighboring points, denoted as odor concentration rise parameter similarity; determine the difference between the average temperature of the stacking concentration point and the neighboring points, denoted as temperature difference; determine the odor spread probability of the stacking concentration point based on the odor concentration similarity, odor concentration rise parameter similarity, and temperature difference between the stacking concentration point and the neighboring points; determine the risk parameters of the stacking concentration point based on its own risk parameters and odor spread probability; and determine the stacking concentration points with risk parameters greater than a sixth preset threshold as the second potential risk points.

[0055] In one specific implementation of this application embodiment, the process of determining the second potential risk point can be implemented as follows: for any stacking concentration point Based on the dimensions of the carriage space and the density of sensors in the carriage temperature field Selected from The M surrounding locations are denoted as the stacking concentration points. The nearest point; for the concentrated stacking point and any of its neighboring points Obtain the stacking concentration point Odor data sequence and neighboring points Odor data sequence Calculated using dynamic time warping algorithm and Odor concentration similarity: The implementation principle of the dynamic time warping algorithm is the same as that of existing technologies, and will not be elaborated here; obtaining the stacking concentration point. Odor concentration increase parameter and neighboring points Odor concentration increase parameter Calculate the stacking concentration point using the smaller and larger values ​​in the range. and its neighboring points Similarity of odor concentration increase parameters between them: The closer its value is to 1, the more concentrated the storage area. and its neighboring points The more similar the changes in odor concentration between them, the better; calculate the concentration points of the stockpiles. and its neighboring points Temperature differences between them: The concentration point of the stacking is calculated using the following formula. Potential for odor expansion: in, Centralized storage point The potential for odor spread reflects the concentration of the storage area. The greater the value, the more likely the odor will spread to its surrounding neighboring points, indicating that the odor originated from the stockpiled area. The higher the probability of it spreading to the surrounding areas; The selected storage concentration point from the temperature field TA of the carriage The number of neighboring points can be set according to the dimensions of the carriage space and the density of sensor deployment. Centralized storage point The similarity of the odor concentration increase parameter with its i-th neighboring point reflects the concentration point of the stockpiling. Consistency with the odor growth rate of its i-th neighboring point; Centralized storage point The similarity of odor concentration with its i-th neighbor reflects the concentration of the stockpiles. Consistency with the time trend of odor concentration at its i-th neighboring point; Centralized storage point The smaller the temperature difference between the i-th and its i-th neighboring points, the more concentrated the storage point. The smaller the temperature gradient with neighboring points, the less obstructed the airflow, the more uniform the heat dissipation, and the easier it is for odors to diffuse to the surrounding area.

[0056] The above formula is used to determine the stacking concentration point. After assessing the potential for odor spread, the concentration point of the stockpiles can be determined using the following formula. Self-risk parameters: in, Centralized storage point Its own risk parameters are used to reflect the concentration of stockpiles. The possibility of meat deterioration due to localized high temperatures and abnormal odor accumulation; Centralized storage point The higher the value of the odor concentration parameter, the faster the release of putrefactive products, and the more likely the meat has entered the spoilage process or has a significant spoilage trend. Centralized storage point The higher the average temperature at a given point, the worse the heat dissipation and the faster the meat will spoil.

[0057] Determine the centralized storage location After determining its own risk parameters and the likelihood of odor spread, the concentration point of the stockpiles can be calculated using the following formula. Risk parameters: in, Centralized storage point The risk parameters are used to quantify the overall degree of harm. Centralized storage point Its own risk parameters; Centralized storage point The possibility of expanding the odor.

[0058] Setting the sixth preset threshold to 0.9, if the calculated risk parameter... If the value is greater than 0.9, then the stacking concentration point will be adjusted. It was identified as the second potential risk point.

[0059] In step S150, if there is a risk point, a first potential risk point, or a second potential risk point in the storage and transportation compartment, an early warning is sent.

[0060] When determining the presence of risk points, first potential risk points, or second potential risk points within the storage and transportation compartment using the above methods, the aforementioned early warning system can achieve the following: Visually identify various risk points (risk points are displayed in red, and potential risk points in yellow), and construct a three-dimensional temperature-odor concentration model of the compartment based on multi-point sensor data within the compartment. Map the state of each sampling point in three-dimensional space onto the model, intuitively reflecting the risk distribution and concentrated storage points within the compartment. When any point is identified as a risk point or potential risk point, it is automatically highlighted on the visualization interface, simultaneously triggering an early warning mechanism to generate alarm information in real time and notify the transport driver or relevant operators, enabling them to promptly inspect and address the transportation environment or meat condition. This effectively reduces the probability of meat spoilage due to untimely risk management, and significantly improves the safety and controllability of the storage and transportation process for chilled livestock and poultry meat.

[0061] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0062] Correspondingly, embodiments of this application also provide an intelligent monitoring system for the storage and transportation of chilled livestock and poultry meat, referencing... Figure 2 As shown, the intelligent monitoring system 200 for the storage and transportation of chilled livestock and poultry meat may include a data acquisition module 210, a risk assessment module 220, and a risk early warning module 230, wherein: The data acquisition module is used to collect temperature and odor data through temperature and odor sensors in the storage and transportation compartment; The risk assessment module is used to determine risk points based on the relationship between temperature data in the temperature data sequence collected by the temperature sensor and a first preset threshold or the relationship between each odor data in the odor data sequence collected by the odor sensor and a second preset threshold, or based on the degree of temperature change in the temperature data sequence and the odor concentration increase parameter in the odor data sequence. The risk assessment module is also used to determine the temperature field of the carriage based on the temperature data sequence of each temperature sensor, determine candidate hot spots based on the temperature difference between the temperature data of each point in the temperature field and the overall temperature distribution, and determine the candidate hot spots whose difference from the average temperature of the temperature field of the carriage is greater than a third preset threshold as the first potential risk points. The risk assessment module is also used to determine the concentrated storage points in the candidate hotspots based on the odor concentration rise parameter, and to determine the second potential risk based on its own temperature data and odor concentration rise parameter, as well as the similarity of its odor concentration, odor concentration rise parameter, and temperature difference with neighboring points. The risk warning module is used to send a warning if there is a risk point, a first potential risk point, or a second potential risk point in the storage and transportation compartment.

[0063] The specific implementation details of the aforementioned intelligent monitoring system for the storage and transportation of chilled livestock and poultry meat have been explained in detail in the corresponding section of the intelligent monitoring method for the storage and transportation of chilled livestock and poultry meat, and therefore will not be repeated here.

[0064] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A livestock and poultry chilled meat storage and transportation process intelligent monitoring method, characterized in that, The method comprises: collecting temperature data and odor data through temperature sensors and odor sensors in the storage and transport compartment; determining a risk point based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensors and a first preset threshold value or the relationship between the odor data in the odor data sequence collected by the odor sensors and a second preset threshold value, or determining the risk point based on the temperature variation degree of the temperature data sequence and the odor concentration increase parameter of the odor data sequence; determining a compartment temperature field based on the temperature data sequence of each temperature sensor, determining a candidate hotspot based on the temperature difference between the temperature data of each point in the compartment temperature field and the overall temperature distribution, and determining the candidate hotspot with a difference value greater than a third preset threshold value from the field average temperature of the compartment temperature field as a first potential risk point; determining a concentrated point in the candidate hotspot based on the odor concentration increase parameter, and determining a second potential risk point based on its own temperature data and odor concentration increase parameter, as well as the odor concentration similarity, odor concentration increase parameter similarity and temperature difference with adjacent points; if the risk point, the first potential risk point or the second potential risk point exists in the storage and transport compartment, sending a warning.

2. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 1, characterized in that, The determination of the risk point based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensors and a first preset threshold value or the relationship between the odor data in the odor data sequence collected by the odor sensors and a second preset threshold value comprises: for each temperature sensor, constructing the temperature data sequence based on the temperature data collected by the temperature sensor, which is recorded as the temperature data sequence of the to-be-judged point at the position of the temperature sensor; for each odor sensor, constructing the odor data sequence based on the odor data collected by the odor sensor, which is recorded as the odor data sequence of the to-be-judged point at the position of the odor sensor; if the temperature data greater than the first preset threshold value exists in the temperature data sequence or the odor data greater than the second preset threshold value exists in the odor data sequence, the to-be-judged point corresponding to the temperature data or the odor data is determined as the risk point.

3. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 2, characterized in that, The determination of the risk point based on the temperature variation degree of the temperature data sequence and the odor concentration increase parameter of the odor data sequence comprises: obtaining the highest temperature data and the lowest temperature data in the temperature data sequence of the to-be-judged point, calculating the difference value between the highest temperature data and the lowest temperature data, which is recorded as the temperature variation degree; performing time series fitting on the odor data sequence of the to-be-judged point, and determining the odor concentration increase parameter based on the fitting result; if the temperature variation degree is less than a fourth preset threshold value and the odor concentration increase parameter is less than a fifth preset threshold value, the to-be-judged point corresponding thereto is determined as a stable point, otherwise, the to-be-judged point corresponding thereto is determined as the risk point.

4. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 1, characterized in that, The determination of the compartment temperature field based on the temperature data sequence of each temperature sensor comprises: Calculate the average value of all the temperature data in each of the temperature data sequences, denoted as the point average temperature of the position where the corresponding temperature sensor is located; For each target point to be supplemented in the storage and transportation compartment where the temperature sensor is not arranged, determine the reference temperature sensor adjacent to the target point to be supplemented, and calculate the spatial distance between each reference temperature sensor and the target point to be supplemented; Determine the temperature data of the target point to be supplemented according to the point average temperature of each reference temperature sensor and the spatial distance between the reference temperature sensor and the target point to be supplemented by using a spatial interpolation algorithm; Merge the temperature data of all the target points to be supplemented and the temperature data collected by all the temperature sensors to obtain the compartment temperature field.

5. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 4, characterized in that, The candidate hot spots are determined based on the temperature difference between the temperature data of each point in the compartment temperature field and the overall temperature distribution, including: Calculate the average value of the point average temperature corresponding to each temperature sensor in the compartment temperature field, denoted as the field average temperature of the compartment temperature field; Obtain the maximum value of the point average temperature corresponding to each temperature sensor in the compartment temperature field, denoted as the maximum point average temperature; For each position point in the compartment temperature field, determine the candidate hot spot in the position point based on the temperature data of the position point, the field average temperature, and the maximum point average temperature.

6. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 5, characterized in that, The concentrated points in the candidate hot spots are determined based on the odor concentration increase parameter, including: Obtain the odor data sequence of each position point in the compartment temperature field, perform time series fitting on the odor data sequence, and determine the odor concentration increase parameter of each position point based on the fitting result; Calculate the average value of the odor concentration increase parameter of each position point in the compartment temperature field, denoted as the average odor concentration increase parameter; Determine the concentrated points in the candidate hot spots as the concentrated points based on the odor concentration increase parameter being greater than the average odor concentration increase parameter.

7. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 6, characterized in that, The second potential risk point is determined based on its own temperature data and odor concentration increase parameter, as well as the odor concentration similarity, odor concentration increase parameter similarity, and temperature difference with adjacent points, including: Obtain the odor concentration increase parameter and the point average temperature of the concentrated point, and determine the self-risk parameter of the concentrated point based on the odor concentration increase parameter and the point average temperature; Determine the adjacent points of the concentrated point, and determine the similarity between the odor data sequences of the concentrated point and the adjacent points, denoted as the odor concentration similarity; Determine the similarity between the odor concentration increase parameters of the concentrated point and the adjacent points, denoted as the odor concentration increase parameter similarity; Determine the difference between the point average temperatures of the concentrated point and the adjacent points, denoted as the temperature difference; Determine the odor spread possibility of the concentrated point based on the odor concentration similarity, odor concentration increase parameter similarity, and temperature difference between the concentrated point and the adjacent points; Determine a risk parameter of the stacking point based on the self-risk parameter and the smell spread possibility, and determine the stacking point with the risk parameter greater than a sixth preset threshold as the second potential risk point.

8. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 7, characterized in that, The determination of the similarity between the smell data sequence of the stacking point and the adjacent point, recorded as smell concentration similarity, includes: Determine the similarity between the smell data sequence of the stacking point and the adjacent point, recorded as smell concentration similarity, by dynamic time warping algorithm.

9. The livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring method according to claim 8, characterized in that, The determination of the similarity between the smell concentration rise parameter of the stacking point and the adjacent point, recorded as smell concentration rise parameter similarity, includes: Obtain the smaller value and the larger value in the smell concentration rise parameter of the stacking point and the adjacent point, and record the ratio of the smaller value to the larger value as the smell concentration rise parameter similarity.

10. A livestock and poultry chilled fresh meat storage and transportation process intelligent monitoring system, characterized in that, The system includes: A data acquisition module is configured to collect temperature data and smell data by temperature sensors and smell sensors in the storage and transport vehicle compartment; A risk judgment module is configured to determine a risk point based on the relationship between the temperature data in the temperature data sequence collected by the temperature sensors and a first preset threshold, or the relationship between the smell data in the smell data sequence collected by the smell sensors and a second preset threshold, or determine the risk point based on the temperature change degree of the temperature data sequence and the smell concentration rise parameter of the smell data sequence; The risk judgment module is further configured to determine a compartment temperature field based on the temperature data sequence of each temperature sensor, determine a candidate hotspot based on the temperature difference between the temperature data of each point in the compartment temperature field and the overall temperature distribution, and determine the candidate hotspot with a difference value greater than a third preset threshold from the field average temperature of the compartment temperature field as a first potential risk point; The risk judgment module is further configured to determine a stacking point in the candidate hotspot based on the smell concentration rise parameter, and determine a second potential risk point based on the temperature data and the smell concentration rise parameter of the stacking point itself, and the smell concentration similarity, smell concentration rise parameter similarity and temperature difference of the stacking point and adjacent points; A risk warning module is configured to send a warning if the risk point, the first potential risk point or the second potential risk point exists in the storage and transport vehicle compartment.

Images