CN113627527B - Nonstandard detection equipment monitoring system - Google Patents
Nonstandard detection equipment monitoring system Download PDFInfo
- Publication number
- CN113627527B CN113627527B CN202110917137.3A CN202110917137A CN113627527B CN 113627527 B CN113627527 B CN 113627527B CN 202110917137 A CN202110917137 A CN 202110917137A CN 113627527 B CN113627527 B CN 113627527B
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- nonstandard
- edge
- detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 107
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000002347 injection Methods 0.000 claims description 3
- 239000007924 injection Substances 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 238000012423 maintenance Methods 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 238000005299 abrasion Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000078 claw Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a nonstandard detection equipment monitoring system, which comprises: edge device: configuring a monitoring program, analyzing the running state of each nonstandard detection device based on the collected running and detection data, and assisting in data processing of the nonstandard devices; data cooperative device: the method comprises the steps of communicating with each edge equipment node, and cooperatively scheduling the computing capacity of the edge equipment to realize data processing optimization; remote gateway: the method comprises the steps of communicating with data cooperative equipment, obtaining the running state of each nonstandard detection equipment, and sending control information and update information of an edge equipment node to the edge equipment node through the data cooperative equipment; the nonstandard detection equipment is communicated with the remote gateway and the tested piece so as to send the tested piece detection information to the remote gateway. An embedded intelligent AI module (edge device) is added into the system framework, and the health state and performance of the nonstandard detection device of the device can be judged by analyzing the data of the device and the test data of the tested piece.
Description
Technical Field
The invention relates to the technical field of railway vehicles, in particular to a monitoring system of nonstandard detection equipment.
Background
The non-standard detection equipment for the rail transit has the characteristic of strong individuation, and the manual maintenance cost is increased. In the digital transformation process of the rail traffic industry, the network is used as a support, so that higher requirements are put forward in the aspects of reducing the maintenance cost of nonstandard detection equipment, realizing remote maintenance and the like.
In the prior art, the maintenance method and the characteristics of the nonstandard detection equipment are as follows.
Common method one: referring to fig. 1, an internet gateway is added to the nonstandard detection device, so that device data can be uploaded to a related common cloud or private cloud, and then the next processing is performed. In this method, the gateway mainly plays a role of uploading and downloading, so that the device can be managed at a remote end.
The common method is as follows: referring to fig. 2, an internet of things gateway is adopted to preprocess original data of a device, and then the processed data is uploaded to a common cloud or a private cloud to be further processed. The original data of the equipment is firstly subjected to preprocessing and calculation such as data cleaning, data slicing and the like in the gateway, and then the data with better value is uploaded to the cloud for further processing.
Two methods commonly used in the prior art can realize networking of equipment and uploading of data, but all require modification of a software architecture inside the equipment. For nonstandard detection equipment, the equipment is different, and the internal software architecture and the data flow are different. In the processing mode in the prior art, the thread is required to be started again on the original measurement and control software program, the data packet is grasped, the data is packed, and then the Internet of things is uploaded. Extensive development of each nonstandard detection device is required, and the processing efficiency is low.
Aiming at the characteristics of 'three-high one-scattering' of non-standard detection equipment and products in the rail transit industry, namely high product category number, high monomer value, high operation and maintenance cost and discrete national distribution, a general framework is urgently needed to solve the problem of how to connect isolated non-standard equipment into a digital network, realize interconnection and intercommunication among the equipment and provide management and control of full life cycle for maintenance and overhaul of the whole vehicle. By deploying the data cooperative equipment, related parameters of various equipment distributed in various places of the country can be observed remotely, and meanwhile, non-standard equipment can be maintained.
Disclosure of Invention
The invention aims to solve one of the technical problems and provides a nonstandard detection equipment monitoring system based on edge calculation.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a nonstandard detection device monitoring system, comprising:
edge device: each edge equipment node can be communicated with at least one type of nonstandard detection equipment to acquire the running state information and detection data of the type of nonstandard detection equipment; wherein, each type of nonstandard detection equipment corresponds to at least one type of communication interface; the operation state of each nonstandard detection device can be analyzed based on the collected operation data, and the data processing of the nonstandard devices is assisted based on the detection data of the nonstandard devices;
data cooperative device: the cloud server data are distributed through communication with each edge equipment node, and the computing capacity of the edge equipment is cooperatively scheduled to realize data processing optimization;
remote gateway: the cloud server is connected with the data cooperative equipment, and is communicated with the cloud server, and control information and update information of the edge equipment node are sent to the edge equipment node through the data cooperative equipment;
the nonstandard detection equipment is communicated with the remote gateway and the tested piece so as to send the tested piece detection information to the remote gateway and collect the detection data of the tested piece.
In some embodiments of the present invention, the data cooperative device is configured at an edge device node connected to the nonstandard detection device, and when there is a new operation calculation requirement, distributes data required by the new operation calculation requirement to an idle edge device node to execute operation calculation, so as to implement data processing optimization.
In some embodiments of the present invention, the edge device node is configured with:
state monitoring algorithm: acquiring data of nonstandard detection equipment, and analyzing the running state of the nonstandard detection equipment based on the data;
expert system algorithm: and acquiring sensor data, and performing data analysis on detection data of non-standard detection equipment to analyze the performance of the tested piece.
In some embodiments of the present invention, the nonstandard detection device includes an industrial personal computer, the edge device includes a TCP/IP-based edge device node, and communicates with the industrial personal computer and a sensor, where the sensor is connected to a tested piece;
the data required by the industrial personal computer state monitoring algorithm and the expert system algorithm can be used for directly acquiring sensor information or carrying out data twinning through the industrial personal computer to acquire the industrial personal computer data.
In some embodiments of the present invention, the execution flow of the expert system algorithm includes:
a data preprocessing step: the method comprises the steps of data slicing processing, filtering processing, resampling processing and normalized sampling frequency processing;
and a feature extraction step: determining normal key features and fault key features based on the statistical information of the normal operation data and the fault operation data;
algorithm training: carrying out algorithm training based on the training model, the preprocessing data and the feature extraction data;
algorithm pre-verification step: and comparing the detected data of the tested piece with the algorithm generation data to verify the accuracy of the algorithm.
In some embodiments of the invention, the expert system algorithm is further configured to:
performing data preprocessing and feature extraction based on historical data;
and (3) carrying out fault data injection based on the twin data, and carrying out algorithm training by combining the data after feature extraction.
In some embodiments of the present invention, the nonstandard detection device includes an image acquisition device, and when the edge device node is an image monitoring edge device, the expert system algorithm is configured to perform image processing algorithms such as denoising, image recognition and the like on the image according to the image acquisition data.
In some embodiments of the present invention, the edge device further includes an edge device node based on serial communication modes such as RS485 and RS232, an edge device node based on USB, and an edge device node based on GPIB.
Compared with the prior art, the invention has the technical advantages that:
an embedded intelligent AI module (edge device) is added into the system framework, and the health state and performance of the nonstandard detection device of the device can be judged by analyzing the data of the device and the test data of the tested piece. The framework enables the existing shaping equipment to realize the edge calculation target of the nonstandard detection equipment without a great deal of transformation.
The method solves the problem that the nonstandard detection equipment generates a large amount of process data and test data to upload to the cloud server in the use process, and network congestion is easy to cause; meanwhile, the networking requirement of nonstandard equipment is met, the manual maintenance cost of the existing nonstandard detection equipment is reduced, and the requirement of remote maintenance is met; while provisioning devices, better services are provided, a detailed solution is proposed for implementing a legacy provisioning mode to a "device + service" provisioning mode.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a monitoring system of a nonstandard detection device according to a first embodiment of the prior art;
FIG. 2 is a schematic diagram of a monitoring system of a nonstandard detection device according to a second embodiment of the prior art;
FIG. 3 is a schematic diagram of a non-standard detection device monitoring system according to the present invention;
FIG. 4 is a diagram of a non-standard detection device monitoring system architecture of the present invention;
FIG. 5 is a diagram of a non-standard detection device monitoring system architecture of the present invention;
FIG. 6 is a diagram of a non-standard detection device monitoring system architecture of the present invention;
FIG. 7 is a diagram of a non-standard detection device monitoring system architecture of the present invention;
FIG. 8 is a flowchart of an expert algorithm diagnosis;
FIG. 9 is a flow chart of expert algorithm data preprocessing and feature extraction;
fig. 10 is a flowchart of expert algorithm training.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a non-standard detection equipment monitoring system which can be used for monitoring non-standard detection equipment in the technical field of railway vehicles.
Referring to fig. 3, the nonstandard detection device monitoring system includes: edge device, data distribution system device, remote gateway.
The nonstandard detection equipment is connected with a sensor, an executing mechanism, a monitoring device and the like.
Edge device: the system comprises a plurality of edge equipment nodes, wherein each edge equipment node can communicate with a class of nonstandard detection equipment to acquire the operation data of the class of nonstandard detection equipment; wherein, each type of nonstandard detection equipment corresponds to at least one type of communication interface; the edge device node is configured with a monitoring program, and based on the collected operation data, the operation state of each nonstandard detection device can be specifically processed or analyzed on the collected data.
The edge equipment comprises Ethernet edge equipment nodes based on TCP/IP, serial port edge equipment nodes based on RS485 and RS232, edge equipment nodes based on USB and edge equipment nodes based on GPIB. Based on rich interface designs, the edge equipment supports various hardware interfaces, and can be downward compatible with nonstandard detection equipment interfaces of industrial computers, PLCs, various embedded equipment and other main controllers; the upward compatible data collaboration device interfaces in a wired or wireless form.
Data cooperative device: and communicating with each equipment node to acquire the operation data and the operation state information of each nonstandard detection equipment.
Remote gateway: and the control information and the update information of the edge equipment node are sent to the edge equipment node through the data cooperative equipment.
The nonstandard detection equipment is communicated with the remote gateway and the tested piece through the data cooperative equipment so as to send the tested piece detection information to the remote gateway.
The present invention defines two interfaces: north interface: interfaces provided for other factories or operators (data cooperative devices) to access and manage, namely interfaces provided upwards; southbound interface: and managing other manufacturer equipment or independently developing interfaces of nonstandard detection equipment by the company, namely interfaces provided downwards.
Southbound interface: with the gradual increase of equipment of each large vehicle section or motor train station in the rail transit industry, the network scale of subordinate equipment is continuously enlarged, and the number of nonstandard equipment in the network is also increased, so that higher requirements and challenges are provided for the southbound interfaces of the edge equipment. And at the same time, the north interface does not need to be changed greatly along with the increase of equipment. The downward interface (southbound interface) of the intelligent gateway should consider the complexity of the communication connection mode of the terminal equipment in each industry, and is required to have rich interface/protocol capability so as to be applied to wider industry markets; currently, for the above analysis, at least the mainstream communication protocols such as TCP/IP, DF1, OPC, SNP, MPI, MODBUS/PLUS, hostLink, controlLink, CC-LINK, MEWTOCOL, etc. are required to be covered, and the communication media of these protocols are basically RJ45, serial port, USB, etc., so that there is a correspondence in physical structure and appearance, and specific protocol contents can be configured at the software level of the intelligent edge device.
North interface: the northbound interface has certain universality, so that in a plurality of interface specifications, an OPC UA unified architecture is selected, complex data embedment, unified address space and cross-platform operation are supported, and abstract service functions are supported. The OPC UA functions are divided into an OPC UA server function and an OPC UA client function by roles, the server function is used for providing data and unified access interfaces and services, a client can operate the data provided by the OPC UA server according to the unified access interfaces and services, the functions can be used as an application program such as a simple OPC UA client tool alone, and can be integrated into a user program such as an MRS system to support the OPC UA client function, and the user program may also centralize functions of both the server and the client. The invention provides an OPC UA unified architecture of edge equipment in edge calculation, wherein the edge equipment is used as a server side of the OPC UA, and other equipment at the upper layer (northbound) of the edge equipment is used as a client side of the OPC UA.
To improve the monitoring efficiency, in some embodiments of the present invention, the data collaboration device is configured to, when an edge device node connected to the nonstandard detection device performs operation computation and has a new operation computation requirement, distribute data required by the new operation computation requirement to an idle edge device node to perform operation computation. Specifically, the data cooperative device can receive and manage the data of the plurality of nonstandard detection devices, perform cooperative management on the data, and when the data size is large, the operation is complex, and the data cooperative device can call other idle edge node devices to process.
Meanwhile, the data distribution and coordination equipment is used as a bridge between the gateway and the edge node equipment, and the remote data end can update the data processing model in the edge computing equipment through the data coordination equipment.
In some embodiments of the present invention, the edge device node has a function of monitoring the status of the nonstandard detection device, and may also perform a function of part of the nonstandard detection device, where specifically, the edge device node is configured with:
state monitoring algorithm: acquiring data of nonstandard detection equipment, and analyzing the running state of the nonstandard detection equipment based on the data;
expert system algorithm: and acquiring sensor data, and performing data analysis on detection data of non-standard detection equipment to analyze the performance of the tested piece.
The following describes a specific monitoring procedure of the edge node according to the present invention in connection with several specific non-standard detection devices.
In some embodiments of the present invention, the nonstandard detection device includes an industrial personal computer, such as a research and development industrial personal computer and an NI industrial personal computer; the edge equipment comprises an edge equipment node based on TCP/IP, and is communicated with the industrial personal computer and the sensor, and the sensor is connected to the tested piece to acquire the data of the tested piece;
the data required by the industrial personal computer state monitoring algorithm and the expert system algorithm can be used for directly acquiring sensor information or carrying out data twinning through the industrial personal computer to acquire the industrial personal computer data.
Aiming at an industrial personal computer, an edge node (device) adopts an embedded hardware system, wherein two sets of algorithms are deployed: the industrial personal computer test bed state monitoring algorithm and the industrial personal computer are connected with the expert system algorithm of the tested piece. The inputs of the two sets of algorithms can be made in two ways: the data are directly obtained from the sensor or are sent to the edge node through the Ethernet by utilizing the industrial personal computer, the edge node carries out a large amount of complex operation on the data, and the high-performance storage and operation of the edge node are utilized, so that the data are analyzed to realize the function of the expert system of the tested piece under the condition that the original detection efficiency is not affected, and the state detection of the nonstandard system can also be realized, thereby realizing the state monitoring algorithm of the test bed. The two ways are different from the real-time requirement, if a test bed needs faster real-time for state monitoring, the data needs to be directly read from the sensor so as to obtain higher sampling rate and synchronism.
The invention provides an edge computing architecture of digital-analog signal nonstandard equipment based on an industrial personal computer, which utilizes a hardware interface and data twinning of the industrial personal computer to transmit detection data of a test bed or test bed state data to edge equipment, and realizes the edge computing capability of big data and complex algorithms on the premise of basically not influencing the functions and performances of the original test bed by the powerful computing force of the edge equipment, and meanwhile, the edge equipment can remotely update a data processing model of the edge computing equipment according to the capability of detecting data updating and data cooperative equipment. The data cooperative equipment can receive and manage a plurality of test bed data, perform cooperative management on the data, and when the data volume is large, the operation is complex, and the data cooperative equipment can call other idle edge computing equipment to process.
In some embodiments of the present invention, the test piece includes a bearing, the edge device node is Compact RIO, the sensor includes a vibration sensor, a speed sensor, and a temperature sensor, and the expert system algorithm includes a bearing diagnosis algorithm.
Specifically, some portable whole car, bogie maintenance equipment and other large-scale equipment (such as rolling tables) all adopt mature collection equipment at home and abroad, and after edge equipment and data cooperative equipment are added, an edge calculation result can be provided for owners as an additional function of the equipment. The invention takes bearing detection equipment as an example, and introduces an edge computing architecture of the equipment.
The bearing detection equipment under the framework can realize the detection of the running state of the real-time equipment or a tested piece by utilizing the bearing fault diagnosis system, and ensure the safety maintenance and the instructive maintenance. When the tested piece is provided with bearing equipment, the problem of disassembly and assembly maintenance of the bearing can be solved.
Compact RIO with high real-time data processing is an edge node with powerful data acquisition, computation, and data storage capabilities, consisting of a reconfigurable Field Programmable Gate Array (FPGA) chassis, and a real-time controller (RT). The FPGA is responsible for high-speed collection of vibration quantity, speed signals and temperature signals, the RT deploys a bearing real-time diagnosis and detection algorithm, and communicates with the industrial control system, and the industrial control system displays and uploads the processing result to the cloud server.
The invention provides an edge computing architecture based on a mature acquisition instrument, which realizes edge computing by utilizing the acquisition and computing functions of the acquisition instrument. When the collector device does not have sufficient computing power or does not provide an open interface for computing power, it may be replaced with a self-grinding chassis-embedded device or other collector device. When the data volume is large and the operation is complex, the data cooperative equipment can call other idle edge computing equipment to process and can update the data processing model in the edge computing equipment.
In some embodiments of the present invention, the nonstandard detection device includes an image acquisition device, the edge device node is an image monitoring edge device, and the expert system algorithm is configured to determine a pantograph state, a vehicle running direction, and identify a vehicle number according to the image acquisition data.
Specifically, the edge side can realize preprocessing of image data, such as image screening, image gray value extraction and the like, so that the image uploading bandwidth is reduced, the equipment volume can be reduced to a greater extent, and the equipment image data processing rate is improved. Taking image-based trackside pantograph abrasion detection equipment in the rail transit industry as an example, a pantograph slide plate belongs to a consumable part, is replaced regularly, and has high failure probability. The pantograph abrasion detection system monitors the pantograph of the vehicle by adopting a non-contact measurement technology, and the image processing edge node has the functions of system self-detection, data communication and data management and automatically judges the states of the pantograph abrasion, the profile, the central line deviation, the claw deformation and the like of the passing vehicle; and can automatically judge the running direction of the train and automatically identify the train number. The defects of the abrasion of the pantograph and other parts of the pantograph can be accurately detected.
In the edge nodes of the image system, the GPU is used for processing image data and training models such as deep learning; the data can be sent to other edge node devices or cloud end through the data cooperative device to train the model; and the CPU in the edge computing node is used for functional logic control and data communication.
Referring to fig. 8 to 10, in the foregoing embodiments, the expert system algorithm may employ the following execution flow:
a data preprocessing step: the method comprises the steps of data slicing processing, filtering processing, resampling processing and normalized sampling frequency processing;
and a feature extraction step: determining normal key features and fault key features based on the statistical information of the normal operation data and the fault operation data;
algorithm training: carrying out algorithm training based on the training model, the preprocessing data and the feature extraction data;
algorithm pre-verification step: and comparing the detected data of the tested piece with the algorithm generation data to verify the accuracy, usability and effect of the algorithm.
In some embodiments of the invention, the expert system algorithm is further configured to:
performing data preprocessing and feature extraction based on historical data;
and (3) carrying out fault data injection based on the twin data, and carrying out algorithm training by combining the data after feature extraction.
Taking edge equipment for a brake system as an example, a brake system high-precision model is embedded in the edge equipment. The monitoring data is fed back to the nonstandard detection device for the braking system through the sensor implementation of the braking system, and the digital twin body is acquired through the nonstandard detection device for the braking system.
The expert system is provided with a data storage unit for storing historical operation data, and performs data preprocessing and feature quantity selection based on the historical operation data. Based on fault data in the twin data, fault characteristic data is perfected. Based on the training result of the expert system, a mature fault diagnosis model is formed to perfect the function of the expert algorithm.
By adopting the method, the traditional industrial personal computer nonstandard detection equipment can be easily deployed with the monitoring of the working state of the equipment and the expert system of the tested piece; the safety of the operation of the device (especially for large rolling devices, such as rolling test stands for vehicles) can be greatly improved and additional functional values of the device can be increased.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (8)
1. A nonstandard detection device monitoring system, comprising:
edge device: each edge equipment node can be communicated with at least one type of nonstandard detection equipment to acquire the running state information and detection data of the type of nonstandard detection equipment; wherein, each type of nonstandard detection equipment corresponds to at least one type of communication interface; the operation state of each nonstandard detection device can be analyzed based on the collected operation data, and the data processing of the nonstandard devices is assisted based on the detection data of the nonstandard devices;
data cooperative device: the cloud server data are distributed through communication with each edge equipment node, and the computing capacity of the edge equipment is cooperatively scheduled to realize data processing optimization;
remote gateway: the cloud server is connected with the data cooperative equipment, and is communicated with the cloud server, and control information and update information of the edge equipment node are sent to the edge equipment node through the data cooperative equipment;
the nonstandard detection equipment is communicated with the remote gateway and the tested piece so as to send the tested piece detection information to the remote gateway and collect the detection data of the tested piece.
2. The nonstandard detection device monitoring system of claim 1, wherein the data collaboration device is configured at an edge device node connected to the nonstandard detection device and has new operational computing requirements, and distributes data required by the new operational computing requirements to idle edge device nodes to perform operational computing, thereby realizing data processing optimization.
3. The nonstandard detection device monitoring system of claim 1, wherein the edge device node is configured with:
state monitoring algorithm: acquiring data of nonstandard detection equipment, and analyzing the running state of the nonstandard detection equipment based on the data;
expert system algorithm: and acquiring sensor data, and performing data analysis on detection data of non-standard detection equipment to analyze the performance of the tested piece.
4. The nonstandard detection device monitoring system of claim 3, wherein the nonstandard detection device comprises an industrial personal computer, the edge device comprises a TCP/IP-based edge device node in communication with the industrial personal computer and a sensor, the sensor connected to the test piece;
the data required by the industrial personal computer state monitoring algorithm and the expert system algorithm can be used for directly acquiring sensor information or carrying out data twinning through the industrial personal computer to acquire the industrial personal computer data.
5. The nonstandard detection device monitoring system of claim 4, wherein the execution flow of the expert system algorithm comprises:
a data preprocessing step: the method comprises the steps of data slicing processing, filtering processing, resampling processing and normalized sampling frequency processing;
and a feature extraction step: determining normal key features and fault key features based on the statistical information of the normal operation data and the fault operation data;
algorithm training: carrying out algorithm training based on the training model, the preprocessing data and the feature extraction data;
algorithm pre-verification step: and comparing the detected data of the tested piece with the algorithm generation data to verify the accuracy of the algorithm.
6. The nonstandard detection device monitoring system of claim 5, wherein the expert system algorithm is further configured to:
performing data preprocessing and feature extraction based on historical data;
and (3) carrying out fault data injection based on the twin data, and carrying out algorithm training by combining the data after feature extraction.
7. The nonstandard detection device monitoring system of claim 6, wherein the nonstandard detection device comprises an image acquisition device, and wherein when the edge device node is an image monitoring edge device, the expert system algorithm is configured to denoise the image, identify the image, and the like based on the image acquisition data.
8. The nonstandard detection device monitoring system of claim 1, wherein the edge device further comprises an edge device node based on RS485, RS232 serial communication, a USB-based edge device node, a GPIB-based edge device node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110917137.3A CN113627527B (en) | 2021-08-11 | 2021-08-11 | Nonstandard detection equipment monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110917137.3A CN113627527B (en) | 2021-08-11 | 2021-08-11 | Nonstandard detection equipment monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627527A CN113627527A (en) | 2021-11-09 |
| CN113627527B true CN113627527B (en) | 2024-02-02 |
Family
ID=78384231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110917137.3A Active CN113627527B (en) | 2021-08-11 | 2021-08-11 | Nonstandard detection equipment monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627527B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114217540A (en) * | 2021-11-10 | 2022-03-22 | 深圳市鑫信腾科技股份有限公司 | Control method, device, equipment and storage medium of non-standard equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110830943A (en) * | 2019-11-06 | 2020-02-21 | 湖南银河电气有限公司 | Equipment state monitoring system based on edge calculation and big data analysis |
| CN111698470A (en) * | 2020-06-03 | 2020-09-22 | 河南省民盛安防服务有限公司 | Security video monitoring system based on cloud edge cooperative computing and implementation method thereof |
| CN112463393A (en) * | 2020-12-14 | 2021-03-09 | 国网辽宁省电力有限公司抚顺供电公司 | Power distribution Internet of things edge computing architecture design method based on Mongo cluster technology |
| KR102262321B1 (en) * | 2019-11-29 | 2021-06-08 | 주식회사 두두원 | IoT GATEWAY SYSTEM FOR INDUSTRIAL |
| CN113112086A (en) * | 2021-04-22 | 2021-07-13 | 北京邮电大学 | Intelligent production system based on edge calculation and identification analysis |
-
2021
- 2021-08-11 CN CN202110917137.3A patent/CN113627527B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110830943A (en) * | 2019-11-06 | 2020-02-21 | 湖南银河电气有限公司 | Equipment state monitoring system based on edge calculation and big data analysis |
| KR102262321B1 (en) * | 2019-11-29 | 2021-06-08 | 주식회사 두두원 | IoT GATEWAY SYSTEM FOR INDUSTRIAL |
| CN111698470A (en) * | 2020-06-03 | 2020-09-22 | 河南省民盛安防服务有限公司 | Security video monitoring system based on cloud edge cooperative computing and implementation method thereof |
| CN112463393A (en) * | 2020-12-14 | 2021-03-09 | 国网辽宁省电力有限公司抚顺供电公司 | Power distribution Internet of things edge computing architecture design method based on Mongo cluster technology |
| CN113112086A (en) * | 2021-04-22 | 2021-07-13 | 北京邮电大学 | Intelligent production system based on edge calculation and identification analysis |
Non-Patent Citations (1)
| Title |
|---|
| 面向3C非标检测设备的可配置监控系统研究与实现;李宝超;武智强;张承瑞;胡天亮;;组合机床与自动化加工技术(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627527A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109144014B (en) | System and method for detecting operation condition of industrial equipment | |
| CN110733038B (en) | Industrial robot remote monitoring and data processing system | |
| CN102072829B (en) | Iron and steel continuous casting equipment oriented method and device for forecasting faults | |
| CN113569475B (en) | Subway axle box bearing fault diagnosis system based on digital twin technology | |
| CN112101767B (en) | Equipment running state edge cloud fusion diagnosis method and system | |
| CN112995022A (en) | Industrial Internet of things gateway | |
| CN108508856B (en) | Intelligent control system and method for industrial equipment | |
| CN107345857A (en) | A kind of electro spindle condition monitoring and failure diagnosis system and its monitoring, diagnosing method | |
| CN112594142B (en) | Terminal cloud collaborative wind power operation and maintenance diagnosis system based on 5G | |
| CN110362037A (en) | A kind of integrated maintenance system platform for numerically-controlled machine tool | |
| CN113627527B (en) | Nonstandard detection equipment monitoring system | |
| CN111242807B (en) | Method for accessing substation data into ubiquitous power Internet of things | |
| CN111770016A (en) | Intelligent cloud gateway, automobile digital detection system and data processing method | |
| CN112506097A (en) | Jig frame remote monitoring system and method based on industrial internet | |
| CN110380880A (en) | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame | |
| WO2009127137A1 (en) | Centralized parsing method for remote device data flow | |
| CN111224840A (en) | Gateway system with fault diagnosis performance and method thereof | |
| CN114827140A (en) | Real-time data centralized management and control system for wind tunnel site | |
| CN201699739U (en) | AT91RM9200-based fieldbus protocol conversion gateway platform | |
| CN111600923A (en) | NET Core-based OPC UA protocol server system | |
| CN201429790Y (en) | Punching-machine remote monitoring device | |
| CN208751840U (en) | A kind of pump health monitoring and fault diagnosis system | |
| CN208296971U (en) | A kind of remote oscillation analysis system | |
| CN109002005A (en) | A kind of intelligent pneumatic data acquisition control terminal | |
| CN116074351A (en) | Edge cloud collaborative management system based on edge computing |
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 |