Environmental protection and performance optimization method and system of temperature and humidity detector

Abstract

The invention relates to an environment protection and performance optimization method and system for a temperature and humidity detector in the field of production of the temperature and humidity detector, and the method comprises the steps: obtaining the operation environment data of a sensor, determining the occurrence frequency and intensity of a dew formation problem and a pollution problem through analyzing the real-time monitoring values of a high-humidity environment and pollutant permeation, and carrying out the optimization of the performance of the temperature and humidity detector. Environment load distribution characteristics are obtained; according to the failure time prediction model, a dynamic simulation algorithm of gradient ventilation packaging is adopted, triggering conditions of air tightness difference and overall imbalance are analyzed, an optimization parameter range of protection efficiency is determined, and a packaging adjustment scheme is obtained; through a packaging adjustment scheme, obtaining quantitative indexes of an adsorption saturation state and a disassembly and assembly difficulty degree of the middle-layer filter unit, and obtaining structure optimization design data of the filter unit; according to the performance verification result, the change trend of the service life of the sensor in long-term operation is obtained, the influence weights of the moisture condensation problem and the pollution problem on the service life are analyzed, and the replacement period and the maintenance triggering condition of the middle-layer filtering unit are determined.

Description

Technical Field

[0001] The present invention relates to the production field of temperature and humidity detectors, and particularly to a method and system for environmental protection and performance optimization of temperature and humidity detectors. Background Art

[0002] In the field of environmental detector manufacturing, the research and development and application of temperature and humidity detectors are crucial for ensuring the stability and reliability of equipment under extreme conditions. With the growth of industrial monitoring, meteorological observation, and smart home needs, the performance of temperature and humidity detectors directly affects data accuracy and system life. However, the condensation problem in high-humidity environments and the sensitivity limitation of traditional packaging structures have become the key bottlenecks restricting their development. How to achieve long-term and efficient operation in complex environments has become a technical problem that the industry urgently needs to break through. Existing solutions mostly rely on a single hydrophobic coating or a simple filter layer to deal with humidity and pollutants, but these methods have shown obvious deficiencies in long-term use. The single coating is prone to aging and failure, and the filter layer loses its function due to adsorption saturation, especially in high-pollution or high-humidity scenarios, the sensor life is significantly shortened. In addition, traditional packaging structures often sacrifice breathability in pursuit of protection, resulting in internal humidity imbalance and affecting detection accuracy. These limitations make it difficult for existing technologies to meet the needs of diverse application scenarios. Specifically, the core challenges faced in this field focus on the optimization of gradient breathable packaging and the sustainability of the middle-layer filtering unit. Although the outer hydrophobic film can block liquid water, it cannot cope with pollutant penetration; the middle-layer activated carbon needs to be frequently replaced after adsorption saturation, and the traditional fixed design is difficult to disassemble and install, increasing the maintenance cost; although the inner hydrophilic film can balance humidity, it cannot solve the overall protection imbalance caused by the failure of the middle layer. These technical factors have not been solved, resulting in the sensor being easily damaged due to condensation or pollution during long-term use, thereby affecting its stability and economy in the industrial environment. Therefore, how to design a middle-layer filtering unit that can be quickly replaced while ensuring the airtightness and protection efficiency of the overall gradient breathable packaging has become the key issue for improving the full-life cycle performance of temperature and humidity detectors. Summary of the Invention

[0003] The present invention provides a method for environmental protection and performance optimization of temperature and humidity detectors, including the following steps:

[0004] Obtain the sensor operating environment data, and determine the occurrence frequency and intensity of condensation problems and pollution problems by analyzing the real-time monitoring values of high-humidity environments and pollutant penetration, so as to obtain the environmental load distribution characteristics;

[0005] According to the environmental load distribution characteristics, extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle-layer filtration from the historical operation data, and judge the relevance of their failures to obtain a failure time prediction model;

[0006] According to the failure time prediction model, adopt the dynamic simulation algorithm of gradient airtight packaging, analyze the triggering conditions of poor airtightness and overall imbalance, determine the optimization parameter range of the protection efficiency, and obtain the packaging adjustment plan;

[0007] Through the packaging adjustment plan, obtain the quantitative indicators of the adsorption saturation state and disassembly difficulty of the middle-layer filter unit, judge the improvement requirements of replaceability, and obtain the structural optimization design data of the filter unit;

[0008] For the structural optimization design data, extract the combination of hydrophobic coating and hydrophilic film suitable for high-humidity environment from the preset material database, analyze its compatibility with the middle-layer filter unit, and determine the configuration plan of the new packaging material;

[0009] According to the configuration plan of the new packaging material, adopt the finite element analysis algorithm to simulate the performance of the gradient airtight packaging under the scenarios of pollutant penetration and humidity imbalance, judge the improvement range of the detection accuracy, and obtain the performance verification result;

[0010] Through the performance verification result, obtain the change trend of the sensor life during long-term operation, analyze the influence weights of the condensation problem and the pollution problem on the life, and determine the replacement cycle and maintenance trigger conditions of the middle-layer filter unit;

[0011] For the replacement cycle and maintenance trigger conditions, extract the abnormal signals of poor airtightness and overall imbalance from the real-time monitoring data, adopt the signal processing algorithm to judge the dynamic adjustment requirements of the protection efficiency, and obtain the packaging adaptive control parameters;

[0012] According to the packaging adaptive control parameters, generate the quick replacement execution instruction of the middle-layer filter unit through the preset control system database, analyze the changes in the sensor life and detection accuracy after the instruction execution, and obtain the full-life cycle performance optimization data.

[0013] The present invention provides an environmental protection and performance optimization system for a temperature and humidity detector, mainly including:

[0014] An environmental monitoring module, used to obtain the sensor operating environment data, and determine the occurrence frequency and intensity of the condensation problem and the pollution problem by analyzing the real-time monitoring values of the high-humidity environment and pollutant penetration, so as to obtain the environmental load distribution characteristics;

[0015] A failure analysis module, used to extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle-layer filter from the historical operation data according to the environmental load distribution characteristics, judge the relevance of the two failures, and obtain the failure time prediction model;

[0016] The simulation optimization module is used to analyze the triggering conditions of poor airtightness and overall imbalance, determine the optimization parameter range of the protection effectiveness, and obtain the package adjustment plan by using the dynamic simulation algorithm of gradient air permeability encapsulation according to the failure time prediction model;

[0017] The structure design module is used to obtain the quantification indexes of the adsorption saturation state and disassembly difficulty of the middle-layer filtering unit through the package adjustment plan, judge the improvement requirements of replaceability, and obtain the structure optimization design data of the filtering unit;

[0018] The material configuration module is used to extract the combination of hydrophobic coating and hydrophilic film applicable to high-humidity environment from the preset material database for the structure optimization design data, analyze its compatibility with the middle-layer filtering unit, and determine the configuration plan of the new packaging material;

[0019] The performance verification module is used to simulate the performance of the gradient air permeability encapsulation in the scenarios of pollutant penetration and humidity imbalance by using the finite element analysis algorithm according to the configuration plan of the new packaging material, judge the improvement range of the detection accuracy, and obtain the performance verification result;

[0020] The life evaluation module is used to obtain the change trend of the sensor life during long-term operation through the performance verification result, analyze the influence weights of the condensation problem and the pollution problem on the life, and determine the replacement cycle and maintenance trigger conditions of the middle-layer filtering unit;

[0021] The dynamic control module is used to extract the abnormal signals of poor airtightness and overall imbalance from the real-time monitoring data for the replacement cycle and maintenance trigger conditions, judge the dynamic adjustment requirements of the protection effectiveness by using the signal processing algorithm, and obtain the package adaptive control parameters;

[0022] The instruction execution module is used to generate the quick replacement execution instruction of the middle-layer filtering unit through the preset control system database according to the package adaptive control parameters, analyze the changes of the sensor life and detection accuracy after the instruction execution, and obtain the full life cycle performance optimization data.

[0023] The technical solution provided by the embodiment of the present invention may include the following beneficial effects:

[0024] The present invention discloses an environmental protection and performance optimization method for a temperature and humidity detector. By analyzing the real-time monitoring data of high humidity environment and pollutant penetration, this method determines the occurrence characteristics of condensation and pollution problems, and establishes a prediction model for the failure of hydrophobic coating and middle layer filtration. Based on this, the present invention uses a dynamic simulation algorithm of gradient air permeable encapsulation to optimize the protection efficiency, and designs a replaceable middle layer filtration unit structure. Through finite element analysis, the present invention verifies the performance of the new encapsulation material in extreme environments, and determines the replacement cycle of the middle layer filtration unit. Finally, the present invention uses real-time monitoring data and adaptive control parameters to realize the performance optimization of the entire life cycle of the sensor, effectively improving the durability and detection accuracy of the sensor in high humidity and polluted environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flowchart of an environmental protection and performance optimization method for a temperature and humidity detector of the present invention.

[0026] Figure 2 It is a schematic diagram of an environmental protection and performance optimization method and system for a temperature and humidity detector of the present invention.

[0027] Figure 3 It is another schematic diagram of an environmental protection and performance optimization method and system for a temperature and humidity detector of the present invention.

[0028] Figure 4 It is a schematic structural diagram of an environmental protection and performance optimization method and system for a temperature and humidity detector of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] To further understand the content of the present invention, the present invention will be described in detail in combination with the drawings and embodiments. The following further elaborates the present application with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention, rather than limiting the invention. Additionally, it should be noted that for the sake of convenience of description, only the parts related to the invention are shown in the drawings.

[0030] Such as Figures 1-4 , a method for environmental protection and performance optimization of a temperature and humidity detector in this embodiment may specifically include:

[0031] S101. Obtain the sensor operating environment data, and determine the occurrence frequency and intensity of condensation problems and pollution problems by analyzing the real-time monitoring values of high humidity environment and pollutant penetration, so as to obtain the environmental load distribution characteristics.

[0032] Obtain environmental data, perform denoising processing on the environmental data using data preprocessing techniques to obtain a clean environmental dataset; extract the real-time monitoring values of high humidity and pollutant penetration from the clean environmental dataset, and determine the fluctuation range of the real-time monitoring values; for the fluctuation range, if the high humidity value exceeds a preset first threshold, it is determined as a condensation phenomenon, record its occurrence time and intensity to obtain a condensation feature set; for the fluctuation range, if the pollutant penetration exceeds a preset second threshold, it is determined as a pollution phenomenon, record its occurrence time and intensity to obtain a pollution feature set; obtain the condensation feature set and the pollution feature set, calculate the occurrence frequency using a frequency analysis algorithm to obtain frequency distribution data; process the condensation feature set and the pollution feature set using an intensity distribution algorithm to determine the intensity distribution characteristics and obtain intensity distribution data; by fusing the frequency distribution data and the intensity distribution data, judge the distribution characteristics of the environmental load to obtain the environmental load distribution result.

[0033] Exemplarily, in an environmental monitoring system, the raw data collected by sensors usually contains noise.

[0034] Exemplarily, a temperature and humidity sensor may be subject to electromagnetic interference, resulting in fluctuating readings. Data preprocessing techniques such as median filtering can effectively remove these outliers and obtain a more accurate environmental dataset.

[0035] Specifically, the real-time monitoring of high humidity and pollutant penetration is crucial.

[0036] For example, in an enclosed space, the humidity sensor records the relative humidity value every 10 minutes. If the readings exceed 85% for three consecutive times, the system may determine that condensation has occurred. At the same time, the VOC sensor detects that the formaldehyde concentration suddenly rises from 0.05mg / m 3 to 0.15mg / m 3 , exceeding the safety threshold of 0.1mg / m 3 , then it may be determined as pollutant penetration.

[0037] It should be noted that the judgment of condensation and pollution phenomena depends not only on the threshold but also on the duration.

[0038] In a possible implementation, the system may require the humidity to exceed the standard for 30 minutes to be recorded as a condensation event, and the pollutant concentration to exceed the standard for 15 minutes to be recorded as a pollution event. This can avoid misjudgment caused by instantaneous fluctuations. The frequency analysis algorithm can reveal the periodicity of environmental problems.

[0039] For example, if the system finds that the humidity significantly increases between 2 am and 4 am every day during 30 consecutive days of monitoring, this may imply a structural problem in the building during the night cooling process.

[0040] Preferably, the intensity distribution algorithm not only focuses on the frequency of problem occurrence but also considers its severity.

[0041] In one embodiment, the system may define humidity of 85%-90% as mild condensation, 90%-95% as moderate condensation, and above 95% as severe condensation. By analyzing the distribution of different intensity levels, the environmental conditions can be evaluated more comprehensively.

[0042] It can be understood that the fusion analysis of frequency distribution and intensity distribution can provide deeper insights.

[0043] For example, if it is found that mild condensation occurs frequently but rarely evolves into severe condensation, this may indicate that the existing dehumidification measures are basically effective and only minor adjustments are needed. On the contrary, if severe condensation, although with a low frequency, lasts for a long time once it occurs, more radical protective measures may be required. This comprehensive analysis method can not only accurately describe the current environmental load situation but also provide strong support for predicting future trends and formulating improvement strategies. Through continuous monitoring and data accumulation, the system can establish a long-term model of environmental changes, providing a scientific basis for building management and environmental optimization.

[0044] S102. According to the distribution characteristics of the environmental load, extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle layer filtration from the historical operation data, judge the correlation between the failures of the two, and obtain a failure time prediction model.

[0045] Obtain historical data, extract the time point of the aging failure of the hydrophobic coating from the historical data to obtain the first time point data; extract the time point of the adsorption saturation of the middle layer filtration from the historical data to obtain the second time point data; use correlation analysis to judge the correlation between the first time point data and the second time point data to obtain a correlation coefficient; if the correlation coefficient exceeds a preset threshold, construct a prediction model of the first time point data and the second time point data through regression analysis to obtain preliminary model parameters; obtain operation data, optimize the preliminary model parameters according to the operation data to obtain a final prediction model; obtain the change trend of the failure time through the final prediction model, and judge the influence of the environmental load on the failure time; use the final prediction model to process the newly collected operation data to obtain a real-time failure time prediction result.

[0046] Exemplarily, obtaining the distribution characteristics of the environmental load through historical data and determining the time point of the aging failure of the hydrophobic coating are key links in environmental monitoring.

[0047] Exemplarily, data can be extracted from sensor records of the past year. Assuming that for a hydrophobic coating in a certain factory, when the humidity exceeds 85% and lasts for 48 hours, tiny cracks begin to appear on the surface, which marks the starting point of aging failure. In this case, historical data may show that whenever the environmental load reaches a certain peak, such as when both humidity and pollutant concentration increase simultaneously, the failure time point will be advanced. Extracting the time point of saturation of the middle layer filtration adsorption from historical data focuses on the performance decay of the filtration system. For example.

[0048] In a possible implementation, the monitoring data shows that after the middle layer filtration material has been continuously operating for 300 hours, its adsorption capacity drops to 50% of the initial value, and this can be regarded as the saturation point at this time.

[0049] Specifically, a certain record shows that when the pollutant concentration reaches 0.5 mg / m 3 and lasts for one week, the saturation phenomenon occurs in advance, which indicates that the intensity of the environmental load directly affects the saturation time. Using correlation analysis to judge the correlation between the aging failure of the hydrophobic coating and the saturation of the middle layer filtration adsorption is the basis for understanding the interaction between the two.

[0050] It should be noted that if the correlation coefficient is 0.8, it indicates a high correlation between the two. For example, historical data may reveal that whenever the hydrophobic coating fails, the saturation time of the middle layer filtration is on average advanced by 20%, which shows that the coating failure may increase the filtration burden and thus accelerate saturation. If the correlation coefficient exceeds a preset threshold, such as 0.7, a prediction model is constructed through regression analysis.

[0051] In one embodiment, the preliminary model may assume a linear relationship between the failure time and humidity and pollutant concentration, and the parameters show that for every 10% increase in humidity, the failure time is shortened by 5 days.

[0052] Preferably, after being optimized according to the operation data, the final model may be adjusted to a non - linear relationship, which can more accurately reflect the actual trend. The advantage of such a model is that it can give early warnings of failure risks and optimize the maintenance plan. By obtaining the change trend of the failure time through the final prediction model, the impact of the environmental load can be intuitively judged.

[0053] For example, the data shows that when the environmental load changes from low to high, the failure time of the hydrophobic coating is shortened from 6 months to 4 months, while the saturation time of the middle layer filtration is reduced from 400 hours to 250 hours. Such trend analysis helps to formulate coping strategies. Processing the newly collected operation data using the final prediction model to obtain the real - time failure time prediction result is the practical application of the technology.

[0054] In one embodiment, after the new data is input into the model for prediction, with the current humidity of 90% and pollutant concentration of 0.6 mg / m 3Under the given conditions, the hydrophobic coating will fail after 3 days, and the middle layer filtration will become saturated after 200 hours.

[0055] It is understandable that this real-time prediction can guide the timely replacement of materials and avoid system failures.

[0056] Specifically, the judgment of the aging failure of the hydrophobic coating can be confirmed by the surface hydrophobic angle dropping below 90 degrees, while the saturation of the middle layer filtration is marked by an adsorption rate lower than 30%. The clarification of these indicators helps to improve the accuracy of the prediction.

[0057] For example, in a high-humidity environment, after the coating fails, pollutants are more likely to penetrate into the middle layer filtration and accelerate its saturation. This causal relationship is reflected in multiple sets of data, mutually supporting the reliability of the prediction model. Ultimately, this method can effectively extend the equipment life and reduce the maintenance cost.

[0058] S103. According to the failure time prediction model, adopt the dynamic simulation algorithm of gradient air permeability encapsulation to analyze the triggering conditions of poor airtightness and overall imbalance, determine the optimization parameter range of the protection efficiency, and obtain the encapsulation adjustment plan.

[0059] Obtain the gradient air permeability characteristic data, where the gradient air permeability characteristic data includes the change trend of poor airtightness; use the dynamic simulation algorithm to analyze the gradient air permeability characteristic data to obtain a preliminary set of triggering conditions; input the preliminary set of triggering conditions into the prediction model to obtain the time series of overall imbalance; determine the failure time distribution from the time series of overall imbalance, and judge whether the failure time exceeds the preset threshold; if the failure time exceeds the preset threshold, then use the dynamic simulation algorithm to adjust the gradient air permeability parameters to obtain the optimized distribution of poor airtightness; calculate the change trend of the protection efficiency according to the optimized distribution of poor airtightness to obtain the alleviation degree of overall imbalance; judge the improvement amplitude of the protection efficiency according to the alleviation degree of overall imbalance, and extract the optimized parameter set; input the optimized parameter set into the prediction model for verification to obtain the stable interval of the parameter range; use the stable interval to adjust the encapsulation plan to obtain the adjusted simulation result; determine the final distribution of the protection efficiency from the adjusted simulation result to obtain the implementation set of encapsulation adjustment; update the gradient air permeability design according to the implementation set to obtain the updated distribution of poor airtightness; judge the control effect of overall imbalance according to the updated distribution of poor airtightness to determine the final plan of encapsulation adjustment.

[0060] Exemplarily, when analyzing the gradient air permeability characteristics using the dynamic simulation algorithm, the change of poor airtightness can be captured by simulating the distribution characteristics of air flow under different environmental loads. For example.

[0061] In a possible implementation, assuming that the ambient temperature rises from 20 degrees to 50 degrees and the air flow velocity increases from 2 m / s to 5 m / s, the simulation results may show that the air permeability decreases by 15%, thus revealing a preliminary trend of poor airtightness. This method helps to infer the triggering conditions from multiple dimensions, such as temperature, humidity or pressure changes, and then form a preliminary set of triggering conditions.

[0062] Specifically, when the prediction model processes the set of triggering conditions, it can analyze the overall imbalance based on historical time series data.

[0063] For example, by collecting the operation data for 30 consecutive days, it is found that the peak of poor airtightness appears on the 10th day and the 25th day, and the failure time distribution is concentrated in two intervals of 8 - 12 days and 23 - 27 days. In this way, the determination of the key failure intervals becomes clear, providing a basis for subsequent adjustments.

[0064] It should be noted that if the failure time exceeds the preset threshold, such as more than 15 days, the dynamic simulation algorithm can optimize the results by adjusting the gradient air permeability parameters.

[0065] In one embodiment, when the air permeability aperture is adjusted from 0.5 mm to 0.8 mm, the simulation shows that the distribution of poor airtightness decreases from the original 20% non-uniformity rate to 10%, significantly alleviating the overall imbalance. This optimized distribution can further be used to calculate the change trend of the protection efficiency, intuitively reflecting the improvement amplitude.

[0066] Preferably, when extracting the set of optimized parameters for the improvement amplitude, it can be analyzed from three aspects: aperture, air permeability and material thickness.

[0067] For example, when the aperture is adjusted to 0.8 mm, the protection efficiency increases by 25%; when the air permeability increases by 10%, it increases by 20%; when the thickness increases from 2 mm to 3 mm, it increases by 15%. After these parameters are verified by the prediction model, the stable interval may fall within the aperture of 0.7 - 0.9 mm and the air permeability of 8 - 12%, ensuring the feasibility of the adjustment.

[0068] In a possible implementation, after adopting the stable interval to adjust the encapsulation scheme, the simulation results show that the final distribution of the protection efficiency tends to be stable.

[0069] For example, the poor airtightness decreases from the initial 18% to 5%, and the degree of alleviating the overall imbalance reaches 70%. This implementation set provides a specific direction for the update of the gradient air permeability design, ensuring that the design is more adaptable to the actual operating environment.

[0070] It can be understood that after updating the design through the implementation set, the change in the distribution of poor airtightness can directly reflect the control effect.

[0071] For example, the failure time of the new design in a high-load environment has been extended from 20 days to 30 days, and the overall imbalance has been effectively suppressed. This adjustment scheme not only improves the protection ability but also provides reliable guarantee for long-term operation.

[0072] Exemplarily, the formation of the final scheme depends on the mutual support of multi-faceted data. The effects of optimized parameters in the scenario of temperature increase, the adjustment of failure distribution when humidity changes, and the improvement of protection efficiency when air flow speed increases jointly prove the comprehensiveness of the scheme. This method can significantly extend the system life and improve stability.

[0073] S104. Through the encapsulation adjustment scheme, obtain the quantitative indicators of the adsorption saturation state and disassembly and assembly difficulty degree of the middle-layer filtering unit, judge the improvement requirements for replaceability, and obtain the structure optimization design data of the filtering unit.

[0074] Obtain the encapsulation adjustment scheme, calculate the parameters of the encapsulation adjustment through the adjustment scheme, and obtain the preliminary quantitative indicator of the disassembly and assembly difficulty degree. Extract features according to the disassembly and assembly difficulty degree, judge the limiting conditions of replaceability, and obtain the classification result of the improvement requirements. If the improvement requirement is the middle-layer filtering unit, obtain the operation data of the middle-layer filtering unit, and analyze the dynamic distribution of the adsorption saturation state for the operation data. Fit the change trend of the saturation state through the adsorption saturation state to obtain the updated value of the quantitative indicator. If the quantitative indicator exceeds the preset threshold, use the structure optimization algorithm to adjust the filtering unit to obtain the initial draft of the design data. Iteratively optimize the encapsulation adjustment scheme according to the initial draft of the design data to obtain the optimal solution of the disassembly and assembly difficulty degree. Update the structure parameters of the filtering unit according to the optimal solution to obtain the final design data.

[0075] Exemplarily, calculate the parameters of the encapsulation adjustment through the adjustment scheme to obtain the preliminary quantitative indicator of the disassembly and assembly difficulty degree. For example.

[0076] In a possible implementation, the disassembly and assembly difficulty degree can be initially quantified as a numerical interval, such as 5 - 10, with the unit being the average operator time-consuming minutes, by analyzing the number of connection points of the encapsulation component and the time required for disassembly. This quantification method is convenient for subsequent analysis.

[0077] It can be understood that the more connection points or the more complex the disassembly steps, the higher the disassembly and assembly difficulty degree, which helps to identify potential problems. Extract features from the disassembly and assembly difficulty degree, judge the limiting conditions of replaceability, and obtain the classification result of the improvement requirements.

[0078] Specifically, features can be extracted from the quantitative indicators, such as the magnitude of the fastening force of the connecting piece or the degree of tool dependence.

[0079] In one embodiment, if the fastening force exceeds 20 Newtons or a special tool is required for disassembly, it can be determined that the replaceability is limited and classified as a "high-difficulty replacement" requirement. This classification provides a clear direction for subsequent improvements. Analyze the operating data of the middle filtration unit in the improvement requirements analysis to obtain the dynamic distribution of the adsorption saturation state.

[0080] Exemplarily, the operating data may show that after the filtration unit has been operating for 100 hours, the adsorption efficiency drops from 95% to 70%. By recording these time points and efficiency changes, a dynamic distribution curve is formed. This distribution reflects the evolution process of the saturation state and provides data support for optimizing the design. Fit the change trend of the saturation state through the adsorption saturation state to obtain an updated value of the quantification index.

[0081] For example, the data can be fitted with a trend line to obtain that the saturation state reaches a critical point at 120 hours, and the updated quantification index for disassembly and assembly difficulty may be adjusted from 8 to 10. This updated value more accurately reflects the actual difficulty level during operation. If the quantification index exceeds the preset threshold, a structural optimization algorithm is used to adjust the filtration unit to obtain a preliminary draft of the design data.

[0082] Preferably, if the threshold is set to 9 and the updated value is 10, optimization is required.

[0083] For example, reduce the number of connectors from 6 to 4, or change the bolt connection to a snap-fit design to generate preliminary draft data. This adjustment reduces the disassembly and assembly complexity. Iteratively optimize the encapsulation adjustment plan according to the preliminary draft of the design data to obtain the optimal solution for the disassembly and assembly difficulty.

[0084] In one embodiment, through simulation testing of the new design, the disassembly and assembly time is shortened from 10 minutes to 6 minutes, and the quantification index drops to 6. This optimal solution improves the operation efficiency while maintaining the encapsulation stability. Update the structural parameters of the filtration unit with the optimal solution to obtain the final design data.

[0085] For example, adjust the thickness of the filtration unit from 5 mm to 4 mm, and at the same time optimize the layout of the adsorption material. This update not only reduces the disassembly and assembly difficulty but may also extend the service life.

[0086] It should be noted that the determination of the final data requires actual verification to ensure the design feasibility.

[0087] Specifically, the above method combines quantification and optimization to form a closed-loop logic from disassembly and assembly difficulty to structural adjustment. This method improves the maintainability of the encapsulation, reduces the replacement time, and at the same time ensures the stability of the filtration efficiency.

[0088] For example, the optimized design may reduce the replacement frequency from once a month to once every two months, significantly improving the practicality.

[0089] In a possible implementation, this improvement can also reduce maintenance costs and enhance the reliability of the overall system.

[0090] S105. For the data of the structural optimization design, extract the combination of the hydrophobic coating and the hydrophilic film applicable to the high-humidity environment from the preset material database, analyze its compatibility with the middle-layer filtering unit, and determine the configuration scheme of the new packaging material.

[0091] Obtain the preset conditions, obtain the combination of the hydrophobic coating and the hydrophilic film applicable to the high-humidity environment from the material database to get the initial material set; for the initial material set, use the environmental adaptability analysis method for screening to judge the material combinations that meet the high-humidity environment; obtain the screened material combinations, conduct a compatibility analysis on the material combinations and the middle-layer filtering unit to determine the compatibility index data; if the compatibility index data reaches the preset threshold, determine the candidate set of the new packaging material through the logical judgment method; obtain the material attributes in the candidate set, use the decision tree algorithm to optimize the configuration scheme to get the optimized configuration scheme; compare the optimized configuration scheme with the judgment basis to determine the configuration scheme of the final packaging material; extract the key parameters from the configuration scheme of the final packaging material to obtain the complete packaging design data applicable to the high-humidity environment.

[0092] Exemplarily, when obtaining the combination of the hydrophobic coating and the hydrophilic film applicable to the high-humidity environment from the material database, the initial material set can be screened out through the preset conditions.

[0093] For example, set the environmental parameters with a humidity tolerance range of 80%-95% and a temperature range of 20-40°C, and extract the qualified materials from the database, such as the polytetrafluoroethylene-based hydrophobic coating and the polyethersulfone hydrophilic film, to form the initial set. This screening is based on the basic properties of the materials, such as the hydrophobicity with a contact angle greater than 120° and the hydrophilicity with a contact angle less than 30°, to ensure the basic requirements for adapting to the high-humidity environment.

[0094] In a possible implementation, the environmental adaptability analysis method can screen by simulating the material performance decay under high-humidity conditions.

[0095] For example, place the materials in the initial set in a test environment with a humidity of 90% and a temperature of 35°C, and observe whether the coating peels off or the air permeability of the film decreases after 72 hours. Assume that the polytetrafluoroethylene coating remains stable, while the air permeability of a certain hydrophilic film decreases by 15%, then eliminate the unqualified ones and retain the combinations with stable performance. This method judges the applicability of the materials in the target environment through dynamic data. Conduct a compatibility analysis on the screened material combinations and the middle-layer filtering unit.

[0096] Specifically, the index data can be determined through surface energy matching and mechanical adhesion testing.

[0097] For example, the difference in surface energy between the hydrophobic coating and the substrate of the filtration unit should be less than 10 mN / m, and the peel strength in the adhesion test should reach 5 N / cm. If a certain combination has a surface energy difference of 8 mN / m and an adhesion of 6 N / cm, exceeding the preset threshold of 4 N / cm, it is considered to have good compatibility. This analysis ensures seamless physical connection between the material and the filtration unit.

[0098] Preferably, when the logical judgment method is used to determine the candidate set of new encapsulation materials, secondary screening can be performed based on compatibility indicators and cost constraints.

[0099] For example, on the premise of meeting the indicators, materials with a unit price lower than 50 yuan / m 2 are preferentially selected, such as the combination of polytetrafluoroethylene and a low-cost hydrophilic membrane, to form a candidate set. This approach finds a balance between technical feasibility and economy. After obtaining the material properties in the candidate set, the optimization of the decision tree algorithm can be carried out from multiple dimensions.

[0100] For example, taking durability, air permeability, and cost as decision nodes, the durability weight is set at 40%, air permeability at 35%, and cost at 25%.

[0101] In one embodiment, assume that a certain combination has a durability score of 90, an air permeability score of 85, and a cost score of 70, with a total score of 83, higher than 75 of other combinations, then it is selected as the optimized configuration plan. This method improves the rationality of the plan through quantitative comparison.

[0102] It should be noted that when comparing the optimized configuration plan with the judgment basis, it can be verified through actual operation data.

[0103] For example, apply the plan to the filtration unit, operate it for 48 hours in an environment with 85% humidity, and detect whether the adsorption efficiency is increased to more than 90%. If it meets the expectation, it is confirmed as the final configuration plan. This verification ensures the practicality of the design.

[0104] In one possible implementation, key parameters are extracted from the final configuration plan, such as a coating thickness of 50 μm and a membrane pore size of 0.2 μm, to obtain complete encapsulation design data.

[0105] For example, a thickness controlled at 50 μm can balance protection and air permeability, and a pore size of 0.2 μm optimizes the filtration accuracy. This parameter extraction provides clear guidance for subsequent production and helps improve the long-term stability of the filtration unit in high-humidity environments.

[0106] S106. According to the configuration plan of the new encapsulation material, use the finite element analysis algorithm to simulate the performance of the gradient air-permeable encapsulation in scenarios of pollutant penetration and humidity imbalance, judge the improvement amplitude of the detection accuracy, and obtain the performance verification result.

[0107] Obtain the configuration scheme of the encapsulation material, where the configuration scheme includes material components and structural parameters; for the configuration scheme, use the finite element analysis algorithm to simulate the performance of the encapsulation material, and obtain the first performance data corresponding to gradient air permeability; obtain the pollutant penetration scenario and the humidity imbalance scenario, and use the finite element analysis algorithm to perform simulation, and obtain the second performance data of the encapsulation material under the pollutant penetration scenario and the humidity imbalance scenario; according to the first performance data and the second performance data, determine the change trend of the performance of the encapsulation material; for the change trend, use the support vector machine algorithm to judge the fluctuation range of the detection accuracy of the encapsulation material, and obtain the accuracy fluctuation data; according to the accuracy fluctuation data, obtain the distribution characteristics of the performance improvement amplitude of the encapsulation material; according to the distribution characteristics, use the clustering analysis algorithm to divide the interval of the performance verification of the encapsulation material, and obtain the classification basis of the verification result; if the classification basis exceeds the preset threshold, adjust the parameters of the configuration scheme, and re-execute the finite element analysis algorithm to obtain the optimized performance data; according to the optimized performance data, judge the stability of the gradient air permeability in multiple scenarios, and obtain the final performance verification result of the encapsulation material.

[0108] Exemplarily, when using the finite element analysis algorithm to simulate the performance of the encapsulation material under the configuration scheme, the behavior of the material in a high humidity environment can be characterized by constructing a virtual model. For example.

[0109] In one possible implementation, assume that the encapsulation material is a multi-layer composite structure, and simulate its stress distribution and deformation under 80% humidity.

[0110] Exemplarily, set the gradient air permeability to 0.5 cm 3 / s, and the obtained performance data may show that the air permeability decreases by 10% from the initial value over time, which provides basic data for subsequent analysis. The advantage of this method is that it can intuitively reflect the dynamic response of the material under specific conditions. In the simulation of the pollutant penetration and humidity imbalance scenarios.

[0111] It can be understood that two environments need to be set separately: one is the input of humid air containing trace particulate pollutants, and the other is the case of rapid humidity fluctuation.

[0112] Specifically, the simulation results may show that when the pollutant concentration is 50 μg / m 3 , the permeability increases by 15%, while the air permeability decreases by 8% under humidity imbalance. These change trends provide multi-dimensional basis for judging the applicability of the material and are helpful for subsequent optimization. When using the support vector machine algorithm to judge the detection accuracy fluctuation range for the change trend.

[0113] Preferably, the model can be trained based on historical data.

[0114] For example, taking the change rate of air permeability as the input feature, the output precision fluctuation range is ±0.02 cm 3 / s. The acquisition of such precision fluctuation data can effectively evaluate the reliability of the detection results and lay a foundation for performance verification. When obtaining the distribution characteristics of the improvement amplitude according to the precision fluctuation data.

[0115] In one embodiment, it can be found through statistical analysis that the improvement amplitude is concentrated in the range of 5% to 15%.

[0116] It should be noted that such distribution characteristics reflect the potential for improving material performance.

[0117] For example, the sample proportion with a 10% increase in air permeability reaches 60%, indicating the consistency of the optimization direction. When using the clustering analysis algorithm to divide the performance verification interval.

[0118] Specifically, the performance data can be clustered into three categories: high, medium, and low according to air permeability and stability.

[0119] Exemplarily, if the air permeability is greater than 0.4 cm 3 / s and the stability fluctuation is less than 5%, it is classified as the high-performance category. If this classification basis exceeds the preset threshold (such as the upper limit of stability fluctuation of 10%), the scheme parameters need to be adjusted, such as increasing the thickness of the hydrophobic coating to 0.1 mm to improve stability. When obtaining the optimized performance data after adjusting the configuration scheme parameters.

[0120] In one possible implementation, it can be observed that the air permeability increases to 0.6 cm 3 / s and the stability fluctuation drops to 3%. This indicates that the adjusted scheme is more adaptable to high-humidity environments.

[0121] Preferably, its stability is verified through multi-scenario simulations. For example, under the alternating conditions of 90% and 60% humidity, the air permeability fluctuation is only 2%, demonstrating good adaptability. When judging the stability of gradient air permeability in multiple scenarios and obtaining the final verification results.

[0122] For example, continuous 72-hour high-humidity operation can be simulated, and it is recorded that the average air permeability remains at 0.55 cm 3 / s and the fluctuation range is less than 5%. Such consistency verification results indicate that the scheme has high reliability in practical applications and can effectively cope with the challenges brought by environmental changes.

[0123] S107. Through the performance verification results, obtain the change trend of the sensor life during long-term operation, analyze the influence weights of the condensation problem and the pollution problem on the life, and determine the replacement cycle and maintenance trigger conditions of the middle-layer filtration unit.

[0124] Obtain the performance verification data of the sensor, extract the change characteristics of the sensor life over time series from the performance verification data, and obtain the life attenuation curve during the long-term operation of the sensor; according to the life attenuation curve, calculate the influence ratio of environmental factors of the condensation problem and the pollution problem, and determine the first influence weight of the condensation problem and the second influence weight of the pollution problem; if the first influence weight exceeds the preset first threshold, use time series analysis to obtain the accelerated attenuation trend of the condensation problem on the sensor life, and obtain the attenuation acceleration; if the second influence weight exceeds the preset second threshold, use data fitting to obtain the cumulative damage trend of the pollution problem on the sensor life, and obtain the damage cumulative value; according to the attenuation acceleration and the damage cumulative value, use the support vector machine algorithm to judge the predicted remaining time of the sensor life, and determine the replacement cycle of the middle filter unit; according to the predicted remaining time and the influence ratio of environmental factors, judge the maintenance trigger condition, and obtain the trigger time point; obtain the trigger time point and the replacement cycle, and generate the maintenance schedule of the middle filter unit.

[0125] Exemplarily, when extracting the change characteristics of the sensor life over time series through the performance verification data.

[0126] It can be understood that the sensor will be affected by environmental factors during long-term operation, and its life will gradually decay.

[0127] For example, for a sensor operating in a high-temperature and high-humidity environment, the deterioration rate of its internal materials may accelerate, resulting in a non-linear downward trend of the life curve.

[0128] In a possible implementation manner, the attenuation curve changing with time can be drawn by collecting the output signal stability data of the sensor at different time nodes. Suppose the output accuracy of a certain sensor is 98% in the initial stage, drops to 90% after 6 months of operation, and drops to 80% after 12 months. This trend can be used as the basic data for life attenuation. The advantage of this method is that it can intuitively reflect the performance degradation of the sensor in actual use and provide a reliable basis for subsequent analysis. When calculating the influence ratio of environmental factors of the condensation problem and the pollution problem using the life attenuation curve.

[0129] It should be noted that the action mechanisms of condensation and pollution on the sensor are different. Condensation may cause internal short circuits or corrosion, while pollution may block the filter unit and reduce air permeability.

[0130] For example, in coastal areas, salt spray pollution may shorten the sensor life by 20%, and the condensation problem may additionally reduce the life by 15% in an environment with a humidity above 90%.

[0131] In one embodiment, the attenuation rates under the conditions of condensation and pollution can be compared through historical operation data to calculate the influence weights of the two. If the condensation weight is 0.6 and the pollution weight is 0.4, it indicates that the condensation problem is the main influencing factor. This weight analysis helps to accurately locate the key points of the environmental factors. If the proportion of the condensation problem exceeds a preset threshold, such as 0.5, the accelerated decay trend can be obtained through time series analysis.

[0132] Specifically, the performance degradation rate of the sensor after condensation occurs can be observed. Assuming that the normal attenuation decreases by 1% per month and decreases by 3% per month after condensation, the attenuation acceleration is 2%.

[0133] Exemplarily, this acceleration trend can be obtained by comparing the experimental data under different humidity conditions, which helps to predict the failure time of the sensor in extreme environments. If the proportion of the pollution problem exceeds the threshold, such as 0.5, the cumulative damage trend can be obtained through data fitting.

[0134] In one embodiment, it is assumed that for every 10 mg / m increase in the concentration of pollution particles 3 , the sensor life is reduced by 5%. After 10 months of accumulation, the damage value may reach 30%. This cumulative effect can help to judge the long-term impact of pollution on the sensor, and then optimize the protection measures. When predicting the remaining life using the support vector machine algorithm based on the attenuation acceleration and the cumulative damage value.

[0135] Preferably, the historical attenuation data can be used as the training set.

[0136] For example, when inputting 12 months of attenuation data and environmental factors, the model outputs a remaining life of 8 months. This prediction can provide a basis for the replacement cycle of the middle filtration unit, such as setting to replace it every 6 months to ensure the stable performance of the sensor. When judging the maintenance trigger condition through the predicted remaining time and the influence ratio of environmental factors.

[0137] It can be understood that the determination of the trigger time point needs to be combined with the actual operating environment.

[0138] For example, if the remaining life is less than 3 months and the condensation weight exceeds 0.6, maintenance is immediately triggered. The advantage of this strategy is that it can avoid sudden failures and improve the system reliability. When obtaining the trigger time point and the replacement cycle to generate a maintenance schedule.

[0139] In one possible implementation, the trigger time point can be set to the 9th month and the replacement cycle can be set to 6 months to form a periodic maintenance plan. This schedule can optimize the resource allocation, extend the overall service life of the sensor, and reduce the maintenance cost at the same time.

[0140] S108. Regarding the replacement cycle and maintenance trigger conditions, extract abnormal signals of poor airtightness and overall imbalance from the real-time monitoring data, and use signal processing algorithms to judge the dynamic adjustment requirements of the protection efficiency to obtain the encapsulation adaptive control parameters.

[0141] Obtain the original data stream, which is obtained by real-time monitoring; perform filtering processing on the original data stream to extract the abnormal signal characteristics of poor airtightness and overall imbalance; separate the key fluctuation components from the abnormal signal characteristics, and judge whether the fluctuation amplitude of the key fluctuation components exceeds a preset threshold to obtain the current state of the protection efficiency; if the current state of the protection efficiency decreases, analyze the duration of the abnormal signal characteristics through historical data comparison to determine the priority of dynamic adjustment; according to the priority of dynamic adjustment, use the linear regression algorithm to predict the change trend of the abnormal signal characteristics to obtain the parameter update requirements for adaptive control; adjust the control model through the parameter update requirements to generate the encapsulation adaptive control parameters matching the current abnormal signal characteristics; if the encapsulation adaptive control parameters exceed the preset range, calculate the adjustment value of the replacement cycle in combination with the trigger conditions to obtain the new cycle parameters; use the new cycle parameters to update the monitoring frequency, and verify whether the abnormal signal characteristics are suppressed through data extraction.

[0142] Exemplarily, obtaining the original data stream through real-time monitoring is the basis of the entire analysis, and usually relies on high-frequency sensors to collect parameters such as pressure and flow related to airtightness. For example.

[0143] In a possible implementation, the sensor collects 10 pressure values per second to obtain a continuous original data stream. When using a filtering algorithm to extract abnormal signal characteristics, a low-pass filter can be used to remove high-frequency noise and retain the low-frequency fluctuations of poor airtightness or overall imbalance.

[0144] It can be understood that poor airtightness may be manifested as a periodic decrease in pressure values, while overall imbalance may be a slow shift in the data mean.

[0145] Specifically, if the fluctuation amplitude extracted after filtering exceeds a preset threshold, such as ±5% of the normal pressure range, it can be determined as abnormal. When separating the key fluctuation components from the abnormal signal characteristics.

[0146] It should be noted that the signal can be decomposed into different frequency bands through wavelet transform to extract the core fluctuations related to airtightness.

[0147] For example, if the fluctuation amplitude reaches 8% and lasts for more than 5 seconds, it can be judged that the protection efficiency has decreased.

[0148] In one embodiment, the comparison of historical data shows that the duration of fluctuations under normal conditions does not exceed 2 seconds, while in the case of anomalies, it can reach up to 10 seconds, indicating the severity of the problem and the need to increase the priority. The dynamic adjustment of the priority is based on the duration of the anomaly.

[0149] For example, for every 3 - second increase in duration, the priority level is increased by one level. When using a linear regression algorithm to predict the changing trend of the anomaly signal.

[0150] Preferably, the data of the past 30 minutes can be used to predict the amplitude of fluctuations in the next 5 minutes.

[0151] For example, if the current fluctuation is 7% and showing an upward trend, the predicted value may reach 10%, indicating the need to update the adaptive control parameters. When the need to update the parameters adjusts the control model.

[0152] Specifically, the opening degree of the control valve can be adjusted from 50% to 60% to meet the suppression requirements of the anomaly signal. If the adjusted parameter exceeds the preset range, such as the opening degree exceeding 70%, then the replacement cycle adjustment value is calculated in combination with the trigger conditions.

[0153] For example, the original replacement cycle of 30 days is shortened to 25 days due to frequent anomalies.

[0154] Exemplarily, after adjusting the cycle parameter and updating the monitoring frequency, it can be increased from 10 times per second to 15 times to verify whether the anomaly signal is suppressed.

[0155] For example, the amplitude of fluctuations drops from 8% to 3%, indicating that the control is effective. The advantage of this method is that it can respond to anomalies in a timely manner and optimize the maintenance rhythm.

[0156] In one embodiment, if the poor airtightness is not alleviated, the aging of the sealing ring may be further inspected and the components may be replaced in advance.

[0157] It should be noted that the dynamic adjustment of the adaptive control parameters not only improves the protection efficiency but also extends the overall life of the equipment.

[0158] In one possible implementation, the increase in the monitoring frequency can also provide richer data support for subsequent optimization, forming a closed - loop of continuous improvement.

[0159] It can be understood that this analysis and adjustment logic, driven by real - time data, can effectively address the potential risks brought by airtightness problems.

[0160] For example, after the anomaly signal is suppressed, the operating stability of the system is improved, avoiding downtime losses caused by malfunctions.

[0161] Specifically, the new cycle parameter can also guide spare - part management and reduce inventory waste.

[0162] Preferably, in combination with the trend analysis of historical data, the threshold setting can be further refined in the future to enhance the prediction accuracy. This implementation method with multi-faceted mutual support not only ensures the integrity of the solution but also improves the practicality through flexible adjustment.

[0163] S109. Generate a quick replacement execution instruction for the middle-layer filtering unit through a preset control system database according to the encapsulation adaptive control parameters, analyze the changes in sensor life and detection accuracy after the instruction execution, and obtain the full-life cycle performance optimization data.

[0164] Obtain a preset system database, obtain control parameters from the system database, generate a replacement execution instruction for the middle-layer filtering unit according to the control parameters to obtain an instruction data set; extract execution instructions from the instruction data set, analyze the change characteristics of sensor life according to the execution instructions to obtain a life change sequence; judge the fluctuation range of detection accuracy according to the life change sequence to obtain an accuracy change sequence; process the life change sequence and the accuracy change sequence using a support vector machine algorithm to determine the change trend eigenvalue; analyze the performance optimization direction according to the change trend eigenvalue to obtain optimization adjustment parameters; update the system database with the optimization adjustment parameters to generate full-life cycle performance optimization data; extract key indicators from the full-life cycle performance optimization data to judge the degree of improvement in adaptability and obtain the final output data.

[0165] Exemplarily, obtain control parameters through a preset system database, generate a replacement execution instruction for the middle-layer filtering unit, and obtain an instruction data set.

[0166] For example, in an encapsulation system, the database stores historical records of key parameters such as temperature and pressure. The system generates specific instructions for replacing the middle-layer filtering unit according to these data, such as "execute replacement when the pressure exceeds 2.5 bar". This method relies on the preset thresholds and rules in the database and can quickly respond to abnormal states. Extract execution instructions from the instruction data set and analyze the change characteristics of sensor life to obtain a life change sequence.

[0167] Specifically, assuming that the instruction data set contains 100 replacement records, by analyzing the running duration of the sensor during each replacement, a sequence can be obtained, such as "500 hours, 480 hours, 510 hours". This sequence reflects the life change trend of the sensor in different environments and provides basic data for subsequent analysis. Judge the fluctuation range of detection accuracy according to the life change sequence to obtain an accuracy change sequence.

[0168] In a possible implementation manner, if the life sequence shows that the running duration gradually shortens, it may mean that the detection accuracy of the sensor decreases due to aging.

[0169] For example, the accuracy fluctuates from ±0.1 bar to ±0.3 bar. The quantification of this fluctuation range helps to evaluate whether the sensor performance meets the requirements. The support vector machine algorithm is used to process the sequences of life changes and accuracy changes to determine the characteristic values of the change trends.

[0170] Exemplarily, the support vector machine can, by classification or regression, identify the associated characteristic values between the shortened life and the decreased accuracy, such as "when the life decreases by 10%, the accuracy decreases by 5%". The extraction of such characteristic values provides data support for performance optimization. Analyze the performance optimization direction based on the characteristic values of the change trends to obtain the optimized adjustment parameters.

[0171] Preferably, if the characteristic values show that the decrease in accuracy is related to the increase in temperature, the optimization direction may be to increase the cooling measures, and the adjustment parameter may be "reduce the operating temperature to 25°C". Such parameter adjustment directly targets the root cause of the problem and has strong pertinence. Update the system database with the optimized adjustment parameters to generate the performance optimization data for the entire life cycle.

[0172] It can be understood that the updated database not only records the real-time parameters but also includes the optimized historical trends, such as "after the temperature is reduced, the sensor life is extended to 550 hours". The generation of such data for the entire life cycle helps the system to operate stably in the long term. Extract the key indicators from the performance optimization data for the entire life cycle, judge the degree of improvement in adaptability, and obtain the final output data.

[0173] In one embodiment, the key indicators may be "the average value of the sensor life" and "the stability of the detection accuracy". By comparing the data before and after optimization, such as the life is increased from 500 hours to 550 hours and the accuracy fluctuation is reduced from ±0.3 bar to ±0.15 bar, it is proved that the adaptability is significantly improved. Such improvement can effectively extend the service life of the device and reduce the maintenance cost.

[0174] It should be noted that the implementation methods of each of the above links closely revolve around the core requirements of the encapsulation system and are logically progressive.

[0175] For example, from extracting parameters from the database to generating instructions, then to analyzing the life and accuracy, and finally forming the optimization data, each step is based on data, ensuring the rigor and practicality of the solution. In addition, this method is supported by multi-dimensional analysis, such as the correlation between life and accuracy, and the linkage between parameter adjustment and data for the entire life cycle, jointly improving the adaptive ability and technical value of the system.

[0176] The present invention provides an environmental protection and performance optimization system for a temperature and humidity detector, mainly including:

[0177] The environmental monitoring module is used to obtain the sensor operating environment data. By analyzing the real-time monitoring values of the high-humidity environment and pollutant penetration, it determines the occurrence frequency and intensity of condensation problems and pollution problems, and obtains the environmental load distribution characteristics;

[0178] The failure analysis module is used to extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle layer filtration from the historical operation data according to the environmental load distribution characteristics, judge the relevance of the two failures, and obtain the failure time prediction model;

[0179] The simulation optimization module is used to analyze the triggering conditions of poor airtightness and overall imbalance according to the failure time prediction model, adopt the dynamic simulation algorithm of gradient air-permeable encapsulation, determine the optimization parameter range of the protection efficiency, and obtain the encapsulation adjustment plan;

[0180] The structure design module is used to obtain the quantitative indexes of the adsorption saturation state and disassembly difficulty degree of the middle layer filtration unit through the encapsulation adjustment plan, judge the improvement requirements of replaceability, and obtain the structure optimization design data of the filtration unit;

[0181] The material configuration module is used to extract the combination of hydrophobic coating and hydrophilic film suitable for the high-humidity environment from the preset material database according to the structure optimization design data, analyze its compatibility with the middle layer filtration unit, and determine the configuration plan of the new encapsulation material;

[0182] The performance verification module is used to simulate the performance of the gradient air-permeable encapsulation in the scenarios of pollutant penetration and humidity imbalance by using the finite element analysis algorithm according to the configuration plan of the new encapsulation material, judge the improvement range of the detection accuracy, and obtain the performance verification result;

[0183] The life evaluation module is used to obtain the change trend of the sensor life during long-term operation through the performance verification result, analyze the influence weight of condensation problems and pollution problems on the life, and determine the replacement cycle and maintenance trigger conditions of the middle layer filtration unit;

[0184] The dynamic control module is used to extract the abnormal signals of poor airtightness and overall imbalance from the real-time monitoring data according to the replacement cycle and maintenance trigger conditions, and use the signal processing algorithm to judge the dynamic adjustment requirements of the protection efficiency, and obtain the encapsulation adaptive control parameters;

[0185] The instruction execution module is used to generate the quick replacement execution instruction of the middle layer filtration unit through the preset control system database according to the encapsulation adaptive control parameters, analyze the changes of the sensor life and detection accuracy after the instruction execution, and obtain the full-life cycle performance optimization data.

[0186] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. An environmental protection and performance optimization method for a temperature and humidity detector, characterized in that The method includes the following steps: S101. Obtain the sensor operating environment data, and by analyzing the real-time monitoring values of the high-humidity environment and pollutant penetration, determine the occurrence frequency and intensity of the condensation problem and the pollution problem, and obtain the environmental load distribution characteristics; S102. For the environmental load distribution characteristics, extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle layer filtration from the historical operation data, judge the correlation between the failures of the two, and obtain the failure time prediction model; S103. According to the failure time prediction model, adopt the dynamic simulation algorithm of gradient airtight packaging, analyze the triggering conditions of poor airtightness and overall imbalance, determine the optimization parameter range of the protection efficiency, and obtain the packaging adjustment plan; S104. Through the packaging adjustment plan, obtain the quantification indexes of the adsorption saturation state and the disassembly and assembly difficulty degree of the middle layer filtration unit, judge the improvement requirements of the replaceability, and obtain the structural optimization design data of the filtration unit; S105. For the structural optimization design data, extract the combination of the hydrophobic coating and the hydrophilic membrane applicable to the high-humidity environment from the preset material database, analyze its compatibility with the middle layer filtration unit, and determine the configuration plan of the new packaging material; S106. According to the configuration plan of the new packaging material, adopt the finite element analysis algorithm to simulate the performance of the gradient airtight packaging in the scenarios of pollutant penetration and humidity imbalance, judge the improvement range of the detection accuracy, and obtain the performance verification result; S107. Through the performance verification result, obtain the change trend of the sensor life during long-term operation, analyze the influence weight of the condensation problem and the pollution problem on the life, and determine the replacement cycle and the maintenance trigger conditions of the middle layer filtration unit; S108. For the replacement cycle and the maintenance trigger conditions, extract the abnormal signals of poor airtightness and overall imbalance from the real-time monitoring data, and adopt the signal processing algorithm to judge the dynamic adjustment requirements of the protection efficiency, and obtain the packaging adaptive control parameters; S109. According to the packaging adaptive control parameters, generate the quick replacement execution instruction of the middle layer filtration unit through the preset control system database, analyze the changes of the sensor life and the detection accuracy after the instruction execution, and obtain the full life cycle performance optimization data.

2. The environmental protection and performance optimization method of a temperature and humidity detector according to claim 1, characterized in that, The S101 includes: Obtain the environmental data, and adopt the data preprocessing technology to denoise the environmental data to obtain a clean environmental data set; Extract the real-time monitoring values of the high-humidity value and pollutant penetration from the clean environmental data set, and determine the fluctuation range of the real-time monitoring values; For the fluctuation range, if the high-humidity value exceeds the preset first threshold, it is judged as a condensation phenomenon, record its occurrence time and intensity, and obtain the condensation characteristic set; For the fluctuation range, if the pollutant penetration exceeds the preset second threshold, it is judged as a pollution phenomenon, record its occurrence time and intensity, and obtain the pollution characteristic set; Obtain the condensation characteristic set and the pollution characteristic set, and adopt the frequency analysis algorithm to calculate the occurrence frequency to obtain the frequency distribution data; Adopt the intensity distribution algorithm to process the condensation characteristic set and the pollution characteristic set, determine the intensity distribution characteristics, and obtain the intensity distribution data; By fusing the frequency distribution data and the intensity distribution data, the distribution characteristics of the environmental load are judged to obtain the environmental load distribution result.

3. The environmental protection and performance optimization method of a temperature and humidity detector according to claim 1, characterized in that, The S102 includes: Obtain historical data, extract the time points of hydrophobic coating aging failure from the historical data to obtain the first time point data; Extract the time points of the middle layer filtration adsorption saturation from the historical data to obtain the second time point data; Use correlation analysis to judge the correlation between the first time point data and the second time point data to obtain the correlation coefficient; If the correlation coefficient exceeds the preset threshold, a prediction model of the first time point data and the second time point data is constructed through regression analysis to obtain the preliminary model parameters; Obtain operation data, and optimize the preliminary model parameters according to the operation data to obtain the final prediction model; Obtain the change trend of the failure time through the final prediction model, and judge the influence of the environmental load on the failure time; Process the newly collected operation data by using the final prediction model to obtain the real-time failure time prediction result.

4. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that, The S103 includes: Obtain gradient air permeability characteristic data, and the gradient air permeability characteristic data includes the change trend of poor air tightness; Use the dynamic simulation algorithm to analyze the gradient air permeability characteristic data to obtain a preliminary set of trigger conditions; Input the preliminary set of trigger conditions into the prediction model to obtain the time series of overall maladjustment; Determine the failure time distribution from the time series of overall maladjustment, and judge whether the failure time exceeds the preset threshold; If the failure time exceeds the preset threshold, use the dynamic simulation algorithm to adjust the gradient air permeability parameters to obtain the optimized distribution of poor air tightness; Calculate the change trend of the protection efficiency according to the optimized distribution of poor air tightness to obtain the mitigation degree of overall maladjustment; Judge the improvement amplitude of the protection efficiency according to the mitigation degree of overall maladjustment, and extract the optimized parameter set; Input the optimized parameter set into the prediction model for verification to obtain the stable interval of the parameter range; Use the stable interval to adjust the encapsulation scheme to obtain the adjusted simulation result; Determine the final distribution of the protection efficiency from the adjusted simulation result to obtain the implementation set of encapsulation adjustment; Update the gradient air permeability design according to the implementation set to obtain the updated distribution of poor air tightness; Judge the control effect of overall maladjustment according to the updated distribution of poor air tightness to determine the final scheme of encapsulation adjustment.

5. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that The S104 includes: Obtain the encapsulation adjustment scheme, calculate the parameters of the encapsulation adjustment through the adjustment scheme to obtain the preliminary quantitative index of the difficulty of disassembly and assembly; Extract features according to the difficulty of disassembly and assembly, judge the limiting conditions of replaceability, and obtain the classification result of improvement requirements; If the improvement requirement is the middle layer filtration unit, obtain the operation data of the middle layer filtration unit, and analyze the dynamic distribution of the adsorption saturation state for the operation data; Fit the change trend of the saturation state through the adsorption saturation state to obtain the updated value of the quantitative index; If the quantitative index exceeds the preset threshold, use the structure optimization algorithm to adjust the filtration unit to obtain the initial draft of the design data; Iteratively optimize the encapsulation adjustment plan according to the initial draft of the design data to obtain the optimal solution for the difficulty of disassembly and assembly; Update the structural parameters of the filter unit according to the optimal solution to obtain the final design data.

6. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that The S105 includes: Obtain preset conditions, and obtain a combination of a hydrophobic coating and a hydrophilic film applicable to a high-humidity environment from the material database to obtain an initial material set; For the initial material set, use an environmental adaptability analysis method to screen and judge the material combinations that meet the high-humidity environment; Obtain the selected material combinations, and perform a compatibility analysis on the material combinations and the middle-layer filter unit to determine the compatibility index data; If the compatibility index data reaches the preset threshold, determine the candidate set of new encapsulation materials through a logical judgment method; Obtain the material properties in the candidate set, and use a decision tree algorithm to optimize the configuration plan to obtain an optimized configuration plan; Compare the optimized configuration plan with the judgment basis to determine the configuration plan of the final encapsulation material; Extract the key parameters from the configuration plan of the final encapsulation material to obtain the complete encapsulation design data applicable to the high-humidity environment.

7. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that The S106 includes: Obtain the configuration plan of the encapsulation material, and the configuration plan includes material components and structural parameters; For the configuration plan, use a finite element analysis algorithm to simulate the performance of the encapsulation material to obtain the first performance data corresponding to gradient air permeability; Obtain the pollutant penetration scenario and the humidity imbalance scenario, and use the finite element analysis algorithm to perform simulation to obtain the second performance data of the encapsulation material under the pollutant penetration scenario and the humidity imbalance scenario; According to the first performance data and the second performance data, determine the change trend of the performance of the encapsulation material; For the change trend, use a support vector machine algorithm to judge the fluctuation range of the detection accuracy of the encapsulation material to obtain accuracy fluctuation data; According to the accuracy fluctuation data, obtain the distribution characteristics of the performance improvement amplitude of the encapsulation material; According to the distribution characteristics, use a clustering analysis algorithm to divide the interval for performance verification of the encapsulation material to obtain the classification basis for the verification result; If the classification basis exceeds the preset threshold, adjust the parameters of the configuration plan and re-execute the finite element analysis algorithm to obtain optimized performance data; According to the optimized performance data, judge the stability of the gradient air permeability in multiple scenarios to obtain the final performance verification result of the encapsulation material.

8. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that, The S107 includes: Obtain the performance verification data of the sensor, extract the change characteristics of the sensor life over time series in the performance verification data to obtain the life decay curve during the long-term operation of the sensor; According to the life decay curve, calculate the influence ratio of the environmental factors of the condensation problem and the pollution problem, and determine the first influence weight of the condensation problem and the second influence weight of the pollution problem; If the first influence weight exceeds the preset first threshold, use time series analysis to obtain the accelerated decay trend of the condensation problem on the sensor life to obtain the decay acceleration; If the second influence weight exceeds the preset second threshold, use data fitting to obtain the cumulative damage trend of the pollution problem on the sensor life to obtain the damage accumulation value; Based on the attenuation acceleration and the damage accumulation value, use the support vector machine algorithm to judge the predicted remaining time of the sensor life and determine the replacement cycle of the middle - layer filtering unit; Based on the predicted remaining time and the influence ratio of environmental factors, judge the maintenance trigger condition to obtain the trigger time point; Obtain the trigger time point and the replacement cycle, and generate a maintenance schedule for the middle - layer filtering unit.

9. A method for environmental protection and performance optimization of a temperature and humidity detector according to any one of claims 1-3, characterized in that The S108 includes: Obtain the original data stream, which is obtained by real - time monitoring; Perform filtering processing on the original data stream to extract abnormal signal features of poor airtightness and overall maladjustment; Separate the key fluctuation components from the abnormal signal features, and judge whether the fluctuation amplitude of the key fluctuation components exceeds a preset threshold to obtain the current state of the protection efficiency; If the current state of the protection efficiency decreases, analyze the duration of the abnormal signal features through historical data comparison to determine the priority of dynamic adjustment; According to the priority of dynamic adjustment, use the linear regression algorithm to predict the change trend of the abnormal signal features and obtain the parameter update requirements for adaptive control; Adjust the control model through the parameter update requirements to generate encapsulated adaptive control parameters that match the current abnormal signal features; If the encapsulated adaptive control parameters exceed the preset range, calculate the adjustment value of the replacement cycle in combination with the trigger condition to obtain a new cycle parameter; Use the new cycle parameter to update the monitoring frequency, and verify whether the abnormal signal features are suppressed through data extraction.

10. An environmental protection and performance optimization system for a temperature and humidity detector, characterized in that, This system is used to implement the environmental protection and performance optimization method of a temperature - humidity detector according to any one of claims 1 - 9. The system includes: An environmental monitoring module, which is used to obtain sensor operating environment data, and determine the occurrence frequency and intensity of condensation problems and pollution problems by analyzing real - time monitoring values of high - humidity environments and pollutant penetration, so as to obtain the environmental load distribution characteristics; A failure analysis module, which is used to extract the aging failure time point of the hydrophobic coating and the adsorption saturation time point of the middle - layer filtration from historical operation data according to the environmental load distribution characteristics, judge the relevance of the two failures, and obtain a failure time prediction model; A simulation optimization module, which is used to analyze the trigger conditions of poor airtightness and overall maladjustment according to the failure time prediction model by using the dynamic simulation algorithm of gradient - permeable encapsulation, determine the optimization parameter range of the protection efficiency, and obtain an encapsulation adjustment plan; A structure design module, which is used to obtain quantitative indicators of the adsorption saturation state and disassembly difficulty of the middle - layer filtering unit through the encapsulation adjustment plan, judge the improvement requirements of replaceability, and obtain the structural optimization design data of the filtering unit; A material configuration module, which is used to extract a combination of hydrophobic coating and hydrophilic film suitable for high - humidity environments from a preset material database according to the structural optimization design data, analyze its compatibility with the middle - layer filtering unit, and determine the configuration plan of the new encapsulation material; A performance verification module, which is used to simulate the performance of gradient - permeable encapsulation in scenarios of pollutant penetration and humidity imbalance according to the configuration plan of the new encapsulation material by using the finite - element analysis algorithm, judge the improvement amplitude of the detection accuracy, and obtain the performance verification result; The lifespan evaluation module is used to obtain the change trend of the sensor lifespan during long-term operation through the performance verification results, analyze the influence weights of condensation problems and pollution problems on the lifespan, and determine the replacement cycle and maintenance trigger conditions of the middle-layer filtration unit; The dynamic control module is used to extract abnormal signals of poor airtightness and overall maladjustment from the real-time monitoring data for the replacement cycle and maintenance trigger conditions, and use signal processing algorithms to judge the dynamic adjustment requirements of the protection efficiency to obtain the encapsulation adaptive control parameters; The instruction execution module is used to generate a quick replacement execution instruction for the middle-layer filtration unit through the preset control system database according to the encapsulation adaptive control parameters, analyze the changes in the sensor lifespan and detection accuracy after the instruction execution, and obtain the full-life cycle performance optimization data.

Images