Secondary radar and collision avoidance system health management method, device, equipment and medium
By establishing a self-test detection tree and fault prediction mechanism, the problem of single health information of traditional secondary radar anti-collision system equipment is solved, and the advance monitoring and preventive maintenance of equipment failures is realized, and the system reliability and cost-effectiveness are improved.
Patent Information
- Application Number
- CN202111548969.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-17
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-12-17
AI Technical Summary
The health information of traditional secondary radar anti-collision system equipment is too single and discrete, and the fault conditions cannot be predicted, resulting in timely detection and maintenance under unattended conditions, which poses unpredictable risks.
By obtaining equipment self-test information, establishing a self-test detection tree, combining historical data and algorithm models, equipment status evaluation and fault prediction, providing troubleshooting plans and decision-making support, realizing early monitoring and preventive maintenance of equipment failures.
It improves the reliability of the system and equipment, changes the post-maintenance to the situational maintenance, reduces the cost of the system life cycle, and enhances the in-camera testing capability and status monitoring.
Smart Images

Figure CN114236484B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of secondary radar, and in particular to a health management method, device, equipment and medium for a secondary radar and an anti-collision system. Background Art
[0002] Secondary radar and anti-collision system are one of the important means to ensure aviation safety and airspace surveillance and control. Secondary radar system provides wide-area air target location and related identity attributes, and anti-collision system ensures that air targets have the ability to quickly escape and avoid collision. Conventional secondary radar system and anti-collision system both have certain equipment status self-check functions.
[0003] The equipment health information of traditional secondary radar collision avoidance systems is too single and discrete. It can only reflect the current equipment status and cannot predict possible faults. In addition, the equipment health information cannot provide troubleshooting solutions and fault location.
[0004] With the increasing demand for unmanned secondary radar and equipment status prediction of anti-collision systems, the current equipment self-test function can no longer meet these requirements. Real-time acquisition of self-test information of each device in the current system can reflect the working status of the current equipment to a certain extent. With long-term use, the status of the equipment cannot be predicted, resulting in sudden failures that cannot be discovered in advance. The unmanned secondary radar system and the anti-collision equipment in flight cannot provide timely equipment detection and maintenance, which will lead to unpredictable risks. Summary of the invention
[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a secondary radar and collision avoidance system health management method, device, equipment and medium, so that relevant personnel can obtain the health status of the equipment and possible failures or abnormal conditions in advance, so as to make detection and maintenance operations in advance to avoid risks and improve the reliability of the corresponding systems and equipment.
[0006] The object of the present invention is achieved through the following technical solutions:
[0007] A secondary radar and anti-collision system health management method, the system includes historical data, initially set node weights and fluctuation thresholds, the method includes:
[0008] Obtain the information required for the self-test of secondary radar equipment;
[0009] Perform equipment self-test according to the information required for the self-test of the secondary radar equipment and upload the self-test information;
[0010] receiving the self-check information and creating or updating a self-check detection tree according to the self-check information;
[0011] Evaluate and determine the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model;
[0012] The self-check detection tree includes self-check item detection values, self-check item estimated ranges and associations between self-check items, the node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
[0013] Further, performing equipment self-test according to the information required for the self-test of the secondary radar equipment and uploading the self-test information specifically includes:
[0014] Preprocessing the information required for the self-test of the secondary radar device;
[0015] Performing self-check information fusion on the pre-processed information, wherein the self-check information fusion includes eliminating abnormal values and determining the missing of self-check items;
[0016] The integrated self-inspection information is reported.
[0017] Further, the creating or updating the self-check detection tree according to the self-check information specifically includes:
[0018] If there is no self-check detection tree, a new self-check detection tree is created; if there is already a self-check detection tree, the existing self-check detection tree is updated;
[0019] The creating or updating of the self-check detection tree includes setting the self-check item detection value, the self-check item estimated range and the association relationship between the self-check items.
[0020] Furthermore, the status assessment specifically includes:
[0021] Update the initially set node weight according to the self-check item detection value fluctuation value and the fluctuation threshold value, wherein the self-check item detection value fluctuation value is a change value of the self-check item detection value compared with the historical detection value;
[0022] Update the evaluation specification according to the updated node weight, report the detection value of each self-check item and generate the self-check item status evaluation value, wherein the evaluation specification is composed of the node weight and the initially set health value;
[0023] Wherein, the updating of the initially set node weight according to the fluctuation value of the self-check item detection value and the fluctuation threshold value specifically includes:
[0024] If the fluctuation value of the self-check item detection value does not exceed the fluctuation threshold, the node weight remains unchanged;
[0025] If the fluctuation value of the self-check item detection value exceeds the fluctuation threshold, the node weight is adjusted according to the preset rules.
[0026] Furthermore, the system also includes an initially set fault rule tree, and the evaluation and determination also includes fault diagnosis, which specifically includes:
[0027] Update the self-check item detection value in the fault rule tree according to the historical data and the self-check detection tree;
[0028] Perform fault diagnosis according to the updated fault rule tree and the self-check item status evaluation value;
[0029] Among them, the fault rule tree includes basic fault judgment rules composed of the association relationship between the self-check items, intermediate fault judgment rules composed of the association relationship between multiple basic fault judgment rules, and top-level fault judgment rules composed of the association relationship between multiple intermediate fault judgment rules.
[0030] Furthermore, the evaluation and determination also includes fault prediction, which specifically includes:
[0031] The Apriori algorithm is used to mine the correlation between system faults and self-check items, which specifically includes the following sub-steps:
[0032] Search historical data layer by layer in a loop to complete the collection of training sample sets of fault events and self-check items;
[0033] Identify the types of fault events in the training sample set, extract the associations between self-check items through learning and training, and complete the update of system fault types and association rules;
[0034] According to the association rules and the current self-test information, forward reasoning of fault knowledge matching and reverse reasoning of rule matching are performed to confirm the current fault state and complete fault matching, thereby obtaining the fault prediction result.
[0035] Furthermore, the method also includes providing troubleshooting solutions and decision support based on the fault prediction results.
[0036] On the other hand, the present invention also provides a secondary radar and collision avoidance system management device, the device comprising:
[0037] An acquisition module is used to obtain information required for self-test of secondary radar equipment;
[0038] A self-test module, used to perform equipment self-test according to the information required for self-test of the secondary radar equipment and upload the self-test information;
[0039] A self-check tree module, used for receiving the self-check information and creating or updating a self-check detection tree according to the self-check information;
[0040] An evaluation module evaluates and determines the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model;
[0041] The self-check detection tree includes self-check item detection values, self-check item estimated ranges and associations between self-check items, the node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
[0042] Optionally, the self-check module performs device self-check according to the information required for the self-check of the secondary radar device and uploads the self-check information specifically including:
[0043] Preprocessing the information required for the self-test of the secondary radar device;
[0044] Performing self-check information fusion on the pre-processed information, wherein the self-check information fusion includes eliminating abnormal values and determining the missing of self-check items;
[0045] The integrated self-inspection information is reported.
[0046] Optionally, the self-check tree module creates or updates the self-check detection tree according to the self-check information, specifically comprising:
[0047] If there is no self-check detection tree, a new self-check detection tree is created; if there is already a self-check detection tree, the existing self-check detection tree is updated;
[0048] The creating or updating of the self-check detection tree includes setting the self-check item detection value, the self-check item estimated range and the association relationship between the self-check items.
[0049] Optionally, the status assessment performed by the assessment module specifically includes:
[0050] Update the initially set node weight according to the self-check item detection value fluctuation value and the fluctuation threshold value, wherein the self-check item detection value fluctuation value is a change value of the self-check item detection value compared with the historical detection value;
[0051] Update the evaluation specification according to the updated node weight, report the detection value of each self-check item and generate the self-check item status evaluation value, wherein the evaluation specification is composed of the node weight and the initially set health value;
[0052] Wherein, the updating of the initially set node weight according to the fluctuation value of the self-check item detection value and the fluctuation threshold value specifically includes:
[0053] If the fluctuation value of the self-check item detection value does not exceed the fluctuation threshold, the node weight remains unchanged;
[0054] If the fluctuation value of the self-check item detection value exceeds the fluctuation threshold, the node weight is adjusted according to the preset rules.
[0055] Optionally, the system further includes an initially set fault rule tree, and the evaluation module further includes fault diagnosis in performing evaluation and determination, and the fault diagnosis specifically includes:
[0056] Update the self-check item detection value in the fault rule tree according to the historical data and the self-check detection tree;
[0057] Perform fault diagnosis according to the updated fault rule tree and the self-check item status evaluation value;
[0058] Among them, the fault rule tree includes basic fault judgment rules composed of the association relationship between the self-check items, intermediate fault judgment rules composed of the association relationship between multiple basic fault judgment rules, and top-level fault judgment rules composed of the association relationship between multiple intermediate fault judgment rules.
[0059] Optionally, the evaluation module further includes fault prediction in performing evaluation and determination, and the fault prediction specifically includes:
[0060] The Apriori algorithm is used to mine the correlation between system faults and self-check items, which specifically includes the following sub-steps:
[0061] Search historical data layer by layer in a loop to complete the collection of training sample sets of fault events and self-check items;
[0062] Identify the types of fault events in the training sample set, extract the associations between self-check items through learning and training, and complete the update of system fault types and association rules;
[0063] According to the association rules and the current self-test information, forward reasoning of fault knowledge matching and reverse reasoning of rule matching are performed to confirm the current fault state and complete fault matching, thereby obtaining the fault prediction result.
[0064] Optionally, the device also includes providing troubleshooting solutions and decision support based on the fault prediction results.
[0065] On the other hand, the present invention also provides a computer device, comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement any one of the above-mentioned secondary radar and collision avoidance system health management methods.
[0066] On the other hand, the present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program is loaded and executed by a processor to implement any one of the above-mentioned secondary radar and collision avoidance system health management methods.
[0067] The beneficial effects of the present invention are:
[0068] Aiming at the deficiencies of the existing self-checking systems of secondary radar systems and anti-collision systems, the present invention combines the original single discrete self-checking items, associates and fuses the self-checking information, and establishes a self-checking detection tree; stores the historical self-checking information of the equipment, and completes the real-time update of the equipment self-checking detection tree, and has the ability to predict equipment failures; according to the results of the fault prediction, decision support for troubleshooting plans and steps is given. This solution can also monitor and predict system failures before they occur. Fault prediction and health management technology will transform post-maintenance or regular maintenance into condition-based maintenance, which is a further expansion of the in-machine testing capability and status monitoring technology. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] Figure 1 It is a flow chart of a secondary radar and anti-collision system health management method provided by an embodiment of the present invention;
[0070] Figure 2 It is a diagram of the secondary radar and collision avoidance system design model provided by an embodiment of the present invention;
[0071] Figure 3 Schematic diagram of the distribution of monitoring points of power modules of the secondary radar and anti-collision system according to an embodiment of the present invention;
[0072] Figure 4 is a business logic diagram of the health management layer of an embodiment of the present invention;
[0073] Figure 5 It is a business processing logic diagram of the self-checking data display of the embodiment of the present invention;
[0074] Figure 6 It is a logic diagram of the state assessment service processing of an embodiment of the present invention;
[0075] Figure 7 This is a schematic diagram of a basic model of a fault rule tree according to an embodiment of the present invention;
[0076] Figure 8 This is a fault diagnosis service processing logic diagram of an embodiment of the present invention;
[0077] Fig. 9 This is a schematic diagram of data mining fault association according to an embodiment of the present invention;
[0078] Fig.10 This is a fault prediction service processing logic diagram of an embodiment of the present invention;
[0079] Fig.11 It is a decision support business processing logic diagram of an embodiment of the present invention;
[0080] Fig.12 It is a structural block diagram of a secondary radar and an anti-collision system management device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0081] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0082] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.
[0083] The equipment health information of traditional secondary radar collision avoidance systems is too single and discrete. It can only reflect the current equipment status and cannot predict possible faults. In addition, the equipment health information cannot provide troubleshooting solutions and fault location.
[0084] With long-term use, the status of the equipment cannot be predicted, resulting in sudden failures that cannot be discovered in advance. The secondary radar system in the unmanned state and the anti-collision equipment in the flight state cannot provide timely equipment inspection and maintenance, which will lead to unpredictable risks.
[0085] In order to solve the above technical problems, the following embodiments of the secondary radar and collision avoidance system health management method, device, equipment and medium of the present invention are proposed.
[0086] Example 1
[0087] The secondary radar and anti-collision system health management method provided in this embodiment proposes a more comprehensive and intelligent health management design model based on the existing secondary radar and anti-collision system equipment.
[0088] Reference Figure 2 ,like Figure 2 The following is a diagram of the secondary radar and anti-collision system design model architecture of this embodiment. The health management system of this embodiment can be divided into a three-layer architecture:
[0089] The bottom layer is the sensor layer, which is distributed in the software and hardware monitoring programs or circuits in each module and component of the device, and completes the acquisition of basic self-test information in the device, that is, the output results of the smallest self-test sensor component or software detection unit in the device;
[0090] The middle layer is the self-check management layer, which is the processing unit for self-check synthesis, processing and output in each module or extension of the equipment. It is the execution unit for real-time monitoring of the operating status of each extension or module. The processor in this layer should support industrial standard control protocols such as OPC and Modbus.
[0091] The top layer is the health management layer, which correlates, confirms, diagnoses and predicts the system self-check status of all modules and extensions, updates the equipment self-check detection tree in real time, dynamically evaluates the equipment working status, forms fault prediction of equipment status and life tracking management of each unit.
[0092] This system can collect self-test and working data information of each module based on standard industrial communication formats such as OPC and Modbus, complete system equipment status monitoring, fault diagnosis, status prediction and pre-assessment, and maintenance decision-making and support. It is a distributed hardware and software integrated system. By monitoring the module status of the system and predicting the life of life parts, passive maintenance is changed to active maintenance and preventive maintenance, reducing the probability of failure during system operation to improve the system task completion rate; by real-time status monitoring of key components, real-time health assessment of their monitoring status is made, and their life assessment is corrected to avoid excessive maintenance of the system, thereby reducing the cost of use of the system life cycle.
[0093] The bottom layer (sensor layer) completes the acquisition of data for each self-test item and reports it to the middle layer. The commonly used communication method is bus or asynchronous serial port.
[0094] For the power module of the equipment, in order to monitor the status of its key points in real time, a low-power single-chip microcomputer plus an external AD method is used to sample the analog quantity of each key point and ensure the sampling accuracy of each analog signal. Figure 3 ,like Figure 3 Shown is a schematic diagram of the distribution of monitoring points of the power modules of the secondary radar and anti-collision system of this embodiment.
[0095] For the signal processing module of the equipment, the key status is mainly the embedded software in the module, FPGA firmware program to complete the detection. The monitoring points are mainly the input data items, output data and the working mode and current temperature of each key component of FPGA and embedded software.
[0096] For the transmitting or receiving module of the equipment, the main monitoring points are the modulation circuit, the detection signals of each level of amplification circuits, some detection signals, and the current and voltage of key components.
[0097] The middle layer (self-inspection management layer) completes the preprocessing of each self-inspection data item, self-inspection information fusion and information reporting. The fusion method mainly includes the elimination of abnormal values, the judgment of missing self-inspection items, etc. The reporting method is mainly network method.
[0098] The top layer (health management layer) completes the evaluation and prediction of the remaining life of the equipment, operating status, planned maintenance needs, etc. The physical failure mechanism of specific components or systems is established based on the actual self-test detection tree and historical database, and the dynamic system component failure and potential failure monitoring and its remaining life prediction are realized.
[0099] The health management layer has three capabilities: status monitoring, comprehensive diagnosis, and status prediction:
[0100] Status monitoring: reasonably divide subsystems or component units and set key test points according to system operating parameters. Effectively configure system sensors to efficiently collect necessary system data and store them in offline databases. Support standard OPC, Modbus and other industrial control protocols to complete data collection and dynamically display the self-test status of each module of the current system on the terminal according to the collected signals.
[0101] Comprehensive diagnosis, based on the analysis of the system operating environment, historical data and online data with the help of the system fault diagnosis model, accurately identifies and diagnoses system faults, isolates faulty components and subsystems, and evaluates the health status of equipment through various indicators, such as whether there is parameter degradation, etc., and can analyze information such as health status historical data, working status and maintenance records.
[0102] Condition prediction estimates the remaining service life or failure time of components or subsystems, and provides the system with maintenance decisions, component or subsystem replacement decisions, and reasonable spare parts reserves based on reasonable predictions.
[0103] The business logic diagram of the health management layer in this embodiment is as follows: Figure 4 As shown, the self-test data is received, and the self-test message reported by the middle layer is received through the network to complete the data collection. The self-test data is displayed by the graphical software to complete the graphical display of the self-test data. The self-test data display business processing logic diagram of this embodiment is as follows Figure 5 shown.
[0104] Reference Figure 1 ,like Figure 1 FIG. 1 is a flow chart of a secondary radar and anti-collision system health management method provided in this embodiment. The method specifically includes the following steps:
[0105] Step S100: Acquire information required for self-test of secondary radar equipment.
[0106] Specifically, the information required for the self-test of the secondary radar device includes monitoring information of the power module, monitoring information of the signal processing module and monitoring information of the transmitting and receiving module.
[0107] Step S200: Perform equipment self-inspection according to the information required for the secondary radar equipment self-inspection and upload the self-inspection information.
[0108] Specifically, performing equipment self-inspection according to the information required for the self-inspection of the secondary radar equipment and uploading the self-inspection information specifically includes:
[0109] Preprocess the information required for the self-test of secondary radar equipment;
[0110] The pre-processed information is subjected to self-inspection information fusion, which includes eliminating abnormal values and judging the missing of self-inspection items;
[0111] The integrated self-inspection information is reported.
[0112] Step S300: receiving self-check information and creating or updating a self-check detection tree according to the self-check information.
[0113] Specifically, creating or updating the self-check detection tree according to the self-check information specifically includes:
[0114] If there is no self-check detection tree, a new self-check detection tree is created; if there is already a self-check detection tree, the existing self-check detection tree is updated;
[0115] Creating or updating the self-check detection tree includes setting the detection value of the self-check item, the estimated range of the self-check item and the association relationship between the self-check items.
[0116] Step S400: Evaluate and determine the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model.
[0117] Among them, the self-check detection tree includes the detection value of the self-check item, the estimated range of the self-check item and the correlation between the self-check items. The node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
[0118] Specifically, the status assessment includes:
[0119] The node weights initially set are updated according to the fluctuation value of the self-check item detection value and the fluctuation threshold, where the fluctuation value of the self-check item detection value is the change value of the self-check item detection value compared with the historical detection value;
[0120] Update the evaluation specification according to the updated node weight, report the detection value of each self-check item and generate the self-check item status evaluation value. The evaluation specification consists of the node weight and the initially set health value;
[0121] Among them, updating the node weights initially set according to the fluctuation value of the self-check item detection value and the fluctuation threshold value specifically includes:
[0122] If the fluctuation value of the self-check item detection value does not exceed the fluctuation threshold, the node weight remains unchanged;
[0123] If the fluctuation value of the self-check item detection value exceeds the fluctuation threshold, the node weight is adjusted according to the preset rules.
[0124] Reference Figure 6 ,like Figure 6 The figure shows the status evaluation service processing logic diagram of this embodiment.
[0125] The setting of node weight is mainly based on the numerical fluctuation of a single self-check item and the basic weight of the self-check item. The weight value needs to float within a reasonable range. If the self-check value fluctuates close to the weight threshold, the node weight value will float up accordingly and will not exceed the set reasonable range. For example, if the 5V voltage value in the voltage detection module fluctuates within ±0.1V, the weight remains unchanged at 1.1. If it fluctuates beyond ±0.2V, the weight fluctuates within 1.1±0.05. If it fluctuates beyond ±0.25V, the weight needs to be adjusted to a higher 1.2.
[0126] The evaluation specifications are updated according to the updated weights, and each inspection item is reported to the judgment criteria management system to complete the generation of the status evaluation values of the relevant self-inspection items.
[0127] As an implementation mode, the system further includes an initially set fault rule tree, and the evaluation and determination further includes fault diagnosis, which specifically includes:
[0128] Update the self-check item detection value in the fault rule tree according to historical data and the self-check detection tree;
[0129] Perform fault diagnosis based on the updated fault rule tree and self-check item status evaluation values;
[0130] Among them, the fault rule tree includes basic fault judgment rules composed of the association relationship between self-check items, intermediate fault judgment rules composed of the association relationship between multiple basic fault judgment rules, and top-level fault judgment rules composed of the association relationship between multiple intermediate fault judgment rules.
[0131] Fault diagnosis is to complete detailed information of the equipment and each submodule based on rule reasoning and self-checking detection tree diagnosis according to the background data. The output mode of fault diagnosis includes graphical display and log recording. Fault diagnosis information is divided into rule model information output and self-checking detection tree diagnosis information output, and the results of data collection and settlement in the diagnosis process are recorded in detail.
[0132] The reasoning rules of sub-modules and equipment mainly include the association rules between LRUs at all levels and sub-self-detection items. The initial rules are set according to the expert experience method, and the data sample sets are accumulated according to the self-detection detection tree and historical data to complete the iterative improvement of the association rules. For example, the key voltage data items in the power supply are associated with the self-detection status of each LRU, the detection value judgment of the transmitting module is associated with the state effective value of the radiation function state, and the channel gain of each channel of the receiving module is associated with the state effective value of the decoding function. The self-detection detection tree is mainly associated through the generated fault detection rules to update the diagnosis rule database. Complete the fault rule generation and rule conversion of the top-level fault diagnosis and the middle-level fault diagnosis. The rule conversion takes time to convert the graphical relationship of the tree structure into a knowledge database of logical items such as "and", "or", "and or", "exclusive or", and "and not", and complete the update of the constructed fault rule list (tree). Reference Figure 7 and Figure 8 ,like Figure 7 The figure is a schematic diagram of the basic model of the fault rule tree of this embodiment. Figure 8 The figure shows the fault diagnosis service processing logic diagram of this embodiment.
[0133] As an implementation mode, the evaluation and determination further includes fault prediction, which specifically includes:
[0134] The Apriori algorithm is used to mine the correlation between system faults and self-check items, which specifically includes the following sub-steps:
[0135] Search historical data layer by layer in a loop to complete the collection of training sample sets of fault events and self-check items;
[0136] Identify the types of fault events in the training sample set, extract the associations between self-check items through learning and training, and complete the update of system fault types and association rules;
[0137] According to the association rules and the current self-test information, forward reasoning of fault knowledge matching and reverse reasoning of rule matching are performed to confirm the current fault state and complete fault matching, thereby obtaining the fault prediction result.
[0138] Fault prediction is based on the fault list, self-check detection tree, rule-based automatic diagnosis service interface and rule tool database to complete the construction of data mining model. Through forward reasoning, reverse reasoning and other fault knowledge and rule matching methods, fault matching and prediction result output are completed, and the output is completed through visual display and log recording.
[0139] Since the occurrence of a certain fault in the system is likely to have indirect associations with multiple sub-self-check items, and this association is somewhat hidden, it is necessary to use data mining technology and an association model set by expert experience to complete reasoning. The expert experience setting model is initially set up through the rule automatic diagnosis service interface and the rule tool database, and combined with the operation records, fault records, and fault rules in the historical database to obtain related items through data mining, and complete the iteration and improvement of the data mining model. The commonly used rule association method is the Apriori algorithm, which completes the collection of training sample sets between key data items through a layer-by-layer cyclic search of historical data, including various system fault events and their related sub-self-check item status data, calibrates the event types in the sample set, and uses learning training methods to extract the association rules of each related data, performs rule extraction, completes the update of system fault types and association rules, and builds and updates data mining models. Reference Fig. 9 and Fig.10 ,like Fig. 9 FIG. 1 is a schematic diagram of data mining fault association in this embodiment. Fig.10 The figure shows the fault prediction service processing logic diagram of this embodiment.
[0140] As an implementation method, the method further includes providing troubleshooting solutions and decision support based on the fault prediction results. Fig.11 ,like Fig.11 The figure shows the logic diagram of the decision support business processing of this embodiment. According to the corresponding fault prediction results, maintenance information query, resource matching details, detection equipment resources, spare parts resources, personnel management and maintenance progress tracking are provided. The decision support list is manually confirmed by the on-site personnel according to the fault prediction results, and the data is entered into the background for real-time maintenance and update.
[0141] The health management system of this embodiment adopts an open structure, collects various parameter information of the system by optimizing the sensor layout and uses as few sensors as possible to estimate the health status of the system itself with the help of various reasoning algorithms and intelligent models.
[0142] The secondary radar and anti-collision system health management method provided in this embodiment aims at the deficiencies of the existing self-checking system of the secondary radar system and the anti-collision system. The original single discrete self-checking items are combined and associated with each other to establish a self-checking detection tree; the historical self-checking information of the equipment is stored, and the real-time update of the equipment self-checking detection tree is completed, and the equipment fault prediction capability is possessed; according to the results of the fault prediction, decision support for the troubleshooting plan and steps is provided. This solution can also monitor and predict system faults before they occur. The fault prediction and health management technology will transform post-maintenance or regular maintenance into condition-based maintenance, which is a further expansion of the in-machine testing capability and status monitoring technology.
[0143] Example 2
[0144] Reference Fig.12 ,like Fig.12 FIG. 1 is a structural block diagram of a secondary radar and collision avoidance system management device provided in this embodiment, and the device specifically includes:
[0145] The acquisition module 10 is used to acquire information required for the self-test of the secondary radar device.
[0146] The self-check module 20 is used to perform equipment self-check according to the information required for the self-check of the secondary radar equipment and upload the self-check information.
[0147] The self-check tree module 30 is used to receive self-check information and create or update a self-check detection tree according to the self-check information.
[0148] The evaluation module 40 evaluates and determines the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model.
[0149] Among them, the self-check detection tree includes the detection value of the self-check item, the estimated range of the self-check item and the correlation between the self-check items. The node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
[0150] As an implementation manner, the self-check module 20 performs device self-check according to the information required for the secondary radar device self-check and uploads the self-check information specifically including:
[0151] Preprocess the information required for the self-test of secondary radar equipment;
[0152] The pre-processed information is subjected to self-inspection information fusion, which includes eliminating abnormal values and judging the missing of self-inspection items;
[0153] The integrated self-inspection information is reported.
[0154] As an implementation manner, the self-check tree module 30 creates or updates the self-check detection tree according to the self-check information, specifically including:
[0155] If there is no self-check detection tree, a new self-check detection tree is created; if there is already a self-check detection tree, the existing self-check detection tree is updated;
[0156] Creating or updating the self-check detection tree includes setting the detection value of the self-check item, the estimated range of the self-check item and the association relationship between the self-check items.
[0157] As an implementation manner, the status assessment performed by the assessment module 40 specifically includes:
[0158] The node weights initially set are updated according to the fluctuation value of the self-check item detection value and the fluctuation threshold, where the fluctuation value of the self-check item detection value is the change value of the self-check item detection value compared with the historical detection value;
[0159] Update the evaluation specification according to the updated node weight, report the detection value of each self-check item and generate the self-check item status evaluation value. The evaluation specification consists of the node weight and the initially set health value;
[0160] Among them, updating the node weights initially set according to the fluctuation value of the self-check item detection value and the fluctuation threshold value specifically includes:
[0161] If the fluctuation value of the self-check item detection value does not exceed the fluctuation threshold, the node weight remains unchanged;
[0162] If the fluctuation value of the self-check item detection value exceeds the fluctuation threshold, the node weight is adjusted according to the preset rules.
[0163] As an implementation mode, the system further includes an initially set fault rule tree, and the evaluation module 40 further includes fault diagnosis in performing evaluation and determination, and the fault diagnosis specifically includes:
[0164] Update the self-check item detection value in the fault rule tree according to historical data and the self-check detection tree;
[0165] Perform fault diagnosis based on the updated fault rule tree and self-check item status evaluation values;
[0166] Among them, the fault rule tree includes basic fault judgment rules composed of the association relationship between self-check items, intermediate fault judgment rules composed of the association relationship between multiple basic fault judgment rules, and top-level fault judgment rules composed of the association relationship between multiple intermediate fault judgment rules.
[0167] As an implementation manner, the evaluation module 40 further includes fault prediction in performing evaluation and determination, and the fault prediction specifically includes:
[0168] The Apriori algorithm is used to mine the correlation between system faults and self-check items, which specifically includes the following sub-steps:
[0169] Search historical data layer by layer in a loop to complete the collection of training sample sets of fault events and self-check items;
[0170] Identify the types of fault events in the training sample set, extract the associations between self-check items through learning and training, and complete the update of system fault types and association rules;
[0171] According to the association rules and the current self-test information, forward reasoning of fault knowledge matching and reverse reasoning of rule matching are performed to confirm the current fault state and complete fault matching, thereby obtaining the fault prediction result.
[0172] As an implementation method, the device also includes providing troubleshooting solutions and decision support based on the fault prediction results.
[0173] The secondary radar and anti-collision system management device provided in this embodiment aims at the deficiencies of the existing self-checking system of the secondary radar system and the anti-collision system. The original single discrete self-checking items are combined and associated with each other through self-checking information to establish a self-checking detection tree; the historical self-checking information of the equipment is stored, and the real-time update of the equipment self-checking detection tree is completed, and the equipment fault prediction capability is provided; according to the results of the fault prediction, decision support for the troubleshooting plan and steps is provided. This solution can also monitor and predict system faults before they occur. The fault prediction and health management technology will transform post-maintenance or regular maintenance into condition-based maintenance, which is a further expansion of the in-machine testing capability and status monitoring technology.
[0174] Example 3
[0175] This preferred embodiment provides a computer device, which can implement the steps in any embodiment of the secondary radar and collision avoidance system health management method provided in the embodiments of the present application. Therefore, the beneficial effects of the secondary radar and collision avoidance system health management method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.
[0176] Example 4
[0177] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions, and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present invention provides a storage medium, which stores multiple instructions, and the instructions can be loaded by a processor to execute the steps of any embodiment of the secondary radar and collision avoidance system health management method provided in the embodiment of the present invention.
[0178] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0179] Since the instructions stored in the storage medium can execute the steps in any of the secondary radar and collision avoidance system health management method embodiments provided in the embodiments of the present invention, the beneficial effects that can be achieved by any of the secondary radar and collision avoidance system health management methods provided in the embodiments of the present invention can be achieved. For details, please refer to the previous embodiments and will not be repeated here.
[0180] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A secondary radar and anti-collision system health management method, the system includes historical data, initially set node weights and fluctuation thresholds, It is characterized in that The method comprises: Obtain the information required for the self-test of secondary radar equipment; Perform equipment self-test according to the information required for the self-test of the secondary radar equipment and upload the self-test information; receiving the self-check information and creating or updating a self-check detection tree according to the self-check information; Evaluate and determine the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model; The self-check detection tree includes self-check item detection values, self-check item estimated ranges and associations between self-check items, the node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
2. The secondary radar and collision avoidance system health management method as claimed in claim 1, It is characterized in that The performing of equipment self-inspection according to the information required for the self-inspection of the secondary radar equipment and uploading the self-inspection information specifically includes: Preprocessing the information required for the self-test of the secondary radar device; Performing self-check information fusion on the pre-processed information, wherein the self-check information fusion includes eliminating abnormal values and determining the missing of self-check items; The integrated self-inspection information is reported.
3. The secondary radar and collision avoidance system health management method as claimed in claim 1, It is characterized in that The creating or updating of the self-check detection tree according to the self-check information specifically includes: If there is no self-check detection tree, a new self-check detection tree is created; if there is already a self-check detection tree, the existing self-check detection tree is updated; The creating or updating of the self-check detection tree includes setting the self-check item detection value, the self-check item estimated range and the association relationship between the self-check items.
4. The secondary radar and collision avoidance system health management method as claimed in claim 1, It is characterized in that The status assessment specifically includes: Update the initially set node weight according to the self-check item detection value fluctuation value and the fluctuation threshold value, wherein the self-check item detection value fluctuation value is a change value of the self-check item detection value compared with the historical detection value; Update the evaluation specification according to the updated node weight, report the detection value of each self-check item and generate the self-check item status evaluation value, wherein the evaluation specification is composed of the node weight and the initially set health value; Wherein, the updating of the initially set node weight according to the fluctuation value of the self-check item detection value and the fluctuation threshold value specifically includes: If the fluctuation value of the self-check item detection value does not exceed the fluctuation threshold, the node weight remains unchanged; If the fluctuation value of the self-check item detection value exceeds the fluctuation threshold, the node weight is adjusted according to the preset rules.
5. The secondary radar and collision avoidance system health management method as claimed in claim 4, It is characterized in that The system also includes an initially set fault rule tree, and the evaluation and determination also includes fault diagnosis, which specifically includes: Update the self-check item detection value in the fault rule tree according to the historical data and the self-check detection tree; Perform fault diagnosis according to the updated fault rule tree and the self-check item status evaluation value; Among them, the fault rule tree includes basic fault judgment rules composed of the association relationship between the self-check items, intermediate fault judgment rules composed of the association relationship between multiple basic fault judgment rules, and top-level fault judgment rules composed of the association relationship between multiple intermediate fault judgment rules.
6. The secondary radar and collision avoidance system health management method as claimed in claim 5, It is characterized in that The evaluation and determination also includes fault prediction, which specifically includes: The Apriori algorithm is used to mine the correlation between system faults and self-check items, which specifically includes the following sub-steps: Search historical data layer by layer in a loop to complete the collection of training sample sets of fault events and self-check items; Identify the types of fault events in the training sample set, extract the associations between self-check items through learning and training, and complete the update of system fault types and association rules; According to the association rules and the current self-test information, forward reasoning of fault knowledge matching and reverse reasoning of rule matching are performed to confirm the current fault state and complete fault matching, thereby obtaining the fault prediction result.
7. The secondary radar and collision avoidance system health management method as claimed in claim 6, It is characterized in that The method also includes providing troubleshooting solutions and decision support based on the fault prediction results.
8. A secondary radar and anti-collision system management device, It is characterized in that The device comprises: An acquisition module is used to obtain the information required for the self-test of the secondary radar equipment; A self-test module, used to perform equipment self-test according to the information required for the self-test of the secondary radar equipment and upload the self-test information; A self-check tree module, used for receiving the self-check information and creating or updating a self-check detection tree according to the self-check information; An evaluation module evaluates and determines the status of the secondary radar device according to the self-check detection tree, the fluctuation threshold, the initially set node weight and the algorithm model; The self-check detection tree includes self-check item detection values, self-check item estimated ranges and associations between self-check items, the node weight is determined by the basic weight of each self-check item, and the evaluation judgment includes status evaluation.
9. A computer device, It is characterized in that The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the secondary radar and collision avoidance system health management method according to any one of claims 1 to 7.
10. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, which is loaded and executed by a processor to implement the secondary radar and collision avoidance system health management method as described in any one of claims 1 to 7.
