Intelligent management monitoring system for cold chain storage and transportation of agricultural products

Abstract

The invention relates to the field of agricultural product cold-chain storage, and discloses an intelligent management monitoring system for agricultural product cold-chain storage and transportation, which comprises the following steps: synchronously sensing operation states and operation behaviors of agricultural product storage units and cold source equipment to form a data input sequence with operation association semantics; introducing a dynamic sampling mechanism based on operation event triggering into the data input sequence, and constructing a continuous evolution feature set reflecting local cold chain stability; performing time sequence analysis on a temperature and humidity parameter recovery track and a cooling capacity response rhythm presented in the continuous evolution characteristic set; delimiting a storage area corresponding to the risk evolution fragment as a key monitoring unit, and constructing an operation influence association model for describing a local cold chain constraint relationship; and performing linkage adjustment on the sensing node acquisition strategy, the monitoring update frequency and the cold source scheduling parameters under the constraint relation limited by the operation influence correlation model. The method has the advantage that the controllability of the cold chain operation process is improved.

Description

Technical Field

[0001] This invention relates to the field of cold chain storage of agricultural products, specifically to an intelligent management and monitoring system for cold chain storage and transportation of agricultural products. Background Technology

[0002] With the continuous expansion of cold chain storage and transportation of agricultural products, the requirements for continuous temperature and humidity stability are increasing for perishable agricultural products such as fruits, vegetables, and meat during graded storage and short-distance cold chain turnover. Existing cold chain management systems typically collect and remotely monitor overall environmental parameters periodically by deploying temperature and humidity sensors in refrigerated warehouses or transport vehicles. However, in practical applications, agricultural products are often stored in palletized or partitioned locations. Due to differences in stacking density, airflow organization, and loading / unloading frequency, local micro-environmental fluctuations can easily form between different storage locations. In specific scenarios, such as when fresh fruits and vegetables are transferred from the origin cold storage to the transit warehouse and then to the delivery vehicle, some storage locations near the warehouse door or the edge of the vehicle may experience a temperature rise for a short period of time when the refrigerated door is opened during loading and unloading. However, such short-term, localized abnormal changes are often difficult for existing systems to effectively identify. On the one hand, existing monitoring systems mainly rely on single-point or limited fixed sensors, resulting in a disconnect between sampling locations and the actual condition of the goods. On the other hand, monitoring data is typically uploaded at fixed time intervals, lacking targeted monitoring and labeling of environmental changes triggered by loading and unloading activities. This makes it difficult to pinpoint the specific stage where localized cold chain instability occurs during post-event traceability. Therefore, it is essential to design an intelligent management and monitoring system for agricultural product cold chain storage and transportation that improves the controllability of the cold chain operation process. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides an intelligent management and monitoring system for cold chain storage and transportation of agricultural products, which has the advantage of improving the controllability of the cold chain operation process and solves the problems mentioned in the background technology.

[0004] To achieve the aforementioned goal of improving the controllability of the cold chain operation process, this invention provides the following technical solution: an intelligent management and monitoring system for cold chain storage and transportation of agricultural products, comprising: Multi-source sensing module: synchronously senses the operating status and operation behavior of agricultural product storage units and cold source equipment, performs spatial rearrangement and temporal discretization processing on the collected data, and forms a data input sequence with operation-related semantics; Event sampling module: Introduces a dynamic sampling mechanism based on operation event triggering for the data input sequence, and performs segmented tracking of temperature gradient, humidity rebound rate and cold energy recovery cycle to construct a continuous evolution feature set reflecting the stability of the local cold chain; The hysteresis analysis module performs time-series analysis on the continuous evolution feature set, characterizes the response hysteresis relationship of different storage units under the influence of the cold source supply path, and screens out the risk evolution segments that lead to cold chain instability by identifying abnormal offset segments and coupling mismatch intervals in the environmental parameter recovery curve. Impact Correlation Module: The storage area corresponding to the risk evolution segment is designated as a key monitoring unit. Information on the refrigeration unit's operating load, airflow organization status, and cargo heat capacity distribution within the key monitoring unit is integrated to construct an operational impact correlation model. Collaborative control module: Under the constraints of the operational impact correlation model, and in conjunction with the stability change trend within the overall cold chain operation cycle, the module adjusts the sensing node acquisition strategy, monitoring update frequency, and cold source scheduling parameters in a coordinated manner.

[0005] Preferably, the process of synchronously sensing the operating status and operational behavior of agricultural product storage units and cold source equipment is as follows: By deploying temperature and humidity sensors, location markers, and cargo location status acquisition devices in each agricultural product storage unit, real-time information on cargo location environmental parameters, storage location, and occupancy status can be obtained. By connecting to the operating interface of the cold source equipment, data reflecting the operating status of the cold source can be collected, including the start-up and shutdown status of the chiller, the cooling output level, the operating load, and the adjustment level. Through the work record interface, event-based data collection is performed on loading and unloading operations, opening and closing of refrigerated doors, vehicle entry and exit, and manual intervention, and the status of various sensing data is aligned.

[0006] Preferably, the process of forming a data input sequence with job-related semantics is as follows: Collect operational status data for each agricultural product storage unit, and label the collected data by product dimension according to the category attributes, freshness level and allowable fluctuation threshold of the agricultural products. By combining the hierarchical relationship of the storage location and the stacking topology, spatial mapping and rearrangement are performed on the data of different sensing points. Based on the frequency distribution of operations obtained from historical operation records, the continuous time axis is discretized at non-equal intervals to generate data segments that match the operation rhythm. The data segments that have undergone spatial rearrangement and temporal discretization are spliced ​​together according to the rules of cargo location and operation association to form a data input sequence with operation association semantics.

[0007] Preferably, the process of introducing a dynamic sampling mechanism based on job event triggering into the data input sequence is as follows: Identify loading and unloading operations, refrigerated door opening and closing, vehicle entry and exit, and cold source start and stop from the data input sequence, and pre-set sampling trigger conditions and duration window lengths for different types of operational events; When an operational event is detected, the sampling frequency of the corresponding storage location and adjacent area sensing nodes is temporarily increased. After the operational event ends, the sampling frequency is gradually reduced back to the normal monitoring level according to the cold chain recovery status. Generate dynamic sampling data that matches the intensity and duration of the operational event.

[0008] Preferably, the process of constructing a continuous evolutionary feature set reflecting local cold chain stability is as follows: Extract the temperature and humidity change curves of each storage unit before, during and after the operation event from the dynamic sampling data, and calculate the temperature gradient change rate and humidity rebound speed between adjacent storage units. The time required for environmental parameters to recover to a set stable range after the intervention of the cold source equipment is statistically analyzed to obtain the cold capacity recovery cycle. The parameters are then divided into multiple continuous evolution segments in chronological order. Each evolutionary segment is standardized and aggregated to form a continuous evolutionary feature set describing the local cold chain operation status.

[0009] Preferably, the process for characterizing the response lag relationship of different storage units under the influence of the cold source supply path is as follows: Time alignment of the temperature and humidity recovery trajectories of each cargo unit in the continuous evolution feature set is performed, and the cold source supply path corresponding to each cargo location is determined by combining the air supply path and refrigeration distribution structure of the cold source equipment. Analyze the start time and rate of change of parameters in different storage units after the cold source is introduced, and calculate the time delay difference between the recovery of environmental parameters of the storage unit and the start time of the cold source. The results describe the response lag relationship between the storage unit and the cold source supply path.

[0010] Preferably, the process of screening out risk evolutionary segments that lead to cold chain instability is as follows: The actual temperature and humidity recovery curve is compared with the standard recovery curve of the corresponding goods to identify abnormal deviation segments that exceed the allowable fluctuation range during the recovery process. Based on the response lag relationship, it is determined whether the abnormal offset segment is mismatched with the cold source supply path, and the time segment that simultaneously meets the abnormal offset and path coupling mismatch conditions is marked as a risk candidate segment. Adjacent risk candidate segments are merged to form risk evolution segments of cold chain instability.

[0011] Preferably, the process of designating the storage area or transportation segment corresponding to the risk evolution segment as a key monitoring unit is as follows: Based on the timestamp and location number corresponding to the risk evolution segment, locate the corresponding storage area; The frequency and duration of risk evolution segments within the same area are statistically analyzed. When the statistical indicators exceed a preset threshold, the corresponding area is designated as a key monitoring unit, and the spatial range and associated cargo location information of the key monitoring unit are recorded.

[0012] Preferably, the process of constructing an operational impact correlation model to describe local cold chain constraint relationships is as follows: Collect real-time operating load and output capacity parameters of the chiller in the key monitoring unit, obtain information on airflow direction, wind speed and circulation path in the key monitoring unit, and form a description of airflow organization status; The heat capacity distribution of goods is calculated based on the product category and stacking method. The refrigeration unit load, airflow organization and heat capacity distribution are correlated and mapped to construct an operational impact correlation model that describes the constraints of local cold chain operation.

[0013] Preferably, the process of adjusting the sensing node acquisition strategy, monitoring update frequency, and cold source scheduling parameters in a coordinated manner is as follows: The stability change trend of each region during the overall cold chain operation cycle is statistically analyzed, and the stability change trend is jointly analyzed with the operation impact correlation model to identify sensitive control nodes; The acquisition frequency and monitoring refresh cycle of the corresponding sensing nodes are dynamically adjusted for sensitive control nodes, and the start-up and shutdown sequence and output intensity of the cold source equipment are adjusted according to the model constraint results. Output control and execution parameters to guide the coordinated operation of warehousing and transportation.

[0014] Compared with existing technologies, the present invention provides an intelligent management and monitoring system for cold chain storage and transportation of agricultural products, which has the following beneficial effects: This invention constructs an intelligent management and monitoring system for the cold chain of agricultural products, covering the entire process of warehousing and transportation. It unifies and collaboratively analyzes product attributes, operational behaviors, and cold source operating status, transforming cold chain operation from post-event monitoring to process control. Through multi-source sensing and event-triggered sampling mechanisms, it tightly couples temperature and humidity changes, cold energy recovery processes, and actual operational rhythms, effectively avoiding the problems of missing key information or redundant data collection caused by conventional fixed-frequency sampling. By analyzing the response lag relationship between storage units and cold source supply paths, it can identify potential instability risks caused by unreasonable airflow organization, uneven cold energy distribution, or differences in the heat capacity of goods, transforming cold chain anomalies from passive detection to proactive early warning. Based on the operational impact correlation model, it characterizes the local cold chain constraints, linking cold source scheduling, monitoring strategies, and actual operating conditions, reducing energy waste caused by ineffective refrigeration and excessive adjustment while ensuring the quality and safety of agricultural products. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1 As shown in the figure, an intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to an embodiment of the present invention includes: Multi-source sensing module: synchronously senses the operating status and operation behavior of agricultural product storage units and cold source equipment. Based on the product category, stacking structure and operation frequency, it performs spatial rearrangement and temporal discretization processing on the collected data to form a data input sequence with operation-related semantics.

[0018] The process of synchronously sensing the operating status and operational behavior of agricultural product storage units and cold source equipment in the multi-source sensing module is as follows: By deploying temperature and humidity sensors, location markers, and cargo location status acquisition devices in each agricultural product storage unit, real-time information on cargo location environmental parameters, storage location, and occupancy status can be obtained. By connecting to the operating interface of the cold source equipment, data reflecting the operating status of the cold source can be collected, including the start-up and shutdown status of the chiller, the cooling output level, the operating load, and the adjustment level. Through the work record interface, event-based data collection is performed on loading and unloading operations, opening and closing of refrigerated doors, vehicle entry and exit, and manual intervention, and the status of various sensing data is aligned.

[0019] The process of forming a data input sequence with job-related semantics in the multi-source sensing module is as follows: The system collects operational status data for each agricultural product storage unit. Based on the product category attributes, preservation level, and allowable fluctuation threshold, the collected data is labeled with the product dimension. In cold chain warehousing and transportation scenarios, operational status collection devices deployed in storage locations, loading and unloading channels, and transportation compartments collect operational status data for agricultural product storage units in real time. The operational status data includes at least the start and end times of loading and unloading, the opening status of refrigerated doors, storage location adjustment actions, and transportation start and stop status. Combined with the agricultural product category information pre-registered in the warehousing management system, the system reads the product category attributes, target preservation temperature and humidity range, and allowable fluctuation threshold for each agricultural product in each storage unit. This information is then added as attribute tags to the collected operational status data, thereby completing the product dimension labeling of the original data and giving the operational behavior data for different agricultural products a distinguishable category semantic basis. By combining the hierarchical relationship of storage locations and the stacking topology, spatial mapping and rearrangement are performed on the data from different sensing points. Based on the frequency distribution of operations obtained from historical operation records, the continuous time axis is discretized at non-uniform intervals to generate data segments that match the operation rhythm. After completing the identification of the goods dimension, the data from different sensing points are spatially mapped and rearranged according to the hierarchical relationship of storage locations, stacking methods, and spatial adjacency structure. This ensures that the data order is consistent with the actual storage location layout and stacking topology, avoiding data misalignment caused by differences in the distribution of sensing nodes. Historical operation records are retrieved to statistically analyze the frequency and duration of loading, unloading, and transfer operations. Based on the statistical results, the continuous time axis is discretized at non-uniform intervals. That is, more dense time segments are divided during high-frequency operation periods, and relatively sparse time segments are used during low-frequency operation periods, thereby generating a set of data segments that match the actual operation rhythm. The data segments that have undergone spatial rearrangement and temporal discretization are spliced ​​together according to the rules of association between storage location and operation to form a data input sequence with operation association semantics. After spatial rearrangement and temporal discretization, the data of the same storage location in adjacent time segments are sequentially spliced ​​according to the rules of association between storage location unit and operation behavior. The data segments corresponding to different operation states such as loading and unloading, static placement, and transportation are connected in series with operation event identifiers to form a continuous data sequence. During the splicing process, an association index is established for data segments that cross storage locations but have direct operation association to reflect the influence of operation behavior on adjacent storage locations, generating an operation association semantic data input sequence that can simultaneously represent storage location structure, operation process, and agricultural product attributes.

[0020] Event sampling module: Introduces a dynamic sampling mechanism based on operation event triggering for the data input sequence, and performs segmented tracking of temperature gradient, humidity rebound rate and cold energy recovery cycle to construct a continuous evolution feature set reflecting the stability of the local cold chain.

[0021] The process of introducing a dynamic sampling mechanism based on job event triggering into the data input sequence in the event sampling module is as follows: The system identifies loading / unloading operations, refrigerated door opening / closing, vehicle entry / exit, and cold source start / stop from the data input sequence. Sampling trigger conditions and duration window lengths are pre-set for different types of operational events. During operation, based on the generated data input sequence, the system parses the operational behavior status identifiers to identify operational event nodes such as loading / unloading operations, refrigerated door opening / closing, transport vehicle entry / exit, and cold source equipment start / stop. For different types of operational events, corresponding sampling trigger conditions are pre-configured in the system, including event duration thresholds, impact range determination rules, and event priority levels. A sampling duration window length is set for each type of operational event. This window length is differentiated based on the degree of disturbance the event causes to the cold chain environment. For example, a shorter but higher frequency sampling window is set for refrigerated door opening events, while a sampling window covering the entire operation process and the subsequent cold chain recovery phase is set for loading / unloading operations, thus ensuring that the sampling strategy matches the actual operational characteristics. When an operational event is detected, the sampling frequency of the corresponding storage location and adjacent sensing nodes is temporarily increased. After the operational event ends, the sampling frequency is gradually reduced back to the normal monitoring level according to the cold chain recovery status. When an operational event that meets the sampling trigger conditions is detected, a sampling adjustment command is immediately issued to the corresponding storage location unit and the sensing nodes in its adjacent spatial area to temporarily increase the sampling frequency of temperature, humidity and related operating parameters in order to capture rapid environmental changes that may occur during the operation. After the operational event ends, the recovery status of environmental parameters is continuously monitored. When key indicators such as temperature and humidity are detected to gradually return to the set stable range, the sampling frequency is reduced in stages according to the pre-set rollback strategy to avoid missing abnormal fluctuations in the cold chain recovery process due to a sudden reduction in sampling, thereby achieving a balance between monitoring accuracy and system resource consumption. Dynamic sampling data matching the intensity and duration of operational events is generated. By dynamically adjusting the sampling frequency, more intensive data sampling results are generated during the occurrence of operational events and the cold chain recovery phase, while maintaining the normal sampling density during the stable cold chain operation phase. Data collected under different sampling densities are uniformly time-labeled and attached with corresponding operational event type, event intensity, and duration labels to generate dynamic sampling data matching the intensity and duration of operational events.

[0022] The process of constructing a continuously evolving feature set reflecting local cold chain stability in the event sampling module is as follows: The temperature and humidity change curves of each storage location unit before, during, and after the operation event are extracted from the dynamic sampling data. The rate of change of temperature gradient and humidity rebound speed between adjacent storage locations are calculated. In the dynamic sampling data output by the event sampling module, the environmental monitoring data of each storage location unit is divided into three stages according to the start and end time of the operation event: before the operation event, during the operation, and after the operation. For each stage, the curves of temperature and humidity change over time are extracted to reflect the changing trend of environmental parameters under operation disturbance. According to the spatial adjacency relationship of the storage locations, the temperature data of adjacent storage location units are selected, and the temperature change difference per unit time is calculated to obtain the rate of change of temperature gradient between adjacent storage locations. For humidity data, the rate of change of humidity from the peak to the target range after the operation is completed is calculated to obtain the humidity rebound speed, thus forming a basic feature that can characterize the degree of local environmental disturbance. The time required for environmental parameters to recover to a set stable range after the intervention of cold source equipment is statistically analyzed to obtain the cold energy recovery cycle. The parameters are divided into multiple continuous evolution segments according to time sequence. Taking the end time of the operation event as the starting point, the time required for key parameters such as temperature and humidity to recover to a pre-set stable range is monitored and defined as the cold energy recovery cycle of the corresponding storage unit. According to the time sequence, the data including operation disturbance, parameter fluctuation and recovery process are divided into multiple continuous evolution segments. Each evolution segment corresponds to a complete environmental change process to reflect the dynamic evolution characteristics of the cold chain operation status within a short time scale. Each evolutionary segment is standardized and aggregated to form a continuous evolutionary feature set describing the local cold chain operation status. For the multiple continuous evolutionary segments that have been divided, in order to eliminate the differences in data volume and duration between different storage locations and different operational events, the feature parameters within each evolutionary segment are standardized, including amplitude normalization, time scale alignment, and other operations. After standardization, features such as temperature gradient change rate, humidity rebound rate, and cold energy recovery cycle are aggregated according to a unified feature structure and organized with the evolutionary segment as the basic unit to form a continuous evolutionary feature set used to describe the local cold chain operation status.

[0023] The hysteresis analysis module performs time-series analysis on the temperature and humidity parameter recovery trajectory and cold energy response rhythm presented in the continuous evolution feature set, and characterizes the response hysteresis relationship of different cargo units under the action of cold source supply path. By identifying abnormal offset segments and coupling mismatch intervals in the environmental parameter recovery curve, it screens out risk evolution segments that lead to cold chain instability.

[0024] The process of characterizing the response lag relationship of different storage units under the influence of the cold source supply path in the lag analysis module is as follows: The temperature and humidity recovery trajectories of each storage unit in the continuous evolution feature set are time-aligned. Combined with the air supply path and refrigeration distribution structure of the cold source equipment, the cold source supply path corresponding to each storage unit is determined. In the continuous evolution feature set, the temperature and humidity parameter recovery trajectory corresponding to each storage unit is extracted. The end time of the operation event or the start time of the cold source equipment is used as a unified time reference benchmark. The recovery trajectories of different storage units are time-aligned. Combined with the structural information of the cold chain system, the air supply direction, air duct layout and refrigeration distribution strategy of the cold source equipment are read. By matching the position of the storage unit in the storage space with the air supply path model, the cold source supply path corresponding to each storage unit is determined, so that the response analysis can clearly identify the cold source transmission channel on which the environmental parameter changes depend. This study analyzes the start time and rate of change of parameters in different storage units after the intervention of a cold source, and calculates the time delay difference between the recovery time of environmental parameters of the storage unit and the start time of the cold source. After clarifying the cold source supply path, a fine-grained analysis of the temperature and humidity recovery trajectory of each storage unit is performed to identify the starting time point when the environmental parameters begin to change continuously, and the rate of parameter change is calculated to characterize the response intensity after the cold energy is transferred to the storage unit. Using the actual start time of the cold source equipment as a reference point, the difference between the start time of environmental parameter change and the start time of the cold source is calculated, and this difference is used as the response delay index of the storage unit. By comparing and analyzing the response delays of different storage units, the differences in the transmission and efficiency of the cold source supply path in spatial distribution can be revealed. Establish a description of the response lag relationship between the storage location unit and the cold source supply path; based on the response delay index corresponding to each storage location unit and its cold source supply path information, summarize and organize the response relationship between the storage location unit and the cold source to form a description of the lag relationship that can reflect the difference in response speed of different storage locations under the same cold source conditions. The description results adopt an associated data structure that represents the storage location unit number, cold source supply path identifier and corresponding response delay value, which is used to characterize the degree of influence of the cold source supply path on the local cold chain stability.

[0025] The process of filtering out risk evolution fragments that lead to cold chain instability in the hysteresis analysis module is as follows: The actual temperature and humidity recovery curves are compared with the standard recovery curves of the corresponding goods to identify abnormal deviation segments that exceed the allowable fluctuation range during the recovery process. For the actual temperature and humidity recovery curves of each storage unit that have been acquired, the corresponding standard recovery curve library pre-established in the system is called. The standard recovery curves are generated based on the category attributes, preservation level and historical stable operation data of different agricultural products. By aligning and comparing the actual recovery curves and the standard recovery curves on the same time scale, the deviation of temperature and humidity at each time point is calculated, and it is determined whether it exceeds the allowable fluctuation range corresponding to the goods. When the deviation exceeds the allowable range continuously at multiple consecutive sampling points, the time segment is identified as an abnormal deviation segment to reflect abnormal fluctuations in the environmental recovery process. Based on the response lag relationship, it is determined whether the abnormal offset segment is mismatched with the cold source supply path. Time segments that simultaneously meet the abnormal offset and path coupling mismatch conditions are marked as risk candidate segments. After identifying the abnormal offset segment, the cold source supply situation during the period of the abnormal offset segment is analyzed based on the established response lag relationship between the storage unit and the cold source supply path. It is determined whether the output status of the cold source equipment and the air supply path within the time segment corresponding to the abnormal offset segment match the cooling demand of the storage unit. If the parameter change trend corresponding to the abnormal offset segment is inconsistent with the recovery rhythm that should theoretically be generated by the cold source supply path, then the abnormal offset segment is considered to have path coupling mismatch. When both the abnormal offset condition and the path coupling mismatch condition are met, the corresponding time segment is marked as a risk candidate segment. Adjacent risk candidate segments are merged to form risk evolution segments of cold chain instability. For multiple marked risk candidate segments, they are sorted in chronological order. When adjacent risk candidate segments are consecutive in time or the interval is less than a preset merging threshold, they are regarded as components of the same risk evolution process and merged. Through this merging operation, scattered risk candidate segments are integrated into risk evolution segments that can reflect the entire process of cold chain instability. The risk evolution segments also retain their corresponding storage unit, occurrence time, and abnormal characteristic information.

[0026] Impact Correlation Module: The storage area corresponding to the risk evolution segment is designated as a key monitoring unit. By integrating the refrigeration unit operating load, airflow organization status and cargo heat capacity distribution information within the key monitoring unit, an operational impact correlation model is constructed to describe the local cold chain constraint relationship.

[0027] The process of designating the storage area or transportation segment corresponding to the risk evolution segment as a key monitoring unit in the impact correlation module is as follows: Based on the timestamp and location number corresponding to the risk evolution segment, the corresponding storage area is located. For each selected risk evolution segment, its corresponding timestamp information and location number are read. Through the location-area mapping relationship table pre-established in the storage management system, the specific storage area or transportation segment to which the risk evolution segment belongs is determined. The mapping relationship table is constructed according to the warehouse zoning structure, shelf level and transportation segment number, and is used to describe the correspondence between location number and physical spatial location. In this way, the scattered risk evolution segments are uniformly mapped to a clear spatial area. The frequency and duration of risk evolution segments within the same area are statistically analyzed. When the statistical indicators exceed a preset threshold, the corresponding area is designated as a key monitoring unit, and the spatial range and associated cargo location information of the key monitoring unit are recorded. After completing the area positioning, all risk evolution segments corresponding to the same storage area or transportation segment are statistically analyzed. The frequency of occurrence of risk evolution segments in the area and the duration of a single risk evolution segment are calculated, and the cumulative duration of regional risk is further obtained. When any one or a combination of statistical indicators exceeds a preset risk threshold, the corresponding storage area or transportation segment is designated as a key monitoring unit, and the spatial range information, the set of cargo location numbers included, and the corresponding risk characteristics of the key monitoring unit are recorded for monitoring strategy adjustment and intervention measure formulation.

[0028] The process of constructing the operational influence correlation model in the influence correlation module to describe the local cold chain constraint relationships is as follows: The system collects real-time operating load and output capacity parameters of the chillers within key monitoring units, obtains information on airflow direction, wind speed, and circulation path within these units, and forms an airflow organization state description. It also collects real-time operating load and output capacity parameters of the chiller equipment within designated key monitoring units, including compressor operating load, refrigeration power output level, start / stop frequency, and current adjustment level. Through wind speed sensors, wind direction sensors, and vent status acquisition devices deployed within the key monitoring units, it continuously monitors the cold air delivery direction, local wind speed changes, and air circulation path. Combined with the structural layout information of storage or transportation compartments, the collected data is spatially integrated to form an airflow organization state description reflecting the airflow distribution characteristics and circulation patterns within the key monitoring units. The heat capacity distribution of goods is calculated based on the category and stacking method. The refrigeration unit load, airflow organization, and heat capacity distribution are correlated and mapped to construct an operational impact correlation model describing the constraints of local cold chain operation. After obtaining information on refrigeration unit operating load, airflow organization status, and heat capacity distribution of goods, the equivalent heat capacity distribution of each cargo location unit is calculated based on the category attributes, packaging specifications, and stacking method of different goods. This is used to describe the characteristics of goods absorbing and releasing cold energy. The refrigeration unit load parameter is used as the cold energy supply-side constraint, the airflow organization status is used as the cold energy transfer path constraint, and the heat capacity distribution of goods is used as the cold energy consumption and buffer constraint. The coupling relationship between the three is constructed through correlation mapping to form an operational impact correlation model describing the constraints of local cold chain operation within the key monitoring unit.

[0029] Collaborative control module: Under the constraints of the operational impact correlation model, and in conjunction with the stability change trend within the overall cold chain operation cycle, the module adjusts the sensing node acquisition strategy, monitoring update frequency, and cold source scheduling parameters in a coordinated manner.

[0030] The process of coordinating and adjusting the sensing node acquisition strategy, monitoring update frequency, and cold source scheduling parameters in the coordinated control module is as follows: The stability change trend of each region within the overall cold chain operation cycle is statistically analyzed. The stability change trend is then jointly analyzed with the operation impact correlation model to identify sensitive control nodes. The stability change trend of each storage area or transportation section within the overall cold chain operation cycle is statistically analyzed. The stability change trend is comprehensively characterized by indicators such as the fluctuation amplitude of environmental parameters, recovery speed, and the density of risk evolution segments. The obtained stability change trend is then jointly analyzed with the refrigeration unit load constraints, airflow transmission path constraints, and cargo heat capacity distribution constraints described in the operation impact correlation model to identify cargo space units, airflow channel nodes, or refrigeration unit adjustment nodes that have an amplification effect on stability changes under model constraints. These nodes are then labeled as sensitive control nodes. For sensitive control nodes, the data acquisition frequency and monitoring refresh cycle of the corresponding sensing nodes are dynamically adjusted. The start-up and shutdown sequence and output intensity of the cold source equipment are adjusted according to the model constraint results. After the sensitive control nodes are determined, the data acquisition frequency and monitoring refresh cycle of the sensing equipment corresponding to the nodes are dynamically increased or decreased. The acquisition frequency is adjusted in stages according to the stability fluctuation and recovery lag of the nodes. Under the constraints of the operation impact correlation model, the start-up and shutdown sequence, cooling output intensity and airflow distribution ratio of the cold source equipment are adjusted synchronously to keep the cold source scheduling action consistent with the sensing data update rhythm, thereby avoiding the cooling capacity adjustment from lagging behind environmental changes or causing over-adjustment, and ensuring that the control action is controllable and convergent within the local cold chain range. The system outputs control and execution parameters to guide the coordinated operation of warehousing and transportation. After completing the linkage adjustment between sensing nodes and cold source equipment, the results of each adjustment are parameterized to form a set of control and execution parameters, including the sensing node acquisition cycle, monitoring refresh interval, chiller start and stop time points, and refrigeration output set values. The control and execution parameters are output through the warehousing management system or transportation monitoring terminal to guide the coordinated operation control of the warehousing area and transportation compartment within the same cold chain operation cycle.

[0031] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0032] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent management and monitoring system for cold chain storage and transportation of agricultural products, characterized in that, include: Multi-source sensing module: synchronously senses the operating status and operation behavior of agricultural product storage units and cold source equipment, performs spatial rearrangement and temporal discretization processing on the collected data, and forms a data input sequence with operation-related semantics; Event sampling module: Introduces a dynamic sampling mechanism based on operation event triggering for the data input sequence, and performs segmented tracking of temperature gradient, humidity rebound rate and cold energy recovery cycle to construct a continuous evolution feature set reflecting the stability of the local cold chain; The hysteresis analysis module performs time-series analysis on the continuous evolution feature set, characterizes the response hysteresis relationship of different storage units under the influence of the cold source supply path, and screens out the risk evolution segments that lead to cold chain instability by identifying abnormal offset segments and coupling mismatch intervals in the environmental parameter recovery curve. Impact Correlation Module: The storage area corresponding to the risk evolution segment is designated as a key monitoring unit. Information on the refrigeration unit's operating load, airflow organization status, and cargo heat capacity distribution within the key monitoring unit is integrated to construct an operational impact correlation model. Collaborative control module: Under the constraints of the operational impact correlation model, and in conjunction with the stability change trend within the overall cold chain operation cycle, the module adjusts the sensing node acquisition strategy, monitoring update frequency, and cold source scheduling parameters in a coordinated manner.

2. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of synchronously sensing the operating status and operational behavior of agricultural product storage units and cold source equipment is as follows: By deploying temperature and humidity sensors, location markers, and cargo location status acquisition devices in each agricultural product storage unit, real-time information on cargo location environmental parameters, storage location, and occupancy status can be obtained. By connecting to the operating interface of the cold source equipment, data reflecting the operating status of the cold source can be collected, including the start-up and shutdown status of the chiller, the cooling output level, the operating load, and the adjustment level. Through the work record interface, event-based data collection is performed on loading and unloading operations, opening and closing of refrigerated doors, vehicle entry and exit, and manual intervention, and the status of various sensing data is aligned.

3. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of forming a data input sequence with job-related semantics is as follows: Collect operational status data for each agricultural product storage unit, and label the collected data by product dimension according to the category attributes, freshness level and allowable fluctuation threshold of the agricultural products. By combining the hierarchical relationship of the storage location and the stacking topology, spatial mapping and rearrangement are performed on the data of different sensing points. Based on the frequency distribution of operations obtained from historical operation records, the continuous time axis is discretized at non-equal intervals to generate data segments that match the operation rhythm. The data segments that have undergone spatial rearrangement and temporal discretization are spliced ​​together according to the rules of cargo location and operation association to form a data input sequence with operation association semantics.

4. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of introducing a dynamic sampling mechanism based on job event triggering to the data input sequence is as follows: Identify loading and unloading operations, refrigerated door opening and closing, vehicle entry and exit, and cold source start and stop from the data input sequence, and pre-set sampling trigger conditions and duration window lengths for different types of operational events; When an operational event is detected, the sampling frequency of the corresponding storage location and adjacent area sensing nodes is temporarily increased. After the operational event ends, the sampling frequency is gradually reduced back to the normal monitoring level according to the cold chain recovery status. Generate dynamic sampling data that matches the intensity and duration of the operational event.

5. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of constructing a continuous evolutionary feature set reflecting the stability of the local cold chain is as follows: Extract the temperature and humidity change curves of each storage unit before, during and after the operation event from the dynamic sampling data, and calculate the temperature gradient change rate and humidity rebound speed between adjacent storage units. The time required for environmental parameters to recover to a set stable range after the intervention of the cold source equipment is statistically analyzed to obtain the cold capacity recovery cycle. The parameters are then divided into multiple continuous evolution segments in chronological order. Each evolutionary segment is standardized and aggregated to form a continuous evolutionary feature set describing the local cold chain operation status.

6. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of characterizing the response lag relationship of different storage units under the influence of the cold source supply path is as follows: Time alignment of the temperature and humidity recovery trajectories of each cargo unit in the continuous evolution feature set is performed, and the cold source supply path corresponding to each cargo location is determined by combining the air supply path and refrigeration distribution structure of the cold source equipment. Analyze the start time and rate of change of parameters in different storage units after the cold source is introduced, and calculate the time delay difference between the recovery of environmental parameters of the storage unit and the start time of the cold source. The results describe the response lag relationship between the storage unit and the cold source supply path.

7. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of identifying risk evolutionary segments that lead to cold chain instability is as follows: The actual temperature and humidity recovery curve is compared with the standard recovery curve of the corresponding goods to identify abnormal deviation segments that exceed the allowable fluctuation range during the recovery process. Based on the response lag relationship, it is determined whether the abnormal offset segment is mismatched with the cold source supply path, and the time segment that simultaneously meets the abnormal offset and path coupling mismatch conditions is marked as a risk candidate segment. Adjacent risk candidate segments are merged to form risk evolution segments of cold chain instability.

8. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of designating the storage area or transport segment corresponding to the risk evolution segment as a key monitoring unit is as follows: Based on the timestamp and location number corresponding to the risk evolution segment, locate the corresponding storage area; The frequency and duration of risk evolution segments within the same area are statistically analyzed. When the statistical indicators exceed a preset threshold, the corresponding area is designated as a key monitoring unit, and the spatial range and associated cargo location information of the key monitoring unit are recorded.

9. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of constructing an operational impact correlation model to describe local cold chain constraint relationships is as follows: Collect real-time operating load and output capacity parameters of the chiller in the key monitoring unit, obtain information on airflow direction, wind speed and circulation path in the key monitoring unit, and form a description of airflow organization status; The heat capacity distribution of goods is calculated based on the product category and stacking method. The refrigeration unit load, airflow organization and heat capacity distribution are correlated and mapped to construct an operational impact correlation model that describes the constraints of local cold chain operation.

10. The intelligent management and monitoring system for cold chain storage and transportation of agricultural products according to claim 1, characterized in that, The process of adjusting the sensing node's data acquisition strategy, monitoring update frequency, and cold source scheduling parameters in a coordinated manner is as follows: The stability change trend of each region during the overall cold chain operation cycle is statistically analyzed, and the stability change trend is jointly analyzed with the operation impact correlation model to identify sensitive control nodes; The acquisition frequency and monitoring refresh cycle of the corresponding sensing nodes are dynamically adjusted for sensitive control nodes, and the start-up and shutdown sequence and output intensity of the cold source equipment are adjusted according to the model constraint results. Output control and execution parameters to guide the coordinated operation of warehousing and transportation.

Images