CN115409213A - Digital road operation and maintenance method based on predictive maintenance - Google Patents

Abstract

The invention relates to a digital road operation and maintenance method based on predictive maintenance. The micro-service is used as a technical framework, three data processing links of data acquisition, data analysis, fault prediction and decision support are separated, a complex predictive operation and maintenance function is effectively decomposed into manageable services, and the main services comprise: data acquisition service, data preprocessing service, fault prediction analysis service, fault early warning and fault alarm processing service.

Description

Digital road operation and maintenance method based on predictive maintenance

Technical Field

The invention belongs to the technical fields of Internet of things technology, smart city application and the like, and particularly relates to a digital road operation and maintenance method based on predictive maintenance, which is particularly suitable for an equipment operation and maintenance management system in the fields of digital roads and intelligent manufacturing industry.

Background

The digital road operation and maintenance method based on predictive maintenance has wide application, is spread in a plurality of fields such as intelligent buildings, smart cities, intelligent transportation, intelligent power grids, environmental protection, industrial monitoring, smart factories and the like, and has wide application prospect. In terms of industrial application, the technical conditions and market conditions of the internet of things technology are most mature when the internet of things technology is popularized in the field of digital roads and intelligent manufacturing industry, the operation and maintenance method of predictive maintenance is combined with the internet of things technology, the use scene is gradually promoted to extend from equipment maintenance to scheduling establishment, spare part management and the like, and huge economic and social benefits can be generated.

As shown in fig. 2, the development of the operation and maintenance service goes through four stages: responsive service, scheduled maintenance, condition-based maintenance, failure prediction-based maintenance. In the technical scheme of the traditional intelligent building, the fault information is mainly realized through alarm information reported by hardware, once a threshold value is configured for a hardware alarm item, when a user needs to configure other threshold values, the dynamic updating of the parameters of the threshold values is difficult to realize, and the predictive analysis of the parameter values cannot be realized. And technicians are arranged to be on site for maintenance only after the equipment is failed and disconnected. Because the traditional maintenance mode usually occurs after the equipment is in failure, the equipment has high unpredictability and burstiness, the damage degree of the equipment is high, the conditions of repair time, cost increase and the like are easily caused, and the side effects of high outage time cost and the like are also easily caused. How to discover the potential safety hazard of equipment in advance, promote the whole operating efficiency of intelligent terminal, the operation and maintenance method of predictive maintenance becomes one of them important link.

Disclosure of Invention

The invention aims to provide a digital road operation and maintenance method based on predictive maintenance, which can find potential equipment safety hazards in time and improve the overall operation efficiency of an intelligent terminal through the predictive maintenance method, wherein the predictive maintenance is the latest development of operation and maintenance service, mainly benefits from the interactive application of the Internet of things, big data and artificial intelligence, and has the characteristics of initiative and strong pertinence. The core idea of predictive maintenance is to monitor the equipment attributes and the running state and perform failure prediction analysis, thereby maximizing the use benefit of components, reducing the cost caused by equipment outage, and reducing unnecessary waste. The technology is particularly suitable for being embedded into a digital road operation and maintenance management system based on the technology of the Internet of things.

In order to achieve the purpose, the technical scheme of the invention is as follows: a digital road operation and maintenance method based on predictive maintenance maximizes the use benefit of components by monitoring equipment attributes and running states and performing fault prediction analysis, and reduces maintenance time caused by equipment faults and unnecessary cost waste; the method provides a digital road operation and maintenance system with predictive maintenance, which comprises a data acquisition module, a data preprocessing module, a fault prediction analysis module and a fault early warning and alarm processing module; wherein the content of the first and second substances,

the data acquisition module is used for acquiring different data from different equipment sources and acquiring real-time data through the sensors and the equipment operation data; production data is acquired through object model information;

the data preprocessing module is used for combining different data from different equipment sources acquired by the data acquisition module according to the object model relation, eliminating abnormal data in the acquired data, and replacing the abnormal data by approximate values or using a smaller data set according to the characteristics of the attributes of the acquired data;

the fault prediction analysis module is used for realizing the prediction analysis of faults by building a fault prediction analysis algorithm, wherein the fault prediction analysis comprises intelligent prediction analysis based on an AI algorithm combined with a knowledge base and fault alarm diagnosis based on expression dynamic operation, an operational expression is generated through the relation of parameters among different attributes of different equipment, the fault prediction analysis algorithm is used for acquiring the running state of the online monitoring equipment in real time, and generating a fault alarm event when the fault early warning condition is met through the parameter assignment and operation of the operational expression;

the fault early warning and fault warning processing module is used for realizing fault prediction and decision support, carrying out maintenance scheduling decision on fault early warning information and fault information of all service systems, issuing a detection instruction to equipment in the maintenance process, acquiring an operation index of the detection equipment or operation attributes of other associated equipment, and judging whether the current equipment is normal or not and whether maintenance is needed or not.

Compared with the prior art, the invention has the following beneficial effects: the invention and the optimized scheme thereof can be widely applied to application scenes of digital roads, intelligent manufacturing industry and the like. The equipment integrated by the system can find potential safety hazards of the equipment in time through a predictive maintenance method, the overall operation efficiency of the intelligent terminal is improved, and the safety and stability of the whole system are guaranteed.

Drawings

FIG. 1 is a schematic diagram of functional modules for implementing the present invention.

FIG. 2 is a development process diagram of an operation and maintenance service.

FIG. 3 is a schematic diagram of the present invention for operational loading.

FIG. 4 is an object model diagram of an apparatus according to an embodiment of the present invention.

Detailed Description

The technical scheme of the invention is specifically explained in the following by combining the attached drawings.

In order to make the features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below:

it should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.

As shown in fig. 1, the digital road operation and maintenance method based on predictive maintenance according to the embodiment of the present invention maximizes the use efficiency of components by monitoring the device attributes and the runtime state and performing fault prediction analysis, and reduces the maintenance time caused by device faults and reduces unnecessary cost waste. The predictive maintenance comprises a plurality of functional modules of data acquisition, data preprocessing, fault prediction analysis, fault early warning and fault alarm processing, helps a client to realize standardized, scientific and intelligent management of equipment, reduces the equipment fault rate, maintains the equipment stability and realizes the comprehensive promotion of asset benefits.

The main business logic contained in the method comprises the following steps:

(1) The data acquisition function is used for acquiring the attribute of the equipment and the running state of the equipment and analyzing according to the attribute of the object model;

(2) The data preprocessing function is realized, different data from different equipment sources are combined according to the object model relationship, and abnormal data in the acquired data are eliminated;

(3) A fault prediction algorithm is realized, and the prediction and fault diagnosis of the fault trend are realized;

(4) Fault prediction and decision support are realized, and maintenance scheduling decision is carried out on fault early warning information and fault information of all service systems;

(5) And issuing detection instructions to different types of equipment instances through the object models of the instances, and receiving messages fed back by the detection instructions.

The technical standard of Restful architecture is adopted in the design of the interface data acquisition interface, the instruction issuing interface, the fault expression configuration interface and the work order interface, the butt joint requirements of application system information developed by different manufacturers, different products, different operating environments and different development tools can be met, loose and low-coupling integration is realized, and different information systems can call functional services mutually. The RESTful architecture is currently one of the most popular internet software architectures. The software designed based on the style has the advantages of clear structure, conformity with standards, easy understanding and convenient expansion, and the software designed based on the style can be simpler, has more layers and is easier to realize mechanisms such as cache and the like.

As shown in fig. 3, the operation process of predictive maintenance of the present embodiment is classified into three stages. Stage one: and data acquisition, wherein the system acquires real-time data through sensor and equipment operation data, and the system supports the acquisition of necessary production data through object model information. And a second stage: and data analysis, namely combining different data from different equipment sources, removing abnormal data in the acquired data, and considering whether to replace approximate values or use a smaller data set according to the characteristics of the acquisition attributes. And a third stage: the fault prediction and decision support is realized, the prediction of the fault trend is realized, the fault alarm diagnosis report is pushed to operation and maintenance personnel in the form of a work order, and the operation and maintenance personnel can maintain or make relevant decisions through the work order platform, carry out relevant processing, issue equipment detection instructions and the like.

The invention discloses a digital road operation and maintenance method based on predictive maintenance, which has the main functions defined as follows:

(1) Data acquisition interface

The collection of the information of the equipment of the Internet of things is realized, the data definition is transmitted in a JSON mode, the concept of an object model is introduced into the system aiming at the problem that the data objects of different equipment are inconsistent, and the data storage is realized in an object model mode aiming at the condition. Data are defined in table 1:

TABLE 1

(2) Instruction issuing interface

The device instruction issuing function is provided, the system can initiate the test more easily, the instruction mainly comprises a query instruction, a control instruction, a parameter configuration instruction and the like, and the system supports the execution condition of the tracking instruction. Data are defined as table 2:

TABLE 2

(3) Object model definition

As shown in fig. 4, the object model defines the functions of the product in a digital description mode of the product, and uses device management as an entry point, and abstracts and summarizes the functions of the products of different brands and categories to form a "standard object model", which is convenient for all parties to describe, control and understand the functions of the product in a uniform language. The object model is a digital representation of an entity (such as a laser radar, a speed measurement camera, an RSU, an OLT, and the like) in a physical space at a cloud end, and describes what the entity is, what the entity can do, and what information can be provided to the outside from three dimensions of attributes, services, and events, respectively, and the storage structure of the object model is shown in fig. 3. Data are defined as table 3:

TABLE 3

(4) Object model attribute definition

The system can read and analyze the data value stored in the object model through the attribute definition of the object model. Data are defined as table 4:

TABLE 4

(5) Alarm rule configuration interface

The system supports the function of an alarm rule configuration interface, an operational expression is generated through the relation of parameters among different attributes of different equipment, the operational state of the equipment is monitored on line in real time through the operational expression, and a fault alarm work order is generated when the fault condition is met. Data are defined as table 5:

TABLE 5

(6) Creating work order interface

The system provides a work order creating interface for calling a fault prediction algorithm, and simultaneously generates different alarm work orders according to the business rules of the business work orders. Data are defined as table 6:

TABLE 6

(7) Work order state feedback interface

And providing a work order state callback interface. Data are defined as table 7:

TABLE 7

The above-described interface uses a REST style Http-based or https-based protocol. All programming languages that support http protocol requests may call APIs such as php, C #, asp, java, delphi, etc. The following describes the interface protocol:

interface calling mode

{ interface issuing address } + { calling method }

For example, http:// host: port/open/sync/sys/getrevnum

Note that sys/getrevnum is the specific interface address

Calling object packet of protocol:

calling the API, system parameters and application parameters must be imported. The application parameters refer to specific API interfaces because different APIs are different respectively; the system parameters and application parameters are a Json object, and the detailed description of the system parameters is shown in table 8:

TABLE 8

Response packet of protocol:

the answer format is returned in json's data format, as in table 9:

TABLE 9

Call instantiation for a protocol

And calling a data synchronization interface of a certain school, wherein the system configuration key is as follows:

SyncSignKey (signing key): XXXXXXXXXXXXXXXXXXXX

Secrekey (data AES encryption/decryption key): XXXXXXXXXXX

initVector (data AES encryption/decryption offset): XXXXXXX

Third party platform encoding: 100000001

Input parameters (System parameters)

Caller：100000001

Timestamp：20170821191701123

TransactionId：X00001

PageSize: 500. remarking: the interface that does not need to be distributed may not store values

Input parameters (application parameters): remarking: input parameters, detailed in each interface definition

StartRevNum：0

EndRevNum：162136

1. Generating Json objects for input application parameters

The generated Json object is as follows:

{StartRevNum:0,EndRevNum:162136}

2. encrypting input application parameter Json object

{ StartRevNum:0, endRevNum 162136} the encryption results are as follows:

/VGEQdcjrxGPsGMaP0+wyxYrSVJ5iH0ODpE62GO5Uabl6lAd7qy5gTBISv+sC1WM

3. generating input parameter signatures

And (3) character strings to be signed:

10000000120190104153645001X000015000/VGEQdcjrxGPsGMaP0+wyxYrSVJ5iH0ODpE62GO5Uabl6lAd7qy5gTBISv+sC1WMA264232F914BAA1CAAD98016C06505829C3C5BCEB92DB331

the generated signature is as follows:

0d81c24655baebabe48cedc45e423119

4. generating submitted Json objects

5. Submit data (POST mode)

The Json object generated in the previous step is put to http:// www.xxx.cn/open/sync/School/Getschool

6. Data returned by server

Matters of attention

All request and response data encodings are in utf-8 format

Commit data committed in Post

Content-Type is set to application/json.

The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.

Claims (4)

1. A digital road operation and maintenance method based on predictive maintenance is characterized in that the use benefit of components is maximized, the maintenance time caused by equipment failure is reduced, and unnecessary cost waste is reduced by monitoring equipment attributes and running states and performing fault predictive analysis.

2. The digital road operation and maintenance method based on predictive maintenance of claim 1, wherein a digital road operation and maintenance system based on predictive maintenance is provided, comprising a data acquisition module, a data preprocessing module, a failure prediction analysis module, a failure early warning and failure alarm processing module; wherein the content of the first and second substances,

the data acquisition module is used for acquiring different data from different equipment sources and acquiring real-time data through the sensors and the equipment operation data; production data is acquired through object model information;

the preprocessing data module is used for combining different data acquired by the data acquisition module from different equipment sources according to an object model relation, eliminating abnormal data in the acquired data, and replacing the abnormal data by approximate values or using a smaller data set according to the characteristics of the acquired data attributes;

the fault prediction analysis module is used for realizing the prediction analysis of faults by building a fault prediction analysis algorithm, the fault prediction analysis comprises intelligent prediction analysis based on an AI algorithm combined with a knowledge base and fault alarm diagnosis based on expression dynamic operation, an operational expression is generated through the relationship of parameters among different attributes of different equipment, the fault prediction analysis algorithm is used for acquiring the running state of the online monitoring equipment in real time, and generating a fault alarm event when fault early warning conditions are met through the parameter assignment and operation of the operational expression;

the fault early warning and fault warning processing module is used for realizing fault prediction and decision support, carrying out maintenance scheduling decision on fault early warning information and fault information of all service systems, issuing a detection instruction to equipment in the maintenance process, acquiring an operation index of the detection equipment or operation attributes of other associated equipment, and judging whether the current equipment is normal or not and whether maintenance is needed or not.

3. The digital road operation and maintenance method based on predictive maintenance according to claim 2, wherein the fault early warning and fault alarm processing module supports issuing detection instructions to different types of equipment instances through the object models of the instances and receives messages fed back by the detection instructions.

4. The digital road operation and maintenance method based on predictive maintenance of claim 2, characterized in that the method performs the following functional definitions:

(1) Data acquisition interface

The method comprises the steps of realizing the acquisition of the equipment information of the Internet of things, transmitting data definition in a JSON mode, introducing the concept of an object model aiming at the problem of inconsistent data objects of different equipment, and storing data in the object model mode aiming at the condition;

(2) Instruction issuing interface

Providing an equipment instruction issuing function, wherein the instruction comprises a query instruction, a control instruction and a parameter configuration instruction, and supports the execution condition of a tracking instruction;

(3) Object model definition

The object model defines the functions of the product by taking the digital description mode of the product and equipment management as an entry point, abstracts and summarizes the functions of the products with different brands and varieties to form a standard object model, and is convenient for all parties to describe, control and understand the functions of the product by using a uniform language; the object model is a digital representation of an entity in a physical space at a cloud end;

(4) Object model attribute definition

The object model attribute defines the concrete form of the object model, and the data value stored in the object model is read and analyzed through the attribute definition of the object model;

(5) Alarm rule configuration interface

Providing an alarm rule configuration interface function, generating an operational expression through the relation of parameters among different attributes of different equipment, monitoring the running state of the equipment in real time and generating a fault alarm work order when fault conditions are met by the expression;

(6) Creating work order interface

Providing a created work order interface for calling a fault prediction analysis algorithm, and generating different alarm work orders according to business work order business rules;

(7) Work order state feedback interface

And providing a work order state callback interface.

Images