CN115729536B - Generalized equipment fault prediction and health management modeling system - Google Patents

Generalized equipment fault prediction and health management modeling system Download PDF

Info

Publication number
CN115729536B
CN115729536B CN202211510198.9A CN202211510198A CN115729536B CN 115729536 B CN115729536 B CN 115729536B CN 202211510198 A CN202211510198 A CN 202211510198A CN 115729536 B CN115729536 B CN 115729536B
Authority
CN
China
Prior art keywords
phm
model
data
modeling
visual
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211510198.9A
Other languages
Chinese (zh)
Other versions
CN115729536A (en
Inventor
张
景特
陈勇刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinhang Digital Technology Co ltd
Original Assignee
Jinhang Digital Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinhang Digital Technology Co ltd filed Critical Jinhang Digital Technology Co ltd
Priority to CN202211510198.9A priority Critical patent/CN115729536B/en
Publication of CN115729536A publication Critical patent/CN115729536A/en
Application granted granted Critical
Publication of CN115729536B publication Critical patent/CN115729536B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Stored Programmes (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention provides a generalized equipment fault prediction and health management modeling system, which comprises: the PHM engineering management module is used for completing the creation of PHM engineering, the PHM data management module is responsible for completing the import and management of the data of each type of sensor, the visual PHM modeling module is used for expressing PHM model elements by using different types of primitives based on the visual modeling technology of graph theory, and realizing the open modeling of models such as data processing, fault diagnosis, prediction, health assessment and the like, and the visual PHM model training module is used for completing the multiple training, verification assessment and optimization of the model aiming at a machine learning algorithm. Therefore, the invention is a visual universal PHM service model modeling system integrating the functions of design, development, verification evaluation, iterative optimization and the like, which is used for meeting PHM development requirements and mainly solving the problem of generalized development support of PHM service models and the problem of rapid development iteration of service models.

Description

Generalized equipment fault prediction and health management modeling system
Technical Field
The invention relates to a fault Prediction and Health Management (PHM) technology in equipment maintenance and guarantee, which is a universal, rapid development and iterative optimization system of a PHM service model.
Background
In the field of equipment maintenance and assurance, fault Prediction and Health Management (PHM) technology focuses on utilizing advanced sensor integration and predicting, diagnosing, monitoring and managing the status of equipment by means of various algorithms and intelligent models. In recent years, the rapid development of fault diagnosis and health management has led to the transition of maintenance and guarantee modes from state monitoring to state management, which is an innovative scheme for testing and maintenance diagnosis and is a comprehensive fault detection, isolation and prediction and health management technology. PHM technology was introduced not to directly eliminate system failures, but to know and predict when a failure might occur; or triggering a series of maintenance activities when an initial failure occurs, thereby realizing autonomous guarantee and reducing the targets of equipment use and guarantee cost.
PHM design, development and verification are a system engineering, and key technologies such as PHM graphical modeling, inference engine, integrated database, PHM model networking collaborative design, verification and evaluation are required to be solved, so that a design development platform integrating multiple functions such as design, development, verification and evaluation is required to meet PHM development requirements. At present, the foreign PHM system technology has a plurality of engineering application examples, but the foreign PHM system technology is relatively weak in the aspect of China, and research work on the PHM system technology is urgently needed to be carried out. The PHM system design, development and face certificate platform can be used for PHM design, auxiliary development, simulation, evaluation and release, and the PHM software is matured through repeated iteration. Through breakthrough of visual hierarchical modeling, diagnosis and prediction algorithm model library design of the PHM system and PHM system verification and evaluation technology, comprehensive grasp of PHM platform software design and development technology is promoted, and the PHM system visual hierarchical modeling method has important significance for improving PHM technology level in China.
The PHM system visual design and interaction technology is to complete modeling of the whole PHM system in a visual mode, on a visual software platform, a PHM design model diagram can be conveniently completed by using various primitives provided by the system through mouse operation for different object users, PHM layering model index distribution is built based on an index compromise coefficient method, PHM layering model design level is analyzed and evaluated, PHM testing schemes are designed and generated, and tests are organized according to a certain sequence to form a model development and operation module for grading, system-level PHM layering and visualization. Therefore, a new PHM system can be built, the development process of the PHM system is greatly simplified, the development efficiency is improved, and the development time is saved.
The visual universal PHM design software is a platform for assisting PHM system development, and specific actual PHM system development, design development factors and visual technologies are organically combined in the platform, so that the visualization of a modeling process, the visualization of a model running process and the visualization of data are respectively realized.
The PHM system of the large equipment is divided into member level and regional level station system level three-level management according to the function level of the job. The member-level PHM system realizes self fault detection and state monitoring, but does not predict and isolate faults, and submits fault and state reports to corresponding regional levels for diagnosis through corresponding data buses. Based on PHM data such as fault reports and state information of the member systems, the regional PHM system utilizes a model-based reasoning and rule-based reasoning algorithm in the expert system to realize fusion diagnosis of PHM data information of the regional I, forms a regional PHM fault state report, and transmits the regional PHM fault state report to the system-level PHM system for fusion diagnosis and decision. The prior art has the following problems:
the PHM algorithm model development in China has low generalization degree, and the suitability of the same algorithm model in other environments is poor; the PHM software design has the advantages that the variety of software tools developed is multiple, the interfaces are not uniform, and the integration is difficult; in the aspect of PHM model development in China, a mature software development supporting tool is lacking, cases are deficient, the flow is not standard and standard is not uniform, and the problem of low overall development efficiency is caused.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a generalized equipment failure prediction and health management modeling system, including:
the PHM engineering management module is used for completing the establishment of PHM engineering, supporting the design of a multi-level 'system level-regional level-component level' equipment structure, configuring and managing related parameters thereof, forming a sensor parameter matrix of the equipment and associating the sensor parameter matrix with PHM data;
the PHM data management module is responsible for completing the importing and the management of the sensor data of each type of equipment, supporting the user-defined data format, and providing input data for visual PHM modeling and visual PHM model training by the equipment state data, which is necessary data for the fault prediction and the monitoring management of the equipment;
the visual PHM modeling module is based on a visual modeling technology of graph theory, expresses PHM model elements by utilizing different types of primitives, realizes open modeling of models such as data processing, fault diagnosis, prediction, health assessment and the like, provides modeling support for PHM functional models of different objects and multiple types, greatly improves the efficiency and generalized support of model development, provides basic algorithm primitives for visual PHM modeling by a generalized algorithm library, provides basic index verification algorithm primitives for PHM model verification indexes, and uses results trained by the visual PHM model training module in the PHM modeling module for use and operation;
the visual PHM model training module is used for completing multiple training and optimization of the model aiming at a machine learning algorithm, providing basic parameter adjustment parameters in various algorithm models, supporting classification of training data and test data of data in the PHM data management module, enabling the training data to be responsible for providing output data for the training model, enabling the training data to have clear fault characteristics, helping the algorithm to complete and optimize, and evaluating training results in a test operator, wherein the evaluated indexes are provided by PHM model verification indexes. And (3) referencing, loading and running the well trained algorithm result in the visual PHM model training module to complete the issuing work of the algorithm.
The PHM model verification index management module is used for providing an evaluation and verification operator for PHM in the PHM model verification index after model development is completed, and is connected with the PHM model to quickly obtain an evaluation result so as to help a user to complete quick debugging on PHM model training and optimization;
the verification indexes include a successful detection rate (PODS), a false alarm rate (POFA), an Accuracy (Accuracy), a receiver operation characteristic curve, a detection threshold (detection threshold), an overall confidence (overallconfildence), stability (Stability), a condition sensitivity (duty sensitivity), a noise sensitivity (noise sensitivity), and the like. Specific metrics of predictive capability include Accuracy (Accuracy), precision (Precision), timeliness of prediction to failure time (TimeToFailure, TTF), confidence of prediction (Confidence), similarity, sensitivity (Sensitivity).
The generalized algorithm library provides generalized primitive algorithms required by modeling for the visual PHM modeling module and the visual PHM model training module, and provides functions of algorithm addition and deletion, query, modification, version lifting and expansion.
According to another aspect of the present invention, a generalized equipment failure prediction and health management modeling system is provided, comprising the steps of:
step 1: the PHM engineering management module creates PHM engineering, creates specific equipment, a multi-level system level-area level-component level structure of the equipment in the engineering, describes health key information in the structure, binds the equipment and the PHM model after the PHM model is built, and develops PHM work aiming at the specific equipment;
step 2: the PHM data management module is used for importing sensor data of a single device, supporting the time sequence data importing of multiple sensors and a single sensor, wherein one file is a data set, and the acquisition characteristics and the data characteristics of the sensors are defined after importing;
step 3: the visualized PHM modeling module creates a PHM model, drags operators in the generalized algorithm library, and combines the operators into a complete DAG data stream, thereby completing the editing of the algorithm; after editing is completed, the PHM model is released, and the released PHM model is bound with equipment; after binding, loading equipment sensor data and running a PHM model to obtain state monitoring, fault diagnosis, fault prediction and health assessment tasks for the equipment;
step 4: for a model to be trained, a visual PHM model training module is dragged into a machine learning algorithm and PHM model verification indexes, a training effect is given by the verification indexes, multiple times of training and optimizing of the model are completed, and finally a model training result is obtained, and the result can be related and quoted in the visual PHM modeling module;
step 5: when the user needs to expand the algorithm by himself, a new algorithm is created in the general algorithm library, and the new algorithm is used as a general operator in the visual PHM modeling module by issuing a conversion operator.
The beneficial effects are that:
the invention provides a generalized PHM modeling function, which can support PHM modeling from parts, subsystems, regional levels and equipment levels; a standard interface mode is adopted, so that model exchange is facilitated; the health state evaluation of the life parts can be realized, the life knowledge is added, and the residual life prediction is realized; supporting the embedding of various artificial intelligence algorithms/models to form the comprehensive integration of the PHM model and the artificial intelligence model; according to the user requirements, a code compiling function can be selected to generate an executable embedded running program; the visual model editing mode is adopted, so that the interface is friendly; the test verification of the model is supported, and indexes such as fault detection rate, fault isolation rate, prediction coverage rate, prediction precision and the like can be given; the PHM case library is provided with a generalized algorithm library and a component library.
The invention provides a visual PHM modeling environment, follows the primitives of PHM basic development flow, has an open system architecture, ensures that the platform meets the requirements of usability and expandability, provides a convenient and simple modeling environment, and completes the modeling of the PHM model by adopting a graphical and layering method. The graphical representation is to represent the PHM model of the system by using the topological graph composed of the graphic elements and the attributes thereof, and aiming at complex equipment, a user can conveniently know the equipment mechanism and the algorithm calculation process by using the application of the visual technology, and the visualization is controlled, managed and monitored by the visual reduction process of the graphic element combination process, so that a clear mapping relation is established between people and PHM system development tasks, the monitoring of the PHM system development process is realized, and the whole development process is transparent.
Layering refers to establishing a model according to a hierarchical structure of an equipment system, and specifically establishing which layer of model is determined according to the purposes of testing and diagnostic analysis. If in system level testing it is necessary to isolate the occurrence of a fault to the subsystem level, the topology map should consist of primitives, attributes, etc. representing the subsystem. By adopting a hierarchical modeling method, the components of the upper stage can be formed by using the information of the components of the lower stage. Hierarchical modeling provides conditions for object-oriented model development. The modeling environment supports the encapsulation of objects, forming a high level component, the newly generated component containing all the information that makes up his substructure. Through hierarchical modeling, complex equipment composition relation can be rapidly realized, hierarchical reasoning and fault diagnosis are realized in fault diagnosis, and the fault diagnosis accuracy is high.
Drawings
Fig. 1: the generalized equipment fault prediction and health management modeling software system is composed;
fig. 2: hierarchical modeling of equipment configuration;
fig. 3: PHM model verification index;
fig. 4: PHM model training and optimizing process;
fig. 5: and the general equipment fault prediction and health management software modeling system core module relation.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without the inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
The invention provides a generalized equipment fault prediction and health management modeling system, which is a software platform for the PHM service model of large complex equipment and is universal, quick in development and iteration technology, integrates the functions of hierarchical modeling, PHM service model visual modeling, PHM service model verification, algorithm quick iteration optimization and universal algorithm management of the large complex equipment, and provides a PHM service model meeting the requirements for PHM application. As shown in fig. 1.
Referring to fig. 5, a generalized equipment failure prediction and health management modeling system of the present invention includes:
PHM engineering management module (1), PHM data management module (2), visual PHM modeling module (3), visual PHM model training module (4), generalized algorithm library (5), PHM model verification index management module (6).
The PHM engineering management module (1) creates engineering, defines a multi-level system level-regional level-component level structure of the equipment, and binds the equipment with a model created by the visual PHM modeling module (3).
The PHM data management module (2) is used for importing and managing sensor data and defining file formats for different data of the file formats; the imported equipment sensor data is used as data input of a visual PHM modeling module (3) and a visual PHM model training module (4). The equipment sensor data is associated with equipment in the project.
And the visualized PHM modeling module (3) completes PHM model algorithm modeling and can be bound with equipment in the PHM engineering management module (1) after being released. After PHM data is loaded, a PHM model is operated, an operation result of the model is obtained, and state monitoring, fault diagnosis, fault prediction and health assessment results of the equipment are given.
And the visual PHM model training module (4) is dragged into a machine learning algorithm and PHM model verification indexes, the verification indexes give training effects, the model is trained and optimized for multiple times, and finally, a model training result is obtained, and the result can be related and quoted in the visual PHM modeling module (3).
And the generalized algorithm library (5) is used for creating a new algorithm in the generalized algorithm library, issuing a conversion operator, and using the new algorithm as a generalized operator in the visual PHM modeling module (3).
And (6) the PHM model verification index management is closely attached to the output result of the PHM algorithm model, a series of verification operators including fault accuracy, life prediction accuracy, health evaluation accuracy and the like are provided, and the verification result of the model can be calculated.
Specifically, the PHM engineering management module is used for completing the establishment of PHM engineering, supporting the design of a multi-level 'system level-area level-component level' equipment structure, configuring and managing related parameters thereof, forming a sensor parameter matrix of the equipment, and associating the sensor parameter matrix with PHM data;
specifically, the PHM data management module is responsible for completing the importing and management of the sensor data of each type of equipment, supporting the user-defined data format, and providing input data for visual PHM modeling and visual PHM model training by the equipment state data, which is necessary data for the fault prediction and monitoring management of the equipment;
specifically, the visualized PHM modeling module expresses PHM model elements by utilizing different types of primitives based on a visual modeling technology of graph theory, realizes open modeling of models such as data processing, fault diagnosis, prediction, health assessment and the like, provides modeling support for PHM functional models of different objects and multiple types, provides basic algorithm primitives for visualized PHM modeling by a generalized algorithm library, provides basic index verification algorithm primitives for the PHM model verification index, and uses results trained by a visualized PHM model training module in the PHM modeling module for use and operation;
specifically, the visual PHM model training module is used for completing multiple training and optimization of the model aiming at a machine learning algorithm, providing basic parameter adjustment parameters in various algorithm models, supporting classification of training data and test data of data in the PHM data management module, enabling the training data to be responsible for providing output data for the training model, enabling the training data to have definite fault characteristics, helping the algorithm to complete and optimize, and evaluating training results in a test operator, wherein the evaluated indexes are provided by PHM model verification indexes. And (3) referencing, loading and running the well trained algorithm result in the visual PHM model training module to complete the issuing work of the algorithm.
Specifically, the PHM model verification index management is used for providing an evaluation and verification operator for the PHM model after model development is completed, and is connected with the PHM model to quickly obtain an evaluation result, so that a user is helped to complete quick debugging on PHM model training and optimization;
the verification indexes include a successful detection rate (PODS), a false alarm rate (POFA), an Accuracy (Accuracy), a receiver operation characteristic curve, a detection threshold (detection threshold), an overall confidence (overallconfildence), stability (Stability), a condition sensitivity (duty sensitivity), a noise sensitivity (noise sensitivity), and the like. Specific metrics of predictive capability include Accuracy (Accuracy), precision (Precision), timeliness of prediction to failure time (TimeToFailure, TTF), confidence of prediction (Confidence), similarity, sensitivity (Sensitivity).
Specifically, the generalized algorithm library provides generalized primitive algorithms required by modeling for the visual PHM modeling module and the visual PHM model training module, and provides functions of algorithm addition and deletion, query, modification, version lifting and expansion.
The system can realize hierarchical modeling of complex equipment, provide hierarchical configuration structural modeling of equipment level, system level and finished product level according to the division of equipment system and hierarchical structure, realize rapid programming, development, testing and iteration of PHM models with different types and functions, coordinate and distribute sensor parameters of different levels of equipment, enhance FMECA information, set diagnosis rules while compiling fault modes and establish a fault signal matrix.
In the specific implementation, a model is built according to the hierarchical structure of the equipment configuration, and the specific level of the model to be built is determined according to the purposes of testing and diagnostic analysis. If in system level testing it is necessary to isolate the occurrence of a fault to the subsystem level, the topology map should consist of primitives, attributes, etc. representing the subsystem. By adopting a hierarchical modeling method, the components of the upper stage can be formed by using the information of the components of the lower stage. Hierarchical modeling provides conditions for object-oriented model development. The modeling environment supports the encapsulation of objects, forming a high level component, the newly generated component containing all the information that makes up its substructures. Modeling can adopt a top-down mode and a bottom-up mode according to the actual condition of the object, as shown in fig. 2;
the PHM service model visual modeling module of the system can realize PHM service model visual modeling, is used for defining multidimensional visual PHM algorithm graphic elements, PHM algorithm graphic element attributes, common attributes of the PHM service model, configuration rules and configuration of control model visual graphic elements by a user, and is convenient for the user to perform visual PHM service model modeling. The visual modeling adopts a data flow mode, various graphic elements are mainly connected through connecting lines to form a directed graph, in a canvas, graphic element nodes are connected among nodes through the directed data connecting lines to represent the flow direction of data, the whole data flow modeling is a directed connection graph for realizing the data, the data flows according to logic, and a PHM service is finally completed under the combination of different functional graphic elements. One data stream in the system is called a PHM model.
PHM visual modeling is to build PHM classification primitive classes on the basis of primitive library, class members comprise names, parameters, implementation functions and the like, and different classes are added to realize different PHM analysis primitives; aiming at different analysis objects, different PHM analysis primitives are utilized, after the primitive parameters are edited and the implementation functions are selected, the primitives are connected, and a PHM visual analysis model diagram of the object is formed.
Firstly, importing the obtained measuring point/sensor layout optimization design scheme into a testability analysis case base in an XML file form, and storing the obtained measuring point/sensor layout optimization design scheme as PHM aided design knowledge; according to the OSA-CBM architecture, the PHM system development flow is roughly divided into data acquisition, data preprocessing, feature extraction, fault diagnosis, fault prediction, health assessment, etc., and these functions are packaged in the form of primitives.
In addition to hierarchical device modeling and visual PHM business modeling capabilities, it is most important to be able to verify and evaluate the PHM model of the observed object. In the measurement and evaluation process of the PHM model, corresponding verification works are respectively carried out from the two aspects of fault diagnosis capability and fault prediction capability, corresponding measurement and evaluation indexes are respectively selected according to different selected verification algorithms to carry out PHM capability verification, finally, verification results are compared with specified values to carry out qualification judgment, verification conclusion is given, and a user carries out iterative optimization on the service model according to the conclusion.
Specifically, a typical algorithm is packaged according to a fault evaluation method of a complex equipment system, a PHM model verification index management module is constructed, and the complex equipment system can be subjected to state monitoring and health condition estimation to evaluate the algorithm. And packaging the evaluation algorithm into a visual graphic primitive, adding the corresponding graphic primitive when modeling the PHM service model, and obtaining an evaluation result through the operation model. The verification index comprises the following contents:
successful detection rate (PODS), false positive rate (POFA), accuracy (Accuracy), receiver operating characteristics, detection threshold (detection threshold), overall confidence (overallconfildence), stability (Stability), condition sensitivity (duty sensitivity), noise sensitivity (noise sensitivity), and the like. Specific metrics of predictive capability include Accuracy (Accuracy), precision (Precision), timeliness of prediction to failure time (TimeToFailure, TTF), confidence of prediction (Confidence), similarity, sensitivity (Sensitivity), etc., as shown in fig. 3;
furthermore, the system of the invention provides a large number of generalized PHM algorithm models, and in practical application, the diagnosis, prediction and evaluation models are required to be verified and iteratively corrected through training. The function can complete the training of PHM algorithm model according to the verification result (precision, error, etc.) expected by the user, and continuous iterative optimization is realized.
The general algorithm library in the system comprises a PHM general algorithm, the PHM general algorithm is used for completing the appointed function through a machine learning method, and the PHM general algorithm is divided into a training operator and a predictor. Training operators: training an algorithm through training data to obtain a training result after fitting/approaching, wherein the training result is usually stored in a parameter value mode; predictors: the operator of the training result is used for inputting the training result, providing initial parameter configuration for the algorithm according to the parameters in the result, and completing the service requirement in the scene.
The specific use process is shown in fig. 4, training is completed by newly building a training task in the PHM model training task, adding a training operator, inputting the training operator into a predictor to obtain a test result, and the verifying operator is responsible for verifying the test result (including fault accuracy, life prediction accuracy, health evaluation accuracy and the like), so that a user can perform optimization of an algorithm through the verification result.
The general algorithm library is used for managing various calculation algorithms in PHM modeling analysis and data analysis according to operators packaged by operator standards, and taking the operators as minimum combinable units of PHM modeling, wherein the PHM business model is a data flow model formed by a plurality of operators, and the functions of necessary equipment state monitoring, fault diagnosis, life prediction and the like are realized by loading data.
The PHM business model algorithm development module can be further included, the primitive algorithm can be an open source algorithm such as a Python function, and the like, so that a user can conveniently carry out algorithm improvement. Meanwhile, the case library and the secondary development sub-environment support the addition of new cases and the encapsulation of new algorithms so as to expand the engineering application range. Two technologies of Python script encapsulation and FMI model encapsulation are selected for realizing the thought, and Python encapsulation is taken as an example, and a user can package Python codes through the function to form primitives which complete specific functions. When running, the software calls python, inputs the input variable of the primitive into the python environment, runs the script, and returns the obtained output variable to the software as the output of the primitive.
The general algorithm is designed around PHM business, and comprises algorithms of data processing, state monitoring, fault diagnosis, fault prediction and health evaluation, wherein the algorithms are converted into operators in the system, and the operators can perform input and output operations.
And the PHM data management module is mainly used for managing equipment data belonging to the engineering. The data mainly comprises single equipment object basic data, single equipment object operation data, fault data, task operation result data and simulation data management to which the engineering belongs.
PHM data is a core asset for researching PHM equipment, PHM equipment data is a generic name for various sensor data of equipment, all models and PHM work development need to be reflected by the sensor data to represent equipment states, and in the module, various sensor data of an object to be researched are managed in an engineering range.
PHM data is data with a specific format of the system, supports the importing of data with formats such as txt, csv and the like, and the imported data needs to be filled with necessary Phm information. Providing the functions of adding, editing, deleting and viewing engineering data.
While the foregoing has been described in relation to illustrative embodiments thereof, so as to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but is to be construed as limited to the spirit and scope of the invention as defined and defined by the appended claims, as long as various changes are apparent to those skilled in the art, all within the scope of which the invention is defined by the appended claims.

Claims (4)

1. A generalized equipment failure prediction and health management modeling system, comprising:
the PHM engineering management module is used for completing the establishment of PHM engineering, supporting the design of a multi-level 'system level-regional level-component level' equipment structure, configuring and managing related parameters, forming a sensor parameter matrix of the equipment and associating the sensor parameter matrix with PHM data;
the PHM data management module is responsible for completing the importing and the management of the sensor data of each type of equipment, supporting the user-defined data format, and providing input data for visual PHM modeling and visual PHM model training by the equipment state data for the fault prediction and the monitoring management of the equipment;
the visual PHM modeling module is based on a visual modeling technology of graph theory, expresses PHM model elements by utilizing different types of primitives, realizes open modeling of data processing, fault diagnosis, prediction and health assessment, provides modeling support for PHM functional models of different objects and multiple types, provides basic algorithm primitives for visual PHM modeling by a generalized algorithm library, provides basic index verification algorithm primitives for PHM model verification indexes, and uses training results of a visual PHM model training module in the visual PHM modeling module;
the visual PHM model training module is used for completing multiple training and optimization of the model aiming at a machine learning algorithm, providing basic parameter adjustment parameters in various algorithm models, supporting training data and test data classification of data in the PHM data management module, enabling the training data to be responsible for providing input data for the training model, enabling the training data to have definite fault characteristics, helping the algorithm to complete optimization, evaluating training results in a test operator, enabling an evaluated index to be provided by a PHM model verification index, enabling algorithm results trained by the visual PHM model training module to be cited, loaded and operated in the visual PHM modeling module, and completing issuing work of the algorithm.
2. The generalized equipment failure prediction and health management modeling system of claim 1, further comprising:
and the PHM model verification index module is used for providing an evaluation and verification operator for PHM in the PHM model verification index after model development is completed, and can quickly obtain an evaluation result by connecting with the PHM model.
3. The generalized equipment failure prediction and health management modeling system of claim 1, further comprising:
the generalized algorithm library provides generalized primitive algorithms required by modeling for the visual PHM modeling module and the visual PHM model training module, and provides functions of algorithm addition and deletion, query, modification, version lifting and expansion.
4. The generalized equipment fault prediction and health management modeling method is characterized by comprising the following steps of:
step 1: the PHM engineering management module creates PHM engineering, creates specific equipment, a multi-level system level-area level-component level structure of the equipment in the engineering, describes health key information in the structure, binds the equipment and the PHM model after the PHM model is built, and develops PHM work aiming at the specific equipment;
step 2: the PHM data management module is used for importing sensor data of a single device, supporting the importing of time sequence data of multiple sensors and a single sensor, wherein one file is a data set, and the acquisition characteristics and the data characteristics of the sensors are defined after importing;
step 3: the visualized PHM modeling module creates a PHM model, drags operators in the generalized algorithm library, and combines the operators into a complete data stream, thereby completing the editing of the algorithm; after editing is completed, the PHM model is released, and the released PHM model is bound with equipment; after binding, loading equipment sensor data and running a PHM model to obtain state monitoring, fault diagnosis, fault prediction and health assessment tasks for the equipment;
step 4: for a model to be trained, a visual PHM model training module is dragged into a machine learning algorithm and PHM model verification indexes, a training effect is given by the verification indexes, multiple times of training and optimizing of the model are completed, and finally a model training result is obtained, and the result can be related and quoted in the visual PHM modeling module;
step 5: when the user needs to expand the algorithm by himself, a new algorithm is created in the general algorithm library, and the new algorithm is used as a general operator in the visual PHM modeling module by issuing a conversion operator.
CN202211510198.9A 2022-11-29 2022-11-29 Generalized equipment fault prediction and health management modeling system Active CN115729536B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211510198.9A CN115729536B (en) 2022-11-29 2022-11-29 Generalized equipment fault prediction and health management modeling system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211510198.9A CN115729536B (en) 2022-11-29 2022-11-29 Generalized equipment fault prediction and health management modeling system

Publications (2)

Publication Number Publication Date
CN115729536A CN115729536A (en) 2023-03-03
CN115729536B true CN115729536B (en) 2023-10-03

Family

ID=85298967

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211510198.9A Active CN115729536B (en) 2022-11-29 2022-11-29 Generalized equipment fault prediction and health management modeling system

Country Status (1)

Country Link
CN (1) CN115729536B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112784501A (en) * 2021-03-23 2021-05-11 中国核电工程有限公司 Modeling system and method for residual life prediction model of equipment and prediction system
CN114510519A (en) * 2022-01-25 2022-05-17 北京航天云路有限公司 Visual analysis method and system based on industrial big data model

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2015247437B2 (en) * 2014-04-17 2018-12-20 Lockheed Martin Corporation Prognostics and health management system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112784501A (en) * 2021-03-23 2021-05-11 中国核电工程有限公司 Modeling system and method for residual life prediction model of equipment and prediction system
CN114510519A (en) * 2022-01-25 2022-05-17 北京航天云路有限公司 Visual analysis method and system based on industrial big data model

Also Published As

Publication number Publication date
CN115729536A (en) 2023-03-03

Similar Documents

Publication Publication Date Title
CN101689111A (en) The automatic management of software requirements verification
CN107085415A (en) Regular composer in process control network
CN107545349A (en) A kind of Data Quality Analysis evaluation model towards electric power big data
Gregoriades et al. Scenario-based assessment of nonfunctional requirements
CN114022005A (en) BIM technology-based engineering cost management system and method
CN108614443A (en) PHM system models are developed and Design for Verification Platform method
CN115617628A (en) Digital twin system, research and development method, equipment and storage medium
De Lemos et al. Analyzing safety requirements for process-control systems
CN114528688A (en) Method and device for constructing reliability digital twin model and computer equipment
Gan et al. A computer-integrated FMEA for dynamic supply chains in a flexible-based environment
Hess et al. The maintenance aware design environment: Development of an aerospace phm software tool
CN110069414A (en) Regression testing method and system
CN116611523B (en) Method and system for predicting interpretable faults of turbofan engine
McInnes et al. Formalizing functional flow block diagrams using process algebra and metamodels
CN115729536B (en) Generalized equipment fault prediction and health management modeling system
CN113742941B (en) Complex equipment system testability modeling platform based on system structure layering analysis
Brodsky et al. Toward smart manufacturing using decision analytics
Zhang et al. Research on Designing an Industrial Product‐Service System with Uncertain Customer Demands
CN105372517A (en) An electrical system modeling method and an electrical system fault diagnosis system based on a qualitative model
CN112214912B (en) External automatic test system and airborne equipment test method
Faheem et al. Analysis of potential errors in technical products by combining knowledge graphs with MBSE approach
Azvine et al. Intelligent process analytics for CRM
Ye et al. Research on the Model Integration in Aircraft PHM Development
Park et al. Verification strategy for artificial intelligence components in nuclear plant instrumentation and control systems
CN113608910B (en) High real-time spacecraft autonomous guarantee fault positioning platform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CB03 Change of inventor or designer information

Inventor after: Zhang Ji

Inventor after: Jing Tete

Inventor after: Chen Yonggang

Inventor before: Zhang Ji

Inventor before: Jing Te

Inventor before: Chen Yonggang

CB03 Change of inventor or designer information