CN109917772B - PHM rapid prototyping system for remotely evaluating equipment state on line - Google Patents
PHM rapid prototyping system for remotely evaluating equipment state on line Download PDFInfo
- Publication number
- CN109917772B CN109917772B CN201811477518.9A CN201811477518A CN109917772B CN 109917772 B CN109917772 B CN 109917772B CN 201811477518 A CN201811477518 A CN 201811477518A CN 109917772 B CN109917772 B CN 109917772B
- Authority
- CN
- China
- Prior art keywords
- phm
- algorithm
- application module
- algorithm model
- module
- 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
Links
Images
Abstract
The invention discloses a PHM rapid prototyping system for remote online evaluation of equipment state, which relates to the field of equipment health evaluation and comprises the following components: the PHM application module is arranged at the equipment and used for acquiring the running data of the equipment through various sensors and evaluating the acquired running data by using an embedded real-time diagnosis tool to obtain the state information of the equipment; the PHM maintenance module is arranged at a remote place and used for establishing a communication circuit connected with the PHM application module and providing an algorithm self-training updating toolkit of an embedded real-time diagnosis tool for the PHM application module through the communication circuit. The PHM algorithm model rapid training and algorithm reconstruction are realized, the corresponding algorithm is updated in time according to different states of the equipment, and the technical problems that the adaptability of a solidified equipment diagnosis evaluation scheme in the prior art is poor and the algorithm updating cost is high are solved.
Description
Technical Field
The invention relates to the field of equipment health assessment, in particular to a PHM rapid prototyping system for remotely and online assessing equipment states.
Background
The working environment of engines and other devices in aviation, ships, high-speed rails and locomotive equipment is severe and the space is narrow in the process of executing tasks, and it is difficult to implement by configuring a set of PHM (probabilistic and Health Management) system integrating data acquisition, algorithm training, feature extraction, diagnosis and evaluation and data storage on the equipment. Especially with certain devices, such as the engine life cycle, the applicability of solidified engine diagnostic evaluation schemes may be progressively reduced, while the cost of algorithm updates may be higher.
Disclosure of Invention
The invention provides a system for remotely evaluating the state of equipment on line, which solves the technical problem that the diagnosis result cannot truly reflect the state of the equipment because a PHM system integrating multiple functions is difficult to install on the same equipment in the prior art.
According to an aspect of the present invention, there is provided a PHM rapid prototyping system for remote online evaluation of device status, the system comprising:
the PHM maintenance module is arranged on the ground and used for training the PHM algorithm model by using historical monitoring data of the movable equipment to obtain a trained algorithm configuration file, generating an algorithm toolkit by using the PHM algorithm model and the algorithm configuration file and sending the algorithm toolkit to the PHM application module;
and the PHM application module is arranged in the movable equipment and used for reconstructing a trained PHM algorithm model by utilizing the received algorithm toolkit and processing the current monitoring data of the movable equipment by utilizing the trained PHM algorithm model to obtain a diagnosis evaluation result of the movable equipment.
Preferably, the PHM maintenance module is further configured to obtain the historical monitoring data from a database and obtain the PHM algorithm model from the PHM development module before training the PHM algorithm model.
Preferably, the PHM maintenance module comprises:
the model training unit is used for loading the historical monitoring data into the PHM algorithm model, training the PHM algorithm model and obtaining an algorithm configuration file containing model parameters of the trained model;
and the packaging integration unit is used for packaging and integrating the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit.
Preferably, the PHM application module includes:
the algorithm reconstruction unit is used for analyzing the algorithm toolkit to obtain the PHM algorithm model and the algorithm configuration file, and loading the algorithm configuration file to the PHM algorithm model to obtain a trained PHM algorithm model;
and the diagnosis evaluation unit is used for extracting the characteristics of the current monitoring data of the movable equipment by using the trained PHM algorithm model to obtain characteristic data, and evaluating the movable equipment according to the characteristic data to obtain a diagnosis evaluation result of the movable equipment.
Preferably, the PHM application module further includes:
the data acquisition unit is used for acquiring current monitoring data of the movable equipment, and the current monitoring data comprises gas path parameter data and vibration parameter data; and/or
And the data storage unit is used for storing the current monitoring data and/or the corresponding diagnosis evaluation result.
Preferably, the PHM application module is further configured to save the current monitoring data and/or the corresponding diagnosis evaluation result to a database.
Preferably, the PHM application module is further configured to send the current monitoring data and/or the corresponding diagnosis and evaluation result to a human-computer interaction module disposed on the mobile device.
Preferably, the PHM maintenance module is further configured to generate a control instruction for reconstructing the PHM algorithm model, and send the algorithm toolkit to the PHM application module, and at the same time, send the control instruction for reconstructing the PHM algorithm model to the PHM application module.
Preferably, the PHM application module is specifically configured to reconstruct the trained PHM algorithm model according to the control instruction for reconstructing the PHM algorithm model.
Preferably, the PHM maintenance module is a high performance workstation, and the PHM application module is an industrial personal computer.
Compared with the prior art, the invention has the beneficial effects that:
the PHM application module arranged at the movable equipment and the maintenance module arranged on the ground are utilized to keep the adaptability of the diagnosis and evaluation scheme, realize the equipment evaluation result on line in real time, accurately and truly reflect the equipment state, and are beneficial to maintenance personnel at a remote end to maintain the equipment in time.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an exemplary embodiment of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a diagram of a PHM rapid prototyping system architecture provided by the present invention;
FIG. 2 is a schematic diagram of the PHM apparatus of the present invention;
FIG. 3 is an overall architecture diagram of a maintenance module and an application module provided by the present invention;
FIG. 4 is a functional block diagram of a maintenance module according to an embodiment of the present invention;
FIG. 5 is a functional block diagram of an application module provided in an embodiment of the present invention;
FIG. 6 is a maintenance module server provided by an embodiment of the present invention;
FIG. 7 is a diagram of an application module hardware architecture provided by an embodiment of the present invention;
FIG. 8 is an application module computer provided by an embodiment of the present invention;
FIG. 9 is a flow diagram of a maintenance module method provided by an embodiment of the present invention;
FIG. 10 is a maintenance module software overview interface provided by an embodiment of the present invention;
FIG. 11 is an algorithm training interface provided by embodiments of the present invention;
FIG. 12 is a remote control interface provided by an embodiment of the present invention;
FIG. 13 is a flowchart of an application module method provided by an embodiment of the present invention;
FIG. 14 is an application module software overview interface provided by an embodiment of the present invention;
FIG. 15 is a block diagram of a PHM rapid prototyping system for remote online evaluation of device status in accordance with the present invention.
Detailed Description
For the purpose of promoting a clear understanding of the objects, aspects and advantages of the embodiments of the present invention, reference will now be made in detail to the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like throughout the several views of the drawings. The illustrative embodiments and descriptions herein are presented to illustrate the invention and are not to be construed as limiting the invention. As used herein, "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
Fig. 15 is a block diagram of a PHM rapid prototyping system for remotely evaluating the status of a device on line according to the present invention, as shown in fig. 15, the system includes: the PHM system comprises a PHM maintenance module arranged on the ground and a PHM application module arranged in the movable equipment.
PHM maintenance module arranged on ground
The PHM maintenance module is arranged on the ground and used for training the PHM algorithm model by using historical monitoring data of the movable equipment to obtain a trained algorithm configuration file, generating an algorithm toolkit by using the PHM algorithm model and the algorithm configuration file and sending the algorithm toolkit to the PHM application module.
In one embodiment, the PHM maintenance module may include:
the model training unit is used for loading the historical monitoring data into the PHM algorithm model, training the PHM algorithm model and obtaining an algorithm configuration file;
and the packaging integration unit is used for packaging and integrating the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit.
In this embodiment, the algorithm configuration file includes model parameters and interface information of the trained model.
In this embodiment, the preset format may be an existing format or a custom format.
Second, PHM application module arranged in the mobile device
And the PHM application module is arranged in the movable equipment and used for reconstructing a trained PHM algorithm model by utilizing the received algorithm toolkit and processing the current monitoring data of the movable equipment by utilizing the trained PHM algorithm model to obtain a diagnosis evaluation result of the movable equipment.
In one embodiment, the PHM application module may include:
the algorithm reconstruction unit is used for analyzing the algorithm toolkit to obtain the PHM algorithm model and the algorithm configuration file, and loading the algorithm configuration file to the PHM algorithm model to obtain a trained PHM algorithm model;
and the diagnosis evaluation unit is used for extracting the characteristics of the current monitoring data of the movable equipment by using the trained PHM algorithm model to obtain characteristic data, and evaluating the movable equipment according to the characteristic data to obtain a diagnosis evaluation result of the movable equipment.
On the basis of the above embodiment, the PHM application module may further include:
the data acquisition unit is used for acquiring current monitoring data of the movable equipment, and the current monitoring data comprises gas path parameter data and vibration parameter data; and/or
And the data storage unit is used for storing the current monitoring data and/or the corresponding diagnosis evaluation result.
The working process of the PHM rapid prototyping system for remotely evaluating the equipment state on line can be as follows:
the first step is as follows: and the PHM maintenance module acquires the historical monitoring data from a database and acquires the PHM algorithm model from the PHM development module.
The second step is that: and the PHM maintenance module trains a PHM algorithm model by using the historical monitoring data, and an algorithm configuration file is obtained after the training is finished.
The third step: and the PHM maintenance module transmits data to the PHM application module.
In one embodiment, the PHM maintenance module generates an algorithm toolkit by using the PHM algorithm model and the algorithm configuration file, and sends the algorithm toolkit to the PHM application module.
On the basis of the embodiment, the PHM maintenance module may generate a control instruction for reconstructing the PHM algorithm model, and send the control instruction for reconstructing the PHM algorithm model to the PHM application module while sending the algorithm toolkit to the PHM application module.
In another embodiment, the PHM maintenance module may send only the algorithm configuration file to the PHM application module.
On the basis of the embodiment, the PHM maintenance module may generate a control instruction for reconstructing the PHM algorithm model, and send the algorithm configuration file to the PHM application module, and at the same time, send the control instruction for reconstructing the PHM algorithm model to the PHM application module.
The fourth step: and the PHM application module acquires the current monitoring data of the mobile equipment in real time.
The fifth step: the PHM application module reconstructs the trained PHM algorithm model.
In one embodiment, the PHM application module may reconstruct the trained PHM algorithm model using the algorithm toolkit.
In this embodiment, the PHM application module obtains a new PHM algorithm model and a new configuration file in the new algorithm toolkit by analyzing the new algorithm toolkit, and loads the new configuration file to the new PHM algorithm model to obtain the new PHM algorithm model loaded with the new configuration file, that is, reconstructs to obtain the trained PHM algorithm model.
In another embodiment, the PHM application module reconstructs a trained PHM algorithm model using the algorithm profile.
In this embodiment, the PHM application module loads the configuration file to an existing PHM algorithm model to obtain a PHM algorithm model loaded with the new configuration file.
In the above embodiment, the action of the PHM application module to reconstruct the trained PHM algorithm model may be performed under the control of the control instruction for reconstructing the PHM algorithm model.
And a sixth step: and the PHM application module processes the current monitoring data by using the trained PHM algorithm model to obtain a diagnosis evaluation result of the movable equipment.
The seventh step: and the PHM application module stores data.
In one embodiment, the PHM application module may store the current monitoring data and/or the corresponding diagnosis evaluation result in a database, so that the PHM maintenance module may call the current monitoring data and/or the corresponding diagnosis evaluation result for updating the algorithm toolkit.
In another embodiment, the PHM application module may store the current monitoring data and/or the corresponding diagnosis evaluation result, or may send the current monitoring data and/or the corresponding diagnosis evaluation result to a human-computer interaction module disposed on the mobile device, so that the human-computer interaction module displays the current monitoring data and/or the corresponding diagnosis evaluation result in real time.
The PHM maintenance module can be a high-performance workstation, and the PHM application module can be an industrial personal computer.
The principle of the present invention will be described in detail below with reference to fig. 1 to 15.
Fig. 1 is a schematic diagram of a PHM rapid prototyping system architecture provided by the present invention, and as shown in fig. 1, a PHM rapid prototyping system for remotely evaluating a device state online includes:
the PHM application module 101 (or a PHM application model) is arranged at the equipment and used for acquiring the running data of the equipment through various sensors and evaluating and processing the acquired running data by utilizing an embedded real-time diagnosis tool to obtain the state information of the equipment;
and the remote PHM maintenance module 102 is used for establishing a communication circuit connected with the PHM application module, and providing an algorithm self-training updating toolkit of the embedded real-time diagnosis tool for the PHM application module through the communication circuit.
Further, the PHM rapid prototyping system for remotely evaluating the status of the device online further includes: and the remote human-computer interaction module is used for receiving the equipment state information sent by the PHM application module 101, and is used for maintaining the equipment in time by remote maintenance personnel according to the equipment state information received in real time.
Further, while the PHM maintenance module 102 provides the algorithm self-training update toolkit of the embedded real-time diagnostic tool to the PHM application module 101, the device real-time operation data transmitted by the PHM application module 101 is received, and the device real-time operation data is quickly trained to obtain the algorithm self-training update toolkit in real time.
Further, the PHM maintenance module 102 includes:
rapidly training the model by using data in the database to obtain a self-training unit suitable for the algorithm of the equipment;
and packaging and integrating the configuration file containing the algorithm to obtain a packaging unit of the algorithm toolkit.
Further, the database includes real-time device operating data transmitted by PHM application module 101 to PHM maintenance module 102 via communication circuitry.
Further, the real-time operation data of the equipment comprises raw data or data subjected to feature extraction.
The method and the device realize rapid training and algorithm reconstruction of the PHM algorithm model, timely update corresponding algorithms according to different states of equipment, and overcome the technical problems that a solidified equipment diagnosis evaluation scheme in the prior art is poor in adaptability and high in algorithm updating cost.
Example 2 PHM device
Fig. 2 is a schematic diagram of the PHM apparatus provided in the present invention, and as shown in fig. 2, a PHM apparatus for remotely and online evaluating the status of a device includes:
the application device (or evaluation device) 1 connected with the equipment comprises a PHM application module 101 and is used for acquiring the running data of the equipment through various sensors, and evaluating and processing the acquired running data by using an embedded real-time diagnosis tool to obtain the state information of the equipment;
the maintenance device 2 remotely connected with the evaluation device (or application device) 1 comprises a PHM maintenance module 102 for establishing a communication circuit connected with the PHM application module 101, and providing an algorithm self-training updating kit of an embedded real-time diagnosis tool for the PHM application module 101 through the communication circuit.
The application device 1 may be any electronic device that can be loaded with the PHM application module 101.
The maintenance device 2 may be any workstation or computer that can be loaded with the PHM maintenance module 102.
The application example is as follows: application of aircraft engine
The main purpose of the aeroengine configurable PHM rapid prototyping system is to realize remote configuration reconstruction and system management of different types of PHM systems according to different application scenes of the aeroengine so as to support rapid development and deployment of PHM applications.
The PHM rapid prototyping system for remotely and online evaluating the equipment state provided by the invention can utilize the monitoring parameters acquired in the life cycle of the aircraft engine to analyze the parameter characteristics of the aircraft engine under different working conditions, realize the real-time online health evaluation and fault diagnosis of the aircraft engine and the storage of related data, provide state monitoring information for an onboard computer and a ground management center, and provide data support for the maintenance decision of the engine. The method has the functions of 1) supporting the fast training of a PHM algorithm model; 2) supporting an algorithm toolkit reconstruction function; 3) and providing the original engine monitoring parameters and the online diagnosis and evaluation results for the ground database of the aircraft engine.
The working environment of the aircraft engine is severe and the space is narrow in the process of executing tasks, and a PHM system integrating data acquisition, algorithm training, feature extraction, diagnosis evaluation and data storage is difficult to realize when the aircraft engine is configured on the aircraft. The applicability of a consolidated engine diagnostic evaluation scheme may gradually decrease over the life cycle of the engine, while the cost of algorithm updates may be higher. Therefore, in order to realize real-time monitoring of the engine state and improve the efficiency and effect of the algorithm, the configurable PHM rapid prototyping system for the aircraft engine is divided into two modules of maintenance and application (namely an aircraft engine PHM maintenance module and an aircraft engine PHM application module), fig. 3 is a general architecture diagram of the maintenance module and the application module provided by the invention, and as shown in fig. 3, the ground maintenance module is composed of a high-performance workstation (or a PHM maintenance server), so that the rapid training and packaging integration of the algorithm can be realized; the airborne application module comprises an industrial personal computer (or a reconfigurable PHM application computer) with strong environmental adaptability and various sensors (used for data acquisition), and can process original signals in real time on line and evaluate the state of the engine. The maintenance and application modules may be online, either by wire or wirelessly.
1. Description of functions
1.1 maintenance Module
The functional structure of the maintenance module of the configurable PHM rapid prototyping system of the aircraft engine is shown in FIG. 4, and the functions comprise: (1) the algorithm training function is as follows: calling original data from a database according to an algorithm model of a PHM development module to quickly train the model to obtain a related configuration file; (2) packaging the integrated functions: packaging and integrating configuration files such as an algorithm, parameters and an interface thereof according to a unified standard to obtain an algorithm toolkit; (3) the communication function is as follows: and the maintenance module and the application module adopt a wired or wireless two-way communication protocol for data transmission. In the maintenance module, the input is an algorithm model, and the output is an algorithm toolkit.
1.2 application Module functional requirements
Fig. 5 shows a functional structure of an application module of a configurable PHM rapid prototyping system of an aircraft engine, which includes: (1) the data acquisition function: the application module can control the sensor to collect engine monitoring data, and the engine monitoring data is mainly divided into gas path parameters and vibration parameters; (2) the algorithm performs the functions of: the application module can read a PHM algorithm model and a configuration file thereof in the algorithm toolkit, and input the collected monitoring data into the PHM algorithm model loaded with the configuration file for calculation to obtain an engine diagnosis evaluation result; (3) the algorithm reconstruction function: if the application module receives the new algorithm toolkit sent by the maintenance module, the application module obtains a new PHM algorithm model and a new configuration file in the new algorithm toolkit through analyzing the new algorithm toolkit to obtain the new PHM algorithm model loaded with the new configuration file, and if the application module only receives the new configuration file sent by the maintenance module, the application module loads the new configuration file to the existing PHM algorithm model to obtain the PHM algorithm model loaded with the new configuration file. (4) Data storage function: the application module can store the original monitoring data and the algorithm operation result. In the application module, the input is an algorithm tool kit, and the output is original monitoring data and an online diagnosis evaluation result.
2. Technical scheme of system
2.1 hardware solution
2.1.1 maintenance Module hardware solution
In order to meet the requirement that multiple processes of a maintenance module run simultaneously and a large amount of data are processed quickly, a maintenance module server should select a workstation with strong performance as far as possible, and a server platform selects an SCW4750 super-quiet workstation of Shanghai-Hai science and technology Co., Ltd, as shown in FIG. 6, a CPU of the maintenance module server adopts a fifth-generation Intel top-level processor-Core i7-5930K, and the execution speed of the CPU operation algorithm can be effectively guaranteed. Meanwhile, most popular intelligent algorithms utilize the GPU to conduct high-speed network training, the GPU of the workstation is specially customized for deep learning and is driven by four paths of NVIDIA TITAN X, a visual and easy-to-use DIGITS training system is carried, and the computing capacity of the machine learning algorithm is greatly enhanced.
2.1.2 application Module hardware solution
The hardware architecture of the application module is shown in fig. 7.
In order to meet the operation requirement of the application module and the real-time requirement of data processing, the application module computer needs to have a relatively strong CPU, and therefore, a fanless embedded industrial personal computer ARK-1550 of the hua science and technology limited company is selected, as shown in fig. 8. The CPU adopts a fourth generation Intel Core i5-4300U, so that the stability is ensured and the calculation speed is high. The industrial personal computer runs a Windows operating system, supports VGA, HDMI and LDVS display modes, and can be externally connected with a display to check the running condition in real time. Considering that the space in the airplane is narrow and the vibration is severe, the working environment is quite severe, the size of the body of the industrial personal computer is only 223 x 46.6 x 133.0mm, the normal working temperature range is-40-85 ℃, the environmental adaptability is strong, the noise is small, and the industrial personal computer is very suitable for being used as a computing center of an application platform.
In order to acquire various parameters required by the system, different types of sensors need to be installed at each test point, and besides the requirements of necessary precision, sampling rate and the like are met, the sensors should be selected as small as possible and have strong environmental adaptability.
2.2 software technical scheme
2.2.1 maintenance Module software solution
2.2.1.1 functional description
The operating conditions of the aircraft engine are complicated in the operating process, the working state health assessment and maintenance state fault diagnosis method is not constant, in order to achieve a better diagnosis assessment effect, the parameter configuration of each algorithm needs to be continuously adjusted according to the historical assessment result and the degradation trend of the engine, and meanwhile, the occurrence and perfection of a novel algorithm such as a deep learning model bring higher precision to the diagnosis assessment of the engine state. Based on the consideration of algorithm quick update iteration, the PHM maintenance module realizes the reconstruction technology of the diagnosis evaluation algorithm through an algorithm tool package, encapsulates the updated algorithm and the optimized configuration thereof into the algorithm tool package to easily realize the optimization and adjustment of the diagnosis evaluation process, and efficiently utilizes the historical evaluation information of the PHM quick prototype system.
On the other hand, algorithms such as a neural network and the like which need to be trained by using a large amount of data are unrealistic to be trained on the machine, in order to improve the efficiency of algorithm execution, the maintenance module can make full use of the strong performance of the maintenance module to carry out rapid training on the algorithms, and the configuration files after training are integrated into an algorithm toolkit, so that the application module can be rapidly executed.
2.2.1.2 implementation method
The maintenance module method flow is shown in fig. 9:
(1) receiving a design scheme of a PHM development module, calling required data from a database and loading the data into a model, and quickly training an algorithm model;
(2) packaging and integrating the algorithm model and the configuration file into an algorithm toolkit according to a uniform rule after training;
(3) and sending the algorithm toolkit and the control instruction of the application module to the application module in a wireless communication mode.
2.2.1.3 inputs and outputs
The inputs of the maintenance module scheme are: an algorithm model and database raw data;
the output of the maintenance module scheme is: control commands to the application modules and an algorithm toolkit.
It should be noted that the control instructions to the application module include, but are not limited to, control instructions for reconstructing the PHM algorithm model.
2.2.1.4 functional visualization
The maintenance module software overall interface is shown in fig. 10.
The selected algorithm may be trained by data loaded into the database in the software, as shown in fig. 11.
In the engine maintenance process, the maintenance module can establish wireless connection with the application module and realize remote control on the application module, the original data and the result data collected by the application module are sent to the database, and the interface is shown in fig. 12.
2.2.2 application Module software solution
2.2.2.1 functional description
Monitoring parameters in the life cycle of the aircraft engine mainly comprise gas path parameters and vibration data, an application module needs to coordinate various sensors to acquire signals such as temperature, flow, pressure and acceleration, and an algorithm toolkit is loaded to process the data, so that real-time engine diagnosis and evaluation are realized.
2.2.2.2 implementation method
The application module method flow is shown in fig. 13:
(1) loading an algorithm toolkit sent by a maintenance module;
(2) coordinating the acquisition of parameters of each sensor according to requirements;
(3) preprocessing and characteristic extraction are carried out on the original data, so that health assessment, fault diagnosis and the like are carried out on the engine, and results and the original data are stored;
(4) the results and raw data are sent to the database at engine maintenance.
2.2.2.3 input and output
The inputs of the application module scheme are: an algorithm toolkit and a control instruction;
the output of the application module scheme is: diagnostic evaluation results and raw monitoring data.
2.2.2.4 function visualization
The overall interface of the application module software is shown in fig. 14. During maintenance, the application module can be externally connected with a display to view original monitoring data and historical diagnosis evaluation results.
In summary, the present invention has the following technical effects:
1. the PHM rapid prototyping system provided by the embodiment of the invention can utilize the operation data (such as vibration signal data and gas circuit parameter data) collected in the life cycle of the equipment (such as electromechanical equipment) to analyze the parameter characteristics of the equipment under different working conditions, realize the real-time online health assessment and fault diagnosis of the equipment and the storage of related data, provide state monitoring information for an onboard computer and a management center, and provide data support for the maintenance decision of the equipment.
2. The PHM rapid prototyping system provided by the embodiment of the invention can realize rapid training and algorithm reconstruction of a PHM algorithm model, timely update the corresponding algorithm according to different states of equipment, and overcome the technical problems of poor adaptability of a solidified equipment diagnosis evaluation scheme and high algorithm updating cost in the prior art.
Although the present invention has been described in detail hereinabove, the present invention is not limited thereto, and various modifications can be made by those skilled in the art in light of the principle of the present invention. Thus, modifications made in accordance with the principles of the present invention should be understood to fall within the scope of the present invention.
Claims (8)
1. A PHM rapid prototyping system for remote online evaluation of device status, said system comprising:
the PHM maintenance module is arranged on the ground and used for training the PHM algorithm model by using the historical monitoring data of the airplane to obtain a trained algorithm configuration file, generating an algorithm toolkit by using the PHM algorithm model and the algorithm configuration file and sending the algorithm toolkit to the PHM application module;
the PHM application module is arranged in the airplane and used for reconstructing the trained PHM algorithm model by using the received algorithm toolkit and processing the current monitoring data of the airplane by using the trained PHM algorithm model to obtain the diagnosis evaluation result of the airplane;
the PHM maintenance module includes:
the model training unit is used for loading the historical monitoring data into the PHM algorithm model, training the PHM algorithm model and obtaining an algorithm configuration file containing model parameters of the trained model;
the packaging integration unit is used for packaging and integrating the PHM algorithm model and the algorithm configuration file according to a preset format to obtain the algorithm toolkit;
wherein, PHM is fault prediction and health management;
the PHM maintenance module is further used for acquiring the historical monitoring data from a database and acquiring the PHM algorithm model from the PHM development module before training the PHM algorithm model.
2. The system of claim 1, wherein the PHM application module comprises:
the algorithm reconstruction unit is used for analyzing the algorithm toolkit to obtain the PHM algorithm model and the algorithm configuration file, and loading the algorithm configuration file to the PHM algorithm model to obtain a trained PHM algorithm model;
and the diagnosis evaluation unit is used for extracting the characteristics of the current monitoring data of the airplane by using the trained PHM algorithm model to obtain characteristic data, and evaluating the airplane according to the characteristic data to obtain the diagnosis evaluation result of the airplane.
3. The system of claim 2, wherein the PHM application module further comprises:
the data acquisition unit is used for acquiring current monitoring data of the airplane, wherein the current monitoring data comprises gas path parameter data and vibration parameter data; and/or
And the data storage unit is used for storing the current monitoring data and/or the corresponding diagnosis evaluation result.
4. The system of claim 3, wherein the PHM application module is further configured to save the current monitoring data and/or corresponding diagnostic assessment results to a database.
5. The system of claim 2, 3 or 4, wherein the PHM application module is further configured to send the current monitoring data and/or corresponding diagnostic assessment results to a human-machine interaction module disposed on the aircraft.
6. The system of claim 1, wherein the PHM maintenance module is further configured to generate control instructions for reconstructing the PHM algorithm model, and send the control instructions for reconstructing the PHM algorithm model to the PHM application module while sending the algorithm toolkit to the PHM application module.
7. The system of claim 6, wherein the PHM application module is specifically configured to reconstruct the trained PHM algorithm model based on the control instructions for reconstructing the PHM algorithm model.
8. The system of claim 1, wherein the PHM maintenance module is a high performance workstation and the PHM application module is an industrial personal computer.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711329017 | 2017-12-13 | ||
| CN2017113290171 | 2017-12-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109917772A CN109917772A (en) | 2019-06-21 |
| CN109917772B true CN109917772B (en) | 2020-09-08 |
Family
ID=66959849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811477518.9A Active CN109917772B (en) | 2017-12-13 | 2018-12-05 | PHM rapid prototyping system for remotely evaluating equipment state on line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109917772B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3764179A1 (en) * | 2019-07-08 | 2021-01-13 | ABB Schweiz AG | Assessing conditions of instustrial equipment and processes |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI225606B (en) * | 2003-05-13 | 2004-12-21 | Univ Nat Cheng Kung | Generic embedded device and method for retrieving and transmitting information of various customized applications |
| CN102521604B (en) * | 2011-11-21 | 2014-11-19 | 上海交通大学 | Device and method for estimating performance degradation of equipment based on inspection system |
| CN104268381B (en) * | 2014-09-16 | 2017-03-29 | 哈尔滨工业大学 | A kind of satellite failure diagnostic method based on AdaBoost algorithms |
| CN104463347A (en) * | 2014-11-06 | 2015-03-25 | 电子科技大学 | Method for electronic product degenerate state trend prediction with singular signals |
| CN106406296B (en) * | 2016-12-14 | 2019-04-23 | 东北大学 | It is a kind of based on vehicle-mounted and cloud train fault diagnostic system and method |
-
2018
- 2018-12-05 CN CN201811477518.9A patent/CN109917772B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109917772A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107600110B (en) | A kind of vehicle-mounted train groups prognostic and health management system | |
| Lu et al. | Edge computing on IoT for machine signal processing and fault diagnosis: A review | |
| Subakti et al. | Indoor augmented reality using deep learning for industry 4.0 smart factories | |
| CN105415374A (en) | Mechanical hand transmission unit on-line fault diagnosis system based on synergetic measurement | |
| CN204425399U (en) | A kind of hydrometeorological operation system based on cloud computing | |
| CN103428552B (en) | Remote controller air mouse realize method | |
| CN102353513B (en) | Pneumatic test system of deformable aircraft | |
| CN107421763B (en) | A kind of equipment fault detection method and device | |
| CN106470141A (en) | A kind of dynamo-electric method for interchanging data based on GJB289A bus | |
| CN109917772B (en) | PHM rapid prototyping system for remotely evaluating equipment state on line | |
| CN106054778B (en) | The cold chain transportation process intellectual monitoring method of sampling, device and cold chain vehicle | |
| CN112770285A (en) | Digital twin factory modeling method and device based on 5G network | |
| JP2018519594A (en) | Local analysis on assets | |
| CN113074807A (en) | Real-time monitoring system for vibration and deformation of cultivation fence facility structure | |
| CN117332635B (en) | Structure online monitoring system and method based on digital twinning | |
| CN112595537A (en) | Equipment health state monitoring method and system based on signal analysis and storage medium | |
| US10524697B2 (en) | System and method for monitoring motor recovery in a post acute stroke treatment | |
| CN108255145A (en) | A kind of test system and method for system of vehicle transmission control unit | |
| CN204085898U (en) | For the multifunctional universal test-bed of pure electric automobile parts test | |
| CN116733688A (en) | Operation monitoring method, device, equipment and medium of wind generating set | |
| CN112160750B (en) | System and method for controlling and predicting state of coal mining machine | |
| CN114165430A (en) | Method, system, equipment and medium for monitoring health of pump based on edge calculation | |
| Levoniuk et al. | The development of geographic information system model for information flows monitoring of complex objects | |
| CN105741520A (en) | A subway vehicle ground test on-line monitoring system based on a wireless data acquisition technique | |
| CN112926194B (en) | Method and system for acquiring state information of mine car suspension system |
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 |