A method and device for screening aging of electronic cabin of seeker
By automatically obtaining sensor data and using support vector machine algorithm to establish an aging model, the problems of low efficiency and poor accuracy of aging screening for the seeker electronic cabin are solved, and multi-faceted aging screening and abnormal detection are realized, which improves work efficiency and management level.
Patent Information
- Application Number
- CN202411035267.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-07-31
AI Technical Summary
In the prior art, the aging screening method for the electronic cabin of the seeker is inefficient and prone to missed inspection, resulting in inaccurate screening of aging.
By automatically obtaining sensor data, using the support vector machine algorithm to establish a temperature aging model and a seeker electronic cabin aging prediction model, perform data preprocessing and abnormal detection, capture temperature, resistance, humidity, current and other parameters in real time, and perform multi-faceted aging screening , and display the aging status through a visual interface.
The accuracy and efficiency of the aging screening of the seeker electronic cabin is improved, the management and maintenance process is simplified, important data support is provided, work efficiency and management level is improved, and potential aging problems can be discovered in a timely manner.
Smart Images

Figure CN118568580B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of electronic digital data processing, and in particular to a method and a device for aging screening of an electronic cabin of a seeker. Background Art
[0002] With the continuous development of modern seeker electronic cabin technology, its importance in various application fields has become increasingly prominent. As a core component of weapon systems such as missiles, aircraft, and rockets, the seeker electronic cabin undertakes key tasks such as precision guidance and target identification. However, long-term use and harsh environmental conditions may cause aging and performance degradation of the seeker electronic cabin, which in turn affects the reliability and combat effectiveness of the entire system. In order to ensure the long-term stable operation and efficient performance of the seeker electronic cabin, it is necessary to use advanced technical means to conduct comprehensive aging monitoring and screening. The traditional aging monitoring method is through manual sampling detection, which is inefficient and prone to missed detection. Therefore, it is of great significance to develop an automated and efficient aging screening device using modern information technology and data analysis methods.
[0003] Existing methods for aging screening of the seeker electronic compartment involve placing components in an environmental chamber through manual sampling testing, heating them to a set temperature, applying the required voltage for testing, or applying multiple electrical stimuli to the components at high temperature and pressure, activating more internal circuits, and monitoring outputs to evaluate reliability and infrared detection technology implementation.
[0004] For example, the invention patent with announcement number: CN108133085B announces a method and system for predicting the temperature of equipment in an electronic equipment cabin, including: based on the equipment type of the electronic equipment cabin, obtaining temperature variable data streams of various types corresponding to the equipment type, the temperature variable data streams including equipment temperature data streams; based on a sliding window with a preset data length, intercepting window data corresponding to each type of temperature variable data stream in each type of temperature variable data stream; using the window data corresponding to all types of temperature variable data streams as a training sample set to train the random vector function network RVFL to obtain an equipment temperature prediction model; sliding the sliding window in the equipment temperature data stream according to the preset data length, and calculating the predicted value of the equipment temperature contained in the sliding window based on the equipment temperature prediction model. The method provided by the present invention has a small error in predicting temperature and a high accuracy.
[0005] For example, the invention patent with announcement number CN108804719B announces a digital circuit aging simulation method and device, including: for each timing path of the digital circuit, obtaining the state information of each module in the timing path, the state information includes the input voltage conversion time, output load and signal probability when the digital circuit is actually running; calculating the aging sensitivity of each module based on the state information of each module; based on the aging sensitivity of each module, obtaining the parameter information of each module from the corresponding relationship between the stored aging sensitivity and parameter information; based on the parameter information of each module, determining the timing information of the timing path. Since the state information includes the signal probability, the signal probability is an important factor in determining the degree of aging in the actual operation of the circuit, and the signal probability is related to the specific structure of the digital circuit, therefore, the timing information determined according to the state information will be more in line with the actual situation of the digital circuit, and the simulation accuracy is improved.
[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:
[0007] In the prior art, the traditional aging monitoring method is through manual sampling detection, which is inefficient and prone to missed detection, and there is a problem of inaccurate aging screening of the seeker electronic cabin. Summary of the invention
[0008] The embodiments of the present application provide a method and device for aging screening of a seeker electronic cabin, thereby solving the problem of inaccurate aging screening of a seeker electronic cabin in the prior art and achieving aging screening of the seeker electronic cabin from multiple aspects.
[0009] The embodiment of the present application provides a method for screening the aging of the electronic cabin of the seeker, comprising the following steps: automatically obtaining the measurement data of the sensor through a test interface, using the measurement data and a calibration algorithm to eliminate noise interference and perform data preprocessing to obtain the preprocessed measurement data, wherein the preprocessed measurement data includes filter data and aging characteristic parameter data; dividing the preprocessed measurement data into a test set, a training set and a validation set; establishing a temperature aging model through the preprocessed measurement data; establishing a seeker electronic cabin aging prediction model for the preprocessed measurement data through a support vector machine algorithm, judging the aging state of the seeker electronic cabin and performing abnormality detection, and if the data is abnormal and If the trend changes abnormally, a warning is issued immediately; the predicted results of the aging prediction model of the seeker electronic cabin are recorded and compared with the actual results, the aging status of the seeker electronic cabin is presented to the user in a visual manner, and the aging status of the seeker electronic cabin is displayed through an interface, wherein the step of constructing a temperature aging model includes: dividing the temperature factor data in the aging characteristic parameters into a first test set, a first training set and a first verification set to establish a temperature aging model; analyzing the collected data through the temperature aging model, and after data processing and data testing, comparing and verifying the first aging value predicted by the temperature aging model with the actual aging status data, and adjusting the model according to the verification results.
[0010] Furthermore, the step of automatically obtaining the measurement data of the sensor through the test interface includes: sending a request to the sensor, filter startup data, and receiving response data from the sensor; the test interface is used to perform functional testing and performance testing according to test cases, update the interface document according to the test results, and record changes and repairs of the interface.
[0011] Furthermore, the step of obtaining the preprocessed measurement data includes: obtaining demand analysis data for data acquisition, and obtaining analog signals of sensors and filters according to the demand analysis data; converting the analog signals of sensors and filters into digital signals to obtain aging characteristic parameters and filter parameters, wherein the aging characteristic parameters include temperature, resistance, humidity and current, and the filter parameters include acquisition accuracy and frequency requirements; performing data acquisition testing and verification, and verifying the data acquisition accuracy by comparing actual measurement values with theoretical values, and performing real-time data transmission.
[0012] Furthermore, the mathematical formula for constructing the temperature aging model is:
[0013] ;
[0014] In the formula, Indicates the first aging value, which is used to reflect the influence of temperature factors on the aging degree of the electronic cabin. x represents the ambient temperature of the electronic cabin of the seeker. Indicates the thermal expansion coefficient of the seeker electronic cabin material, Indicates the variation of the ambient temperature of the seeker electronic cabin.
[0015] Furthermore, the step of establishing the aging prediction model of the seeker electronic compartment is: taking resistance, humidity and current as features, constructing a feature vector ,in represents the resistance value of the i-th sample, represents the humidity value of the i-th sample, represents the current value of the i-th sample, and converts the characteristics of the i-th sample to The corresponding aging status label Composition feature vector , n represents the aging state label The total number of ; Use feature vectors to train the SVM model, use cross-validation technology to select the best hyperparameters, adjust the hyperparameter C and the parameters of the kernel function until the model achieves optimal performance, and save the trained model and data results in the database.
[0016] Furthermore, the SVM model formula is:
[0017] ;
[0018] Where: is the weight vector, obtained by calculating the normal vector of the hyperplane, b is the bias term, is a slack variable used to deal with inseparable situations, C is a regularization parameter used to balance the penalty of interval maximization and misclassified samples, is the aging status label of sample i, is the eigenvector of sample i, Represents the weight vector Model.
[0019] Furthermore, the abnormality detection process is: collecting the first aging value calculated by the temperature aging model and the aging status label calculated by the aging prediction model of the seeker electronic cabin in real time, and evaluating the influence of temperature, resistance, humidity and current on the aging of the seeker electronic cabin; according to the abnormality detection strategy, triggering the alarm mechanism to notify the user by judging the abnormal data value of the seeker electronic cabin; setting the threshold of the aging alarm, and when the threshold is reached, triggering different alarm mechanisms according to different aging causes to alarm.
[0020] Furthermore, the visualization presentation method is: visually outputting the first aging value obtained by the temperature aging model and the aging status label calculated by the aging prediction model of the seeker electronic cabin, displaying the corresponding information type and content, including aging degree, degradation trend, and abnormal warning.
[0021] The embodiment of the present application provides a device for aging screening of a seeker electronic cabin, including a test interface module, a data processing module, a temperature aging model module, an aging prediction model module for the seeker electronic cabin and a result display module: the test interface module is used to automatically obtain the measurement data of the sensor through the test interface, and use the measurement data and the calibration algorithm to eliminate noise interference to perform data preprocessing to obtain the preprocessed measurement data, and the preprocessed measurement data includes filtering data and aging characteristic parameter data; the data processing module is used to divide the preprocessed measurement data into a test set, a training set and a validation set; the temperature aging model module is used to establish a temperature aging model through the preprocessed measurement data; the aging prediction model module for the seeker electronic cabin is used to establish a temperature aging model through the preprocessed measurement data through the support vector machine algorithm A seeker electronic cabin aging prediction model is established to determine the aging status of the seeker electronic cabin and perform abnormal detection. If abnormal data and abnormal trend changes are found, a warning is immediately issued; the result display module records the prediction results of the seeker electronic cabin aging prediction model and compares them with the actual results, presents the aging status of the seeker electronic cabin to the user in a visual manner, and displays the aging status of the seeker electronic cabin through an interface, wherein the step of constructing a temperature aging model includes: dividing the temperature factor data in the aging characteristic parameters into a first test set, a first training set and a first validation set to establish a temperature aging model; analyzing the collected data through the temperature aging model, and after data processing and data testing, comparing and verifying the first aging value predicted by the temperature aging model with the actual aging status data, and adjusting the model according to the verification result.
[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0023] 1. By capturing various parameter data of the seeker electronic cabin in real time and using support vector machine algorithm for data processing and analysis technology, a comprehensive evaluation of the temperature, resistance, humidity, and current of the seeker electronic cabin aging is performed, thereby realizing multi-faceted aging screening of the seeker electronic cabin, effectively solving the problem of inaccurate aging screening of the seeker electronic cabin in the prior art.
[0024] 2. Through the database module, the aging data of the seeker electronic cabin can be effectively stored and managed, and the temperature, resistance, humidity, and current parameters can be saved, thereby providing important data support for future analysis, research, and improvement.
[0025] 3. Through automated data collection, processing and analysis, as well as database storage and management functions, the entire management and maintenance process is simplified and optimized, thereby improving work efficiency and management level, and helping to better cope with complex and changing environments and task requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 A flow chart of a method for aging screening of a seeker electronic cabin provided in an embodiment of the present application;
[0027] Figure 2 An image of the aging prediction model of the seeker electronic cabin provided in an embodiment of the present application;
[0028] Figure 3 A diagram of a device for aging screening of a seeker electronic cabin provided in an embodiment of the present application. DETAILED DESCRIPTION
[0029] The embodiments of the present application solve the problem of inaccurate aging screening of the seeker electronic cabin in the prior art by providing a method and device for aging screening of the seeker electronic cabin. By constructing a temperature aging model and an aging prediction model for the seeker electronic cabin, multi-faceted aging screening of the seeker electronic cabin is achieved.
[0030] The technical solution in the embodiment of the present application is to solve the problem of inaccurate aging screening of the electronic cabin of the seeker, and the overall idea is as follows:
[0031] Five modules are set up for collaborative processing, including test interface module, data processing module, temperature aging model module, seeker electronic cabin aging prediction model module and result display module. The test interface module is set up as the basis of the whole device, connecting the seeker electronic cabin with various devices for electrical connection and data transmission, and connecting the seeker electronic cabin to the device through a specially designed interface; a data acquisition module is set up, using high-precision sensors to collect aging characteristic parameters of the seeker electronic cabin in real time. The aging characteristic parameters include temperature, resistance, humidity, and current. By closely matching the sensor with the test interface, data transmission is carried out, and filtering and calibration algorithms are used to eliminate noise interference for data preprocessing; the data processing module obtains the pre-processed data from the data acquisition module Process data and conduct in-depth analysis. The data processing module integrates a pre-built aging model, matches and analyzes the collected data through the support vector machine algorithm to determine the aging status of the seeker electronic cabin, establishes an aging prediction model for the seeker electronic cabin, predicts its future aging trend, adds anomaly detection function, and immediately issues a warning if data anomalies and trend changes are found; the result display module presents the processing results to the user in an intuitive manner, displays the aging status and performance evaluation information of the seeker electronic cabin through the interface, and provides data export and report generation functions, which are convenient for users to conduct subsequent analysis and archiving; the database module stores the aging status and aging characteristic parameters of the seeker electronic cabin in the database, achieving multi-faceted aging screening of the seeker electronic cabin.
[0032] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0033] like Figure 1 As shown, it is a flow chart of a method for aging screening of a seeker electronic cabin provided by an embodiment of the present application, the method is applied to a device for aging screening of a seeker electronic cabin, the method comprising the following steps: automatically obtaining measurement data of a sensor through a test interface, preprocessing the data by eliminating noise interference using the measurement data and a calibration algorithm, and obtaining preprocessed measurement data, the preprocessed measurement data comprising filter data and aging characteristic parameter data; dividing the preprocessed measurement data into a test set, a training set, and a validation set; establishing a temperature aging model through the preprocessed measurement data; establishing an aging prediction model for the seeker electronic cabin for the preprocessed measurement data through a support vector machine algorithm, judging the aging state of the seeker electronic cabin and performing anomaly detection, and immediately issuing a warning if data anomalies and trend changes are found to be abnormal; recording the prediction results of the seeker electronic cabin aging prediction model and comparing them with the actual results, presenting the aging state of the seeker electronic cabin to the user in a visual manner, and displaying the aging state of the seeker electronic cabin through an interface.
[0034] In this embodiment, accurate judgment and abnormality detection of the aging status of the seeker electronic cabin are achieved through multiple steps such as automatically acquiring sensor data, preprocessing data, and establishing an aging prediction model. The benefits of this method are mainly reflected in the following aspects: Automatically acquiring sensor data through the test interface and preprocessing it using the calibration algorithm can greatly improve the efficiency and accuracy of data acquisition, effectively eliminate noise interference, and provide a high-quality data basis for subsequent model building; in the data preprocessing stage, not only the temperature factor is considered, but also a variety of aging characteristic parameters such as resistance, humidity, and current, making the aging screening more comprehensive and accurate, and able to discover more potential aging problems; an aging prediction model for the seeker electronic cabin is established through the support vector machine (SVM) algorithm. The model can predict the future aging state based on historical data, which helps to timely discover the aging trend of the seeker electronic cabin and provide a scientific basis for maintenance and replacement; in the aging prediction process, once abnormal data or abnormal trend changes are found, the system can immediately issue a warning, which helps to quickly respond to and deal with potential problems and avoid failures of the seeker electronic cabin in actual use; the aging state of the seeker electronic cabin is displayed through the interface, so that users can intuitively understand the current status of the seeker electronic cabin, which not only improves the user experience, but also helps users better understand and evaluate the performance of the seeker electronic cabin.
[0035] Furthermore, the steps of automatically obtaining the measurement data of the sensor through the test interface include: sending a request to the sensor, filter startup data, and receiving response data from the sensor; the test interface is used to perform functional testing and performance testing according to test cases, update the interface document according to the test results, and record changes and repairs of the interface.
[0036] In this embodiment, the test interface automatically sends requests and receives data, so as to realize the rapid acquisition of the sensor data of the electronic cabin of the seeker. Compared with the traditional manual testing method, this method improves the test efficiency and shortens the test cycle; the test interface performs functional testing and performance testing according to the test case, and follows the predetermined test specifications and standards when obtaining sensor data, which helps to reduce human errors and improve the accuracy and reliability of the data; the test interface can not only update the interface document according to the test results, but also record the changes and repairs of the interface, which helps to maintain the real-time and accuracy of the interface document, and provides strong support for subsequent maintenance and optimization; functional testing and performance testing through the test interface can help to timely discover potential problems in the system and repair them. This preventive maintenance strategy can enhance the maintainability of the system and reduce the subsequent maintenance costs; the automation and standardization of the test interface can help to improve the efficiency and accuracy of the aging screening of the electronic cabin of the seeker, thereby improving the user experience. Users can understand the aging status of the electronic cabin of the seeker in real time through the visual interface to provide support for decision-making.
[0037] Furthermore, the step of obtaining the preprocessed measurement data includes: obtaining demand analysis data for data acquisition, and obtaining analog signals of sensors and filters according to the demand analysis data; converting the analog signals of sensors and filters into digital signals to obtain aging characteristic parameters and filter parameters, wherein the aging characteristic parameters include temperature, resistance, humidity and current, and the filter parameters include acquisition accuracy and frequency requirements; performing data acquisition testing and verification, and verifying the data acquisition accuracy by comparing the actual measurement value with the theoretical value, and performing real-time transmission of data.
[0038] In this embodiment, by obtaining demand analysis data, data redundancy and invalid collection can be avoided, which not only improves work efficiency but also reduces the cost of data processing and storage; converting the analog signals of sensors and filters into digital signals can ensure the accuracy and reliability of data. At the same time, by obtaining aging characteristic parameters and filter parameters, the working status of the seeker electronic cabin can be more comprehensively understood, providing accurate data support for subsequent aging prediction and abnormality detection. The data acquisition test and verification process verifies the accuracy of data acquisition by comparing actual measurement values with theoretical values, and realizes real-time transmission of data, ensuring the timeliness and effectiveness of aging screening of the seeker electronic cabin, and helping to timely discover and deal with potential problems; by obtaining and processing the sensor measurement data of the seeker electronic cabin, its working status and aging trend can be fully understood.
[0039] Furthermore, the step of constructing a temperature aging model includes: dividing the temperature factor data in the aging characteristic parameters into a first test set, a first training set and a first validation set to construct a temperature aging model; analyzing the collected data through the temperature aging model, and after data processing and data testing, comparing and verifying the first aging value predicted by the model with the actual aging status data, and adjusting the model according to the verification results.
[0040] In this embodiment, by constructing a temperature aging model, the aging trend of the seeker electronic cabin under different temperature environments can be accurately predicted, which helps to formulate a targeted maintenance plan to avoid performance degradation or failure under extreme temperature conditions; temperature is one of the important factors affecting the aging of the seeker electronic cabin. Through a special temperature aging model, the aging state of the seeker electronic cabin can be more accurately evaluated, and the accuracy and reliability of aging screening can be improved. Based on the prediction results of the temperature aging model, resource allocation can be optimized, such as preparing replacement parts in advance, adjusting maintenance cycles, etc. This helps to reduce maintenance costs and improve resource utilization efficiency. Through the verification and adjustment of the temperature aging model, it can be ensured that the seeker electronic cabin can still maintain stable performance when the temperature changes. This enhances the reliability of the system and reduces the risk of failure caused by temperature changes. This is not only used for current aging screening, but also as a tool for long-term performance monitoring. By regularly updating the model data, the aging state of the seeker electronic cabin can be continuously tracked to provide data support for long-term maintenance.
[0041] Furthermore, the mathematical formula of the temperature aging model is constructed:
[0042] ;
[0043] In the formula, Indicates the first aging value, which is used to reflect the influence of temperature factors on the aging degree of the electronic cabin. x represents the ambient temperature of the electronic cabin of the seeker. Indicates the thermal expansion coefficient of the seeker electronic cabin material, Indicates the variation of the ambient temperature of the seeker electronic cabin.
[0044] In this embodiment, if Figure 2 As shown in the figure, it is the training result diagram of the aging prediction model of the electronic compartment of the seeker. Each small circle in the image represents a data point. Their positions on the X-axis and Y-axis represent the characteristic value of each sample. The data points are randomly distributed in different positions, indicating the randomness and diversity of the characteristics of the samples. The oblique lines on the X-axis and Y-axis represent hyperplanes, which are used to separate data points of different categories. The direction of the oblique line is positively correlated with the weight vector W, and the position of the oblique line is positively correlated with the bias term b. The inseparable situation in the image is handled by the relaxation variable ξ, that is, some data points are allowed to be on the wrong side of the decision boundary, which is manifested in the image as data points close to and across the oblique line. It can be obtained by defining the thermal expansion coefficient and also by thermal experiments. It can be obtained by calculating the temperature difference at different times, or by calculating historical data. It can also be obtained by calculating the chemical reaction rate under the influence of temperature through the Arrhenius equation.
[0045] Furthermore, the steps of establishing the aging prediction model of the seeker electronic compartment are as follows: taking resistance, humidity and current as features, constructing a feature vector ,in represents the resistance value of the i-th sample, represents the humidity value of the i-th sample, represents the current value of the i-th sample, and converts the characteristics of the i-th sample to The corresponding aging status label Composition feature vector , n represents the aging state label The total number of ; Use feature vectors to train the SVM model, use cross-validation technology to select the best hyperparameters, adjust the hyperparameter C and the parameters of the kernel function until the model achieves optimal performance, and save the trained model and data results in the database.
[0046] In this embodiment, by using the SVM algorithm to construct the aging prediction model of the seeker electronic compartment, the nonlinear relationship in the aging process of the seeker electronic compartment can be captured more accurately. The SVM algorithm can also adapt well to new and unseen data, enhancing the practicality and long-term effectiveness of the model. The model not only takes into account resistance, humidity and current, but also fuses these features together by constructing feature vectors. This multi-feature fusion method can more comprehensively reflect the aging state of the seeker electronic compartment and improve the comprehensiveness and accuracy of the prediction. By real-time monitoring of the aging state of the seeker electronic compartment and predicting its future aging trend, maintenance personnel can promptly discover potential problems and take preventive maintenance measures, which helps to avoid failures of the seeker electronic compartment at critical moments and ensure the stable operation of the system. Through accurate aging prediction and preventive maintenance, unnecessary downtime and high maintenance costs can be avoided. It helps to reduce the maintenance cost of the seeker electronic compartment and improve the overall economic benefits.
[0047] Furthermore, the SVM model formula is:
[0048] ;
[0049] Where: is the weight vector, obtained by calculating the normal vector of the hyperplane, b is the bias term, is a slack variable used to deal with inseparable situations, C is a regularization parameter used to balance the penalty of interval maximization and misclassified samples, is the aging status label of sample i, is the eigenvector of sample i, Represents the weight vector The model, Represents the category label of sample i. If sample i belongs to the positive class, then =1, if sample i belongs to the negative class, then = -1, Indicates that sample i is in the hyperplane The function value on is the distance from the sample to the hyperplane. Represents the function interval The gap between the geometric interval and the hyperplane is the distance between the sample and the hyperplane. The gap is maximized as much as possible. Therefore, is the constraint condition for each sample i, which means that for each sample i, its function interval Should be at least equal to 1 minus the corresponding slack variable , if sample i is correctly classified and on the interval boundary, that is, the function interval is 1, then Should be 0; if sample i is correctly classified but lies between the interval boundary and the separating hyperplane, that is, the function interval is less than 1, then Should be a value greater than 0. Represents the slack variable for all samples Penalize, where C is a regularization parameter, which is used to balance the maximization of the interval and the penalty for misclassification. This part is the penalty for misclassification, which makes the model more inclined to choose a larger interval at the expense of some misclassification.
[0050] In this embodiment, the aging feature label Relevant aging label elements can also be obtained through big data analysis technology and obtained by averaging. The function interval is obtained by calculating the distance between the hyperplane and the relative position of the coordinates of the two category labels. The slack variable can be calculated through the function interval and can also be obtained by obtaining the empirical data of the SVM algorithm and calculating the median.
[0051] The aging prediction table of the seeker electronic cabin is shown in Table 1:
[0052] Table 1 Aging prediction table of the seeker electronic compartment
[0053]
[0054] By real-time monitoring and fault warning of the seeker electronic compartment, the system can promptly detect and deal with potential safety hazards and reduce the probability of accidents. This is crucial to ensure the safe operation of equipment and the safety of personnel. Based on the data and analysis results provided by the remote monitoring and fault warning system, managers can formulate maintenance plans more accurately to avoid unnecessary downtime and waste of resources. This helps to reduce maintenance costs and improve the operating efficiency of equipment. Through the remote monitoring and fault warning system, users can understand the operating status and maintenance of the seeker electronic compartment at any time, which helps to improve user satisfaction and trust.
[0055] Furthermore, the abnormality detection process is as follows: the first aging value calculated by the temperature aging model and the aging status label calculated by the seeker electronic cabin aging prediction model are collected in real time to evaluate the influence of temperature, resistance, humidity and current on the aging of the seeker electronic cabin; according to the abnormality detection strategy, the abnormal data value of the seeker electronic cabin is judged to trigger the alarm mechanism to notify the user; the threshold of the aging alarm is set, and when the threshold is reached, different alarm mechanisms are triggered according to different aging causes to alarm.
[0056] In this embodiment, the alarm mechanism is tested and verified to simulate various aging conditions to ensure that the alarm mechanism can trigger the alarm accurately and promptly. The alarm threshold and alarm mode are adjusted according to the test results. Finally, the alarm mechanism is integrated into the entire aging screening device and coordinated with other modules to ensure the normal operation of the system.
[0057] Furthermore, the visualization presentation method is: visually output the first aging value obtained by the temperature aging model and the aging status label calculated by the aging prediction model of the seeker electronic cabin, and display the corresponding information type and content, including aging degree, degradation trend, and abnormal warning.
[0058] In this embodiment, the advantage of this formula over the traditional SVM algorithm is that it allows misclassification to occur to a certain extent by finding a hyperplane that can completely separate the two categories, and introduces a slack variable To deal with misclassification, by adjusting the regularization control to the degree of penalty for misclassified samples, the model is made robust to noise and outliers in the training data, avoiding overfitting of the model and thus improving the generalization ability of the model.
[0059] like Figure 3 As shown, it is a structural diagram of a device for screening aging of an electronic cabin of a seeker provided in an embodiment of the present application. The device for screening aging of an electronic cabin of a seeker provided in an embodiment of the present application comprises: a test interface module, a data processing module, a temperature aging model module, an aging prediction model module for the electronic cabin of a seeker and a result display module. The test interface module is used to automatically obtain the measurement data of the sensor through the test interface, and to preprocess the data by eliminating noise interference using the measurement data and the calibration algorithm to obtain the preprocessed measurement data, wherein the preprocessed measurement data comprises filtering data and aging characteristic parameter data; the data processing module is used to divide the preprocessed measurement data into Test set, training set and validation set; Temperature aging model module: used to establish a temperature aging model through preprocessed measurement data; Seeker head electronic cabin aging prediction model module: used to establish a seeker head electronic cabin aging prediction model for preprocessed measurement data through the support vector machine algorithm, determine the aging status of the seeker head electronic cabin and perform anomaly detection, and immediately issue a warning if data anomalies and trend changes are found; Result display module: record the prediction results of the seeker head electronic cabin aging prediction model and compare them with the actual results, present the aging status of the seeker head electronic cabin to the user in a visual way, and display the aging status of the seeker head electronic cabin through the interface.
[0060] The technical solutions in the above-mentioned embodiments of the present application have at least the following technical effects or advantages: relative to a method and system for predicting the temperature of equipment in an electronic equipment cabin as disclosed in the invention patent announcement with publication number: CN108133085B, the embodiments of the present application capture the various parameter data of the seeker electronic cabin in real time and use the support vector machine algorithm for data processing and analysis technology, thereby comprehensively evaluating the temperature, resistance, humidity, and current of the aging of the seeker electronic cabin, thereby realizing multi-faceted aging screening of the seeker electronic cabin; relative to a method and device for simulating aging of a digital circuit as disclosed in the invention patent announcement with publication number: CN108804719B, the embodiments of the present application simplify and optimize the entire management and maintenance process through automated data collection, processing and analysis processes, as well as database storage and management functions, thereby realizing improved work efficiency and management level.
[0061] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0062] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0063] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0065] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0066] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for aging screening of a seeker electronic cabin, characterized in that: The following steps are involved: Automatically obtain the measurement data of the sensor through the test interface, use the measurement data and the calibration algorithm to eliminate noise interference and perform data preprocessing to obtain preprocessed measurement data, wherein the preprocessed measurement data includes filter data and aging characteristic parameter data; Divide the preprocessed measurement data into a test set, a training set, and a validation set; Establish a temperature aging model through preprocessed measurement data; The support vector machine algorithm is used to establish the aging prediction model of the seeker electronic cabin based on the preprocessed measurement data, to determine the aging status of the seeker electronic cabin and perform abnormal detection. If abnormal data and abnormal trend changes are found, a warning will be issued immediately. The prediction results of the seeker electronic cabin aging prediction model are recorded and compared with the actual results, and the aging status of the seeker electronic cabin is presented to the user in a visual way, and the aging status of the seeker electronic cabin is displayed through the interface; Wherein, the step of constructing a temperature aging model comprises: The temperature factor data in the aging characteristic parameters are divided into a first test set, a first training set and a first validation set to establish a temperature aging model; The collected data is analyzed by the temperature aging model. After data processing and data testing, the first aging value predicted by the temperature aging model is compared and verified with the actual aging state data, and the model is adjusted according to the verification results; Among them, the mathematical formula for constructing the temperature aging model is: ; In the formula, Indicates the first aging value, which is used to reflect the influence of temperature factors on the aging degree of the electronic cabin. x represents the ambient temperature of the electronic cabin of the seeker. Indicates the thermal expansion coefficient of the seeker electronic cabin material, Indicates the variation of the ambient temperature of the seeker electronic cabin; The steps of establishing the seeker electronic cabin aging prediction model are as follows: Use resistance, humidity and current as features to construct a feature vector ,in represents the resistance value of the i-th sample, represents the humidity value of the i-th sample, represents the current value of the i-th sample, and converts the characteristics of the i-th sample to The corresponding aging status label Composition feature vector , n represents the aging state label The total number of ; Use feature vectors to train the SVM model, use cross-validation techniques to select the best hyperparameters, adjust the hyperparameter C and kernel function parameters until the model achieves optimal performance, and save the trained model and data results in the database.
2. A method for screening aging of a seeker electronic cabin as claimed in claim 1, characterized in that: The step of automatically obtaining the measurement data of the sensor through the test interface includes: Send requests to sensors, filter activation data, and receive response data from sensors; The test interface is used to perform functional testing and performance testing according to test cases, update interface documents according to test results, and record changes and repairs to the interface.
3. A method for screening aging of a seeker electronic cabin as claimed in claim 1, characterized in that: The step of obtaining the pre-processed measurement data comprises: Obtain demand analysis data for data collection, and obtain analog signals of sensors and filters based on the demand analysis data; Converting analog signals of sensors and filters into digital signals to obtain aging characteristic parameters and filter parameters, wherein the aging characteristic parameters include temperature, resistance, humidity and current, and the filter parameters include acquisition accuracy and frequency requirements; Conduct data collection testing and verification, verify data collection accuracy and perform real-time data transmission by comparing actual measured values with theoretical values.
4. A method for screening aging of a seeker electronic cabin as claimed in claim 1, characterized in that: The SVM model formula is: ; Where: is the weight vector, obtained by calculating the normal vector of the hyperplane, b is the bias term, is a slack variable used to deal with inseparable situations, C is a regularization parameter used to balance the penalty of interval maximization and misclassified samples, is the aging status label of sample i, is the eigenvector of sample i, Represents the weight vector Model.
5. A method for screening aging of a seeker electronic cabin as claimed in claim 1, characterized in that: The anomaly detection process is as follows: The first aging value calculated by the temperature aging model and the aging status label calculated by the seeker electronic cabin aging prediction model are collected in real time to evaluate the influence of temperature, resistance, humidity and current on the aging of the seeker electronic cabin; According to the anomaly detection strategy, the abnormal data value of the seeker electronic cabin is judged to trigger the alarm mechanism to notify the user; Set the threshold for aging alarm. When the threshold is reached, different alarm mechanisms will be triggered according to different aging reasons.
6. A method for screening aging of a seeker electronic cabin as claimed in claim 1, characterized in that: The visualization presentation method is: The first aging value obtained by the temperature aging model and the aging status label calculated by the aging prediction model of the seeker electronic cabin are visualized and output to display the corresponding information type and content, including aging degree, degradation trend, and abnormal warning.
7. A device for screening the aging of the electronic cabin of a seeker, characterized in that: It includes test interface module, data processing module, temperature aging model module, seeker electronic compartment aging prediction model module and result display module: The test interface module is used to automatically obtain the measurement data of the sensor through the test interface, and to perform data preprocessing by eliminating noise interference using the measurement data and the calibration algorithm to obtain preprocessed measurement data, wherein the preprocessed measurement data includes filter data and aging characteristic parameter data; The data processing module is used to divide the preprocessed measurement data into a test set, a training set and a validation set; The temperature aging model module is used to establish a temperature aging model through preprocessed measurement data; The seeker electronic compartment aging prediction model module is used to establish a seeker electronic compartment aging prediction model for the preprocessed measurement data through a support vector machine algorithm, determine the aging state of the seeker electronic compartment and perform abnormality detection, and immediately issue a warning if abnormal data and abnormal trend changes are found; The result display module records the prediction results of the seeker electronic cabin aging prediction model and compares them with the actual results, presents the aging status of the seeker electronic cabin to the user in a visual manner, and displays the aging status of the seeker electronic cabin through an interface; Wherein, the step of constructing a temperature aging model comprises: The temperature factor data in the aging characteristic parameters are divided into a first test set, a first training set and a first validation set to establish a temperature aging model; The collected data is analyzed by the temperature aging model. After data processing and data testing, the first aging value predicted by the temperature aging model is compared and verified with the actual aging state data, and the model is adjusted according to the verification results; Among them, the mathematical formula for constructing the temperature aging model is: ; In the formula, Indicates the first aging value, which is used to reflect the influence of temperature factors on the aging degree of the electronic cabin. x represents the ambient temperature of the electronic cabin of the seeker. Indicates the thermal expansion coefficient of the seeker electronic cabin material, Indicates the variation of the ambient temperature of the seeker electronic cabin; The steps of establishing the seeker electronic cabin aging prediction model are as follows: Use resistance, humidity and current as features to construct a feature vector ,in represents the resistance value of the i-th sample, represents the humidity value of the i-th sample, represents the current value of the i-th sample, and converts the characteristics of the i-th sample to The corresponding aging status label Composition feature vector , n represents the aging state label The total number of ; Use feature vectors to train the SVM model, use cross-validation techniques to select the best hyperparameters, adjust the hyperparameter C and kernel function parameters until the model achieves optimal performance, and save the trained model and data results in the database.
