An engine health management model training data processing method and system based on expert experience, a storage medium and an electronic device
By parsing multi-source data through schema mapping and rule base, defining hierarchical If-Then rules, and combining K-Fold cross-validation and stratified sampling, the problems of low data processing efficiency and difficulty in integrating expert experience in engine health management model training are solved, achieving efficient model training and improved generalization ability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 四川腾盾科技有限公司
- Filing Date
- 2026-02-24
- Publication Date
- 2026-06-19
AI Technical Summary
Existing engine health management model training suffers from problems such as data heterogeneity and strong labeling dependence, fragmented and inefficient training processes, and difficulty in effectively integrating and standardizing expert experience, resulting in low data processing efficiency and insufficient model generalization ability.
By combining schema mapping technology with statistical analysis and rule bases, multi-source data is parsed and hierarchical If-Then rules are defined. The rules are then transformed and validated to generate an initial dataset. K-Fold cross-validation and stratified sampling are used to partition the dataset, reducing manual intervention and improving data processing efficiency.
It significantly improves model training efficiency, reduces reliance on human intervention, ensures accurate integration of domain expertise into the model, and enhances the model's adaptability and generalization ability.
Smart Images
Figure CN122241215A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of training data processing technology, and more specifically, to a method, system, storage medium, and electronic device for processing training data of an engine health management model based on expert experience. Background Technology
[0002] Engine health management model training refers to building an intelligent model by integrating artificial intelligence, machine learning algorithms, and domain expert experience to assess, predict, and optimize the health status of UAV engines in real time.
[0003] In the training process of Engine Health Management (EHM) models, existing technologies face the following key bottlenecks: (1) Strong data heterogeneity and labeling dependence: Training data comes from diverse sources (multiple sources), with heterogeneous formats (CSV, JSON, XML, etc.), and is highly dependent on manual labeling, resulting in low data processing efficiency, obvious subjectivity in labeling results, and difficulty in ensuring data quality consistency; (2) Fragmented and inefficient training process: The data acquisition, feature engineering, and training task scheduling required for model training are independent of each other, relying on a large number of manual operations, resulting in a long overall development cycle and huge consumption of computing resources; (3) Difficulty in effectively integrating and standardizing expert experience: Valuable experience of domain experts (such as diagnostic rules and threshold settings) is difficult to efficiently transform into standardized input information usable by the model, and mainly relies on manual coding rules. This approach has low knowledge utilization, which limits the generalization ability of the model and its adaptability to different working conditions and different engine models. Summary of the Invention
[0004] The embodiments of this application provide a method, system, storage medium, and electronic device for processing training data of an engine health management model based on expert experience, so as to improve the model training efficiency, reduce the reliance on manual intervention, ensure that the trained model accurately integrates domain expertise, and effectively solve the pain points of the prior art.
[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.
[0006] According to a first aspect of the embodiments of this application, a method for processing training data of an engine health management model based on expert experience is provided, including: Data and protocols are obtained from a multi-source dataset server, and the protocols are parsed. Define hierarchical If-Then rules based on expert experience, and perform rule transformation, rule validation, and storage; Select the validated hierarchical If-Then rules to map and transform the data after protocol parsing, and obtain the initial dataset; Based on the model training requirements, the initial dataset is divided into a training set and a test set.
[0007] In some embodiments of this application, based on the foregoing scheme, the protocol parsing includes: By using schema mapping technology, combined with statistical analysis, rule bases, and protocols, the acquired data is parsed to identify field types.
[0008] In some embodiments of this application, based on the foregoing scheme, the step of defining hierarchical If-Then rules by combining expert experience, and performing rule transformation, rule verification, and storage includes: The hierarchical If-Then rules are transformed into rules, with rule types including classification feature information and threshold parameters; One-hot encoding is used to convert categorical feature information into vectors; The threshold parameters are converted into numerical variables usable by the model and support adaptation to multiple engine models. The transformation rules are validated, and once the validation is successful, the rule is saved to the rule base.
[0009] In some embodiments of this application, based on the foregoing scheme, the threshold parameter is generated according to the engine model mapping.
[0010] In some embodiments of this application, based on the foregoing scheme, the step of selecting a verified hierarchical If-Then rule to map and transform the data after protocol parsing to obtain an initial dataset includes: Obtain the verified rule base; Select validated rules from the rule base to perform data transformation on the data parsed by the protocol, and generate the initial dataset.
[0011] In some embodiments of this application, based on the foregoing scheme, dividing the initial dataset into a training set and a test set according to model training requirements includes: Depending on the model training requirements, the initial dataset is divided into training and test sets using K-Fold cross-validation, stratified sampling, or user-defined methods.
[0012] In some embodiments of this application, based on the aforementioned scheme, K-Fold cross-validation is used to divide the initial dataset into a training set and a test set, including: The initial dataset is divided into K subsets, which are used sequentially as the validation set and the remainder as the training set. K is a positive integer, and the formula is defined as follows: ; in, For the entire set; Let the i-th subset be used as the verification set; for Removed from the middle The set of is used as the training set.
[0013] In some embodiments of this application, based on the foregoing scheme, stratified sampling is used to divide the initial dataset into a training set and a test set, including: The samples are divided into strata according to the proportion of labels to ensure that the samples in each stratum are balanced. ; in Let be the number of training samples sampled from the j-th class. This represents the total number of training samples. Let J be the total number of samples in class j. This represents the total number of samples.
[0014] According to a second aspect of the embodiments of this application, an engine health management model training data processing system based on expert experience is provided, comprising: The data acquisition module is used to acquire data and protocols from a multi-source dataset server and perform protocol parsing. The expert rule engine is used to define hierarchical If-Then rules by combining expert experience, and to perform rule transformation, rule verification and storage; and to select verified hierarchical If-Then rules to map and transform parameters of the data after protocol parsing to obtain the initial dataset; The training scheduling module is used to divide the initial dataset into a training set and a test set according to the model training requirements.
[0015] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided, the storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the method as described in the first aspect.
[0016] According to a fourth aspect of the embodiments of this application, an electronic device is provided, including: a memory and a processor; The memory is used to store computer instructions; The processor is configured to invoke computer instructions stored in the memory, causing the electronic device to execute the method described in the first aspect.
[0017] The technical solution of this application can significantly improve model training efficiency, greatly reduce reliance on manual intervention, ensure that the trained model accurately integrates domain expertise, and effectively solve the pain points of existing technologies.
[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart illustrating a method for processing training data of an engine health management model based on expert experience, according to an embodiment of this application, is shown. Figure 2 A structural block diagram of an engine health management model training data processing system based on expert experience according to an embodiment of this application is shown. Figure 3 A block diagram of an electronic device according to one embodiment of this application is shown; Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation
[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.
[0021] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.
[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0023] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.
[0024] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.
[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.
[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0027] The following detailed description of some embodiments of this application will be provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0028] See Figure 1 The diagram shows a flowchart illustrating a method for processing training data of an engine health management model based on expert experience, according to an embodiment of this application.
[0029] like Figure 1 As shown, a method for processing training data for an engine health management model based on expert experience is presented, specifically including steps S100 to S300.
[0030] refer to Figure 1 Step S100: Obtain data and protocols from the multi-source dataset server and perform protocol parsing.
[0031] In some feasible embodiments, based on the foregoing scheme, the protocol parsing includes: By using schema mapping technology, combined with statistical analysis, rule bases, and protocols, the acquired data is parsed to identify field types.
[0032] For example, the data acquisition process is as follows: Remotely access the multi-source dataset server via HTTPS / FTP protocol, and automatically download CSV, JSON, and XML format files via secure encryption (HTTPS) or file transfer (FTP) protocol.
[0033] For example, the specific process of protocol parsing is as follows: 1. Metadata parsing: Parse the protocol file and extract file structure information (column names, data type labels).
[0034] 2. Sample Statistics: Perform statistical analysis on the sample data for each field. You can configure relevant statistical rules as needed, such as mean, standard deviation, number of unique values, and null value rate. For example, "null value rate" = "number of null values" / "total number of samples" × 100%. If the null value rate exceeds the threshold (e.g., 30%), the data cleaning process will be triggered.
[0035] 3. Type Inference: Identify types such as timestamps, text, and numbers. If the field value matches the date format (e.g., `regular expression match(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})`), it is marked as a timestamp type and converted to the standard format.
[0036] Continue to refer to Figure 1 Step S200: Define hierarchical If-Then rules based on expert experience, and perform rule transformation, rule verification, and storage. Select the validated hierarchical If-Then rule to map and transform the data after protocol parsing, and obtain the initial dataset.
[0037] For example, the hierarchical If-Then rule is defined as follows: If (speed > And (temperature > Then mark it as "high risk"; in, and The dynamic thresholds preset by experts can be adjusted according to the engine model.
[0038] The defined hierarchical If-Then rules support nested structures (such as multi-level condition combinations).
[0039] In some feasible embodiments, based on the foregoing scheme, the step of defining hierarchical If-Then rules by combining expert experience, and performing rule transformation, rule verification, and storage includes: The hierarchical If-Then rules are transformed into rules, with rule types including classification feature information and threshold parameters; One-hot encoding is used to convert categorical feature information into vectors; The threshold parameters are converted into numerical variables usable by the model and support adaptation to multiple engine models. The transformation rules are verified, and once verified, the rule is saved to the rule base. In some feasible embodiments, based on the aforementioned scheme, the step of selecting the verified hierarchical If-Then rules to map and transform the data after protocol parsing to obtain the initial dataset includes: Obtain the verified rule base; Select validated rules from the rule base to perform data transformation on the data parsed by the protocol, and generate the initial dataset.
[0040] It should be noted that data transformation is to match the original protocol data with expert rules and output transformed data (which can reduce the dimensionality of the data) so that the model can use it.
[0041] The threshold parameter is generated based on the engine model mapping.
[0042] The rules are defined as follows: .
[0043] Continue to refer to Figure 1 Step S300: According to the model training requirements, the initial dataset is divided into a training set and a test set.
[0044] In some feasible embodiments, based on the foregoing scheme, dividing the initial dataset into a training set and a test set according to model training requirements includes: Depending on the model training requirements, the dataset can be divided into training and test sets using K-Fold cross-validation, stratified sampling, or user-defined methods.
[0045] For example, the partitioning process for K-Fold cross-validation is as follows: Divide the dataset into K subsets (K=5 is recommended, but can be adjusted from 3 to 10), using the subsets as the validation set and the remainder as the training set, as defined in the following formula: ; in For the entire set; Let the i-th subset be used as the verification set; for Removed from the middle The set of is used as the training set.
[0046] For example, stratified sampling: stratification is performed based on label proportions to ensure balanced samples in each stratum. ; in Let be the number of training samples sampled from the j-th class. This represents the total number of training samples. Let J be the total number of samples in class j. This represents the total number of samples.
[0047] User-defined proportions: Divide the dataset according to the proportion selected by the user (e.g., 80% training set / 20% test set).
[0048] Based on the same inventive concept, embodiments of this application also provide an engine health management model training data processing system based on expert experience.
[0049] For example, see Figure 2 The system includes: The data acquisition module is used to acquire data and protocols from a multi-source dataset server and perform protocol parsing. The expert rule engine is used to define hierarchical If-Then rules by combining expert experience, and to perform rule transformation, rule verification and storage; and to select verified hierarchical If-Then rules to map and transform parameters of the data after protocol parsing to obtain the initial dataset; The training scheduling module is used to divide the initial dataset into a training set and a test set according to the model training requirements.
[0050] like Figure 2 As shown, the system obtains data and protocols from a multi-source dataset server, processes the data to generate a dataset in a unified format, divides the dataset into training and test sets according to preset rules, uploads the training and test sets, along with the generated expert rule files, to the model training server, and starts model training; it also receives the training results from the model training server and provides model designers with a way to query the model training results.
[0051] like Figure 2 As shown below, an application example of this system is provided.
[0052] 1) System Deployment Architecture This system supports distributed deployment and includes three types of core nodes: Multi-source data access nodes: deployed on the data processing server (recommended configuration: 24-core CPU, 64GB memory, GPU accelerator card, 10TB storage, ≥100Mbps concurrent transmission capability); Rule engine node: Deployed on the data processing server (capable of high-concurrency matching calculation of 1000+ rules per second); Model training nodes: consist of a GPU server cluster (recommended configuration: ≥2 servers, each with an NVIDIA A100 GPU and 512GB of memory), supporting model training.
[0053] Inter-node communication includes two types: Inter-node communication within a single server: High-speed data exchange is achieved using shared memory and inter-process communication (IPC); Communication between server nodes: Transmission is achieved through an encrypted VPN tunnel, and data is protected by a high-strength encryption algorithm (such as 3DES, which can be selected according to requirements) to ensure communication security.
[0054] 2) Module-by-module implementation steps Data acquisition module implementation: Protocol configuration: Configure access information for multiple data servers (HTTPS / FTP address, port, authentication credentials such as username / password / certificate) in the system management interface. Supports parallel configuration of ≥10 data sources and automatically generates a data source health status monitoring dashboard (checks connection status every 5 minutes).
[0055] Parsing rule configuration: Upload the protocol description file (such as XML format) of each data source. The system will automatically parse and generate a field mapping table. Users can adjust the field type in the visual interface (such as changing "Runtime Length" from text to numeric). After adjustment, a preview sample will be generated in real time (200 data points will be extracted to show the conversion effect).
[0056] Automated scheduling: Set the data synchronization cycle (e.g., daily full synchronization), and trigger an alarm mechanism when the synchronization task fails.
[0057] Implementation of the expert rule engine: Rule entry: Experts can enter If-Then rules through the control software, which supports dragging and dropping to generate nested conditions (such as "(RPM>" θ_A ")And(Temperature>" θ_B ")"). After the entry is completed, the software will automatically detect syntax errors (such as missing Then statement or undefined threshold).
[0058] Threshold parameter configuration: For different engine models (such as a turbofan engine or piston engine), enter the baseline values and adjustment coefficients of thresholds such as θ_A and θ_B in the parameter configuration table (such as θ_A is reduced by 2% for every 10°C increase in ambient temperature). The system will automatically generate the threshold matrix for each model based on the mapping function (such as f("engine model")).
[0059] Rule activation process: After a new rule is entered, it enters the trial operation phase (only effective for 5% of the data). The rule matching accuracy is monitored for 72 hours (compared with the results of manual annotation). If the accuracy is ≥ 95%, it will be automatically converted into a formal rule; otherwise, the expert review process will be triggered.
[0060] Initial dataset output process: Based on the selected rules, receive the parsed data transmitted by the data acquisition module, perform data transformation, and obtain the initial dataset.
[0061] Training scheduling module implementation: Dataset partitioning configuration: Select the partitioning method in the training task creation interface. For example, when using K-Fold cross-validation, the user enters the value of K (default 5), and the system automatically generates K training / validation sets and displays the label distribution histogram of each subset. When using stratified sampling, the system automatically calculates the number of samples for each label category (accurate to ten decimal places) and supports manual fine-tuning (adjustment range not exceeding ±5%).
[0062] Training task monitoring: After training starts, GPU utilization (refreshed every second), training progress and other information are displayed in real time. When GPU utilization is below 30% for 10 consecutive minutes, resource reallocation is automatically triggered (allocating idle GPU computing power to other tasks).
[0063] Anomaly Handling: When training is interrupted, the system automatically saves breakpoint information such as model parameters and attempts to restart within 1 minute. If the restart fails, it uses backup server resources (reserving 20% redundant computing power) to ensure data consistency for task continuation (verifying sample hash values before and after the breakpoint).
[0064] like Figure 3 As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the above-described method for processing training data of an engine health management model based on expert experience.
[0065] Since the electronic device described in this embodiment is the device used to implement the engine health management model training data processing system based on expert experience in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application is within the scope of protection of this application.
[0066] In practice, when the computer program 311 is executed by the processor, it can implement any of the embodiments corresponding to the first aspect.
[0067] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.
[0068] It should be noted that, Figure 4 The computer system 400 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0069] like Figure 4 As shown, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from storage portion 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 403. The CPU 401, ROM 402, and RAM 403 are interconnected via bus 404. An Input / Output (I / O) interface 405 is also connected to bus 404.
[0070] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.
[0071] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of this application.
[0072] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.
[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0074] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.
[0075] In another aspect, this application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the engine health management model training data processing method based on expert experience described in the above embodiments.
[0076] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the engine health management model training data processing method based on expert experience described in the above embodiments.
[0077] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0078] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.
[0079] Other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.
Claims
1. A method for processing training data for an engine health management model based on expert experience, characterized in that, include: Data and protocols are obtained from a multi-source dataset server, and the protocols are parsed. Based on expert experience, hierarchical If-Then rules are defined, and rule transformation, verification, and storage are performed. The verified hierarchical If-Then rules are selected to map and transform the data after protocol parsing to obtain the initial dataset. Based on the model training requirements, the initial dataset is divided into a training set and a test set.
2. The method according to claim 1, characterized in that, The protocol parsing process includes: By using schema mapping technology, combined with statistical analysis, rule bases, and protocols, the acquired data is parsed to identify field types.
3. The method according to claim 1, characterized in that, The process of defining hierarchical If-Then rules based on expert experience, and then performing rule transformation, rule validation, and storage includes: The hierarchical If-Then rules are transformed into rules, with rule types including classification feature information and threshold parameters; One-hot encoding is used to convert categorical feature information into vectors; The threshold parameters are converted into numerical variables usable by the model and support adaptation to multiple engine models. The transformation rules are validated, and once the validation is successful, the rule is saved to the rule base.
4. The method according to claim 3, characterized in that, The selected, validated hierarchical If-Then rules are used to map and transform the parsed data to obtain an initial dataset, including: Obtain the verified rule base; Select validated rules from the rule base to perform data transformation on the data parsed by the protocol, and generate the initial dataset.
5. The method according to claim 1, characterized in that, The step of dividing the initial dataset into a training set and a test set according to the model training requirements includes: Depending on the model training requirements, the initial dataset is divided into training and test sets using K-Fold cross-validation, stratified sampling, or user-defined methods.
6. The method according to claim 5, characterized in that, The initial dataset is divided into training and test sets using K-Fold cross-validation, including: The initial dataset is divided into K subsets, which are used sequentially as the validation set and the remainder as the training set. K is a positive integer, and the formula is defined as follows: ； in, For the entire set; Let the i-th subset be used as the verification set; for Removed from the middle The set of is used as the training set.
7. The method according to claim 5, characterized in that, The initial dataset is divided into training and test sets using stratified sampling, including: The samples are divided into strata according to the proportion of labels to ensure that the samples in each stratum are balanced. ； in Let be the number of training samples sampled from the j-th class. This represents the total number of training samples. Let J be the total number of samples in class j. This represents the total number of samples.
8. A training data processing system for an engine health management model based on expert experience, characterized in that, include: The data acquisition module is used to acquire data and protocols from a multi-source dataset server and perform protocol parsing. The expert rule engine is used to define hierarchical If-Then rules by combining expert experience, and to perform rule transformation, rule validation and storage; Then, the validated hierarchical If-Then rules are selected to map and transform the data after protocol parsing, resulting in the initial dataset; The training scheduling module is used to divide the initial dataset into a training set and a test set according to the model training requirements.
9. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-7.
10. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer instructions; The processor is configured to invoke computer instructions stored in the memory, causing the electronic device to perform the method as described in any one of claims 1-5.