Dehumidification control method and system based on humidity detection and intelligent dehumidifier

Abstract

The invention relates to the technical field of intelligent dehumidification, in particular to a dehumidification control method and system based on humidity detection and an intelligent dehumidifier, and the method comprises the following steps: collecting outdoor humidity data and indoor humidity data through a humidity sensor, executing time synchronization and marking, and carrying out data normalization processing to obtain initial environment humidity detection data; according to the invention, through humidity detection, advanced data processing and trend prediction, the precision and foresight of dehumidification control are improved, subtle humidity change is identified by using a difference technology, real-time fluctuation of environment humidity is accurately reflected, the humidity change in a short period is predicted by using a linear regression model, the accuracy of a prediction result is improved, prediction errors are reduced, and the method is suitable for large-scale popularization and application. By means of the calculation result of the humidity setting difference of the different areas, accurate adjustment, continuous monitoring and dynamic adjustment of dehumidification parameters of the dehumidification equipment in the different areas are achieved, it is ensured that the equipment is kept in the optimal operation state all the time, the energy efficiency is remarkably improved, and the comfort and safety of the living and working environment are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent dehumidification technology, and in particular to a dehumidification control method and system based on humidity detection and an intelligent dehumidifier. Background Art

[0002] The field of intelligent dehumidification technology involves the use of advanced sensors and control systems to automatically adjust the humidity in the air, thereby providing a more comfortable and healthy living and working environment. It combines environmental monitoring, Internet of Things technology and automated control systems to achieve precise humidity control. It usually includes humidity sensors, microprocessors and actuators (such as electronic valves or fans). The components work together to respond to environmental changes in real time and automatically adjust the operating status of the equipment to achieve the ideal humidity level. It is widely used in home, office, industrial and storage environments, especially in places where humidity needs to be strictly controlled to protect sensitive equipment or items.

[0003] Among them, the dehumidification control method of humidity detection is a technology that uses environmental humidity data to dynamically adjust the operation of the dehumidifier. Its main purpose is to automatically control indoor humidity to prevent various problems caused by excessively high or low humidity, such as mold growth, wood expansion or contraction, electronic equipment failure, etc. By monitoring the indoor humidity in real time and comparing it with the set target humidity value, the dehumidifier can be automatically turned on or off, thereby effectively maintaining the indoor humidity within an ideal range, which not only improves energy efficiency, but also enhances the comfort and safety of the living and working environment.

[0004] Existing technologies mainly rely on basic humidity monitoring and equipment adjustment, which results in an inability to effectively respond to complex or rapidly changing environmental conditions. At the same time, they lack advanced data analysis and prediction capabilities, and can only achieve reactive adjustments, but fail to adopt predictive control, which leads to delayed response to environmental changes in actual operations. Such an operating mode easily leads to frequent start and stop of equipment, increased energy consumption and equipment wear. For example, under rapidly changing humidity conditions, if the system fails to adjust in time, the indoor environment will be invaded by mold or structural materials will be damaged, affecting the safety and comfort of the space. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a dehumidification control method, system and intelligent dehumidifier based on humidity detection.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a dehumidification control method based on humidity detection, comprising the following steps:

[0007] S1: Collect outdoor humidity data and indoor humidity data through humidity sensors, perform time synchronization and marking, perform data normalization processing, and obtain initial environmental humidity detection data;

[0008] S2: Based on the initial environmental humidity detection data, using differential technology to identify trends and seasonal fluctuations in the data, performing local analysis on the data points, and outputting environmental humidity difference analysis results;

[0009] S3: Based on the results of the environmental humidity difference analysis, a linear regression model is used to predict the change trend of environmental humidity in the short term in the future, and the prediction error is analyzed by comparing with historical data to generate a humidity trend prediction result;

[0010] S4: using the humidity trend prediction result, calculating the humidity setting difference of the difference area, matching the needs of each area by controlling and adjusting the fan speed and operating frequency of the dehumidification equipment, and outputting the regional dehumidification plan;

[0011] S5: Apply the regional dehumidification scheme, continuously monitor and record the real-time humidity data of the region, dynamically adjust the dehumidification parameters according to the real-time data, determine that the dehumidification equipment maintains the optimal operating state, and obtain a dynamic dehumidification control scheme.

[0012] As a further solution of the present invention, the initial environmental humidity detection data includes a timestamp, a normalized humidity value and a synchronization marking result, the environmental humidity difference analysis result includes a trend offset value, a fluctuation frequency record and an abnormal fluctuation point record, the humidity trend prediction result includes a prediction confidence interval, a prediction standard error and a prediction time range, the regional dehumidification scheme includes setting a humidity difference, a fan adjustment parameter and a frequency adjustment value, and the dynamic dehumidification control scheme includes real-time humidity monitoring data, equipment performance monitoring records and environmental adaptability adjustment records.

[0013] As a further solution of the present invention, the specific steps of collecting outdoor humidity data and indoor humidity data through a humidity sensor, performing time synchronization and marking, and performing data normalization processing to obtain initial environmental humidity detection data are as follows:

[0014] S101: Collect outdoor humidity data and indoor humidity data through a humidity sensor, synchronize data timestamps, and calibrate timestamp errors to generate a time-synchronized humidity data set;

[0015] S102: Based on the time-synchronized humidity dataset, mark the source of each data point to identify it as an external or internal source, and uniquely encode each piece of data to generate a marked enhanced humidity dataset;

[0016] S103: Based on the marked enhanced humidity data set, the data set is normalized, the data value is converted to a range of 0 to 1 using a minimum-maximum scaling method, the consistency and accuracy of the converted data are verified, and initial environmental humidity detection data is generated.

[0017] As a further solution of the present invention, based on the initial environmental humidity detection data, the differential technology is used to identify the trend and seasonal fluctuations in the data, and the data points are locally analyzed to output the specific steps of the environmental humidity difference analysis results:

[0018] S201: Based on the initial environmental humidity detection data, the difference between consecutive data points is calculated, and the humidity change trend is identified by comparing the difference between the previous and next data points, and the significant change points are marked to generate trend identification humidity data;

[0019] S202: Based on the trend identification humidity data, analyze the periodic changes in the data, identify the seasonal fluctuation pattern by comparing the differential results of the data points in the continuous period, and calculate the average amplitude and periodic characteristics of the fluctuation to generate seasonal fluctuation humidity data;

[0020] S203: Based on the seasonal fluctuation humidity data, each data point is locally analyzed to highlight the key change areas in each cycle, and the humidity changes in the key change areas are summarized to output the environmental humidity difference analysis results.

[0021] As a further solution of the present invention, according to the results of the environmental humidity difference analysis, a linear regression model is used to predict the change trend of environmental humidity in the short term in the future, and the prediction error is analyzed by comparing with historical data to generate the specific steps of the humidity trend prediction result:

[0022] S301: Based on the environmental humidity difference analysis result, perform data format conversion, arrange the humidity difference data in time series, ensure the continuity and time consistency of the data, and generate prediction analysis input data;

[0023] S302: Based on the prediction analysis input data, linear trend fitting is performed on the humidity values ​​at consecutive time points to predict humidity changes in the future, and the predicted time range is recorded to generate future humidity prediction data;

[0024] S303: Based on the future humidity prediction data, the predicted humidity value is compared and analyzed with the historical data at the corresponding time point, the difference between the predicted value and the actual observed value is calculated, the error range and prediction accuracy of the model are evaluated, and the humidity trend prediction result is output.

[0025] As a further embodiment of the present invention, the difference between the calculated predicted value and the actual observed value is calculated according to the formula:

[0026]

[0027] Calculate, where w i is the time weighting coefficient, is the predicted value, yi is the actual observed value, n is the number of samples, and MSE represents the difference value.

[0028] As a further solution of the present invention, the humidity trend prediction result is used to calculate the humidity setting difference of the difference area, and the fan speed and operating frequency of the dehumidification equipment are controlled and adjusted to match the needs of each area. The specific steps of outputting the regional dehumidification plan are as follows:

[0029] S401: Based on the humidity trend prediction result, a humidity demand analysis is performed on each area, the difference between the future expected humidity and the current actual humidity is calculated, a new humidity target is set for each area, and regional humidity adjustment demand data is generated;

[0030] S402: Based on the regional humidity adjustment demand data, adjust the fan speed and operating frequency of the dehumidification equipment, increase and decrease the fan speed step by step, ensure that each area is accurately controlled according to the humidity adjustment demand, and generate equipment adjustment parameter data;

[0031] S403: Based on the equipment adjustment parameter data, implement the dehumidification adjustment plan for each area, record the adjustment details of the fan speed and operating frequency of each area, and output the regional dehumidification plan.

[0032] As a further solution of the present invention, the regional dehumidification solution is applied to continuously monitor and record the real-time humidity data of the region, dynamically adjust the dehumidification parameters according to the real-time data, determine the dehumidification equipment to maintain the optimal operating state, and obtain the specific steps of the dynamic dehumidification control solution:

[0033] S501: Based on the regional dehumidification scheme, monitor the regional humidity data in real time, record the data periodically, capture the periodic changes of humidity in each region, and generate real-time humidity monitoring data;

[0034] S502: Based on the real-time humidity monitoring data, analyzing the data to determine the necessity of humidity adjustment, comparing the target humidity value with the actual reading, calculating the difference and determining whether the operating parameters of the dehumidification equipment need to be adjusted, responding to changes in the real-time data, and generating dynamically adjusted dehumidification parameters;

[0035] S503: Based on the dynamically adjusted dehumidification parameters, dynamically update the dehumidification equipment settings, optimize the equipment operation to match the real-time humidity demand, continuously monitor the adjustment effect, verify the accuracy of humidity control, and output a dynamic dehumidification control solution.

[0036] Dehumidification control system based on humidity detection, including:

[0037] The data synchronization and encoding module collects outdoor humidity data and indoor humidity data through humidity sensors, synchronizes data timestamps, marks the source of each data point, and uniquely encodes each data to generate a marked enhanced humidity data set;

[0038] The data normalization processing module normalizes the data set based on the marked enhanced humidity data set, converts the data value using the minimum and maximum scaling method, calculates the difference between consecutive data points, marks significant change points, and generates trend recognition humidity data;

[0039] The periodicity analysis module identifies humidity data based on the trend, analyzes periodic changes in the data, identifies seasonal fluctuation patterns, and calculates the average amplitude and periodic characteristics of fluctuations, highlights key change areas within each cycle, and outputs environmental humidity difference analysis results;

[0040] The humidity prediction and analysis module performs data format conversion based on the environmental humidity difference analysis results, performs linear trend fitting on the humidity values ​​at consecutive time points, predicts humidity changes in the future, calculates the difference between the predicted value and the actual observed value, and outputs the humidity trend prediction result;

[0041] The dehumidification control and adjustment module calculates the difference between the future expected humidity and the current actual humidity based on the humidity trend prediction result, adjusts the fan speed and operating frequency of the dehumidification equipment, records the adjustment details of the fan speed and operating frequency of each area, and outputs the regional dehumidification plan;

[0042] The dynamic dehumidification adjustment module captures the periodic changes in humidity in each area based on the regional dehumidification plan, compares the target humidity value with the actual reading, calculates the difference and determines whether the operating parameters of the dehumidification equipment need to be adjusted, dynamically updates the dehumidification equipment settings, and outputs a dynamic dehumidification control plan.

[0043] The intelligent dehumidifier for dehumidification control based on humidity detection comprises a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the dehumidification control method based on humidity detection are implemented.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, the accuracy and foresight of dehumidification control are improved through humidity detection, advanced data processing and trend prediction, differential technology is used to identify subtle humidity changes, accurately reflect real-time fluctuations in ambient humidity, and a linear regression model is used to predict short-term humidity changes, thereby improving the accuracy of prediction results and reducing prediction errors. The calculation results of humidity setting differences in different areas are used to achieve precise adjustment of dehumidification equipment in different areas, continuously monitor and dynamically adjust dehumidification parameters, ensure that the equipment always maintains the optimal operating state, significantly improve energy efficiency, and significantly improve the comfort and safety of living and working environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0047] Figure 2 This is a flow chart for obtaining the initial environmental humidity detection data of the present invention;

[0048] Figure 3 The present invention is a flowchart for obtaining the results of the environmental humidity difference analysis;

[0049] Figure 4 A flow chart for obtaining humidity trend prediction results of the present invention;

[0050] Figure 5 A flowchart for obtaining a regional dehumidification solution of the present invention;

[0051] Figure 6 The following is a flow chart of obtaining the dynamic dehumidification control scheme of the present invention;

[0052] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0055] See also Figure 1 , a dehumidification control method based on humidity detection comprises the following steps:

[0056] S1: Collect outdoor humidity data and indoor humidity data through humidity sensors, perform time synchronization and marking, perform data normalization processing, and obtain initial environmental humidity detection data;

[0057] S2: Based on the initial environmental humidity detection data, the differential technology is used to identify trends and seasonal fluctuations in the data, and the data points are locally analyzed to output the environmental humidity difference analysis results;

[0058] S3: Based on the results of the environmental humidity difference analysis, a linear regression model is used to predict the changing trend of environmental humidity in the short term in the future. The prediction error is analyzed by comparing with historical data to generate the humidity trend prediction result;

[0059] S4: Calculate the humidity setting difference of the difference area by using the humidity trend prediction results, control and adjust the fan speed and operating frequency of the dehumidification equipment to match the needs of each area, and output the regional dehumidification plan;

[0060] S5: Apply the regional dehumidification solution, continuously monitor and record the real-time humidity data of the area, dynamically adjust the dehumidification parameters according to the real-time data, determine the dehumidification equipment to maintain the optimal operating state, and obtain a dynamic dehumidification control solution.

[0061] The initial environmental humidity detection data includes timestamp, normalized humidity value and synchronization marking results. The environmental humidity difference analysis results include trend offset value, fluctuation frequency record and abnormal fluctuation point record. The humidity trend prediction results include prediction confidence interval, prediction standard error and prediction time range. The regional dehumidification plan includes setting humidity difference, fan adjustment parameters and frequency adjustment value. The dynamic dehumidification control plan includes real-time humidity monitoring data, equipment performance monitoring records and environmental adaptability adjustment records.

[0062] See also Figure 2 , the specific steps of S1 are:

[0063] S101: Collect outdoor humidity data and indoor humidity data through a humidity sensor, synchronize data timestamps, and calibrate timestamp errors to generate a time-synchronized humidity data set;

[0064] The outdoor humidity data and indoor humidity data are collected through humidity sensors, the data timestamps are synchronized, the difference between the external data timestamp and the internal data timestamp is calculated, and the linear interpolation method is used for correction to ensure the consistency of the timestamps of the two. First, the time series and humidity values ​​of the external humidity sensor and the internal humidity sensor are extracted, the mean and standard deviation of the timestamp deviation are calculated, and the time deviation is adjusted according to the statistical results to ensure that the error is within an acceptable range. In this way, a time-synchronized humidity data set is generated, which includes the synchronized timestamp and the corresponding humidity value.

[0065] S102: Based on the time-synchronized humidity dataset, mark the source of each data point to identify it as an external or internal source, and uniquely encode each piece of data to generate a marked enhanced humidity dataset;

[0066] Based on the time-synchronized humidity dataset, each data point is source-tagged to identify it as an external or internal source, and then a unique code is generated for each piece of data. The specific method is to use a hash function to encode the timestamp and source to generate a unique identifier, which is attached to each data point. The data integrity is also checked during this process to ensure that each data point is correctly tagged and encoded for subsequent data tracking and processing. The generated tag-enhanced humidity dataset will contain the timestamp, humidity value, source tag and its unique code for each data point.

[0067] S103: Based on the marked enhanced humidity data set, the data set is normalized, the data value is converted to a range of 0 to 1 using the minimum and maximum scaling method, the consistency and accuracy of the converted data are verified, and the initial environmental humidity detection data is generated;

[0068] Based on the labeled enhanced humidity dataset, the dataset is normalized and the data values ​​are converted to the range of 0 to 1 using the minimum-maximum scaling method. The specific operation includes calculating the maximum and minimum values ​​of humidity in the dataset, and then applying the formula: (humidity value-minimum value) / (maximum-minimum value) to adjust the humidity value. In this step, the converted data is also statistically analyzed to verify its consistency and accuracy to ensure that all data points are correctly normalized. After completing these steps, the initial environmental humidity detection data is generated, and this dataset will provide a basis for environmental monitoring and further data analysis.

[0069] See also Figure 3 , the specific steps of S2 are:

[0070] S201: Based on the initial environmental humidity detection data, the difference between consecutive data points is calculated, and the humidity change trend is identified by comparing the difference between the previous and next data points, and the significant change points are marked to generate trend identification humidity data;

[0071] Based on the initial environmental humidity detection data, the difference between consecutive data points is calculated. The method is to subtract the humidity value of the current data point from the humidity value of the previous data point. Through this difference calculation, the humidity change in the short term can be revealed. The specific difference formula is Δh i =h i -h i-1 , where h i and h i-1 Represents the continuous humidity measurement value, Δh i Indicates the difference value within each cycle. Next, by setting a change threshold, the difference between the previous and next data points is compared to identify the significant change points of humidity. Significant change points are those data points whose difference values ​​exceed the threshold, which indicate that the humidity has changed rapidly or significantly. In this way, significant change points are marked and special identifiers are added to the data set to generate trend identification humidity data, providing key information for subsequent detailed analysis.

[0072] S202: Identify humidity data based on trends, analyze periodic changes in the data, identify seasonal fluctuation patterns by comparing differential results of data points in consecutive periods, and calculate the average amplitude and periodic characteristics of fluctuations to generate seasonal fluctuation humidity data;

[0073] Based on the trend identification of humidity data, the data is first analyzed in time series to identify periodic changes in the data. Autocorrelation and partial autocorrelation function analysis techniques are used to detect and confirm periodic features in the data. Through these techniques, recurring patterns in the data, such as seasonal fluctuations, can be identified. Subsequently, the difference results of the data points within each period are calculated, and the average amplitude of the fluctuations is estimated by the difference values. The calculation formula is Where Δh i Represents the difference value within each cycle, and N is the number of data points within the cycle. In addition, the maximum and minimum values ​​within the cycle are compared to obtain periodic characteristics, and the information is combined to generate seasonal fluctuation humidity data, which can be used to further analyze the impact of seasonal changes on environmental monitoring.

[0074] S203: Based on the seasonal fluctuation humidity data, perform local analysis on each data point, highlight the key change areas in each cycle, summarize the humidity changes in the key change areas, and output the environmental humidity difference analysis results;

[0075] Based on the seasonal fluctuation humidity data, each data point is analyzed locally, focusing on the key change areas within each cycle. By analyzing the maximum increase and decrease points within each cycle, the possible causes of these changes are identified, such as sudden changes in environmental factors or periodic natural changes. Further, the data points in the key change areas are analyzed in depth to summarize the characteristics and trends of humidity changes in each area. Finally, these local analysis results are summarized and the environmental humidity difference analysis results are output, where the humidity change in each key change area can be calculated by the formula Var k =max(Δh k )-min(Δh k ) to describe, Var k represents the maximum humidity variation range of the kth cycle, where Δh k represents the humidity difference value in the kth cycle. The results not only provide in-depth insights into environmental changes, but also provide data support for formulating countermeasures.

[0076] See also Figure 4 , the specific steps of S3 are:

[0077] S301: Based on the results of the environmental humidity difference analysis, data format conversion is performed, and the humidity difference data is arranged in a time series to ensure the continuity and time consistency of the data, and generate prediction analysis input data;

[0078] Based on the results of the environmental humidity difference analysis, the data format is converted and the humidity difference data is arranged in time series to ensure the continuity and time consistency of the data. First, the timestamp and corresponding humidity difference value of each data point are extracted from the difference analysis results, and then sorted according to the timestamp to ensure that all data are arranged in time order, thereby eliminating the impact caused by time dislocation in data collection or processing. Through this formatting process, structured predictive analysis input data is generated, providing a clear and consistent data foundation for subsequent data analysis and trend prediction.

[0079] S302: Based on the prediction analysis input data, linear trend fitting is performed on the humidity values ​​at consecutive time points to predict the humidity change in the future, and the predicted time range is recorded to generate future humidity prediction data;

[0080] Based on the forecast analysis input data, the humidity values ​​at consecutive time points are fitted with a linear trend to predict the humidity changes in the future and record the predicted time range. The specific method is to apply a linear regression model to estimate the relationship between humidity value and time through the least squares method. The fitting formula is H(t) = β0+

[0081] β1·t, where β0 is the intercept, β1 is the slope, indicating the trend over time, t represents the time variable, and H(t) represents the predicted humidity value at any given time t. This model will calculate the optimal β0 and β1 based on the existing data points to predict the humidity value at any given time point. In this way, future humidity forecast data is generated to provide a basis for further decision-making and planning.

[0082] S303: Based on the future humidity prediction data, the predicted humidity value is compared and analyzed with the historical data at the corresponding time point, the difference between the predicted value and the actual observed value is calculated, the error range and prediction accuracy of the model are evaluated, and the humidity trend prediction result is output;

[0083] Calculate the difference between the predicted value and the actual observed value, according to the formula,

[0084]

[0085] Calculate, where w i is the time weighting coefficient, is the predicted value, y i is the actual observed value, n is the number of samples, and MSE represents the difference value.

[0086] The execution process is as follows:

[0087] First, a weight w is assigned to each data point according to its temporal proximity i , recent data are given a higher weight to reflect their greater impact on the accuracy of the forecast; then, the square of the difference between the predicted value and the actual value at each time point is calculated, and the square of the difference is multiplied by the corresponding weight; finally, all weighted square differences are accumulated and divided by the number of samples n to obtain the MSE of the difference between the predicted value and the actual observed value. By introducing the time weighting coefficient, the impact of the forecast error at different time points on the overall performance of the model can be more accurately reflected.

[0088] Confirm the weight coefficient w i The steps are as follows:

[0089] Determine the weight assignment strategy, you can choose linearly decreasing weights, where the most recent observations are given the highest weights;

[0090] Calculate the weight based on the time distance from the observation point to the prediction starting point;

[0091] Normalize all weights to ensure that the sum is 1, ensure the reasonable distribution of weight coefficients, and effectively reflect the importance of data at different time points.

[0092] See also Figure 5 , the specific steps of S4 are:

[0093] S401: Based on the humidity trend prediction results, humidity demand analysis is performed for each area, the difference between the future expected humidity and the current actual humidity is calculated, a new humidity target is set for each area, and regional humidity adjustment demand data is generated;

[0094] Based on the humidity trend forecast results, humidity demand analysis is performed for each area to calculate the difference between the expected humidity in the future and the current actual humidity. Use the formula ΔH1=H 预期 -H 实际 , where H 预期 is the expected humidity predicted based on environmental conditions and seasonal demand, while H 实际 is the current humidity obtained from the most recent environmental monitoring data, and ΔH1 is the humidity difference value. Through this difference value analysis, new humidity targets are set for each area, and these targets will be adjusted according to the specific environmental needs and usage of each area. This will generate regional humidity adjustment demand data, which will directly affect the subsequent equipment adjustment strategy to ensure that each area can achieve its optimal environmental conditions.

[0095] S402: Based on the regional humidity adjustment demand data, the fan speed and operating frequency of the dehumidification equipment are adjusted, and the fan speed is gradually increased or decreased to ensure that each area is accurately controlled according to the humidity adjustment demand, and the equipment adjustment parameter data is generated;

[0096] Based on the regional humidity adjustment demand data, adjust the fan speed and operating frequency of the dehumidification equipment. First, calculate the required fan speed adjustment amount based on the humidity adjustment demand data of each area, using the formula V 新 =V 旧 +k·ΔH1, where V 新 and V 旧 are the adjusted and current fan speeds, ΔH1 is the humidity difference, and k is the calibration coefficient used to determine the relationship between speed change and humidity difference. By increasing and decreasing the fan speed step by step, each zone is accurately controlled according to its humidity adjustment needs. In this way, equipment adjustment parameter data is generated, which provides accurate control parameters for the actual operation of the equipment.

[0097] S403: Based on the equipment adjustment parameter data, implement the dehumidification adjustment plan for each area, record the adjustment details of the fan speed and operating frequency of each area, and output the regional dehumidification plan;

[0098] Based on the equipment adjustment parameter data, implement the dehumidification adjustment plan for each area. In this step, adjust the fan speed and operating frequency of the dehumidification equipment according to the new humidity target and equipment adjustment parameters set for each area. Record the adjustment details of the fan speed and operating frequency of each area, including the fan speed value before and after the adjustment, the operating frequency, and the specific time point of the adjustment. Finally, output the dehumidification plan for each area. These plans describe in detail how to meet the specific humidity requirements of each area by adjusting the fan speed and frequency to ensure the optimization of environmental comfort and equipment efficiency.

[0099] See also Figure 6 , the specific steps of S5 are:

[0100] S501: Based on the regional dehumidification solution, monitor the regional humidity data in real time, record the data periodically, capture the periodic changes of humidity in each region, and generate real-time humidity monitoring data;

[0101] Based on the regional dehumidification solution, the regional humidity data is monitored in real time and the data is recorded periodically. First, humidity sensors are deployed to continuously collect humidity data in each area. The sensors send data regularly, and each data point is marked with a timestamp to ensure the real-time and accuracy of the data. Then, time series analysis is used to capture the periodic changes in humidity in each area, using formula H t =αH t-1 +(1-α)H 新测量 To smooth the data, where α is the smoothing coefficient, H t is the estimated humidity for the current period, H t-1 is the humidity of the previous cycle, H 新测量 It is the latest measurement value, which generates real-time humidity monitoring data after processing, providing a basis for subsequent analysis and adjustment.

[0102] S502: Based on the real-time humidity monitoring data, analyze the data to determine the necessity of humidity adjustment, compare the target humidity value with the actual reading, calculate the difference and determine whether the operating parameters of the dehumidification equipment need to be adjusted, respond to the changes in the real-time data, and generate dynamically adjusted dehumidification parameters;

[0103] Based on real-time humidity monitoring data, analyze the data to determine the need for humidity adjustment. Compare the target humidity value with the actual reading and use the formula to calculate the difference between the two ΔH2=H 目标 -H 实测 , where H 目标 Indicates the target humidity value, H 实测Indicates the measured humidity value. If the difference ΔH2 exceeds the preset tolerance range, it indicates that the operating parameters of the dehumidification equipment need to be adjusted. Based on these analysis results, dynamically adjusted dehumidification parameters are generated, including adjusting the fan speed or operating frequency to respond to changes in real-time data and ensure that the humidity is controlled within the ideal range.

[0104] S503: Based on the dynamically adjusted dehumidification parameters, dynamically update the dehumidification equipment settings, optimize the equipment operation to match the real-time humidity demand, continuously monitor the adjustment effect, verify the accuracy of humidity control, and output a dynamic dehumidification control solution;

[0105] Dynamically update the dehumidification equipment settings based on the dynamically adjusted dehumidification parameters. Optimize the operation of the equipment according to the adjusted parameters, and match the real-time humidity requirements in this way to ensure the equipment operation efficiency and the accuracy of humidity control. Continuously monitor the adjustment effect, record the equipment operation status and humidity control data in real time, verify the accuracy of humidity control, and further optimize the adjustment strategy based on the monitoring results. Output the dynamic dehumidification control plan, provide detailed operation and maintenance guidelines for equipment management, and ensure that the regional humidity is maintained at the optimal state.

[0106] See also Figure 7 , a dehumidification control system based on humidity detection, including:

[0107] The data synchronization and encoding module collects outdoor humidity data and indoor humidity data through humidity sensors, synchronizes data timestamps, marks the source of each data point, and uniquely encodes each data to generate a labeled enhanced humidity data set;

[0108] The data normalization processing module normalizes the data set based on the marker-enhanced humidity data set, uses the minimum-maximum scaling method to transform the data values, calculates the difference between consecutive data points, marks significant change points, and generates trend-recognized humidity data;

[0109] The periodic analysis module identifies humidity data based on trends, analyzes periodic changes in the data, identifies seasonal fluctuation patterns, and calculates the average amplitude and periodic characteristics of fluctuations, highlights key change areas within each cycle, and outputs environmental humidity difference analysis results;

[0110] The humidity prediction and analysis module converts the data format based on the results of the environmental humidity difference analysis, performs linear trend fitting on the humidity values ​​at consecutive time points, predicts the humidity changes in the future, calculates the difference between the predicted value and the actual observed value, and outputs the humidity trend prediction results;

[0111] The dehumidification control and adjustment module calculates the difference between the future expected humidity and the current actual humidity based on the humidity trend prediction results, adjusts the fan speed and operating frequency of the dehumidification equipment, records the adjustment details of the fan speed and operating frequency of each area, and outputs the regional dehumidification plan;

[0112] The dynamic dehumidification adjustment module is based on the regional dehumidification plan, captures the periodic changes in humidity in each area, compares the target humidity value with the actual reading, calculates the difference and determines whether the operating parameters of the dehumidification equipment need to be adjusted, dynamically updates the dehumidification equipment settings, and outputs a dynamic dehumidification control plan.

[0113] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A dehumidification control method based on humidity detection, characterized in that: The following steps are involved: The outdoor humidity data and indoor humidity data are collected through the humidity sensor, time synchronization and marking are performed, and data normalization processing is performed to obtain the initial environmental humidity detection data; Based on the initial environmental humidity detection data, using differential technology to identify trends and seasonal fluctuations in the data, performing local analysis on the data points, and outputting environmental humidity difference analysis results; According to the results of the environmental humidity difference analysis, a linear regression model is used to predict the change trend of environmental humidity in the short term in the future, and the prediction error is analyzed by comparing with historical data to generate a humidity trend prediction result; Utilizing the humidity trend prediction results, the humidity setting difference of the difference area is calculated, and the fan speed and operating frequency of the dehumidification equipment are controlled and adjusted to match the needs of each area, and a regional dehumidification plan is output; The regional dehumidification scheme is applied to continuously monitor and record the real-time humidity data of the region, dynamically adjust the dehumidification parameters according to the real-time data, determine that the dehumidification equipment maintains the optimal operating state, and obtain a dynamic dehumidification control scheme.

2. The dehumidification control method based on humidity detection according to claim 1, characterized in that: The initial environmental humidity detection data includes a timestamp, a normalized humidity value and a synchronization mark result; the environmental humidity difference analysis result includes a trend offset value, a fluctuation frequency record and an abnormal fluctuation point record; the humidity trend prediction result includes a prediction confidence interval, a prediction standard error and a prediction time range; the regional dehumidification scheme includes a set humidity difference, a fan adjustment parameter and a frequency adjustment value; the dynamic dehumidification control scheme includes real-time humidity monitoring data, equipment performance monitoring records and environmental adaptability adjustment records.

3. The dehumidification control method based on humidity detection according to claim 1, characterized in that: The specific steps of collecting outdoor humidity data and indoor humidity data through humidity sensors, performing time synchronization and marking, and performing data normalization processing to obtain initial environmental humidity detection data are as follows: Collect outdoor humidity data and indoor humidity data through humidity sensors, synchronize data timestamps, and calibrate timestamp errors to generate time-synchronized humidity data sets; Based on the time-synchronized humidity dataset, each data point is source-tagged to identify it as an external or internal source, and each piece of data is uniquely encoded to generate a tagged enhanced humidity dataset; Based on the labeled enhanced humidity data set, the data set is normalized, the data value is converted to a range of 0 to 1 using the minimum and maximum scaling method, the consistency and accuracy of the converted data are verified, and initial environmental humidity detection data is generated.

4. The dehumidification control method based on humidity detection according to claim 1, characterized in that: Based on the initial environmental humidity detection data, the specific steps of using differential technology to identify trends and seasonal fluctuations in the data, performing local analysis on the data points, and outputting the environmental humidity difference analysis results are as follows: Based on the initial environmental humidity detection data, the difference between consecutive data points is calculated, and the humidity change trend is identified by comparing the difference between the previous and next data points, and the significant change points are marked to generate trend identification humidity data; Based on the trend identification humidity data, the periodic changes in the data are analyzed, and the seasonal fluctuation pattern is identified by comparing the difference results of the data points in the consecutive periods, and the average amplitude and periodic characteristics of the fluctuation are calculated to generate seasonal fluctuation humidity data; Based on the seasonal fluctuation humidity data, each data point is locally analyzed to highlight the key change areas in each cycle, and the humidity changes in the key change areas are summarized to output the environmental humidity difference analysis results.

5. The dehumidification control method based on humidity detection according to claim 1, characterized in that: According to the results of the environmental humidity difference analysis, a linear regression model is used to predict the change trend of environmental humidity in the short term in the future. By comparing and analyzing the prediction error with historical data, the specific steps of generating the humidity trend prediction result are as follows: Based on the environmental humidity difference analysis results, data format conversion is performed, the humidity difference data is arranged in time series to ensure the continuity and time consistency of the data, and prediction analysis input data is generated; Based on the forecast analysis input data, linear trend fitting is performed on the humidity values ​​at consecutive time points to predict humidity changes in the future, and the predicted time range is recorded to generate future humidity forecast data; Based on the future humidity prediction data, the predicted humidity value is compared and analyzed with the historical data at the corresponding time point, the difference between the predicted value and the actual observed value is calculated, the error range and prediction accuracy of the model are evaluated, and the humidity trend prediction result is output.

6. The dehumidification control method based on humidity detection according to claim 5, characterized in that: The difference between the predicted value and the actual observed value is calculated according to the formula, Calculate, where w i is the time weighting coefficient, is the predicted value, y i is the actual observed value, n is the number of samples, and MSE represents the difference value.

7. The dehumidification control method based on humidity detection according to claim 1, characterized in that: The humidity trend prediction results are used to calculate the humidity setting difference of the difference area, and the fan speed and operating frequency of the dehumidification equipment are controlled and adjusted to match the needs of each area. The specific steps of outputting the regional dehumidification plan are as follows: Based on the humidity trend prediction results, a humidity demand analysis is performed on each area, the difference between the future expected humidity and the current actual humidity is calculated, a new humidity target is set for each area, and regional humidity adjustment demand data is generated; Based on the humidity adjustment demand data of the area, the fan speed and operating frequency of the dehumidification equipment are adjusted, and the fan speed is gradually increased or decreased to ensure that each area is accurately controlled according to the humidity adjustment demand, and the equipment adjustment parameter data is generated; Based on the equipment adjustment parameter data, a dehumidification adjustment plan for each zone is implemented, the adjustment details of the fan speed and operating frequency of each zone are recorded, and the zone dehumidification plan is output.

8. The dehumidification control method based on humidity detection according to claim 1, characterized in that: Apply the regional dehumidification scheme, continuously monitor and record the real-time humidity data of the region, dynamically adjust the dehumidification parameters according to the real-time data, determine the dehumidification equipment to maintain the optimal operating state, and obtain the specific steps of the dynamic dehumidification control scheme as follows: Based on the regional dehumidification scheme, the regional humidity data is monitored in real time, the data is recorded periodically, the periodic changes of humidity in each region are captured, and real-time humidity monitoring data is generated; Based on the real-time humidity monitoring data, analyzing the data to determine the necessity of humidity adjustment, comparing the target humidity value with the actual reading, calculating the difference and determining whether the operating parameters of the dehumidification equipment need to be adjusted, and responding to changes in the real-time data to generate dynamically adjusted dehumidification parameters; Based on the dynamically adjusted dehumidification parameters, the dehumidification equipment settings are dynamically updated, the equipment operation is optimized to match the real-time humidity demand, the adjustment effect is continuously monitored, the accuracy of the humidity control is verified, and a dynamic dehumidification control solution is output.

9. A dehumidification control system based on humidity detection, characterized in that: The dehumidification control system based on humidity detection is used to execute the dehumidification control method based on humidity detection according to any one of claims 1 to 8, and the system comprises: The data synchronization and encoding module collects outdoor humidity data and indoor humidity data through humidity sensors, synchronizes data timestamps, marks the source of each data point, and uniquely encodes each data to generate a labeled enhanced humidity data set; The data normalization processing module normalizes the data set based on the marked enhanced humidity data set, converts the data value using the minimum and maximum scaling method, calculates the difference between consecutive data points, marks significant change points, and generates trend recognition humidity data; The periodicity analysis module identifies humidity data based on the trend, analyzes periodic changes in the data, identifies seasonal fluctuation patterns, and calculates the average amplitude and periodic characteristics of fluctuations, highlights key change areas within each cycle, and outputs environmental humidity difference analysis results; The humidity prediction and analysis module performs data format conversion based on the environmental humidity difference analysis results, performs linear trend fitting on the humidity values ​​at consecutive time points, predicts humidity changes in the future, calculates the difference between the predicted value and the actual observed value, and outputs the humidity trend prediction result; The dehumidification control and adjustment module calculates the difference between the future expected humidity and the current actual humidity based on the humidity trend prediction result, adjusts the fan speed and operating frequency of the dehumidification equipment, records the adjustment details of the fan speed and operating frequency of each area, and outputs the regional dehumidification plan; The dynamic dehumidification adjustment module captures the periodic changes in humidity in each area based on the regional dehumidification plan, compares the target humidity value with the actual reading, calculates the difference and determines whether the operating parameters of the dehumidification equipment need to be adjusted, dynamically updates the dehumidification equipment settings, and outputs a dynamic dehumidification control plan.

10. A dehumidification control intelligent dehumidifier based on humidity detection, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the processor executes the computer program, the steps of the dehumidification control method based on humidity detection according to any one of claims 1 to 9 are implemented.

Images