Method for monitoring the storage environment of gas-sensitive nanomaterials

Abstract

This application provides a method for monitoring the storage environment of gas-sensitive nanomaterials, relating to the field of environmental monitoring technology. The method includes: determining suitable temperature and humidity thresholds for the gas-sensitive nanomaterials, i.e., rated storage temperature and humidity thresholds; setting monitoring points in the storage environment to collect time-series temperature and humidity data; establishing a temperature and humidity prediction model to obtain information on regulating equipment and assess its comprehensive impact; setting equipment compensation power based on predictions and rated thresholds; determining the regulating power and nodes by combining equipment impact and compensation power; and activating the equipment at the regulating nodes to set the power-controlled environment. This application addresses the problem in existing technologies where the lack of timely response to minute changes in temperature and humidity leads to large fluctuations in the temperature and humidity of the storage environment, further affecting the performance and stability of gas-sensitive nanomaterials. It achieves effective control of the temperature and humidity of the storage environment, helping to protect gas-sensitive nanomaterials from adverse environmental effects and improving energy utilization and management efficiency.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology, and in particular to a method for monitoring the storage environment of gas-sensitive nanomaterials. Background Technology

[0002] The performance of gas-sensitive nanomaterials is greatly affected by the storage environment, so the storage environment needs to be strictly monitored.

[0003] Currently, existing monitoring technologies for gas-sensitive nanomaterial storage environments mostly rely on simple thermometers and hygrometers and periodic manual checks, lacking intelligent and automated management systems. This approach is not only inefficient but also struggles to respond promptly to minute changes in environmental parameters, thus making it difficult to guarantee the stability of the storage environment.

[0004] In summary, existing technologies lack the ability to respond promptly to minute changes in temperature and humidity, resulting in large fluctuations in the temperature and humidity of the storage environment, which further affects the performance and stability of gas-sensitive nanomaterials. Summary of the Invention

[0005] The purpose of this application is to provide a method for monitoring the storage environment of gas-sensitive nanomaterials, in order to solve the problem that the existing technology lacks the ability to respond promptly to small changes in temperature and humidity, resulting in large fluctuations in the temperature and humidity of the storage environment, which further affects the performance and stability of gas-sensitive nanomaterials.

[0006] In view of the above problems, this application provides a method for monitoring the storage environment of gas-sensitive nanomaterials.

[0007] This application provides a method for monitoring the storage environment of gas-sensitive nanomaterials. The method includes: determining a rated storage temperature threshold and a rated storage humidity threshold, which are constructed based on the sensitivity to temperature and humidity after analyzing the property information of the gas-sensitive nanomaterials; establishing monitoring points in the storage environment, each equipped with a temperature sensor and a humidity sensor, and using these monitoring points to perform time-series monitoring of the storage environment, establishing temperature and humidity sequence data; configuring a prediction model based on the temperature and humidity sequence data, the prediction model including a first prediction network and a second prediction network, the first prediction network being a temperature prediction network and the second prediction network being a humidity prediction network; acquiring equipment information of regulating devices, and establishing a comprehensive regulation effect based on the equipment information and the location distribution of the regulating devices in the storage environment; predicting temperature and humidity based on the prediction model, and configuring the device time-series compensation power based on the rated storage temperature threshold and the rated storage humidity threshold; establishing the device regulation power through the comprehensive regulation effect and the device time-series compensation power, and determining regulation nodes; activating the regulating device at the regulation node, and controlling the regulating device to perform storage environment control through the device regulation power.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By determining the rated storage temperature threshold and rated storage humidity threshold, which are constructed based on the sensitivity to temperature and humidity after analyzing the property information of gas-sensitive nanomaterials; establishing monitoring points in the storage environment, each equipped with a temperature sensor and a humidity sensor, to perform time-series monitoring of the storage environment and establish temperature and humidity sequence data; configuring a prediction model based on the temperature and humidity sequence data, the prediction model including a first prediction network and a second prediction network, the first prediction network being a temperature prediction network and the second prediction network being a humidity prediction network; acquiring equipment information of the regulating device, and based on... The system establishes a comprehensive regulatory impact based on the device information and the location distribution of regulating devices within the storage environment. Temperature and humidity are predicted using a forecasting model, and device timing compensation power is configured based on rated storage temperature and humidity thresholds. Device regulation power is established through the comprehensive regulatory impact and device timing compensation power, and regulation nodes are determined. The regulating devices are activated at these nodes, and their regulation power controls the storage environment. This effectively solves the problem of large temperature and humidity fluctuations in the storage environment caused by the lack of timely response to minute changes in temperature and humidity in existing technologies, which further affects the performance and stability of gas-sensitive nanomaterials. This system achieves effective control of the temperature and humidity of the storage environment, helping to protect gas-sensitive nanomaterials from adverse environmental effects and improving energy utilization and management efficiency.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1This is a flowchart illustrating the storage environment monitoring method for gas-sensitive nanomaterials in this application.

[0013] Figure 2 This is a schematic diagram of the process for predictive correction in the storage environment monitoring method for gas-sensitive nanomaterials in this application. Detailed Implementation

[0014] This application provides a method for monitoring the storage environment of gas-sensitive nanomaterials, solving the problem that existing technologies lack the ability to respond promptly to minute changes in temperature and humidity, leading to large fluctuations in the temperature and humidity of the storage environment, which further affects the performance and stability of gas-sensitive nanomaterials. This method enables effective control of the temperature and humidity of the storage environment, helping to protect gas-sensitive nanomaterials from adverse environmental effects and improving energy utilization and management efficiency.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Please see the appendix Figure 1 This application provides a method for monitoring the storage environment of gas-sensitive nanomaterials, wherein the method specifically includes the following steps:

[0017] S1: Determine the rated storage temperature threshold and the rated storage humidity threshold, which are constructed based on the sensitivity to temperature and humidity after analyzing the property information of the gas-sensitive nanomaterials.

[0018] Specifically, a comprehensive property analysis is performed on the gas-sensitive nanomaterials. This includes analyzing the material's crystal structure, lattice constant, surface morphology, particle size, and chemical composition. This information can be obtained through X-ray diffraction, transmission electron microscopy, scanning electron microscopy, and energy dispersive spectroscopy. By gradually changing the temperature and humidity of the storage environment and monitoring changes in the material's performance, such as resistance and sensitivity, the material's sensitivity range to temperature and humidity can be determined. Based on the results of the sensitivity tests, the temperature and humidity points where the material's performance begins to change significantly are identified; these points can then serve as references for the rated storage temperature threshold and rated storage humidity threshold. Preferably, the material is placed in a temperature- and humidity-controlled environment, with the temperature gradually adjusted (e.g., from -20°C to 80°C, with each 10°C test point) and the humidity adjusted (e.g., from 10% RH to 90% RH, with each 10% test point). Performance data, such as resistance and response time, are recorded at each test point. The test data is analyzed to identify the temperature and humidity points where the material's performance changes significantly. Based on the analysis results, the rated storage temperature threshold and rated storage humidity threshold are set.

[0019] S2: Establish monitoring points in the storage environment. The monitoring points are equipped with temperature sensors and humidity sensors. Use the monitoring points to perform time-series monitoring of the storage environment and establish temperature sequence data and humidity sequence data.

[0020] Specifically, representative locations are selected as monitoring points based on the layout and characteristics of the storage environment. These locations should reflect the overall temperature and humidity conditions within the storage environment. Due to the characteristics of gas-sensitive nanomaterials and storage requirements, the selected monitoring points should avoid areas that may affect temperature and humidity readings, such as direct sunlight and ventilation openings. Temperature and humidity sensors are installed at the selected monitoring points. The data acquisition frequency is set, such as per minute or per hour, and adjusted according to actual needs. Temperature and humidity data for each monitoring point are automatically recorded at the set frequency. Over time, the temperature and humidity data for each monitoring point will form a time-series sequence.

[0021] S3: Configure a prediction model based on temperature sequence data and humidity sequence data. The prediction model includes a first prediction network and a second prediction network. The first prediction network is a temperature prediction network, and the second prediction network is a humidity prediction network.

[0022] Furthermore, configuring the prediction model based on temperature and humidity sequence data includes:

[0023] The prediction model formula is as follows:

[0024]

[0025] Where T(t) represents the first prediction network, H(t) represents the second prediction network, α and α′ represent the constant terms in the model, p and p′ are the orders of the autoregressive part, i represents the lag order of the autoregressive part, and φ i and φ′ i The autoregressive coefficients are represented by T(ti) and H(ti), which represent the actual temperature and humidity values ​​at past time points. q and q′ represent the order of the moving average component, j represents the lag order of the moving average component, and θ represents the lag order. j and θ′ j ∈(th) and ∈′(tj) represent the temperature error term and humidity error term at past time points, respectively. ∈(t) represents the temperature error term at the current time point, and ∈′(t) represents the humidity error term at the current time point.

[0026] Specifically, the collected temperature and humidity sequence data are cleaned, removing outliers and filling in missing values. The data is normalized to make it suitable for model input. The data is divided into training, validation, and test sets. Based on the data characteristics and prediction requirements, the two networks are trained using the training set data. Two independent networks are designed: one for temperature prediction (the first prediction network) and the other for humidity prediction (the second prediction network). Network parameters are adjusted using backpropagation algorithms and optimizers such as Adam and SGD to minimize the error between predicted and actual values. The model is validated using the validation set data to prevent overfitting. The model's performance is evaluated on the test set using metrics such as mean squared error and mean absolute error. Based on the evaluation results, the model is adjusted and optimized, such as changing the number of network layers, neurons, and learning rate. The specific model formula is as follows:

[0027] Where T(t) represents the first prediction network, H(t) represents the second prediction network, α and α′ represent the constant terms in the model, p and p′ are the orders of the autoregressive part, i represents the lag order of the autoregressive part, and φ i and φ′ i The autoregressive coefficients are represented by T(ti) and H(ti), which represent the actual temperature and humidity values ​​at past time points. q and q′ represent the order of the moving average component, j represents the lag order of the moving average component, and θ represents the lag order. j and θ′ j ∈(tj) and ∈′(tj) represent the temperature error term and humidity error term at past time points, respectively. ∈(t) represents the temperature error term at the current time point, and ∈′(t) represents the humidity error term at the current time point.

[0028] S4: Obtain the equipment information of the regulating device, and establish a comprehensive regulating effect based on the equipment information and the location distribution of the regulating device in the storage environment.

[0029] Specifically, basic information on all temperature and humidity control devices in the storage environment is collected, such as device model, power, control range, and control speed. The specific location of each control device in the storage environment is determined. The relative positional relationship between the devices and monitoring points is recorded, including distance and orientation. Based on the device location and performance parameters, the impact capability of each device on different areas of the storage environment is analyzed. The influence range of each device is estimated based on its control range, power, and environmental factors such as air circulation, walls, and obstructions. The overlap and interaction between the influence ranges of all devices are analyzed. The impact of different devices on the temperature and humidity of the storage environment under different settings is simulated using mathematical modeling or simulation software. Based on the simulation results, the layout or settings of the devices are adjusted to maximize the control effect and reduce energy consumption. Control strategies are developed for different areas and conditions to ensure the stability and uniformity of the storage environment.

[0030] S5: Predict temperature and humidity based on the prediction model, and configure the device timing compensation power based on the rated storage temperature threshold and the rated storage humidity threshold.

[0031] Specifically, the established prediction models, including temperature and humidity prediction networks, are used as inputs, along with current and recent temperature and humidity series data. The prediction models output predicted temperature and humidity values ​​for a future period, such as several hours or days. These predicted values ​​are then compared to the rated storage temperature and humidity thresholds. Periods and degrees of potential exceedance of these thresholds are identified. Based on the prediction results, the timing and amount of temperature and humidity adjustments required are determined. Finally, by considering the performance parameters of the regulating equipment, such as adjustment speed and power, the required compensation power to reach the rated thresholds is calculated.

[0032] S6: Establish equipment regulation power by adjusting the overall impact and equipment timing compensation power, and determine the regulation node;

[0033] Furthermore, the establishment of equipment regulation power by adjusting the overall influence and equipment timing compensation power includes:

[0034] The formula for adjusting the power of the equipment is as follows:

[0035]

[0036] Among them, P T (t) and P H (t) represents the equipment temperature regulation power and the equipment humidity regulation power, respectively, P base(T) and P base(H)These are the equipment time-series temperature compensation power and the equipment time-series humidity compensation power, respectively. T and γ H These are the temperature regulation coefficient and humidity regulation coefficient, respectively. pred (t) and H pred (t) represents the predicted temperature and humidity values ​​at time point t, respectively. set and H set Here, denoted as the rated storage temperature threshold and the rated storage humidity threshold, respectively; f(d, v, L) characterizes the comprehensive influence function of regulation; τ is the location influence coefficient; d is the distance between the regulating equipment and the monitoring point; β is the response speed influence coefficient; and t... delay To adjust the delay time, v is used to adjust the device's response speed, and L is used to adjust the response time. max L represents the power level of the device being adjusted to its maximum power rating.

[0037] Specifically, the impact of each regulating device on different areas and the interactions between devices are identified. Which areas in the storage environment are most susceptible to temperature and humidity fluctuations, or which areas are most critical for material preservation, are determined. These areas are marked as critical regulating areas, which will be the focus of determining device regulating power and regulating nodes. Based on predictive models and rated storage temperature and humidity thresholds, the compensation power required by each regulating device to achieve and maintain suitable temperature and humidity conditions within the critical regulating areas is calculated. Combining the device's timing compensation power requirements and the performance parameters of the regulating devices, a model is built to determine the regulating power that each device should provide at different time points. This model can dynamically adjust the device's power output to adapt to real-time changes in temperature and humidity in the storage environment. Regulating nodes refer to the time and spatial points that require special attention and precise regulation. Based on the device regulating power model and the analysis results of the critical regulating areas, the specific time points and locations where temperature and humidity regulation is required are determined. These nodes correspond to specific time periods, such as peak or off-peak periods, or specific areas in the storage environment, such as areas with large temperature and humidity fluctuations. The specific model is as follows: Among them, P T (t) and P H (t) represents the equipment temperature regulation power and the equipment humidity regulation power, respectively, P base(T) and P base(H) These are the equipment time-series temperature compensation power and the equipment time-series humidity compensation power, respectively. T and γ H These are the temperature regulation coefficient and humidity regulation coefficient, respectively. pred (t) and H pred (t) represents the predicted temperature and humidity values ​​at time point t, respectively. set and Hset Here, denoted as the rated storage temperature threshold and the rated storage humidity threshold, respectively; f(d, v, L) characterizes the comprehensive influence function of regulation; τ is the location influence coefficient; d is the distance between the regulating equipment and the monitoring point; β is the response speed influence coefficient; and t... delay To adjust the delay time, v is used to adjust the device's response speed, and L is used to adjust the response time. max L represents the power level of the device being adjusted to its maximum power rating.

[0038] S7: Activate the regulating device at the regulating node, and use the device to regulate power control to control the storage environment.

[0039] Specifically, before reaching the predetermined adjustment node, ensure that the relevant adjustment equipment is in standby mode. Perform self-checks and calibrations on the equipment to ensure it can function properly and accurately execute adjustment tasks. When the preset adjustment node is reached, automatically trigger the activation signal of the adjustment equipment. Based on the equipment's adjustment power model, send specific power control commands to the adjustment equipment. The adjustment equipment adjusts its operating state according to the received power commands, such as heating, cooling, humidifying, or dehumidifying.

[0040] Furthermore, this application also includes:

[0041] Establish a verification time window mapped to the adjustment node; when the storage environment is controlled through the adjustment node, control monitoring is performed within the verification time window to establish a monitoring time series dataset; timing compensation authentication is performed through the monitoring time series dataset, and the device adjustment power is optimized based on the timing compensation authentication results.

[0042] Specifically, identify the critical adjustment nodes, which are based on time, changes in environmental parameters, or other triggering conditions. For each adjustment node, set a specific time window, the verification time window. This time window should be long enough to capture the impact of the adjustment equipment on the environment, but not too long to avoid affecting efficiency. Ensure a clear mapping relationship between each adjustment node and its corresponding verification time window. Within the verification time window, monitor environmental parameters such as temperature and humidity in real time using sensors. Record the operating status of the adjustment equipment, actual changes in environmental parameters, and any adjustment operations. Organize the collected data into a time-series monitoring dataset. This dataset should include timestamps, environmental parameter values, equipment status, and other information. Using the time-series monitoring dataset, analyze the differences between actual and expected environmental parameters, and how these differences change over time. Based on the results of the time-series compensation verification, adjust the equipment's adjustment power strategy. For example, if the equipment response is too slow, increase the power initially to speed up the response; if overshoot is detected, appropriately reduce the adjustment power or adjust the control algorithm. Apply the optimized strategy to actual equipment adjustment and continuously monitor its effects.

[0043] Furthermore, such as Figure 2 As shown, this application also includes:

[0044] The temperature and humidity sequence data are evaluated to establish independent variation results; normalization coefficients are configured for the independent variation results, and the independent variation results are adjusted according to the normalization coefficients. An abnormal range is established based on the normalization adjustment results; external features are monitored within a time window in the abnormal range, and abnormal response features are configured based on the external feature monitoring results; the prediction model is corrected based on the abnormal response features.

[0045] Specifically, the quality of temperature and humidity series data is assessed to check for missing values, outliers, or noise. Statistical methods, such as mean, median, standard deviation, and quartiles, are used to describe the distribution and fluctuation of the data. The correlation between the temperature and humidity series is analyzed to determine whether they vary independently. If the correlation is low, they can be considered to vary independently. For independently varying series, their trends are calculated separately, using methods such as moving averages or exponential smoothing. A normalization method is determined, such as min-max normalization or Z-score normalization. Normalization coefficients, such as minimum, maximum, mean, and standard deviation, are calculated based on the selected method. The normalization coefficients are applied to normalize the results of independent variations, ensuring the data falls on a uniform scale. Based on the normalized data, the range of normal variation, i.e., the normal interval, is determined. Data exceeding the normal interval is defined as abnormal data, and the range of these data constitutes the abnormal interval. Within the abnormal interval, a delay window is set to monitor external characteristics, such as environmental changes and equipment status. These external characteristic data are collected through sensors or other monitoring methods. Finally, abnormal response features are configured based on the external feature monitoring results, and the prediction model is revised accordingly. The correlation between external feature data and abnormal data is analyzed to identify abnormal response features that cause data abnormalities. These features include sudden environmental changes, equipment failures, etc. The identified abnormal response features are incorporated into the prediction model as additional input variables. The model is retrained to account for the impact of these abnormal factors on the prediction results. In this way, the prediction model can more accurately predict temperature and humidity changes under abnormal conditions.

[0046] Furthermore, this application also includes:

[0047] Analyze the continuous decrease values ​​of temperature and humidity series data within a preset time period to generate a first change result; analyze the changes of temperature and humidity series data per unit time to establish a second change result; establish an independent change result based on the first and second change results.

[0048] Specifically, a suitable time period is determined, such as one hour, one day, or one week, depending on the granularity of the data and the analytical requirements. Starting from the beginning of the temperature series data, the data is examined periodically. The continuous decrease in temperature within each time period is recorded. The continuous decrease refers to the difference between the highest and lowest temperature points within the preset time period. Recording the continuous decrease in temperature for each time period forms the first change result for temperature. Using the same method as for the temperature series, the humidity data within each time period is analyzed for continuous decreases. The continuous decrease in humidity for each time period forms the first change result for humidity. A unit of time is determined; this unit of time can be minutes, hours, etc., depending on the data sampling frequency and analytical requirements. For each data point in the temperature series data, the difference between it and the previous data point is calculated, i.e., the temperature change per unit time. These differences are recorded, forming the second change result for temperature. Similarly, for each data point in the humidity series data, the difference between it and the previous data point is calculated, i.e., the humidity change per unit time. These differences are recorded, forming the second change result for humidity. For both temperature and humidity, two sets of changes were obtained: a continuous decrease (the first result) and a change per unit time (the second result). The correlation between these two results was analyzed. A low correlation indicates that their changes are relatively independent. Based on this analysis, independent changes in temperature and humidity can be derived. These results reflect the continuous decreasing trend of temperature and humidity within a preset time period, as well as their fluctuations per unit time.

[0049] Furthermore, this application also includes:

[0050] Establish the life cycle of gas-sensitive nanomaterials and establish an additional adjustment coefficient that maps to the life cycle; adjust the compensation sensitivity of the adjustment device through the additional adjustment coefficient, and control the storage environment based on the adjustment result.

[0051] Specifically, data related to the entire process of gas-sensitive nanomaterials from production to disposal is collected. This includes the material's production date, start date of use, performance degradation data, and replacement or disposal date. Based on the collected data, the life cycle stages of the gas-sensitive nanomaterials are defined. For example, they can be divided into an initial stage, a stable operating stage, a performance degradation stage, and a disposal stage. Data analysis techniques, such as machine learning or statistical models, are used to build models that can predict each stage of the gas-sensitive nanomaterial's life cycle. At each life cycle stage, the performance of the gas-sensitive nanomaterials is evaluated, particularly their sensitivity to gases and response speed. Based on the performance evaluation results, an additional adjustment coefficient is set for each life cycle stage. For example, in the initial stage, when the material performance is optimal, the coefficient may be set to 1; in the performance degradation stage, due to the decrease in material sensitivity, the coefficient may need to be increased accordingly to improve the device's compensation sensitivity. The corresponding additional adjustment coefficient is selected based on the current life cycle stage of the gas-sensitive nanomaterials. The selected additional adjustment coefficient is applied to the adjustment device to adjust its compensation sensitivity. This is achieved by modifying the device's control algorithm. After adjusting the sensitivity, the gas concentration and other relevant parameters of the storage environment are continuously monitored. Based on the monitoring results, the adjustment device is used to control the storage environment in real time to ensure that environmental parameters are maintained within a preset safe range. Based on actual results, the additional adjustment coefficients and control strategies are continuously adjusted and optimized to improve the accuracy and efficiency of storage environment control.

[0052] Furthermore, this application also includes:

[0053] Configure an early warning response threshold, and perform continuous analysis of temperature and humidity sequence data based on the early warning response threshold; report control anomalies based on the results of the trigger timing analysis.

[0054] Specifically, based on historical data analysis and business needs, those skilled in the art should set reasonable early warning response thresholds for temperature and humidity. These thresholds should have upper and lower limits to detect excessively high or low temperatures and humidity levels. Sensors should be used to collect temperature and humidity data in real time. The real-time monitored data should be compared with the preset early warning response thresholds. If the real-time monitored data exceeds the early warning response threshold, an early warning mechanism is triggered. When data exceeds the threshold, the time, data, and type of exceeding the threshold (high temperature, low temperature, high humidity, low humidity) of the trigger event should be recorded. The timing of the trigger events should be analyzed to observe whether there are persistent or intermittent exceedances of the threshold. The time intervals between trigger events, as well as the duration and extent of exceeding the threshold, should be checked. Based on the trigger timing analysis results, it should be determined whether there is a control anomaly. For example, if temperature and humidity consistently exceed the threshold or fluctuate abnormally, it may indicate a problem with the control system. Once a control anomaly is identified, an anomaly report should be generated immediately. The report should include the time of occurrence, duration, and type of anomaly (e.g., excessively high temperature, excessively low humidity), as well as possible cause analysis.

[0055] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0056] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for monitoring the storage environment of gas-sensitive nanomaterials, characterized in that, include: The rated storage temperature threshold and rated storage humidity threshold are determined. These thresholds are constructed based on the sensitivity to temperature and humidity after analyzing the property information of the gas-sensitive nanomaterials. Monitoring points are established in the storage environment. These monitoring points are equipped with temperature and humidity sensors. Time-series monitoring of the storage environment is performed using these monitoring points to establish temperature and humidity sequence data. A prediction model is configured based on temperature and humidity sequence data. The prediction model includes a first prediction network and a second prediction network. The first prediction network is a temperature prediction network, and the second prediction network is a humidity prediction network. Obtain equipment information of the regulating devices, and establish a comprehensive regulating effect based on the equipment information and the location distribution of the regulating devices in the storage environment; Temperature and humidity are predicted based on the prediction model, and the timing compensation power of the equipment is configured based on the rated storage temperature threshold and the rated storage humidity threshold. The equipment regulation power is established by adjusting the overall impact and the equipment timing compensation power, and the regulation node is determined; The regulating device is activated at the regulating node, and the regulating device is used to regulate the power of the regulating device to control the storage environment. The step of configuring a prediction model based on temperature and humidity sequence data further includes: The prediction model formula is as follows: Where T(t) represents the first prediction network, H(t) represents the second prediction network, α and α′ represent the constant terms in the model, p and p′ are the orders of the autoregressive part, i represents the lag order of the autoregressive part, and φ i and φ′ i The autoregressive coefficients are represented by T(ti) and H(ti), which represent the actual temperature and humidity values ​​at past time points. q and q′ represent the order of the moving average component, j represents the lag order of the moving average component, and θ represents the lag order. j and θ′ j ∈(tj) and ∈′(tj) represent the temperature error term and humidity error term at past time points, respectively; ∈(t) represents the temperature error term at the current time point; and ∈′(t) represents the humidity error term at the current time point. The method of establishing equipment regulation power by adjusting the comprehensive influence and equipment timing compensation power further includes: The formula for adjusting the power of the equipment is as follows: Among them, P T (t) and P H (t) represents the equipment temperature regulation power and the equipment humidity regulation power, respectively, P base(T) and P base(H) These are the equipment time-series temperature compensation power and the equipment time-series humidity compensation power, respectively. T and γ H These are the temperature regulation coefficient and humidity regulation coefficient, respectively. pred (t) and H pred (t) represents the predicted temperature and humidity values ​​at time point t, respectively. set and H set Here, denoted as the rated storage temperature threshold and the rated storage humidity threshold, respectively; f(d, v, L) characterizes the comprehensive influence function of regulation; τ is the location influence coefficient; d is the distance between the regulating equipment and the monitoring point; β is the response speed influence coefficient; and t... delay To adjust the delay time, v is used to adjust the device's response speed, and L is used to adjust the response time. max L represents the power level of the device being adjusted to its maximum power rating.

2. The method for monitoring the storage environment of gas-sensitive nanomaterials as described in claim 1, characterized in that, Also includes: Establish and adjust the verification time window for node mapping; When the storage environment is controlled through the adjustment node, control monitoring is performed during the verification time window to establish a monitoring time series dataset. Timing compensation authentication is performed using the monitored time-series dataset, and the device power adjustment is optimized based on the timing compensation authentication results.

3. The method for monitoring the storage environment of gas-sensitive nanomaterials as described in claim 1, characterized in that, Also includes: Data evaluation was conducted on temperature and humidity series data to establish independent variation results; Configure the normalization coefficients for independent variation results, adjust the normalization of independent variation results according to the normalization coefficients, and establish the abnormal range based on the normalization adjustment results; External feature monitoring is performed within a time window in the abnormal range, and abnormal response features are configured based on the external feature monitoring results. The prediction model is corrected based on the abnormal response characteristics.

4. The method for monitoring the storage environment of gas-sensitive nanomaterials as described in claim 3, characterized in that, The process of evaluating temperature and humidity series data and establishing independent variation results also includes: The temperature and humidity series data are analyzed for continuous decrease within a preset time period to generate the first change result. We performed variation analysis on temperature and humidity series data per unit time, respectively, and established a second variation result. Establish independent change results based on the first change result and the second change result.

5. The method for monitoring the storage environment of gas-sensitive nanomaterials as described in claim 1, characterized in that, Also includes: Establish the life cycle of gas-sensitive nanomaterials and establish an additional adjustment coefficient that maps to the life cycle; The compensation sensitivity of the regulating device is adjusted by the additional adjustment coefficient, and the storage environment is controlled based on the adjustment result.

6. The method for monitoring the storage environment of gas-sensitive nanomaterials as described in claim 1, characterized in that, Also includes: Configure an early warning response threshold, and perform continuous analysis of temperature and humidity sequence data based on the early warning response threshold; A control anomaly was reported based on the trigger timing analysis results.

Images