An intelligent construction method and construction system of prefabricated building

Abstract

The present invention discloses an intelligent construction method and a construction system for prefabricated buildings, comprising dividing the prefabricated buildings into a number of different construction steps, performing different forms of sampling processing on each different construction step, judging whether the different construction steps are in an abnormal state of construction progress and whether the quality monitoring parameters exceed or are below a preset value interval, and performing construction steps on the different construction steps in the abnormal state of construction progress and the quality monitoring parameters exceeding or below the preset value interval to avoid unqualified installation precision in other different construction steps; and also using a graph neural network algorithm to check each lifting equipment, assembly equipment, and transportation equipment in the quality monitoring parameters exceeding or below the preset value interval to determine the locations of unqualified installation precision therein. The method improves the inspection efficiency and accuracy of prefabricated buildings and ensures the construction rhythm of prefabricated buildings.

Description

Technical Field

[0001] The present invention relates to the field of prefabricated building construction, and in particular to an intelligent construction method and a construction system of a prefabricated building. Background Art

[0002] Prefabricated buildings have been widely promoted in the global construction industry due to their high efficiency, energy saving and environmental protection. However, in traditional construction methods, the production, transportation, hoisting and assembly of modules often have problems such as high manual participation, information isolation and difficulty in ensuring accuracy. This not only limits the large-scale application of prefabricated buildings, but also leads to low construction efficiency, uncontrollable costs and unstable construction quality. In addition, modern construction needs are developing towards high-rise and complex construction, and construction scenes have put forward higher requirements for accuracy, speed and safety. In this context, the introduction of intelligent construction methods and systems has become an inevitable trend, and the bottlenecks in traditional construction methods have been solved through technical means.

[0003] At present, prefabricated building construction mainly relies on lifting equipment and manual collaboration for modular assembly. Although these methods have solved some of the complexities of on-site construction, they have significant disadvantages: first, low efficiency. Module lifting and assembly rely on manual command and alignment, which can easily lead to construction delays due to poor communication or human errors; second, insufficient accuracy. Traditional equipment cannot monitor the position and angle of the module in real time, which can easily lead to problems such as misalignment or unstable connection; third, lack of real-time data support. The existing construction process does not monitor the environment, equipment and module status sufficiently, making it difficult to adjust the construction plan in a timely manner, especially when multiple devices are collaborating. There is a lack of intelligent scheduling capabilities. In addition, complex on-site conditions and changing environmental factors further increase the difficulty of construction management. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides an intelligent construction method and a construction system for a prefabricated building.

[0005] The present invention provides an intelligent construction method for prefabricated buildings, comprising the following steps:

[0006] Step S1, dividing the prefabricated building into several different construction steps, and connecting a multimodal building real-time data monitoring sensor to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step; and judging whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors;

[0007] Step S2, performing construction step efficiency judgment processing on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and performing splicing gap size collection processing on each different construction step in an abnormal construction progress state, to obtain construction period influencing factors between different construction steps in an abnormal construction progress state; judging whether the different construction steps in an abnormal construction progress state belong to a quality monitoring parameter exceeding or falling below a preset value interval according to the construction period influencing factors;

[0008] Step S3, according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval, the corresponding construction step status of different construction steps in the abnormal construction progress state is adjusted; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained;

[0009] Step S4, predicting and processing the verticality and flatness data to determine the installation accuracy unqualified positions where the quality monitoring parameters exceed or fall below the preset value interval;

[0010] After the construction step efficiency is judged for the location where the installation accuracy is unqualified, the working state of the multimodal building real-time data monitoring sensor is adjusted.

[0011] In one embodiment disclosed in the present application, in step S1, the prefabricated building is divided into several different construction steps, and a multimodal building real-time data monitoring sensor is connected to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step, including:

[0012] Obtaining the operation coordination time of all lifting equipment, assembly equipment, and transportation equipment in the prefabricated building, dividing the prefabricated building into a number of different construction steps according to the operation coordination time, and identifying the working status of the common lifting equipment, assembly equipment, and transportation equipment between different construction steps, and determining the unqualified installation accuracy deviation of all the common lifting equipment, assembly equipment, and transportation equipment in the prefabricated building;

[0013] A multimodal building real-time data monitoring sensor is connected to each different construction step to collect and process component positioning errors, and all bolt torque data and all welding temperature and time data of each multimodal building real-time data monitoring sensor in unit time are obtained, which are used as the factors affecting the construction progress.

[0014] In one embodiment disclosed in the present application, in the step S1, judging whether the different construction steps are in an abnormal state of construction progress according to the construction progress influencing factors includes:

[0015] The long short-term memory network is used to predict all bolt torque data and all welding temperature and time data, and the fluctuation range of bolt torque data and welding temperature and time data corresponding to different construction steps in the first unit time is determined;

[0016] If the fluctuation range of the bolt torque data or the fluctuation range of the welding temperature and time data is greater than the preset data fluctuation threshold, it is judged that the different construction steps are in an abnormal construction progress state; otherwise, it is judged that the different construction steps are not in an abnormal construction progress state.

[0017] In one embodiment disclosed in the present application, in the step S2, a construction step efficiency judgment process is performed on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and a splicing gap size collection process is performed on each different construction step in an abnormal construction progress state, and the construction period influencing factors between different construction steps in an abnormal construction progress state are obtained, including:

[0018] According to the respective integrity of all the shared lifting equipment, assembly equipment, and transportation equipment of different construction steps in an abnormal construction progress state, all the shared lifting equipment, assembly equipment, and transportation equipment are switched to a standby state, and the abnormal causes of the different construction steps in an abnormal construction progress state are found; the integrity is detected by the working state of the lifting equipment, assembly equipment, and transportation equipment. When the lifting equipment, assembly equipment, and transportation equipment are damaged, the working state will be abnormal. The judgment includes the lifting speed, assembly efficiency, and equipment scheduling of the lifting equipment, assembly equipment, and transportation equipment;

[0019] The size of the splicing gap is collected and processed for each different construction step in an abnormal construction progress state, and the influence range of the time error and failure rate of the coordination between the different internal lifting equipment, assembly equipment and transportation equipment in the different construction steps in an abnormal construction progress state are obtained, which is used as the influencing factor of the construction period.

[0020] In one embodiment disclosed in the present application, in the step S2, judging whether different construction steps in the abnormal construction progress state belong to the quality monitoring parameters exceeding or falling below the preset value range according to the construction period influencing factors includes:

[0021] Analyze the time error of coordination and determine whether the workload of different lifting equipment, assembly equipment, and transportation equipment working together includes the risk factor of mechanical structure damage;

[0022] The influence range of the failure rate is predicted and processed to determine whether all workloads with mechanical structure damage risk factors have the same failure rate within the operation cycle of the prefabricated building; if so, it is judged that the different construction steps in the abnormal construction progress state belong to the quality monitoring parameters exceeding or falling below the preset value range; otherwise, it is judged that the different construction steps in the abnormal construction progress state do not belong to the quality monitoring parameters exceeding or falling below the preset value range.

[0023] In one embodiment disclosed in the present application, in step S3, according to the judgment result of whether the quality monitoring parameter exceeds or falls below the preset value range, the construction step status of the corresponding different construction steps in the abnormal construction progress state is adjusted, specifically including:

[0024] When the quality monitoring parameters of different construction steps in the abnormal construction progress state do not exceed or fall below the preset value range, all the shared lifting equipment, assembly equipment, and transportation equipment of the different construction steps in the abnormal construction progress state are switched to the operating state according to their respective integrity levels;

[0025] When the quality monitoring parameters of different construction steps that are in an abnormal construction progress state exceed or fall below the preset value range, the current standby status of all shared lifting equipment, assembling equipment, and transport equipment of the different construction steps that are in an abnormal construction progress state shall be kept unchanged according to the respective integrity levels of all shared lifting equipment, assembling equipment, and transport equipment.

[0026] In one embodiment disclosed in the present application, in step S3, the graph neural network algorithm is used to judge the time interval of the construction process when the quality monitoring parameter exceeds or is lower than the preset value interval, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeds or is lower than the preset value interval are obtained. The quality monitoring parameter is set in the graph neural network algorithm and compared with the preset value set in advance, so as to judge the time interval of the construction process. Because the carrying capacity of the construction process is limited, when the quality monitoring parameter is too large, the rotor stator coil will be damaged, resulting in a time interval condition, which specifically includes:

[0027] According to the quality monitoring parameter exceeding or falling below the preset value interval containing the unqualified installation accuracy deviation of each multimodal building real-time data monitoring sensor, a measurement request instruction is sent to each multimodal building real-time data monitoring sensor respectively, and the verticality and flatness data of the response of each multimodal building real-time data monitoring sensor regarding the measurement request instruction are sampled and intercepted, and the response verticality and flatness data are fed back to the graph neural network algorithm.

[0028] In one embodiment disclosed in the present application, in the step S4, the verticality and flatness data are predicted and processed to determine the installation accuracy unqualified position where the quality monitoring parameter exceeds or falls below the preset value interval, specifically including:

[0029] Decompile the response verticality and flatness data to obtain the installation accuracy failure occurrence time of the response verticality and flatness data of each multi-modal building real-time data monitoring sensor;

[0030] The time when the unqualified installation accuracy occurs is predicted to determine whether there is a time error when the unqualified installation accuracy occurs; if so, the corresponding multimodal building real-time data monitoring sensor is determined to belong to a location with unqualified installation accuracy; and the quality monitoring parameter is determined to be greater than or less than the unqualified installation accuracy deviation of all locations with unqualified installation accuracy in a preset value interval and the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to locations with unqualified installation accuracy.

[0031] In one embodiment disclosed in the present application, in the step S4, after the construction step efficiency judgment processing is performed on the location where the installation accuracy is unqualified, the working state of the multimodal building real-time data monitoring sensor is adjusted, specifically including:

[0032] According to the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy positions in the range where the quality monitoring parameter exceeds or is lower than the preset value, all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy positions are checked for unqualified installation accuracy;

[0033] According to the unqualified installation accuracy deviation of all the unqualified installation accuracy positions in the preset value interval where the quality monitoring parameter exceeds or falls below, the unqualified installation accuracy deviation of all the lifting equipment, assembly equipment, and transportation equipment connected to all the unqualified installation accuracy positions is determined, so that all the lifting equipment, assembly equipment, and transportation equipment connected to all the unqualified installation accuracy positions are switched to the standby state, thereby performing construction step efficiency judgment processing on all the unqualified installation accuracy positions; and then adjusting the working state of the multimodal building real-time data monitoring sensor.

[0034] The present invention also provides an intelligent construction system for prefabricated buildings, comprising:

[0035] The module for dividing different construction steps and integrating data is used to divide the prefabricated building into several different construction steps, and connect the multimodal building real-time data monitoring sensor to each different construction step to collect and process the component positioning error, so as to obtain the factors affecting the construction progress of each different construction step;

[0036] A construction progress abnormality judgment module, used to judge whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors;

[0037] A construction period influencing factor module is used to perform construction step efficiency judgment processing on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and to collect and process the size of the splicing gap for each different construction step in an abnormal construction progress state, so as to obtain the construction period influencing factors between the different construction steps in an abnormal construction progress state;

[0038] A quality monitoring parameter judgment module is used to judge whether the quality monitoring parameters of different construction steps in the abnormal construction progress state exceed or fall below the preset value range according to the construction period influencing factors;

[0039] A construction process time interval judgment module is used to adjust the construction step status of different construction steps in an abnormal construction progress state according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained;

[0040] An installation accuracy unqualified position judgment module is used to predict and process the verticality and flatness data to determine the installation accuracy unqualified position where the quality monitoring parameter exceeds or falls below a preset value interval;

[0041] The construction step state adjustment module is used to adjust the working state of the multimodal building real-time data monitoring sensor after performing construction step efficiency judgment processing on the location where the installation accuracy is unqualified.

[0042] The beneficial effects of the present invention are:

[0043] Compared with the prior art, the intelligent construction method and construction system of prefabricated buildings divide the prefabricated buildings into several different construction steps, perform different forms of sampling processing on each different construction step, judge whether the different construction steps are in an abnormal state of construction progress and whether the quality monitoring parameters exceed or fall below the preset value interval, and perform construction steps on the different construction steps in the abnormal state of construction progress and the quality monitoring parameters exceed or fall below the preset value interval, so as to avoid the occurrence of unqualified installation accuracy in other different construction steps; and also use the graph neural network algorithm to check each lifting equipment, assembly equipment, and transportation equipment in the quality monitoring parameters exceeding or falling below the preset value interval to determine The locations with unqualified installation accuracy are divided into different construction steps and the construction step status of all other different construction steps in the prefabricated building to be constructed. The corresponding multimodal building real-time data monitoring sensors are quickly and accurately located by dividing the prefabricated buildings into different construction steps and sampling and checking the zones, so as to timely avoid the unqualified installation accuracy locations from affecting the normal operation of other multimodal building real-time data monitoring sensors in the prefabricated buildings. The monitoring of the construction process and the working status of lifting equipment, assembly equipment, and transportation equipment is effectively realized, and the inspection efficiency and accuracy of prefabricated buildings are improved, and the construction rhythm of prefabricated buildings is ensured. The intelligent construction method effectively makes up for the shortcomings of traditional methods by introducing automation and information technology. It combines precision sensors and cutting-edge technologies of intelligent lifting equipment to achieve high-precision positioning and rapid assembly of modules. With the help of digital management platforms and big data technologies, equipment scheduling, real-time monitoring and feedback during the construction process can be realized. In addition, the intelligent system can dynamically optimize the construction plan according to the real-time conditions of the construction site, thereby reducing manual participation and improving efficiency and quality. Compared with traditional methods, intelligent construction methods can not only greatly improve the efficiency and safety of prefabricated building construction, but also lay the foundation for the comprehensive promotion of intelligent buildings in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of an intelligent construction method for prefabricated buildings provided by the present invention;

[0045] Figure 2 A block diagram of the module composition of an intelligent construction system for prefabricated buildings provided by the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] like Figure 1 FIG. 1 is a flow chart of an intelligent construction method for a prefabricated building provided by an embodiment of the present invention. The intelligent construction method for a prefabricated building comprises the following steps:

[0048] Step S1, dividing the prefabricated building into several different construction steps, and connecting a multimodal building real-time data monitoring sensor to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step; and judging whether the different construction step is in an abnormal construction progress state according to the construction progress influencing factors;

[0049] Step S2, performing construction step efficiency judgment processing on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and performing splicing gap size collection processing on each different construction step in an abnormal construction progress state, to obtain construction period influencing factors between different construction steps in an abnormal construction progress state; judging whether the different construction steps in an abnormal construction progress state belong to a quality monitoring parameter exceeding or falling below a preset value interval according to the construction period influencing factors;

[0050] Step S3, according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval, the construction step status of the corresponding different construction steps in the abnormal construction progress state is adjusted; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained;

[0051] Step S4, predicting and processing the verticality and flatness data, determining the unqualified installation accuracy position where the quality monitoring parameter exceeds or is lower than the preset value interval; after judging the construction step efficiency of the unqualified installation accuracy position, adjusting the working state of the multimodal building real-time data monitoring sensor.

[0052] The beneficial effects of the above technical scheme are as follows: the intelligent construction method and construction system of the prefabricated building divide the prefabricated building into several different construction steps, perform different forms of sampling processing on each different construction step, judge whether the different construction steps are in an abnormal state of construction progress and whether the quality monitoring parameters exceed or are below the preset value interval, and perform construction steps on the different construction steps in the abnormal state of construction progress and the quality monitoring parameters exceed or are below the preset value interval, so as to avoid the occurrence of unqualified installation accuracy in other different construction steps; the graph neural network algorithm is also used to check each unqualified installation accuracy position in the interval where the quality monitoring parameters exceed or are below the preset value, determine the unqualified installation accuracy position therein, perform separate construction steps on the unqualified installation accuracy position and the construction step status of all other different construction steps in the prefabricated building to be constructed, and quickly and accurately locate the corresponding multimodal building real-time data monitoring sensor by dividing the prefabricated building into different construction steps and sampling and checking the zones, timely avoid the unqualified installation accuracy position affecting the normal operation of other multimodal building real-time data monitoring sensors in the prefabricated building, improve the inspection efficiency and accuracy of the prefabricated building, and ensure the safety and stability of the overall work of the prefabricated building.

[0053] Preferably, the multimodal building real-time data monitoring sensor includes a variety of sensing devices for position, geometry, mechanics, environment and quality monitoring. In terms of position and attitude monitoring, it mainly includes GNSS positioning sensors, inertial measurement units (IMUs) and laser positioning sensors to ensure accurate positioning and attitude control of modules during transportation and installation; in geometric measurement, laser scanning sensors, structured light sensors and ultrasonic sensors are used to collect module joint gap size and surface shape data to evaluate assembly accuracy.

[0054] In addition, mechanical and environmental monitoring sensors include pressure sensors, strain sensors, wind speed sensors, and temperature and humidity sensors to ensure construction safety and stability. Quality monitoring relies on laser verticality sensors and flatness sensors to measure the installation accuracy of the modules; at the same time, high-definition cameras and infrared thermal imagers are used for dynamic image recording and material defect detection, and RFID sensors and wireless communication modules are used to achieve information tracking and real-time data transmission. Through the comprehensive use of multimodal sensors, the construction system can fully monitor and optimize the construction process.

[0055] Preferably, in step S1, the prefabricated building is divided into several different construction steps, and a multimodal building real-time data monitoring sensor is connected to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step, including:

[0056] Obtain the operation coordination time of all lifting equipment, assembly equipment, and transportation equipment in the prefabricated building, divide the prefabricated building into several different construction steps according to the operation coordination time, and identify the working status of the common lifting equipment, assembly equipment, and transportation equipment between different construction steps, and determine the unqualified installation accuracy deviation of all common lifting equipment, assembly equipment, and transportation equipment in the prefabricated building;

[0057] For each different construction step, a multimodal building real-time data monitoring sensor is connected to collect and process the component positioning error, and all bolt torque data and all welding temperature and time data of each multimodal building real-time data monitoring sensor in unit time are obtained, which are used as the factors affecting the construction progress.

[0058] The beneficial effects of the above technical solution are as follows: the prefabricated building includes several lifting equipment, assembly equipment, transportation equipment and several multimodal building real-time data monitoring sensors, each of which is connected to the corresponding lifting equipment, assembly equipment and transportation equipment, and together constitutes the corresponding prefabricated building structure. According to the operation connection structure of all lifting equipment, assembly equipment and transportation equipment in the prefabricated building, the prefabricated building is divided into areas to obtain several different construction steps, so that each different construction step is subsequently sampled as a separate prefabricated building area, thereby improving the sampling reliability of each different construction step. Among them, some lifting equipment, assembling equipment and transport equipment are used as shared lifting equipment, assembling equipment and transport equipment to realize the connection between different construction steps. The working status of each shared lifting equipment, assembling equipment and transport equipment is identified, and the unqualified deviation of the installation accuracy of each shared lifting equipment, assembling equipment and transport equipment in the prefabricated building is determined. This is convenient for the subsequent switching of the shared lifting equipment, assembling equipment and transport equipment between the standby state and the operating state based on the shared lifting equipment, assembling equipment and transport equipment, so as to quickly realize the construction step efficiency judgment and processing of each different construction step.

[0059] Preferably, in step S1, judging whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors includes:

[0060] The long short-term memory network is used to predict all bolt torque data and all welding temperature and time data, and the fluctuation range of bolt torque data and welding temperature and time data corresponding to different construction steps in the first unit time is determined;

[0061] If the fluctuation range of the bolt torque data or the fluctuation range of the welding temperature and time data is greater than the preset data fluctuation threshold, it is judged that the different construction steps are in an abnormal construction progress state; otherwise, it is judged that the different construction steps are not in an abnormal construction progress state.

[0062] The beneficial effect of the above technical solution is: when the data fluctuation of the multimodal building real-time data monitoring sensor suddenly increases in a short period of time, it indicates that the multimodal building real-time data monitoring sensor may have an abnormal operation. All bolt torque data and all welding temperature and time data obtained by sampling the multimodal building real-time data monitoring sensor contained in each different construction step are predicted and processed using a long short-term memory network to obtain the bolt torque / welding temperature and time data fluctuation range of the different construction steps as a whole in the first unit time, so as to judge whether there is an abnormal situation in which the data flow of different construction steps exceeds or is lower than the preset value range, thereby realizing accurate distinction and identification of whether each different construction step is abnormal or not.

[0063] Preferably, in step S2, the construction step efficiency judgment process is performed on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and the splicing gap size collection process is performed on each different construction step in an abnormal construction progress state, so as to obtain the construction period influencing factors between the different construction steps in an abnormal construction progress state, including:

[0064] According to the integrity of all the shared lifting equipment, assembly equipment, and transportation equipment of different construction steps in abnormal construction progress, all the shared lifting equipment, assembly equipment, and transportation equipment are switched to the standby state, so as to find the abnormal causes of the different construction steps in abnormal construction progress; the integrity detection can be carried out through the working state of the lifting equipment, assembly equipment, and transportation equipment. When the lifting equipment, assembly equipment, and transportation equipment are damaged, the working state will be abnormal. The judgment content includes the lifting speed, assembly efficiency, and equipment scheduling of the lifting equipment, assembly equipment, and transportation equipment;

[0065] The size of the splicing gap is collected and processed for each different construction step in an abnormal construction progress state, and the influence range of the time error and failure rate of the coordination between different internal lifting equipment, assembly equipment and transportation equipment in different construction steps in an abnormal construction progress state are obtained, which is used as the influencing factor of the construction period.

[0066] The beneficial effects of the above technical solution are: through the above method, the installation accuracy unqualified deviations of all common lifting equipment, assembly equipment, and transportation equipment associated with different construction steps in an abnormal state of construction progress are determined, so that all related common lifting equipment, assembly equipment, and transportation equipment can be switched to a standby state based on the installation accuracy unqualified deviations, thereby realizing the construction steps of different construction steps in an abnormal state of construction progress, avoiding data interaction between different construction steps in an abnormal state of construction progress and other different construction steps. In addition, for different construction steps in an abnormal state of construction progress, separate splicing gap size collection and processing can be performed specifically, effectively reducing the workload of splicing gap size collection and processing and ensuring the data sampling reliability of splicing gap size collection and processing.

[0067] Preferably, in step S2, judging whether different construction steps in the abnormal construction progress state belong to the quality monitoring parameters exceeding or falling below the preset value range according to the construction period influencing factors includes:

[0068] Analyze the time error of the coordination and determine whether the workload of different lifting equipment, assembly equipment, and transportation equipment working together includes the risk factor of mechanical structure damage;

[0069] The influence range of the failure rate is predicted and processed to determine whether all workloads with mechanical structure damage risk factors have the same failure rate within the operation cycle of the prefabricated building; if so, it is judged that the different construction steps in the abnormal construction progress state belong to the range where the quality monitoring parameters exceed or are lower than the preset value; otherwise, it is judged that the different construction steps in the abnormal construction progress state do not belong to the range where the quality monitoring parameters exceed or are lower than the preset value.

[0070] The beneficial effects of the above technical solution are: through the above method, the content analysis of the working load obtained by collecting and processing the splicing gap size is carried out to determine whether the working load contains risk factors for mechanical structure damage; wherein the risk factors for mechanical structure damage may be but are not limited to the characteristics corresponding to the unqualified installation accuracy of the predetermined type; and the failure rate of the working load is also identified to determine whether the failure rates of all working loads with risk factors for mechanical structure damage are the same or not, so as to reliably identify and judge whether the current different construction steps belong to the quality monitoring parameters exceeding or falling below the preset value range.

[0071] Preferably, in step S3, according to the judgment result of whether the quality monitoring parameter exceeds or falls below the preset value range, the construction step status of the corresponding different construction steps in the abnormal construction progress state is adjusted, specifically including:

[0072] When the quality monitoring parameters of different construction steps in the abnormal construction progress state do not exceed or fall below the preset value range, all the shared lifting equipment, assembly equipment, and transportation equipment of the different construction steps in the abnormal construction progress state are switched to the operating state according to their respective integrity levels;

[0073] When the quality monitoring parameters of different construction steps that are in an abnormal construction progress state exceed or fall below the preset value range, the current standby status of all shared lifting equipment, assembling equipment, and transport equipment of the different construction steps that are in an abnormal construction progress state shall be kept unchanged according to the respective integrity levels of all shared lifting equipment, assembling equipment, and transport equipment.

[0074] The beneficial effects of the above technical solution are: through the above method, all the associated shared lifting equipment, assembly equipment, and transportation equipment whose quality monitoring parameters exceed or are lower than the preset value range are kept in the current waiting state unchanged, and all the associated shared lifting equipment, assembly equipment, and transportation equipment of different construction steps whose non-quality monitoring parameters exceed or are lower than the preset value range are switched to the running state, which can further narrow the inspection scope of different construction steps in the prefabricated building, thereby reducing the workload of subsequent sampling processing and ensuring that other non-quality monitoring parameters exceed or are lower than the preset value range. Different construction steps are connected to the Internet in time to ensure the normal operation of the prefabricated building.

[0075] Preferably, in step S3, the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or falling below the preset value interval by using a graph neural network algorithm, and the verticality and flatness data from each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or falling below the preset value interval is obtained, specifically including:

[0076] According to the quality monitoring parameter exceeding or falling below the preset value interval containing the unqualified installation accuracy deviation of each multimodal building real-time data monitoring sensor, a measurement request instruction is sent to each multimodal building real-time data monitoring sensor respectively, and the verticality and flatness data of each multimodal building real-time data monitoring sensor in response to the measurement request instruction are sampled and intercepted, and the response feedback to the graph neural network algorithm is fed back.

[0077] The beneficial effects of the above technical solution are: through the above method, the quality monitoring parameters exceeding or lower than the preset value range of the multimodal building real-time data monitoring sensor are calibrated for the unqualified installation accuracy deviation, and by setting the graph neural network algorithm to induce each multimodal building real-time data monitoring sensor to interact with the graph neural network algorithm, it is convenient to further identify whether each multimodal building real-time data monitoring sensor belongs to the installation accuracy unqualified position.

[0078] Preferably, in step S4, the verticality and flatness data are predicted and processed to determine the installation accuracy unqualified position where the quality monitoring parameter exceeds or falls below the preset value interval, specifically including:

[0079] The response verticality and flatness data are decompiled to obtain the installation accuracy failure occurrence time of the response verticality and flatness data of each multi-modal building real-time data monitoring sensor;

[0080] The time when the unqualified installation accuracy occurs is predicted to determine whether there is a time error when the unqualified installation accuracy occurs; if so, the corresponding multimodal building real-time data monitoring sensor is determined to be a location where the installation accuracy is unqualified; and the quality monitoring parameter is determined to be greater than or less than the unqualified installation accuracy deviation of all locations where the installation accuracy is unqualified in the preset value interval and the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to the locations where the installation accuracy is unqualified.

[0081] The beneficial effects of the above technical solution are: by decompiling the response verticality and flatness data fed back by each multimodal building real-time data monitoring sensor and identifying the time when the installation precision is unqualified, it is possible to accurately identify the unqualified installation precision positions that exist in the range where the quality monitoring parameters exceed or fall below the preset value, and thereby identify the unqualified installation precision positions and the unqualified installation precision deviations of the non-unqualified installation precision positions, thereby facilitating the subsequent precise construction steps of the unqualified installation precision positions and the unqualified installation precision inspection and processing.

[0082] Preferably, in step S4, after the construction step efficiency judgment processing is performed on the location with unqualified installation accuracy, the working state of the multimodal building real-time data monitoring sensor is adjusted, specifically including:

[0083] According to the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy positions in the preset value interval where the quality monitoring parameter exceeds or falls below, unqualified installation accuracy inspection processing is performed on all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy positions;

[0084] According to the unqualified installation accuracy deviation of all the unqualified installation accuracy positions in the preset value range where the quality monitoring parameter exceeds or falls below, the unqualified installation accuracy deviation of all the lifting equipment, assembly equipment and transportation equipment connected to all the unqualified installation accuracy positions is determined, and thereby all the lifting equipment, assembly equipment and transportation equipment connected to all the unqualified installation accuracy positions are switched to the standby state, thereby performing construction step efficiency judgment processing on all the unqualified installation accuracy positions; and then adjusting the working state of the multimodal building real-time data monitoring sensor.

[0085] The beneficial effect of the above technical solution is: through the above method, all lifting equipment, assembly equipment, and transportation equipment connected to all locations with unqualified installation accuracy are switched to a standby state, and the construction steps and installation accuracy inspection processing can be carried out on the locations with unqualified installation accuracy in a targeted manner, so that the source of unqualified installation accuracy can be quickly and accurately located without the need to work on the prefabricated building.

[0086] like Figure 2 FIG. 1 is a block diagram of an intelligent construction system for prefabricated buildings provided by an embodiment of the present invention. The intelligent construction system for prefabricated buildings includes:

[0087] The module for dividing different construction steps and integrating data is used to divide the prefabricated building into several different construction steps, and connect the multimodal building real-time data monitoring sensor to each different construction step to collect and process the component positioning error, so as to obtain the factors affecting the construction progress of each different construction step;

[0088] A construction progress abnormality judgment module is used to judge whether the different construction steps are in an abnormal state of construction progress according to the factors affecting the construction progress;

[0089] The construction period influencing factor module is used to judge the construction step efficiency of all different construction steps in the prefabricated building that are in an abnormal construction progress state, and collect the size of the splicing gap of each different construction step in an abnormal construction progress state to obtain the construction period influencing factors between the different construction steps in an abnormal construction progress state;

[0090] A quality monitoring parameter judgment module is used to judge whether the quality monitoring parameters of different construction steps in an abnormal construction progress state exceed or fall below a preset value range according to the factors affecting the construction period;

[0091] The construction process time interval judgment module is used to adjust the construction step status of the corresponding different construction steps in the abnormal construction progress state according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained;

[0092] The module for judging the position of unqualified installation accuracy is used to predict and process the verticality and flatness data, and determine the position of unqualified installation accuracy where the quality monitoring parameter exceeds or falls below the preset value interval;

[0093] The construction step state adjustment module is used to adjust the working state of the multimodal building real-time data monitoring sensor after performing construction step efficiency judgment processing on the location with unqualified installation accuracy.

[0094] It can be seen from the contents of the above embodiments that the intelligent construction method and construction system of the prefabricated building divide the prefabricated building into several different construction steps, perform different forms of sampling processing on each different construction step, judge whether the different construction steps are in an abnormal state of construction progress and whether the quality monitoring parameters exceed or are lower than the preset value interval, and perform construction steps on the different construction steps in the abnormal state of construction progress and the quality monitoring parameters exceed or are lower than the preset value interval, so as to avoid the occurrence of unqualified installation accuracy in other different construction steps; the graph neural network algorithm is also used to check each unqualified installation accuracy position in the interval where the quality monitoring parameters exceed or are lower than the preset value, determine the unqualified installation accuracy position therein, and perform a separate construction step on the unqualified installation accuracy position and the construction step status of all other different construction steps in the prefabricated building to be constructed. It quickly and accurately locates the corresponding multimodal building real-time data monitoring sensor by dividing the prefabricated building into different construction steps and sampling and checking the zones, and timely avoids the unqualified installation accuracy position from affecting the normal operation of other multimodal building real-time data monitoring sensors in the prefabricated building, improves the inspection efficiency and accuracy of the prefabricated building, and ensures the safety and stability of the overall work of the prefabricated building.

[0095] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent construction method for prefabricated buildings, characterized in that: The method includes: Step S1, dividing the prefabricated building into several different construction steps, and connecting a multimodal building real-time data monitoring sensor to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step; and judging whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors; Step S2, performing construction step efficiency judgment processing on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and performing splicing gap size collection processing on each different construction step in an abnormal construction progress state, to obtain construction period influencing factors between different construction steps in an abnormal construction progress state; judging whether the different construction steps in an abnormal construction progress state belong to a quality monitoring parameter exceeding or falling below a preset value interval according to the construction period influencing factors; Step S3, according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval, the corresponding construction step status of different construction steps in the abnormal construction progress state is adjusted; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained; Step S4, predicting and processing the verticality and flatness data, determining the unqualified installation accuracy position where the quality monitoring parameter exceeds or is lower than the preset value interval; after judging the construction step efficiency of the unqualified installation accuracy position, adjusting the working state of the multimodal building real-time data monitoring sensor; Decompile the response verticality and flatness data to obtain the installation accuracy failure occurrence time of the response verticality and flatness data of each multi-modal building real-time data monitoring sensor; Predict the time when the unqualified installation accuracy occurs to determine whether there is a time error when the unqualified installation accuracy occurs; if so, determine the corresponding multimodal building real-time data monitoring sensor as belonging to a location where the installation accuracy is unqualified; and determine the unqualified installation accuracy deviation of all unqualified installation accuracy locations in which the quality monitoring parameter exceeds or is lower than a preset value interval and the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to the location where the installation accuracy is unqualified; According to the unqualified installation accuracy deviation of all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy position in the preset value interval where the quality monitoring parameter exceeds or falls below, all multimodal building real-time data monitoring sensors that do not belong to the unqualified installation accuracy position are subjected to unqualified installation accuracy inspection processing; According to the unqualified installation accuracy deviation of all the unqualified installation accuracy positions in the preset value interval where the quality monitoring parameter exceeds or falls below, the unqualified installation accuracy deviation of all the lifting equipment, assembly equipment, and transportation equipment connected to all the unqualified installation accuracy positions is determined, so that all the lifting equipment, assembly equipment, and transportation equipment connected to all the unqualified installation accuracy positions are switched to the standby state, thereby performing construction step efficiency judgment processing on all the unqualified installation accuracy positions; and then adjusting the working state of the multimodal building real-time data monitoring sensor.

2. The intelligent construction method of an assembled building according to claim 1, characterized in that: In step S1, the prefabricated building is divided into several different construction steps, and a multimodal building real-time data monitoring sensor is connected to each different construction step to collect and process component positioning errors, so as to obtain the construction progress influencing factors of each different construction step, including: Obtaining the operation coordination time of all lifting equipment, assembly equipment, and transportation equipment in the prefabricated building, dividing the prefabricated building into a number of different construction steps according to the operation coordination time, and identifying the working status of the common lifting equipment, assembly equipment, and transportation equipment between different construction steps, and determining the unqualified installation accuracy deviation of all the common lifting equipment, assembly equipment, and transportation equipment in the prefabricated building; A multimodal building real-time data monitoring sensor is connected to each different construction step to collect and process component positioning errors, and all bolt torque data and all welding temperature and time data of each multimodal building real-time data monitoring sensor in unit time are obtained, which are used as the factors affecting the construction progress.

3. The intelligent construction method of an assembled building according to claim 2, characterized in that: In the step S1, judging whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors includes: The long short-term memory network is used to predict all bolt torque data and all welding temperature and time data, and the fluctuation range of bolt torque data and welding temperature and time data corresponding to different construction steps in the first unit time is determined; If the fluctuation range of the bolt torque data or the fluctuation range of the welding temperature and time data is greater than the preset data fluctuation threshold, it is judged that the different construction steps are in an abnormal construction progress state; otherwise, it is judged that the different construction steps are not in an abnormal construction progress state.

4. The intelligent construction method of an assembled building according to claim 1, characterized in that: In step S2, a construction step efficiency judgment process is performed on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and a splicing gap size collection process is performed on each different construction step in an abnormal construction progress state, so as to obtain the construction period influencing factors between the different construction steps in an abnormal construction progress state, including: The construction schedule of prefabricated buildings is used to judge the efficiency of different construction steps in abnormal construction progress through a negative feedback model. According to the respective integrity of all the shared lifting equipment, assembly equipment, and transportation equipment of different construction steps in an abnormal construction progress state, all the shared lifting equipment, assembly equipment, and transportation equipment are switched to a standby state, and the abnormal causes of the different construction steps in an abnormal construction progress state are found; the integrity is detected by the working state of the lifting equipment, assembly equipment, and transportation equipment. When the lifting equipment, assembly equipment, and transportation equipment are damaged, the working state will be abnormal. The judgment includes the lifting speed, assembly efficiency, and equipment scheduling of the lifting equipment, assembly equipment, and transportation equipment; The size of the splicing gap is collected and processed for each different construction step in an abnormal construction progress state, and the influence range of the time error and failure rate of the coordination between the different internal lifting equipment, assembly equipment and transportation equipment in the different construction steps in an abnormal construction progress state are obtained, which is used as the influencing factor of the construction period.

5. The intelligent construction method of an assembled building according to claim 1, characterized in that: In step S2, judging whether different construction steps in an abnormal construction progress state belong to a quality monitoring parameter exceeding or falling below a preset value range according to the construction period influencing factors includes: Analyze the time error of coordination and determine whether the workload of different lifting equipment, assembly equipment, and transportation equipment working together includes the risk factor of mechanical structure damage; The influence range of the failure rate is predicted and processed to determine whether all workloads with mechanical structure damage risk factors have the same failure rate within the operation cycle of the prefabricated building; if so, it is judged that the different construction steps in the abnormal construction progress state belong to the quality monitoring parameters exceeding or falling below the preset value range; otherwise, it is judged that the different construction steps in the abnormal construction progress state do not belong to the quality monitoring parameters exceeding or falling below the preset value range.

6. The intelligent construction method of an assembled building according to claim 1, characterized in that: In step S3, according to the judgment result of whether the quality monitoring parameter exceeds or falls below the preset value range, the construction step status of the corresponding different construction steps in the abnormal construction progress state is adjusted, specifically including: When the quality monitoring parameters of different construction steps in the abnormal construction progress state do not exceed or fall below the preset value range, all the shared lifting equipment, assembly equipment, and transportation equipment of the different construction steps in the abnormal construction progress state are switched to the operating state according to their respective integrity levels; When the quality monitoring parameters of different construction steps that are in an abnormal construction progress state exceed or fall below the preset value range, the current standby status of all shared lifting equipment, assembling equipment, and transport equipment of the different construction steps that are in an abnormal construction progress state shall be kept unchanged according to the respective integrity levels of all shared lifting equipment, assembling equipment, and transport equipment.

7. The intelligent construction method of an assembled building according to claim 1, characterized in that: In step S3, the graph neural network algorithm is used to perform construction process time interval judgment processing on the quality monitoring parameter exceeding or falling below the preset value interval, and the verticality and flatness data from each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or falling below the preset value interval are obtained, specifically including: According to the quality monitoring parameter exceeding or falling below the preset value interval containing the unqualified installation accuracy deviation of each multimodal building real-time data monitoring sensor, a measurement request instruction is sent to each multimodal building real-time data monitoring sensor respectively, and the verticality and flatness data of the response of each multimodal building real-time data monitoring sensor regarding the measurement request instruction are sampled and intercepted, and the response verticality and flatness data are fed back to the graph neural network algorithm.

8. A system corresponding to the intelligent construction method of an assembled building as claimed in any one of claims 1 to 7, characterized in that: The system includes: The module for dividing different construction steps and integrating data is used to divide the prefabricated building into several different construction steps, and connect the multimodal building real-time data monitoring sensor to each different construction step to collect and process the component positioning error, so as to obtain the factors affecting the construction progress of each different construction step; A construction progress abnormality judgment module, used to judge whether the different construction steps are in an abnormal construction progress state according to the construction progress influencing factors; A construction period influencing factor module is used to perform construction step efficiency judgment processing on all different construction steps in the prefabricated building that are in an abnormal construction progress state, and to collect and process the size of the splicing gap for each different construction step in an abnormal construction progress state, so as to obtain the construction period influencing factors between the different construction steps in an abnormal construction progress state; A quality monitoring parameter judgment module is used to judge whether the quality monitoring parameters of different construction steps in the abnormal construction progress state exceed or fall below the preset value range according to the construction period influencing factors; A construction process time interval judgment module is used to adjust the construction step status of different construction steps in an abnormal construction progress state according to the judgment result of whether the quality monitoring parameter exceeds or is lower than the preset value interval; the construction process time interval judgment processing is performed on the quality monitoring parameter exceeding or lower than the preset value interval through the graph neural network algorithm, and the verticality and flatness data of each multimodal building real-time data monitoring sensor included in the quality monitoring parameter exceeding or lower than the preset value interval are obtained; An installation accuracy unqualified position judgment module is used to predict and process the verticality and flatness data to determine the installation accuracy unqualified position where the quality monitoring parameter exceeds or falls below a preset value interval; The construction step state adjustment module is used to adjust the working state of the multimodal building real-time data monitoring sensor after performing construction step efficiency judgment processing on the location where the installation accuracy is unqualified.

Images