One-stop offline detection method for electric air door

Abstract

The invention discloses a one-stop offline detection method for an electric air door, and relates to the technical field of electric air door detection, and the method comprises the following steps: at the beginning of detection, an ultrasonic sensor carries out the comprehensive detection of the sealing performance of the electric air door at the initial sensitivity, and collects the leakage signal data of the air door in real time; and preprocessing the obtained leakage signal data, and aggregating the preprocessed data to establish a data set. By implementing initial sensitivity detection, data preprocessing and feature extraction, intelligent evaluation and sensitivity dynamic adjustment, the system can accurately identify leakage signals having actual influences on the performance of the air door, and misjudgment of tiny leakage caused by environmental fluctuation is avoided. According to the method, false alarm and unnecessary maintenance are reduced, resource waste and production downtime are reduced, and the reliability and flexibility of a detection system are improved at the same time. And by optimizing the maintenance period and improving the production efficiency, the economic benefit is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric damper detection, and particularly relates to a one-stop offline detection method for an electric damper. Background Art

[0002] The one-stop offline detection of an electric damper refers to the quality inspection stage before the electric damper leaves the factory after being manufactured. Through an integrated detection platform, an integrated detection operation of the whole process and all functions of the damper system is carried out. This method usually integrates multiple detection links such as electrical control, sensor response, communication protocol, linkage mechanism, and action execution. Through a unified test interface and an intelligent control system, the automatic detection and recording of key performance parameters such as damper opening and closing control, electric actuator response, sensor status feedback, fault alarm function, and remote communication ability are completed at one detection station, ensuring that the damper system meets the factory operation standard, reducing the labor input and the risk of missed detection and false detection caused by decentralized detection, and improving the product offline efficiency and consistency.

[0003] In the one-stop offline detection process of an electric damper, the ultrasonic leak detection method is one of the important means to detect the sealing performance of the electric damper. This method uses an ultrasonic sensor to perform highly sensitive detection on the damper sealing surface, and can capture ultrasonic signals caused by gas leakage in real time. Its function is to accurately measure the integrity of the damper sealing performance, timely identify possible leakage points, and evaluate the severity of the leakage. The ultrasonic detection method can efficiently detect minute leaks in the damper sealing part without contact, and is particularly sensitive to the detection of minute leaks. Therefore, it can ensure that the sealing performance of the damper meets the standard requirements before leaving the factory, thus preventing energy waste, uneven air flow or safety hazards caused by leakage.

[0004] The prior art has the following deficiencies: When using the ultrasonic leak detection method to detect the sealing performance of an electric damper, there may be a problem of over-sensitivity, that is, the ultrasonic sensor responds to minute and almost negligible leakage signals. These minute leakage signals often originate from natural fluctuations caused by environmental factors (such as temperature changes, humidity fluctuations, etc.), and these leaks do not have a significant impact on the performance of the damper in actual applications, especially there is no substantial harm to the airtightness, ventilation effect or safety of the working environment of the damper.

[0005] Due to the high sensitivity of the ultrasonic sensor, it can detect these minute leakage signals and then mark them as potential leakage problems in the detection report. However, the air flow generated by these minute leaks is extremely limited and is not sufficient to affect the actual use performance of the damper. Therefore, the over-sensitive detection results may lead to unnecessary repairs or adjustments to the damper, thus wasting resources, increasing maintenance costs, and prolonging the downtime of the production line.

[0006] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide a one-stop offline detection method for an electric air damper. By implementing initial sensitivity detection, data preprocessing and feature extraction, intelligent evaluation, and sensitivity dynamic adjustment, the system can accurately identify leakage signals that actually affect the performance of the air damper and avoid misjudgment of minor leaks caused by environmental fluctuations. This method reduces false alarms and unnecessary repairs, reduces resource waste and production downtime, and at the same time improves the reliability and flexibility of the detection system. By optimizing the maintenance cycle and improving production efficiency, the economic benefits are significantly improved to solve the problems in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: A one-stop offline detection method for an electric air damper, comprising the following steps: At the beginning of the detection, the ultrasonic sensor comprehensively detects the sealing performance of the electric air damper with the initial sensitivity and real-time collects the leakage signal data of the air damper; Preprocess the obtained leakage signal data and aggregate the preprocessed data to establish a data set; Extract from the data set the key indicators reflecting that the leakage is the natural fluctuation caused by environmental factors through feature engineering, comprehensively analyze the extracted key indicators, quantify the severity of the leakage, and evaluate the actual impact of the leakage on the performance of the air damper; Input the key indicators after comprehensive analysis into a pre-trained machine learning model, and through the machine learning model, conduct an intelligent evaluation of the leakage to determine whether the leakage belongs to an actual airtightness problem; When it is identified that the leakage signal is a negligible leakage, based on the evaluation result, reduce the sensitivity of the sensor to shield minor and non-essential leakage signals.

[0009] Preferably, the specific steps of preprocessing the data and establishing a data set are as follows: First, perform denoising processing on the obtained leakage signal data, and use filtering technology to remove the noise components in the signal; Next, convert the data in different time periods into a unified standard through data normalization to eliminate the influence of unit and magnitude differences on the analysis results; Then, apply a smoothing algorithm to smooth the signal to reduce the interference caused by instantaneous fluctuations, For signals with outliers, use outlier detection methods to eliminate or correct them; After completing the preprocessing steps, the leakage signal data under each time period and environmental conditions are aggregated, and the data are integrated into a data set according to the dimensions of time, damper working status, and environmental factors, ensuring the integrity and consistency of the data, and providing accurate and stable basic data for subsequent analysis and modeling.

[0010] Preferably, through feature engineering, key indicators reflecting that the leakage is caused by natural fluctuations of environmental factors are extracted from the data set. The extracted key indicators include the influence of air pressure change on the damper sealing performance and the influence of stress change of the damper sealing material under temperature change on the sealing performance. The influence of air pressure change on the damper sealing performance and the influence of stress change of the damper sealing material under temperature change on the sealing performance are comprehensively analyzed under the detection window, and the air pressure change response reference value and the temperature sensitivity stress reference value are generated respectively. The severity of the leakage is quantified through the air pressure change response reference value and the temperature sensitivity stress reference value, and the actual influence of the leakage on the damper performance is evaluated.

[0011] Preferably, the specific steps for comprehensively analyzing the influence of air pressure change on the damper sealing performance under the detection window to generate the air pressure change response reference value are as follows: First, collect the time series of air pressure change data and the leakage signal of the electric damper, establish the relationship between air pressure change and the leakage signal, and quantitatively describe the influence of air pressure change on the damper sealing performance by introducing the air pressure-leakage difference index. The calculation expression of the air pressure-leakage difference index is as follows: , where is the air pressure-leakage difference index, and are the air pressure values at time point and time point respectively, and are the leakage signal values at time point and time point respectively, is the total number of time points; After obtaining the air pressure-leakage difference index, generate the air pressure change response reference value through the air pressure-leakage difference index. The generation formula is as follows: , where is the air pressure-leakage difference index calculated at time point , is the air pressure change response reference value.

[0012] Preferably, the specific steps for comprehensively analyzing the influence of the stress change of the damper sealing material under temperature change on the sealing performance under the detection window to generate the temperature sensitivity stress reference value are as follows: First, analyze the stress change of the electric damper sealing material under temperature changes, and then calculate the stress change amount caused by temperature. Assume that the volume change of the sealing material caused by temperature change has a direct impact on the sealing performance. The calculation expression of the stress change amount is as follows: , where is the stress change amount, is the elastic modulus of the damper sealing material, is the strain change amount, and its calculation formula is: , where is the length change of the sealing material caused by temperature change, is the initial length of the sealing material; Based on the stress change amount , combined with the amplitude of temperature change, generate a temperature-sensitive stress reference value. The calculation expression is as follows: , where is the temperature-sensitive stress reference value, is the amplitude of temperature change, is the reference temperature.

[0013] Preferably, input the air pressure change response reference value and the temperature-sensitive stress reference value after comprehensive analysis into a pre-trained machine learning model. Generate a micro-leakage change coefficient through the machine learning model, and use the micro-leakage change coefficient to intelligently evaluate the leakage and determine whether the leakage belongs to an actual airtightness problem.

[0014] Preferably, compare and analyze the micro-leakage change coefficient with a pre-set micro-leakage change coefficient reference threshold to determine whether the leakage belongs to an actual airtightness problem. The judgment logic is as follows: If the micro-leakage change coefficient is greater than the pre-set micro-leakage change coefficient reference threshold, it is determined that the leakage is a natural fluctuation caused by environmental factors; if the micro-leakage change coefficient is less than or equal to the pre-set micro-leakage change coefficient reference threshold, it is determined that the leakage is not a natural fluctuation caused by environmental factors.

[0015] Preferably, when the leakage signal is identified as a negligible leakage, based on the evaluation result, reduce the sensitivity of the sensor. The specific steps to shield tiny and non-essential leakage signals are as follows: Once the leakage signal is identified as a natural fluctuation caused by environmental factors and is determined to be a negligible leakage, reduce the sensitivity of the sensor based on the evaluation result. By reducing the sensitivity of the sensor, tiny and non-essential leakage signals will be automatically shielded to avoid interfering with the detection result. The adjustment formula is as follows: , where is the adjusted sensor sensitivity, is the initial sensor sensitivity, is the sensitivity adjustment coefficient, which controls the rate of sensitivity decline. is the micro-leakage change coefficient. is the reference threshold of the micro-leakage change coefficient. is the non-linear exponential factor, which enhances the non-linear response effect of sensitivity adjustment. is the sensitivity correction factor.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are as follows: By implementing a comprehensive solution of initial sensitivity detection, data preprocessing and feature extraction, intelligent evaluation, and sensitivity dynamic adjustment, the system of the present invention can accurately identify and process leakage signals that only have a substantial impact on the performance of the air damper, thereby effectively avoiding misjudgment of small natural fluctuation signals caused by environmental factors (such as temperature fluctuations, humidity changes, etc.). This method significantly improves the detection accuracy, reduces unnecessary false alarms and maintenance operations, avoids waste of resources and unnecessary shutdown of the production line. At the same time, the sensitivity adjustment mechanism ensures that the system can adapt to different environmental conditions, improving the flexibility and adaptability of the detection system. Ultimately, this not only improves the overall reliability of the system, reduces the maintenance cost, but also realizes significant economic benefits by optimizing the maintenance cycle and improving the production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is the method flow chart of a one-stop offline detection method for an electric air damper of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more complete and comprehensive, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0020] The present invention provides a one-stop offline detection method for an electric air damper as shown in Figure 1 and includes the following steps: At the beginning of the detection, the ultrasonic sensor comprehensively detects the sealing performance of the electric air damper with the initial sensitivity and real-time collects the leakage signal data of the air damper; By setting the initial sensitivity, the sensor can capture all signals, regardless of their intensity, which provides the raw data basis for subsequent analysis. The role of this step is to ensure the comprehensiveness of data collection, provide sufficient information for subsequent data processing and analysis, and avoid missing any potential leakage signals as much as possible.

[0021] The sensor will collect leakage signal data from the damper in real time, covering all possible leakage information, including small leaks and natural fluctuations caused by environmental factors. The initial sensitivity setting ensures that the sensor responds to a wide range of leakage situations to collect complete leakage data.

[0022] Preprocessing the acquired leakage signal data, and aggregating the preprocessed data to establish a data set; Data preprocessing includes signal denoising, normalization, smoothing filtering, and outlier correction. Through data preprocessing, the noise and external interference factors in the original signal are removed to ensure the accuracy of subsequent analysis and the stability of the data.

[0023] Data preprocessing can eliminate interference signals caused by environmental noise, sensor errors or irrelevant factors to ensure data quality. Through this step, the error caused by signal fluctuations can be reduced, providing accurate and stable data for subsequent key indicator extraction and analysis. The goal of this stage is to remove irrelevant data and improve the accuracy of detection.

[0024] The data set contains leakage signal data from different times and different environmental conditions, which will serve as the basis for further analysis.

[0025] The establishment of a data set can summarize leakage information from multiple tests and take into account changes under different working conditions. By correlating leakage signals according to environmental parameters (such as temperature, humidity) and damper operating status, a complete historical data set can be established, and potential relationships between data can be identified in subsequent analysis. This provides multi-dimensional information support for the subsequent extraction of key indicators.

[0026] The specific steps to preprocess data and create a data set are as follows: First, denoise the acquired leakage signal data. Use filtering techniques to remove the noise components in the signal, such as electromagnetic interference, sensor errors, or external environmental noise. Next, through data normalization, convert the data in different time periods into a unified standard to eliminate the influence of unit and magnitude differences on the analysis results. Then, apply a smoothing algorithm (such as the moving average method or Gaussian smoothing) to smooth the signal to reduce the interference caused by instantaneous fluctuations. For signals with outliers, use outlier detection methods to remove or correct them. After completing the preprocessing steps, aggregate the leakage signal data in each time period and environmental condition, and integrate the data into a data set according to dimensions such as time, damper working state, and environmental factors to ensure the integrity and consistency of the data, providing accurate and stable basic data for subsequent analysis and modeling.

[0027] Through feature engineering, extract key indicators from the data set that reflect the natural fluctuations of the leakage caused by environmental factors (such as temperature changes, humidity fluctuations, etc.). Conduct a comprehensive analysis of the extracted key indicators to quantify the severity of the leakage and evaluate the actual impact of the leakage on the damper performance; Through feature engineering, extract key indicators from the data set that reflect the natural fluctuations of the leakage caused by environmental factors. The extracted key indicators include the impact of air pressure changes on the damper sealing performance and the stress changes of the damper sealing material under temperature changes on the sealing performance. Conduct a comprehensive analysis of the impact of air pressure changes on the damper sealing performance and the stress changes of the damper sealing material under temperature changes on the sealing performance under the detection window, and generate an air pressure change response reference value and a temperature sensitivity stress reference value respectively. Quantify the severity of the leakage through the air pressure change response reference value and the temperature sensitivity stress reference value, and evaluate the actual impact of the leakage on the damper performance.

[0028] When the air pressure change has an obvious impact on the damper sealing performance, it usually indicates that the leakage is a natural fluctuation caused by environmental factors. This is because the sealing performance of the damper is not only affected by its structural design and the quality of the sealing material, but also highly dependent on the physical parameters of the environment it is in, especially the air pressure. The air pressure change will cause the pressure difference on both sides of the damper to fluctuate, thus changing the stress state of the sealing strip or the contact surface, which may lead to short-term and minor leakage phenomena. Especially in high-altitude, underground, or places with frequent climate fluctuations, the drastic air pressure change may cause a temporary imbalance in the tension of the sealing surface, resulting in the generation of reversible leakage signals. Such leakage signals are often sudden and short-term, and will automatically recover as the air pressure stabilizes. Usually, they will not cause long-term or substantial impacts on the actual operating performance and ventilation efficiency of the damper. Therefore, if the leakage phenomenon is highly correlated with the air pressure change and the leakage signal has environmental response characteristics (such as being consistent with the air pressure curve trend, having no continuous growth trend, etc.), it can be determined as a natural fluctuation driven by the environment, different from the essential leakage caused by structural damage or component failure.

[0029] The specific steps for comprehensively analyzing the influence of air pressure changes on the air door sealing performance under the detection window to generate an air pressure change response reference value are as follows: First, collect the time series of air pressure change data and the electric air door leakage signal, establish the relationship between air pressure changes and the leakage signal, and quantitatively describe the influence of air pressure changes on the air door sealing performance by introducing an air pressure-leakage difference index. The calculation expression of the air pressure-leakage difference index is as follows: , where is the air pressure-leakage difference index, which quantifies the relationship between air pressure changes and leakage signal changes and helps to determine whether the air door leakage is affected by air pressure changes. and are the air pressure values at time point and time point respectively. and are the leakage signal values at time point and time point respectively. is the total number of time points. The function of this step is to quantify the correlation between the two by combining the changes in air pressure and leakage signal. If the air pressure changes significantly and is consistent with the change in the leakage signal, it indicates that the leakage may be natural fluctuations caused by environmental factors.

[0030] After obtaining the air pressure-leakage difference index, generate an air pressure change response reference value through the air pressure-leakage difference index. The air pressure change response reference value can accurately reflect whether the leakage is natural fluctuations caused by air pressure changes. The generation formula is as follows: , where is the air pressure-leakage difference index calculated at time point , is the air pressure change response reference value.

[0031] This formula generates by weighted summing and the change in the leakage signal, reflecting the degree of influence of air pressure changes on the leakage signal. When has a large value, it indicates that air pressure changes have a significant impact on the air door sealing performance, and most of the leakage signals are natural fluctuations caused by environmental air pressure fluctuations; if has a small value, it indicates that the leakage is more likely to come from structural problems of the air door itself.

[0032] This step can intelligently determine whether the leakage signal is natural fluctuations caused by air pressure changes by generating . If has a high value, most of the leakage is caused by natural fluctuations; on the contrary, if If it is low, the leakage signal may stem from defects in the damper structure or other non-environmental factors.

[0033] The larger the reference value of the air pressure change response generated by comprehensively analyzing the influence of air pressure change on the damper sealing performance under the detection window, the higher the correlation between the leakage signal and the air pressure change, that is, the leakage intensity changes synchronously with the air pressure fluctuation, indicating that the leakage may be a natural fluctuation caused by environmental air pressure change, rather than the failure of the damper structure or sealing material; the leakage at this time usually has reversibility and non-persistence. When the reference value is low or the change trend has no obvious corresponding relationship with the air pressure, it indicates that the leakage signal is less affected by the air pressure change, and the cause of the leakage is more likely to come from essential problems such as sealing structure defects or mechanical wear.

[0034] When the stress of the damper sealing material changes under temperature change, which in turn has a fluctuating effect on the sealing performance, it usually indicates that this type of leakage belongs to the natural fluctuation caused by environmental factors. This is because the sealing material (such as rubber, composite elastomer or metal gasket) may expand thermally when the temperature rises and may contract or harden in a low-temperature environment. This slight dimensional change or decrease in contact compressive force caused by the change in the thermal physical properties of the material will cause slight gas leakage at the sealing surface in a short time. However, this type of leakage is not caused by damper structural defects or poor assembly, but is the natural response behavior of the sealing material to external thermal environment changes. Usually, as the temperature stabilizes or the environmental fluctuation returns to normal, the material will gradually return to its original form, and the sealing performance will also recover automatically. Therefore, this type of leakage has the characteristics of reversibility, periodicity and non-essentiality. From the perspective of the leakage source and cause, this behavior directly stems from environmental thermal disturbance rather than the stability problem of the damper system itself, so it is reasonably classified as the natural fluctuation type of leakage caused by environmental factors.

[0035] The specific steps for comprehensively analyzing the influence of the stress change of the damper sealing material under temperature change on the sealing performance and generating the temperature sensitivity stress reference value under the detection window are as follows: First, analyze the stress change of the electric damper sealing material under temperature change, and then calculate the stress change amount caused by temperature. It is assumed that the volume change of the sealing material caused by temperature change has a direct impact on the sealing performance. The calculation expression of the stress change amount is as follows: , where is the stress change amount, indicating the stress change of the damper sealing material caused by temperature change, is the elastic modulus of the damper sealing material, also called Young's modulus, which is the stiffness coefficient of the material and is defined as the strain degree of the material under unit stress, is the strain change amount, indicating the deformation degree of the material caused by external force or temperature change, and its calculation formula is: , where is the change in the length of the sealing material caused by temperature change (unit: meter), is the initial length of the sealing material (unit: meter); By measuring the deformation caused by temperature change ( ), and the elastic properties of the sealing material ( ), the stress change caused by temperature can be obtained, and this stress change can be used to characterize the impact of temperature change on the airtightness of the air door. A larger stress change value indicates a greater impact of temperature change on airtightness, and vice versa, the impact is smaller.

[0036] Based on the stress change , combined with the amplitude of temperature change, a temperature-sensitive stress reference value is generated, and the calculation expression is as follows:

[0037] In the formula, is the temperature-sensitive stress reference value, is the amplitude of temperature change, which represents the degree of temperature change in the environment where the air door is located during the measurement, referring to the change amount of the environmental temperature, usually caused by factors such as temperature fluctuations outside the air door, seasonal changes, and equipment heat, is the reference temperature, which is usually selected as the standard working temperature of the sealing material of the air door.

[0038] By calculating the temperature-sensitive stress reference value , the impact of temperature change on the stress change of the sealing material of the air door is quantified, so as to evaluate the impact degree of temperature fluctuation on the sealing performance. This step can identify natural fluctuation-type leaks caused by temperature change and distinguish actual faulty leaks unrelated to environmental factors.

[0039] The larger the temperature-sensitive stress reference value generated after comprehensively analyzing the impact of the stress change of the sealing material of the air door on airtightness under the detection window, the more sensitive the sealing material is to the current temperature change, resulting in significant stress fluctuations. This kind of fluctuation further leads to the fluctuation of short-term leakage signals. Therefore, the leakage is more likely to be a natural fluctuation caused by environmental temperature change rather than a structural or functional failure of the air door. On the contrary, if this reference value is low, that is, the stress response of the sealing material to temperature change is weak, it indicates that the leakage change has a weak correlation with temperature. At this time, it is more likely to be a substantial leakage caused by non-environmental factors (such as seal aging, assembly deviation, structural wear, etc.).

[0040] Input the key indicators after comprehensive analysis into a pre-trained machine learning model, and use the machine learning model to intelligently evaluate the leakage to determine whether the leakage belongs to an actual airtightness problem; Input the reference value of air pressure change response and the reference value of temperature-sensitive stress after comprehensive analysis into a pre-trained machine learning model. Generate a micro-leakage change coefficient through the machine learning model, and use the micro-leakage change coefficient to intelligently evaluate the leakage and determine whether the leakage belongs to an actual airtightness problem.

[0041] The pre-trained machine learning model refers to a predictive classification model constructed by supervised learning or semi-supervised learning methods for the leakage detection task of electric air dampers, based on a large amount of historical detection data, environmental monitoring data, and actual leakage results. During the training stage of the model, by inputting multiple characteristic parameters such as the reference value of air pressure change response, the reference value of temperature-sensitive stress, signal fluctuation frequency, and leakage duration, it performs mapping learning with the corresponding actual leakage categories (such as "negligible leakage" or "structural airtightness problem") to form a model structure with discrimination ability. After training, the model can automatically determine whether the input signal characteristics conform to a certain leakage pattern when facing new detection data, and accordingly output a micro-leakage change coefficient reflecting the risk level, which is used to measure the severity of the current leakage signal and its relationship with the natural fluctuations of the environment.

[0042] The so-called "pre-trained" means that the model has completed the modeling process through an offline data set before system deployment, and has been iteratively updated through methods such as cross-validation, accuracy optimization, and error correction to ensure its sufficient generalization ability and prediction accuracy. In practical applications, when the detection system extracts multi-dimensional indicators such as the reference value of air pressure change response and the reference value of temperature-sensitive stress, these features are input into the model as inputs, and the model will perform intelligent inference based on its existing knowledge system and output a quantitative result - the micro-leakage change coefficient. The larger the value of this coefficient, the more highly correlated the current leakage signal is with environmental disturbances, and the more inclined it is to be judged as natural fluctuations; conversely, if the value is low, it indicates that there may be an airtightness problem with the structure of the air damper, and further inspection or warning is required. Therefore, the core role of this machine learning model is to improve the intelligence level of leakage classification, reduce misjudgment and missed judgment, and improve the adaptive decision-making ability of the detection system.

[0043] The machine learning model is not limited here, and any machine learning model that can synthesize and analyze the reference value of air pressure change response and the reference value of temperature-sensitive stress to generate a micro-leakage change coefficient can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation method: The generation formula of the micro-leakage change coefficient is as follows: and are respectively the reference value of air pressure change response and the temperature-sensitive stress reference value of a preset proportionality coefficient, and and are both greater than 0.

[0044] The preset proportionality coefficient refers to the coefficient used to adjust the influence weights of each input variable (i.e., the air pressure change response reference value and the temperature-sensitive stress reference value ) on the final result when calculating the micro-leakage change coefficient , and are respectively denoted as and . These two coefficients are artificially preset parameters in practical applications and are used to control the contribution degree of each physical quantity in the model. For example, if the temperature has a more significant influence on micro-leakage under a certain working condition, then can be set to strengthen the proportion of the temperature-sensitive stress reference value in the calculation.

[0045] These proportionality coefficients have two core functions: one is to reflect the sensitivity of different physical factors to the micro-leakage fluctuation according to experience or model training results, and the other is to provide a quantization method of linear combination for simplified processing when deep learning modeling is not carried out. Although they are fixed values, they can be optimized through experimental data to adapt to the response characteristics of different damper materials, environments and sealing structures to leakage behavior. Therefore, the "preset proportionality coefficient" is essentially a weight control mechanism with physical significance, which is used to ensure that the MLVC is more accurate and representative in actual judgment.

[0046] It can be seen from the micro-leakage change coefficient that the larger the air pressure change response reference value generated by comprehensively analyzing the influence of air pressure change on the damper sealing performance under the detection window, and the larger the temperature-sensitive stress reference value generated by comprehensively analyzing the influence of the stress change of the damper sealing material on the sealing performance under the temperature change under the detection window, the larger the micro-leakage change coefficient generated by the intelligent evaluation of leakage through the pre-trained machine learning model to judge whether the leakage belongs to the actual airtightness problem, indicating that the probability that the leakage may be caused by natural fluctuations of environmental factors is greater. On the contrary, it indicates that the probability that the leakage may be caused by natural fluctuations of environmental factors is smaller.

[0047] Compare and analyze the micro-leakage change coefficient with the preset micro-leakage change coefficient reference threshold to judge whether the leakage belongs to the actual airtightness problem. The judgment logic is as follows: If the micro-leakage change coefficient is greater than the pre-set reference threshold of the micro-leakage change coefficient, it is determined that the leakage is a natural fluctuation caused by environmental factors; if the micro-leakage change coefficient is less than or equal to the pre-set reference threshold of the micro-leakage change coefficient, it is determined that the leakage is not a natural fluctuation caused by environmental factors.

[0048] When it is recognized that the leakage signal is a negligible leakage, based on the evaluation result, the sensitivity of the sensor is reduced, thereby shielding tiny and non-essential leakage signals.

[0049] When it is recognized that the leakage signal is a negligible leakage, reducing the sensitivity of the sensor is to shield those tiny and non-essential leakage signals caused by environmental factors and prevent them from affecting the subsequent detection process and judgment. The main function of this step is to reduce false alarms and unnecessary maintenance operations caused by over-sensitivity, thereby improving the efficiency and accuracy of the detection system.

[0050] The high sensitivity of the ultrasonic leakage detection system enables it to capture extremely weak signals, including natural fluctuations caused by environmental factors such as temperature changes, humidity fluctuations, or external air pressure changes. Although these tiny fluctuations can be detected by the sensor, they do not have an actual impact on the airtightness, ventilation effect, or safety of the air damper. Therefore, if not controlled, these tiny signals may be wrongly determined as leaks that need to be repaired, resulting in unnecessary maintenance, adjustment, or replacement of components in the system.

[0051] By reducing the sensor sensitivity, the system can automatically ignore these tiny leakage signals and reduce their interference with the detection results. In this way, the sensor will only respond to those leakage signals that truly have an impact, ensuring more accurate detection results. This measure not only avoids over-reaction but also significantly reduces the frequency of equipment maintenance and production downtime, thereby improving the overall production efficiency and saving maintenance costs.

[0052] When it is recognized that the leakage signal is a negligible leakage, based on the evaluation result, the specific steps to reduce the sensitivity of the sensor to shield tiny and non-essential leakage signals are as follows: Once it is recognized that the leakage signal is a natural fluctuation caused by environmental factors and is determined to be a negligible leakage, the sensitivity of the sensor will be reduced based on the evaluation result. By reducing the sensitivity of the sensor, tiny and non-essential leakage signals will be automatically shielded to avoid interfering with the detection results. The adjustment formula is as follows: , where is the adjusted sensor sensitivity, is the initial sensor sensitivity, is the sensitivity adjustment coefficient, which controls the rate of sensitivity decrease ( ), which is usually adjusted according to actual requirements. is the micro-leakage change coefficient. is the reference threshold of the micro-leakage change coefficient. is the non-linear exponential factor, which enhances the non-linear response effect of sensitivity adjustment, making the influence of the micro-leakage signal on sensitivity more significant. , The selection of affects the speed of sensitivity change and the dynamic adjustment of sensitivity. is the sensitivity correction factor, representing the "hysteresis" adjustment of the sensor's response to micro-leakage signals, and controlling the final adjustment result of sensitivity.

[0053] By dynamically adjusting the sensitivity of the ultrasonic sensor, overreaction to tiny and insubstantial leakage signals is avoided, thereby reducing unnecessary false alarms and repairs. This sensitivity adjustment mechanism ensures that only leakage signals that actually affect the airtightness of the air damper and the ventilation effect can trigger a system response, improving the accuracy and efficiency of detection.

[0054] By implementing a comprehensive solution of initial sensitivity detection, data preprocessing and feature extraction, intelligent evaluation, and dynamic sensitivity adjustment, the system of the present invention can accurately identify and process leakage signals that only have a substantial impact on the performance of the air damper, thereby effectively avoiding misjudgment of tiny natural fluctuation signals caused by environmental factors (such as temperature fluctuations, humidity changes, etc.). This method significantly improves the detection accuracy, reduces unnecessary false alarms and maintenance operations, avoids waste of resources and unnecessary shutdown of the production line. At the same time, the sensitivity adjustment mechanism ensures that the system can adapt to different environmental conditions, improving the flexibility and adaptability of the detection system. Ultimately, this not only improves the overall reliability of the system, reduces the maintenance cost, but also realizes significant economic benefits by optimizing the maintenance cycle and improving the production efficiency.

[0055] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0056] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

[0057] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0058] It should be understood that in various embodiments of the present application, the magnitude of the sequence numbers of the above processes does not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0059] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0060] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0061] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0062] In addition, in various embodiments of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0063] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0064] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A one-stop offline detection method for electric dampers, characterized in that: The following steps are involved: At the beginning of the test, the ultrasonic sensor conducts a comprehensive test of the electric damper's sealing performance with initial sensitivity and collects the damper's leakage signal data in real time; Preprocessing the acquired leakage signal data, and aggregating the preprocessed data to establish a data set; Through feature engineering, key indicators reflecting the natural fluctuation of leakage caused by environmental factors are extracted from the data set, and the extracted key indicators are comprehensively analyzed to quantify the severity of leakage and evaluate the actual impact of leakage on damper performance; The key indicators after comprehensive analysis are input into the pre-trained machine learning model, and the machine learning model is used to intelligently evaluate the leak to determine whether the leak is an actual airtightness problem; When the leakage signal is identified as a negligible leakage, the sensitivity of the sensor is reduced based on the evaluation result, thereby shielding the tiny, non-essential leakage signal.

2. The one-stop offline detection method for electric dampers according to claim 1 is characterized in that: The specific steps to preprocess data and create a data set are as follows: First, the acquired leakage signal data is denoised, and the noise components in the signal are removed by using filtering technology; Next, data from different time periods are converted to a unified standard through data normalization to eliminate the impact of unit and magnitude differences on the analysis results; Then, a smoothing algorithm is applied to smooth the signal to reduce the interference caused by instantaneous fluctuations. For signals with abnormal values, the outlier detection method is used to eliminate or correct them; After completing the preprocessing steps, the leakage signal data under various time periods and environmental conditions are aggregated, and the data are integrated into a data set according to the dimensions of time, damper working status, and environmental factors to ensure the integrity and consistency of the data and provide accurate and stable basic data for subsequent analysis and modeling.

3. The one-stop offline detection method for electric dampers according to claim 1 is characterized in that: Through feature engineering, key indicators reflecting the natural fluctuation of leakage caused by environmental factors are extracted from the data set. The extracted key indicators include the impact of air pressure changes on the sealing of the damper and the impact of stress changes of the damper sealing material under temperature changes on the sealing. The impact of air pressure changes on the sealing of the damper and the impact of stress changes of the damper sealing material under temperature changes on the sealing are comprehensively analyzed under the detection window, and the air pressure change response reference value and the temperature sensitivity stress reference value are generated respectively. The severity of the leakage is quantified by the air pressure change response reference value and the temperature sensitivity stress reference value, and the actual impact of the leakage on the damper performance is evaluated.

4. The one-stop offline detection method for electric dampers according to claim 3 is characterized in that: The specific steps for comprehensively analyzing the impact of air pressure changes on the air door sealing under the detection window to generate the air pressure change response reference value are as follows: First, the time series of air pressure change data and electric damper leakage signals are collected to establish the relationship between air pressure change and leakage signals. The air pressure-leakage difference index is introduced to quantitatively describe the effect of air pressure change on damper sealing. The calculation expression of the air pressure-leakage difference index is as follows: , where is the pressure-leakage difference index, and At the time point Moments and time points The air pressure value at the moment, and At the time point Moments and time points The leakage signal value at time is the total number of time points; After obtaining the air pressure-leakage difference index, the air pressure change response reference value is generated by the air pressure-leakage difference index. The generation formula is as follows: , where It's time point The pressure-leakage difference index calculated at each moment, It is the reference value of the response to air pressure changes.

5. The one-stop offline detection method for electric dampers according to claim 3 is characterized in that: The specific steps for comprehensively analyzing the influence of the stress change of the damper sealing material under temperature change on the sealing performance under the detection window to generate the temperature sensitivity stress reference value are as follows: Firstly, the stress change of the electric damper sealing material under temperature change is analyzed, and then the stress change caused by temperature is calculated. Assuming that the volume change of the sealing material caused by temperature change has a direct impact on the sealing performance, the calculation expression of the stress change is as follows: , where is the stress change, is the elastic modulus of the damper seal material, is the strain change, and its calculation formula is: ,in, It is the change in length of the sealing material caused by temperature change. is the initial length of the sealing material; Based on the stress variation , combined with the amplitude of temperature change, generate the reference value of temperature sensitivity stress, the calculation expression is as follows: , where is the reference value of temperature sensitivity stress, is the temperature variation, is the reference temperature.

6. The one-stop offline detection method for electric dampers according to claim 3 is characterized in that: The pressure change response reference value and temperature sensitivity stress reference value after comprehensive analysis are input into the pre-trained machine learning model, and the micro-leakage variation coefficient is generated by the machine learning model. The leakage is intelligently evaluated by the micro-leakage variation coefficient to determine whether the leakage is an actual airtightness problem.

7. The one-stop offline detection method for electric dampers according to claim 6 is characterized in that: The micro-leakage variation coefficient is compared and analyzed with the preset micro-leakage variation coefficient reference threshold to determine whether the leakage is an actual airtightness problem. The judgment logic is as follows: If the micro-leakage variation coefficient is greater than the preset micro-leakage variation coefficient reference threshold, it is judged that the leakage is a natural fluctuation caused by environmental factors; if the micro-leakage variation coefficient is less than or equal to the preset micro-leakage variation coefficient reference threshold, it is judged that the leakage is not a natural fluctuation caused by environmental factors.

8. The one-stop offline detection method for electric dampers according to claim 7 is characterized in that: When the leakage signal is identified as a negligible leakage, the specific steps for reducing the sensitivity of the sensor based on the evaluation results to shield the tiny, non-essential leakage signal are as follows: Once the leakage signal is identified as a natural fluctuation caused by environmental factors and judged to be a negligible leakage, the sensitivity of the sensor will be reduced based on the evaluation results. By reducing the sensitivity of the sensor, small, non-essential leakage signals will be automatically shielded to avoid interference with the detection results. The adjustment formula is as follows: , where is the adjusted sensor sensitivity, is the initial sensor sensitivity, is the sensitivity adjustment coefficient, which controls the rate at which the sensitivity decreases. is the micro-leakage variation coefficient, is the micro-leakage variation coefficient reference threshold, is a nonlinear exponential factor that enhances the nonlinear response effect of sensitivity adjustment. is the sensitivity correction factor.

Images