Construction machinery intelligent verification method applied to railway construction industry

By combining computer vision technology and intelligent verification methods of digital site systems, problems such as discontinuity of manual verification and signal interference in construction machinery identification verification are solved, efficient and accurate supervision of construction machinery is achieved, and mechanical recognition rate and construction safety are improved. .

CN119027045APending Publication Date: 2024-11-26SHANGHAI DONGHUA DIFANG TIELU DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411061415.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing construction machinery identification and verification methods have problems such as discontinuous manual verification, high signal interference, high cost and low accuracy, making it difficult to achieve efficient and accurate construction machinery supervision.

Method used

Using intelligent verification methods combining computer vision technology and digital construction site systems, the construction machinery is identified through intelligent analysis boxes and cameras, and the mechanical identification model is used to compare with the allowed work list to achieve real-time early warning and alarm, ensuring the standardization of the mechanical verification and exit process. .

Benefits of technology

The mechanical identification rate has been improved to 98%, efficient and accurate construction machinery supervision has been achieved, the frequency of production accidents has been reduced, and construction safety has been ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027045A_ABST
    Figure CN119027045A_ABST
Patent Text Reader

Abstract

The invention discloses a construction machinery intelligent verification method applied to the railway construction industry, and the method comprises the steps: carrying out the online verification of construction machinery, carrying out the examination and approval of the verification, issuing a mechanical verification certificate for the construction machinery which passes the examination and approval, and pasting the certificate on the construction machinery; performing construction machinery identification on a video currently shot by a camera on a construction site by using a machinery identification model in the intelligent analysis box, and comparing an identification result with a list of construction machinery allowed to work on the current day; on the basis of the identification result and the comparison result, early warning or alarm pushing is carried out on the construction machinery which is not submitted for inspection and / or is not in the list of construction machinery allowed to work on the current day; and initiating a withdrawal application for the construction machinery which is not submitted for inspection and / or is not in the list of construction machinery allowed to work on the current day, and withdrawing the construction machinery after approval is passed. The system has the advantages that the standardized management capability of mechanical construction is improved, site construction machinery is effectively monitored, the production accident frequency of a company is reduced, and the safety of iron-related construction is effectively guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of construction machinery verification, and in particular to an intelligent verification method for construction machinery applied to the railway construction industry. Background Art

[0002] At present, the identification and verification of construction machinery in the construction industry mainly include the following methods:

[0003] 1. On-site or remote video monitoring verification: The existing process for machinery verification mostly uses manual verification. After the machinery is reported for inspection, the supervision engineer will affix a certificate of inspection and use on-site inspection or remote inspection with high-definition cameras to manually monitor the machinery and equipment in the construction site in real time. The construction unit, construction unit, and supervision unit are mainly responsible for the part of production safety that is responsible for ensuring the validity of the machinery and equipment inspection and preventing construction risks. Manual verification and some automated systems are difficult to achieve continuous and uninterrupted monitoring. Some machinery may enter the site without inspection but be difficult to detect for a long time, resulting in a supervision loophole.

[0004] 2. Radio Frequency Identification (RFID) Technology: Automatically identify and track machinery with RFID tags through wireless radio frequency signals, and read data without direct line of sight. RFID technology is suitable for asset management, but may encounter signal interference and cost issues in large, mobile or metal-intensive construction machinery environments.

[0005] 3. Barcode and QR code recognition: simple and low-cost, suitable for static mechanical recognition and basic information reading, but limited in durability and scanning efficiency in dynamic, outdoor or harsh environments.

[0006] 4. GPS and GIS technology: used to remotely track and locate heavy machinery, suitable for large-scale construction projects, but the accuracy is affected by satellite signal quality and obstruction, and does not directly provide detailed identity information of mechanical equipment.

[0007] To sum up, the construction industry urgently needs a new construction machinery identification and verification method to solve the problems existing in the current construction machinery identification and verification method. Summary of the invention

[0008] The purpose of the present invention is to provide an intelligent verification method for construction machinery applied to the railway construction industry, so as to solve the above-mentioned problems existing in the prior art.

[0009] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0010] A construction machinery intelligent verification method applied to the railway construction industry comprises the following steps:

[0011] S1. Mechanical inspection stage:

[0012] Conduct online inspection and approval of construction machinery, issue machinery inspection certificates to the corresponding construction machinery that has passed the inspection and approval, and post them on the corresponding construction machinery;

[0013] S2, On-site construction stage:

[0014] When the construction plan is issued, the machine recognition model in the intelligent analysis box is used to identify the construction machines in the video currently captured by the construction site camera, and the recognition results are compared with the list of construction machines allowed to operate on that day. Based on the recognition and comparison results, early warnings or alarms are pushed for construction machines that have not been reported and / or are not on the list of construction machines allowed to operate on that day;

[0015] S3, Mechanical Exit Stage:

[0016] For construction machinery that has not been inspected and / or is not on the list of construction machinery allowed to operate on that day, an application for withdrawal will be initiated. After approval, the corresponding construction machinery will withdraw from the construction site.

[0017] Preferably, step S1 specifically includes the following contents:

[0018] S11. Create a construction project in the digital construction site system and assign construction units and personnel accounts and job roles to the construction project;

[0019] S12. The data clerk of the construction unit conducts online mechanical inspection in the digital construction site system and submits it for approval after completing the filling;

[0020] S13. The project manager of the construction unit, the professional supervision engineer of the supervision unit and the chief supervision engineer shall review the machinery inspection report. After the review is passed, the construction machinery inspection report is qualified. The professional supervision engineer shall issue a machinery inspection certificate to the qualified construction machinery and post it on the corresponding construction machinery.

[0021] Preferably, the mechanical online inspection of the digital construction site system supports manual input, AI query input and data fixation selection;

[0022] Manual input: The content entered by the user is used as a temporary memory bank. If there is the same input later, the previously entered content will be automatically listed in a drop-down list for the user to choose. Typos in the content are automatically identified during the input process, and the correct replacement content is given;

[0023] AI query input: If the corresponding device information exists in the device library, users can filter the device library by keywords, and the matching device data will be accurately presented in the drop-down list for users to select;

[0024] Fixed data selection: Click the drop-down list next to the text box to view and directly select the corresponding data to fill in the fixed data that has not been filtered by AI.

[0025] Preferably, during the machinery inspection process, when the filling function is triggered, the data in the equipment library is automatically matched with the large equipment as a benchmark; and the data that meets the conditions is progressively screened out from the automatically matched equipment data.

[0026] Preferably, during the machinery inspection process, the machinery information and photos can be filled in individually; or the template can be downloaded and imported, and the machinery information and photos can be filled in in batches according to the template.

[0027] Preferably, step S2 specifically includes the following steps:

[0028] S21. After the construction plan is issued, cameras and intelligent analysis boxes are deployed at the construction site. The cameras are connected to the intelligent analysis boxes. By drawing the deployment area, the mechanical recognition model is selected, and the alarm detection time, allocation confidence threshold, and IOU target intrusion overlap threshold are set, and the corresponding construction project number is selected to implement the deployment of cameras and intelligent analysis boxes.

[0029] S22. During the construction process, the intelligent analysis box uses the mechanical recognition model trained by Yo lov5 to identify the construction machinery target in the video captured by the camera according to the deployment settings, and pushes the recognition results to the background of the digital construction site system;

[0030] S23, the digital construction site system backend calls the railway adjacent operating lines and operating line construction plan interface to obtain the list of construction machinery allowed to operate on the current construction project on that day;

[0031] S24. The digital construction site system backend compares the identification result with the list of construction machinery allowed to operate on that day to obtain a comparison result, and based on the identification result and the comparison result, issues a warning or an alarm push for the construction machinery that has not been reported and / or is not in the list of construction machinery allowed to operate on that day.

[0032] Preferably, in step S21, the 5-meter alarm area, the 30-meter adjacent warning area, and the 30-meter reminder area are mapped through on-site reference object calibration and binocular ranging algorithm, and area matching is performed according to the target object coincidence algorithm to realize the deployment setting of the camera and the intelligent analysis box.

[0033] Preferably, step S2 further includes,

[0034] S25. After receiving the early warning or alarm push, the command center of the construction unit, supervision unit, construction unit, and equipment management unit will initiate emergency response, and based on manual verification, issue a safety inspection question sheet and a supervision engineer notice for rectification feedback.

[0035] The beneficial effects of the present invention are as follows: 1. The present invention proposes a solution to the problem of intelligent supervision of machinery verification in railway construction. By combining advanced computer vision technology and digital construction site systems, it ensures that construction machinery complies with the predetermined plan and realizes efficient and accurate safety management. 2. The method of the present invention improves the standardized management capability of mechanical construction, with a mechanical recognition rate of more than 98%, effectively monitors on-site construction machinery, reduces the frequency of production accidents in the company, and effectively ensures the safety of railway-related construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of an intelligent verification method in an embodiment of the present invention;

[0037] Figure 2 is a schematic diagram of creating a digital construction site system project in an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of a single filling in mechanical inspection in an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of batch filling of mechanical inspection in an embodiment of the present invention;

[0040] Figure 5 It is a schematic diagram of mechanical inspection and filling rules in an embodiment of the present invention;

[0041] Figure 6 It is the mechanical equipment import rule in the embodiment of the present invention;

[0042] Figure 7 This is a schematic diagram of mechanical inspection and approval in an embodiment of the present invention;

[0043] Figure 8 is a schematic diagram of construction machinery control in an embodiment of the present invention;

[0044] Fig. 9 is a schematic diagram of a list of construction machinery allowed to operate in an embodiment of the present invention;

[0045] Fig.10 This is a schematic diagram of early warning or alarm push in an embodiment of the present invention;

[0046] Fig.11 This is a schematic diagram of the alarm push process in an embodiment of the present invention;

[0047] Fig.12 It is a schematic diagram of closed-loop rectification of problems in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention and are not used to limit the present invention.

[0049] like Figure 1 As shown, in this embodiment, a construction machinery intelligent verification method applied to the railway construction industry is provided, which specifically includes three parts:

[0050] 1. Mechanical inspection stage:

[0051] The construction machinery is inspected and approved online, and a machinery inspection certificate is issued to the construction machinery that has passed the inspection and approval, and it is posted on the corresponding construction machinery.

[0052] Specifically, it includes the following contents:

[0053] 1.1. Create a construction project in the digital construction site system, and assign participating units and personnel accounts and job roles to the construction project (participating units include construction units, supervision units, construction units, equipment management units, etc.); see Attachment Figure 2 .

[0054] 1.2. The construction unit's document clerk conducts online machinery inspection in the "Large Machinery Inspection Module" in the digital construction site system, and submits it for approval after completing the form.

[0055] In this embodiment, during the machinery inspection process, by clicking the add button, you can fill in the machinery information and photos individually (such as Figure 3 You can also click Import to download the import template, fill in the machinery information and photos in batches according to the template, and upload the import in batches (such as Figure 4 Then click Submit to enter the approval process.

[0056] like Figure 5 As shown, in this embodiment, during the machinery inspection process, when the filling function is triggered, the data in the equipment library is automatically matched based on the large equipment; and the data that meets the conditions is progressively screened out from the automatically matched equipment data.

[0057] The mechanical online inspection of the digital construction site system supports manual input, AI query input and data fixation selection;

[0058] (1) Manual input: The content entered by the user is used as a temporary memory bank. If the same content is entered later, the previously entered content will be automatically listed in a drop-down list for the user to select. Typos in the content will be automatically identified during the input process, and the correct replacement content will be given;

[0059] (2) AI query input: If the corresponding device information exists in the device library, the user can filter the device library by keyword, and the matching device data will be accurately presented in the drop-down list for the user to select;

[0060] (3) Fixed data selection: Click the drop-down list next to the text box to view and directly select the corresponding data to fill in the fixed data that has not been filtered by AI.

[0061] In this embodiment, a large amount of device information is stored in the device library. For the rules for importing device information into the device library, see the attached Figure 6 .

[0062] 1.3. The project manager of the construction unit, the professional supervision engineer of the supervision unit and the chief supervision engineer shall review the machinery inspection report. After the review is passed, the construction machinery inspection report is qualified. The professional supervision engineer shall issue a machinery inspection certificate to the qualified construction machinery and post it on the corresponding construction machinery. Figure 7 shown.

[0063] 2. On-site construction stage:

[0064] When a construction plan is issued, the machine recognition model in the intelligent analysis box is used to identify the construction machinery in the video currently captured by the construction site camera, and the recognition result is compared with the list of construction machinery allowed to operate on that day. Based on the recognition and comparison results, early warnings or alarms are pushed to construction machinery that has not been reported and / or is not on the list of construction machinery allowed to operate on that day.

[0065] Specifically, it includes the following contents:

[0066] 2.1. After the construction plan is issued, cameras and smart analysis boxes are deployed at the construction site. The cameras are connected to the smart analysis boxes. By drawing the deployment area, the machine recognition model is selected (multiple machine recognitions can be supported), and the alarm detection time, allocation confidence threshold, IOU target intrusion overlap threshold are set, and the corresponding construction project number is selected to implement the deployment of cameras and smart analysis boxes; see the attached Figure 8 .

[0067] In this embodiment, the 5-meter alarm area, the 30-meter adjacent warning area, and the 30-meter reminder area are mapped through on-site reference object calibration and binocular ranging algorithm, and area matching is performed according to the target object coincidence algorithm to realize the deployment setting of the camera and the intelligent analysis box.

[0068] In this embodiment, intelligent analysis boxes and cameras are deployed in the construction area, specific algorithms are configured to identify different types of machinery, and alarm thresholds are set to ensure accurate monitoring and timely response.

[0069] 2.2. During the construction process, the intelligent analysis box uses the mechanical recognition model trained by Yo lov5 to identify construction machinery targets in the video captured by the camera according to the deployment settings, and pushes the recognition results to the background of the digital construction site system.

[0070] In this embodiment, during construction, the intelligent analysis box analyzes the video stream in real time, uses the training model to identify the type and quantity of machinery, and compares it with the plan. If it is found that the inspection is not completed or the quantity is exceeded (the quantity does not match the plan), the system automatically issues an early warning message, and the low credibility situation is pushed to the platform for review to ensure that the inspection is correct or the discrepancy is handled quickly.

[0071] 2.3. The digital construction site system backend calls the railway adjacent operating lines and operating line construction plan interface to obtain the list of construction machinery allowed to operate on the current construction project on that day; see the attached Fig. 9 .

[0072] 2.4. The digital construction site system backend will compare the identification results with the list of construction machinery allowed to operate on that day to obtain the comparison results, and based on the identification results and comparison results, issue early warnings or alarm pushes for construction machinery that has not been reported and / or is not in the list of construction machinery allowed to operate on that day; see Attachment Fig.10 and attached Fig.11 .

[0073] 2.5. After receiving the early warning or alarm push, the command center of the construction unit, supervision unit, construction unit, and equipment management unit will initiate emergency response. According to the manual verification, they will issue a safety inspection problem sheet and a supervision engineer notice sheet for rectification feedback, forming a closed-loop process to achieve high-efficiency and high-accuracy all-weather safety monitoring; see Attachment Fig.12 .

[0074] In this embodiment, the early warning or alarm information is directly transmitted to the command center of the construction, supervision, construction, and equipment management units, and emergency measures are immediately initiated. Relying on functions such as problem sheets and supervision notices, rapid rectification feedback and processing of on-site problems are achieved, forming a closed-loop management to ensure safe and efficient construction.

[0075] 3. Mechanical exit stage:

[0076] For construction machinery that has not been inspected and / or is not on the list of construction machinery allowed to operate on that day, an application for withdrawal will be initiated. After approval, the corresponding construction machinery will withdraw from the construction site.

[0077] By adopting the above technical solution disclosed in the present invention, the following beneficial effects are obtained:

[0078] The present invention provides a construction machinery intelligent verification method applied to the railway construction industry. The present invention proposes a solution to the problem of intelligent supervision of machinery verification in railway construction. By combining advanced computer vision technology and digital construction site systems, it ensures that construction machinery complies with the predetermined plan and realizes efficient and accurate safety management. The method of the present invention improves the standardized management capability of mechanical construction, with a mechanical recognition rate of more than 98%, effectively monitors on-site construction machinery, reduces the frequency of production accidents of the company, and effectively ensures the safety of railway-related construction.

[0079] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. An intelligent verification method for construction machinery used in the railway construction industry, characterized by: The following steps are included: S1. Mechanical inspection stage: Conduct online inspection and approval of construction machinery, issue machinery inspection certificates to the corresponding construction machinery that has passed the inspection and approval, and post them on the corresponding construction machinery; S2, On-site construction stage: When the construction plan is issued, the machine recognition model in the intelligent analysis box is used to identify the construction machines in the video currently captured by the construction site camera, and the recognition results are compared with the list of construction machines allowed to operate on that day. Based on the recognition and comparison results, early warnings or alarms are pushed for construction machines that have not been reported and / or are not on the list of construction machines allowed to operate on that day; S3, Mechanical Exit Stage: For construction machinery that has not been inspected and / or is not on the list of construction machinery allowed to operate on that day, an application for withdrawal will be initiated. After approval, the corresponding construction machinery will withdraw from the construction site.

2. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 1 is characterized by: Step S1 specifically includes the following contents: S11. Create a construction project in the digital construction site system and assign construction units and personnel accounts and job roles to the construction project; S12. The data clerk of the construction unit conducts online mechanical inspection in the digital construction site system and submits it for approval after completing the filling; S13. The project manager of the construction unit, the professional supervision engineer of the supervision unit and the chief supervision engineer shall review the machinery inspection report. After the review is passed, the construction machinery inspection report is qualified. The professional supervision engineer shall issue a machinery inspection certificate to the qualified construction machinery and post it on the corresponding construction machinery.

3. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 2 is characterized in that: The mechanical online inspection of the digital construction site system supports manual input, AI query input and data fixation selection; Manual input: The content entered by the user is used as a temporary memory bank. If there is the same input later, the previously entered content will be automatically listed in a drop-down list for the user to choose. Typos in the content are automatically identified during the input process, and the correct replacement content is given; AI query input: If the corresponding device information exists in the device library, users can filter the device library by keywords, and the matching device data will be accurately presented in the drop-down list for users to select; Fixed data selection: Click the drop-down list next to the text box to view and directly select the corresponding data to fill in the fixed data that has not been filtered by AI.

4. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 2 is characterized in that: During the machinery inspection process, when the filling function is triggered, the data in the equipment library will be automatically matched based on large equipment; the data that meets the conditions will be progressively filtered out from the automatically matched equipment data.

5. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 2 is characterized by: During the machinery inspection process, you can fill in the machinery information and photos individually; you can also download and import templates and fill in the machinery information and photos in batches according to the templates.

6. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 1 is characterized by: Step S2 specifically includes the following steps: S21. After the construction plan is issued, cameras and intelligent analysis boxes are deployed at the construction site. The cameras are connected to the intelligent analysis boxes. By drawing the deployment area, the mechanical recognition model is selected, and the alarm detection time, allocation confidence threshold, and IOU target intrusion overlap threshold are set, and the corresponding construction project number is selected to implement the deployment of cameras and intelligent analysis boxes. S22. During the construction process, the intelligent analysis box uses the mechanical recognition model trained by Yolov5 to identify the construction machinery target in the video captured by the camera according to the deployment settings, and pushes the recognition results to the background of the digital construction site system; S23, the digital construction site system backend calls the railway adjacent operating lines and operating line construction plan interface to obtain the list of construction machinery allowed to operate on the current construction project on that day; S24. The digital construction site system backend compares the identification result with the list of construction machinery allowed to operate on that day to obtain a comparison result, and based on the identification result and the comparison result, issues a warning or an alarm push for the construction machinery that has not been reported and / or is not in the list of construction machinery allowed to operate on that day.

7. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 6 is characterized by: In step S21, the 5-meter alarm area, 30-meter adjacent warning area, and 30-meter reminder area are mapped through on-site reference object calibration and binocular ranging algorithm, and area matching is performed according to the target object coincidence algorithm to realize the deployment setting of the camera and the intelligent analysis box.

8. The intelligent verification method for construction machinery applied to the railway construction industry according to claim 6 is characterized by: Step S2 also includes, S25. After receiving the early warning or alarm push, the command center of the construction unit, supervision unit, construction unit, and equipment management unit will initiate emergency response, and based on manual verification, issue a safety inspection question sheet and a supervision engineer notice for rectification feedback.