Civil aviation measuring instrument monitoring and prediction maintenance system and method based on edge intelligence

Abstract

The invention discloses a civil aviation measuring instrument monitoring and prediction maintenance system and method based on edge intelligence, and relates to the technical field of civil aviation measuring instrument maintenance management, and the system comprises a data collection unit, a degradation prediction unit, an attenuation recognition unit, an evaluation grading unit, and an adjustment output unit. The data acquisition unit is used for bidirectionally connecting an edge computing node deployed at a nearby position of a civil aviation measuring instrument in a low-delay wireless communication mode, establishing a bidirectional data interaction channel with a cloud server through an encrypted wireless communication link, acquiring and processing real-time operation data of the civil aviation measuring instrument, and sending the real-time operation data to the degradation prediction unit; a maintenance plan can be made in advance, preventive maintenance can be carried out before the civil aviation measuring instrument breaks down, losses such as high cost and flight delay caused by post-maintenance are avoided, the overall cost of civil aviation operation is reduced, meanwhile, targeted maintenance measures can be taken according to different risk levels, and the service life of the civil aviation measuring instrument is prolonged.

Description

Technical Field

[0001] This invention relates to the field of civil aviation metrology instrument maintenance and management technology, specifically to a civil aviation metrology instrument monitoring and predictive maintenance system and method based on edge intelligence. Background Technology

[0002] In the field of civil aviation metrology instrument maintenance and management technology, the normal operation of civil aviation metrology instruments plays a vital role in ensuring flight safety and improving operational efficiency. Currently, the monitoring and maintenance of civil aviation metrology instruments mainly rely on traditional methods. In terms of maintenance decision-making, traditional methods are mainly based on experience and judgment, which makes it difficult to identify the key points of performance degradation of civil aviation metrology instruments. At the same time, there is a lack of scientific prediction of the performance degradation trend of metrology instruments. Often, repairs or replacements are only carried out after the metrology instruments have obvious failures. This reactive maintenance model not only increases maintenance costs, but may also lead to serious consequences such as flight delays due to equipment failures, affecting the normal order of civil aviation operations.

[0003] Therefore, in view of this, the present invention proposes a civil aviation metrology instrument monitoring and predictive maintenance system and method based on edge intelligence to make up for and improve the shortcomings of the prior art. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a civil aviation metrology instrument monitoring and predictive maintenance system and method based on edge intelligence, thereby resolving the corresponding technical issues raised in the background section.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is: a civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence, including a data acquisition unit, a degradation prediction unit, an attenuation identification unit, an evaluation and grading unit, and an adjustment output unit; The data acquisition unit is used to connect bidirectionally to the edge computing node deployed near the civil aviation metrology instrument via low-latency wireless communication, and at the same time establish a bidirectional data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instrument and send it to the degradation prediction unit. The degradation prediction unit is used to acquire the real-time operating data of the processed civil aviation metrology instruments. At the same time, it retrieves the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, a lightweight prediction model is constructed and trained using the support vector machine algorithm. The real-time operating data is input into the trained lightweight prediction model for prediction. The model calculates and outputs the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods to determine the performance change law of the civil aviation metrology instruments. The prediction results are then sent to the degradation identification unit. The attenuation identification unit is used to obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of the civil aviation metrology instrument parameter by parameter. Based on the comparison results and combined with the preset performance attenuation key node judgment rules, the key nodes of the performance attenuation of the civil aviation metrology instrument are identified, and the core node judgment is performed. The key node identification results and the core node judgment results are sent to the evaluation and grading unit. The assessment and grading unit is used to obtain the key node identification results and core node judgment results. Combining the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments, it constructs a performance evaluation index system, calculates the current performance evaluation score of civil aviation metrology instruments through the analytic hierarchy process, and grades the operational risks of civil aviation metrology instruments according to the preset risk grading rules, determines the risk impact range corresponding to different risk levels, and makes judgments on maintenance measures to be taken. The judgment results of maintenance measures to be taken are then sent to the adjustment output unit. The adjustment output unit is used to obtain the judgment result of maintenance measures, generate corresponding adjustment instructions according to the preset maintenance strategy rules, combined with the location and type of key nodes, and send them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, the adjustment instructions are backed up to the cloud server for subsequent maintenance traceability.

[0006] As a preferred option, In the data acquisition unit, The real-time operating data is acquired in real time through a sensor group deployed on civil aviation metrology equipment. The real-time operating data includes vibration data, temperature data, pressure data, and electrical parameter data. The sensor group includes vibration sensors, temperature sensors, pressure sensors, and electrical parameter sensors. The vibration sensor is used to acquire vibration data of civil aviation measuring instruments; The temperature sensor is used to acquire temperature data from civil aviation measuring instruments. The pressure sensor is used to acquire pressure data from civil aviation measuring instruments. The electrical parameter sensor is used to acquire electrical parameter data of civil aviation measuring instruments.

[0007] As a preferred method, the specific process of calculating and outputting the performance degradation trend curve and degradation parameters of civil aviation metrology instruments over future time periods to determine the performance change patterns of civil aviation metrology instruments is as follows: S101. Obtain the real-time operating data of the processed civil aviation metrology instruments, and at the same time retrieve the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server, and integrate them into a historical dataset. S102. A lightweight performance degradation prediction model is constructed using the support vector machine algorithm. The historical dataset is divided into a training set and a test set in an 8:2 ratio. The constructed lightweight performance degradation prediction model is trained using the training set. The model performance is optimized by adjusting the parameters of the lightweight performance degradation prediction model. During the training process, the generalization ability of the lightweight performance degradation prediction model is evaluated using cross-validation. The optimal parameter combination is selected. The lightweight performance degradation prediction model is tested using the test set. S103. After training, the real-time operating data is input into the lightweight performance degradation prediction model to calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instrument over a future time period, in order to determine the performance change law of the civil aviation metrology instrument. The formula is as follows: ; Where m is the number of prediction time points; It is a predicted time point; It is a prediction curve of a certain item in the real-time running data within a future time period; r is the average degradation rate of a certain item in the real-time running data over a future time period.

[0008] As a preferred option, In the attenuation identification unit, The preset performance degradation key node judgment rules are formulated based on civil aviation metrology instrument industry standards, manufacturer technical parameters, and historical fault data, and clearly define the degradation critical values ​​corresponding to different performance parameters.

[0009] As a preferred approach, the specific process for identifying key points of performance degradation in civil aviation metrology instruments and simultaneously determining core points is as follows: S201. Based on the design parameters and operating specifications of civil aviation measuring instruments, preset the standard performance parameter ranges for each performance parameter. The system compares the performance parameter values ​​at each time point on the performance degradation trend curve with the preset standard performance parameter range parameter by parameter. Based on the comparison results and the preset key performance degradation node judgment rules, it identifies the key nodes of performance degradation of civil aviation metrology instruments. When the key node judgment conditions are met, the specific time when the key node is reached is recorded. and actual values ​​of performance parameters; S202. Based on the preset performance degradation key node judgment rules, and combined with the key node identification results, the core node is judged. The core node refers to the node that has the greatest and most critical impact on the performance of civil aviation measuring instruments. When the actual value of the performance parameter of the key node reaches the preset maximum allowable value, the key node is judged as the core node.

[0010] As a preferred method, the specific process for calculating the current performance evaluation score of civil aviation metrology instruments using the analytic hierarchy process is as follows: S301. Construct a performance evaluation index system by combining the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments. The performance evaluation index system includes performance parameter indexes, service life indexes, and historical failure frequency indexes. S302. Divide the performance evaluation index system into target layer, criterion layer and index layer, and construct a judgment matrix. ,in, This indicates the importance of indicator i relative to indicator j, satisfying the following condition: , , ; S303. Calculate the largest eigenvalue of the judgment matrix using the eigenvalue method. And its corresponding feature vector W, after normalizing the feature vector W, the weight vector of each index is obtained. ,in, It is the weight of the i-th indicator; S304. Quantify each indicator in the indicator layer. Based on the indicator weight vector and the quantified indicator values, calculate the current performance evaluation score S of the civil aviation metrology instrument. The formula is as follows: ; in, is the quantified value of the i-th indicator, and n is the number of indicators.

[0011] As a preferred approach, the operational risks of civil aviation metrology instruments are classified, the risk impact range corresponding to different risk levels is determined, and the specific process for judging maintenance measures is as follows: S401. Obtain the current performance evaluation score S of the civil aviation metrology instrument, and classify the operational risk of the civil aviation metrology instrument according to the preset risk classification rules as follows: like If so, it is judged as low risk; like If so, it is judged as medium risk; like If so, it is judged as high risk; in, , , , All are preset risk classification thresholds; S402. Based on the operational risk classification results of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and simultaneously make the following judgments regarding maintenance measures: When the risk is low, the scope of the impact is determined to be the measurement accuracy of the civil aviation metrology instruments themselves, and measures such as regular inspection and maintenance are taken. When the risk level is medium, the scope of impact is determined to be the operation of civil aviation equipment related to civil aviation metrology instruments. At the same time, civil aviation metrology instruments are fully calibrated and vulnerable parts are replaced. In cases of high risk, if the impact is determined to be a serious malfunction of civil aviation equipment related to civil aviation metrology instruments, the use of the civil aviation metrology instruments should be stopped immediately, and emergency replacement and comprehensive overhaul should be carried out.

[0012] As a preferred option, In the adjusted output unit, The preset maintenance strategy rules correspond one-to-one with the risk level, and are formulated in combination with the type of civil aviation metrology instrument and the type of key node, clarifying the maintenance methods corresponding to different risk levels and different attenuation types; The adjustment instructions include maintenance instructions, calibration instructions, and replacement instructions; The preset encrypted communication method is adapted to the data security requirements of various civil aviation industries.

[0013] A method for monitoring and predictive maintenance of civil aviation metrology instruments based on edge intelligence includes the following steps: Step 1: Connect the edge computing node deployed near the civil aviation metrology instrument via low-latency wireless communication in both directions, and establish a two-way data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instrument. Step 2: Obtain the real-time operating data of the processed civil aviation metrology instruments. At the same time, obtain the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, construct and train a lightweight prediction model using the support vector machine algorithm. Input the real-time operating data into the trained lightweight prediction model for prediction, calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods, so as to determine the performance change law of the civil aviation metrology instruments. Step 3: Obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of civil aviation metrology instruments parameter by parameter. Based on the comparison results and combined with the preset key node judgment rules for performance degradation, identify the key nodes of performance degradation of civil aviation metrology instruments and make judgments on core nodes. Step 4: Obtain the key node identification results and core node judgment results. Combine the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments to construct a performance evaluation index system. Calculate the current performance evaluation score of civil aviation metrology instruments through the analytic hierarchy process. According to the preset risk classification rules, classify the operational risks of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and make judgments on maintenance measures. Step 5: Obtain the judgment result of maintenance measures. Based on the preset maintenance strategy rules and the location and type of key nodes, generate the corresponding adjustment instructions and send them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, back up the adjustment instructions to the cloud server for subsequent maintenance traceability.

[0014] Compared with existing technologies, the beneficial effects of this invention are as follows: By collecting and processing real-time operational data of civil aviation metrology instruments, historical operational data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments are obtained. A lightweight prediction model is constructed and trained using a support vector machine algorithm to calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments over future time periods. This determines the performance change pattern of the civil aviation metrology instruments, identifies key nodes in the performance degradation of the instruments, and simultaneously judges core nodes. A performance evaluation index system is constructed, and the current performance evaluation score of the civil aviation metrology instruments is calculated. Based on preset risk classification rules, the operational risks of the civil aviation metrology instruments are classified, and the risks of non-compliance are determined. The system assesses the risk impact range corresponding to the risk level, assesses maintenance measures, generates corresponding adjustment instructions, and sends them to the management terminal of the civil aviation metrology instrument using a preset encrypted communication method. Simultaneously, the adjustment instructions are backed up to a cloud server for subsequent maintenance traceability. Through a scientific performance degradation prediction and assessment grading system, maintenance plans can be developed in advance, enabling preventative maintenance before civil aviation metrology instruments malfunction. This avoids the high costs and flight delays associated with post-failure repairs, reducing the overall cost of civil aviation operations. Furthermore, targeted maintenance measures based on different risk levels improve the accuracy and effectiveness of maintenance work and extend the service life of civil aviation metrology instruments. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the overall structure of a preferred embodiment of the present invention; Figure 2 This is a flowchart of the method shown in this invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Embodiments of the present invention: Please refer to Figures 1 to 2 As shown, the civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence includes a data acquisition unit, a degradation prediction unit, a decay identification unit, an evaluation and grading unit, and an adjustment output unit. The data acquisition unit is used to connect bidirectionally to the edge computing nodes deployed near the civil aviation metrology instruments via low-latency wireless communication. At the same time, it establishes a bidirectional data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instruments and send it to the degradation prediction unit. The degradation prediction unit is used to acquire real-time operating data of processed civil aviation metrology instruments. At the same time, it retrieves historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, a lightweight prediction model is constructed and trained using the support vector machine algorithm. The real-time operating data is input into the trained lightweight prediction model for prediction. The model calculates and outputs the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods to determine the performance change law of the civil aviation metrology instruments. The prediction results are then sent to the degradation identification unit. The attenuation identification unit is used to obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of the civil aviation metrology instrument parameter by parameter. Based on the comparison results and combined with the preset key node judgment rules for performance attenuation, the key nodes of performance attenuation of the civil aviation metrology instrument are identified, and the core node judgment is performed. The key node identification results and the core node judgment results are sent to the evaluation and grading unit. The assessment and grading unit is used to obtain the key node identification results and core node judgment results. Combining the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments, a performance evaluation index system is constructed. The current performance evaluation score of civil aviation metrology instruments is calculated through the analytic hierarchy process. According to the preset risk grading rules, the operational risks of civil aviation metrology instruments are graded, the risk impact range corresponding to different risk levels is determined, and the maintenance measures are judged. The results of the maintenance measures judgment are sent to the adjustment output unit. The adjustment output unit is used to obtain the judgment results of maintenance measures. Based on the preset maintenance strategy rules and the location and type of key nodes, it generates corresponding adjustment instructions and sends them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, the adjustment instructions are backed up to the cloud server for subsequent maintenance traceability.

[0018] In the data acquisition unit, Real-time operational data is acquired in real time through a sensor array deployed on civil aviation metrology equipment. The real-time operational data includes vibration data, temperature data, pressure data, and electrical parameter data. The sensor array includes vibration sensors, temperature sensors, pressure sensors, and electrical parameter sensors. Vibration sensors are used to acquire vibration data from civil aviation measuring instruments; Temperature sensors are used to acquire temperature data from civil aviation measuring instruments; Pressure sensors are used to acquire pressure data from civil aviation measuring instruments; Electrical parameter sensors are used to acquire electrical parameter data of civil aviation measuring instruments.

[0019] The specific process for calculating and outputting the performance degradation trend curve and degradation parameters of civil aviation metrology instruments over future time periods to determine the performance change patterns of civil aviation metrology instruments is as follows: S101. Obtain the real-time operating data of the processed civil aviation metrology instruments, and at the same time retrieve the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server, and integrate them into a historical dataset. S102. A lightweight performance degradation prediction model is constructed using the support vector machine algorithm. The historical dataset is divided into a training set and a test set in an 8:2 ratio. The constructed lightweight performance degradation prediction model is trained using the training set. The model performance is optimized by adjusting the parameters of the lightweight performance degradation prediction model. During the training process, the generalization ability of the lightweight performance degradation prediction model is evaluated using cross-validation. The optimal parameter combination is selected. The lightweight performance degradation prediction model is tested using the test set. S103. After training, the real-time operating data is input into the lightweight performance degradation prediction model to calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instrument over a future time period, in order to determine the performance change law of the civil aviation metrology instrument. The formula is as follows:

[0020] Where m is the number of prediction time points; It is a predicted time point; It is a prediction curve of a certain item in the real-time running data within a future time period; r is the average degradation rate of a certain item in the real-time running data over a future time period.

[0021] In the attenuation recognition unit, The pre-defined rules for judging key performance degradation nodes are based on civil aviation metrology industry standards, manufacturer technical parameters, and historical fault data, and clearly define the degradation threshold values ​​corresponding to different performance parameters.

[0022] The specific process for identifying key points of performance degradation in civil aviation metrology instruments and simultaneously determining core points is as follows: S201. Based on the design parameters and operating specifications of civil aviation measuring instruments, preset the standard performance parameter ranges for each performance parameter. The system compares the performance parameter values ​​at each time point on the performance degradation trend curve with the preset standard performance parameter range parameter by parameter. Based on the comparison results and the preset key performance degradation node judgment rules, it identifies the key nodes of performance degradation of civil aviation metrology instruments. When the key node judgment conditions are met, the specific time when the key node is reached is recorded. and actual values ​​of performance parameters; S202. Based on the preset performance degradation key node judgment rules, and combined with the key node identification results, the core node is judged. The core node refers to the node that has the greatest and most critical impact on the performance of civil aviation metrology instruments. When the actual value of the performance parameter of the key node reaches the preset maximum allowable value, the key node is judged as the core node.

[0023] The specific process of calculating the current performance evaluation score of civil aviation metrology instruments using the analytic hierarchy process is as follows: S301. Construct a performance evaluation index system based on the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments. The performance evaluation index system includes performance parameter indicators, service life indicators, and historical failure frequency indicators. S302. Divide the performance evaluation index system into target layer, criterion layer and index layer, and construct a judgment matrix. ,in, This indicates the importance of indicator i relative to indicator j, satisfying the following condition: , , ; S303. Calculate the largest eigenvalue of the judgment matrix using the eigenvalue method. And its corresponding feature vector W, after normalizing the feature vector W, the weight vector of each index is obtained. ,in, It is the weight of the i-th indicator; S304. Quantify each indicator in the indicator layer. Based on the indicator weight vector and the quantified indicator values, calculate the current performance evaluation score S of the civil aviation metrology instrument. The formula is as follows: ; in, is the quantified value of the i-th indicator, and n is the number of indicators.

[0024] The specific process for classifying the operational risks of civil aviation metrology instruments, determining the risk impact range corresponding to different risk levels, and making judgments on maintenance measures is as follows: S401. Obtain the current performance evaluation score S of the civil aviation metrology instrument, and classify the operational risk of the civil aviation metrology instrument according to the preset risk classification rules as follows: like If so, it is judged as low risk; like If so, it is judged as medium risk; like If so, it is judged as high risk; in, , , , All are preset risk classification thresholds; S402. Based on the operational risk classification results of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and simultaneously make the following judgments regarding maintenance measures: When the risk is low, the scope of the impact is determined to be the measurement accuracy of the civil aviation metrology instruments themselves, and measures such as regular inspection and maintenance are taken. When the risk level is medium, the scope of impact is determined to be the operation of civil aviation equipment related to civil aviation metrology instruments. At the same time, civil aviation metrology instruments are fully calibrated and vulnerable parts are replaced. In cases of high risk, if the impact is determined to be a serious malfunction of civil aviation equipment related to civil aviation metrology instruments, the use of the civil aviation metrology instruments should be stopped immediately, and emergency replacement and comprehensive overhaul should be carried out.

[0025] In adjusting the output unit The preset maintenance strategy rules correspond one-to-one with the risk level, and are formulated in combination with the types of civil aviation metrology instruments and key node types, clarifying the maintenance methods corresponding to different risk levels and different attenuation types; Adjustment instructions include maintenance instructions, calibration instructions, and replacement instructions; The preset encrypted communication method is adapted to the data security requirements of various civil aviation industries.

[0026] A method for monitoring and predictive maintenance of civil aviation metrology instruments based on edge intelligence includes the following steps: Step 1: Connect the edge computing node deployed near the civil aviation metrology instrument via low-latency wireless communication in both directions, and establish a two-way data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instrument. Step 2: Obtain the real-time operating data of the processed civil aviation metrology instruments. At the same time, obtain the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, construct and train a lightweight prediction model using the support vector machine algorithm. Input the real-time operating data into the trained lightweight prediction model for prediction, calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods, so as to determine the performance change law of the civil aviation metrology instruments. Step 3: Obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of civil aviation metrology instruments parameter by parameter. Based on the comparison results and combined with the preset key node judgment rules for performance degradation, identify the key nodes of performance degradation of civil aviation metrology instruments and make judgments on core nodes. Step 4: Obtain the key node identification results and core node judgment results. Combine the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments to construct a performance evaluation index system. Calculate the current performance evaluation score of civil aviation metrology instruments through the analytic hierarchy process. According to the preset risk classification rules, classify the operational risks of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and make judgments on maintenance measures. Step 5: Obtain the judgment result of maintenance measures. Based on the preset maintenance strategy rules and the location and type of key nodes, generate the corresponding adjustment instructions and send them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, back up the adjustment instructions to the cloud server for subsequent maintenance traceability.

[0027] By collecting and processing real-time operational data from civil aviation metrology instruments, historical operational data and corresponding performance degradation labels for the same batch of instruments are obtained. A lightweight prediction model is constructed and trained using a support vector machine algorithm to calculate and output the performance degradation trend curve and degradation parameters of the instruments over future time periods. This determines the performance change patterns of the instruments, identifies key nodes in performance degradation, and performs core node judgment. A performance evaluation index system is constructed, and the current performance evaluation score of the instruments is calculated. Based on preset risk classification rules, the operational risks of the instruments are classified, and the risks corresponding to different risk levels are determined. The system assesses the scope of risk impact, assesses maintenance measures, generates corresponding adjustment instructions, and sends them to the management terminal of the civil aviation metrology instrument using a pre-set encrypted communication method. Simultaneously, the adjustment instructions are backed up to a cloud server for future maintenance traceability. Through a scientific performance degradation prediction and assessment grading system, maintenance plans can be developed in advance, enabling preventative maintenance before civil aviation metrology instruments malfunction. This avoids the high costs and flight delays associated with post-failure repairs, reducing the overall cost of civil aviation operations. Furthermore, targeted maintenance measures can be implemented based on different risk levels, improving the accuracy and effectiveness of maintenance work and extending the service life of civil aviation metrology instruments.

[0028] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0029] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. In the two embodiments provided in this application, it should be understood that the disclosed apparatus and system can be implemented in other ways; for example, the apparatus embodiments described above are merely illustrative, and the division of modules is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; furthermore, the coupling or direct coupling or communication connection between the shown or discussed mutuals can be through some interfaces, and the indirect coupling or communication connection between the apparatus or modules can be electrical, mechanical or other forms. The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence, characterized in that, It includes a data acquisition unit, a degradation prediction unit, a decay identification unit, an evaluation and grading unit, and an output adjustment unit; The data acquisition unit is used to connect bidirectionally to the edge computing node deployed near the civil aviation metrology instrument via low-latency wireless communication, and at the same time establish a bidirectional data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instrument and send it to the degradation prediction unit. The degradation prediction unit is used to acquire the real-time operating data of the processed civil aviation metrology instruments. At the same time, it retrieves the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, a lightweight prediction model is constructed and trained using the support vector machine algorithm. The real-time operating data is input into the trained lightweight prediction model for prediction. The model calculates and outputs the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods to determine the performance change law of the civil aviation metrology instruments. The prediction results are then sent to the degradation identification unit. The attenuation identification unit is used to obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of the civil aviation metrology instrument parameter by parameter. Based on the comparison results and combined with the preset performance attenuation key node judgment rules, the key nodes of the performance attenuation of the civil aviation metrology instrument are identified, and the core node judgment is performed. The key node identification results and the core node judgment results are sent to the evaluation and grading unit. The assessment and grading unit is used to obtain the key node identification results and core node judgment results. Combining the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments, it constructs a performance evaluation index system, calculates the current performance evaluation score of civil aviation metrology instruments through the analytic hierarchy process, and grades the operational risks of civil aviation metrology instruments according to the preset risk grading rules, determines the risk impact range corresponding to different risk levels, and makes judgments on maintenance measures to be taken. The judgment results of maintenance measures to be taken are then sent to the adjustment output unit. The adjustment output unit is used to obtain the judgment result of maintenance measures, generate corresponding adjustment instructions according to the preset maintenance strategy rules, combined with the location and type of key nodes, and send them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, the adjustment instructions are backed up to the cloud server for subsequent maintenance traceability.

2. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 1, characterized in that, In the data acquisition unit, The real-time operating data is acquired in real time through a sensor group deployed on civil aviation metrology equipment. The real-time operating data includes vibration data, temperature data, pressure data, and electrical parameter data. The sensor group includes vibration sensors, temperature sensors, pressure sensors, and electrical parameter sensors. The vibration sensor is used to acquire vibration data of civil aviation measuring instruments; The temperature sensor is used to acquire temperature data from civil aviation measuring instruments. The pressure sensor is used to acquire pressure data from civil aviation measuring instruments. The electrical parameter sensor is used to acquire electrical parameter data of civil aviation measuring instruments.

3. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 2, characterized in that, The specific process for calculating and outputting the performance degradation trend curve and degradation parameters of civil aviation metrology instruments over future time periods to determine the performance change patterns of civil aviation metrology instruments is as follows: S101. Obtain the real-time operating data of the processed civil aviation metrology instruments, and at the same time retrieve the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server, and integrate them into a historical dataset. S102. A lightweight performance degradation prediction model is constructed using the support vector machine algorithm. The historical dataset is divided into a training set and a test set in an 8:2 ratio. The constructed lightweight performance degradation prediction model is trained using the training set. The model performance is optimized by adjusting the parameters of the lightweight performance degradation prediction model. During the training process, the generalization ability of the lightweight performance degradation prediction model is evaluated using cross-validation. The optimal parameter combination is selected. The lightweight performance degradation prediction model is tested using the test set. S103. After training, the real-time operating data is input into the lightweight performance degradation prediction model to calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instrument over a future time period, in order to determine the performance change law of the civil aviation metrology instrument. The formula is as follows: ； Where m is the number of prediction time points; It is a predicted time point; It is a prediction curve of a certain item in the real-time running data within a future time period; r is the average degradation rate of a certain item in the real-time running data over a future time period.

4. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 3, characterized in that, In the attenuation identification unit, The preset performance degradation key node judgment rules are formulated based on civil aviation metrology instrument industry standards, manufacturer technical parameters, and historical fault data, and clearly define the degradation critical values ​​corresponding to different performance parameters.

5. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 4, characterized in that, The specific process for identifying key points of performance degradation in civil aviation metrology instruments and simultaneously determining core points is as follows: S201. Based on the design parameters and operating specifications of civil aviation measuring instruments, preset the standard performance parameter ranges for each performance parameter. The system compares the performance parameter values ​​at each time point on the performance degradation trend curve with the preset standard performance parameter range parameter by parameter. Based on the comparison results and the preset key performance degradation node judgment rules, it identifies the key nodes of performance degradation of civil aviation metrology instruments. When the key node judgment conditions are met, the specific time when the key node is reached is recorded. and actual values ​​of performance parameters; S202. Based on the preset performance degradation key node judgment rules, and combined with the key node identification results, the core node is judged. The core node refers to the node that has the greatest and most critical impact on the performance of civil aviation measuring instruments. When the actual value of the performance parameter of the key node reaches the preset maximum allowable value, the key node is judged as the core node.

6. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 5, characterized in that, The specific process of calculating the current performance evaluation score of civil aviation metrology instruments using the analytic hierarchy process is as follows: S301. Construct a performance evaluation index system by combining the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments. The performance evaluation index system includes performance parameter indexes, service life indexes, and historical failure frequency indexes. S302. Divide the performance evaluation index system into target layer, criterion layer and index layer, and construct a judgment matrix. ,in, This indicates the importance of indicator i relative to indicator j, satisfying the following condition: , , ; S303. Calculate the largest eigenvalue of the judgment matrix using the eigenvalue method. And its corresponding feature vector W, after normalizing the feature vector W, the weight vector of each index is obtained. ,in, It is the weight of the i-th indicator; S304. Quantify each indicator in the indicator layer. Based on the indicator weight vector and the quantified indicator values, calculate the current performance evaluation score S of the civil aviation metrology instrument. The formula is as follows: ； in, is the quantified value of the i-th indicator, and n is the number of indicators.

7. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 6, characterized in that, The specific process for classifying the operational risks of civil aviation metrology instruments, determining the risk impact range corresponding to different risk levels, and making judgments on maintenance measures is as follows: S401. Obtain the current performance evaluation score S of the civil aviation metrology instrument, and classify the operational risk of the civil aviation metrology instrument according to the preset risk classification rules as follows: like If so, it is judged as low risk; like If so, it is judged as medium risk; like If so, it is judged as high risk; in, , , , All are preset risk classification thresholds; S402. Based on the operational risk classification results of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and simultaneously make the following judgments regarding maintenance measures: When the risk is low, the scope of the impact is determined to be the measurement accuracy of the civil aviation metrology instruments themselves, and measures such as regular inspection and maintenance are taken. When the risk level is medium, the scope of impact is determined to be the operation of civil aviation equipment related to civil aviation metrology instruments. At the same time, civil aviation metrology instruments are fully calibrated and vulnerable parts are replaced. In cases of high risk, if the impact is determined to be a serious malfunction of civil aviation equipment related to civil aviation metrology instruments, the use of the civil aviation metrology instruments should be stopped immediately, and emergency replacement and comprehensive overhaul should be carried out.

8. The civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence according to claim 7, characterized in that, In the adjusted output unit, The preset maintenance strategy rules correspond one-to-one with the risk level, and are formulated in combination with the type of civil aviation metrology instrument and the type of key node, clarifying the maintenance methods corresponding to different risk levels and different attenuation types; The adjustment instructions include maintenance instructions, calibration instructions, and replacement instructions; The preset encrypted communication method is adapted to the data security requirements of various civil aviation industries.

9. A method for monitoring and predictive maintenance of civil aviation metrology instruments based on edge intelligence, applied to the civil aviation metrology instrument monitoring and predictive maintenance system based on edge intelligence as described in any one of claims 1-8, characterized in that, Includes the following steps: Step 1: Connect the edge computing node deployed near the civil aviation metrology instrument via low-latency wireless communication in both directions, and establish a two-way data interaction channel with the cloud server through an encrypted wireless communication link to collect and process the real-time operating data of the civil aviation metrology instrument. Step 2: Obtain the real-time operating data of the processed civil aviation metrology instruments. At the same time, obtain the historical operating data and corresponding performance degradation labels of the same batch of civil aviation metrology instruments from the historical database associated with the cloud server. Based on the historical operating data and the corresponding performance degradation labels, construct and train a lightweight prediction model using the support vector machine algorithm. Input the real-time operating data into the trained lightweight prediction model for prediction, calculate and output the performance degradation trend curve and degradation parameters of the civil aviation metrology instruments for future time periods, so as to determine the performance change law of the civil aviation metrology instruments. Step 3: Obtain the prediction results and compare the performance degradation trend curve and degradation parameters in the prediction results with the preset standard performance parameter range of civil aviation metrology instruments parameter by parameter. Based on the comparison results and combined with the preset key node judgment rules for performance degradation, identify the key nodes of performance degradation of civil aviation metrology instruments and make judgments on core nodes. Step 4: Obtain the key node identification results and core node judgment results. Combine the usage scenarios, service life, and historical failure frequency of civil aviation metrology instruments to construct a performance evaluation index system. Calculate the current performance evaluation score of civil aviation metrology instruments through the analytic hierarchy process. According to the preset risk classification rules, classify the operational risks of civil aviation metrology instruments, determine the risk impact range corresponding to different risk levels, and make judgments on maintenance measures. Step 5: Obtain the judgment result of maintenance measures. Based on the preset maintenance strategy rules and the location and type of key nodes, generate the corresponding adjustment instructions and send them to the management terminal of civil aviation metrology instruments according to the preset encrypted communication method. At the same time, back up the adjustment instructions to the cloud server for subsequent maintenance traceability.

Images