Granary side wall temperature control system and method based on big data analysis

Abstract

The invention relates to the technical field of grain storage, in particular to a granary side wall temperature control system and method based on big data analysis, in the granary side wall temperature control system and method based on big data analysis, computing power, thermal power and environmental parameters are integrated in real time through a dynamic correlation modeling module, and a multi-dimensional data tensor of space-time alignment is constructed; a dynamic weight parameter set containing an environment interference factor, a real-time correlation matrix and a historical correlation mode is generated by combining sliding time window analysis, and the problem of heat dissipation response lag caused by data isolation in a traditional method is solved; the hierarchical decision-making module is based on a double-time scale framework, a load migration path and a priority weight are dynamically generated by a micro layer according to a real-time incidence matrix, calculation power immediate balance in a heat sensitive scene is achieved, a heat dissipation strategy is evolved and optimized by a macro layer through a superposition historical mode and a real-time trend, and an environment interference factor correction instruction is periodically fused, so that the calculation power immediate balance in the heat sensitive scene is achieved. Dynamic collaborative optimization of computing power and heat dissipation is achieved, local overheating is avoided, energy consumption is reduced, and the energy efficiency and operation stability of the data center are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of grain storage, and in particular to a grain silo side wall temperature control system and method based on big data analysis. Background Art

[0002] The grain silo side wall temperature control system based on big data analysis is a system that uses big data technology to analyze the temperature change patterns of the grain pile and maintains a stable environment in the silo by intelligently controlling the silo wall cooling power. Its goal is to ensure grain storage safety and reduce energy consumption.

[0003] However, the system still faces certain challenges, such as how to accurately adjust the cooling power of the warehouse wall according to the temperature change trend inside the grain pile to effectively solve the problem of pest breeding caused by local overheating.

[0004] The core of this problem lies in the need to simultaneously monitor and predict the temperature distribution inside the grain pile, and accordingly achieve dynamic and precise power allocation and regulation, which may be affected by factors such as data accuracy, algorithm prediction ability and system response speed. Summary of the Invention

[0005] The present invention aims to provide a granary sidewall temperature control system and method based on big data analysis to solve the problems raised in the above background technology. Specific technical issues include: how to regulate the silo wall cooling power according to the temperature change trend inside the grain pile to solve the problem of local overheating leading to pest breeding.

[0006] To achieve the above-mentioned purpose, the present invention aims at a grain silo side wall temperature control system based on big data analysis, including: a data acquisition module for collecting temperature data through sensors inside the grain pile; a big data analysis module, which is in communication with the data acquisition module and uses a big data analysis algorithm to predict the temperature change trend inside the grain pile; a temperature control area determination module, which determines the target temperature control area and refrigeration demand according to the temperature change trend; a power calculation module, which calculates the power adjustment parameters of the side wall refrigeration equipment based on the refrigeration demand; and an equipment control module, which applies the adjustment parameters to the side wall refrigeration equipment and dynamically adjusts the refrigeration power. The big data analysis module is connected to the power calculation module; based on the formula Determine whether the temperature change trend exceeds the warning range, To predict the temperature change rate, K1 is the temperature sensitivity coefficient, T target is the expected target temperature, T current is the current collected temperature;

[0007] If not satisfied, the power calculation module sets P adjust =P initial ×r1, otherwise increase the control sensitivity r2, and adjust Promoted to P initial×r2, r1 is the initial power correction factor, r2 is the power correction factor after the control sensitivity is improved, and the equipment control module controls the operation of the side wall refrigeration equipment accordingly.

[0008] The temperature control area determination module includes a distance weight calculation unit, which calculates the distance weight W of the target temperature control area. d =e λ×d , d is the distance between the sensor position and the refrigeration side wall, λ is the spatial attenuation coefficient;

[0009] Also includes a weighted average unit, based on W d Weighted average of temperature sampling data;

[0010] The power calculation module uses P adjust ≥K2×ΔT×W d Calibrate the power adjustment parameters, K2 represents the power correction coefficient, ΔT is the target temperature offset, and the device control module sets differentiated cooling power adjustments for different distance zones.

[0011] The big data analysis module includes a temperature gradient calculation unit, which uses the formula Determine the dynamic temperature gradient, G T is the temperature gradient value, T top and T bottom are the temperatures of the upper and lower sampling points of the grain pile, respectively, and ΔH is the vertical height difference;

[0012] When G T >Threshold G When the temperature is controlled by the equipment control module, the local cooling power is increased to P zone =Base P +G T ×P factor , and set the partition power limit; among them, Threshold G is the temperature gradient threshold, Base P is the basic power, P factor is the power impact factor.

[0013] The equipment control module includes a priority allocation unit, which allocates priorities according to the cooling requirements of the zones and allocates priority to the temperature control units N that meet the temperature warning conditions. i , if (T max -T min )>K3×Tavg, give priority to adjusting the maximum power regional cooling module, and apply the special mode power Max(P i ×α),α=5,update and redistribute the remaining power to ensure energy balance;

[0014] Among them, T max and Tmin They are temperature control unit N i The highest and lowest temperatures in the room; K3 is the temperature difference coefficient; Tavg is the temperature control unit N i The average temperature inside; P i Temperature control unit N i Cooling power; Max P is the maximum power allowed by the system; i is the number of the temperature control unit, ranging from 1 to N; N is the total number of zones.

[0015] The big data analysis module includes a risk assessment unit, which introduces a time series prediction model to assess overheating risk R overheat , the historical temperature fitting goodness of fit is measured by mean square error MSE(t+1). When MSE exceeds the preset level, the power calculation module Adjust power parameters to optimize power consumption performance;

[0016] Power New The new power after adjustment; Power Base Refers to the benchmark cooling power; K4 is the empirical calibration constant, ε=

[0017] 1×10 -6 , used to prevent the denominator from being zero; MSE t is the mean square error at time t.

[0018] The big data analysis module includes an anomaly detection unit, which detects abnormal points through the temperature change slope. err <Threshold s ×log(σ), σ is the standard deviation of the predicted fluctuation. The equipment control module freezes the current power value and corrects the cooling effect in combination with the feedback closed loop. Press Recovery pows =min(Cap Max ,C0 powers +β×σ slope ) restore power;

[0019] Among them, slope err is the temperature change slope error, Threshold s is the slope error threshold; β controls the power ramp speed, Cap Max is the power upper limit; C0 powers is the power value when frozen; σ slope is the standard deviation of the temperature change slope.

[0020] The equipment control module includes a compensation mechanism unit and a power planning unit; the compensation mechanism unit is based on the situation that the local overheating has not been restored for a long time. To start the compensation cooling module, press Eadd =Comp Ratio ×P zone Increased energy consumption;

[0021] Among them, t stay is the duration of the overheating state in the local area; T cycle is the system monitoring period; γ is the compensation start threshold, Comp Ratio To compensate for the power ratio, P zone is the cooling power of the local area;

[0022] The power planning unit pre-plans a dynamic power curve based on environmental fluctuations. It uses a piecewise polynomial representation, with each part corresponding to a working condition switch. The specific calculation logic is: Each order coefficient corresponds to the influence of different control variables; finally, the power output at each moment is combined into a complete operation diagram; among them, C k is the power calculation value at time k; a k are polynomial coefficients; t is time; p k is the polynomial order;

[0023] It also includes an efficiency evaluation module, which is connected to the equipment control module to optimize the function through cost saving Comprehensively evaluate the long-term economic performance of the system, including J energy (i,j) represents the actual electricity consumption record value of the jth refrigeration equipment in the i-th time period; Total Eff is the comprehensive efficiency index of the system, and η is the energy-saving gain weight.

[0024] The method of the granary side wall temperature control system based on big data analysis includes the following steps:

[0025] S1. Based on the temperature data collected by sensors inside the grain pile, use big data analysis to predict the temperature change trend inside the grain pile;

[0026] S2. Determine the target temperature control area and the corresponding cooling demand based on the predicted temperature change trend;

[0027] S3. Calculate adjustment parameters of the side wall cooling equipment power based on the cooling demand;

[0028] S4. Applying the adjustment parameters to the side wall refrigeration equipment to dynamically adjust the refrigeration power, suppress local overheating and prevent pest breeding. Compared with the prior art, the beneficial effects of the present invention are:

[0029] This grain silo side wall temperature control system, based on big data analysis, uses the big data analysis module to deeply mine internal grain pile temperature data and make accurate predictions. Working in conjunction with the temperature control area determination module and the power calculation module, it can dynamically and accurately adjust the power of the silo wall refrigeration equipment based on the real-time and predicted temperature change trends of the grain pile, avoiding local overheating and creating a stable temperature environment for grain storage. Precise temperature control keeps the internal temperature of the grain pile within a range unsuitable for pest growth and reproduction, fundamentally reducing the risk of pest breeding caused by local overheating and ensuring grain storage safety. The system's modules efficiently exchange data and perform rapid calculations, overcoming data processing delays and significantly improving the response speed to changes in grain pile temperature. If the grain pile temperature fluctuates abnormally, the equipment control module can quickly adjust the refrigeration power and intervene in the grain pile temperature in a timely manner. The efficiency evaluation module evaluates the long-term economic operation of the system, and the power planning unit rationally plans the power under different operating conditions, realizing on-demand allocation of refrigeration power. This ensures the safety of grain storage while effectively reducing overall energy consumption and saving operating costs, achieving both economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the M process of the present invention;

[0031] Figure 2 It is a schematic diagram of M of the present invention. DETAILED DESCRIPTION

[0032] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0033] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "an", "a", "the", "these" and the like in this application do not indicate quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0034] Next, see Figure 1 This invention describes a grain silo sidewall temperature control system based on big data analysis and how it regulates sidewall cooling power to address the problem of localized overheating leading to pest infestation. The entire system includes multiple steps: data acquisition and processing, trend prediction, determination of target temperature control areas and cooling requirements, calculation of cooling equipment power parameters, and dynamic adjustment of sidewall cooling power. One objective of this embodiment is to provide a grain silo sidewall temperature control system based on big data analysis. The system includes a data acquisition module that collects temperature data from sensors within the grain pile. The first step involves collecting and processing temperature data from sensors within the grain pile. During this process, a large number of temperature sensors are placed at various depths and locations within the grain pile, regularly recording temperature information at each node. The acquired data is cleaned and standardized before being stored in a database. This multi-dimensional, real-time data collection method provides a comprehensive understanding of the grain storage environment. For example, a sensor array is placed every 10 cubic meters within the grain silo, each array containing temperature sensors at different heights on three horizontal planes. These sensors upload their measured data via a wireless network to a big data platform within a centralized controller, providing a comprehensive and reliable foundation for subsequent data analysis.

[0035] The big data analysis module is in communication with the data acquisition module, and uses the big data analysis algorithm to predict the temperature change trend inside the grain pile; secondly, the second step is to use big data technology to predict the temperature change trend inside the grain pile. This operation relies on machine learning algorithms such as random forest regression or long short-term memory (LSTM) network models. The system trains an accurate trend prediction model through massive data sets accumulated historically, which can estimate the temperature values that each area may reach in a short period of time in the future, and discover risk areas where high temperature anomalies may occur. Specifically, a deep neural network structure with time series labels is used for fitting operations to infer the trend of local heat accumulation in the short term. This can help operation and maintenance personnel predict risk areas in advance and take proactive precautions rather than just passively responding to sudden problems. In one embodiment, if the average daily temperature rise in a certain grain layer exceeds 0.3°C for three consecutive days, the system will automatically mark it as a key focus and prepare to implement a stricter cooling control plan;

[0036] The temperature control area determination module determines the target temperature control area and cooling demand based on the temperature change trend; the power calculation module calculates the power adjustment parameters of the side wall refrigeration equipment based on the cooling demand; then, the third step is to clarify the target temperature control area and the corresponding cooling demand based on the above prediction results. This step combines the properties of the grain itself and the physical conditions of the storage to comprehensively determine which places do have excessive possibilities and thus pose risks of pests. If certain local areas are expected to reach the optimal temperature range for promoting the development and growth of pests, it is necessary to set goals to reduce the actual operating temperatures of these hot spots. For example, when the predicted temperature in a specific area is close to 15°C to 20°C, which is the key temperature range for many grain insects to increase their activity and begin to reproduce, efforts should be made to reduce it by at least three to five degrees Celsius to block the development chain of the reproduction process. In addition, it is necessary to quantify the required cooling power intensity to match the expected cooling effect;

[0037] The equipment control module applies the adjustment parameters to the side wall refrigeration equipment to dynamically adjust the cooling power; then enters the fourth step, and calculates the specific side wall refrigeration equipment power adjustment value as the core operation instruction according to the cooling demand proposed in the previous link. This involves precise modeling simulation calculations and intelligent optimization solution methods to generate equipment power consumption adjustment recommendations that best suit the current state change needs. For each target area to be processed, consider the influence of external meteorological conditions and the performance limitations of existing infrastructure, and find the best combination strategy to achieve the ideal energy consumption ratio while ensuring that performance meets the standards. For example, when a higher warning level appears on one side close to the facade, the output of the corresponding cold air duct will be appropriately increased but will not be significantly overloaded to prevent energy waste or other unnecessary losses; at the same time, ensure that the remaining parts that normally maintain a lower temperature are not overcooled;

[0038] Finally, after determining all necessary adjustments, the modified settings are formally applied to the physical hardware facilities on site. This is the fifth step - dynamically and adaptively controlling the working conditions of the sidewall cooling units. The pre-programmed automatic control module issues real-time updated drive commands that are transmitted to the relevant devices to execute the task change instructions. Ultimately, this ensures that the entire interior space maintains a reasonably stable and cool microenvironment, preventing localized excessive temperatures from causing the spread of pathogens or parasites. For example, in actual application scenarios, if a significant deviation from the baseline value is detected in the northeast corner and it has been determined that the probability of harm is high and requires urgent treatment, the small fan equipped in that direction will be immediately notified to increase its speed by one level and increase the opening angle of the associated heat sink to enhance the efficiency of heat absorption and removal until it is confirmed that the balance is restored.

[0039] Therefore, the above process fully demonstrates how to complete the design and implementation path of the scientific and precise control plan in the granary based on the big data-driven concept to answer the above-mentioned question: the cooling power of the silo wall is adjusted according to the temperature change trend inside the grain pile, thereby successfully responding to and eliminating potential insect pest risks caused by temperature rise.

[0040] Next, we will describe the present invention's granary sidewall temperature control system based on big data analysis. The system operates in the following steps: First, a formula is used to determine whether the temperature trend exceeds the warning range; second, cooling power parameters are set or adjusted based on the determination result; and third, the sidewall cooling equipment is controlled based on the adjusted power.

[0041] Next, we'll describe the present invention's granary sidewall temperature control system based on big data analysis. The system operates in the following steps: First, a formula is used to determine whether the temperature trend exceeds the warning range; second, cooling power parameters are set or adjusted based on the determination; and third, the sidewall cooling equipment is controlled based on the adjusted power.

[0042] In the first step, use the formula To judge the temperature change trend. Represents the predicted temperature change rate. This data can be calculated by the data analysis module within the system based on historical and real-time temperature data. K1 is the temperature sensitivity coefficient, which is used to determine the sensitivity of the warning limit to temperature differences. The value range is usually 0.05 to 0.2 (expressed as the inverse of the temperature change per unit time), with the preferred value being 0.1. The specific value depends on the temperature control accuracy requirements. target The target temperature is the ideal ambient temperature preset according to the characteristics of the stored grain variety. current This is the actual temperature value, obtained from the temperature sensor installed on the side wall. By comparing the temperature change rate on the left with the threshold on the right, it determines whether to trigger the control process.

[0043] If the first step judgment condition is not met, then enter the second step of the initial control stage, the power adjustment parameter P adjust Let P initial ×r1. Here P initial Refers to the base operating power of the refrigeration equipment, while r1 acts as a correction factor to reduce the possibility of overreaction. Generally, the recommended value of r1 is between 0.75 and 0.9 to maintain stable cooling power output and avoid frequent and drastic adjustments that waste resources.

[0044] When the temperature exceeds the warning range, a higher sensitivity control mode is executed, the control sensitivity is increased from the default value to the new proportional factor r2 and the adjusted power is set to P adjust =P initial × r2. At this point, r2 should be greater than r1, within the range of 1.2 to 1.5, for example, 1.4, to rapidly reduce temperatures and mitigate the risk of overheating. This step allows for rapid adjustments to the operating conditions of the refrigeration sidewall equipment to match the actual required intensity.

[0045] In one embodiment, assuming that the wheat seeds stored in the granary need to maintain an ideal storage environment of 15°C for a long time, and the current detection finds that the temperature of a certain side wall has risen to 18°C, and the system estimates that it will further rise in the next few hours, then the above formula is used to judge that the condition is true, and the refrigeration intensity of the equipment is automatically increased until the area returns to a balanced state. Specifically, if the preliminary assessment shows that the temperature will climb at a rate of +0.5°C per hour, and the estimated temperature difference exceeds the warning line, the refrigeration efficiency of the corresponding side wall area will be immediately increased to 1.4 times the base value to deal with emergencies. Next, the distance weight calculation, temperature data weighted average target value acquisition, and power adjustment parameter calibration method in the granary side wall temperature control system based on big data analysis of the present invention are described.

[0046] First, calculate the distance weight W of the target temperature control area d By formula W d =e λ×d Implementation: where d is the physical distance between the sensor and the refrigeration sidewall, a nonnegative real number; λ is the spatial attenuation coefficient, typically selected in the range [0.1, 1.0], with an optimal value of 0.5. This formula simulates the effect of distance on the temperature during heat transfer. The greater the distance, the lower the weight. Therefore, this formula provides a more scientific assessment of the importance of temperature data.

[0047] Second, according to the obtained W dThe target temperature value is obtained by weighted average of all temperature sampling data in the target temperature control area. In this step, the temperature values recorded by all sensors are multiplied by their corresponding distance weights and then a comprehensive calculation is performed to obtain a more accurate target temperature reference value. For example, if there are multiple sensors distributed in an area, if some sensors are close to the refrigeration side wall and W d If the value is larger, the measured temperature data will be given a greater proportion, thereby increasing the impact on the temperature control strategy of key locations.

[0048] Third, the power adjustment parameter P adjust Apply the constraint P adjust ≥K2×ΔT×W d , used to adjust the cooling equipment's operating intensity. K2 represents the power correction factor. Based on experimental results, its reasonable value lies in the range [0.5, 2.0], with a preferred value of 1.0. This step aims to adjust the cooling output based on the difference ΔT between the current and desired temperatures. Combined with the previously calculated distance weight, this step specifies the minimum power requirement for a specific location, avoiding resource waste or excessive energy consumption.

[0049] In one embodiment, assume that five temperature sensors are installed on the side wall of a granary. They are numbered S1 to S5 from the one closest to the cooling wall to the one farthest away. Specifically, the distance of S1 is 0 meters, and the others are separated by two meters. When λ is set to 0.5, the distance weight of each point can be obtained: 0.5×0 =1.0 (for S1), e 0.5×2 ≈0.368 (for S2). Subsequently, if the real-time temperature data recorded by these sensors are {24, 23, 26, 28, 30} ℃ respectively, weighted and normalized according to the above weights can obtain the ideal target control temperature that accurately reflects the actual situation. Finally, the above constraints are used to configure the power value required for each corresponding refrigeration unit to ensure that different parts of the granary can efficiently maintain the ideal state without losing uniformity. Next, the method of determining the dynamic temperature gradient and executing the partitioned and layered temperature control strategy of the present invention is described. First, its various steps are listed, including calculating the temperature gradient value, judging whether it is necessary to start the temperature control strategy, and setting the local cooling power and distance threshold to define the partition, and the specific meaning of each step is explained in detail later.

[0050] The first step is to use the formula To determine the temperature gradient between the upper and lower sampling points of the grain pile. In this formula, T top Represents the real-time monitoring temperature of the top area of the grain pile (in °C), which is generally between 0 °C and 40 °C. The specific value depends on the type of stored grain and seasonal changes. bottomis the temperature measured at the bottom of the grain pile (also in °C); and ΔH represents the vertical height difference between the two temperature measurement points (in meters). The function of this formula is to calculate the degree of temperature change in the grain pile in the vertical direction, that is, the temperature gradient, so as to evaluate whether there is a significant temperature difference that leads to uneven grain storage environment. The second step is based on the set threshold Threshold G , determine whether to implement zoned and layered temperature control. If the calculated temperature gradient value G T Greater than the set threshold Threshold G , which means that there is a large risk of vertical temperature difference inside the granary. Therefore, corresponding zoning management measures need to be taken to further refine the optimization operations of each independent temperature control zone.

[0051] When the condition G is met T >Threshold G In this case, the third key stage of adjusting the refrigeration system parameters is entered. In this stage, the formula P is calculated. zone =Base P +G T ×P factor , gradually increase the cooling power to effectively deal with sudden local temperature rise. P Refers to the basic power benchmark, which is set by default to a basic value suitable for most common grain storage modes (ranging from 1 to 5kW), and the factor P factor It represents the correction items introduced to meet the needs of different scenarios to ensure that the actual adjustment is flexible, efficient and energy-efficient. The optimal choice is determined based on historical big data analysis.

[0052] The last part is to define the criteria for partitioning: using a fixed distance threshold D =5m to determine which physical spaces are assigned to the same control scope. Based on this, each independent unit is individually assigned a maximum output power limit, ensuring that each area can accurately respond to control targets based on its own load conditions while maintaining maximum energy efficiency.

[0053] In one embodiment, suppose a large intelligent granary encounters an abnormal situation when using a side wall cooling solution based on big data analysis. For example, one morning, monitoring shows that the temperature data T reported by the two sensor probes near the window are top =32℃ and T bottom =18℃, and the height difference ΔH=4m. By substituting the formula, we can quickly get the result, that is, there is a serious thermal field deviation (G T= (32-18) / 4 = 3.5° / m). Since the pre-calibrated alarm threshold is set to Threshold_G = 3° / m, it is confirmed that the warning line has been exceeded and immediate intervention is required. Then, the additional supplementary supply power P is calculated by combining the preset algorithm. zone =3+(3.5*0.8)=6kW(Base P =3KW, P factor =0.8 as the optimal balance point verified by experiments. Meanwhile, within the spatial structure segmentation, any area separated by less than five meters is considered a coherent and unified processing block. Ultimately, the entire complex process was successfully completed, returning the affected areas to a stable operating range and achieving the desired goal of maximizing energy conservation and emission reduction.

[0054] Next, we will describe the priority allocation and power setting steps in the granary sidewall temperature control system based on big data analysis. The first step involves assigning priorities based on cooling requirements for each zone. This process uses data derived from big data analysis to determine the actual needs of different temperature control units. An algorithm compares regional temperature data with preset warning thresholds to identify high-risk areas requiring priority. The higher the priority of a temperature control unit, the more weight it receives in energy allocation to ensure that critical areas remain stable within an appropriate range.

[0055] The second step is to determine the special mode power adjustment rule to be applied under the maximum temperature difference condition. Formula (T max -T min )>K3×Tavg means that when the highest temperature T max and the minimum temperature T min If the difference exceeds the allowable temperature difference calculated by multiplying the coefficient K3 by the current average temperature Tavg, the special mode power adjustment logic is entered. For example, if the temperature difference exceeds the limit, the special power multiplier α=5 is enabled to adjust the maximum power of the corresponding area.

[0056] The third step is to update the power setting value according to the formula. For each temperature control unit i, use the formula Update the base power value of a single unit, where N represents the total number of all sub-controlled temperature units. Specifically, the purpose of this formula is to adjust the dynamic response speed of the region by introducing an exponential factor and rationally plan the energy consumption of the cooling source equipment.

[0057] The fourth step is to ensure that the remaining available power can be redistributed to achieve the overall energy efficiency optimization and balance goals of the system. This process combines big data statistics to dynamically evaluate and compensate for the real-time power consumption of each area.

[0058] In one embodiment, if the temperature of the second zone is abnormal and meets the special conditions (T max-T min )>K3×Tavg, where the optimal K3 value is set to 0.1, indicating that the startup power increase ratio α=5 will quickly cool down the area with the largest temperature difference, and the other areas will be cooled by P i The formula allocates basic power values one by one and then re-optimizes resource utilization efficiency to ensure that the entire system is in an efficient state.

[0059] Next, we will describe the optimization steps and working principle of the granary side wall temperature control system based on big data analysis. Specifically, the following steps and their meanings are included:

[0060] The first step is to collect and process historical data to build a time series forecasting model to assess the risk of future overheating of the granary. overheat This step requires a detailed statistical analysis of the historically stored temperature curves. The time series model uses the mean square error (MSE) as an indicator of the accuracy of the historical data fit.

[0061] The second step defines a dynamic adjustment of cooling power Power New The calculation rules of . Its formula is expressed as Power Base is the baseline power value of the initial cooling system, which is generally in the range of [10W, 100W] and can be adjusted to an optimal value of 50W according to the actual load. K4 is an empirical calibration constant, which is usually selected in the range of [1, 10] to adapt to different environmental requirements. The recommended optimal value is 5.6, and ε is set to 1×10 -6 The small amount is to ensure that the denominator does not approach zero during the calculation process, which may cause numerical fluctuations or non-convergence problems.

[0062] The third step is to determine whether the current temperature control strategy needs to be adjusted. That is, when the calculated MSE reaches or exceeds a predefined threshold, the power re-evaluation process is triggered.

[0063] In one embodiment, for example, assuming that the temperature prediction MSE(t+1) in the current monitoring period is 12, and the above formula is used for power consumption optimization, since the preset maximum tolerance error limit is set to 10 (i.e., if MSE>10, the correction mechanism is activated), the updated cooler operating power can be calculated. The reason for this setting is that as the historical temperature fitting error increases, it reflects that the model's ability to grasp changes in external factors decreases, so the actual output power should be relatively weakened to save energy consumption.

[0064] The above method achieves the goal of accurately controlling the heat level in the food storage environment while effectively reducing resource waste.

[0065] Next, we will describe the granary sidewall temperature control system based on big data analysis. The key steps are as follows:

[0066] The first step is to detect abnormal points based on the temperature change slope to refine the local cooling control rules. This step is done by the formula slope err <Threshold s ×log(σ) determines whether the current power value needs to be frozen. err Indicates the error between the temperature change slope and the expected value; Threshold s is the error tolerance threshold, a parameter derived from historical data and system experience, generally ranging from 0.1 to 1.5, with an optimal value of 0.5; σ is the standard deviation of the predicted fluctuation, representing the uncertainty of the temperature prediction model. The purpose of this formula is to identify areas of abnormal temperature change and take timely measures through dynamic evaluation of temperature fluctuation characteristics. Only when the error exceeds the set range will the system activate the freezing power control module. Freezing power can prevent further temperature imbalance. For example, if the sensor feedback on one side of the granary shows that the slope error is significantly higher than the average standard deviation, the system enters freezing mode to avoid excessive adjustments that affect the temperature balance.

[0067] The second step is to use a closed-loop feedback loop to correct the cooling effect and ensure stability for at least three consecutive cycles before resuming the state. This is accomplished by monitoring the temperature change curve and using the feedback mechanism to continuously fine-tune the refrigerator output. The continuous cycle in this process is the length of the time window defined by the system, usually set to ten minutes or longer. This approach can effectively eliminate misjudgments caused by short-term interference. For example, a temporary temperature rise disturbance caused by the start-up of ventilation equipment will not cause uncontrolled power adjustment. In one embodiment, when the system is frozen, the signal value after three consecutive stable cycles is automatically recorded before unlocking, thereby achieving more reliable control.

[0068] The third step involves determining the power recovery method from the frozen state to the normal operating state. This is done by the formula Recovery pows =min(Cap Max ,C0 powers +β×σ slope ) is implemented. Specifically, parameter C0 powers Refers to the initial power level of the refrigeration equipment in the freezing state, Cap Max is the upper limit of the cooling system capacity (in kilowatts) to prevent overload; β is the key factor for controlling the power ramp speed, with a typical value between 0.1 and 0.5, and the optimal value is 0.25; σ slopeis the predicted variance of the temperature difference slope, which is used to quantify the adjustment risk caused by uncertainties. This setting not only ensures the safety of gradually resuming normal operations, but also effectively reduces the impact on the entire cold chain environment. Specifically, during a period of local cooling failure in a granary, assuming the initial freezing power C0 = 3 kW and the predicted standard deviation is 4, the power recovery will slowly climb to the new level while not exceeding the upper capacity limit (for example, 6 kW). Therefore, the purpose of this formula is to smooth the switching process.

[0069] Next, the specific steps of setting up a compensation mechanism for local overheating in the grain silo side wall temperature control system based on big data analysis of the present invention are described. First, the retention time parameter and the judgment formula are introduced; second, the calculation method of the additional energy consumption and the setting rules of the compensation power are defined; finally, an example is used to illustrate the application process and rationality in the actual scenario of the grain silo. Specifically, the following steps are included: the first step is to monitor and record the abnormal temperature conditions in the local area, and according to the retention time t stay Determine whether the area is in a continuous high temperature state. Here, t stay It refers to the time required for a region to recover from the first occurrence of overheating, and its range is generally [0, T total ](T total is the upper limit time of a single cooling cycle). The second step is to use the judgment condition Determines whether to start the compensation cooling module. cycle is the standard temperature control cycle, and γ is the threshold coefficient (typically ranging from 0.5 to 0.8) used to determine whether the overheating condition is a short-term disturbance or a long-term uncontrollable condition. This condition setting can distinguish whether abnormal overheating is accidental or a systemic problem.

[0070] In the third step, if the compensation mechanism is triggered, the additional energy consumption is calculated according to formula E add =Comp Ratio ×P zone Calculation is performed to compensate for the insufficient cooling capacity in the local area. The parameters here are: Comp Ratio is the proportional factor of the compensation power, the default value is set to 15 (the optimal value range is usually between 10 and 20, adjusted according to historical data analysis); and P zone represents the base cooling power requirement for a specific area. This allows for dynamic quantification of energy consumption increases, enabling more rational resource allocation. This formula is designed to minimize the impact of localized issues, ensuring overall system performance while minimizing excessive energy consumption.

[0071] For example, in one embodiment, suppose that the side wall of a grain storage warehouse is close to the direct sunlight area outside, and the temperature rises significantly due to the influence of external heat conduction, and exceeds the set safety limit for two consecutive days, and the retention time is 48 hours. At this time, through the formula (assuming γ = 0.6), it can be determined that an additional cooling unit needs to be activated immediately for intervention. The newly added energy cost in the compensation process is expressed as E add = 15% * basic power consumption 100kW = 15kW Description: This case specifically demonstrates how to use the compensation mechanism to optimize system operation stability.

[0072] Next, the dynamic power curve planning method of the present invention is described. This method aims to optimize the operating efficiency of the granary sidewall temperature control system based on big data analysis and adapt to environmental fluctuations within a specific time period.

[0073] Specifically, the following steps are included: determining the time period that needs to be controlled and the corresponding environmental variable characteristics; obtaining the control logic expression under each operating condition based on data modeling, which is described using piecewise polynomials; calculating and calibrating the polynomial parameter values for each stage; and finally integrating the power output at all times to form a complete operation diagram for actual operation.

[0074] First, we conduct preliminary identification and classification of time periods and environmental fluctuation characteristics. This step ensures that appropriate control measures for different time periods can more accurately match the impact of diurnal or seasonal changes, such as significant temperature fluctuations between day and night. Data from these time periods is collected in advance through big data analysis and used to formulate judgment criteria.

[0075] Then, create the control function Here we define C k Indicates the target power to be achieved within the kth period, with time being based on t. Each order coefficient is a k It can be regarded as a scalar measuring the intensity of different control conditions; for any p k , which indicates the time-weighted relationship between the corresponding variables. Integer values from 1 to 5 are generally selected as a reasonable order range. This effectively balances the conflict between accuracy requirements and implementation difficulty, while reducing unnecessary complexity. This formula is designed to comprehensively consider the interaction effects of multiple factors, simulate system behavior trends, and design optimized paths. Subsequently, the key parameters in the above formula are calibrated and verified based on actual conditions to ensure optimal application results. This process is repeatedly adjusted until the expected performance goals are met.

[0076] For example, consider a scenario where increased daylight causes rapid internal temperature rise, necessitating a rapid increase in sidewall cooling capacity. Meanwhile, energy consumption should be reduced at night to avoid unnecessary losses. Therefore, the daytime curve can be configured to resemble a binomial or trigonometric high-order form to reflect the rapid response requirement. Meanwhile, the low-amplitude nighttime fluctuations may require only a first-order approximation to represent their simple, stable characteristics and meet accuracy requirements.

[0077] In one embodiment, for example, if the day length increases significantly in a particular summer month, a higher quadratic power component is allocated during the day to strengthen the dynamic regulation strength, while a low-order linear decreasing model is set to be used to maintain a stable energy-saving situation at night.

[0078] Next, we'll describe the various steps of the present invention. The first step involves expanding the cooling efficiency evaluation system to include long-term economic analysis. This step requires improving existing cooling efficiency evaluation metrics to include system economics as a key consideration. This expansion facilitates a comprehensive assessment of the performance of a silo's sidewall temperature control system throughout its entire lifecycle, not just focusing on short-term energy consumption.

[0079] The second step involves setting the form of the cost saving optimization function. The formula is expressed as: Among them J energy Represents the value of the electricity consumption recorded during each actual operation. It is usually determined by the electricity consumption and the unit electricity price. Its value range can be dynamically adjusted according to the local electricity pricing policy. Eff This refers to the effective cooling capacity or heat removal performance of the overall system. A positive value indicates a more efficient system. η is the energy-saving gain weight, set within a range based on specific energy-saving targets. The optimal value depends on the balance between economic returns and environmental goals. By introducing a formula to comprehensively balance the system's energy use and energy-saving results, minimizing costs becomes the core driving force.

[0080] The third step requires a practical benefit analysis using the aforementioned optimization framework. For example, in one implementation, assuming a grain storage system requires continuous cooling year-round to protect storage quality, and with an average daily power consumption of 100 kWh and an electricity price of 0.5 yuan / kWh, the annual direct electricity cost would be nearly 20,000 yuan. Specifically, in comparative tests before and after optimization, using the big data model to adjust the air supply strategy reduced the daily peak load by 30% while maintaining temperature fluctuations within ±1°C, demonstrating the formula's guiding significance in significantly improving economic efficiency and environmental friendliness.

[0081] These steps enable the grain silo side wall temperature control system based on big data analysis to not only achieve precise temperature control functions, but also improve the economic benefits and social responsibility manifestations throughout the entire operation cycle from a long-term perspective.

[0082] See also Figure 2 A second objective of this embodiment is to provide a method for a grain silo sidewall temperature control system based on big data analysis, comprising the following steps: The method begins with data collection, using sensors placed within the grain pile to obtain real-time temperature distribution and trend data within each area of the grain. S1. Based on the temperature data collected by sensors within the grain pile, big data analysis is used to predict temperature trends within the grain pile. These sensors can be densely distributed to ensure coverage of the entire grain pile space, providing detailed data support for subsequent analysis.

[0083] S2. Based on the predicted temperature trends, the target temperature control areas and corresponding cooling requirements are determined. The system then enters the data analysis phase. By inputting the collected temperature data from the grain pile into a pre-established big data analysis platform, the system uses advanced data analysis techniques such as machine learning algorithms to predict potential temperature fluctuations and anomalies within the grain pile, particularly areas at risk of localized overheating. These predictions further guide the delineation of target temperature control areas and assess the cooling requirements for these areas based on the potential high-temperature risks within the grain pile. This step is crucial to solving the problem, as it uses temperature trends to determine which areas will likely achieve environmental conditions suitable for pest breeding and reproduction within a short period of time.

[0084] S3. Calculate the power adjustment parameters for the sidewall refrigeration equipment based on the cooling demand. Based on this predicted cooling demand information, the system further calculates specific adjustment parameters to precisely control the power of the refrigeration equipment located on the warehouse wall. For example, if a specific layer or section is found to have a high probability of temperature rise, the system will automatically increase the operating efficiency or power of the refrigeration equipment installed on the nearby sidewall. Conversely, if the probability of temperature rise is high, the power will be appropriately reduced to avoid energy waste and the potential waste of resources caused by overcooling or the impact on grain quality.

[0085] S4. Regulating parameters are applied to the sidewall refrigeration equipment to dynamically adjust cooling power, suppressing localized overheating and preventing pest growth. In the final step, the control system outputs adjustment commands and sends the aforementioned adjustment parameters to the actual actuators—the various refrigeration modules or units installed around the silo's sidewalls. These dynamically adjust the operating status of each relevant module, ensuring the sidewalls produce the appropriate cooling capacity to suppress any unfavorable heat accumulation that could lead to pest problems and effectively prevent the threat of pest growth induced by such localized overheating. This approach achieves intelligent and precise management, significantly improving energy savings and optimizing stored grain quality and safety.

[0086] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A granary side wall temperature control system based on big data analysis, characterized in that: include: A data acquisition module is used to collect temperature data through sensors inside the grain pile; The big data analysis module is connected to the data acquisition module and uses the big data analysis algorithm to predict the temperature change trend inside the grain pile; The temperature control area determination module determines the target temperature control area and cooling demand based on the temperature change trend; the power calculation module calculates the power adjustment parameters of the side wall cooling equipment based on the cooling demand; The equipment control module applies the adjustment parameters to the side wall cooling equipment and dynamically adjusts the cooling power.

2. The granary side wall temperature control system based on big data analysis according to claim 1 is characterized in that: The big data analysis module is connected to the power calculation module; Based on the formula Determine whether the temperature change trend exceeds the warning range, To predict the temperature change rate, K1 is the temperature sensitivity coefficient, T target is the expected target temperature, T current is the current collected temperature; If not satisfied, the power calculation module sets P adjust =P initial ×r1, otherwise increase the control sensitivity r2, and adjust Promoted to P initial ×r2, r1 is the initial power correction factor, r2 is the power correction factor after the control sensitivity is improved, and the equipment control module controls the operation of the side wall refrigeration equipment accordingly.

3. The granary side wall temperature control system based on big data analysis according to claim 2 is characterized in that: The temperature control area determination module includes a distance weight calculation unit to calculate the distance weight W of the target temperature control area. d =e λ×d , d is the distance between the sensor position and the refrigeration side wall, λ is the spatial attenuation coefficient; Also includes a weighted average unit, based on W d Weighted average of temperature sampling data; The power calculation module uses P adjust ≥K2×ΔT×W d Calibrate the power adjustment parameters, K2 represents the power correction coefficient, ΔT is the target temperature offset, and the device control module sets differentiated cooling power adjustments for different distance zones.

4. The granary side wall temperature control system based on big data analysis according to claim 3 is characterized in that: The big data analysis module includes a temperature gradient calculation unit, through the formula Determine the dynamic temperature gradient, G T is the temperature gradient value, T top and T bottom are the temperatures of the upper and lower sampling points of the grain pile, respectively, and ΔH is the vertical height difference; When G T >Threshold G When the temperature is controlled by the equipment control module, the local cooling power is increased to P zone =Base P +G T ×P factor , and set the upper limit of partition power; Among them, Threshold G is the temperature gradient threshold, Base P is the basic power, P factor is the power impact factor.

5. The granary side wall temperature control system based on big data analysis according to claim 4 is characterized in that: The equipment control module includes a priority allocation unit, which allocates priorities according to the cooling requirements of the zones, and allocates priority to the temperature control units N that meet the temperature warning conditions. i , if (T max -T min )>K3×Tavg, give priority to adjusting the maximum power regional cooling module, and apply the special mode power Max(P i ×α),α=5,update And redistribute the remaining power to ensure energy balance; among them, T max and T min They are temperature control unit N i The highest and lowest temperatures in the room; K3 is the temperature difference coefficient; Tavg is the temperature control unit N i The average temperature inside; P i Temperature control unit N i Cooling power; Max P is the maximum power allowed by the system; i is the number of the temperature control unit, ranging from 1 to N; N is the total number of zones.

6. The granary side wall temperature control system based on big data analysis according to claim 5 is characterized in that: The big data analysis module includes a risk assessment unit, which introduces a time series prediction model to assess the overheating risk R overheat , the historical temperature fitting goodness of fit is measured by mean square error MSE(t+1). When MSE exceeds the preset level, the power calculation module Adjust power parameters to optimize power consumption performance; Power New The new power after adjustment; Power Base Refers to the benchmark cooling power; K4 is the empirical calibration constant, ε= 1×10 -6 , used to prevent the denominator from being zero; MSE t is the mean square error at time t.

7. The granary side wall temperature control system based on big data analysis according to claim 6 is characterized in that: The big data analysis module includes an anomaly detection unit, which detects abnormal points by the temperature change slope. err <Threshold s ×log(σ), σ is the standard deviation of the predicted fluctuation. The equipment control module freezes the current power value and corrects the cooling effect in combination with the feedback closed loop. Press Recovery pows =min(Cap Max ,C0 powers +β×σ slope ) restore power; Among them, slope err is the temperature change slope error, Threshold s is the slope error threshold; β controls the power ramp speed, Cap Max is the power upper limit; C0 powers is the power value when frozen; σ slo[e is the standard deviation of the temperature change slope.

8. The granary side wall temperature control system based on big data analysis according to claim 7 is characterized in that: The device control module includes a compensation mechanism unit and a power planning unit; The compensation mechanism unit is based on the situation that local overheating has not recovered for a long time. To start the compensation cooling module, press E add =Comp Ratio ×P zone Increased energy consumption; Among them, t stay is the duration of the overheating state in the local area; T cycle is the system monitoring period; γ is the compensation start threshold, Comp Ratio To compensate for the power ratio, P zone is the cooling power of the local area; The power planning unit pre-plans a dynamic power curve based on environmental fluctuations. It uses a piecewise polynomial representation, with each part corresponding to a working condition switch. The specific calculation logic is: Each order coefficient corresponds to the influence of different control variables; Finally, the power output at each moment is combined into a complete operation diagram; among them, C k is the power calculation value at time k; a k are polynomial coefficients; t is time; p k is the polynomial order.

9. The granary side wall temperature control system based on big data analysis according to claim 8 is characterized in that: It also includes an efficiency evaluation module, which is connected to the equipment control module to optimize the function through cost saving Comprehensively evaluate the long-term economic performance of the system, including J energy (i,j) represents the actual electricity consumption record value of the jth refrigeration equipment in the i-th time period; Total Eff is the comprehensive efficiency index of the system, and η is the energy-saving gain weight.

10. A method for using a granary side wall temperature control system comprising the big data analysis according to any one of claims 1 to 9, characterized in that: The method comprises the following steps: S1. Based on the temperature data collected by sensors inside the grain pile, use big data analysis to predict the temperature change trend inside the grain pile; S2. Determine the target temperature control area and the corresponding cooling demand based on the predicted temperature change trend; S3. Calculating adjustment parameters of the side wall refrigeration equipment power based on the refrigeration demand; S4. Applying the adjustment parameters to the side wall refrigeration equipment to dynamically adjust the refrigeration power, suppress local overheating and prevent pest breeding.

Images