A method and system for monitoring the safety of tower crane construction

Abstract

The application provides a tower crane construction safety monitoring method and system, and belongs to the technical field of engineering construction safety monitoring. The method comprises the following steps: acquiring multi-source data of a target tower crane, wherein the multi-source data comprises sensor data, video monitoring data and environmental data; determining a plurality of operating characteristics of the target tower crane based on the multi-source data; the plurality of operating characteristics comprise operating state characteristics, importance characteristics and environmental risk characteristics; determining a monitoring strategy of the target tower crane based on the plurality of operating characteristics; monitoring safety parameters of the target tower crane based on the monitoring strategy to obtain safety monitoring results; performing risk assessment based on the safety monitoring results and generating a risk avoidance strategy; wherein the target tower crane is one of a plurality of tower cranes in a construction site. The application improves the accuracy of tower crane construction safety monitoring, discovers risks in a timely manner and generates a risk avoidance strategy, thereby ensuring the safety of tower crane construction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering construction safety monitoring, in particular to a tower crane construction safety monitoring method and system. BACKGROUND

[0002] In large construction projects, multiple tower cranes are working at the same time, which puts higher requirements on the construction safety management of tower cranes. In the traditional tower crane construction safety monitoring, a single data source is used for monitoring, and the single data source cannot comprehensively and accurately represent the running status of the tower crane. Relying only on sensor data will ignore the influence of the environment around the tower crane and the state of the driver on safety; simply using video monitoring data cannot accurately monitor the internal structure and mechanical properties of the tower crane; and only considering environmental data cannot grasp the running status and key parameters of the tower crane. The single data monitoring method makes it difficult to determine a reasonable monitoring strategy, cannot effectively monitor the safety parameters of the tower crane and accurately assess the risks, and is prone to safety hazards.

[0003] Therefore, there is an urgent need for a tower crane construction safety monitoring method and system. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a tower crane construction safety monitoring method and system.

[0005] The first aspect of the embodiment of the present application provides a tower crane construction safety monitoring method, comprising:

[0006] Obtaining multi-source data of a target tower crane, the multi-source data comprising sensor data, video monitoring data and environmental data;

[0007] Determining a plurality of running characteristics of the target tower crane based on the multi-source data; the plurality of running characteristics comprising running state characteristics, importance characteristics and environmental risk characteristics;

[0008] Determining a monitoring strategy of the target tower crane based on the plurality of running characteristics;

[0009] Monitoring safety parameters of the target tower crane based on the monitoring strategy to obtain safety monitoring results;

[0010] Performing risk assessment based on the safety monitoring results and generating a risk avoidance strategy;

[0011] The target tower crane is one of a plurality of tower cranes in a construction site.

[0012] The second aspect of the embodiment of the present application provides a tower crane construction safety monitoring system, comprising:

[0013] The data acquisition module is configured to acquire multi-source data of the target tower crane, wherein the multi-source data comprises sensor data, video monitoring data and environmental data.

[0014] The feature analysis module is configured to determine a plurality of operating features of the target tower crane based on the multi-source data, wherein the plurality of operating features comprises operating state features, importance features and environmental risk features.

[0015] The strategy generation module is configured to determine a monitoring strategy of the target tower crane based on the plurality of operating features.

[0016] The monitoring execution module is configured to monitor safety parameters of the target tower crane based on the monitoring strategy to obtain a safety monitoring result.

[0017] The monitoring evaluation module is configured to perform risk evaluation based on the safety monitoring result and generate a risk avoidance strategy.

[0018] The target tower crane is one of a plurality of tower cranes in a construction site.

[0019] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the monitoring method for tower crane construction safety when running the computer program.

[0020] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the monitoring method for tower crane construction safety when executed by a processor.

[0021] The monitoring method and system for tower crane construction safety provided by the embodiments of the present application have the following advantages: the embodiments of the present application comprehensively determine the operating and environmental conditions of the target tower crane by acquiring multi-source data of the target tower crane; the embodiments of the present application can deeply understand the operating state, importance and environmental risk of the target tower crane by determining a plurality of operating features based on the multi-source data; the embodiments of the present application make the monitoring more targeted by determining a monitoring strategy according to the plurality of operating features; the embodiments of the present application can accurately determine the safety condition of the target tower crane by monitoring safety parameters according to the monitoring strategy to obtain a safety monitoring result; and the embodiments of the present application can effectively reduce the risk of the target tower crane construction safety by performing risk evaluation based on the safety monitoring result and generating a risk avoidance strategy. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A flowchart of the monitoring method for tower crane construction safety provided by an embodiment of the present application is shown;

[0023] Figure 2 A structural block diagram of the monitoring system for tower crane construction safety provided by an embodiment of the present application is shown.

[0024] Figure 3 A schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0026] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be combined with the accompanying drawings to make a detailed description. Figures 1-3 The present application is described by way of specific embodiments.

[0027] Reference will be made to Figure 1 , Figure 1 A flowchart of a tower crane construction safety monitoring method according to an embodiment of the present application is shown in the figure. The method comprises the following steps.

[0028] S101: Obtain multi-source data of a target tower crane, the multi-source data comprising sensor data, video monitoring data, and environmental data.

[0029] In the present embodiment, the target tower crane is a certain tower crane in the construction site that is currently being intensively monitored, and is the main object of the monitoring. In a scenario of multiple tower cranes working together, different tower cranes need to be distinguished, and the target tower crane is one of them. For example, in a certain construction site, there are 5 tower cranes working together, numbered T1-T5. In the present embodiment, the tower crane numbered T3 is selected as the target tower crane for safety monitoring, and the remaining T1, T2, T4, and T5 are other tower cranes. The multi-source data is a data set obtained from multiple different sources and different types of channels, representing the running state of the target tower crane and the surrounding environment.

[0030] The sensor data is collected by sensors installed at each part of the target tower crane, and can be used to directly monitor the mechanical operation parameters and structural state of the target tower crane. The sensor and data types include: stress sensor: stress value of tower body, hoist arm, steel wire rope and other parts; vibration sensor: tower body vibration frequency, amplitude; angle sensor: hoist arm elevation angle, rotation angle; weight sensor: hook load, rated load; displacement sensor: tower body verticality deviation, trolley amplitude displacement; wind speed sensor: real-time wind speed at the target tower crane operating height. For example: install a stress sensor at the root of the hoist arm of the target tower crane T3 to collect real-time stress data in units of MPa; install a vibration sensor at the top of the tower body to obtain the vibration frequency (units: Hz) and amplitude (units: mm); install a weight sensor at the hook to collect load data in units of t; the above data collectively constitute the sensor data of the target tower crane, and the sampling frequency is 10 Hz. The video monitoring data is video image data collected by cameras installed at key positions of the target tower crane body and the construction site, which can be used to visually monitor the tower crane operation environment, hook position, surrounding personnel and equipment state, and whether there is illegal operation. For example, install a high-definition camera under the cab of the target tower crane T3 with a resolution of 1920x1080 and a frame rate of 25fps to capture real-time video of the hoist arm, hook and the area below; set three fixed cameras around the construction site to capture the relative position of the target tower crane within the rotation range and other tower cranes, and transmit the video monitoring data to the monitoring center through wireless transmission.

[0031] The environmental data is the natural environment and construction environment data around the target tower crane, which can affect the safe operation of the target tower crane and needs to be monitored. The main data types of environmental data include: meteorological data: site wind speed, wind direction, temperature, humidity, visibility, such as visibility changes caused by weather such as fog, rain, snow; geographical environment data: construction site terrain slope, surrounding building and obstacle distribution and height; For example: set up a meteorological monitoring station at the high point of the construction site to collect environmental data of the target tower crane T3 operating area: including real-time wind speed (units: m / s), wind direction (azimuth angle), environmental temperature (units: ℃), relative humidity (units: %); obtain the height and horizontal distance of obstacles (such as existing buildings and high-voltage towers) within a range of 300 meters around the tower crane by laser radar scanning as geographical environment data.

[0032] S102: determining a plurality of operating characteristics of the target tower crane based on the plurality of source data; the plurality of operating characteristics include operating state characteristics, importance characteristics and environmental risk characteristics.

[0033] In this embodiment, the operation feature is a comprehensive feature representing the operation state, importance and environmental risk of the target tower crane, which is extracted by analyzing multi-source data and is the basis for formulating the monitoring strategy. The operation feature can convert multi-source data into an index that can be analyzed to evaluate the safety state of the target tower crane.

[0034] Among them, the operation state feature is a feature representing the current mechanical operation state of the target tower crane based on sensor data and video monitoring data, including operation stage, load condition, structural stability and other information. The operation stage is idle, light load, heavy load or special operation; the load condition is the actual lifting capacity and the rated lifting capacity; the structural stability includes structural vibration intensity (amplitude, frequency), stress value at key positions and operation speed, such as slewing speed, luffing speed and hoisting speed. The importance feature is a feature representing the importance based on the functional positioning and task priority data of the target tower crane in the construction site, which is used to determine the allocation weight of the monitoring resources, such as higher monitoring frequency for important tower cranes. The environmental risk feature is a feature representing the external environmental risk faced by the target tower crane based on environmental data and operation state data of other tower cranes.

[0035] S103: determining the monitoring strategy of the target tower crane based on the plurality of operation features.

[0036] In this embodiment, the monitoring strategy is a specific monitoring rule formulated for the safe operation of the target tower crane, including monitoring threshold and monitoring frequency. The monitoring threshold is the critical value of the safety parameter, such as the maximum allowed lifting capacity, the maximum swing angle of the steel wire rope, and the maximum vibration amplitude of the structure. If it is greater than the monitoring threshold, it will trigger a warning. The monitoring frequency is the detection interval of the safety parameter sampling, such as 1 time per second or 1 time per 10 seconds. The higher the frequency, the more intensive the monitoring frequency. The monitoring strategy is adjusted according to the plurality of operation features, such as increasing the frequency in the heavy load stage and reducing the threshold in bad weather, so that accurate monitoring can be performed.

[0037] S104: monitoring the safety parameters of the target tower crane based on the monitoring strategy to obtain a safety monitoring result.

[0038] In this embodiment, the safety parameter is an index representing the safety of the target tower crane in operation, which is determined according to the structural characteristics and construction risk points of the target tower crane, including: structural safety parameters, such as stress, vibration frequency, verticality deviation, steel wire rope wear degree, and hook position accuracy; operation state parameters, such as lifting capacity, lifting height, boom rotation angle, running speed, and brake system response time; environmental related parameters, such as wind speed, visibility, and real-time distance to surrounding obstacles (including other tower cranes) within the operation range of the target tower crane; and operation safety parameters, such as driver operation instruction response delay and emergency stop button effectiveness.

[0039] In this embodiment, the safety monitoring result is the concluding information obtained after monitoring, including: normal result: all safety parameters are within the monitoring threshold range, and the running state is risk-free; abnormal result: part or all parameters are greater than the monitoring threshold, and the risk level needs to be further evaluated, such as slight warning, moderate warning, and emergency warning. The safety monitoring result includes the time of abnormality, the duration, and the specific abnormal parameter, for example, the lifting capacity of 12t is greater than the monitoring threshold of 10t.

[0040] S105: Risk assessment based on the safety monitoring result and generation of risk avoidance strategy.

[0041] In this embodiment, risk assessment is a process of analyzing and grading the current or potential safety risks of the target tower crane based on the safety monitoring result. It includes: risk identification: identifying the specific risk type corresponding to the abnormal parameter, such as structural overload risk, collision risk, and environmental interference risk; risk value analysis: calculating the risk value by rules, such as using the over-standard amplitude x duration to evaluate the risk severity; risk grading: dividing the risk into different levels, such as low risk, medium risk, high risk, and emergency risk.

[0042] In this embodiment, the risk avoidance strategy is a specific measure formulated based on the risk assessment result, which eliminates, reduces, or controls the risk and ensures the safe operation of the target tower crane. The risk avoidance strategy must be operable, including: immediate intervention measures, such as emergency braking, adjusting operating parameters (reducing lifting capacity, reducing rotation speed), etc.; coordinated adjustment measures, such as coordinating with other tower cranes to avoid, suspending work in adjacent areas, etc.; long-term optimization measures, such as adjusting monitoring thresholds, strengthening equipment maintenance for repeated risks, etc.

[0043] From the above, it can be concluded that the present application comprehensively determines the running and environmental conditions of the target tower crane by acquiring multi-source data of the target tower crane; determines multiple operating characteristics based on the multi-source data, which can deeply understand the operating state, importance, and environmental risk of the target tower crane; determines a monitoring strategy according to the multiple operating characteristics, which makes the monitoring more targeted; obtains a safety monitoring result by monitoring safety parameters according to the monitoring strategy, which can accurately determine the safety status of the target tower crane; performs risk assessment based on the safety monitoring result and generates a risk avoidance strategy, which can effectively reduce the risk of target tower crane construction safety.

[0044] In an embodiment of the present application, the monitoring strategy of the target tower crane is determined based on the multiple operating characteristics, including:

[0045] determining a first monitoring threshold of the target tower crane based on the operating state characteristics of the target tower crane;

[0046] determining a first monitoring frequency of the target tower crane based on the importance characteristics of the target tower crane;

[0047] determine the monitoring bias of the target tower crane based on the operation bias feature of the target tower crane;

[0048] adjust the first monitoring threshold based on the monitoring bias to obtain a second monitoring threshold;

[0049] adjust the first monitoring frequency based on the monitoring bias to obtain a second monitoring frequency;

[0050] determine the monitoring strategy of the target tower crane based on the second monitoring threshold and the second monitoring frequency.

[0051] In this embodiment, the first monitoring threshold is a safety parameter critical value preliminarily determined based on the operation state feature, such as the maximum allowable load and the maximum swing angle. For example, because the structural load is higher when heavy load, the load threshold of the first monitoring threshold in the heavy load stage is smaller than that in the light load stage. The first monitoring frequency is a parameter detection interval preliminarily determined based on the importance feature, such as the number of samples per second. For example, because the target tower crane in the core area is important, the first monitoring frequency of the base is greater than that of other tower cranes in the edge area.

[0052] In this embodiment, the operation bias feature is a monitoring focus direction calculated based on the environmental risk feature (such as wind speed, distance from other tower cranes, and obstacle density), such as structural health bias, structural stability or collision warning bias under high wind speed, and space conflict under dense tower crane operation. The monitoring bias is the focus monitoring direction determined according to the operation bias feature, which determines which parameters need to be monitored more strictly, including structural health bias and collision warning bias.

[0053] In this embodiment, the second monitoring threshold is the final threshold after adjusting the first monitoring threshold according to the monitoring bias, for example, if the bias is structural health, the allowable range of structural vibration is reduced; if the bias is collision warning, the safety distance requirement from other tower cranes is increased. The second monitoring frequency is the final frequency after adjusting the first monitoring frequency according to the monitoring bias, for example, if the bias is collision warning, the sampling frequency of the position parameter is increased; if the bias is structural health, the detection frequency of the stress sensor is increased.

[0054] From the above, it can be concluded that after obtaining multiple operation features of the target tower crane by acquiring multiple source data, the first monitoring threshold is determined according to the operation state feature, and the monitoring standard is set according to different operation states of the target tower crane; the first monitoring frequency is determined according to the importance feature, so that the target tower crane can reasonably arrange the monitoring frequency in construction; the monitoring bias is determined according to the operation bias feature, and the first monitoring threshold and the first monitoring frequency are adjusted based on the monitoring bias to obtain the second monitoring threshold and the second monitoring frequency, which can further optimize the monitoring strategy, so that the monitoring strategy is more suitable for the actual situation of the target tower crane, thereby more accurately and effectively monitoring the safety parameters of the target tower crane, and improving the accuracy and reliability of the tower crane construction safety monitoring.

[0055] In an embodiment of the present application, further comprising:

[0056] If the lifting weight of the target tower crane is greater than the first threshold value, and the swing amplitude of the steel wire rope is less than the second threshold value, then the second monitoring frequency is reduced based on the first step size to obtain a third monitoring frequency;

[0057] If the lifting weight of the target tower crane is less than the first threshold value, and the swing amplitude of the steel wire rope is greater than the second threshold value, then the second monitoring frequency is increased based on the second step size to obtain a third monitoring frequency.

[0058] In the embodiment, the lifting weight is the weight of the object currently lifted by the target tower crane, which is a parameter representing the load state of the target tower crane. The greater the lifting weight, the greater the stress on the structure of the target tower crane, such as the jib, steel wire rope, and tower body, and the higher the safety risk. The first threshold value is a critical value set for the lifting weight to determine whether the target tower crane is in a high load state. For example, if the maximum rated lifting weight of the target tower crane is 10 t, the first threshold value is set to 7 t, and greater than 7 t is considered as high load. The swing amplitude of the steel wire rope is the angle or horizontal displacement distance of the steel wire rope deviating from the vertical direction when the target tower crane lifts the object, which represents the stability of the lifted object. The greater the swing amplitude, the more likely the lifted object will collide with surrounding objects or cause the center of gravity of the target tower crane to shift, increasing the risk of overturning. The second threshold value is a critical value set for the swing amplitude of the steel wire rope to determine whether the lifted object is stable. For example, the second threshold value is set to 5°, and a swing angle greater than 5° is considered as unstable state.

[0059] In the embodiment, the first step size is the adjustment amplitude for reducing the second monitoring frequency, for example, reducing from sampling once every 1 second to sampling once every 2 seconds, and the first step size is 1 second. The first step size is used in a low-risk scenario to avoid resource waste caused by excessive monitoring. The second step size is the adjustment amplitude for increasing the second monitoring frequency, for example, increasing from sampling once every 1 second to sampling once every 0.5 second, and the second step size is 0.5 second.

[0060] The first step length calculation formula is: first step length = basic reduction step length x overload coefficient x stability coefficient. The basic reduction step length is S1, and the preset reference value is fixed based on the target tower crane type. For example, for large tower cranes with a lifting capacity greater than or equal to 20 t: S1 = 0.3 s, the structure responds slowly under heavy load, and the frequency can be reduced more significantly; for small and medium-sized tower cranes with a lifting capacity less than 20 t, S1 = 0.2 s, the structure is highly flexible, and the reduction amplitude is conservative. The overload coefficient is K1, which is calculated based on the proportion of the lifting capacity greater than the first threshold value, indicating the degree of overload, K1 = 1 + 0.1 x (current lifting capacity - first threshold value) / first threshold value. For example, the first threshold value = 8 t, and the current lifting capacity = 10 t, then K1 = 1 + 0.1 x (10 - 8) / 8 = 1.025, the more significant the overload, the higher the coefficient, and the larger the step length. The stability coefficient is W1, which is calculated based on the proportion of the steel wire rope swing amplitude less than the second threshold value, indicating the stability of the load, W1 = 1 + 0.2 x (second threshold value - current swing amplitude) / second threshold value. For example, the second threshold value = 3°, and the current swing amplitude = 2°, then W1 = 1 + 0.2 x (3 - 2) / 3 ≈ 1.067, the more stable, the higher the coefficient, and the larger the step length. The first step length upper limit is less than or equal to 0.5 s, to avoid long intervals leading to missed detection and sudden risks.

[0061] For example, for small and medium-sized tower cranes S1 = 0.2 s, lifting capacity 10 t, first threshold value 8 t, swing amplitude 2°, and second threshold value 3°, then the first step length = 0.2 x 1.025 x 1.067 ≈ 0.22 s, taking 0.2 s, the interval is extended by 0.2 s.

[0062] In the present embodiment, the second step length calculation formula is: second step length = basic increase step length x light load coefficient x instability coefficient. The basic increase step length is S2, and the preset reference value is fixed based on the load type. For example, for rigid loads (such as steel structures): S2 = 0.2 s, the swing is regular, and the adjustment amplitude is moderate; for flexible loads (such as steel reinforcement bundles): S2 = 0.3 s, the swing is more violent, and the frequency needs to be increased more significantly. The light load coefficient is K2, which is calculated based on the proportion of the lifting capacity less than the first threshold value, indicating the degree of light load: K2 = 1 + 0.15 x (first threshold value - current lifting capacity) / first threshold value. For example, the first threshold value = 8 t, and the current lifting capacity = 5 t, then K2 = 1 + 0.15 x (8 - 5) / 8 ≈ 1.056, the lighter the load, the higher the coefficient, and the larger the step length. The instability coefficient is W2, which is calculated based on the proportion of the steel wire rope swing amplitude greater than the second threshold value, indicating the degree of instability, W2 = 1 + 0.3 x (current swing amplitude - second threshold value) / second threshold value. For example, the second threshold value = 3°, and the current swing amplitude = 5°, then W2 = 1 + 0.3 x (5 - 3) / 3 ≈ 1.2, the more unstable, the higher the coefficient, and the larger the step length. The second step length lower limit is greater than or equal to 0.1 s, to avoid overloading due to high frequency.

[0063] For example, the flexible hanging object S2 = 0.3 seconds, the lifting weight is 5t, the first threshold is 8t, the swing amplitude is 5°, and the second threshold is 3°: the second step size = 0.3 x 1.056 x 1.2 ≈ 0.38 seconds, taking 0.4 seconds, and the interval is shortened by 0.4 seconds.

[0064] In the embodiment, the second monitoring frequency is an intermediate frequency obtained after the bias adjustment, and is an adjustment reference of the embodiment. For example, the second monitoring frequency is 1 sample per 1 second. The third monitoring frequency is a final monitoring frequency obtained by adjusting the second monitoring frequency by the first step size reduction or the second step size increase, and is used to update the monitoring strategy of the target tower crane.

[0065] From the above, the embodiment can match the monitoring frequency with the actual operation of the target tower crane by adjusting the second monitoring frequency to obtain the third monitoring frequency according to the size relationship between the target tower crane lifting weight and the first threshold and the size relationship between the steel wire rope swing amplitude and the second threshold, thereby improving the pertinence and effectiveness of the monitoring, avoiding unnecessary frequent monitoring or insufficient monitoring, and more accurately monitoring the safety parameters of the target tower crane.

[0066] In an embodiment of the present application, the first monitoring threshold of the target tower crane is determined based on the operating state characteristics of the target tower crane, including:

[0067] The corresponding operating phase is determined based on the operating state characteristics of the target tower crane.

[0068] The corresponding reference threshold is determined based on the operating phase and the predefined first mapping table.

[0069] The reference threshold is corrected based on the environmental data to generate the first monitoring threshold.

[0070] The first monitoring frequency of the target tower crane is determined based on the importance characteristics of the target tower crane, including:

[0071] The base monitoring frequency is determined according to the importance level of the target tower crane in the construction layout.

[0072] The base monitoring frequency is adjusted based on the current construction phase to generate the first monitoring frequency.

[0073] In the embodiment, the operating phase is a working mode of the target tower crane divided according to the operating state characteristics, including: an idle phase, no load, and a stationary state; a light load phase, the load weight is less than 30% and the rated maximum lifting weight; a heavy load phase, the load weight is greater than or equal to 30% and the rated maximum lifting weight; and a special operation phase, such as load rotation, amplitude change, emergency stop, and other high-risk operations.

[0074] In the embodiment, the predefined first mapping table is a correspondence table of predefined running stages and reference thresholds, for example, the reference threshold of the lifting capacity in the heavy load stage is less than that in the light load stage, and the reference threshold of the vibration in the special operation stage is more stringent. The reference threshold is an initial safety parameter critical value matched with the current running stage queried from the predefined first mapping table, and the environmental influence is not considered. The environmental data is an external environmental factor affecting the safety of the target tower crane, such as wind speed, temperature, humidity, and visibility. The first monitoring threshold is a final threshold obtained by correcting the reference threshold based on the environmental data, and is the basis for monitoring.

[0075] In the embodiment, the importance feature is an attribute representing the key degree of the target tower crane in the construction scene, such as the carrying capacity (maximum lifting capacity), the position key degree (whether located in the core construction area), and the task priority (whether participating in the key process). The importance level is a level divided based on the importance feature, for example, high, medium, and low, for example, the target tower crane in the core area is high level, and the target tower crane in the edge area is low level. The basic monitoring frequency is an initial monitoring interval determined according to the importance level, for example, the target tower crane of high level is 1 time per 1 second, and the target tower crane of low level is 1 time per 3 seconds.

[0076] In the embodiment, the current construction stage is the stage of the engineering project, for example, the foundation construction (low frequency of the target tower crane), the main body construction (high intensity operation of the target tower crane), and the decoration construction (decreasing frequency of the target tower crane). The first monitoring frequency is a final frequency obtained by adjusting the basic monitoring frequency according to the construction stage, and represents the need of different construction stages for monitoring density.

[0077] From the above, it can be concluded that the embodiment determines the running stage according to the running state feature of the target tower crane, determines the reference threshold according to the predefined first mapping table, and obtains the first monitoring threshold by correcting the reference threshold by using the environmental data, so that the monitoring threshold is more suitable for the actual running condition and the environmental condition of the target tower crane, and the accuracy of monitoring is improved. The basic monitoring frequency is determined according to the importance level of the target tower crane in the construction layout, and the first monitoring frequency is obtained by adjusting the basic monitoring frequency based on the current construction stage, so that the monitoring frequency can be flexibly adjusted according to the importance of the target tower crane and the construction stage, and the monitoring efficiency is improved.

[0078] In an embodiment of the present application, based on the running bias feature of the target tower crane, the monitoring bias of the target tower crane is determined, including:

[0079] The running bias feature is calculated based on the environmental risk feature of the target tower crane, wherein the environmental risk feature includes wind speed, visibility, surrounding obstacle density, and safety distance from other tower cranes.

[0080] The monitoring bias is determined according to the running bias feature, and the monitoring bias includes the structure health bias and the collision warning bias.

[0081] In this embodiment, the operation bias feature is calculated based on the environmental risk feature, which represents the parameter of the risk direction that the target tower crane should focus on, and can be obtained by scoring or weight calculation. For example: if the wind speed is extremely high, for example 12 m / s, the score related to the structure health is increased, and the operation bias feature is biased to the structure safety; if the distance to other tower cranes is too close, for example 30 m, the score related to the collision warning is increased, and the operation bias feature is biased to the space safety. The environmental risk feature is a set of external environmental factors that affect the safe operation of the target tower crane, and is the basis for calculating the operation bias feature, including: wind speed: the real-time wind speed in the target tower crane operation area, and the high wind speed will increase the structural load of the target tower crane, such as boom vibration and tower stress, resulting in structural stability risk; visibility: the visibility of the working environment, such as fog, rain, night lighting, etc., and low visibility will affect the judgment of the driver on the surrounding obstacles, increasing the collision risk; surrounding obstacle density: the number and distribution density of fixed obstacles in the target tower crane operation range, and the higher the density, the higher the collision risk, such as buildings and high-voltage lines; safe distance from other tower cranes: the real-time distance between the target tower crane and other tower cranes in the construction site, and the closer the distance, the higher the risk of interference between the tower cranes or the hoisted objects.

[0082] In this embodiment, the monitoring bias is determined according to the operation bias feature, which determines which safety parameters need more strict monitoring, including the structure health bias and the collision warning bias. Among them, the structure health bias is to focus on monitoring the parameters related to the structural stability of the target tower crane itself, such as boom stress, tower verticality, steel wire rope wear degree, structural vibration frequency, etc.; the collision warning bias focuses on monitoring the parameters related to space safety, such as the real-time distance from other tower cranes, the boom rotation track, the relative position of the surrounding obstacles, the hoisted object swing range, etc.

[0083] From the above, it can be concluded that the embodiment calculates the operation bias feature based on the wind speed, visibility, surrounding obstacle density and safe distance from other tower cranes of the target tower crane, comprehensively considers the influence of various environmental factors on the operation of the target tower crane, and then determines the monitoring bias of the structure health bias and the collision warning bias according to the operation bias feature, so that the monitoring strategy is more targeted, the monitoring accuracy of the structure health and collision risk of the target tower crane is improved, and the safety of the tower crane construction is ensured.

[0084] In an embodiment of the present application, based on the monitoring bias, the first monitoring threshold is adjusted to obtain the second monitoring threshold, and based on the monitoring bias, the first monitoring frequency is adjusted to obtain the second monitoring frequency, including:

[0085] If the monitoring emphasis is structural health, the first monitoring frequency of structural vibration and stress parameters is increased based on the fourth step size to obtain a second monitoring frequency, and the allowed range of the first monitoring threshold is reduced based on the third step size to obtain a second monitoring threshold;

[0086] If the monitoring emphasis is collision warning, the first monitoring threshold of the amplitude and height parameters is reduced based on the third step size to obtain a second monitoring threshold, and the first monitoring frequency of position detection is increased based on the fourth step size to obtain a second monitoring frequency.

[0087] In this embodiment, the first monitoring threshold is a preliminary safety parameter threshold value determined based on the operating state characteristics and environmental data, such as the maximum allowed value of structural vibration, the minimum safe distance from other objects, etc., and is the basis for adjustment. The first monitoring frequency is a preliminary parameter detection interval determined based on the importance characteristics and the construction stage, such as the number of samples per second, and is the basis for adjustment. The second monitoring threshold is the final threshold obtained after adjusting the first monitoring threshold according to the monitoring emphasis, which meets the prevention and control needs of the current key risks. The second monitoring frequency is the final frequency obtained after adjusting the first monitoring frequency according to the monitoring emphasis, so that the monitoring of key parameters is more intensive or more sparse.

[0088] In this embodiment, the third step size is the magnitude for adjusting the allowed range of the first monitoring threshold, such as a decrease of 10% or an increase of 2 meters. The fourth step size is the magnitude for adjusting the first monitoring frequency, such as a reduction of 0.2 second intervals or an extension of 0.5 second intervals.

[0089] wherein the third step size calculation formula is: third step size = base threshold step size × risk level coefficient × equipment attenuation coefficient. The base threshold step size is B t , a preset reference value according to the parameter type, and the reference value is a fixed value: structure type parameters (vibration, stress): B t = 10%, the structure risk consequence is more serious, and the base step size is larger; space type parameters (amplitude, distance): B t = 5%, the space risk can be avoided by operation, and the base step size is small. The risk level coefficient is R t , calculated based on environmental risk characteristics, ranging from 0.5 to 1.5, R t = Σ (single factor risk index × weight. Wherein, the single factor risk index is an index mapped to 0-1 from environmental parameters, such as 1.0 when the wind speed is greater than 12 m / s and 0.3 when the wind speed is less than 5 m / s. The weight distribution is: structure type parameters: wind speed 0.6, temperature 0.2, humidity 0.2; space type parameters: distance from other tower cranes 0.7, obstacle density 0.3. The equipment attenuation coefficient is D t , calculated based on the service life of the target tower crane and maintenance records, ranging from 1.0 to 1.5, D t= 1 + 0.1 x (service life - 5), after serving for 5 years, every increase of 1 year, the coefficient +0.1, the highest is 1.5. Among them, the upper limit of the third step is less than or equal to 15% for structure class and less than or equal to 10% for space class, to avoid false positives caused by excessive tightening of the threshold.

[0090] For example, a target tower crane monitors the vibration of the structure B t = 10%, wind speed 10 m / s (risk index 0.8), temperature 38℃ (risk index 0.6), weight calculation R t = 0.8 x 0.6 + 0.6 x 0.2 = 0.6; service for 7 years, D t = 1 + 0.1 x (7-5) = 1.2; then the third step = 10% x 0.6 x 1.2 = 7.2%, rounded to 7%.

[0091] In this embodiment, the fourth step calculation formula is: fourth step = basic frequency step x parameter change rate coefficient x computing power coefficient. Among them, the basic frequency step is B, the reference value is preset according to the parameter change speed, and the reference value is a fixed value: fast changing parameters (position, angle): B = 0.2 seconds, high frequency monitoring is needed, and the basic step is smaller; slowly changing parameters (stress, wear): B = 0.5 seconds, the change is gentle, and the basic step is larger. The parameter change rate coefficient V is calculated based on the parameter change speed, and the range is 0.5-2.0, V = current change rate / safe change rate threshold, for example: the safe threshold of the swing arm rotation speed is 5° / s, and the current speed is 8° / s, then V = 8 / 5 = 1.6. The computing power coefficient C is calculated based on the remaining computing power, and the range is 0.7-1.0, the formula is C = 1-0.3 x (used computing power proportion), for example, the used computing power proportion is 60%, then C = 1-0.3 x 0.6 = 0.82. Among them, the lower limit of the fourth step is greater than or equal to 0.1 seconds, to avoid overloading caused by too dense sampling.

[0092] For example, a target tower crane monitors the position of other tower cranes, B = 0.2 seconds, distance change rate 0.9 m / s (safe threshold 0.5 m / s), V = 0.9 / 0.5 = 1.8, used computing power proportion 50%, C = 1-0.3 x 0.5 = 0.85, then the fourth step = 0.2 seconds x 1.8 x 0.85 ≈ 0.306 seconds, take 0.3 seconds.

[0093] In the embodiment, the structural vibration and stress parameters are indexes representing the safety of the target tower crane structure: the structural vibration includes the vibration frequency or amplitude of the jib and tower body, which is too large to cause structural fatigue or fracture; the stress parameter is the stress at the key position of the structure, such as the root of the jib and the connection of the tower body, which is greater than the limit to cause structural damage. The amplitude and height parameters are parameters related to the working space of the target tower crane. The amplitude is the rotating radius of the jib or the horizontal movement distance of the hoisted object, and the height is the lifting height of the hoisted object or the vertical height corresponding to the luffing angle of the jib. The position detection is the real-time monitoring of the position of the target tower crane itself and the surrounding objects (such as other tower cranes and obstacles), including coordinates, distances, and relative motion directions.

[0094] From the above, it can be concluded that when the monitoring bias is the structural health bias, the first monitoring frequency of the structural vibration and stress parameters is increased, and the allowable range of the first monitoring threshold is reduced, which can more accurately monitor the health status of the target tower crane structure and timely find safety hazards in the structure; when the monitoring bias is the collision warning bias, the first monitoring threshold of the amplitude and height parameters is reduced, and the first monitoring frequency of the position detection is increased, which can more effectively prevent the tower crane from colliding and enhance the safety of the tower crane construction.

[0095] In an embodiment of the present application, it further comprises:

[0096] Based on the environmental data and the operation state data of other tower cranes in the multi-source data, the safety influence degree between the multiple tower cranes is determined;

[0097] In response to the safety monitoring result being abnormal for the target tower crane, the monitoring strategy corresponding to the target tower crane is adjusted based on the safety influence degree;

[0098] For the other tower cranes with a safety influence degree greater than a preset influence threshold, an influence coefficient is calculated;

[0099] Based on the influence coefficient, a fifth step size is calculated;

[0100] Based on the fifth step size, the monitoring frequency of the other tower cranes is increased.

[0101] In the embodiment, the operation state data of the other tower cranes is the operation parameter of the other tower cranes except the target tower crane at the construction site, which can be used to analyze the mutual influence of the multiple tower cranes when they work cooperatively, such as the collision risk. The main data includes: the real-time position (rotation angle, amplitude) of the other tower cranes, the lifting capacity, the running speed, and the operation state running or stopping. The safety influence degree is the risk level of the mutual influence between the multiple tower cranes, which is used to interfere with the safe operation of the other tower cranes when a certain tower crane is abnormal. For example, the closer the distance and the more the intersection of the running tracks of the tower cranes, the higher the safety influence degree; the safety influence degree of the heavy-load running tower crane on the surrounding tower cranes is greater than that of the empty-load tower crane.

[0102] In this embodiment, the safety monitoring result that the target tower crane is abnormal is that the safety parameter of the target tower crane is greater than the monitoring threshold value, and the safety parameter is, for example, the lifting weight, the structural vibration, and the distance from other tower cranes, which are determined to be in a state of safety risk, such as overload and too close distance. The preset influence threshold value is a pre-set critical value of the safety influence degree, which is used to determine whether other tower cranes need to follow the adjustment of the monitoring strategy. For example, the preset influence threshold value is 60 points, and the full score is 100 points. Other tower cranes with a safety influence degree greater than 60 points are to be focused on. The influence coefficient represents the specific proportion of the influence of the target tower crane abnormality on other tower cranes, which is a value between 0 and 1. For example, an influence coefficient of 0.8 indicates that the influence degree of a certain tower crane on the target tower crane abnormality is 80%.

[0103] In this embodiment, the fifth step length is an adjustment amplitude for increasing the monitoring frequency of other tower cranes, for example, shortening the length of the sampling interval, and the value thereof is positively correlated with the influence coefficient. The greater the influence, the greater the step length, and the more significant the frequency increase. Other tower cranes are other tower cranes in the construction site except the target tower crane, and whether to adjust the monitoring frequency of other tower cranes needs to be determined according to the safety influence degree of the target tower crane.

[0104] From the above, it can be concluded that the embodiment determines the safety influence degree between multiple tower cranes based on environmental data and other tower crane operating state data, adjusts the monitoring strategy according to the safety influence degree when the target tower crane is abnormal, and can calculate the influence coefficient and the fifth step length for other tower cranes with a safety influence degree greater than the preset influence threshold value, thereby increasing the monitoring frequency of these tower cranes and improving the accuracy and comprehensiveness of the tower crane group construction safety monitoring.

[0105] In an embodiment of the present application, the safety influence degree between multiple tower cranes is determined based on environmental data and operating state data of other tower cranes in multi-source data, including:

[0106] The first safety influence degree is determined based on the spatial distance between the tower cranes, wherein the spatial distance is calculated based on the safety distance from other tower cranes in the environmental risk characteristics;

[0107] The second safety influence degree is determined based on the overlap degree of the tower crane operating area;

[0108] The third safety influence degree is determined based on the historical collision or interference event;

[0109] The first safety influence degree, the second safety influence degree, and the third safety influence degree are weighted and calculated to obtain the safety influence degree; wherein the weighting coefficient is determined based on the importance characteristics of the target tower crane and the environmental risk characteristics.

[0110] In this embodiment, the spatial distance is the real-time distance between the target tower crane and other tower cranes, which is the basic physical parameter for calculating the safety impact, and is directly obtained or converted based on the safety distance data from other tower cranes in the environmental risk characteristics. The first safety impact degree is the impact degree obtained based on the spatial distance between the tower cranes, and the closer the distance, the higher the impact degree. For example: full score 100 points, distance less than or equal to 50 m is high impact, 80 points; 50-100 m is medium impact, 50 points; more than 100 m is low impact, 20 points.

[0111] In this embodiment, the overlap degree of the work area is the work range of the target tower crane and other tower cranes, such as the intersection proportion of the hoist arm rotation coverage area and the hoisted object activity range, and the higher the overlap, the greater the collision risk. The second safety impact degree is the impact degree obtained based on the overlap degree of the work area, and the higher the overlap proportion, the higher the impact degree. For example: overlap proportion greater than 60% is high impact, 90 points; 30%-60% is medium impact, 60 points; less than 30% is low impact, 30 points.

[0112] In this embodiment, the historical collision or interference event is the close-range interference, slight collision or warning record between the target tower crane and other tower cranes in the past period of time, such as 3 months, which indicates the historical risk of potential conflict between the two. The third safety impact degree is the impact degree obtained based on the frequency and severity of the historical events, and the more and more serious the events, the higher the impact degree. For example: 2 times or more warnings in 3 months is high impact, 70 points; 1 warning is medium impact, 40 points; no event is low impact, 10 points.

[0113] In this embodiment, the weighted calculation is the process of superimposing the first safety impact degree, the second safety impact degree and the third safety impact degree according to different weights to obtain the comprehensive safety impact degree, and the weight represents the contribution of each factor to the overall risk. The weighting coefficient is the weight value allocated to the first safety impact degree, the second safety impact degree and the third safety impact degree, and the sum is 1. The weighting coefficient is determined based on the following factors: the importance characteristics of the target tower crane: the weight of the core area tower crane is inclined to the spatial distance to avoid close-range risk; environmental risk characteristics: in high wind environment, the weight is inclined to the work area overlap to avoid wind-induced hoisted object deviation. According to the relative high and low of the importance characteristic score S1 and the environmental risk characteristic score S2, the weights of the first safety impact degree, the second safety impact degree and the third safety impact degree are allocated, as shown in Table 1. The safety impact degree is the comprehensive score obtained after weighted calculation, ranging from 0 to 100 points, which is used to represent the overall risk level of the mutual influence between the tower cranes.

[0114] Table 1 Weight distribution adjustment table

[0115]

[0116] From the above, it can be concluded that the embodiment determines the safety influence degree between multiple tower cranes by comprehensively considering the spatial distance between the tower cranes, the overlap degree of the operation areas, and the historical collision or interference events, and the weighting coefficients are determined based on the importance features and the environmental risk features of the target tower crane, which can more comprehensively and accurately evaluate the safety influence degree between multiple tower cranes, provide a basis for adjusting the monitoring strategy, and improve the safety of tower crane construction.

[0117] In an embodiment of the present application, determining the monitoring strategy of the target tower crane based on multiple operating characteristics further includes:

[0118] When the safety influence degree is greater than the collaborative operation risk threshold, a risk prediction value of the target tower crane is obtained based on the multiple operating characteristics through a risk prediction model;

[0119] A first monitoring threshold and a first monitoring frequency are determined based on the risk prediction value to form the monitoring strategy.

[0120] In the embodiment, the collaborative operation risk threshold is a pre-set safety influence degree critical value for determining whether the risk of collaborative operation between tower cranes is too high. For example, the collaborative operation risk threshold is set to 60 points, and when the safety influence degree is greater than 60 points, it is determined as high collaborative risk. The risk prediction model is a comprehensive model for predicting the future risk of the target tower crane, which is composed of a first risk prediction model and a time series prediction model, and outputs the final risk prediction value through multi-dimensional data input and adjustment.

[0121] The risk prediction value is the result output by the risk prediction model, for example, 0-10 points, indicating the potential risk of the target tower crane in the collaborative operation scenario, and the higher the value, the greater the risk. The first monitoring threshold is a safety parameter critical value determined based on the risk prediction value, for example, the upper limit of the lifting capacity and the maximum value of the structural vibration, and the higher the risk prediction value, the stricter the first monitoring threshold. The first monitoring frequency is a parameter monitoring interval determined based on the risk prediction value, for example, the sampling frequency, and the higher the risk prediction value, the higher the frequency, and the more intensive the sampling. The monitoring strategy is a complete monitoring rule composed of the first monitoring threshold (safety parameter allowable range) and the first monitoring frequency (sampling interval), which is used to guide the safety monitoring of the target tower crane.

[0122] From the above, it can be concluded that the embodiment, when the safety influence degree between multiple tower cranes is greater than the collaborative operation risk threshold, obtains the risk prediction value of the target tower crane based on multiple operating characteristics using a risk prediction model, and then determines the first monitoring threshold and the first monitoring frequency according to the risk prediction value to form the monitoring strategy, so that the monitoring strategy is more suitable for the actual risk situation of the target tower crane, improves the accuracy of safety monitoring of tower crane construction, and better safeguards the safety of tower crane construction.

[0123] In an embodiment of the present application, the risk prediction value of the target tower crane is obtained by a risk prediction model, comprising:

[0124] The plurality of operating characteristics are input into a first risk prediction model to obtain an initial predicted risk value;

[0125] The continuous time series of multi-source data is input into a time series prediction model to obtain a risk change trend in a future preset time;

[0126] The initial predicted risk value is adjusted based on the risk change trend to obtain a final predicted risk value as the risk prediction value.

[0127] In the present embodiment, the first risk prediction model is a random forest algorithm model trained based on historical data, and the training data includes the operating records and risk events of the target tower crane within 3 months. The input is a plurality of operating characteristics, and the output is an initial predicted risk value of the target tower crane in a future period of time (for example, within 5 minutes). The initial predicted risk value is the output result of the first risk prediction model, for example, 0-10 points, indicating the risk level of the target tower crane in the current state, but without considering the change of risk over time, for example, the risk rising due to the future increase in wind speed.

[0128] The continuous time series of multi-source data is multi-dimensional data continuously collected in time sequence, for example, every second data in the past 10 minutes, including: time-series operating state data, such as the change curve of lifting capacity over time, the time series of structural vibration; time-series environmental data, such as continuous changes in wind speed and visibility; and time-series operating data of other tower cranes, such as the rotation trajectory of the boom angle over time.

[0129] In the present embodiment, the time series prediction model is a model for processing time series data, and a long short-term memory network model trained based on historical time series data is used to predict future risk-related parameters, wherein the historical time series data includes parameters that change over time, such as wind speed, lifting capacity, and distance. The long short-term memory network model inputs the continuous time series of multi-source data, and outputs the change trend of the risk-related parameters in a future period of time, for example, the wind speed will rise from 8 m / s to 10 m / s and the distance to other tower cranes will shrink from 50 m to 40 m in the next 5 minutes. The future preset time is a pre-set risk prediction time, for example, 5 minutes or 10 minutes, which is determined according to the tower crane operation rhythm and risk response time, and the preset time can be shortened to 1 minute in high-risk operations. The risk change trend is the future risk parameter change direction and amplitude output by the time series prediction model, for example, risk rising trend, risk falling trend, and risk stability, for example: in the next 5 minutes, the structural vibration value will rise at a rate of 0.2 Hz / minute. The final predicted risk value is the final result obtained by adjusting the initial predicted risk value based on the risk change trend, which includes not only the current state risk but also the risk evolution in a future period of time.

[0130] From the above, in the embodiment, the initial predicted risk value is obtained by inputting multiple operating characteristics into the first risk prediction model, and the initial predicted risk value is adjusted based on the risk change trend in the future preset time obtained by inputting the continuous time sequence of the multi-source data into the time series prediction model, so that a more accurate final predicted risk value is obtained as the risk prediction value. Based on the risk prediction value, the first monitoring threshold and the first monitoring frequency are determined to form a monitoring strategy, so that the safety parameters of the target tower crane can be more accurately monitored and risk evaluated, and a more effective risk avoidance strategy can be generated.

[0131] In an embodiment of the present application, based on the video monitoring data, state data of the target tower crane driver is obtained;

[0132] Based on the state data of the driver, a driver risk factor is determined;

[0133] Based on the driver risk factor, the monitoring strategy is adjusted;

[0134] When the driver risk factor is greater than a preset risk threshold, the safety parameter monitoring frequency of the target tower crane is increased, and the safety parameter monitoring threshold of the target tower crane is reduced.

[0135] In the embodiment, the video monitoring data is a real-time video stream collected by a camera installed in the cockpit of the target tower crane, which is used to capture the behavior and state of the driver, such as facial expression, body movement, and gaze direction. The state data of the target tower crane driver is an index extracted from the video monitoring data, which represents the physiological or behavioral state of the driver, including: physiological state: such as whether to close eyes (fatigue), yawning frequency (drowsiness degree), heart rate (indirectly judged by facial skin color change); behavioral state: such as whether the line of sight deviates from the operation area (distraction), whether the operation action is slow (reaction ability decreases), and whether the mobile phone is used (violation behavior).

[0136] In the embodiment, the driver risk factor is a comprehensive risk score calculated based on the driver state data, such as 0-10 points, which is used to represent the influence degree of the driver state on the safe operation of the target tower crane. The higher the score, the worse the driver state, such as fatigue, distraction, and operation failure risk; the lower the score, the better the driver state, and the higher the operation stability. The preset risk threshold is a pre-set critical value of the driver risk factor, such as 6 points, which is used to judge whether the monitoring strategy needs to be adjusted. When the driver risk factor is greater than the preset threshold, it is determined as a high-risk state, and the monitoring needs to be strengthened; when the driver risk factor is less than the preset threshold, it is determined as a low-risk state, and the regular monitoring is maintained.

[0137] In the embodiment, the safety parameter monitoring frequency is a sampling interval of the safety parameters of the target tower crane, such as the lifting weight, the structural vibration, and the distance from other tower cranes, for example, 1 time per 0.5 seconds, wherein the higher the frequency, the more intensive the monitoring. The safety parameter monitoring threshold is a critical value of the allowable range of the safety parameters, for example, the lifting weight is less than or equal to 10 t, and the structural vibration is less than or equal to 2.0 Hz.

[0138] From the above, it can be concluded that the embodiment can accurately grasp the real-time state of the driver by using the video monitoring data to obtain the state data of the driver of the target tower crane. The driver risk factor is determined, and the influence degree of the state of the driver on the safety of the target tower crane can be obtained. The monitoring strategy is adjusted based on the driver risk factor, so that the monitoring strategy is more in line with the actual situation. When the driver risk factor is greater than the preset risk threshold, the safety parameter monitoring frequency is increased and the safety parameter monitoring threshold is reduced, the monitoring of the safety of the target tower crane is strengthened, and potential risks are discovered in time.

[0139] In an embodiment of the present application, the driver risk factor is determined based on the state data of the driver, comprising:

[0140] The face video stream data is extracted to obtain face feature data, which is input into a pre-trained convolutional neural network model to obtain a fatigue index and a tension index of the driver;

[0141] Based on the eye close-up image data, the blinking frequency and the average closed-eye duration per unit time are calculated;

[0142] Based on the posture image data of the upper body of the driver, a posture estimation algorithm is used to determine whether the head of the driver is continuously deviated from the front operation interface, and a head deviation angle is obtained;

[0143] The fatigue index, the tension index, the blinking frequency, the average closed-eye duration, and the head deviation angle of the driver are weighted and fused to calculate a comprehensive risk factor as the driver risk factor;

[0144] The weights of the weighted fusion are adjusted based on the operating phase of the target tower crane.

[0145] In the embodiment, the face video stream data is a sequence of continuous video frames of the face of the driver collected by the cockpit camera, including facial expressions, eye states, and head postures, and is basic data for extracting driver state features. The face feature data is a key feature extracted from the face video stream, such as the face contour, the eyebrow position, the mouth corner radian, and the eye region, which is used to judge the physiological and emotional state of the driver, such as fatigue and tension.

[0146] In this embodiment, the pre-trained convolutional neural network model is a deep learning model trained on a large amount of facial image data, capable of extracting spatial features in the image for analyzing facial feature data. The output state indicators are fatigue index and tension index, where the fatigue index is a score representing the degree of driver fatigue, ranging from 0 to 10 points, with higher scores indicating more fatigue; the tension index is a score representing the degree of emotional tension of the driver, ranging from 0 to 10 points, with higher scores indicating more tension leading to operational errors. The eye close-up image data is a high-definition image of the eye region cropped from the facial video stream, focusing on the eyelid and pupil, for analyzing physiological features related to blinking. The blink rate is the number of blinks per unit time (e.g. 1 minute), with normal adults having about 15-20 times per minute, increasing to more than 30 times or decreasing to less than 5 times when fatigued; the average eye closure duration is the average duration of eyelid closure during each blink, with normal being 0.2-0.4 seconds, lengthening to more than 0.6 seconds when fatigued.

[0147] In this embodiment, the upper body posture image data includes video frame data of the driver's upper body (head, shoulders, arms) for analyzing whether the body posture conforms to the safety operation specification. The posture estimation algorithm is an algorithm for calculating the body posture by recognizing key points (such as head vertex, shoulder joint) in the image, using the OpenPose algorithm, which is a posture estimation algorithm trained on a large amount of image and video data labeled with human key points (such as joints, facial feature points), capable of detecting the positions of multiple human body, face and hand key points. The head key points are recognized by the OpenPose algorithm to calculate the deviation angle and determine whether the driver's head deviates from the operating interface. The head deviation angle is the angle between the driver's head axis and the front operating interface (such as operating lever, instrument panel) (0° is directly opposite, more than 30° is significantly deviated), indicating whether the driver is distracted, such as turning his head to look at his phone or chatting.

[0148] In this embodiment, the weighted fusion is the process of adding the fatigue index, tension index, blink rate, average eye closure duration and head deviation angle according to different weights to obtain a comprehensive score. The comprehensive risk factor is the final score obtained after weighted fusion, ranging from 0 to 10 points, representing the driver's operational risk, with higher scores indicating greater risk. The operating phase of the target tower crane is the current working mode of the target tower crane, such as idle, light load, heavy load, special operation phase, with different sensitivity to the driver's state, such as higher concentration required in heavy load phase, thus adjusting the weights of the weighted fusion.

[0149] From the above, it can be concluded that the embodiment can comprehensively evaluate the driver state by processing the driver face video stream, eye close-up image and upper body posture image data. The comprehensive risk factor is calculated by weighting and fusing the fatigue index, tension index, blink frequency, average closed-eye duration and head deviation angle, and the weight is adjusted according to the target tower crane operation stage, so that the driver risk factor can be determined more accurately.

[0150] In an embodiment of the present application, further comprising: obtaining the predicted motion path of the target tower crane based on the operation state data of the target tower crane;

[0151] Based on the video monitoring data, the existing conflict targets around the target tower crane are identified, including personnel below the tower crane and other tower crane jibs;

[0152] The position, speed and motion trajectory of the existing conflict targets relative to the target tower crane are obtained, and the predicted motion path of the existing conflict targets is obtained;

[0153] Based on the predicted motion path of the target tower crane and the predicted motion path of the existing conflict targets, the minimum predicted distance of the path within a future preset time and the time to reach the minimum predicted distance are calculated;

[0154] Based on the minimum predicted distance and the arrival time, a spatial conflict risk coefficient is generated;

[0155] Based on the spatial conflict risk coefficient, the safety monitoring result is corrected.

[0156] In the embodiment, the predicted motion path is the position change trajectory of the target tower crane (or the conflict target) within a future period of time based on the current operation state data (such as the jib rotation angular velocity, amplitude change speed), for example, the movement route of the jib end within 10 minutes. The existing conflict target is an object that interferes with the target tower crane in space, including personnel below the tower crane and other tower crane jibs. Among them, the personnel below the tower crane are construction personnel within the working range of the target tower crane, which have the risk of falling of hoisted objects or collision of jibs; the other tower crane jibs are the jibs of other tower cranes on the construction site or the hoisted objects of the target tower crane jib intersecting and colliding.

[0157] In the embodiment, the position is the real-time coordinate of the conflict target, such as the GPS position of the personnel, the three-dimensional coordinate of the end of the other crane jib; the speed is the moving speed of the conflict target, such as the walking speed of the personnel, the rotating speed of the other jib; the motion trajectory is the position change record of the conflict target in the past period of time, which is used to predict the future motion path. The minimum prediction distance is the shortest path distance between the target crane and the conflict target (such as personnel, other jib) in the future preset time, the closer the distance, the higher the risk, for example, the closest distance between the two is 3 meters in 5 minutes, the smaller the distance, the higher the conflict risk. The time to reach the minimum prediction distance is the time when the path of the target crane and the conflict target reaches the minimum prediction distance, which represents the degree of risk urgency, the shorter the time, the more urgent the risk, for example, the closest distance will be reached in 2 minutes in the future, which is used to judge the degree of risk urgency. The space conflict risk coefficient is a comprehensive risk score based on the minimum prediction distance and the arrival time, which is obtained by querying from the space conflict risk mapping table, and the range is 0-10 points, which represents the risk level of the space interference between the target crane and the conflict target, the smaller the distance and the shorter the time, the higher the coefficient, for example, the minimum distance is 1 meter and the arrival time is 1 minute, the coefficient is 8 points. The safety monitoring result is the safety state evaluation obtained based on the parameters of the target crane itself (such as structural vibration, lifting weight). The corrected safety monitoring result is the original safety monitoring result adjusted by the space conflict risk coefficient, for example, the original safety monitoring result is low risk, and it is corrected to medium risk due to high conflict coefficient, so that the evaluation is more comprehensive.

[0158] From the above, it can be concluded that the embodiment can improve the accuracy of the tower crane construction safety monitoring result and more accurately evaluate the tower crane construction safety risk by obtaining the predicted motion path based on the target crane operating state data, identifying the surrounding conflict target based on the video monitoring data and obtaining the predicted motion path thereof, calculating the minimum prediction distance and the arrival time of the path in the future preset time to generate the space conflict risk coefficient, and then correcting the safety monitoring result.

[0159] In an embodiment of the present application, based on the minimum prediction distance and the arrival time, the space conflict risk coefficient is generated, comprising:

[0160] a preset space conflict risk mapping table based on distance and time;

[0161] inputting the calculated minimum prediction distance and the time to reach the minimum prediction distance into the space conflict risk mapping table to query the space conflict risk coefficient;

[0162] wherein, under the condition that the arrival time is the same, the smaller the minimum prediction distance, the greater the space conflict risk coefficient obtained by querying; under the condition that the minimum prediction distance is the same, the shorter the arrival time, the greater the space conflict risk coefficient obtained by querying.

[0163] In the embodiment, the space conflict risk mapping table is a two-dimensional mapping table preset in advance, taking the minimum prediction distance as the horizontal axis and the time to reach the minimum prediction distance as the vertical axis, each intersection point corresponding to a specific space conflict risk coefficient, ranging from 0 to 10 points, indicating the influence relationship of distance and time on risk. The space conflict risk coefficient is a comprehensive risk score obtained by querying the space conflict risk mapping table, ranging from 0 to 10 points, and the higher the score, the higher the risk.

[0164] From the above, in the embodiment, the minimum prediction distance and the time to reach the minimum prediction distance of the target tower crane prediction motion path and the existing conflict target prediction motion path are obtained, the space conflict risk coefficient is queried by using the preset space conflict risk mapping table, and the risk size can be accurately represented according to different conditions of distance and time, thereby the safety monitoring result is corrected, and the accuracy and reliability of the tower crane construction safety monitoring are improved.

[0165] In a specific embodiment, for example, in a large commercial complex project construction site, 5 tower cranes (numbered T1-T5) are arranged, T3 is the core construction area tower crane, responsible for hoisting key components of the main structure, the rated maximum lifting capacity is 10t, the service life is 3 years, and the current is in the main construction stage (high intensity operation period). There are 3 existing buildings (the nearest horizontal distance from T3 is 80m) around the construction site, and gusty weather often occurs during construction, so T3 needs to be monitored for safety.

[0166] Step 1: Obtain the multi-source data of T3 through the multi-source data acquisition terminal, as follows: sensor data: collected through sensors installed at various parts of T3, sampling frequency 10Hz. Including: stress sensor at the root of the hoisting arm (stress value 28MPa), vibration sensor at the top of the tower body (vibration frequency 3.2Hz, amplitude 0.8mm), hook weight sensor (lifting weight 6.5t), angle sensor (hoisting arm elevation angle 45°, rotation angle 120°), displacement sensor (tower body verticality deviation 0.3‰). Video monitoring data: high-definition camera (1920x1080 resolution, 25fps) under the cab captures the hoisting arm, hook and the area below; 3 fixed cameras on the construction site capture the T3 rotation range and the relative position with T2 and T4, and the video data is transmitted to the monitoring center through wireless transmission. Environmental data: construction site weather monitoring station collects data: wind speed 7.8m / s, wind direction northeast, environmental temperature 28℃, relative humidity 65%, visibility 1500m; laser radar scanning obtains obstacle data within 300m around, the existing building is 32m high, and the horizontal distance from T3 is 80m. Other tower crane data: T2 lifting weight 3.2t, rotation angle 80°, horizontal distance from T3 65m; T4 lifting weight 4.8t, rotation angle 150°, horizontal distance from T3 72m.

[0167] Step 2: Extract 3 types of running features of T3 by feature analysis module: running state features: according to sensor data and video monitoring data, it is determined that T3 is in heavy load stage (lifting weight 6.5t is greater than or equal to 30% x 10t = 3t), load rate 65%, structure stability is good (tower body perpendicularity deviation 0.3‰ is less than the allowable value 1‰, vibration amplitude 0.8mm is less than the safety value 2mm), current running speed: slewing speed 3° / s, luffing speed 0.5m / s. Importance features: T3 is located in the core construction area, undertakes the task of hoisting key components, and the importance level is high. Environmental risk features: wind speed 7.8m / s (medium risk), good visibility, medium density of surrounding obstacles (3 buildings), safe distance from T2 65m, safe distance from T4 72m.

[0168] Step 3: Monitoring strategy making: initial parameter determination: first monitoring threshold determination: according to the operating state characteristics (heavy load stage), query the predefined first mapping table to obtain the weight reference threshold 8t and the vibration reference threshold 1.2 mm; according to the environmental data (wind speed 7.8 m / s), correction, the first monitoring threshold of the weight is 7.5t, and the first monitoring threshold of the vibration is 1.0 mm. First monitoring frequency determination: T3 importance level is high, and the basic monitoring frequency is 1 time per second; currently, it is the main construction stage (high intensity operation), and the first monitoring frequency after adjustment is 1 time per 0.8 seconds. Operating weight characteristic and monitoring weight determination: the operating weight characteristic is determined based on the environmental risk characteristic, and the wind speed 7.8 m / s has a greater impact on the structural stability, so the monitoring weight is determined as the structural health weight. Monitoring threshold and frequency adjustment: since the monitoring weight is the structural health weight, the first monitoring threshold range is reduced based on the third step (structural parameter basic threshold step 10%, risk level coefficient 0.7, equipment attenuation coefficient 1.0, third step = 10% x 0.7 x 1.0 = 7%), the second monitoring threshold of the weight is 7.0t (7.5t x (1-7%)), and the second monitoring threshold of the vibration is 0.93 mm (1.0 mm x (1-7%)); the monitoring frequency of the structural vibration and stress parameters is increased based on the fourth step (slowly changing parameter basic frequency step 0.5 seconds, parameter change rate coefficient 1.2, computing power coefficient 0.9, fourth step = 0.5 x 1.2 x 0.9 = 0.54 seconds), and the second monitoring frequency is 1 time per 0.3 seconds (0.8 seconds-0.54 seconds, rounded to 0.3 seconds). Frequency secondary adjustment: T3 weight 6.5t is less than the first threshold 7t, and the wire rope swing amplitude 3° is less than the second threshold 5°, so the second monitoring frequency does not need to be adjusted, the final monitoring frequency is maintained at 1 time per 0.3 seconds, and the monitoring threshold is weight 7.0t, vibration 0.93 mm, and stress 35 MPa. Collaborative work strategy adjustment: calculate the safety influence degree of T3 with T2 and T4: first safety influence degree (spatial distance): T3 is 65m away from T2, scoring 60 points; and 72m away from T4, scoring 55 points. Second safety influence degree (operation overlap): T3 and T2 have an operation overlap ratio of 40%, scoring 60 points; and T3 and T4 have an operation overlap ratio of 35%, scoring 55 points. Third safety influence degree (historical events): T3 has no collision warning record with T2 and T4 in the past 3 months, scoring 10 points. Weighted calculation: current S1 (importance score 8 points) ≥ S2 (environmental risk score 6 points), weight distribution is spatial distance 0.5, operation overlap 0.3, and historical events 0.2. The safety influence degree of T3 with T2 is 60 x 0.5 + 60 x 0.3 + 10 x 0.2 = 30 + 18 + 2 = 50 points; and the safety influence degree of T3 with T4 is 55 x 0.5 + 55 x 0.3 + 10 x 0.2 = 27.5 + 16.5 + 2 = 46 points, both of which are less than the collaborative work risk threshold 60 points, and the risk prediction model does not need to be adjusted.

[0169] Step 4: Monitor the safety parameters of T3 by executing the monitoring strategy (lifting weight 7.0t, vibration 0.93mm, stress 35MPa; frequency 1 time / 0.3 seconds). After monitoring for 1 hour, the safety monitoring results are as follows: structural safety parameters: the stress of the lifting arm is stable at 28-30MPa (less than 35MPa), the vibration amplitude of the tower body is 0.8-0.9mm (less than 0.93mm), the verticality deviation is maintained at 0.3‰, and the steel wire rope wear is slight. Operating state parameters: the lifting weight is stable at 6.5t (less than 7.0t), the lifting height is 28m, the rotation angle fluctuates between 100-140°, the running speed is stable, the brake system response time is 0.2 seconds. Environmental related parameters: the wind speed in the operating range fluctuates between 7.5-8.2m / s, the distance from T2 is 63-67m, and the distance from T4 is 70-74m, all of which are greater than the safety distance threshold. Operation safety parameters: the driver's operation instruction response is timely, and the emergency stop button is effective. Preliminary conclusion: all safety parameters are within the monitoring threshold, and the safety monitoring result is normal.

[0170] Step 5: Based on the video data collected by the camera in the cockpit, the driver's facial feature data is extracted and input into the pre-trained convolutional neural network model to obtain a fatigue index of 3.2 points and a tension index of 2.8 points; the blinking frequency in unit time is calculated to be 18 times / minute, and the average closed eye duration is 0.3 seconds; through the OpenPose pose estimation algorithm detection, the head deviation angle is less than or equal to 5°. Weighted fusion calculation of the driver's risk factor: the current is in the heavy load stage, the weight distribution is fatigue index 0.3, tension index 0.2, blinking frequency 0.2, average closed eye duration 0.2, head deviation angle 0.1, driver's risk factor = 3.2x0.3+2.8x0.2+18x0.2 (standardized 0.3)+0.3x0.2 (standardized 0.4)+5x0.1 (standardized 0.1)=0.96+0.56+0.06+0.08+0.05=1.71 points, less than the preset risk threshold of 6 points, no need to adjust the monitoring strategy.

[0171] Step 6: Based on the T3 operating state data (rotation speed 3° / s, amplitude speed 0.5 m / s), the future 10-minute predicted motion path is calculated: the jib end will move from the current coordinates (X120, Y80, Z28) to (X150, Y90, Z32). Based on the video monitoring data, the conflict target is identified: there are 3 construction personnel (coordinates X125, Y75, Z0) under T3, walking at a speed of 1.2 m / s, with a motion trajectory in the northwest direction; the T2 jib end coordinates are (X90, Y70, Z25), with a predicted motion path in the northeast direction. The minimum predicted distance and arrival time are calculated: the minimum predicted distance between T3 jib and the construction personnel below is 8.5 m in the next 10 minutes, with an arrival time of 6 minutes; the minimum predicted distance between T3 and T2 jib is 58 m, with an arrival time of 8 minutes. The spatial conflict risk coefficient is generated: referring to the spatial conflict risk mapping table, the minimum distance of 8.5 m and the arrival time of 6 minutes correspond to a risk coefficient of 2.5 points (low risk); the minimum distance of 58 m and the arrival time of 8 minutes correspond to a risk coefficient of 1.8 points (low risk). The result is corrected: according to the spatial conflict risk coefficient (average 2.15 points), the initial safety monitoring result is corrected, and the final safety monitoring result is still normal.

[0172] Step 7: Risk assessment: based on the safety monitoring result (all parameters are normal) and the spatial conflict risk assessment (low risk), it is determined that the current construction risk level of T3 is low risk, with no safety hazards such as structural overload and collision. Risk avoidance strategy: immediate strategy: maintain the current monitoring frequency and threshold, continuously monitor the wind speed change (if the wind speed is greater than 10 m / s, reduce the lifting weight to less than 5 t); remind the construction personnel below to stay away from the area within 5 m below the lifted object. Collaborative strategy: inform the T2 and T4 operators to pay attention to the relative position with T3 to avoid entering the overlapping operation area at the same time. Long-term strategy: regularly check the lifting arm stress sensor and wire rope wear condition, and calibrate the verticality detection equipment before daily construction.

[0173] Through this complete monitoring process, the overall perception and accurate monitoring of the T3 tower crane operating state are realized, with a monitoring data coverage rate of 100% and an abnormal response time of less than or equal to 0.5 seconds, effectively avoiding the risk omission problem caused by single data monitoring, and ensuring the safe operation of the tower crane in the core construction area. At the same time, based on the actual operating conditions, the monitoring strategy is dynamically adjusted to avoid resource waste caused by excessive monitoring, and the construction safety management efficiency is improved.

[0174] The tower crane construction safety monitoring method corresponding to the above embodiment, Figure 2 A structural block diagram of a tower crane construction safety monitoring system according to an embodiment of the present application is provided. For ease of illustration, only parts related to the embodiments of the present application are shown. For reference Figure 2The tower crane construction safety monitoring system 20 includes: a data acquisition module 21, a feature analysis module 22, a strategy generation module 23, a monitoring execution module 24, and a monitoring evaluation module 25.

[0175] Among them, the data acquisition module 21 is used to acquire multi-source data of the target tower crane, including sensor data, video surveillance data, and environmental data;

[0176] The feature analysis module 22 is used to determine multiple operational features of the target tower crane based on multi-source data; the multiple operational features include operational status features, importance features, and environmental risk features;

[0177] The strategy generation module 23 is used to determine the monitoring strategy for the target tower crane based on multiple operational characteristics;

[0178] The monitoring execution module 24 is used to monitor the safety parameters of the target tower crane based on the monitoring strategy and obtain the safety monitoring results;

[0179] The monitoring and assessment module 25 is used to conduct risk assessments based on security monitoring results and generate risk avoidance strategies.

[0180] The target tower crane is one of several tower cranes at the construction site.

[0181] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the data acquisition module 21, feature analysis module 22, strategy generation module 23, monitoring execution module 24, and monitoring evaluation module 25 are shown.

[0182] It should be appreciated that in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0183] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a speaker, etc.

[0184] The memory 304 can include a read-only memory and a random access memory, and provide instructions and data for the processor 301. A portion of the memory 304 can also include a non-volatile random access memory. For example, the memory 304 can also store device type information.

[0185] In specific implementations, the processor 301, the input device 302 and the output device 303 described in the embodiments of the present application can execute the implementation manner described in any embodiment of the tower crane construction safety monitoring method provided by the embodiments of the present application, and can also execute the implementation manner of the electronic device described in the embodiments of the present application, which will not be described here again.

[0186] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0187] The computer readable storage medium can be an internal storage unit of the electronic device of any of the preceding embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0188] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0189] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0190] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic, and the division of units is merely logical function division, and there can be other division manners in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between units can be indirect coupling or communication connection through some interfaces, or can be electrical, mechanical or other forms of connection.

[0191] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0192] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0193] The above is merely specific embodiments of the present application, and the protection scope of the present application is not limited thereto, and any modification or replacement within the technical scope disclosed in the present application can be easily thought by those skilled in the art, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for monitoring the safety of a tower crane construction, characterized in that The method comprises: acquiring multi-source data of a target tower crane, the multi-source data comprising sensor data, video monitoring data, and environmental data; determining a plurality of operating characteristics of the target tower crane based on the multi-source data; the plurality of operating characteristics comprising operating state characteristics, importance characteristics, and environmental risk characteristics; determining a monitoring strategy for the target tower crane based on the plurality of operating characteristics, comprising: determining a first monitoring threshold for the target tower crane based on the operating state characteristics of the target tower crane; determining a first monitoring frequency for the target tower crane based on the importance characteristics of the target tower crane; determining a monitoring bias for the target tower crane based on the operating bias characteristics of the target tower crane; adjusting the first monitoring threshold based on the monitoring bias to obtain a second monitoring threshold; adjusting the first monitoring frequency based on the monitoring bias to obtain a second monitoring frequency; determining the monitoring strategy for the target tower crane based on the second monitoring threshold and the second monitoring frequency; if the lifting capacity of the target tower crane is greater than a first threshold and the swing amplitude of the steel wire rope is less than a second threshold, reducing the second monitoring frequency based on a first step to obtain a third monitoring frequency; if the lifting capacity of the target tower crane is less than the first threshold and the swing amplitude of the steel wire rope is greater than the second threshold, increasing the second monitoring frequency based on a second step to obtain a third monitoring frequency; monitoring safety parameters of the target tower crane based on the monitoring strategy to obtain a safety monitoring result; performing risk assessment based on the safety monitoring result and generating a risk avoidance strategy; wherein the target tower crane is one of a plurality of tower cranes in a construction site; determining the first monitoring threshold for the target tower crane based on the operating state characteristics of the target tower crane, comprising: determining a corresponding operating phase based on the operating state characteristics of the target tower crane; determining a corresponding reference threshold based on the operating phase and a predefined first mapping table; correcting the reference threshold based on environmental data to generate the first monitoring threshold; determining the first monitoring frequency for the target tower crane based on the importance characteristics of the target tower crane, comprising: determining a basic monitoring frequency according to the importance level of the target tower crane in the construction layout; adjusting the basic monitoring frequency based on the current construction phase to generate the first monitoring frequency; determining the monitoring bias for the target tower crane based on the operating bias characteristics of the target tower crane, comprising: calculating the operating bias characteristics based on the environmental risk characteristics of the target tower crane, wherein the environmental risk characteristics comprise wind speed, visibility, surrounding obstacle density, and safety distance from other tower cranes; determining a monitoring bias according to the operating bias characteristics, the monitoring bias comprising a structure health bias and a collision warning bias; The first monitoring threshold is adjusted based on the monitoring bias to obtain a second monitoring threshold, and the first monitoring frequency is adjusted based on the monitoring bias to obtain a second monitoring frequency, including: if the monitoring bias is the structure health bias, increasing the first monitoring frequency of structure vibration and stress parameters based on a fourth step size to obtain the second monitoring frequency, and decreasing the allowable range of the first monitoring threshold based on a third step size to obtain the second monitoring threshold; if the monitoring bias is the collision warning bias, decreasing the first monitoring threshold of amplitude and height parameters based on the third step size to obtain the second monitoring threshold, and increasing the first monitoring frequency of position detection based on the fourth step size to obtain the second monitoring frequency.

2. The tower crane construction safety monitoring method according to claim 1, characterized in that, Also includes: Based on the environmental data and the operating state data of other tower cranes in the multi-source data, determine the safety influence degree between multiple tower cranes; In response to the safety monitoring result being abnormal for the target tower crane, adjust the monitoring strategy corresponding to the target tower crane based on the safety influence degree; For the other tower cranes whose safety influence degree is greater than a preset influence threshold, calculate an influence coefficient; Based on the influence coefficient, calculate a fifth step size; Increase the monitoring frequency of the other tower cranes based on the fifth step size.

3. The tower crane construction safety monitoring method according to claim 2, characterized in that, The safety influence degree between multiple tower cranes is determined based on the environmental data and the operating state data of other tower cranes in the multi-source data, including: Determine a first safety influence degree based on the spatial distance between tower cranes, wherein the spatial distance is calculated based on the safety distance of the environmental risk features from other tower cranes; Determine a second safety influence degree based on the overlap degree of tower crane operation areas; Determine a third safety influence degree based on historical collision or interference events; Weighted calculation is performed on the first safety influence degree, the second safety influence degree, and the third safety influence degree to obtain the safety influence degree; wherein the weighting coefficients are determined based on the importance features and the environmental risk features of the target tower crane.

4. The tower crane construction safety monitoring method according to claim 2, characterized in that, The monitoring strategy of the target tower crane is determined based on the multiple operating features, further including: When the safety influence degree is greater than a cooperative operation risk threshold, a risk prediction value of the target tower crane is obtained based on the multiple operating features through a risk prediction model; The first monitoring threshold and the first monitoring frequency are determined based on the risk prediction value to form the monitoring strategy.

5. A monitoring system for operating the tower crane construction safety monitoring method according to any one of claims 1 to 4, characterized by It includes: A data acquisition module is configured to acquire multi-source data of a target tower crane, the multi-source data including sensor data, video monitoring data, environmental data, and operating state data of other tower cranes; A feature analysis module is configured to determine multiple operating features of the target tower crane based on the multi-source data; the operating features include operating state features, importance features, and environmental risk features; A strategy generation module is configured to determine a monitoring strategy of the target tower crane based on the multiple operating features; A monitoring execution module is configured to monitor safety parameters of the target tower crane based on the monitoring strategy to obtain a safety monitoring result; A monitoring evaluation module is configured to perform risk assessment based on the safety monitoring result and generate a risk avoidance strategy; The target tower crane is one of a plurality of tower cranes in a construction site. The target tower crane is one of a plurality of tower cranes in a construction site.

Images