Aviation equipment maintenance management system based on real-time data

Abstract

The invention discloses an aviation equipment maintenance management system based on real-time data, belongs to the technical field of aviation equipment maintenance, and constructs an aviation equipment fault identification model by adopting a multi-feature extraction mechanism and a weight redistribution mechanism, and performs fault prediction on aviation equipment by using the aviation equipment fault identification model. Therefore, potential faults can be found in advance, the maintenance cost is reduced, the state of the aviation equipment is monitored in real time, the operation safety is improved, a worker can make a reasonable maintenance plan, the maintenance efficiency is improved, resource waste is reduced, and the intelligent level of maintenance management of the aviation equipment is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of aviation equipment maintenance, and particularly relates to an aviation equipment maintenance management system based on real-time data. Background Art

[0002] Aviation equipment refers to various systems and components used in aircraft (such as airplanes, helicopters, drones, etc.), which jointly ensure the safe flight, navigation, operation, and mission execution of the aircraft. With the rapid development of the aviation industry, the operational safety of aviation equipment has received increasing attention. Traditional aviation equipment maintenance management mainly relies on manual experience and has the following problems: faults are not discovered in a timely manner, which may lead to safety accidents; maintenance plans are unreasonable, resulting in waste of resources; and the maintenance process lacks data support, making it difficult to achieve precise maintenance. Summary of the Invention

[0003] The present invention provides an aviation equipment maintenance management system based on real-time data to solve the technical problems of untimely fault discovery and unreasonable maintenance existing in the prior art.

[0004] An aviation equipment maintenance management system based on real-time data includes: a sample data acquisition module, a model construction module, a model training module, a real-time data acquisition module, an equipment data identification module, and a maintenance management module; The sample data acquisition module is used to acquire a training set and a test set; wherein, both the training set and the test set include training samples and training labels corresponding to the training samples; The model construction module is used to construct an aviation equipment fault identification model by adopting a multi-feature extraction mechanism and a weight reallocation mechanism; The model training module is used to train the aviation equipment fault identification model based on the training set and the test set to obtain the trained aviation equipment fault identification model; The real-time data acquisition module is used to collect real-time data corresponding to the aviation equipment for the aviation equipment; wherein, the data structure of the real-time data is the same as the data structure of the training samples; The equipment data identification module is used to call the trained aviation equipment fault identification model to identify the real-time data corresponding to the aviation equipment and determine the fault situation of the aviation equipment; wherein, the fault situation of the aviation equipment includes specific fault type states and normal states; The maintenance management module is used to generate aviation equipment maintenance suggestions and abnormal situation warning information based on the fault situation of the aviation equipment, and perform aviation equipment maintenance management according to the aviation equipment maintenance suggestions and abnormal situation warning information.

[0005] Further, the training samples include sample currents and sample voltages at multiple consecutive time points.

[0006] Furthermore, a multi-feature extraction mechanism and a weight redistribution mechanism are adopted to construct an aircraft equipment fault recognition model, including: Construct the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network with different network layer depths, and perform multi-scale feature fusion on the features output by the fully connected layers of the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network to obtain fused features; Construct an ECA-Net model to perform weight allocation on the fused features and output the features after weight allocation; Construct a BiLSTM model to perform data enhancement on the features after weight allocation in the time dimension through forward and backward propagation operations and output the final vector to be recognized; Construct a CatBoost model to recognize the final vector to be recognized and output the aircraft equipment fault type; According to the first convolutional neural network, the second convolutional neural network, the third convolutional neural network, the ECA-Net model, the BiLSTM model, and the CatBoost model, obtain the aircraft equipment fault recognition model.

[0007] Furthermore, based on the training set and the test set, train the aircraft equipment fault recognition model to obtain the trained aircraft equipment fault recognition model, including: After initializing the model parameters to be optimized of the aircraft equipment fault recognition model, generate a population to be trained, and use the training set to train the population to be trained to obtain the optimal parameter combination in the population to be trained; Apply the optimal parameter combination in the population to be trained to the aircraft equipment fault recognition model, and use the test set to test the aircraft equipment fault recognition model to obtain the test results; When the test results meet the conditions, obtain the trained aircraft fault recognition model, otherwise return to the step of obtaining the optimal parameter combination in the population to be trained.

[0008] Furthermore, use the training set to train the population to be trained to obtain the optimal parameter combination in the population to be trained, including: Use the training set to obtain the objective function value corresponding to each parameter combination in the population to be trained, and determine the optimal parameter combination according to the objective function value; Based on the optimal parameter combination, perform multi-directional guided optimization on each parameter combination in the population to be trained to obtain the parameter combination after multi-directional guided optimization; For the parameter combination after multi-directional guided optimization, perform fractional-order memory search on the parameter combination after multi-directional guided optimization to obtain the parameter combination after fractional-order memory search; For the parameter combination after fractional-order memory search, perform a normal distribution search on the parameter combination after fractional-order memory search to obtain the parameter combination after normal distribution search; Repeat multi-directional guided optimization, fractional-order memory search, and normal distribution search until the training end condition is met, and output the optimal parameter combination.

[0009] Furthermore, based on the optimal parameter combination, perform multi-directional guided optimization on each parameter combination in the population to be trained to obtain the parameter combination after multi-directional guided optimization, including: For each parameter combination in the population to be trained, randomly match an other parameter combination for each parameter combination, and the matched other parameter combination is different from the optimal parameter combination; Fuse the matched other parameter combination with the optimal parameter combination, and based on the fused data, obtain the difference information combination between the parameter combinations; After adjusting the difference information combination using a randomly adjusted step factor, perform multi-directional guided optimization on the parameter combination using the adjusted difference information combination to obtain the parameter combination after multi-directional guided optimization.

[0010] Furthermore, for the parameter combination after multi-directional guided optimization, perform fractional-order memory search on the parameter combination after multi-directional guided optimization to obtain the parameter combination after fractional-order memory search, including: For the parameter combination after multi-directional guided optimization, memorize the historical position information of the parameter combination multiple times to obtain the memory information combination; Obtain the overall information difference combination between the parameter combination and the overall position, and based on the memory information combination and the overall information difference combination, perform fractional-order memory search on the parameter combination to obtain the parameter combination after fractional-order memory search.

[0011] Furthermore, for the parameter combination after fractional-order memory search, perform normal distribution search on the parameter combination after fractional-order memory search to obtain the parameter combination after normal distribution search, including: For the parameter combination after fractional-order memory search, generate a random adjustment factor using a normal distribution, and adjust the random adjustment factor using a scaling factor to obtain the adjusted random adjustment factor; Adjust the parameter combination after fractional-order memory search using the adjusted random adjustment factor to obtain the parameter combination after normal distribution search.

[0012] Furthermore, for aviation equipment, collect the real-time data corresponding to the aviation equipment, including: For aviation equipment, based on the data sampling frequency corresponding to the training samples, the real-time current and real-time voltage corresponding to the aviation equipment are collected to obtain the real-time data corresponding to the aviation equipment.

[0013] Furthermore, based on the fault conditions of the aviation equipment, maintenance suggestions and early warning information for abnormal conditions of the aviation equipment are generated, and maintenance management of the aviation equipment is carried out according to the maintenance suggestions and early warning information for abnormal conditions of the aviation equipment, including: When the fault condition of the aviation equipment is a specific fault type state, determine the maintenance suggestions for the aviation equipment corresponding to the preset specific fault type state; When the fault condition of the aviation equipment is a specific fault type state, generate an audible and visual alarm message and a text alarm message to obtain early warning information for abnormal conditions; Transmit the text alarm message in the maintenance suggestions and early warning information for abnormal conditions of the aviation equipment to the equipment corresponding to the staff, and transmit the audible and visual alarm message to the audible and visual alarm device for alarm, so that the staff can carry out timely maintenance of the aviation equipment.

[0014] A maintenance management system for aviation equipment based on real-time data provided by the present invention constructs a fault identification model for aviation equipment by adopting a multi-feature extraction mechanism and a weight reallocation mechanism, and uses the fault identification model for aviation equipment to predict faults of the aviation equipment, so as to detect potential faults in advance, reduce maintenance costs, realize real-time monitoring of the state of the aviation equipment, improve operation safety, enable the staff to formulate a reasonable maintenance plan, improve maintenance efficiency, reduce resource waste, and improve the intelligent level of aviation equipment maintenance management. Description of the Drawings

[0015] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments in line with the present invention, and are used together with the specification to explain the principles of the present invention.

[0016] Figure 1 It is a schematic structural diagram of a maintenance management system for aviation equipment based on real-time data provided by an embodiment of the present invention.

[0017] Among them, 11 - sample data acquisition module, 12 - model construction module, 13 - model training module, 14 - real-time data acquisition module, 15 - equipment data identification module, 16 - maintenance management module.

[0018] Through the above drawings, specific embodiments of the present invention have been shown, and there will be more detailed descriptions later. These drawings and text descriptions are not intended to limit the scope of the inventive concept in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. Detailed Embodiments

[0019] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0020] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] As Figure 1 shown, an aviation equipment maintenance management system based on real-time data provided by an embodiment of the present invention includes: a sample data acquisition module 11, a model construction module 12, a model training module 13, a real-time data acquisition module 14, an equipment data identification module 15, and a maintenance management module 16; The sample data acquisition module 11 is used to acquire a training set and a test set; wherein, both the training set and the test set include training samples and training labels corresponding to the training samples; The training samples are data collected under various specific fault types or data at the initial stage of a fault, and the training labels corresponding to the training samples are the specific fault types. However, there may be no fault during real-time monitoring. Therefore, the training labels should also include normal normality, so that the fault characteristics and normal characteristics can be learned through the training set and combined with deep learning techniques, and it can be determined whether the learning result is feasible through the test set.

[0022] The model construction module 12 is used to construct an aviation equipment fault identification model by adopting a multi-feature extraction mechanism and a weight reallocation mechanism; In the prior art, a single data classification model is often used for data learning and data identification, resulting in low accuracy and unable to effectively achieve fault prediction. Therefore, an embodiment of the present invention constructs an aviation equipment fault identification model through a multi-feature extraction mechanism and a weight reallocation mechanism to improve the feature analysis ability and ultimately improve the fault prediction ability.

[0023] The model training module 13 is used to train the aviation equipment fault identification model based on the training set and the test set to obtain a trained aviation equipment fault identification model; Training the aviation equipment fault identification model may include: training the aviation equipment fault identification model by using intelligent optimization algorithms such as the gradient descent method and the particle swarm algorithm to obtain a trained aviation equipment fault identification model.

[0024] The real-time data acquisition module 14 is used to collect the real-time data corresponding to the aviation equipment for the aviation equipment; wherein, the data structure of the real-time data is the same as the data structure of the training samples. By ensuring that the data structure of the real-time data is the same as the data structure of the training samples, the aviation equipment fault recognition model after training can accurately identify the data, thereby realizing fault prediction.

[0025] The equipment data recognition module 15 is used to call the trained aviation equipment fault recognition model to identify the real-time data corresponding to the aviation equipment and determine the fault situation of the aviation equipment; wherein, the fault situation of the aviation equipment includes specific fault type status and normal status. The maintenance management module 16 is used to generate aviation equipment maintenance suggestions and abnormal situation warning information based on the fault situation of the aviation equipment, and perform aviation equipment maintenance management according to the aviation equipment maintenance suggestions and abnormal situation warning information.

[0026] The association database between the fault situation of the aviation equipment and the maintenance suggestions of the aviation equipment can be set in advance, and the maintenance suggestions of the aviation equipment can be obtained through various historical data. Then, after predicting the fault situation of the aviation equipment, suggestions can be quickly given to improve the maintenance efficiency of the staff. At the same time, abnormal situation warning information can be generated, and warnings can be issued through the abnormal situation warning information to realize real-time monitoring of the status of the aviation equipment.

[0027] An aviation equipment maintenance management system based on real-time data provided by the present invention constructs an aviation equipment fault recognition model by adopting a multi-feature extraction mechanism and a weight reallocation mechanism, and performs fault prediction on the aviation equipment with the aviation equipment fault recognition model, so as to discover potential faults in advance, reduce maintenance costs, realize real-time monitoring of the status of the aviation equipment, improve operation safety, enable the staff to formulate reasonable maintenance plans, improve maintenance efficiency, reduce resource waste, and improve the intelligent level of aviation equipment maintenance management.

[0028] In the embodiment of the present invention, the training samples include sample currents and sample voltages at multiple consecutive time points. Currents and voltages can effectively reflect the operation of the equipment, such as short circuits, open circuits, poor contacts, damage to cameras, or abnormal operation of motors, etc. Therefore, in the embodiment of the present invention, currents and voltages are used to detect whether the aviation equipment is operating abnormally.

[0029] It should be noted that, in addition to the above features, other features can also be used to construct training samples for different aviation equipment. For example, when it comes to motor equipment, vibration frequencies can also be collected to improve the accuracy of fault prediction.

[0030] The sample current and sample voltage at multiple consecutive time points are data collected at a preset data sampling frequency. When collecting real-time data subsequently, data should also be collected at the data sampling frequency to ensure that the data can be accurately identified.

[0031] In the embodiment of the present invention, a multi-feature extraction mechanism and a weight redistribution mechanism are adopted to construct an aircraft equipment fault identification model, including: Construct a first convolutional neural network, a second convolutional neural network, and a third convolutional neural network with different network layer depths, and perform multi-scale feature fusion on the features output by the fully connected layers of the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network to obtain fused features; The multi-scale feature fusion can be: performing element-wise product operations on the features output by the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network, so that fused features can be obtained. Therefore, the collected training samples or real-time data can be constructed as a data matrix as the input, so that feature extraction can be effectively realized.

[0032] Construct an ECA-Net (Efficient Channel Attention Network, lightweight attention mechanism) model to perform weight distribution on the fused features and output the features after weight distribution; Construct a BiLSTM (Bidirectional Long Short-Term Memory) model to perform data enhancement on the features after weight distribution in the time dimension through forward and backward propagation bidirectional operations and output the final vector to be identified; Construct a CatBoost (regression classification) model to identify the final vector to be identified and output the aircraft equipment fault type; According to the first convolutional neural network, the second convolutional neural network, the third convolutional neural network, the ECA-Net model, the BiLSTM model, and the CatBoost model, an aircraft equipment fault identification model is obtained.

[0033] The aircraft equipment fault identification model provided by the embodiment of the present invention can first use the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network with different network layer depths to more comprehensively extract the characteristics of the data and enhance the overall performance of the network. Then, the ECA-Net model is used to redistribute the weights, effectively capturing the information of cross-channel interactions. Then, the BiLSTM model further strengthens the data features in the time dimension. Finally, the CatBoost model is used for fault classification. Compared with a single classification model, the data identification accuracy can be effectively improved, thereby improving the fault prediction accuracy.

[0034] In an embodiment of the present invention, based on the training set and the test set, the aviation equipment fault recognition model is trained to obtain the trained aviation equipment fault recognition model, including: After initializing the model parameters to be optimized of the aviation equipment fault recognition model, a population to be trained is generated, and the training set is used to train the population to be trained to obtain the optimal parameter combination in the population to be trained; The model parameters to be optimized of the aviation equipment fault recognition model can be the connection weights between each network layer. By optimizing these connection weights, the aviation equipment fault recognition model can effectively identify real-time data in the subsequent process.

[0035] Apply the optimal parameter combination in the population to be trained to the aviation equipment fault recognition model, and use the test set to test the aviation equipment fault recognition model to obtain the test result; Among them, the test result can be the accuracy rate obtained by using the test set. When the accuracy rate is higher than the preset threshold, it can be considered to meet the conditions, otherwise it can be determined not to meet the conditions.

[0036] When the test result meets the conditions, the trained aviation fault recognition model is obtained, otherwise return to the step of obtaining the optimal parameter combination in the population to be trained.

[0037] In the process of training the deep learning model in the prior art, there is a technical problem of being easily trapped in local optimum, resulting in a low final fault prediction accuracy rate. Therefore, the embodiment of the present invention is improved by multi-directional guided optimization, fractional-order memory search and normal distribution search to enhance the global search ability of the algorithm, so that the obtained parameters are more accurate, the performance of the deep learning model is improved, and finally the fault prediction accuracy rate is improved.

[0038] In an embodiment of the present invention, the training set is used to train the population to be trained to obtain the optimal parameter combination in the population to be trained, including: Use the training set to obtain the objective function value corresponding to each parameter combination in the population to be trained, and determine the optimal parameter combination according to the objective function value; among them, the parameter combination can be a vector to facilitate data calculation.

[0039] The objective function value can be obtained through the cross-entropy loss function. The smaller the objective function value, the better the parameter combination. Therefore, the parameter combination with the smallest objective function value can be determined as the optimal parameter combination.

[0040] Based on the optimal parameter combination, multi-directional guided optimization is performed on each parameter combination in the population to be trained to obtain the parameter combination after multi-directional guided optimization; For the parameter combination after multi-directional guided optimization, perform fractional-order memory search on the parameter combination after multi-directional guided optimization to obtain the parameter combination after fractional-order memory search; For the parameter combination after fractional-order memory search, perform normal distribution search on the parameter combination after fractional-order memory search to obtain the parameter combination after normal distribution search; Repeat multi-directional guided optimization, fractional-order memory search, and normal distribution search until the training end condition is met, and output the optimal parameter combination. Among them, the training end condition can be that the number of training times reaches the maximum number of training times.

[0041] In the embodiment of the present invention, based on the optimal parameter combination, perform multi-directional guided optimization on each parameter combination in the population to be trained to obtain the parameter combination after multi-directional guided optimization, including: For each parameter combination in the population to be trained, randomly match an other parameter combination for each parameter combination, and the matched other parameter combination is different from the optimal parameter combination; Fuse the matched other parameter combination with the optimal parameter combination, and based on the fused data, obtain the difference information combination between the parameter combinations as: ; where represents the t th parameter combination in the i th training process, represents the other parameter combination matched for the t th parameter combination in the i th training process, represents the optimal parameter combination.

[0042] After adjusting the difference information combination by using a random adjustment step factor, perform multi-directional guided optimization on the parameter combination by using the adjusted difference information combination to obtain the parameter combination after multi-directional guided optimization as: ; where represents the parameter combination after multi-directional guided optimization , represents the random adjustment step factor, , represents the preset maximum step size, represents a random number between (0, 1), i =1, 2,..., M, and M represents the total number of parameter combinations.

[0043] The multi-directional guided optimization provided by the embodiment of the present invention can not only search the parameter combination in the optimal direction, but also be affected by other parameter combinations and can fluctuate continuously during the search process, which can reduce the probability of the algorithm falling into local optimum while ensuring the search efficiency of the algorithm.

[0044] In the embodiment of the present invention, for the parameter combination after multi-directional guided optimization, perform fractional-order memory search on the parameter combination after multi-directional guided optimization to obtain the parameter combination after fractional-order memory search, including: For the parameter combination after multi-directional guided optimization, perform memory of historical position information on the parameter combination multiple times to obtain the memory information combination as: ; where represents the memory factor, and , e represents the natural constant, iter represents the maximum number of training times, represents the t th parameter combination after multi-directional guided optimization during the j th training process, represents the parameter combination in the t -1th training process, represents the parameter combination in the t -2th training process, represents the parameter combination in the t -3th training process; Obtain the overall information difference combination between the parameter combination and the overall position as: ; where represents a random number between (0, 0.5), represents the overall position, that is, the parameter of each dimension is the mean value of all parameter combinations in the same dimension parameter.

[0045] According to the memory information combination and the overall information difference combination, perform fractional-order memory search on the parameter combination to obtain the parameter combination after fractional-order memory search as: ; where represents the parameter combination after fractional-order memory search .

[0046] The fractional-order memory search provided by the embodiment of the present invention can enable the parameter combination to remember its own historical state, and as time goes by, it decreases, which can effectively ensure the diversity of the parameter combination, improve the global search ability of the algorithm, and as the algorithm progresses, all parameter combinations gradually gather in the solution space, and the remembered positions are also getting better, which can effectively improve the local search ability of the algorithm.

[0047] In the embodiment of the present invention, for the parameter combination after fractional-order memory search, perform normal distribution search on the parameter combination after fractional-order memory search to obtain the parameter combination after normal distribution search, including: For the parameter combination after fractional-order memory search, a random adjustment factor is generated using a normal distribution, and the random adjustment factor is adjusted using a scaling factor to obtain the adjusted random adjustment factor as follows: ; where represents the random adjustment factor generated for the d -dimensional parameter, which is generated through the standard normal distribution . represents the scaling ratio adjustment factor generated for the d -dimensional parameter, and . represents a preset constant factor (such as 0.5, 0.55, etc.), represents the upper limit of the d -dimensional parameter, represents the lower limit of the d -dimensional parameter; The parameter combination after fractional-order memory search is adjusted using the adjusted random adjustment factor to obtain the parameter combination after normal distribution search as follows:

[0048] where represents the t th dimension parameter of the m th parameter combination after fractional-order memory search in the d th training process, represents the parameter after normal distribution search.

[0049] Optionally, when the objective function value of the parameter combination after normal distribution search decreases, the search is retained; otherwise, the search is rejected.

[0050] Whenever a search is performed on a parameter combination, the parameter combination should be processed for out-of-bounds to ensure that the d -dimensional parameter is always within , .

[0051] In the embodiments of the present invention, for an aviation device, real-time data corresponding to the aviation device is collected, including: For the aviation device, based on the data sampling frequency corresponding to the training samples, the real-time current and real-time voltage corresponding to the aviation device are collected to obtain the real-time data corresponding to the aviation device.

[0052] In the embodiments of the present invention, based on the fault condition of the aviation device, maintenance suggestions and abnormal condition warning information for the aviation device are generated, and aviation device maintenance management is performed according to the maintenance suggestions and abnormal condition warning information for the aviation device, including: When the failure situation of the aviation equipment is in the state of a specific failure type, determine the maintenance suggestions for the aviation equipment corresponding to the preset specific failure type state; When the failure situation of the aviation equipment is in the state of a specific failure type, generate an audible and visual alarm message and a text alarm message to obtain an early warning message for the abnormal situation; Transmit the maintenance suggestions for the aviation equipment and the text alarm message in the early warning message for the abnormal situation to the equipment corresponding to the staff, and transmit the audible and visual alarm message to the audible and visual alarm device for alarm, so that the staff can perform timely maintenance on the aviation equipment.

[0053] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0054] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0055] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocksFigure 1 Steps of functions specified in one or more boxes.

[0057] Those of ordinary skill in the art can understand that all or part of the steps in realizing the above facts and methods can be completed by instructing relevant hardware through a program. The program involved or the said program can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: At this time, the corresponding method steps are introduced. The storage medium can be ROM / RAM, magnetic disk, optical disc, etc.

[0058] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An aviation equipment maintenance management system based on real-time data, characterized in that: include: Sample data acquisition module, model building module, model training module, real-time data acquisition module, equipment data identification module and maintenance management module; The sample data acquisition module is used to acquire a training set and a test set; wherein the training set and the test set both include training samples and training labels corresponding to the training samples; The model building module is used to build an aviation equipment fault identification model by adopting a multi-feature extraction mechanism and a weight redistribution mechanism; The model training module is used to train the aviation equipment fault identification model based on the training set and the test set to obtain the trained aviation equipment fault identification model; The real-time data acquisition module is used to collect real-time data corresponding to the aviation equipment; wherein the data structure of the real-time data is the same as the data structure of the training sample; The equipment data identification module is used to call the trained aviation equipment fault identification model to identify the real-time data corresponding to the aviation equipment and determine the aviation equipment fault condition; wherein the aviation equipment fault condition includes a specific fault type state and a normal state; The maintenance management module is used to generate aviation equipment maintenance suggestions and abnormal situation warning information based on the aviation equipment failure situation, and perform aviation equipment maintenance management according to the aviation equipment maintenance suggestions and abnormal situation warning information.

2. The aviation equipment maintenance management system based on real-time data according to claim 1, characterized in that: The training samples include sample currents and sample voltages at a plurality of consecutive time points.

3. The aviation equipment maintenance management system based on real-time data according to claim 1, characterized in that: A multi-feature extraction mechanism and a weight redistribution mechanism are used to build an aviation equipment fault identification model, including: Constructing a first convolutional neural network, a second convolutional neural network, and a third convolutional neural network with different network layer depths, and performing multi-scale feature fusion on features output by fully connected layers of the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network to obtain fused features; Construct an ECA-Net model to assign weights to fused features and output the features after weight assignment; Construct a BiLSTM model to perform data enhancement on the features after weight assignment in the time dimension through forward and backward propagation bidirectional operations, and output the final vector to be identified; Build a CatBoost model to identify the final vector to be identified and output the aviation equipment fault type; According to the first convolutional neural network, the second convolutional neural network, the third convolutional neural network, the ECA-Net model, the BiLSTM model and the CatBoost model, an aviation equipment fault identification model is obtained.

4. The aviation equipment maintenance management system based on real-time data according to claim 3 is characterized in that: Based on the training set and the test set, the aviation equipment fault identification model is trained to obtain the trained aviation equipment fault identification model, including: After initializing the model parameters to be optimized of the aviation equipment fault identification model, generating a population to be trained, and using a training set to train the population to be trained to obtain an optimal parameter combination in the population to be trained; Apply the optimal parameter combination in the training population to the aviation equipment fault identification model, and use the test set to test the aviation equipment fault identification model to obtain the test results; When the test result meets the conditions, the trained aviation fault identification model is obtained, otherwise the step of obtaining the optimal parameter combination in the population to be trained is returned.

5. The aviation equipment maintenance management system based on real-time data according to claim 4, characterized in that: The training set is used to train the population to be trained to obtain the optimal parameter combination in the population to be trained, including: The training set is used to obtain the objective function value corresponding to each parameter combination in the population to be trained, and the optimal parameter combination is determined according to the objective function value; Based on the optimal parameter combination, a multi-directional guided optimization search is performed on each parameter combination in the training population to obtain a parameter combination after the multi-directional guided optimization search; For the parameter combination after the multi-directional guided optimization search, a fractional-order memory search is performed on the parameter combination after the multi-directional guided optimization search to obtain the parameter combination after the fractional-order memory search; For the parameter combination after the fractional-order memory search, a normal distribution search is performed on the parameter combination after the fractional-order memory search to obtain the parameter combination after the normal distribution search; Repeat multi-directional guided optimization, fractional-order memory search, and normal distribution search until the training end conditions are met and output the optimal parameter combination.

6. The aviation equipment maintenance management system based on real-time data according to claim 5, characterized in that: Based on the optimal parameter combination, a multi-directional guided optimization is performed on each parameter combination in the training population to obtain a parameter combination after the multi-directional guided optimization, including: For each parameter combination in the training population, a random matching of another parameter combination is performed for each parameter combination, and the matching other parameter combination is different from the optimal parameter combination; Perform data fusion on other matching parameter combinations and the optimal parameter combination, and obtain the difference information combination between the parameter combination based on the fused data; After the difference information combination is adjusted by using a random adjustment step factor, the adjusted difference information combination is used to perform multi-directional guided optimization on the parameter combination to obtain the parameter combination after the multi-directional guided optimization.

7. The aviation equipment maintenance management system based on real-time data according to claim 6, characterized in that: For the parameter combination after the multi-directional guided optimization search, a fractional-order memory search is performed on the parameter combination after the multi-directional guided optimization search to obtain the parameter combination after the fractional-order memory search, including: For the parameter combination after multi-directional guided optimization, the historical position information of the parameter combination is memorized multiple times to obtain a memorized information combination; The overall information difference combination between the parameter combination and the overall position is obtained, and a fractional order memory search is performed on the parameter combination according to the memory information combination and the overall information difference combination to obtain the parameter combination after the fractional order memory search.

8. The aviation equipment maintenance management system based on real-time data according to claim 7, characterized in that: For the parameter combination after the fractional-order memory search, a normal distribution search is performed on the parameter combination after the fractional-order memory search to obtain the parameter combination after the normal distribution search, including: For the parameter combination after the fractional-order memory search, a normal distribution is used to generate a random adjustment factor, and a scaling factor is used to adjust the random adjustment factor to obtain the adjusted random adjustment factor; The parameter combination after the fractional-order memory search is adjusted using the adjusted random adjustment factor to obtain the parameter combination after the normal distribution search.

9. The aviation equipment maintenance management system based on real-time data according to claim 1, characterized in that: For aviation equipment, collect real-time data corresponding to aviation equipment, including: For aviation equipment, based on the data sampling frequency corresponding to the training samples, the real-time current and real-time voltage corresponding to the aviation equipment are collected to obtain the real-time data corresponding to the aviation equipment.

10. The aviation equipment maintenance management system based on real-time data according to claim 9, characterized in that: Based on the aviation equipment failure situation, aviation equipment maintenance suggestions and abnormal situation warning information are generated, and aviation equipment maintenance management is performed according to the aviation equipment maintenance suggestions and abnormal situation warning information, including: When the aviation equipment failure condition is a specific failure type state, determine the aviation equipment maintenance suggestion corresponding to the preset specific failure type state; When the aviation equipment fails in a specific fault type state, an audible and visual alarm message and a text alarm message are generated to obtain abnormal situation warning information; The text alarm information in the aviation equipment maintenance suggestions and abnormal situation warning information is transmitted to the corresponding equipment of the staff, and the sound and light alarm information is transmitted to the sound and light alarm equipment for alarm, so that the staff can perform timely maintenance on the aviation equipment.

Images