A method and system for detecting the lifetime of a sensitive component

Abstract

The application provides a sensitive component life detection method and system, and relates to the field of sensitive component life detection.The method comprises the following steps: recording the factory UTC time of a sensitive component and initial performance data at the factory; based on a preset timing monitoring period, acquiring the current UTC time and average performance data of the sensitive component in the timing monitoring period at the end of each timing monitoring period; adjusting the weight coefficient corresponding to different timing monitoring periods according to environmental data and sensitive component load parameters; performing weighted summation on the average performance data according to the weight coefficient to obtain a total integral value; when it is detected that the total integral value is greater than or equal to a preset integral threshold value or the variable value of the average performance data exceeds a preset amplitude threshold value, triggering alarm information that the life has reached the limit. By implementing the method, the performance change of the sensitive component under different environmental and load conditions can be dynamically responded, and the life end of the sensitive component can be more accurately predicted.

Description

Technical Field

[0001] This application relates to the field of life testing of sensitive components, and in particular to a method and system for testing the life of sensitive components. Background Technology

[0002] Sensitive components are elements capable of sensing specific physical quantities (such as temperature, humidity, and pressure) and generating corresponding responses. They are typically part of sensors, used to convert sensed physical quantities into measurable signals. Especially in the manufacturing processes of high-precision wafer packaging and foldable screen electronic devices, sensitive components are an indispensable part of sensors, used to detect and analyze data such as temperature, humidity, and pressure. The accuracy of these sensitive components is crucial to the quality of the final product. With technological advancements, the application areas and demands for sensitive components are constantly expanding, and the requirements for their performance and reliability are also increasing.

[0003] In related technologies, periodic performance testing methods are commonly used to assess the condition and lifespan of sensitive components. In these methods, sensitive components undergo performance testing at specific time intervals, measuring parameters such as response time and sensitivity. These tests are typically performed under specific standard test conditions to ensure data consistency and comparability. By comparing the new test data with baseline data from the factory, the degree of performance degradation of the sensitive components is assessed.

[0004] However, while regular performance testing can reflect the performance status of sensitive components to some extent, this method usually relies on data collection at fixed time points, ignoring the continuous and rapidly changing environmental factors that sensitive components may encounter in the actual operating environment. It is difficult to capture performance changes caused by environmental fluctuations or different load conditions in real time, resulting in inaccurate life prediction results for sensitive components. Summary of the Invention

[0005] This application provides a method and system for detecting the lifespan of sensitive components, which addresses the problem of how to dynamically monitor the performance degradation of sensitive components under different environmental and load conditions, thereby improving the accuracy of the lifespan detection of sensitive components.

[0006] In a first aspect, this application provides a method for detecting the lifespan of sensitive components, applied to a system for detecting the lifespan of sensitive components, the method comprising:

[0007] When the sensitive components leave the factory, record the UTC time of the sensitive components and the initial performance data at the time of leaving the factory;

[0008] Based on a preset timed monitoring cycle, the current UTC time and the average performance data of the sensitive components during the timed monitoring cycle are obtained at the end of each timed monitoring cycle.

[0009] Adjust the weighting coefficients corresponding to different timed monitoring cycles based on environmental data and load parameters of sensitive components;

[0010] The average performance data is weighted and summed according to the weighting coefficients to obtain the total integral value;

[0011] When the total integral value is detected to be greater than or equal to a preset integral threshold, or when the variable value of the average performance data exceeds a preset amplitude threshold, an alarm message indicating that the lifespan has reached its limit is triggered.

[0012] Through the above embodiments, the sensitive component lifespan detection system assigns different weighting coefficients to different monitoring cycles based on the performance changes of the sensitive component under different environmental and load conditions. A weighted summation is then used to obtain a total integral value that reflects the overall performance change of the sensitive component. Finally, the relationship between the total integral value and a corresponding preset threshold is used to determine whether the lifespan of the sensitive component is nearing its limit. This method can dynamically respond to the performance changes of sensitive components under different environmental and load conditions, thereby more accurately predicting the end of the sensitive component's lifespan.

[0013] In some embodiments, the step of obtaining the current UTC time and the average performance data of the sensitive component within the timed monitoring period at the end of each preset timed monitoring period specifically includes:

[0014] Within each of the timed monitoring cycles, performance data of the sensitive components are collected at preset time intervals, and the performance data includes multiple parameter indicators;

[0015] Calculate the parameter-weighted sum of the performance data based on the preset weight corresponding to each parameter indicator;

[0016] The average value of the weighted sum of multiple parameters within the timed monitoring period is determined as the average performance data within the timed monitoring period.

[0017] Through the above embodiments, the sensitive component life monitoring system collects multiple performance parameters at fixed time intervals within each monitoring cycle, assigns different weights to these parameters, and calculates the average of the weighted sums as the average performance data for that cycle. This method highlights key indicators and reduces the interference of secondary indicators through weight configuration, enabling the average performance data to more accurately reflect the overall operating status of the sensitive component within the monitoring cycle.

[0018] In some embodiments, the step of adjusting the weighting coefficients corresponding to different timing monitoring periods based on environmental data and load parameters of sensitive components specifically includes:

[0019] Obtain environmental data and sensitive component load parameters corresponding to different timed monitoring cycles;

[0020] The environmental data and the load parameters of the sensitive components are input into the machine learning model, and the performance prediction values ​​of the sensitive components corresponding to different timed monitoring cycles are output.

[0021] Based on the performance prediction value, assign weight coefficients corresponding to different timed monitoring periods.

[0022] Through the above embodiments, the sensitive component lifespan monitoring system collects environmental data and load parameters from different monitoring cycles and inputs them into a pre-trained machine learning model to obtain a performance prediction value that takes into account the current specific operating conditions. Based on this prediction value, the weight coefficients of the monitoring cycles can be dynamically adjusted, giving higher weights to cycles with faster predicted performance degradation and lower weights to cycles with relatively stable predicted performance, so that the final weighted integral result can more closely reflect the actual usage state of the sensitive components.

[0023] In some embodiments, before the step of obtaining environmental data and sensitive component load parameters corresponding to different timed monitoring cycles, the method further includes:

[0024] A training dataset is constructed based on historical sensitive component data, which includes historical environmental data, historical sensitive component load parameters, and historical performance data.

[0025] The machine learning model is trained using the training dataset, so that the machine learning model outputs the performance prediction value of the sensitive components based on the input historical environmental data and historical load parameters of the sensitive components.

[0026] Through the above embodiments, the sensitive component lifespan monitoring system collects historical operating data of sensitive components, including environmental conditions, load parameters, and corresponding performance data, to construct a training set that comprehensively reflects the performance variation patterns of sensitive components. This dataset is then used to train a machine learning model, enabling it to accurately predict the performance degradation of sensitive components based on environmental and load data.

[0027] In some embodiments, after the step of obtaining the current UTC time and the average performance data of the sensitive component within the timed monitoring period at the end of each timed monitoring period based on a preset timed monitoring period, the method further includes:

[0028] The performance degradation trend of the sensitive component is determined based on the initial performance data and the average performance data;

[0029] The lifespan of the sensitive components is predicted based on the performance degradation trend.

[0030] An alarm message indicating that the lifespan has reached its limit is triggered when the lifespan duration is detected to be less than a preset duration threshold.

[0031] Through the above embodiments, the sensitive component lifespan detection system analyzes initial performance data and average performance data for each monitoring cycle to determine the performance degradation trend of sensitive components over time, and extrapolates the lifespan of sensitive components based on this trend. When the predicted lifespan is lower than a preset threshold, an alarm is triggered in a timely manner, indicating that the sensitive component has entered the end of its lifespan and needs to be replaced as soon as possible.

[0032] In some embodiments, prior to the step of predicting the lifespan of the sensitive component based on the performance degradation trend, the method further includes:

[0033] The size of the timed monitoring cycle is adjusted according to the lifespan duration, and the size of the timed monitoring cycle is positively correlated with the lifespan duration.

[0034] Through the above embodiments, the sensitive component lifespan detection system appropriately extends the monitoring cycle and reduces unnecessary frequent sampling when the predicted lifespan of a sensitive component is long; conversely, it shortens the monitoring cycle and increases the sampling frequency when the predicted lifespan is short, in order to more closely track performance changes. This adaptive monitoring strategy balances the timeliness of monitoring and resource consumption, ensuring close monitoring of the performance of sensitive components during critical periods while avoiding oversampling during non-critical periods, thus improving the overall efficiency of the detection method.

[0035] In some embodiments, the step of triggering an alarm message indicating that the lifespan has reached its limit when the total integral value is detected to be greater than or equal to a preset integral threshold, or when the variable value of the average performance data exceeds a preset amplitude threshold, specifically includes:

[0036] Multiple preset integration ranges and preset amplitude ranges are set, and different levels of alarm information are provided for different preset integration ranges or different preset amplitude ranges.

[0037] The first alarm information and the second alarm information are determined based on the preset integration range of the total integration value and the preset amplitude range of the average performance data, respectively.

[0038] The warning will be issued using the highest-level alarm information among the first and second alarm information.

[0039] Through the above embodiments, the sensitive component lifespan monitoring system compares the current integral value and the magnitude of performance change to determine which preset warning range they fall into, thus deriving two preliminary warning levels. The higher level is then taken as the final warning level. This multi-level warning system avoids the problem that simple binary warnings (normal / abnormal) cannot accurately reflect the performance status of sensitive components. It describes the health level of sensitive components in a more granular way, allowing users to understand the current performance degradation status more intuitively and comprehensively.

[0040] Secondly, this application provides a sensitive component life detection system, the system comprising: one or more processors and a memory;

[0041] The memory is coupled to the one or more processors. The memory is used to store computer program code, which includes computer instructions. The one or more processors call the computer instructions so that the system can implement the sensitive component lifetime detection method provided in the above embodiments, which will not be described in detail here.

[0042] Thirdly, this application provides a computer-readable storage medium including instructions that, when executed on a sensitive component lifetime testing system, enable the system to implement a sensitive component lifetime testing method provided in the above embodiments, which will not be elaborated further here.

[0043] Fourthly, this application provides a computer program product that, when run on a sensitive component life testing system, enables the system to implement a sensitive component life testing method provided in the above embodiments, which will not be elaborated further here.

[0044] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0045] 1. The sensitive component lifespan monitoring system assigns different weighting coefficients to different monitoring periods based on the performance changes of sensitive components under different environmental and load conditions. By weighted summing of the average performance data from each monitoring period, a total integral value that comprehensively reflects the overall performance changes of the sensitive component is obtained. This mechanism can dynamically adapt to the changing patterns of sensitive component performance, effectively improving the accuracy of lifespan prediction.

[0046] 2. The sensitive component lifespan monitoring system collects environmental data and load parameters from different monitoring cycles and inputs them into a pre-trained machine learning model to obtain performance predictions that take into account the current specific operating conditions. The weighting coefficients of each monitoring cycle are dynamically adjusted based on the predictions, assigning higher weights to cycles with faster predicted performance degradation. This ensures that the weighted integral result more closely reflects the actual usage state of the sensitive components, improving the accuracy of lifespan prediction. Simultaneously, a comprehensive machine learning training set is constructed using historical operating data, further enhancing the model's predictive capabilities.

[0047] 3. By analyzing initial performance data and average performance data for each monitoring cycle, the performance degradation trend of sensitive components over time is determined, and the lifespan of sensitive components is predicted by extrapolation based on this trend. When the predicted lifespan is lower than a preset threshold, an alarm is triggered in a timely manner to indicate that the sensitive component has entered the end of its lifespan, providing an important basis for maintenance and replacement decisions for sensitive components. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating a method for detecting the lifetime of a sensitive component in an embodiment of this application;

[0049] Figure 2 This is another flowchart illustrating a method for detecting the lifespan of sensitive components in an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the physical device structure of a sensitive component life detection system in the embodiments of this application. Detailed Implementation

[0051] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0052] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0053] It should be noted that the "sensitive component" in the embodiments of this application is one of the structures of the "sensor", and the data detected by the sensitive component is displayed by the sensor. Therefore, in some embodiments, the "sensitive component" can also be described as the "sensor", and this is not limited.

[0054] For ease of understanding, the method provided in this implementation is described in process below. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating a method for detecting the lifespan of sensitive components in an embodiment of this application.

[0055] S101. When sensitive components leave the factory, record the UTC time of the sensitive components and the initial performance data at the time of leaving the factory.

[0056] The sensitive component lifespan monitoring system records the UTC (Universal Time of Catch) of a sensitive component as the starting time point when it leaves the factory. Simultaneously, the system can also measure and record the initial performance data of the sensitive component at the time of manufacture, including but not limited to key indicators such as sensitivity, response time, and baseline noise. This initial performance data serves as a baseline for the performance of the sensitive component and is an important reference for subsequent performance degradation assessment.

[0057] For example, when a gas detection electrical sensitive component leaves the factory, the sensitive component life test system records its manufacturing time as January 1, 2022, 00:00 (UTC), and measures its initial sensitivity as 1.2 nA / ppm, response time (T90) as 15 s, and baseline noise as 2 pA. This data is stored in a database for subsequent performance trend analysis.

[0058] Understandably, UTC time is an international standard time, which avoids time errors caused by time zone differences.

[0059] S102. Based on the preset timed monitoring cycle, obtain the current UTC time and the average performance data of the sensitive components during the timed monitoring cycle at the end of each timed monitoring cycle.

[0060] The sensitive component lifespan monitoring system periodically collects performance data of sensitive components according to a pre-set timed monitoring cycle (such as daily, weekly, or monthly). At the end of each monitoring cycle, the system records the current UTC time, calculates the average value of various performance indicators of the sensitive components within that cycle, and then sums the calculated average values ​​according to preset weights to obtain the average performance data for that cycle.

[0061] S103. Adjust the weighting coefficients corresponding to different timed monitoring cycles based on environmental data and load parameters of sensitive components.

[0062] Specifically, the sensitive component lifespan monitoring system acquires environmental data (such as temperature, humidity, and pressure) and load parameters (such as target concentration and sampling frequency) for each monitoring cycle. The system then inputs this data into a pre-trained machine learning model, which predicts the performance changes of the sensitive component within that cycle based on the input environmental and load conditions. The model outputs a predicted decay rate, indicating how quickly the sensitive component's performance degrades under the current conditions. Next, the system adjusts the weighting coefficients for that monitoring cycle based on the predicted decay rate. A higher decay rate indicates a greater impact of the current cycle's operating environment and load on the sensitive component's performance, thus assigning it a higher weight in subsequent weighted integral calculations; conversely, a lower predicted decay rate results in a lower weighting coefficient for that cycle. Through this dynamic weighting adjustment mechanism, the system can adaptively respond to complex and changing usage scenarios, more accurately assessing the overall performance status of the sensitive component.

[0063] For example, in one specific embodiment, suppose a sensitive component is used in a factory environment to detect toxic gases during the production process. During the first monitoring period, the workshop temperature is maintained at 25°C, the air humidity is 50%RH, and the target gas concentration is below the safety threshold. Based on this data, the system predicts a performance degradation rate of 0.1% / day for this period. During the second monitoring period, due to equipment failure, the workshop temperature suddenly rises to 40°C, and the detected toxic gas concentration also increases significantly. The system re-predicts based on updated environmental and load data, obtaining a performance degradation rate of 0.8% / day for this period. Accordingly, the system sets the weighting coefficient for the second period to four times that of the first period to reflect the impact of harsh operating conditions on the lifespan of the sensitive component.

[0064] S104. The average performance data is weighted and summed according to the weighting coefficients to obtain the total integral value.

[0065] The sensitive component life monitoring system multiplies the average performance data of each monitoring cycle by its corresponding weighting coefficient to obtain a series of weighted performance values. Then, the system sums the weighted performance values ​​of all cycles to obtain the final total integral value.

[0066] The specific calculation formula is: Total integral value = ∑(average performance data of the i-th period × weight coefficient of the i-th period), i = 1, 2, 3...n; where n represents the total number of monitoring periods.

[0067] For example, in one specific embodiment, suppose that the average performance data of a certain sensitive component in the past three monitoring periods were 0.98, 0.95, and 0.9, respectively, with corresponding weighting coefficients of 1, 1.5, and 2. Then the total integral value of the sensitive component is:

[0068] Total integral = 0.98×1 + 0.95×1.5 + 0.9×2 = 4.205.

[0069] S105. When the total integral value is detected to be greater than or equal to the preset integral threshold, or the variable value of the average performance data exceeds the preset amplitude threshold, an alarm message indicating that the lifespan has reached its limit is triggered.

[0070] Based on two key indicators—total integral value and average performance change rate—the sensitive component lifespan monitoring system can determine whether a sensitive component is nearing the end of its service life. Specifically, the system pre-sets two thresholds: an integral threshold and an amplitude threshold. When the detected indicators exceed these thresholds, the system triggers a corresponding early warning mechanism, alerting the user that the sensitive component may be about to fail and needs to be replaced as soon as possible.

[0071] The integral threshold represents the critical point at which the performance of a sensitive component deteriorates to the point where it is difficult to meet application requirements. Generally, when the total integral value reaches or exceeds this threshold, it means that the sensitive component has been working in a non-ideal state for a long time, and the accumulated performance loss is already quite significant. Continued use may bring great risks. The setting of the integral threshold needs to take into account factors such as the type of sensitive component, application scenario, and historical data, which are not limited here.

[0072] Furthermore, amplitude thresholds are used to monitor the magnitude of changes in the performance of sensitive components within a short period. For example, if a performance indicator drops sharply by 20% compared to the previous period within a monitoring cycle, even if the total integral value has not yet reached the threshold, this sudden performance decline often indicates that some critical components of the sensitive component have failed, or that the operating environment has deteriorated to an extreme state. Timely detection of these abnormal changes can prevent the serious consequences of complete failure of sensitive components.

[0073] Furthermore, when the system detects that the total score or average performance change exceeds the corresponding preset threshold, it immediately issues a warning to the user. The content and presentation of the warning can be customized according to actual needs, such as sending alarm emails, mobile phone push notifications, and audible and visual alarms. Simultaneously, the system can also output detailed performance reports for sensitive components, including performance trend charts for each monitoring period, key event markers, and lifespan estimates, providing decision support for users; however, this is not limited here.

[0074] In the above embodiments, the sensitive component lifespan detection system assigns different weighting coefficients to different monitoring periods based on the performance changes of the sensitive component under different environmental and load conditions. A weighted summation is then used to obtain a total integral value that reflects the overall performance change of the sensitive component. Finally, the system determines whether the lifespan of the sensitive component is nearing its limit based on the relationship between the total integral value and a corresponding preset threshold. This method can dynamically respond to the performance changes of the sensitive component under different environmental and load conditions, thereby more accurately predicting the end of the sensitive component's lifespan.

[0075] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating a method for detecting the lifespan of sensitive components in an embodiment of this application.

[0076] S201. In each timed monitoring cycle, collect performance data of sensitive components at preset time intervals.

[0077] The sensitive component lifespan monitoring system continuously collects performance data of sensitive components at preset time intervals within each monitoring cycle. These performance indicators include, but are not limited to, key parameters reflecting the operating status of sensitive components such as sensitivity, response time, baseline noise, and drift. The sampling time interval is set by relevant technical personnel taking into account factors such as the type of sensitive component, operating environment, and data transmission rate, and is not limited here.

[0078] S202. Calculate the weighted sum of the parameters corresponding to the performance data based on the preset weights corresponding to each parameter indicator.

[0079] The sensitive component lifespan monitoring system pre-assigns a weight value to each performance parameter. A larger weight value indicates greater importance of that parameter in evaluating the sensitive component's performance, and thus a greater impact on the final weighted sum. After obtaining the raw data for each performance parameter of the sensitive component within a monitoring period, the system adds the product of each parameter value and its weight to obtain a weighted sum as the overall performance score of the sensitive component at that moment.

[0080] For example, in one specific embodiment, for a certain electrochemical gas sensitive device, its output signal current value, response time, and baseline noise are considered as three key indicators for evaluating its performance. In the sensitive device lifetime monitoring system, the weights of these three are set to 0.5, 0.3, and 0.2, respectively. In a performance evaluation, if the current value is 50 nA, the response time is 30 s, and the baseline noise is 5 pA, the weighted sum calculation process is as follows:

[0081] Weighted sum = 50nA×0.5 + 30s×0.3 + 5pA×0.2 = 35.

[0082] S203. The average value of the weighted sum of multiple parameters within the timed monitoring period is determined as the average performance data within the timed monitoring period.

[0083] Specifically, at the end of each monitoring cycle, the sensitive component life detection system obtains the weighted sum of parameters calculated at each sampling time point within that cycle, calculates its arithmetic mean, and uses it as a representative indicator of the sensitive component's performance within that cycle, i.e., average performance data.

[0084] In the above embodiments, the sensitive component life monitoring system collects multiple performance parameters at fixed time intervals within each monitoring cycle, assigns different weights to these parameters, and calculates the average of the weighted sums as the average performance data for that cycle. This method highlights key indicators and reduces the interference of secondary indicators through weight configuration, enabling the average performance data to more accurately reflect the overall operating status of the sensitive component within the monitoring cycle.

[0085] S204. Determine the performance degradation trend of sensitive components based on initial performance data and average performance data.

[0086] Specifically, similar to the calculation method for the average performance data in step S203, the initial average performance data corresponding to the initial performance data is calculated and used as the starting point of the performance degradation trend curve. Then, the average performance data corresponding to each monitoring period obtained in step S203 is added to the performance degradation trend curve in chronological order to determine the performance degradation trend of the sensitive components.

[0087] S205. Predict the lifespan of sensitive components based on performance degradation trends, and trigger an alarm message indicating that the lifespan has reached its limit when the detected lifespan is less than a preset time threshold.

[0088] The sensitive component lifespan monitoring system predicts the time it takes for the average performance data of a sensitive component to reach a set minimum performance threshold based on performance degradation trends; this is the lifespan of the sensitive component. Furthermore, the system can preset a remaining lifespan warning threshold. When the lifespan of a sensitive component falls below this threshold, the system automatically triggers a high-priority warning message, alerting relevant personnel that the sensitive component has entered the end of its service life and that preparations for replacement or repair should be made in advance.

[0089] In the above embodiments, the sensitive component lifespan detection system analyzes initial performance data and average performance data for each monitoring cycle to determine the performance degradation trend of the sensitive component over time, and extrapolates the prediction of the sensitive component's lifespan based on this trend. When the predicted lifespan is lower than a preset threshold, an alarm is triggered in a timely manner, indicating that the sensitive component has entered the end of its lifespan and needs to be replaced as soon as possible.

[0090] S206. Adjust the size of the timed monitoring cycle according to the lifespan.

[0091] Specifically, when sensitive components are detected to be in the early or middle stages of their lifespan, the sensitive component lifespan monitoring system can adopt a longer monitoring cycle, such as collecting performance data monthly or quarterly. This reduces the system workload, saves storage and energy costs, and ensures that the long-term performance evolution trend of sensitive components is not missed. However, when sensitive components are detected to be in the later stages of their lifespan, especially when approaching the warning threshold, their performance often exhibits accelerated degradation, and the risk of failure increases sharply. At this point, the system should shorten the monitoring cycle accordingly, such as sampling weekly or daily.

[0092] In the above embodiments, when the sensitive component lifetime detection system detects a long predicted lifetime for a sensitive component, it appropriately extends the monitoring cycle to reduce unnecessary frequent sampling; when the predicted lifetime is short, it shortens the monitoring cycle and increases the sampling frequency to more closely track performance changes. This adaptive monitoring strategy balances the timeliness of monitoring and resource consumption, ensuring close monitoring of the performance of sensitive components during critical periods while avoiding oversampling during non-critical periods, thus improving the overall efficiency of the detection method.

[0093] S207. Based on historical sensitive component data, construct a training dataset to train a machine learning model, so that it outputs the performance prediction value of the sensitive component based on the input historical environmental data and historical sensitive component load parameters.

[0094] The sensitive component life detection system uses historical environmental data and historical load parameters of sensitive components as input features of the machine learning model, and uses the performance prediction value as the output target of the model. Through data preprocessing and feature engineering, a high-quality training dataset is constructed.

[0095] S208. Obtain environmental data and load parameters of sensitive components corresponding to different timed monitoring cycles.

[0096] Specifically, at the beginning of each monitoring cycle, the sensitive component lifespan monitoring system obtains the average environmental parameters for that cycle, such as average temperature, humidity, and pressure, as well as statistical information on load parameters, such as sampling frequency and maximum / minimum concentration, from various data sources via a data interface. This data serves as input to the prediction model, representing the operating conditions of the sensitive component during that monitoring cycle.

[0097] For example, in one specific embodiment, a monitoring cycle is one day (24 hours). At the beginning of the cycle, the sensitive component life monitoring system automatically extracts the temperature data (18~25℃, average 22℃), humidity data (40%~60%, average 50%), gas concentration data (0.20ppm, average 5ppm), and the sampling frequency setting of the sensitive components (once per minute) within the workshop. This data will serve as the environmental and load characteristics for that monitoring cycle, used for subsequent performance prediction and weight calculation.

[0098] S209. Input environmental data and load parameters of sensitive components into the machine learning model, and output the performance prediction values ​​of sensitive components corresponding to different timed monitoring cycles.

[0099] After obtaining the environmental and load data for the monitoring period, the sensitive component life detection system inputs it into a pre-trained machine learning model to obtain the predicted value of the sensitive component's performance within that period.

[0100] In the above embodiments, the sensitive component lifespan monitoring system collects historical operating data of sensitive components, including environmental conditions, load parameters, and corresponding performance data, to construct a training set that comprehensively reflects the performance variation patterns of sensitive components. This dataset is then used to train a machine learning model, enabling it to accurately predict the performance degradation of sensitive components based on environmental and load data.

[0101] S210. Assign weight coefficients to different timed monitoring periods based on the performance prediction values.

[0102] Specifically, the sensitive component lifespan monitoring system pre-sets a mapping relationship between predicted performance values ​​and weighting coefficients. For example, when the predicted performance of a certain cycle decreases by less than 10% compared to the initial value, the weighting coefficient is 1; when it decreases by 10% to 20%, the weighting coefficient is 1.5; when it decreases by 20% to 30%, the weighting coefficient is 2; and when it decreases by more than 30%, the weighting coefficient is 3. The sensitive component lifespan monitoring system calculates the percentage of performance degradation based on the predicted performance of each cycle, and then assigns the corresponding weighting coefficient according to the mapping relationship.

[0103] In the above embodiments, the sensitive component lifespan detection system collects environmental data and load parameters for different monitoring cycles and inputs them into a pre-trained machine learning model to obtain a performance prediction value that takes into account the current specific operating conditions. Based on this prediction value, the weight coefficients of the monitoring cycles can be dynamically adjusted, giving higher weights to cycles with faster predicted performance degradation and lower weights to cycles with relatively stable predicted performance, so that the final weighted integral result can more closely reflect the actual usage state of the sensitive components.

[0104] S211. The average performance data is weighted and summed according to the weighting coefficients to obtain the total integral value.

[0105] This step is the same as step S104, and will not be repeated here.

[0106] S212. Set multiple preset integration ranges and preset amplitude ranges, and determine the first alarm information and the second alarm information based on the preset integration range where the total integration value is located and the preset amplitude range where the average performance data is located, respectively.

[0107] The sensitive component lifespan monitoring system first predefines multiple threshold ranges for performance integrals and performance variation amplitudes. These ranges, from low to high, represent different degrees of performance degradation, with each range corresponding to a specific level of warning information. For example, the system can set three integral thresholds: 0-70, 70-80, and 80-100, and three amplitude thresholds: 5%, 10%, and 20%. When the total integral value of a sensitive component falls within 0-70, it indicates good performance and no warning is triggered; 70-80 is a mild warning, and 80-100 is a severe warning. Similarly, an average performance variation amplitude of less than 5% is within the normal fluctuation range; 5%~10% is a mild anomaly, 10%~20% is a severe anomaly, and exceeding 20% ​​is considered a serious fault.

[0108] In the actual early warning determination process, the sensitive component life detection system compares the currently calculated total integral value and average performance change rate with the aforementioned preset threshold ranges to identify the range in which the component falls and obtain the corresponding early warning level, which is used as the first alarm information and the second alarm information, respectively. For example, if the current total integral value of a sensitive component is 85 and the average performance decrease is 15%, then its first alarm information is "severe warning" and its second alarm information is "severe anomaly".

[0109] S213. Use the highest-level alarm information among the first and second alarm information to issue a warning.

[0110] After obtaining the total performance score and the two warning levels (first alarm information and second alarm information) corresponding to the average performance change, the sensitive component life detection system further determines how to issue the final warning notification.

[0111] Specifically, in this embodiment, the sensitive component lifespan detection system takes the higher of the first and second alarm messages as the final alarm level. For example, the first alarm message (based on the total integral value) for a sensitive component is "severe warning," and the second alarm message (based on the average performance change) is "minor anomaly." The sensitive component lifespan detection system compares the levels of the two alarm messages and determines that "severe warning" has a higher priority; therefore, the final warning notification issued to the user is "severe warning." Furthermore, to provide more comprehensive diagnostic information, the system can also supplement the warning notification with explanations of the main basis for triggering the warning, such as "the total performance index of the sensitive component is 85, which has reached the severe warning threshold; it is recommended to arrange maintenance or replacement as soon as possible," etc., which are not limited here.

[0112] In the above embodiments, the sensitive component lifespan detection system compares the current integral value and the performance change range to determine which preset warning range they fall into, thus obtaining two preliminary warning levels. The higher level is then taken as the final warning level. This multi-level warning avoids the problem that simple binary warnings (normal / abnormal) cannot accurately reflect the performance status of sensitive components. It describes the health level of sensitive components in a more granular way, allowing users to understand the current performance degradation status more intuitively and comprehensively.

[0113] The sensitive component life detection system of this invention is applied to electronic devices. Figure 3 A schematic diagram of the architecture of an electronic device suitable for implementing embodiments of the present invention is shown.

[0114] It should be noted that, Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0115] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by instructions (computer programs), or by instructions (computer programs) controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein the storage medium stores multiple instructions that can be loaded by the processor to execute any step of the method provided in the embodiments of the present invention.

[0116] Specifically, the storage medium and the processor are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more signal lines. The storage medium stores computer-executable instructions that implement data access control methods, including at least one software functional module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software program and module stored in the storage medium. The storage medium can be, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The storage medium stores the program, and the processor executes the program after receiving the execution instructions.

[0117] Furthermore, the software programs and modules within the aforementioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip with signal processing capabilities. The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc., which can implement or execute the methods, steps, and logic flowcharts disclosed in this embodiment. The general-purpose processor may be a microprocessor or any conventional processor.

[0118] Since the instructions stored in the storage medium can execute the steps in any of the methods provided in the embodiments of the present invention, the beneficial effects of any of the methods provided in the embodiments of the present invention can be achieved, as detailed in the preceding embodiments, and will not be repeated here.

[0119] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for detecting the lifespan of sensitive components, applied to a system for detecting the lifespan of sensitive components, characterized in that, The method includes: When the sensitive components leave the factory, record the UTC time of the sensitive components and the initial performance data at the time of leaving the factory; Based on a preset timed monitoring cycle, the current UTC time and the average performance data of the sensitive components during the timed monitoring cycle are obtained at the end of each timed monitoring cycle. Adjust the weighting coefficients corresponding to different timed monitoring cycles based on environmental data and load parameters of sensitive components; The average performance data is weighted and summed according to the weighting coefficients to obtain the total integral value; When the total integral value is detected to be greater than or equal to a preset integral threshold, or when the variable value of the average performance data exceeds a preset amplitude threshold, an alarm message indicating that the lifespan has reached its limit is triggered.

2. The method according to claim 1, characterized in that, The step of obtaining the current UTC time and the average performance data of the sensitive component within the timed monitoring period at the end of each preset timed monitoring period specifically includes: Within each of the timed monitoring cycles, performance data of the sensitive components are collected at preset time intervals, and the performance data includes multiple parameter indicators; Calculate the parameter-weighted sum of the performance data based on the preset weight corresponding to each parameter indicator; The average value of the weighted sum of multiple parameters within the timed monitoring period is determined as the average performance data within the timed monitoring period.

3. The method according to claim 1, characterized in that, The step of adjusting the weighting coefficients corresponding to different timed monitoring cycles based on environmental data and load parameters of sensitive components specifically includes: Obtain environmental data and sensitive component load parameters corresponding to different timed monitoring cycles; The environmental data and the load parameters of the sensitive components are input into the machine learning model, and the performance prediction values ​​of the sensitive components corresponding to different timed monitoring cycles are output. Based on the performance prediction value, assign weight coefficients corresponding to different timed monitoring periods.

4. The method according to claim 3, characterized in that, Before the step of obtaining environmental data and sensitive component load parameters corresponding to different timed monitoring cycles, the method further includes: A training dataset is constructed based on historical sensitive component data, which includes historical environmental data, historical sensitive component load parameters, and historical performance data. The machine learning model is trained using the training dataset, so that the machine learning model outputs the performance prediction value of the sensitive components based on the input historical environmental data and historical load parameters of the sensitive components.

5. The method according to claim 1, characterized in that, After the step of obtaining the current UTC time and the average performance data of the sensitive component within the timed monitoring period at the end of each preset timed monitoring period, the method further includes: The performance degradation trend of the sensitive component is determined based on the initial performance data and the average performance data; The lifespan of the sensitive components is predicted based on the performance degradation trend. An alarm message indicating that the lifespan has reached its limit is triggered when the lifespan duration is detected to be less than a preset duration threshold.

6. The method according to claim 5, characterized in that, Before the step of predicting the lifespan of the sensitive component based on the performance degradation trend, the method further includes: The size of the timed monitoring cycle is adjusted according to the lifespan duration, and the size of the timed monitoring cycle is positively correlated with the lifespan duration.

7. The method according to claim 1, characterized in that, The step of triggering an alarm message indicating that the lifespan has reached its limit when the total integral value is detected to be greater than or equal to a preset integral threshold, or when the variable value of the average performance data exceeds a preset amplitude threshold, specifically includes: Multiple preset integration ranges and preset amplitude ranges are set, and different preset integration ranges or different preset amplitude ranges correspond to different levels of alarm information. The first alarm information and the second alarm information are determined based on the preset integration range of the total integration value and the preset amplitude range of the average performance data, respectively. The warning will be issued using the highest-level alarm information among the first and second alarm information.

8. A lifespan detection system for sensitive components, characterized in that, The system includes: one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are run on the sensitive component lifetime detection system, the system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on a sensitive component life testing system, the system performs the method as described in any one of claims 1-7.

Images