Cross-business-line bridge construction monitoring method based on machine vision recognition algorithm

Abstract

The invention relates to a cross-business-line bridge construction monitoring method based on a machine vision recognition algorithm, which belongs to the technical field of construction monitoring, and comprises the following steps of: 1, constructing a finite element calculation model, and calculating a theoretical value of a construction equipment monitoring index at a current construction stage; monitoring values of all monitoring indexes of the construction equipment in the test stage and the completed similar load construction stage are obtained; 2, segmenting a bridge construction area and a bridge body based on a safety risk four-color theory, determining risk blocks corresponding to a bridge construction site and a bridge construction part, and drawing a risk block graph; 3, determining a corresponding range of a risk color value corresponding to the risk block based on the theoretical value; and 4, according to a comparison result of a monitoring value and a theoretical value of the monitoring index of the construction equipment at the current construction stage, judging a construction risk state of the construction equipment at the current moment, and filling different colors into the risk block map to display risk states of different positions in the risk block so as to form a field risk four-color map.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction monitoring, and in particular relates to a method for monitoring the construction of a bridge across an operating line based on a machine vision recognition algorithm. Background Art

[0002] With the continuous expansion and improvement of the domestic transportation network, the intersections between existing railway operating lines and newly built highways, railways and municipal roads are becoming more and more frequent. In the process of bridge construction, it is easy for the unfavorable situation that personnel on the operating lines and construction sites are injured or the quality of the project is damaged due to the failure to timely identify and warn of dangerous factors in the construction process and the operating status of the operating lines.

[0003] Therefore, a construction monitoring system and a construction monitoring method are needed to detect the construction site to prevent the occurrence of dangerous situations or accidents. For example, a monitoring method based on machine vision. In general methods, the equipment structure is complex and expensive, and it is difficult to achieve automatic monitoring. Therefore, Chinese patent CN115727820A discloses a multi-point measurement bridge construction monitoring system and method based on machine vision. The monitoring system includes a number of infrared targets, a number of infrared cameras and a control system. The infrared targets are placed at the target points of the bridge in batches according to the construction progress of the bridge. Each infrared camera is used to monitor the captured infrared targets and automatically capture the newly appeared infrared targets. The control system is used to receive the images obtained by the infrared camera in real time and monitor the displacement of the target points. The multi-point measurement bridge construction monitoring system and method based on machine vision provided by the present invention can automatically identify and track the infrared targets at the target points; it applies photogrammetry technology, relies on identifiable infrared targets to automatically identify the construction stage and track and measure the target points around the clock, realizes the monitoring and control of the bridge during the construction process, and realizes the automation and intelligence of bridge construction monitoring;

[0004] However, when special equipment such as bridge erection machines are used for construction, the stress at a certain part of the equipment may be too large or too small. The above scheme does not propose a monitoring method for monitoring indicators such as stress. Stress can only be monitored through displacement monitoring, which has low monitoring accuracy and poor monitoring intuitiveness. Therefore, a cross-operating line bridge construction monitoring method based on machine vision recognition algorithm with high monitoring accuracy and good monitoring intuitiveness is needed. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a method for monitoring the construction of a bridge across an operating line based on a machine vision recognition algorithm, which has the characteristics of high monitoring accuracy and good monitoring intuitiveness.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm comprises the following steps:

[0008] Step 1: Construct a finite element calculation model, calculate the theoretical values ​​of the monitoring indicators of the construction equipment in the current construction phase, and obtain the monitoring values ​​of the monitoring indicators of the construction equipment in the test phase and the completed similar load construction phase;

[0009] Step 2: Based on the four-color theory of safety risk, divide the bridge construction area and the bridge body, determine the risk blocks corresponding to the bridge construction site and the bridge construction part, and draw a risk block map;

[0010] Step 3: Based on the theoretical value, determine the corresponding range of the risk color value corresponding to the risk block;

[0011] Step 4: According to the comparison results between the monitoring values ​​and theoretical values ​​of the monitoring indicators of the construction equipment in the current construction stage, the construction risk status of the construction equipment at the current moment is determined, and different colors are filled in the risk block diagram to show the risk status of different positions in the risk block, forming a four-color map of on-site risks:

[0012] Among them, the colors of the four-color risk map include: red, orange, yellow, and blue, and the corresponding risk levels are: major risk, relatively large risk, general risk, and low risk respectively; when the monitoring value is lower than 50% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a low risk status, and the risk block is displayed in blue; when the monitoring value is between 50%-80% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a general risk status, and the risk block is displayed in yellow; when the monitoring value is between 80%-120% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a relatively large risk status, and the risk block is displayed in orange; when the monitoring value is higher than 120% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a major risk status, and the risk block is displayed in red.

[0013] As a preferred technical solution of the present invention, step one also includes: calculating the theoretical stress values ​​of the beam body, bridge piers, pedestals, ball joints and pile foundations during the construction process, and using them as theoretical values; monitoring the actual stress values ​​of the beam body, bridge piers, pedestals, ball joints and pile foundations during the construction process, and using them as monitoring values.

[0014] As a preferred technical solution of the present invention, the step 2 further includes: when dividing the bridge body, the bridge body is divided into: a beam body, a pier, a cap, a ball joint and a pile foundation.

[0015] As a preferred technical solution of the present invention, the step 2 also includes: after dividing the bridge body, according to engineering requirements, the beam body is split into 0#, 1#, ... N# by segment, and the stress values ​​are counted separately in units of segments.

[0016] As a preferred technical solution of the present invention, the step one also includes: when dividing the bridge construction area, the bridge construction site area is divided into a production area, an office area, a living area, a construction area and an existing line area.

[0017] As a preferred technical solution of the present invention, it also includes step five: performing non-data monitoring to monitor whether there are risk items in the relevant area. If there are risk items, adjusting the risk status of the relevant area to a corresponding level.

[0018] The beneficial effects of the present invention are:

[0019] (1) By effectively dividing the bridge into different parts and carrying out independent risk management for each part within the overall scope of bridge construction, the refinement of bridge safety risk management can be further improved, thereby improving the efficiency of risk management;

[0020] (2) By comparing the theoretical value results of the finite element model with the monitoring values, the safety risks of bridge construction can be predicted and analyzed, the safety risk status of construction equipment in the current construction stage can be accurately assessed, and the accuracy of risk identification can be improved;

[0021] (3) By setting the impact range of each region to 120% of the actual coverage area of ​​the region, when the risk level of a certain region is high, the entire potential impact range of the equipment and structure in this region is included in the impact range. All impact ranges of the equipment or structure in a certain region can be monitored, thereby improving the monitoring accuracy;

[0022] (4) By conducting non-data-based monitoring, some risk items that are difficult to quantify can be included in the color adjustment of the risk four-color diagram and then included in the detection scope, thereby increasing the coverage of the monitoring items and thus improving the monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0024] Figure 1 It is a schematic diagram of the overall steps of the present invention;

[0025] Figure 2 It is a schematic diagram of the relationship between the monitored value and the theoretical value and the color in the four-color diagram of the present invention;

[0026] Figure 3 It is a schematic diagram of the relationship between the influence range of the region and the actual coverage area in the present invention;

[0027] Figure 4 It is a schematic diagram when the influence ranges of the two regions of the present invention overlap.

[0028] Figure 5 It is a schematic diagram after the bridge body of the present invention is divided.

[0029] Legend: 1. Beam; 2. Pier; 3. Ball joint; 4. Cap; 5. Pile foundation. DETAILED DESCRIPTION

[0030] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0031] See also Figure 1-5 A method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm comprises the following steps:

[0032] Step 1: Construct a finite element calculation model, calculate the theoretical values ​​of the monitoring indicators of the construction equipment in the current construction phase, and obtain the monitoring values ​​of the monitoring indicators of the construction equipment in the test phase and the completed similar load construction phase;

[0033] Specifically, the theoretical value is the theoretical stress value calculated in advance according to the "Railway Engineering Seismic Design Code GB50111-2006";

[0034] The monitoring value is obtained by monitoring the actual stress values ​​of the beam body 1, the bridge pier 2, the cap 4, the ball joint 3 and the pile foundation 5 during the construction process;

[0035] Step 2: Based on the four-color theory of safety risk, divide the bridge construction area and the bridge body, determine the risk blocks corresponding to the bridge construction site and the bridge construction part, and draw a risk block map;

[0036] Step 3: Based on the theoretical value, determine the corresponding range of the risk color value corresponding to the risk block;

[0037] Step 4: According to the comparison results between the monitoring values ​​and theoretical values ​​of the monitoring indicators of the construction equipment in the current construction stage, the construction risk status of the construction equipment at the current moment is determined, and different colors are filled in the risk block diagram to show the risk status of different positions in the risk block, forming a four-color map of on-site risks:

[0038] During actual construction, different bridge parts bear or are subjected to different potential stress values, so different monitoring standards are needed for monitoring. When all bridge parts are divided into the same area for overall monitoring, there is a probability that the stress value of a certain bridge part has actually exceeded the threshold, while the overall monitoring result still shows that it has not exceeded the threshold. The monitoring accuracy is not high. Therefore, in step 1, the theoretical stress values ​​of the beam body 1, bridge pier 2, abutment 4, ball joint 3 and pile foundation 5 during the construction process are calculated before construction, and are used as the theoretical value array; during the construction process, the actual stress values ​​of the beam body 1, bridge pier 2, abutment 4, ball joint 3 and pile foundation 5 during the construction process are monitored respectively, and are used as monitoring values;

[0039] Meanwhile, in step 2, when dividing the bridge body, the bridge body is divided into: beam body 1, bridge pier 2, cap 4, ball joint 3 and pile foundation 5;

[0040] At this time, the beam 1, the pier 2, the cap 4, the spherical joint 3 and the pile foundation 5 are each regarded as a risk block. In step 3, based on the theoretical value, the corresponding range of the risk color value corresponding to each risk block is determined. Figure 5 As shown, the bridge body consists of several blocks;

[0041] Specifically, different areas of the same bridge part bear or are subjected to different potential stress values. For example, the bridge beam 1 itself is a long strip structure, spanning a wide area, and different sections of the beam 1 are subjected to different stresses. Similarly, if the beam 1 is divided into the same area for overall monitoring, there is a probability that the stress value of a certain part of the beam 1 has actually exceeded the threshold, while the overall monitoring result still shows that it has not exceeded the threshold, and the monitoring accuracy is not high. Therefore, in step 2, after dividing the bridge body, the beam 1 is split into 0#, 1#, ... N# according to the engineering requirements, and the stress values ​​are separately counted in units of segments;

[0042] At this time, the actual monitoring values ​​include the stress values ​​of 0#, 1#, ...N# beam body 1 segment, and the stress values ​​of pier 2, abutment 4, ball joint 3 and pile foundation 5; the theoretical values ​​include the theoretical stress values ​​of 0#, 1#, ...N# beam body 1 segment and the theoretical stress values ​​of pier 2, abutment 4, ball joint 3 and pile foundation 5; 0#, 1#, ...N# beam body 1 segment, pier 2, abutment 4, ball joint 3 and pile foundation 5 are each regarded as a risk block.

[0043] For reasons similar to those of the bridge body and beam body 1, when dividing the bridge construction area, the bridge construction site area is divided into production area, office area, living area, construction area and existing line area;

[0044] Specifically, the contracted work areas include: the project manager area, the laboratory area, and the data room area;

[0045] The living area includes: dormitory area, canteen area, and entertainment room area;

[0046] The existing line area includes: the area where the existing line is located and the area affected by the existing line;

[0047] Specifically, the impact area of ​​each region is 120% of the actual coverage area of ​​the region;

[0048] When the impact ranges of two regions overlap, the higher risk level of the overlapping part shall be taken;

[0049] When in use, when the risk level of a certain area is high, and the risk level of the adjacent area of ​​this area is low, the risk level of the overlapping part between this area and the adjacent area is consistent with that of this area, and both are defined as high risk level;

[0050] When in use, when the risk level of equipment or structures in a certain area is high, in addition to affecting the personnel and equipment in the area, there is a probability of affecting the personnel and equipment in the surrounding space of the area. Therefore, it is necessary to include an area equivalent to 120% of the actual coverage area of ​​this area into the impact range. All impact ranges of equipment or structures in a certain area can be monitored, which improves the monitoring accuracy.

[0051] By setting the impact range of each area to 120% of the actual coverage area of ​​the area, when the risk level of a certain area is high, the entire potential impact range of the equipment structure in this area is included in the impact range. All impact ranges of equipment or structures in a certain area can be monitored, thereby improving monitoring accuracy.

[0052] In some cases, some risk factors cannot be directly detected by sensors and then quantified into specific values ​​such as stress values. In this case, the above scheme cannot measure such risk factors, and a visual risk four-color map is drawn based on the risk block map. Step 5: Perform non-data monitoring. Specifically, non-data monitoring includes: monitoring whether there are risk items in the relevant area. If there are risk items, adjust the risk status of the relevant area to the corresponding level;

[0053] During actual construction, monitor whether there are risk items in the relevant areas. If there are risk items, adjust the risk status of the relevant areas to the corresponding level, including the following sub-steps:

[0054] Step a1: Operators count the possible risk items in the relevant areas and form a knowledge base and database corresponding to the regional risk levels;

[0055] Step a2: Sort out the risk characteristics of the relevant areas, identify risk items through visual monitoring technology, determine the risk status of the relevant areas through the knowledge base and database, and directly assign corresponding colors to each risk block in the risk four-color map;

[0056] Operators can adjust the frequency of identifying risk items according to the operation situation, such as once every ten minutes or once every half an hour, and update the risk items obtained from non-data-based monitoring every ten minutes or half an hour, and adjust the color assigned to each risk block in the risk four-color map;

[0057] By conducting non-data-based monitoring, some risk items that are difficult to quantify can be included in the color adjustment of the risk four-color diagram and then included in the detection scope, thereby increasing the coverage of the monitoring items and thus improving the monitoring accuracy.

[0058] The above process of determining the risk status of the relevant area through the knowledge base and the database, and directly assigning corresponding colors to each risk block in the risk four-color map, specifically, also includes the following sub-steps:

[0059] Step b1: Risk factor identification: In this embodiment, the method for identifying the risk status of the existing line area is to list all factors that may affect the safety of the existing line area of ​​the bridge, including structural integrity, material aging, bearing capacity, maintenance history, natural disaster frequency and surrounding environmental changes;

[0060] Step b2: Data collection: Collect data and information related to the above factors, including historical records, monitoring data, and expert evaluation reports;

[0061] Step b3: Risk quantification: Quantify and score each risk factor using a 1 to 10 scoring system, where 1 represents very low risk and 10 represents very high risk;

[0062] Step b4: Weighted average: Assign a weight to each risk factor in each block to reflect its importance to the overall risk, then calculate the score of the risk factor, and perform a weighted average calculation based on the weight of the risk factor to obtain the risk score of this block;

[0063] Step b5: Obtain the colors in the risk four-color map: low risk (green): 0-2.5; medium-low risk (yellow): 2.6-5.0; medium-high risk (orange): 5.1-7.5; high risk (red): 7.6-10;

[0064] Step b6: Result display: The calculated risk level of each block is expressed by the colors of the four-color diagram, so as to facilitate intuitive understanding and communication to relevant personnel;

[0065] Step b7: Repeat steps b1 to b6 at the end of a cycle based on the frequency of identifying risky items.

[0066] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for monitoring construction of bridges across operating lines based on machine vision recognition algorithm, characterized in that: The following steps are involved: Step 1: Construct a finite element calculation model, calculate the theoretical values ​​of the monitoring indicators of the construction equipment in the current construction phase, and obtain the monitoring values ​​of the monitoring indicators of the construction equipment in the test phase and the completed similar load construction phase; Step 2: Based on the four-color theory of safety risk, divide the bridge construction area and the bridge body, determine the risk blocks corresponding to the bridge construction site and the bridge construction part, and draw a risk block map; Step 3: Based on the theoretical value, determine the corresponding range of the risk color value corresponding to the risk block; Step 4: According to the comparison results between the monitoring values ​​and theoretical values ​​of the monitoring indicators of the construction equipment in the current construction stage, the construction risk status of the construction equipment at the current moment is determined, and different colors are filled in the risk block diagram to show the risk status of different positions in the risk block, forming a four-color map of on-site risks: Among them, the colors of the four-color risk map include: red, orange, yellow, and blue, and the corresponding risk levels are: major risk, relatively large risk, general risk, and low risk respectively; when the monitoring value is lower than 50% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a low risk status, and the risk block is displayed in blue; when the monitoring value is between 50%-80% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a general risk status, and the risk block is displayed in yellow; when the monitoring value is between 80%-120% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a relatively large risk status, and the risk block is displayed in orange; when the monitoring value is higher than 120% of the theoretical value, the construction hazard risk status of the construction equipment at the current moment is a major risk status, and the risk block is displayed in red.

2. According to claim 1, a method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm is characterized by: The step one also includes: calculating the theoretical stress values ​​of the beam body, bridge piers, pedestals, ball joints and pile foundations during the construction process, and using them as theoretical values; monitoring the actual stress values ​​of the beam body, bridge piers, pedestals, ball joints and pile foundations during the construction process, and using them as monitoring values.

3. The method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm according to claim 2 is characterized in that: The step 2 also includes: when dividing the bridge body, the bridge body is divided into: a beam body, a pier, a cap, a ball joint and a pile foundation.

4. The method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm according to claim 3 is characterized by: The step 2 also includes: after dividing the bridge body, according to engineering requirements, splitting the beam body into 0#, 1#, ... N# by segment, and counting the stress values ​​separately in units of segments.

5. The method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm according to claim 1 is characterized in that: The step one also includes: when dividing the bridge construction area, the bridge construction site area is divided into a production area, an office area, a living area, a construction area and an existing line area.

6. The method for monitoring construction of a bridge across an operating line based on a machine vision recognition algorithm according to claim 1, characterized in that: It also includes step five: conducting non-data monitoring to monitor whether there are risk items in the relevant areas. If there are risk items, the risk status of the relevant areas will be adjusted to the corresponding level.

Images