Energy-saving refrigeration regulation method and system based on storage target and internet of things technology

Abstract

The application provides an energy-saving refrigeration regulation method and system based on storage targets and Internet of Things technology, relates to the technical field of Internet of Things, and the system comprises: a data acquisition module used for acquiring storage target objects and historical storage data of a plurality of sub-regions included in a refrigeration region; a temperature and humidity sensing module used for determining an optimal temperature and humidity sensing scheme for each sub-region based on the storage target objects and the historical storage data of the sub-region; and a refrigeration regulation module used for performing temperature and humidity sensing effectiveness verification for each sub-region based on temperature and humidity data of a temperature and humidity sensing position collected by each temperature and humidity sensor, judging whether to perform refrigeration regulation of the sub-region based on the temperature and humidity data of the temperature and humidity sensing position collected by each temperature and humidity sensor after the verification, and determining dynamic regulation parameters of the sub-region through finite element analysis after determining to perform refrigeration regulation of the sub-region, so that the refrigeration intelligent level is improved.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to an energy-saving cooling control method and system based on storage targets and IoT technology. Background Technology

[0002] In cold chain logistics, industrial refrigeration, and commercial cold storage, refrigeration systems are core equipment for ensuring storage quality, and their energy consumption accounts for more than 40% of the overall operating cost. Traditional refrigeration control methods mainly rely on fixed temperature and humidity thresholds, maintaining the storage temperature by starting and stopping the compressor or adjusting the opening of the expansion valve. However, they lack the ability to dynamically sense the storage target and cannot adjust refrigeration parameters in real time according to the temperature and humidity sensitivity differences of the types of goods (such as fresh produce, pharmaceuticals, and chemicals), stacking density, and respiration heat characteristics. This results in temperature and humidity fluctuations within the storage facility ranging from ±3 to 5°C, which not only affects storage quality but also causes 15% to 20% energy waste due to over-refrigeration.

[0003] In recent years, the development of Internet of Things (IoT) technology and edge computing has provided new directions for the intelligentization of refrigeration systems. Among the existing technologies, some solutions monitor the environment inside the cold storage by deploying a network of temperature and humidity sensors, but the sensor layout is limited by the structure of the cold storage, resulting in blind spots and failing to consider the storage requirements of the goods. Other solutions use machine learning algorithms to predict the refrigeration load, but these rely on historical data for training and are not adaptable to sudden operating conditions. A few systems attempt to adjust refrigeration parameters by combining cargo information, but this requires manual input of cargo type and quantity, resulting in low automation and failing to consider the dynamic impact of changes in cargo status (such as heat release from the decay of fresh produce) on refrigeration demand.

[0004] Therefore, there is a need to provide energy-efficient cooling control methods and systems based on storage targets and Internet of Things (IoT) technologies to improve the level of intelligent cooling. Summary of the Invention

[0005] This invention provides an energy-saving cooling control system based on storage targets and Internet of Things (IoT) technology, comprising: a data acquisition module for acquiring storage targets and historical storage data of multiple sub-regions included in the cooling area; a temperature and humidity sensing module for determining the optimal temperature and humidity sensing scheme for each sub-region based on the storage targets and historical storage data of the sub-region, wherein the optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, each temperature and humidity sensing location being equipped with a temperature and humidity sensor; and a cooling control module for performing temperature and humidity sensing validity verification for each sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the temperature and humidity sensing location, and after passing the temperature and humidity sensing validity verification, determining whether to perform cooling control for the sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the temperature and humidity sensing location, and determining the dynamic control parameters of the sub-region through finite element analysis after determining whether to perform cooling control for the sub-region.

[0006] Furthermore, the data acquisition module is used to: determine the temperature and humidity sensing density based on the stored target objects and historical stored data of the sub-region; set up multiple test temperature and humidity sensors based on the temperature and humidity sensing density; collect test datasets through multiple test temperature and humidity sensors, wherein the test datasets include temperature and humidity data collected by each test temperature and humidity sensor at multiple historical time points; and determine the optimal temperature and humidity sensing scheme based on the test datasets.

[0007] Furthermore, the data acquisition module is used to: acquire the breathing intensity of the stored target object in the sub-region; determine the access frequency of the sub-region based on the historical stored data of the sub-region; and determine the temperature and humidity sensing density based on the breathing intensity and access frequency of the stored target object in the sub-region.

[0008] Furthermore, the data acquisition module is used to: determine the similarity of temperature and humidity changes between any two test temperature and humidity sensors based on the test dataset; determine multiple test temperature and humidity sensors to be screened based on the similarity of temperature and humidity changes between any two test temperature and humidity sensors; and determine the optimal temperature and humidity sensing scheme based on the multiple test temperature and humidity sensors to be screened using a butterfly optimization algorithm with improved search strategy.

[0009] Further, the data acquisition module is used for: for each test temperature and humidity sensor to be screened, calculating the temperature and humidity fluctuation value of the test temperature and humidity sensor to be screened based on the temperature and humidity data collected by the test temperature and humidity sensor at multiple historical time points; for any two test temperature and humidity sensors to be screened, calculating the temperature and humidity fluctuation correlation coefficient between the two test temperature and humidity sensors to be screened based on the temperature and humidity data collected by the two test temperature and humidity sensors at multiple historical time points; setting parameters, wherein the parameters include at least population size, maximum number of iterations, search space dimension, convergence accuracy threshold, and step size control parameters; initializing the population, wherein each butterfly includes at least two test temperature and humidity sensors to be screened; and constructing a fitness function, wherein the dependent variable of the fitness function includes at least the temperature and humidity fluctuation value of each test temperature and humidity sensor to be screened included in the butterfly. The correlation coefficients of temperature and humidity fluctuations between any two test temperature and humidity sensors to be screened are calculated; a transition probability function is constructed, wherein the dependent variable of the transition probability function includes at least the search distance between the butterfly and the current global optimum; based on the fitness function, the fragrance intensity of each butterfly is calculated and the global optimum is identified; for each butterfly, based on the transition probability function, the transition probability corresponding to the butterfly is determined, a random number corresponding to the butterfly is generated, and based on the random number corresponding to the butterfly and the transition probability, the search strategy of the butterfly is determined, wherein the search behavior is either global search or adaptive local search. When the search strategy of the butterfly is adaptive local search, based on the test temperature and humidity sensors to be screened included in each butterfly, the search distance of each other butterfly is calculated, and combined with the fitness value of each other butterfly, reference butterflies are screened, and the position is updated based on the reference butterflies; iterative optimization is performed until the termination condition is met to determine the optimal temperature and humidity sensing scheme.

[0010] Furthermore, the cooling control module is used to: determine the calibration time difference and calibration time window of any two temperature and humidity sensors based on the test dataset; for any two temperature and humidity sensors, determine the baseline correlation coefficient of the two temperature and humidity sensors based on the test dataset and the calibration time difference and calibration time window of the two temperature and humidity sensors; determine the current correlation coefficient of the two temperature and humidity sensors based on the temperature and humidity data collected by the two temperature and humidity sensors at their sensing locations and the calibration time difference and calibration time window of the two temperature and humidity sensors; and perform temperature and humidity sensing validity verification based on the baseline correlation coefficient and the current correlation coefficient of any two temperature and humidity sensors.

[0011] Furthermore, the cooling control module is used to: determine multiple calibration parameter combinations, wherein the calibration parameter combination includes a calibration time difference and a calibration time window, and any two calibration parameter combinations include different calibration time differences or calibration time windows; based on the test dataset, determine the correlation coefficient consistency parameter of the two temperature and humidity sensors corresponding to each calibration parameter combination; and based on the correlation coefficient consistency parameter of the two temperature and humidity sensors corresponding to each calibration parameter combination, determine the calibration time difference and calibration time window of the two temperature and humidity sensors.

[0012] Furthermore, the cooling control module is used to: acquire the target temperature and humidity of the stored target object in the sub-region; and determine whether to perform cooling control of the sub-region based on the target temperature and humidity of the stored target object in the sub-region and the temperature and humidity data collected by each temperature and humidity sensor at the sensing location.

[0013] Furthermore, the cooling control module is used to: construct a finite element model of the sub-region; determine similar historical control records based on the temperature and humidity data collected by each temperature and humidity sensor at the sensing location; and determine the dynamic control parameters of the sub-region based on the finite element model of the sub-region, similar historical control records, and the temperature and humidity data collected by each temperature and humidity sensor at the sensing location using a genetic algorithm.

[0014] This invention provides an energy-saving cooling control method based on storage targets and Internet of Things (IoT) technology, applied to the aforementioned energy-saving cooling control system based on storage targets and IoT technology. The method includes: acquiring storage targets and historical storage data for multiple sub-regions within the cooling area; for each sub-region, determining an optimal temperature and humidity sensing scheme based on the storage targets and historical storage data, wherein the optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, each equipped with a temperature and humidity sensor; for each sub-region, performing a temperature and humidity sensing validity verification based on the temperature and humidity data collected by each temperature and humidity sensor at its sensing location; after passing the validity verification, determining whether to perform cooling control for the sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at its sensing location; and, if cooling control for the sub-region is determined, determining the dynamic control parameters for the sub-region through finite element analysis.

[0015] Compared with existing technologies, the energy-saving cooling control method and system based on storage targets and Internet of Things technology provided by this invention have at least the following beneficial effects: 1. By analyzing the characteristics of the stored target objects and historical stored data in the sub-region through the data acquisition module, the optimal temperature and humidity sensing scheme is customized for each sub-region to avoid data distortion caused by unreasonable layout. This ensures that the temperature and humidity data collected by the sensors can truly reflect the environmental status of the sub-region, providing a reliable basis for subsequent regulation and reducing the risk of misregulation caused by data errors.

[0016] 2. Based on historical data, a baseline correlation coefficient is calculated between sensors, and then compared with the correlation coefficient of real-time data. The effectiveness of the sensors is judged by the mean of the difference. This mechanism can identify sensor faults or sudden environmental changes in real time, avoiding invalid data from interfering with control decisions.

[0017] 3. By simulating the temperature and humidity distribution of sub-regions through finite element analysis and combining it with a genetic algorithm to select the optimal parameter combination from historical control records, a dynamic control strategy is generated. This solution can accurately adjust the operating parameters of the cooling equipment according to different storage targets and real-time environmental changes, avoiding energy waste caused by "one-size-fits-all" control. Attached Figure Description

[0018] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein: Figure 1 This is a schematic diagram of a module of an energy-saving cooling control system based on storage targets and Internet of Things technology, according to some embodiments of this specification; Figure 2 This is a flowchart illustrating the determination of the optimal temperature and humidity sensing scheme according to some embodiments of this specification. Figure 3 This is a flowchart illustrating an energy-saving cooling control method based on storage targets and Internet of Things (IoT) technology, according to some embodiments of this specification. Detailed Implementation

[0019] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0020] Figure 1 These are schematic diagrams of modules for an energy-saving cooling control system based on storage targets and Internet of Things (IoT) technology, as shown in some embodiments of this specification. Figure 1 As shown, an energy-saving cooling control system based on storage targets and Internet of Things (IoT) technology may include a data acquisition module, a temperature and humidity sensing module, and a cooling control module.

[0021] The data acquisition module is used to acquire the storage targets and historical storage data of multiple sub-regions included in the cooling area.

[0022] Specifically, the storage target refers to items within a sub-area that require temperature and humidity monitoring; their characteristics directly impact environmental control needs. For example: Medicines: must be strictly controlled at 2-8℃ (refrigerated) or below 25℃ (room temperature), and the humidity must be ≤65%RH to prevent moisture and deterioration.

[0023] Electronic products: Excessive temperature may cause component aging, and excessive humidity may easily cause short circuits. It is necessary to maintain a temperature of 15-30℃ and a humidity of 40-60%RH.

[0024] Food: Different foods have different requirements for temperature and humidity. For example, meat needs to be refrigerated at 0-4℃, and dried goods need to be ≤15℃ and ≤50%RH to prevent mold growth.

[0025] Historical storage data can include the number of times the stored target was stored and retrieved over multiple historical time periods.

[0026] The temperature and humidity sensing module is used to determine the optimal temperature and humidity sensing scheme for each sub-region based on the stored target objects and historical stored data of the sub-region.

[0027] The optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, with a temperature and humidity sensor installed at each location.

[0028] In some embodiments, the data acquisition module is used for: Based on the storage target objects and historical storage data of the sub-region, the temperature and humidity sensing density is determined. Based on the temperature and humidity sensing density, multiple temperature and humidity sensors for testing are set up. For example, multiple temperature and humidity sensors for testing are evenly set up at different horizontal and vertical positions according to the temperature and humidity sensing density. Test datasets were collected using multiple test temperature and humidity sensors, which included temperature and humidity data collected by each test temperature and humidity sensor at multiple historical time points. Based on the test dataset, the optimal temperature and humidity sensing scheme was determined.

[0029] Temperature and humidity sensing density refers to the number of sensors arranged per unit area or volume.

[0030] In some embodiments, the data acquisition module is used for: Obtain the respiratory intensity of the stored target object in the sub-region; Determine the access frequency of a sub-region based on its historical stored data. The temperature and humidity sensing density is determined based on the breathing intensity and access frequency of the stored target objects in the sub-region.

[0031] Specifically, the respiration intensity of a stored object refers to its ability to dynamically change temperature and humidity due to its own metabolism, chemical reactions, or environmental interactions (such as moisture absorption and gas release). For example, fresh foods (such as fruits and meats) continuously release moisture and heat during storage, leading to localized increases in humidity and temperature fluctuations.

[0032] The access frequency of a sub-region can be calculated by dividing the sum of the number of times a target is stored and retrieved in a sub-region over multiple historical time periods by the length of those historical time periods.

[0033] The breathing intensity and access frequency of the stored target objects in the sub-region are normalized. Based on the normalized breathing intensity and access frequency of the stored target objects in the sub-region, the temperature and humidity sensing density is determined. The higher the breathing intensity and access frequency of the normalized stored target objects, the higher the temperature and humidity sensing density.

[0034] The "breathing intensity" of stored objects reflects their ability to dynamically change temperature and humidity due to their own metabolism, chemical reactions, or environmental interactions (such as moisture absorption and gas release). For example, fresh food releases moisture and heat during storage, causing local temperature and humidity fluctuations. Storage and retrieval frequency encompasses not only environmental disturbances caused by human activities but also the impact of the stored object's own temperature and humidity on the surrounding environment, calculated by statistically analyzing historical storage and retrieval frequency and duration. After normalizing both to eliminate dimensional differences, a comprehensive consideration is made, resulting in higher temperature and humidity sensor density for sub-regions with higher breathing intensity and higher storage and retrieval frequency (meaning higher risk of temperature and humidity fluctuations). This approach offers significant benefits: it accurately captures the combined effects of the object's inherent characteristics and external disturbances on temperature and humidity, avoiding the inadequacy of considering a single factor; and it allows for flexible adjustment of sensor density based on the actual risk of different sub-regions, ensuring accurate environmental monitoring while rationally allocating resources, reducing unnecessary sensor deployments, and lowering overall costs.

[0035] In some embodiments, the data acquisition module is used for: Based on the test dataset, determine the similarity of temperature and humidity changes between any two test temperature and humidity sensors; Based on the similarity of temperature and humidity changes between any two test temperature and humidity sensors, multiple test temperature and humidity sensors to be screened are identified. The butterfly optimization algorithm, improved through a search strategy, determines the optimal temperature and humidity sensing scheme based on multiple test temperature and humidity sensors to be screened.

[0036] Specifically, for each test temperature and humidity sensor, a temperature and humidity sequence corresponding to the test temperature and humidity sensor is constructed based on the temperature and humidity data collected by the test temperature and humidity sensor at multiple historical time points. Among them, one element of the temperature and humidity sequence is the temperature and humidity collected by the test temperature and humidity sensor at a historical time point.

[0037] For any two temperature and humidity sensors used for testing, calculate the cosine similarity between the temperature and humidity sequences corresponding to the two temperature and humidity sensors. If the cosine similarity between the two temperature and humidity sensors is greater than the cosine similarity threshold (e.g., 0.7), then retain one of the temperature and humidity sensors used for testing as the test temperature and humidity sensor to be screened.

[0038] Figure 2 This is a flowchart illustrating the determination of the optimal temperature and humidity sensing scheme according to some embodiments shown in this specification, such as... Figure 2 As shown, in some embodiments, the data acquisition module is used for: For each temperature and humidity sensor to be screened, the temperature and humidity fluctuation value of the sensor to be screened is calculated based on the temperature and humidity data collected by the sensor at multiple historical time points. For example, the variance of the temperature and humidity data collected by the sensor to be screened at multiple historical time points can be calculated as the temperature and humidity fluctuation value of the sensor to be screened. For any two temperature and humidity sensors to be screened, the temperature and humidity fluctuation correlation coefficient between the two sensors is calculated based on the temperature and humidity data collected at multiple historical time points. For example, the temperature and humidity data collected at multiple historical time points of the two sensors to be screened can be substituted into the calculation formula of the correlation coefficient (e.g., Pearson correlation coefficient) to obtain the temperature and humidity fluctuation correlation coefficient between the two sensors to be screened. Parameter settings include at least the population size, maximum number of iterations, search space dimension, convergence accuracy threshold, and step size control parameter. The population size determines the breadth of the algorithm's search; too small a population size can easily lead to local optima, while too large a population size increases the computational burden. The maximum number of iterations limits the algorithm's running time, requiring a trade-off between convergence speed and result quality. The search space dimension corresponds to the number of temperature and humidity sensors to be screened for testing; the higher the dimension, the more exponentially the problem complexity increases. The convergence accuracy threshold is used to determine whether the algorithm terminates; iteration stops when the fitness value changes less than this threshold. The step size control parameter adjusts the stride length of the butterfly individuals; too large a step size may cause oscillations, while too small a step size results in slow convergence. Population initialization is performed, wherein each butterfly includes at least two test temperature and humidity sensors to be screened, for example, sampling from multiple test temperature and humidity sensors to be screened as one butterfly; A fitness function is constructed, wherein the dependent variable of the fitness function includes at least the temperature and humidity fluctuation values ​​of each temperature and humidity sensor to be screened in the butterfly and the temperature and humidity fluctuation correlation coefficients of any two temperature and humidity sensors to be screened. Specifically, the temperature and humidity fluctuation values ​​of each temperature and humidity sensor to be screened in the butterfly are summed to obtain the total temperature and humidity fluctuation values. The average temperature and humidity fluctuation correlation coefficients of any two temperature and humidity sensors to be screened in the butterfly are averaged to obtain the average temperature and humidity fluctuation correlation coefficient. The larger the total temperature and humidity fluctuation values ​​and the higher the average temperature and humidity fluctuation correlation coefficient, the greater the fitness value of the butterfly. The fitness function can also include the number of temperature and humidity sensors to be screened. The fewer the number of temperature and humidity sensors to be screened in the butterfly, the greater the fitness value of the butterfly. By comprehensively considering the three factors of the total temperature and humidity fluctuation values, the average correlation coefficient, and the number of sensors, the optimization algorithm is effectively guided to screen out a high-quality sensor layout scheme. The larger the sum of temperature and humidity fluctuation values, the greater the temperature and humidity changes at the location of the temperature and humidity sensor to be screened, which is a location where storage targets are likely to accumulate, and can more accurately capture temperature and humidity dynamics; the higher the average correlation coefficient, the stronger the data complementarity between sensors; and the fewer sensors there are, the lower the cost and energy consumption can be while meeting monitoring requirements, so that the algorithm can automatically eliminate layouts with small fluctuations, low correlations, or redundant numbers during iteration, and finally generate a sensor network that ensures both monitoring accuracy and high efficiency and economy. A transition probability function is constructed, where the dependent variable of the transition probability function includes at least the search distance between the butterfly and the current global optimum. The overlap between the test temperature and humidity sensors included in the butterfly and those included in the butterfly corresponding to the current global optimum can be calculated to obtain the search distance between the butterfly and the current global optimum. A higher overlap results in a smaller search distance between the butterfly and the current global optimum, leading to a lower transition probability. This indicates a high similarity between the current butterfly layout and the optimal solution. In this case, reducing the transition probability can reduce ineffective perturbations near high-quality solutions and accelerate local fine-tuning. Conversely, a low overlap (larger search distance) increases the transition probability, enhancing the butterfly's tendency to migrate towards the global optimum and avoiding getting trapped in local optima. Based on the fitness function, the fragrance intensity of each butterfly is calculated and the global optimal solution is identified; For each butterfly, the transition probability corresponding to the butterfly is determined based on the transition probability function, and a random number corresponding to the butterfly is generated. Based on the random number corresponding to the butterfly and the transition probability, the search strategy for the butterfly is determined. The search behavior is either a global search or an adaptive local search. When the search strategy for the butterfly is an adaptive local search, the search distance of each other butterfly is calculated based on the temperature and humidity sensors to be screened for each butterfly. Combined with the fitness value of each other butterfly, a reference butterfly is selected. Based on the reference butterfly, the position is updated. The method of calculating the search distance between any two butterflies is similar to the method of calculating the search distance between the butterfly and the current global optimal solution, and will not be elaborated here. The search distance and fitness value of each other butterfly can be normalized. The normalized search distance and fitness value are weighted and summed to calculate the reference probability of the butterfly. The larger the normalized search distance and fitness value, the larger the reference probability of the butterfly. The butterfly with the highest reference probability is selected as the reference butterfly. The position update formula for global search and the position update formula for adaptive local search are existing technologies, and will not be elaborated here. Iterative optimization continues until termination conditions are met (e.g., reaching the maximum number of iterations, or if the fitness value of the optimal solution changes less than the convergence accuracy threshold in several consecutive iterations), to determine the optimal temperature and humidity sensing scheme.

[0039] The cooling control module is used to verify the validity of temperature and humidity sensors for each sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location. After the validity verification is passed, it determines whether to perform cooling control for the sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location. After determining whether to perform cooling control for the sub-region, it determines the dynamic control parameters of the sub-region through finite element analysis.

[0040] In some embodiments, the cooling control module is used for: Based on the test dataset, determine the calibration time difference and calibration time window for any two temperature and humidity sensors; For any two temperature and humidity sensors, the baseline correlation coefficient of the two temperature and humidity sensors is determined based on the test dataset and the calibration time difference and calibration time window of the two temperature and humidity sensors. The current correlation coefficient of the two temperature and humidity sensors is determined based on the temperature and humidity data collected by the two temperature and humidity sensors at the sensing locations and the calibration time difference and calibration time window of the two temperature and humidity sensors. The effectiveness of temperature and humidity sensing is verified based on the baseline correlation coefficient and the current correlation coefficient of any two temperature and humidity sensors.

[0041] In some embodiments, the cooling control module is used for: Multiple verification parameter combinations are determined. Each verification parameter combination includes a verification time difference and a verification time window. Any two verification parameter combinations may have different verification time differences or verification time windows. For example, the verification time window may be 20 seconds, 30 seconds, 40 seconds, 60 seconds, etc., and the verification time difference may be 5 seconds, 10 seconds, 15 seconds, etc. Based on the test dataset, determine the correlation coefficient consistency parameter of the two temperature and humidity sensors corresponding to each combination of verification parameters. Based on the consistency parameters of the correlation coefficients of the two temperature and humidity sensors corresponding to each combination of calibration parameters, the calibration time difference and calibration time window of the two temperature and humidity sensors are determined.

[0042] Specifically, the correlation coefficient consistency parameter between the two temperature and humidity sensors corresponding to each combination of calibration parameters can be determined according to the following procedure: S1. By verifying the time difference and the time window, the temperature and humidity data collected by the two temperature and humidity sensors in the test dataset at multiple historical time points are divided into multiple data segments. The time length of the data segment is the verification time window, and the difference between the start times of the data segments of the two temperature and humidity sensors corresponding to the same verification time window is the verification time difference. S2. For each calibration time window, substitute the temperature and humidity data collected by the two temperature and humidity sensors at multiple historical time points corresponding to the calibration time window into the calculation formula of the correlation coefficient (e.g., Pearson correlation coefficient, etc.) to obtain the correlation coefficient of the two temperature and humidity sensors corresponding to the calibration time window. S3. Calculate the variance of the correlation coefficients of the two temperature and humidity sensors for each calibration time window. The larger the variance, the smaller the consistency parameter of the correlation coefficients of the two temperature and humidity sensors corresponding to the calibration parameter combination.

[0043] Select the calibration parameter combination with the highest correlation coefficient consistency parameter, and determine the calibration time difference and calibration time window for the two temperature and humidity sensors.

[0044] Based on the calibration time difference and calibration time window of the two temperature and humidity sensors, the mean value of the correlation coefficient of the two temperature and humidity sensors for each calibration time window is calculated as the benchmark correlation coefficient of the two temperature and humidity sensors.

[0045] Based on the calibration time difference and calibration time window of the two temperature and humidity sensors, the temperature and humidity data collected by the two temperature and humidity sensors at multiple time points are processed, and the average value of the correlation coefficient of the two temperature and humidity sensors for each calibration time window is calculated as the current correlation coefficient of the two temperature and humidity sensors.

[0046] For any two temperature and humidity sensors, calculate the difference between the baseline correlation coefficient and the current correlation coefficient of the two sensors. Calculate the mean of the differences between the baseline and current correlation coefficients of any two temperature and humidity sensors. If the mean difference is less than a threshold (e.g., 0.1), the validity check is considered passed.

[0047] First, by comparing and analyzing multiple sets of verification parameter combinations (such as different combinations of time windows and time differences), the combination with the highest consistency of correlation coefficient parameters is selected, ensuring that the verification parameters can reflect the true correlation between sensors to the greatest extent and avoiding misjudgment due to improper parameter settings. Second, using the benchmark correlation coefficient as a benchmark, by comparing the average difference of the current correlation coefficient (such as setting the threshold to 0.1), it is possible to dynamically identify whether the sensor data is distorted due to faults, positional shifts, or environmental changes, and to trigger maintenance or adjustments in a timely manner to ensure the reliability of monitoring data.

[0048] In some embodiments, the cooling control module is used for: Obtain the target temperature and humidity of the stored target object in the sub-region; Based on the target temperature and humidity of the stored target object in the sub-region and the temperature and humidity data collected by each temperature and humidity sensor at the sensor location, it is determined whether to perform cooling control in the sub-region.

[0049] Specifically, the cooling control module acquires the target temperature and humidity of the stored items in the sub-region (e.g., the fresh food area needs to maintain 2-8℃ and 45%-65% humidity), and dynamically compares it with the local temperature and humidity data collected in real time by each temperature and humidity sensor to achieve precise control decisions. Specifically, it monitors the temperature and humidity values ​​at each sensor location in real time and calculates the degree of deviation from the target range. If the deviation exceeds a certain percentage (e.g., 30%) of the temperature and humidity sensor locations (e.g., 20%), it determines that there is an environmental anomaly risk in that sub-region and initiates cooling control for that sub-region.

[0050] In some embodiments, the cooling control module is used for: Construct a finite element model of the sub-region; Based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location, similar historical control records are identified. Using a genetic algorithm, based on the finite element model of the sub-region, similar historical control records, and temperature and humidity data collected by each temperature and humidity sensor at its sensing location, the dynamic control parameters of the sub-region are determined.

[0051] Specifically, the refrigeration control module first establishes a three-dimensional finite element model for the storage sub-area (such as a specific shelving area or cold storage compartment), dividing the space into multiple micro-units and defining their physical properties (such as airflow resistance and thermal conductivity) and boundary conditions (such as wall insulation performance and equipment heat dissipation). This model can simulate the dynamic distribution of temperature and humidity in the space, such as the temperature gradient change when cold air diffuses from the air conditioner vent to each shelf layer, providing a physical simulation basis for subsequent parameter optimization. Control cases similar to the current temperature and humidity sensor data are selected from the historical database. For example, if the current sensor detects that the temperature in the middle shelf layer is too high (28℃) and the humidity is too low (40%), then historical control records at the same sensor location under similar temperature and humidity conditions (such as temperature 27-29℃, humidity 38-42%) are matched, including parameters such as the air conditioner fan speed, air outlet angle, and humidifier power, as well as the control effect (such as the time taken to drop the temperature to 25℃ in 10 minutes). By reusing historical data, optimization from scratch is avoided, improving decision-making efficiency. Using a finite element model as the simulation environment, a genetic algorithm encodes historical regulation parameters as "chromosomes" (e.g., wind speed 5 m / s → gene 0101), generating multiple sets of candidate parameters through selection, crossover, and mutation operations. After each set of parameters is input into the model, the simulation runs for a period of time (e.g., 30 minutes), outputting the predicted results for temperature and humidity distribution and energy consumption. By comparing the deviations between the predicted values ​​and the target values ​​(e.g., temperature 25℃, humidity 50%), and combining the energy consumption prediction results, the fitness is calculated (the less time, the smaller the deviation, and the lower the energy consumption, the higher the fitness). The optimal parameter combination is then selected to quickly balance the temperature and humidity of the sub-region to the target range, while also optimizing energy consumption.

[0052] Figure 3 This is a flowchart illustrating an energy-saving cooling control method based on storage targets and Internet of Things (IoT) technology, as shown in some embodiments of this specification. Figure 3 As shown, an energy-saving cooling control method based on storage targets and Internet of Things (IoT) technology may include the following steps: Acquire the storage targets and historical storage data of multiple sub-regions included in the cooling zone; For each sub-region, based on the stored target objects and historical stored data of the sub-region, the optimal temperature and humidity sensing scheme is determined. The optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, and each temperature and humidity sensing location is equipped with a temperature and humidity sensor. For each sub-region, the validity of the temperature and humidity sensors is verified based on the temperature and humidity data collected at the sensing locations of each temperature and humidity sensor. After the validity verification is passed, it is determined whether to implement cooling control for the sub-region based on the temperature and humidity data collected at the sensing locations of each temperature and humidity sensor. If it is determined that cooling control should be implemented for the sub-region, the dynamic control parameters of the sub-region are determined through finite element analysis.

[0053] For a more detailed description of energy-saving cooling control methods based on storage targets and IoT technology, please refer to the relevant description of energy-saving cooling control systems based on storage targets and IoT technology, which will not be repeated here.

[0054] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. An energy-saving cooling control system based on storage targets and Internet of Things (IoT) technology, characterized in that, include: The data acquisition module is used to acquire the storage target objects and historical storage data of multiple sub-regions included in the cooling area; The temperature and humidity sensing module is used to determine the optimal temperature and humidity sensing scheme for each sub-region based on the stored target objects and historical stored data of the sub-region. The optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, and each temperature and humidity sensing location is equipped with a temperature and humidity sensor. The cooling control module is used to verify the validity of temperature and humidity sensors for each sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location. After the validity verification is passed, it determines whether to perform cooling control for the sub-region based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location. After determining whether to perform cooling control for the sub-region, it determines the dynamic control parameters of the sub-region through finite element analysis.

2. The energy-saving cooling control system based on storage target and Internet of Things technology according to claim 1, characterized in that, The data acquisition module is used for: Based on the storage target objects and historical storage data of the sub-region, the temperature and humidity sensing density is determined. Based on the temperature and humidity sensing density, multiple temperature and humidity sensors for testing were set up. Test datasets are collected using multiple test temperature and humidity sensors, wherein the test datasets include temperature and humidity data collected by each test temperature and humidity sensor at multiple historical time points; Based on the test dataset, the optimal temperature and humidity sensing scheme was determined.

3. The energy-saving cooling control system based on storage target and Internet of Things technology according to claim 2, characterized in that, The data acquisition module is used for: Obtain the respiratory intensity of the stored target object in the sub-region; Determine the access frequency of a sub-region based on its historical stored data. The temperature and humidity sensing density is determined based on the breathing intensity and access frequency of the stored target objects in the sub-region.

4. The energy-saving cooling control system based on storage target and Internet of Things technology according to claim 2, characterized in that, The data acquisition module is used for: Based on the test dataset, determine the similarity of temperature and humidity changes between any two test temperature and humidity sensors; Based on the similarity of temperature and humidity changes between any two test temperature and humidity sensors, multiple test temperature and humidity sensors to be screened are identified. The butterfly optimization algorithm, improved through a search strategy, determines the optimal temperature and humidity sensing scheme based on multiple test temperature and humidity sensors to be screened.

5. The energy-saving cooling control system based on storage target and Internet of Things technology according to claim 4, characterized in that, The data acquisition module is used for: For each temperature and humidity sensor to be screened, the temperature and humidity fluctuation value of the sensor to be screened is calculated based on the temperature and humidity data collected by the sensor at multiple historical time points. For any two temperature and humidity sensors to be screened, the correlation coefficient of temperature and humidity fluctuations between the two temperature and humidity sensors is calculated based on the temperature and humidity data collected by the two temperature and humidity sensors at multiple historical time points. Parameter settings are performed, wherein the parameters include at least the population size, maximum number of iterations, search space dimension, convergence accuracy threshold, and step size control parameters; Population initialization was performed, in which each butterfly included at least two test temperature and humidity sensors to be screened; Construct a fitness function, wherein the dependent variable of the fitness function includes at least the temperature and humidity fluctuation values ​​of each test temperature and humidity sensor to be screened in the butterfly and the temperature and humidity fluctuation correlation coefficients of any two test temperature and humidity sensors to be screened. Construct a transformation probability function, wherein the dependent variable of the transformation probability function includes at least the search distance between the butterfly and the current global optimum; Based on the fitness function, the fragrance intensity of each butterfly is calculated and the global optimal solution is identified; For each butterfly, the transition probability corresponding to the butterfly is determined based on the transition probability function, and a random number corresponding to the butterfly is generated. Based on the random number corresponding to the butterfly and the transition probability, the search strategy for the butterfly is determined. The search behavior is either a global search or an adaptive local search. When the search strategy for the butterfly is an adaptive local search, the search distance of each other butterfly is calculated based on the test temperature and humidity sensors included in each butterfly. Combined with the fitness value of each other butterfly, reference butterflies are selected. Based on the reference butterflies, the position is updated. Iterative optimization continues until the termination condition is met, determining the optimal temperature and humidity sensing scheme.

6. The energy-saving cooling control system based on storage target and Internet of Things technology according to any one of claims 2-4, characterized in that, The cooling control module is used for: Based on the test dataset, determine the calibration time difference and calibration time window for any two temperature and humidity sensors; For any two temperature and humidity sensors, the baseline correlation coefficient of the two temperature and humidity sensors is determined based on the test dataset and the calibration time difference and calibration time window of the two temperature and humidity sensors. The current correlation coefficient of the two temperature and humidity sensors is determined based on the temperature and humidity data collected by the two temperature and humidity sensors at the sensing locations and the calibration time difference and calibration time window of the two temperature and humidity sensors. The effectiveness of temperature and humidity sensing is verified based on the baseline correlation coefficient and the current correlation coefficient of any two temperature and humidity sensors.

7. The energy-saving cooling control system based on storage target and Internet of Things technology according to claim 6, characterized in that, The cooling control module is used for: Multiple verification parameter combinations are determined, wherein the verification parameter combination includes verification time difference and verification time window, and any two verification parameter combinations include different verification time differences or verification time windows; Based on the test dataset, determine the correlation coefficient consistency parameter of the two temperature and humidity sensors corresponding to each combination of verification parameters. Based on the consistency parameters of the correlation coefficients of the two temperature and humidity sensors corresponding to each combination of calibration parameters, the calibration time difference and calibration time window of the two temperature and humidity sensors are determined.

8. The energy-saving cooling control system based on storage target and Internet of Things technology according to any one of claims 1-4, characterized in that, The cooling control module is used for: Obtain the target temperature and humidity of the stored target object in the sub-region; Based on the target temperature and humidity of the stored target object in the sub-region and the temperature and humidity data collected by each temperature and humidity sensor at the sensor location, it is determined whether to perform cooling control in the sub-region.

9. The energy-saving cooling control system based on storage target and Internet of Things technology according to any one of claims 1-4, characterized in that, The cooling control module is used for: Construct a finite element model of the sub-region; Based on the temperature and humidity data collected by each temperature and humidity sensor at the sensor location, similar historical control records are identified. Using a genetic algorithm, based on the finite element model of the sub-region, similar historical control records, and temperature and humidity data collected by each temperature and humidity sensor at its sensing location, the dynamic control parameters of the sub-region are determined.

10. An energy-saving cooling control method based on storage targets and Internet of Things (IoT) technology, characterized in that, The energy-saving cooling control system based on storage target and Internet of Things technology as described in claim 1 includes: Acquire the storage targets and historical storage data of multiple sub-regions included in the cooling zone; For each sub-region, based on the stored target objects and historical stored data of the sub-region, the optimal temperature and humidity sensing scheme is determined. The optimal temperature and humidity sensing scheme includes multiple temperature and humidity sensing locations, and each temperature and humidity sensing location is equipped with a temperature and humidity sensor. For each sub-region, the validity of the temperature and humidity sensors is verified based on the temperature and humidity data collected at the sensing locations of each temperature and humidity sensor. After the validity verification is passed, it is determined whether to implement cooling control for the sub-region based on the temperature and humidity data collected at the sensing locations of each temperature and humidity sensor. If it is determined that cooling control should be implemented for the sub-region, the dynamic control parameters of the sub-region are determined through finite element analysis.

Images