Search

CN-121502707-B - Intelligent diagnosis method and system for signal lamp faults based on Internet of things

CN121502707BCN 121502707 BCN121502707 BCN 121502707BCN-121502707-B

Abstract

The invention provides a signal lamp fault intelligent diagnosis method and system based on the Internet of things, and relates to the technical field of data processing, wherein the method comprises the following steps of 1, collecting electric parameters, environment data, working time sequence information and video image data of a signal lamp unit in real time, and constructing a multi-mode data set of the running state of the signal lamp; and step 3, selecting a plurality of monitoring devices associated with time and space to form a diagnosis group based on the fault position information, and carrying out fusion analysis and collaborative diagnosis on multi-source data of the diagnosis group to generate a fault judgment result. The intelligent diagnosis and operation management of the signal lamp operation state are realized, and the accuracy and the disposal efficiency of fault identification are improved.

Inventors

  • LI JING
  • DU GUANGJUN
  • GAO ZHENXING

Assignees

  • 杭州烽景智能科技有限公司

Dates

Publication Date
20260508
Application Date
20260114

Claims (7)

  1. 1. The intelligent diagnosis method for the signal lamp faults based on the Internet of things is characterized by comprising the following steps of: step 1, acquiring electric parameters, environment data, working time sequence information and video image data of a signal lamp unit in real time, and constructing a multi-mode data set of the running state of the signal lamp; Step 2, transmitting the multi-mode data set to a central diagnosis platform, and carrying out feature extraction and preliminary fault identification by utilizing a pre-trained fault identification model to generate fault type and fault position information; Step 3, determining a space-time association range based on fault location information by combining a preset geographic adjacent threshold value and a time synchronization window, screening signal lamp monitoring equipment in the range, checking the communication state and the data availability, and then constructing a collaborative diagnosis group, collecting multi-source monitoring data of the collaborative diagnosis group in the same time period, performing space-time alignment treatment to generate a standardized collaborative data set with uniform time stamps and geographic coordinates, performing consistency comparison analysis on electric parameters from different monitoring equipment in the standardized collaborative data set, and performing matching degree calculation on the display state and the logic relation of video image data from different monitoring equipment; Step 4, inquiring a fault grade rule base in a platform knowledge base based on a final fault judging result, obtaining grade judging rules and influence range calculating parameters corresponding to fault types, determining an affected traffic road network area and generating a boundary coordinate set according to fault position information and calculating parameters, substituting each vertex coordinate sequence in the boundary coordinate set into a shoelace formula, calculating a polygonal area surrounded by coordinate points in sequence, generating a quantized traffic influence range value, inputting the traffic influence range value and the fault types into the grade judging rules, determining a fault severity grade, integrating the fault types, the fault position information, the fault severity grade and the traffic influence range value, generating structural fault alarm information, pushing the structural fault alarm information to a visual decision board of a command center in real time, and generating an intelligent treatment strategy by combining a preset treatment strategy base; Step 5, extracting a treatment instruction and skill requirements based on an intelligent treatment strategy to generate a work order core element set, integrating structural fault alarm information to generate a standardized electronic operation and maintenance work order, calculating Euclidean distance to generate a distance matrix based on fault position information in the electronic operation and maintenance work order and operation and maintenance personnel dynamic position data acquired in real time, and generating an operation and maintenance personnel candidate list meeting the conditions by combining the skill requirements and an operation and maintenance personnel qualification database; and 6, recording diagnosis data and operation and maintenance response information in the fault treatment process, and adjusting diagnosis logic and treatment strategies by using the operation and maintenance response information to realize intelligent diagnosis and operation and maintenance management of the signal lamp faults.
  2. 2. The intelligent diagnosis method of signal lamp fault based on internet of things according to claim 1, wherein transmitting the multi-modal dataset to a central diagnosis platform, performing feature extraction and preliminary fault recognition by using a pre-trained fault recognition model, generating fault type and fault location information, comprises: Carrying out data preprocessing on the multi-modal data set to generate normalized multi-modal data, and inputting the normalized multi-modal data into a pre-trained fault recognition model; Deep feature learning is carried out on the input regularized multi-mode data by utilizing a feature extraction network in the fault recognition model, and a multi-dimensional feature vector representing the state of the signal lamp is generated; Inputting the multidimensional feature vector into a fault classification branch in a fault recognition model, executing fault mode recognition analysis, and generating a preliminary fault type judgment result; The preliminary fault type judgment result and the multidimensional feature vector are input into a positioning analysis branch in a fault identification model together, the comprehensive feature and the fault type are subjected to association analysis, and positioning information of the fault component or signal lamp position corresponding to the fault type judgment result is generated; And integrating the positioning information of the fault component or the signal lamp position with the preliminary fault type judgment result to generate complete fault type and fault position information.
  3. 3. The intelligent diagnosis method for signal lamp faults based on the internet of things according to claim 2, wherein the fault types comprise signal lamp non-lighting, long-lighting, conflict, jumping, darkening, signal machine crash, power failure, network disconnection, overvoltage, undervoltage, overcurrent and electric leakage electrical abnormality.
  4. 4. The intelligent diagnosis method for signal lamp faults based on the internet of things as claimed in claim 3, wherein the step 6 comprises the following steps: in the whole process from the fault handling flow to the completion of the work order, diagnostic process data related to the fault event, operation and maintenance personnel response time, a handling action sequence executed on site and final handling result verification information are collected and recorded in real time, and a complete fault handling closed-loop record is generated; Carrying out structural processing on the fault treatment closed-loop record, extracting key performance indexes, and generating a multidimensional efficiency evaluation data set comprising fault diagnosis accuracy, response timeliness and treatment success rate; integrating the multidimensional efficacy evaluation data set with the accumulated fault treatment records to generate a training sample set for adjusting the fault recognition model, and performing parameter adjustment on the pre-trained fault recognition model by utilizing the training sample set to generate an adjusted fault recognition model; Based on the fault characteristic analysis result obtained by the adjusted fault recognition model, combining the treatment efficiency and result data recorded in the training sample set, carrying out rule and parameter calibration on a fault level rule base and a treatment strategy base in a platform knowledge base, and generating a calibrated decision rule base; updating the adjusted fault identification model and the calibrated decision rule base to a central diagnosis platform, executing new fault diagnosis and treatment flow, continuously recording operation and maintenance response information, starting a new round of adjustment period, and realizing intelligent diagnosis and operation and maintenance management of the signal lamp faults.
  5. 5. Signal lamp fault intelligent diagnosis system based on the internet of things, which implements the method according to any one of claims 1 to 4, characterized by comprising: The acquisition module is used for acquiring the electrical parameters, the environmental data, the working time sequence information and the video image data of the signal lamp unit in real time and constructing a multi-mode data set of the running state of the signal lamp; the recognition module is used for transmitting the multi-mode data set to the central diagnosis platform, and performing feature extraction and preliminary fault recognition by utilizing the pre-trained fault recognition model to generate fault type and fault position information; the diagnosis module is used for selecting a plurality of monitoring devices related to time and space to form a diagnosis group based on the fault position information, carrying out fusion analysis and collaborative diagnosis on multi-source data of the diagnosis group, and generating a fault judgment result; The judging module is used for combining a fault grade rule base preset in a platform knowledge base based on a fault judging result, quantifying an influence range by calculating an area surrounded by boundary coordinates of a traffic influence area, automatically judging the grade of a fault and the traffic influence range, generating structural fault alarm information, pushing the structural fault alarm information to a visual decision board of a command center for dynamic display, and obtaining an intelligent treatment strategy; The dispatching module is used for generating a standardized electronic operation and maintenance work order according to the intelligent disposal strategy, dispatching the standardized electronic operation and maintenance work order to the mobile terminal of the corresponding operation and maintenance personnel, and starting a fault disposal flow; And the management module is used for recording diagnosis data and operation and maintenance response information in the fault treatment process, and adjusting diagnosis logic and treatment strategies by utilizing the operation and maintenance response information so as to realize intelligent diagnosis and operation and maintenance management of the signal lamp faults.
  6. 6. A computing device, comprising: One or more processors; Storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1 to 4.
  7. 7. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1 to 4.

Description

Intelligent diagnosis method and system for signal lamp faults based on Internet of things Technical Field The invention relates to the technical field of data processing, in particular to a signal lamp fault intelligent diagnosis method and system based on the Internet of things. Background In the field of intelligent traffic management, monitoring and fault diagnosis of the running state of a signal lamp are important links for guaranteeing the traffic safety and efficiency of a road, at present, some existing monitoring schemes mostly rely on acquisition and analysis of electrical parameters of a signal lamp unit to realize fault identification, and in practical application, the dimension and the cooperativity of data analysis of the method are relatively limited, for example, when a system judges the fault of the signal lamp only according to current abnormality, the system can not effectively distinguish whether a light source is damaged or instant fluctuation caused by factors such as poor line contact, environmental interference and the like, and the judgment basis of single dimension can sometimes influence the accuracy of fault positioning and can also limit the evaluation of fault influence. In addition, in the management and treatment links of fault information, the existing partial systems have some limitations in terms of structural presentation of alarm information and automatic scheduling of operation and maintenance resources, and operation and maintenance personnel sometimes need to manually compare information of different systems to comprehensively judge, which may influence timeliness of operation and maintenance response to a certain extent. Disclosure of Invention The technical problem to be solved by the invention is to provide the intelligent diagnosis method and the intelligent diagnosis system for the signal lamp faults based on the Internet of things, so that intelligent diagnosis and operation and maintenance management of the running state of the signal lamp are realized, and the accuracy and the disposal efficiency of fault identification are improved. In order to solve the technical problems, the technical scheme of the invention is as follows: in a first aspect, a signal lamp fault intelligent diagnosis method based on the internet of things, the method comprising: step 1, acquiring electric parameters, environment data, working time sequence information and video image data of a signal lamp unit in real time, and constructing a multi-mode data set of the running state of the signal lamp; Step 2, transmitting the multi-mode data set to a central diagnosis platform, and carrying out feature extraction and preliminary fault identification by utilizing a pre-trained fault identification model to generate fault type and fault position information; Step 3, based on fault location information, selecting a plurality of monitoring devices associated with time and space to form a diagnosis group, and performing fusion analysis and collaborative diagnosis on multi-source data of the diagnosis group to generate a fault judgment result; step 4, based on the fault judgment result, combining a fault grade rule base preset in a platform knowledge base, quantifying an influence range by calculating an area surrounded by boundary coordinates of a traffic influence area, automatically judging the grade of the fault and the traffic influence range, generating structural fault alarm information, pushing the structural fault alarm information to a visual decision board of a command center for dynamic display, and obtaining an intelligent treatment strategy; step 5, generating a standardized electronic operation and maintenance work order according to the intelligent disposal strategy, distributing the standardized electronic operation and maintenance work order to a mobile terminal of a corresponding operation and maintenance person, and starting a fault disposal flow; and 6, recording diagnosis data and operation and maintenance response information in the fault treatment process, and adjusting diagnosis logic and treatment strategies by using the operation and maintenance response information to realize intelligent diagnosis and operation and maintenance management of the signal lamp faults. In a second aspect, a signal lamp fault intelligent diagnosis system based on the internet of things includes: The acquisition module is used for acquiring the electrical parameters, the environmental data, the working time sequence information and the video image data of the signal lamp unit in real time and constructing a multi-mode data set of the running state of the signal lamp; the recognition module is used for transmitting the multi-mode data set to the central diagnosis platform, and performing feature extraction and preliminary fault recognition by utilizing the pre-trained fault recognition model to generate fault type and fault position information; the diagnosis module is used for selecting a p