A construction engineering safety hidden danger detection method and system

Abstract

The present application relates to the technical field of risk assessment in automated safety detection, and discloses a construction engineering safety hidden danger detection method and system, comprising the following steps: according to the sensor sensing data definition, selectively determining a set of unexamined key check points which cannot be reached by defining a detection blind area or point-by-point path planning; then, accumulating the basic risk weight thereof, combining the surrounding high-risk operation type and risk exposure time, dynamically generating a quantitative total risk score, and generating a visual risk report and pushing it to a management terminal, wherein the present application couples the simple state description of physical obstruction with the importance of the structural key points and the dynamic influence of external high-risk operation, so as to convert an invisible detection blind area into a quantifiable decision basis which can reflect the risk accumulation process over time, and realizes the leap from physical perception to risk semantics.

Description

TECHNICAL FIELD

[0001] The present application relates to a construction safety hazard detection method and system, belonging to the risk assessment technology field in automatic safety detection. BACKGROUND

[0002] In dynamic and complex environments such as construction projects, in order to improve the coverage and timeliness of safety supervision, automatic inspection equipment equipped with environmental perception sensors such as laser radars is generally used. Through autonomous path planning and obstacle avoidance functions, it periodically checks the preset key points. This method has become a common technical path to improve the intelligent level of site management.

[0003] However, when such automatic equipment is deployed from a relatively stable industrial environment to a construction site full of temporary and uncertain obstacles, a contradiction arises between the high fidelity of the equipment's environmental perception and the value decay of its information output at the decision application level. In the construction site, temporary power cables, randomly stacked construction materials, and fixed formwork support rods are intertwined and coexist. The automatic inspection equipment identifies and avoids all these obstacles, resulting in a large number of path blocked alarm events. Most of these events are caused by temporary harmless operations, and their frequent occurrence causes the attention of safety management personnel to be continuously diluted. The core value of the alarm information, i.e. the signal function of early warning potential dangers, is severely weakened due to the continuous reduction of signal-to-noise ratio. In order to maintain work efficiency, management personnel will gradually filter or ignore such alarms as a kind of normalized operational background noise, which is an implicit cost universally accepted by the industry in exchange for automation coverage. To solve this problem, the most direct approach is to optimize the alarm filtering algorithm, such as setting a time threshold or simple regional shielding. However, this approach does not address the root cause of the problem, as it cannot effectively distinguish between a temporary harmless temporary obstruction and a long-term detection blind spot that may hide high-risk hazards formed by temporary and permanent obstacles in the initial stage. False filtering may lead to silence on the evolution of key risks, allowing risks to continue to accumulate in an invisible state.

[0004] Specifically, the prior art has inherent limitations in the information processing chain: 1. The path blocked information output by the system is essentially a binary physical state description, which does not carry any semantic information about the consequences, and cannot reveal the potential risk level corresponding to this inspection interruption; 2. When the alarm is generated, it is unknown whether there is a real hidden danger in the blind area, and its risk value depends entirely on the importance of the unexplored key points in the overall structure, and this core information is completely missing in the existing alarm; 3. Due to the lack of risk quantification basis in the alarm information, managers cannot effectively judge the risk level and prioritize intervention based on the data provided by the system, and their decision-making behavior is forced to decouple from the information provided by the automation system, and reverts to the traditional mode of relying on personal experience or confirming through inefficient remote communication. Therefore, how to establish a new technical way to enable the output information of the automated inspection equipment to go beyond simple physical state reports when it encounters physical obstacles, to give it accurate risk semantics, to convert an invisible detection blind area into a risk level assessment result that can be directly used for decision-making, has become a technical problem to be solved by the present application. SUMMARY

[0005] The present application provides a construction safety hazard detection method and system, which mainly aims to solve the problem that the prior art cannot quantitatively evaluate the potential risk of the blind area when the automated inspection forms a detection blind area due to physical obstacles, making it difficult for management personnel to make effective decisions, and thus possibly ignoring high-risk hazards.

[0006] To achieve the above-mentioned purpose, the present application provides a construction safety hazard detection method, which comprises:

[0007] A step for determining a set of unexamined key inspection points that cannot be reached is performed, which includes selecting one of the following two execution paths according to the clarity of the sensor perception data of the inspection equipment:

[0008] Path one, under the condition that the sensor perception data is clear, the sensor is used to scan the environment around the physical obstacle to generate environment data, the geometric range of the detection blind area is calculated and determined in combination with the positioning information of the inspection equipment, and the key inspection points located within the geometric range of the detection blind area in the spatial coordinates are determined as the set of unexamined key inspection points;

[0009] Path two, in the condition that the sensor perceives that the data is blurred due to environmental interference, a list of all key checkpoints in the current task range is obtained, and for each key checkpoint in the list, a safe access path from the current position of the inspection device to the key checkpoint is independently tried to be planned, and all key checkpoints that cannot plan a safe access path are determined as a set of unexamined key checkpoints; based on the determined set of unexamined key checkpoints, and according to the basic risk weight of each unexamined key checkpoint obtained by querying the risk value table, a basic total risk score is accumulated; the construction operation information around the spatial position of the detection blind area is obtained, the risk exposure time length of the detection blind area exposed to the influence of high-risk operation is tracked and accumulated; according to the basic total risk score, and in combination with the type of high-risk operation and the corresponding accumulated risk exposure time length, a total risk score is generated; a visual risk report containing the total risk score is generated, and the visual risk report is pushed to the terminal of the manager.

[0010] Preferably, according to the basic total risk score, and in combination with the type of high-risk operation and the corresponding accumulated risk exposure time length, the step of generating a total risk score is specifically: for each high-risk operation that affects the detection blind area, according to the risk impact factor corresponding to the operation type and the corresponding accumulated risk exposure time length, a risk accumulation increment is calculated; all calculated risk accumulation increments and the basic total risk score are accumulated to obtain an updated total risk score.

[0011] Preferably, the calculation of the risk accumulation increment is based on a risk accumulation function; the risk accumulation function takes the accumulated risk exposure time length as an input variable and outputs a cumulative effect value representing the nonlinear growth of risk with time; the cumulative effect value is multiplied by the risk impact factor to obtain the risk accumulation increment.

[0012] Preferably, when the detection blind area is simultaneously in the influence area determined by multiple high-risk operations, the step of accumulating all calculated risk accumulation increments and the basic total risk score before the step is further comprising: querying the operation type combination rule library to analyze whether there is an interaction relationship between multiple high-risk operation types; if there is an interaction relationship, then according to the interaction relationship, each risk accumulation increment is adjusted before accumulation.

[0013] Preferably, if there is no interaction relationship in the operation type combination rule library, the method further comprises: at the edge position of the detection blind area, using the sensor carried by the inspection device to monitor the change of at least one physical parameter; synchronously obtaining the running characteristics of multiple high-risk operations; by analyzing the time correlation between the monitored physical parameter change and the external operation running characteristics, the actual interaction relationship between multiple high-risk operation types is identified and quantified, and is used to update the operation type combination rule library.

[0014] Preferably, the monitored physical parameters include the amplitude and frequency of the micro-vibration signals, and the operation characteristics include the start-stop time and operation power of the vibration-type operation equipment; the step of analyzing the time correlation between the changes in the monitored physical parameters and the external operation characteristics includes: performing time-frequency analysis on the micro-vibration signals to extract energy components associated with each high-risk operation frequency; when multiple high-risk operations are running simultaneously, determining whether there is a nonlinear superposition phenomenon between the energy components associated with them; if there is a nonlinear superposition phenomenon, determining that the interaction relationship is synergistic enhancement according to the degree of nonlinear superposition, and quantifying the enhancement coefficient.

[0015] Preferably, in path one, the sensor is a laser radar, the environmental data is three-dimensional point cloud data, the positioning information is obtained through an inertial measurement unit and a real-time positioning and map building technology; the high-risk operation includes heavy equipment vibration operation, deep foundation pit excavation operation, and large-volume concrete pouring operation; the influence area of the high-risk operation is a circular area with the center of the high-risk operation as the center and an influence radius determined according to industry safety standards as the radius.

[0016] Preferably, the step of generating a visual risk report includes: highlighting the area corresponding to the set of un-inspected key inspection points on the two-dimensional site plan using a specified color; inside the highlighted area, using a graphical identifier corresponding to the risk level to mark the location of each un-inspected key inspection point; at a specified location on the two-dimensional plan, displaying the total risk score generated in numerical form, and displaying the main high-risk operation type that contributes to the total risk score and the corresponding cumulative risk exposure duration.

[0017] Preferably, in path two, the step of attempting to plan a safe passage path is to perform A-star pathfinding algorithm or rapid extended random tree algorithm operation in a temporary local environment map constructed according to the fuzzy perception data.

[0018] A construction engineering safety hazard detection system, the system comprises:

[0019] a checkpoint determination module, which determines a set of unvisited key checkpoints according to a sensor data clarity of the inspection device, and selects one of the following two modes to operate: in a first operating mode, the checkpoint determination module is configured to: scan a surrounding environment of a physical obstacle by using the sensor to generate environment data, calculate and determine a geometric range of a detection blind area in combination with positioning information of the inspection device, and determine key checkpoints located within the geometric range of the detection blind area in spatial coordinates as the set of unvisited key checkpoints; in a second operating mode, the checkpoint determination module is configured to: obtain a list of all key checkpoints within a current task range, and for each key checkpoint in the list, independently attempt to plan a safe passage path from a current position of the inspection device to the key checkpoint, and determine all key checkpoints for which safe passage paths cannot be planned as the set of unvisited key checkpoints;

[0020] a risk assessment module, which is configured to: based on the set of unvisited key checkpoints determined by the checkpoint determination module, and according to a basic risk weight of each unvisited key checkpoint obtained by querying a risk value table, accumulate a basic total risk score; obtain construction operation information around a spatial position of the detection blind area, track and accumulate a risk exposure time length during which the detection blind area is exposed to influence of a high-risk operation, and generate a total risk score according to the basic total risk score, in combination with a type of the high-risk operation and the accumulated risk exposure time length;

[0021] a report generation and pushing module, which is configured to generate a visual risk report containing the total risk score generated by the risk assessment module, and push the visual risk report to a terminal of a manager.

[0022] Compared with the prior art, the method has the following beneficial effects:

[0023] 1. When the automated inspection device senses that physical passage is blocked in the field environment, instead of interrupting the task or only reporting the path state, the method performs real-time spatial correlation between physical space information of the dynamically generated blocked area and structure key point information in a preset building information model, and then converts each unvisited key point falling into the area into a quantitative risk weight value according to its importance in the engineering structure and performs accumulation; thus, the information output by the system is changed from a simple state description of physical accessibility to structured data directly revealing a potential safety risk level, so that when the manager faces an inspection interruption event, the focus can be naturally shifted from whether the path is smooth to how much risk is brought by information deficiency, and the experiential neglect of high-risk blind areas due to information overload is avoided.

[0024] 2、In the presence of dust or water vapor and other dispersed media that interfere with optical sensors on the construction site, the method avoids the difficult problem of accurately reconstructing the geometric boundary of the blurred environment information. It changes the logical basis of risk assessment from the overall definition of a continuous and possibly distorted blind area range to the one-by-one accessibility path planning attempt of a series of discrete and position-determined key inspection points. This way, the accumulation of risk values is based on the certainty of whether each independent target point is accessible. Even in the case of overall quality decline of the perception data, the system can still form a reliable risk assessment result that is not affected by the accuracy of the blind area boundary description, maintaining the stability of the basis for safety decision-making.

[0025] 3、The method further considers that the risk of key points in the detection blind area is not constant, but may be dynamically accumulated due to indirect influence of ongoing construction work outside the blind area. It correlates the blind area spatial information generated by the inspection equipment with the time and space information of surrounding high-risk operations obtained from the construction site management platform, and introduces tracking of risk exposure time, so that the risk score calculation is no longer a simple summation of the static weights of un-inspected key points, but a dynamic value reflecting the process of potential damage accumulation over time caused by external stress. This allows risk assessment to evolve from a snapshot judgment of the current spatial shielding state to a process insight into the development of potential hazards in the time dimension, providing objective data support for managers to intervene in areas that may appear harmless temporarily but have increasing long-term risks. BRIEF DESCRIPTION OF DRAWINGS

[0026] Fig. 1 A flowchart of a construction engineering safety hazard detection method of the present application;

[0027] Fig. 2 A comparison test result graph for verifying the effectiveness of the dynamic risk score calculation method of the present application;

[0028] Fig. 3 A structural diagram of a construction engineering safety hazard detection system of the present application. DETAILED DESCRIPTION

[0029] To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0030] The building engineering safety hidden danger detection method and system provided by the embodiment of the application is configured as a risk perception and decision support process, which starts from data collection on the physical environment by sensors carried by the inspection equipment, then identifies the detection coverage missing caused by physical obstruction through a double-path adaptive checkpoint accessibility analysis stage, and then generates a time-evolving risk score in a risk quantification model that combines the structural static importance and external operation dynamic influence, and finally converts the quantification result into a visual report to assist managers in making intervention decisions.

[0031] In a dynamic changing environment such as a construction site, the performance of the environmental perception sensors of the automated inspection equipment may be affected by temporary obstacles and diffusing media such as dust or water vapor, which may in turn cause deviations in the evaluation of the inspection task coverage completeness; to address this challenge, the present solution is configured with an un-inspected key checkpoint set determination step that selects a path based on the clarity of sensor perception data; when the sensor, for example a solid-state laser radar, returns point cloud data with a signal-to-noise ratio higher than a preset threshold , for example, the signal-to-noise ratio is greater than , that is, the condition that the sensor perception data is clear, the system executes path one, which uses the laser radar in combination with the inertial measurement unit and the real-time positioning and mapping technology to scan the environment around the physical obstacle to generate three-dimensional point cloud data with spatial coordinates, and combines the positioning information of the inspection equipment in the global map to outline the geometric range of the detection blind area formed by the obstruction by using the convex hull algorithm or the Alpha-shapes algorithm, which is defined as a polygonal region in a three-dimensional space, then the system identifies and includes all key checkpoints in the preloaded building information model that have an intersection with the polygonal region in the spatial coordinates into a set, which is determined as the un-inspected key checkpoint set; and in the condition that the sensor perception data is blurred due to high concentration of dust scattering, that is, the signal-to-noise ratio of the point cloud data is lower than the threshold , then path two is switched to execute, at this time, the system does not attempt to reconstruct the geometric boundary of the blurred perception data, but obtains the list of all key checkpoints within the current task range from the building information model database, and for each key checkpoint in the list, independently attempts to plan a safe passage path from the current position of the inspection equipment to the key checkpoint, this path planning is performed in a temporary local environment map constructed based on the blurred perception data, and the A-star pathfinding algorithm or the rapid extended random tree algorithm is operated, wherein if a path that does not pass through any key checkpoint with a density higher than the threshold If a path collides with a point cloud cluster, it is determined that the path cannot be planned. All critical checkpoints for which a safe passage path cannot be planned are ultimately identified as the set of unchecked critical checkpoints. This dual-path adaptive approach enables the system to transform from defining a continuous geometric range to making a deterministic judgment on the reachability of a series of discrete target points based on data quality, providing a definite input for subsequent risk quantification.

[0032] Simply identifying unchecked critical checkpoints is insufficient to provide a basis for risk level ranking, as the potential failure consequences of checkpoints at different structural locations vary. Therefore, this invention introduces a procedure for quantifying basic risk based on a risk value table. This risk value table is a pre-defined table that associates building component types defined in the Building Information Model with a dimensionless basic risk weight. The data structure used for mapping, for example, the load-bearing column base components are defined. The value is 10, while in ordinary floor slab areas... The value is 3; once the system determines the set of unchecked critical checkpoints, it queries this value table and assigns the basic risk weights corresponding to each unchecked critical checkpoint in the set. The scores are accumulated to obtain the basic total risk score. Its calculation can be expressed as ,in, This represents the total number of unchecked critical checkpoints in the set; for example, if a blind spot contains a load-bearing column base with a weight of 10 and two ordinary floor slab areas with a weight of 3, then its total foundation risk score is... identified as Through this step, the information output by the system changes from a binary state description of physical accessibility to quantitative data that reveals the level of potential security risks.

[0033] The risks at construction sites are not static. Potential risks within detection blind spots accumulate dynamically due to ongoing high-risk operations that can transmit physical stress. To incorporate this cumulative effect into the risk assessment model, this invention includes a dynamic risk increment calculation module. This module first acquires construction operation information surrounding the spatial location of the detection blind spot. For example, it obtains the type, location, and start / stop times of operations such as heavy equipment vibration operations or deep foundation pit excavation through the application programming interface of the construction site management platform. Based on industry safety standards, it determines an influence radius for each type of operation and then determines whether the detection blind spot is located within this influence area. If so, the system starts a timer to track and accumulate the risk exposure time of the detection blind spot to this high-risk operation. And based on the accumulated duration Generate a total risk score based on the type of task. ;Specific generation steps are: for each high-risk operation that affects the detection blind area , according to the risk influence factor corresponding to the operation type and the corresponding cumulative risk exposure time , calculate a risk accumulation increment , the calculation is based on a risk accumulation function , which takes the cumulative risk exposure time as an input variable and outputs a cumulative effect value representing the nonlinear growth of risk over time, for example, the function can be set as a logarithmic function , where, is a time scale parameter (e.g. 60 minutes) to adjust the rate of risk growth, accordingly, the risk accumulation increment is calculated by , finally, all calculated risk accumulation increments are added to the basic total risk score to obtain the updated total risk score , this design makes the risk assessment reflect the development process of potential hazards in the time dimension.

[0034] In the working condition where the detection blind area is simultaneously in the influence area of multiple high-risk operations, the interaction relationship between these operations may not be linear superposition; to solve this problem, before adding all the calculated risk accumulation increments, the system first queries a operation type combination rule library to analyze whether there is a predefined interaction relationship between multiple high-risk operation types; if there is a corresponding rule in the rule library, for example, the rule defines that there is a synergistic effect when vibration operation and large volume concrete pouring operation occur at the same time, then adjust each risk accumulation increment according to the rule, for example, increase the multiplying by an enhancement coefficient greater than 1 and then accumulating; in the absence of a corresponding action relationship in the rule base, the system is also configured to update the rules by active sensing, which detects the edge position of the blind area, uses the sensors carried by the inspection equipment, such as high-precision micro-electromechanical system accelerometers, to monitor the changes of physical parameters such as the amplitude and frequency of micro-vibration signals, and synchronously acquires the running characteristics of multiple high-risk operations, such as the start-stop time and running power of vibration-type operation equipment; by performing time-frequency analysis on the micro-vibration signals, such as short-time Fourier transform, the energy components associated with the running frequencies of each high-risk operation are extracted, and when multiple high-risk operations are running simultaneously, the system determines whether there is a nonlinear superposition phenomenon between the energy components associated with them, and if the total energy after superposition is greater than the sum of the component energies, then according to the degree of nonlinear superposition, the interaction relationship is determined to be synergistic enhancement, and the enhancement coefficient is quantified to update the operation type combination rule base; finally, in order to effectively deliver the quantified risk results generated in the foregoing steps to the management personnel, the system performs a generation and pushing step of a visual risk report, which uses a specified color to highlight the area corresponding to the set of un-inspected key checkpoints on the two-dimensional plan of the construction site, and inside the highlighted area, the location of each un-inspected key checkpoint is marked using a graphical identifier corresponding to the risk level; at the same time, the total risk score generated is displayed in numerical form at a specified position on the two-dimensional plan , along with the main high-risk operation types that contribute to the total risk score and the corresponding cumulative risk exposure time . After the visual risk report is encapsulated into a standard data format, it is pushed to the designated management personnel terminal through a wireless communication network, thereby providing an objective data basis for the management to prioritize interventions.

[0035] Embodiment 1: The technical solution disclosed in the embodiment of the application has the following specific operation mode in a specific industrial application scenario; in a large bridge construction project, an automatic inspection equipment is responsible for periodic inspection of the structural integrity of the bridge pier main structure during concrete curing, wherein the P-01 bearing column root at the bottom of No. 3 bridge pier is marked as a first-level key checkpoint by the building information model, and the corresponding basic risk weight is set to 10; in a routine inspection task, due to temporary cable laying by the on-site construction team, the cable and the fixed steel scaffolding jointly form a physical shielding area at the bottom of No. 3 bridge pier, preventing the inspection equipment from reaching the P-01 checkpoint; after the path planning fails, the inspection equipment immediately enables the detection blind area geometric range definition program based on laser radar point cloud data, determines a set of un-inspected key checkpoints including the P-01 checkpoint, and calculates the basic total risk score of the blind area according to the risk value table 10; thereafter, the risk assessment of this blind zone does not stop, but enters the external operation influence correlation analysis stage, the system identifies through the data interface query of the construction site management platform that in the river close to the No. 3 pier, a large hydraulic vibration hammer is carrying out steel sheet pile sinking operation, this operation is predefined as high-risk operation type, and its risk influence factor Is set to 5, and its influence radius is calculated to cover the area where the No. 3 pier is located.

[0036] At this time, the risk assessment result based on the static spatial shielding state becomes the direct input of the external dynamic stress source time cumulative risk assessment; the unexamined key checkpoint P-01 determined by the former provides a clear action object for the risk accumulation calculation of the latter, and the latter gives the risk assessment result of the former a time evolution dimension; the system starts the risk exposure timer for the detection blind zone containing the P-01 point, and begins to accumulate the time length of its exposure to the vibration operation influence ; as the sinking operation continues, when Reaches 120 minutes, the system calculates the risk accumulation increment According to the risk accumulation function , wherein the time scale parameter Is set to 60 minutes; further, the system adds this increment to the basic total risk score to obtain the updated total risk score .

[0037] The system immediately generates a visual risk report and pushes it to the management personnel terminal, which not only highlights the detection blind zone at the bottom of the No. 3 pier and labels the position of the P-01 unexamined key checkpoint, but also displays the dynamic changed total risk score of 15.49 in numerical form, and clearly attaches a note that the risk increase is due to the external vibration operation that has lasted for two hours; the information provided by this report changes the basis for the decision of the management personnel from a temporarily blocked known point to a key load-bearing structure under the action of continuous vibration stress, which is not monitored, so as to prompt them to immediately assign a structural engineer to carry out manual intervention inspection, instead of delaying the processing as a regular event; this way does not directly solve the physical obstruction, but through the correlation and quantification of an invisible detection blind zone and an external dynamic risk source at the data level, changes the definition of the risk nature of this blind zone, so that it changes from a low-priority accessibility problem to a high-priority structure safety hazard; the information received by the management terminal is no longer a binary state report about whether the physical path of the equipment is smooth, but a quantitative decision basis reflecting the time accumulation process of the potential damage of the structure under the action of external stress.

[0038] Example 2: To objectively verify the effectiveness of the dynamic risk score calculation method in the technical solution of the present application, the following comparative test is designed and performed; the purpose of the test is to quantitatively verify the performance difference of the method of the present application in distinguishing the potential high-risk detection blind area caused by external dynamic stress from the conventional static detection blind area compared with the method only having static risk assessment capability; the test is carried out on a 10-meter-by-10-meter indoor test platform, which is pre-provided with a standardized template support rod matrix on the ground, and is configured with a programmable industrial vibrator to simulate the persistent low-frequency vibration generated by heavy equipment vibration operation, and the vibration frequency and amplitude parameters are set to match the ground vibration characteristics generated by a 30-kilowatt vibrating ram at a distance of 5 meters; two independent test samples are set, one is a control group that can only calculate the basic total risk score, and the other is a test group that realizes the complete technical solution of the present application; two test scenarios are set, scenario A is a static shielding scenario, in which only a detection blind area is formed by combining temporary cables and support rods; scenario B is a dynamic stress composite scenario, in which the industrial vibrator is started beside the blind area to apply persistent external vibration stress; the detection blind areas formed in the two scenarios are completely consistent in geometric range and internal contained un-inspected key checkpoints, both containing a main beam welding point with a basic risk weight of 8 and a common floor area with a weight of 3, so that the basic total risk score of both is 11; the total test duration is set to 240 minutes, and the risk score outputs of the test group and the control group are recorded synchronously, with a recording period of 30 minutes, which is the result of technical trade-off between ensuring the ability to capture the nonlinear growth trend of the risk accumulation function and taking into account the data recording system processing load.

[0039] After the test starts, in scenario A, the total risk scores reported by the control group and the test group are stably maintained at the basic total risk score of 11 throughout the 240-minute test period; in scenario B, the outputs of the two samples show significant differences, the total risk score reported by the control group is also stably maintained at 11, and fails to reflect the application of external vibration stress; in contrast, the total risk score reported by the test group exhibits clear time-dependent growth, starting from the initial value of 11 after the vibrator is started, rising to 15.49 at 120 minutes of the test, and finally reaching 19.05 at 240 minutes of the end of the test; the test data show that the control group cannot distinguish between the two blind areas with different potential risk levels due to the lack of the ability to associate the time and space information outside the blind area when working and the quantitative model of risk accumulation over time; while the test group couples the spatial shielding information of the blind area with the time accumulation effect of the external vibration source at the data level through the configured dynamic risk increment calculation module, and the change trend of the total risk score of the output is consistent with the potential risk accumulation process caused by the continuous bearing of external stress by the internal structure of the blind area in scenario B; the test result confirms that the technical solution of the present application can identify and quantify the risk increment caused by external dynamic factors, thereby providing an objective data basis for solving the problem of experiential neglect of high-risk blind areas due to information loss.

[0040] Embodiment 3: This embodiment combines Figs. 1 to 3 a building engineering safety hazard detection method and system, as shown in Fig. 1 , the process starts with the inspection equipment starting the environment scanning, the sensor system feeds back the detection data clarity to the inspection equipment, if the signal-to-noise ratio is lower than the threshold value of, for example, 15 dB, the fuzzy perception data is returned, the inspection equipment immediately requests and obtains the complete list of key checkpoints from the BIM database, and requests the path planning module for path planning for each checkpoint in the list, after the path planning module executes the algorithm, if the path planning is successful, the passable path is returned, if the path planning fails, the point is marked as an un-inspected point, after the cyclic iteration of all the checkpoints, the inspection equipment delivers the finally determined set of un-inspected key checkpoints to the risk assessment module, the module calculates the basic total risk score and generates the final risk assessment result in combination with the influence of external work, and finally pushes the result to the management terminal.

[0041] As shown in Fig. 2 , the graph takes time (minutes) as the horizontal coordinate and the total risk score as the vertical coordinate, and compares the output results of the method of the present application (test group) and the traditional static method (control group), wherein the dotted line (control group) representing the traditional static method has a constant total risk score of 11 during the entire 240-minute test period; while the solid line (test group) representing the method of the present application starts from the same initial value of 11 as the control group, and presents a non-linear growth over time, reaching 15.49 at 120 minutes, and growing to 19.05 at the end of the 240-minute test, which directly confirms that the method of the present application can effectively quantify the potential risk increment caused by external dynamic stress and accumulated over time.

[0042] AsFig. 3 As shown in the diagram, the core of the detection system is at its center. This core receives sensor data from inspection equipment equipped with sensors such as LiDAR and inertial measurement units, as well as operation information from the site management platform, including high-risk operation types, locations, and start / stop times. The core system includes a checkpoint determination module, which adaptively selects the operating mode based on the clarity of the sensor data to identify the set of uninspected critical checkpoints; a risk assessment module, which integrates the static importance of the structure with the dynamic impact of external operations to calculate and generate a total risk score; and a report generation and push module, which transforms the quantified risk score into intuitive decision-making information and pushes it to designated terminals. During operation, the core system calls upon three external databases: the Building Information Model (BIM), the Risk Value Table (VFA), and the Operation Type Combination Rule Base, ultimately generating a visualized risk report and transmitting it to the management personnel's terminal.

[0043] Example 4: In the context of an upcoming automated safety inspection of a large subway transfer hub project, a systematic on-site calibration procedure is required to establish the mapping relationship between the risk assessment model in this invention and the specific engineering environment. This project employs a large-span arch structure and plans to introduce a new type of high-frequency hydraulic rock drilling rig. Therefore, general risk weights and influencing factor parameters cannot be directly applied; the risk value table and risk parameters related to the operation of the new rock drilling rig must be initialized and calibrated. The calibration process begins with the basic total risk score. The core basis for this approach is the construction of the Risk Value Table. The building information model of the key project is imported into structural analysis software. For each type of critical structural component within the model, finite element stress analysis is performed targeting the main load-bearing path. By simulating the stress distribution of the component and its contribution to the overall structural stability under 150% overload conditions of the standard design load, a quantitative structural importance coefficient is obtained. Subsequently, this coefficient is weighted and averaged with the protection level requirements for this type of component in the local building safety code. Finally, the result is normalized to a range of 1-10, serving as the basic risk weight for this component type. According to this regulation, the keystone of the large-span arch unique to this project... It was determined to be 10, while a non-load-bearing precast partition wall panel... It is then determined to be 2, thus making the risk value statement reflect the structural mechanical characteristics of this particular project.

[0044] Furthermore, for the specific high-risk operation type of the new high-frequency hydraulic rock drilling rig, its risk impact factors are analyzed. With time scale parameters Physical measurement calibration is performed; in the predetermined initial operation area of the trolley, three-axis high-precision micro-electromechanical system accelerometers are arranged at positions of 5 meters, 10 meters and 20 meters in the radial direction; the jumbo is started and continuously operated at a standard power for 10 minutes, and the vibration signals of each measurement point are recorded synchronously; by analyzing the root mean square amplitude of the signals at the measurement points and comparing the vibration limit value allowed for the concrete structure in the vibration safety standard of the industry, the risk influence factor of the operation is calibrated In this calibration, the measured vibration energy at 5 meters is 1.5 times the standard limit value, and the risk influence factor of the operation is 6.0; at the same time, the vibration signal is subjected to frequency spectrum analysis to obtain the main vibration frequency, and the time scale parameter in the risk accumulation function is determined according to the fatigue life curve of the concrete under the corresponding frequency sinusoidal load in material mechanics The parameter is determined as one-twentieth of the cumulative cycle period corresponding to the initial damage point on the fatigue life curve to provide an engineering safety margin, and in this scenario, the value is determined as 45 minutes; finally, after the calibration of the risk value table and the key operation parameters is completed, the entire risk assessment model is completed for the localization configuration of the subway hub project; the setting of all key parameters in the model is anchored on the basis of the structure analysis based on the engineering design file and the measured data based on the physical environment on site; thus, the total risk score generated by the system in the future, the value of each component of which is derived from the output of the aforementioned structure analysis or physical measurement steps, provides a decision basis consistent with the site conditions for the detection of safety hazards in this specific scenario.

[0045] Example 5: In the environment of urban deep tunnel shield construction, the wireless network communication is unstable due to the complex electromagnetic shielding effect, and the high humidity and alkaline mist generated by the concrete spraying operation form a composite interference to the optical sensor; when the automatic inspection equipment operates in this working condition, the data interface with the construction site management platform will be periodically interrupted, resulting in the inability to obtain the space-time information of the surrounding high-risk operation through the application program interface; to deal with this situation, the method of the present application is configured to enable a backup procedure for operation type inference and risk assessment based on local multi-modal sensing information.

[0046] Under this procedure, when the inspection device forms a detection blind area due to path obstruction, and its interface call to the construction site management platform fails to return a successful state within the preset timeout threshold, the system activates the standby local sensor array, which includes high-sensitivity acoustic sensors and temperature and humidity sensors; the system performs fast Fourier transform on the real-time collected audio stream, and matches its spectral features with the preloaded high-risk operation acoustic feature model library locally; when the acoustic features matching the concrete spraying operation are identified, the system associates the operation type with the current detection blind area; then, the system calls an exponential function corresponding to the chemical solidification type of operation from a risk accumulation function library based on the chemical reaction kinetics model calibration , to calculate its risk accumulation increment; the construction of this function library is in an offline state, by performing physical and chemical experiments on the solidification process of different construction materials, fitting the empirical curve of the change of key performance indicators with time, and preloading the mathematical expression of the curve in the library; through this standby procedure, the risk assessment process can continue to operate based on local environmental perception data under communication interruption conditions, and apply the cumulative model matching the operation type.

[0047] In another subsequent application scenario, a certain detection blind area in the same area of the tunnel identifies the ongoing concrete spraying operation through the local acoustic sensor during the risk assessment period after its formation, and almost simultaneously monitors the new high-frequency hydraulic rock drilling jumbo operation signal through the high-precision micro-electro-mechanical system accelerometer; the system immediately queries the operation type combination rule library, and because the interaction rule of the two operations is not preloaded in the library, the risk accumulation increments calculated by the two operations are initially linearly superimposed; at the same time, the online learning module for updating the operation type combination rule library identifies the energy component associated with the rock drilling jumbo operation frequency after time-frequency analysis of the micro-vibration signals collected in this period, and its amplitude shows a nonlinear superposition phenomenon of 15% exceeding the independent running state in the background of the continuous high humidity and acoustic white noise generated by the spraying operation; the system quantifies the synergistic enhancement coefficient as 1.15, and generates a rule update log to be audited, which, in addition to pushing the visual risk report containing the current total risk score, is submitted to the management personnel terminal for human confirmation, and then the newly discovered interaction relationship is solidified into the rule library.

[0048] Embodiment 6: In order to adapt the technical solution of the present application to the physical characteristics of a specific building environment, a set of pre-deployment system self-checking and sensing parameter calibration procedures need to be performed before the formal deployment in a large hospital building with internal high-reflectivity glass curtain walls and various materials such as diffusely reflective concrete walls; the procedures are used to verify the positioning accuracy of the inspection equipment, and to set the operating parameters of the equipment sensors that are suitable for the optical and geometric characteristics of the on-site environment; the procedure first starts a positioning system accuracy verification step, and the inspection equipment is instructed to run autonomously along a reference route that includes a closed-loop path, which is pre-calibrated by a high-precision static three-dimensional scanner and covers a variety of typical ground and wall materials; after the run is completed, the system compares the terminal pose calculated by the real-time positioning and mapping technology of the inspection equipment with the true pose of the point in the pre-calibrated reference map, and calculates the absolute positioning error; only when the error is less than the pre-set task execution threshold of 5 cm, the equipment is authorized to perform the subsequent inspection task, if it exceeds this threshold, the task is aborted and a prompt is given to recalibrate the positioning sensors such as the inertial measurement unit.

[0049] After the positioning accuracy verification is passed, the system performs adaptive adjustment of the sensing parameters on the same reference route; the device continuously records the signal-to-noise ratio of the point cloud data returned by the laser radar in different material areas during the journey, the system selects the two data segments with the highest and lowest signal-to-noise ratios, and sets the median of the average signal-to-noise ratio values of the two segments as the threshold for distinguishing between clear and blurred sensor sensing data in this task ; at the same time, the system analyzes the lowest effective point cloud density of the point cloud cluster identified as a solid obstacle in the low signal-to-noise ratio area, and sets 70% of this density as the non-passing threshold for judging the existence of obstacles in the path planning algorithm ; through this procedure, the inspection system completes the performance verification of its positioning and sensing subsystems before formally starting the safety inspection, and loads the key operating parameters corresponding to the physical characteristics of the current operating environment for subsequent inspection tasks.

[0050] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application.

Claims

1. A construction work safety hazard detection method characterized by, The method comprises: A step for determining a set of un-inspected key inspection points that cannot be reached, which comprises selecting one of the following two execution paths according to the clarity of sensor perception data of the inspection device: Path one: under the condition that the sensor perception data is clear, scanning the environment around the physical obstacle by the sensor to generate environment data, combining the positioning information of the inspection device to calculate and determine the geometric range of the detection blind area, and determining the key inspection points located within the geometric range of the detection blind area in the spatial coordinates as the set of un-inspected key inspection points; Path two: under the condition that the sensor perception data is blurred due to environmental interference, obtaining a list of all key inspection points within the current task range, and for each key inspection point in the list, independently attempting to plan a safe passage path from the current position of the inspection device to the key inspection point, and determining all key inspection points for which a safe passage path cannot be planned as the set of un-inspected key inspection points; based on the determined set of un-inspected key inspection points, and according to the basic risk weight of each un-inspected key inspection point obtained by querying the risk value table, the basic total risk score is obtained by accumulation; obtaining construction operation information around the spatial position of the detection blind area, tracking and accumulating the risk exposure time length of the detection blind area exposed to the influence of high-risk operations; generating a total risk score according to the basic total risk score, combined with the type of high-risk operation and the corresponding accumulated risk exposure time length; generating a visual risk report containing the total risk score, and pushing the visual risk report to the terminal of the management personnel.

2. The construction safety hazard detection method of claim 1, wherein, The step of generating a total risk score according to the basic total risk score, combined with the type of high-risk operation and the corresponding accumulated risk exposure time length, is specifically: for each high-risk operation that affects the detection blind area, according to the risk impact factor corresponding to its operation type and the corresponding accumulated risk exposure time length, calculating the risk accumulation increment; All calculated risk accumulation increments are added to the basic total risk score to obtain an updated total risk score.

3. The construction safety hazard detection method of claim 2, wherein, The calculation of the risk accumulation increment is based on a risk accumulation function; the risk accumulation function takes the accumulated risk exposure time length as an input variable and outputs a cumulative effect value representing the nonlinear growth of risk over time; The cumulative effect value is multiplied by the risk impact factor to obtain the risk accumulation increment.

4. The construction safety hazard detection method of claim 2, wherein, When the detection blind area is determined to be in the influence area of multiple high-risk operations at the same time, before the step of adding all calculated risk accumulation increments to the basic total risk score, there is also a step of: querying the operation type combination rule library to analyze whether there is an interaction relationship between multiple high-risk operation types; if there is an interaction relationship, then according to the interaction relationship, adjust each risk accumulation increment before accumulation.

5. The construction safety hazard detection method of claim 4, wherein, If the interaction relationship does not exist in the job type combination rule library, the method further comprises: at the edge position of the detection blind area, monitoring the change of at least one physical parameter by using the sensor carried by the inspection equipment; synchronously acquiring the running characteristics of multiple high-risk operations; by analyzing the time correlation between the monitored physical parameter change and the external operation running characteristics, identifying and quantifying the actual interaction relationship between multiple high-risk operation types.

6. The construction safety hazard detection method of claim 5, wherein, The monitored physical parameters include the amplitude and frequency of micro-vibration signals, and the running characteristics include the start-stop time and running power of the vibration-type operation equipment; the step of analyzing the time correlation between the monitored physical parameter change and the external operation running characteristics comprises: performing time-frequency analysis on the micro-vibration signals to extract energy components associated with the running frequencies of each high-risk operation; when multiple high-risk operations are running simultaneously, it is determined whether there is a nonlinear superposition phenomenon between the associated energy components; if there is a nonlinear superposition phenomenon, it is determined that the interaction relationship is synergistic enhancement according to the degree of nonlinear superposition, and the enhancement coefficient is quantified.

7. The construction safety hazard detection method of claim 1, wherein, In path one, the sensor is a laser radar, the environmental data is three-dimensional point cloud data, the positioning information is obtained through an inertial measurement unit and a real-time positioning and map building technology, the high-risk operations include heavy equipment vibration operations, deep foundation pit excavation operations, and large-volume concrete pouring operations, and the influence area of the high-risk operations is a circular area with the center of the high-risk operation as the center and an influence radius determined according to industry safety standards as the radius.

8. The construction safety hazard detection method of claim 1, wherein, The generation step of the visual risk report comprises: on the two-dimensional site plan, using a specified color to highlight the area corresponding to the set of un-inspected key checkpoints; inside the highlighted area, using a graphical identifier corresponding to the risk level to mark the location of each un-inspected key checkpoint; at a specified position on the two-dimensional plan, display the generated total risk score in numerical form, and display the main high-risk operation type that contributes to the total risk score and the corresponding cumulative risk exposure time.

9. The construction safety hazard detection method of claim 1, wherein, In path two, the step of trying to plan a safe passage path is to perform A-star pathfinding algorithm or rapid expansion random tree algorithm operation in a temporary local environment map constructed according to fuzzy perception data.

10. A construction work safety hazard detection system characterized by, The system comprises: A checkpoint determination module is configured to determine a set of unvisited key checkpoints based on sensor perception data clarity of the inspection device, by selecting one of two modes of operation. In a first mode of operation, the checkpoint determination module is configured to: scan the environment of a physical barrier using the sensor to generate environment data, calculate and determine a geometric range of the detection blind zone based on positioning information of the inspection device, and determine key checkpoints within the geometric range of the detection blind zone in spatial coordinates as the set of unvisited key checkpoints. In a second mode of operation, the checkpoint determination module is configured to: obtain a list of all key checkpoints within a current task range, and for each key checkpoint in the list, independently attempt to plan a safe passage path from a current position of the inspection device to the key checkpoint, and determine all key checkpoints for which a safe passage path cannot be planned as the set of unvisited key checkpoints. A risk assessment module is configured to: obtain a basic total risk score by accumulating basic risk weights of each unvisited key checkpoint obtained from a risk value table based on the set of unvisited key checkpoints determined by the checkpoint determination module, obtain construction operation information around a spatial position of the detection blind zone, track and accumulate a risk exposure duration of the detection blind zone exposed to influence of a high-risk operation, and generate a total risk score based on the basic total risk score, combined with a type of the high-risk operation and the accumulated risk exposure duration. A report generation and pushing module is configured to generate a visual risk report including the total risk score generated by the risk assessment module, and push the visual risk report to a terminal of a manager.

Images