Construction method for whole process of marching type deduction project

Abstract

The invention belongs to the technical field of engineering construction, and particularly relates to a full-process construction method for a marching type deductive project, which comprises the following steps of: acquiring construction foundation, construction equipment, technical standard, historical similar projects, cultural content associated data and performance plot data of the deductive project; constructing a project risk early warning library by using a fusion early warning algorithm, storing the project risk early warning library in a cloud data center, issuing an early warning threshold and data to an edge computing gateway, and completing communication adaptation with a construction equipment sensor, a deduction equipment controller and a team terminal; the process is divided into stages through a WBS algorithm, a task generation algorithm is used for issuing a marching type construction task book, deploying three IMUs, collecting construction data and comparing the construction data with a risk early warning library threshold value for each stage, and if the threshold value is exceeded, early warning is triggered, and the construction task book is updated; and after construction is finished, stage acceptance and whole-process rechecking are carried out, and the project experience library is updated. Therefore, the problems of difficulty in project management and control, weak monitoring capability and the like in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of engineering construction, and particularly relates to a construction method for a whole process of a traveling performance project. BACKGROUND

[0002] With the vigorous development of culture and tourism industries, traveling performance projects are increasing. Such projects usually have the characteristics of complex scenes, coherent processes, high requirements for construction precision and progress, which puts forward special requirements of "dynamic sensing, accurate control and real-time response" for the whole process management of the project. At the same time, under the dual promotion of the intelligentization of industrial equipment and the transformation of large-scale and complex engineering construction field, predictive maintenance and fine management of the whole process become the common direction of the industry. On the one hand, traveling performance projects need to integrate multi-source data such as basic parameters, equipment status, technical standards, historical cases, performance plot data and performance equipment parameters, balance construction precision and progress in coherent processes, and vibration monitoring is a key means for equipment fault diagnosis, structure health assessment and cultural carrier protection, which is a core link for sensing the state of equipment actuators, performance scene construction objects and surrounding environment in construction. On the other hand, the technology of embedded microcontroller and high-performance inertial measurement unit is mature, which makes it possible for low-cost and high-integration vibration monitoring solutions, and also creates technical conditions for traveling performance projects to break through the "dispersed monitoring-lagging control" barrier and realize the integrated management of "real-time sensing-data linkage-process adaptation". The cooperation of the two becomes an important path to solve the contradiction between the special construction requirements of such projects and the traditional management mode.

[0003] The prior art system still has the dual limitations of "inability to match the characteristics of the traveling deductive project" and "insufficient cross-domain collaboration": from the project management end, the traditional construction method is difficult to adapt to the scene complexity and process continuity of the traveling deductive project - the data is "islanded" distributed, not only the engineering data is fragmented, but also the integration of the performance plot data and the deductive equipment parameters is lacking, the risk early warning relies on single data or experience threshold, the cultural compliance and performance plot adaptability early warning dimensions are not set, and the real-time adjustment mechanism is not embedded in combination with the project coherent process and the performance plot narrative rhythm, resulting in poor precision control, progress lagging, and more likely to appear cultural or performance content distortion; from the vibration monitoring end, the inherent defects of the existing equipment are further magnified by the project characteristics - the single or double channel IMU supported by the existing equipment cannot cover the multi-dimensional monitoring needs of "equipment-object-environment" in complex scenes, the single transmission mode relying on the serial port cannot meet the real-time transmission requirements of high-frequency data in the project coherent construction, and the low integration solution requiring external multi-modules will increase the complexity of on-site deployment and slow down the construction progress. The separation of the two makes it difficult for the traveling deductive project to support real-time precision control and progress adjustment through accurate vibration data, and it is also difficult to realize the value of embedded monitoring technology, ultimately restricting the project quality and efficiency, and a technical system deeply integrating the two is urgently needed. SUMMARY

[0004] The present application provides a construction method for a traveling deductive project full process to solve the problems of difficult control, single early warning and weak monitoring ability of the traveling deductive project in the prior art.

[0005] The first aspect embodiment of the application provides a construction method for a traveling deduction project whole process, comprising the following steps: obtaining deduction project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content correlation data and performance plot data; according to the deduction project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content correlation data and performance plot data, using a fusion early warning algorithm, constructing a project risk early warning library, storing in a cloud data center, and issuing early warning thresholds and data to an edge computing gateway, completing communication adaptation with construction equipment sensors, deduction equipment controllers and team terminals; based on the edge computing gateway and the cloud data center, combining the narrative logic of performance plot and scene conversion requirements, dividing the process into basic, main structure and end acceptance stages through a WBS algorithm, and using a task generation algorithm to issue a traveling construction task sheet containing process flow, quality standards, deduction equipment installation parameters, program control interface requirements and cultural presentation requirements for each stage, at the same time, deploying three IMUs to collect vibration data of equipment actuators, construction objects and surrounding environment; according to the traveling construction task sheet, performing traveling stage construction, comparing the data collected by the IMU in real time with the risk early warning library threshold, and if the data exceeds the threshold, triggering an early warning, pushing an adjustment scheme to a project management terminal, updating the construction task sheet and issuing it to the team terminal; after the traveling stage construction is completed, based on the collected and stored construction data, adjustment records, deduction equipment operation test data and cultural content presentation compliance data, carrying out stage acceptance and generating a stage acceptance report, after the whole process of the project is completed, summarizing the stage acceptance reports, risk disposal records and resource consumption data, carrying out whole process review and updating to the project experience library.

[0006] Preferably, using a fusion early warning algorithm, a project risk early warning library is constructed, comprising: constructing a fusion early warning algorithm; inputting the processed deduction project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content correlation data and performance plot data into the fusion early warning algorithm, extracting trend characteristics, mutation characteristics, frequency spectrum characteristics, correlation characteristics, performance plot adaptation characteristics and deduction equipment installation precision characteristics, and performing importance evaluation and screening to output comprehensive risk correlation parameters; based on the comprehensive risk correlation parameters, combining the technical standard data and the historical similar project data, setting multi-level early warning thresholds and corresponding early warning levels, trigger conditions and disposal suggestions, integrating the risk early warning rules and uploading them to the cloud data center to form the project risk early warning library.

[0007] Preferably, the formula of the fusion early warning algorithm is: ; ; ; ; ; ; wherein, is a processed multi-source fusion feature matrix; is a preprocessing function; D is an original multi-source data set; is a trend feature; is a mutation feature; is a spectrum feature; is a correlation feature; is a performance plot adaptation feature; is a performance device installation precision feature; is an abnormality degree output by a statistical learning model; is a statistical model parameter; is a risk score output by machine learning; is a machine learning model parameter; is a comprehensive risk correlation parameter; is a weight coefficient; is a k-level early warning threshold; k is a warning level number.

[0008] Preferably, based on the edge computing gateway and the cloud data center, the process is divided into foundation, main structure, and acceptance stage by WBS algorithm, and a task generation algorithm is used to issue a moving construction task sheet containing process flow and quality standards for each stage, including: constructing a WBS algorithm and a task generation algorithm; inputting the performance project construction basic data, technical standard data, performance plot data, performance device technical specifications, cultural content correlation data, and related requirements in the risk early warning library stored in the cloud data center into the WBS algorithm, defining stage boundaries, process sequencing, and quality index mapping in combination with the narrative logic of the performance plot, to obtain stage division results including stages, processes, quality indexes, performance device installation nodes, risk thresholds, and cultural adaptation requirements; based on the stage division results, using a task generation algorithm and combining technical standard data and resource constraints, resource allocation and construction time period arrangement are performed, and at the same time, risk early warning rules are embedded in the process execution link to generate a moving construction task sheet; the moving construction task sheet is issued to the edge computing gateway and distributed to the corresponding team terminal by the edge computing gateway.

[0009] Preferably, a three-way IMU is deployed to collect vibration data of the equipment actuator, the construction object and the surrounding environment, including: using an STM32F407 master chip to connect three-way inertial measurement units through three independent SPI buses; using TIM2 and TIM3 timers of the STM32F407 to control the collection timing, and synchronously collecting vibration data of the equipment actuator, the equipment actuator component, the performance stage and the surrounding environment at a default sampling rate of 800 Hz; expanding an SD card through an SDIO interface, storing the vibration data in segmented TXT files every 5 seconds based on a FATFS file system, and transmitting the vibration data in real time to the edge computing gateway and the performance equipment program control console through a USB2.0 CDC protocol.

[0010] Preferably, based on the collected and stored construction data and adjustment records, stage acceptance is carried out, and a stage acceptance report is generated, including: constructing a report generation algorithm; inputting the collected and stored construction data, adjustment records, quality detection data, performance equipment installation precision data, program control synchronization test data, cultural content presentation compliance data and compliance evidence into the report generation algorithm, combining threshold requirements of the cloud data center risk early warning library, performing index evaluation, deviation analysis and cultural content presentation compliance verification, and generating a stage acceptance report; uploading the stage acceptance report to the cloud data center as a basis for generating the next stage construction task and optimizing the performance equipment program control.

[0011] The second aspect embodiment of the application provides a construction system for a whole process of a traveling deduction project, comprising: an acquisition module, configured to acquire deduction project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content association data and performance plot data; a construction module, configured to construct a project risk early warning library by using a fusion early warning algorithm according to the deduction project construction basic data, the construction equipment data, the technical standard data, the historical similar project data, the cultural content association data and the performance plot data, store the project risk early warning library in a cloud data center, and send an early warning threshold and data to an edge computing gateway to complete communication adaptation with a construction equipment sensor, a deduction equipment controller and a team terminal; a generation module, configured to divide a process into a foundation stage, a main structure stage and a tail end acceptance stage by using a WBS algorithm based on the edge computing gateway and the cloud data center, in combination with narrative logic of performance plot and scene conversion requirements, and send a traveling construction task sheet containing a process flow, a quality standard, a deduction equipment installation parameter, a program control interface requirement and a cultural presentation requirement to each stage by using a task generation algorithm, and simultaneously deploy three IMUs to collect vibration data of an equipment actuator, a construction object and a surrounding environment; an adjustment module, configured to perform a traveling stage construction according to the traveling construction task sheet, compare data collected by the IMUs in real time with the risk early warning library threshold, trigger an early warning if the data is over the threshold, push an adjustment scheme to a project management terminal, update the construction task sheet and send the construction task sheet to a team terminal; and an update module, configured to perform a stage acceptance based on collected and stored construction data, adjustment records, deduction equipment operation test data and cultural content presentation compliance data after the traveling stage construction is completed, generate a stage acceptance report, and perform a whole process review after a whole process of the project is completed, and update the whole process review to a project experience library.

[0012] The third aspect embodiment of the application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement a construction method for a whole process of a traveling deduction project according to the above embodiment.

[0013] The fourth aspect embodiment of the application provides a computer readable storage medium, having a computer program stored thereon, and the program is executed by a processor to implement a construction method for a whole process of a traveling deduction project according to the above embodiment.

[0014] The fifth aspect embodiment of the application provides a computer program product, comprising a computer program or instructions, to implement a construction method for a whole process of a traveling deduction project according to the above embodiment.

[0015] Therefore, the application has the following beneficial effects: The embodiment of the application breaks the limitation of multi-source data island in traditional construction management by obtaining project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content associated data and performance plot data, integrating and deducing equipment parameters, providing comprehensive and coherent data support for whole-process management and control; the fusion early warning algorithm is used to extract trend, mutation, frequency spectrum, correlation characteristics, performance plot adaptation characteristics and deducing equipment installation precision characteristics, and a project risk early warning library containing multi-level early warning thresholds, cultural compliance thresholds, performance plot adaptation thresholds and disposal suggestions is constructed by weighted fusion output of comprehensive risk correlation parameters through statistical learning and machine learning model, so that the risk identification accuracy and disposal pertinence are improved, and the early warning data is sent to the edge computing gateway to complete the communication adaptation with the construction equipment sensor, the deducing equipment controller and the team terminal, so that efficient linkage is ensured; The construction process is divided into foundation, main structure and completion acceptance stage by WBS algorithm combined with performance plot narrative logic, and the marching construction task sheet containing process flow, quality standard, deducing equipment installation parameter and program control interface requirement is issued by cooperating with the task generation algorithm, so that fine decomposition of construction process and accurate delivery of task are realized, and three IMUs are deployed, the vibration data of equipment actuators, deducing equipment execution components and surrounding environment are synchronously collected by means of STM32F407 master control chip, independent SPI bus and double timers, and data stable storage and real-time transmission are realized through SDIO interface and USB2.0 CDC protocol, so as to make up for the defects of single monitoring dimension and lagging data processing in traditional monitoring; the IMU data and the threshold value of the early warning library are compared in real time during construction, and if the threshold value is exceeded, the adjustment scheme containing deducing equipment calibration and program control synchronization is pushed to the management terminal, the construction task sheet is synchronously updated and issued to the team terminal, the construction dynamic optimization is realized, and the construction precision, progress and performance plot presentation effect are ensured; the stage acceptance and whole-process review generate a report based on the collected data, adjustment records, deducing equipment operation test data and cultural content presentation compliance data, update the disposal records and resource consumption data to the experience library, refine the adaptation experience of performance plot, deducing equipment and engineering construction, and provide support for subsequent similar projects, so as to continuously improve the intelligent level of construction management and the overall quality of the project. Thus, the problems of marching deducing project management and control difficulty, single early warning and weak monitoring capability in the prior art are solved.

[0016] Additional aspects and advantages of the application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and / or additional aspects and advantages of the application will become apparent and be readily appreciated from the following description, including the appended drawings, wherein: Figure 1A flow chart of a construction method of a whole process of a traveling deductive project according to an embodiment of the present application is provided; Figure 2 A structure diagram of a data acquisition device according to an embodiment of the present application is provided; Figure 3 A working flow chart of a data acquisition device according to an embodiment of the present application is provided; Figure 4 A structure diagram of a construction system of a whole process of a traveling deductive project according to an embodiment of the present application is provided; Figure 5 A structure diagram of an electronic device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0018] Embodiments of the present application are described in detail below with reference to the attached drawings. The embodiments of the present application are shown by way of example in the drawings and are not to be construed as limiting the present application. The same or similar components are denoted by the same or similar reference numerals throughout the drawings.

[0019] With reference to the accompanying drawings, a construction method of a whole-process traveling deduction project is described below. In view of the weak monitoring capability mentioned in the background art, the present application provides a construction method of a whole-process traveling deduction project. In the method, by acquiring project construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content correlation data, and performance plot data, integrating deduction equipment parameters, breaking the limitation of multi-source data island in traditional construction management, and providing comprehensive and coherent data support for whole-process management and control, the trend, mutation, frequency spectrum, correlation characteristics, performance plot adaptation characteristics, and deduction equipment installation precision characteristics are extracted by using a fusion early warning algorithm, the comprehensive risk correlation parameters are output by weighted fusion of statistical learning and machine learning models, the project risk early warning library containing multi-level early warning thresholds, cultural compliance thresholds, performance plot adaptation thresholds, and disposal suggestions is constructed, the risk identification accuracy and disposal pertinence are improved, the early warning data is sent to the edge computing gateway, the communication adaptation with the construction equipment sensor, the deduction equipment controller, and the team terminal is completed, and the efficient linkage is ensured. The construction process is divided into the foundation, main structure, and completion acceptance stages by using the WBS algorithm combined with the performance plot narrative logic, the traveling construction task sheet containing the process flow, quality standard, deduction equipment installation parameter, and program control interface requirement is sent by using the task generation algorithm, the construction process is finely disassembled, and the task is accurately assigned, three IMUs are deployed, the vibration data of the equipment actuator, the deduction equipment actuator, and the surrounding environment are synchronously collected by using the STM32F407 master control chip, independent SPI bus, and double timers, the data is stably stored and real-time transmitted by using the SDIO interface and USB2.0 CDC protocol, the defects of single monitoring dimension and lagging data processing in the traditional monitoring are made up, the IMU data and the early warning library threshold are compared in real time during construction, the threshold is exceeded, the early warning is triggered, the adjustment scheme containing the deduction equipment calibration and program control synchronization is pushed to the management terminal, the construction task sheet is synchronously updated and sent to the team terminal, the construction dynamic optimization is realized, the construction precision, progress, and performance plot presentation effect are ensured, the stage acceptance and whole-process review are based on the collected data, adjustment records, deduction equipment operation test data, and cultural content presentation compliance data to generate a report, the disposal records and resource consumption data are updated to the experience library, the adaptation experience of the performance plot, deduction equipment, and engineering construction is refined, support is provided for subsequent similar projects, and the intelligent level of construction management and the overall quality of the project are continuously improved. Thus, the problems of traveling deduction project management and control difficulty, single early warning, and weak monitoring capability in the prior art are solved.

[0020] Specifically, Figure 1 A flowchart of a construction method of a whole-process traveling deduction project provided by the present application embodiment.

[0021] As Figure 1 shown, the construction method of a whole-process traveling deduction project includes the following steps: In step S101, the following data are obtained: basic construction data of the performance project, construction equipment data, technical standard data, historical data of similar projects, cultural content association data, and performance plot data.

[0022] It is understood that the embodiments of this application, by acquiring basic construction data, construction equipment data, technical standard data, historical data of similar projects, performance plot data, and cultural content-related data of the performance project, break down the traditional data silos in construction, avoid blind spots in management, provide input for the integrated early warning algorithm, help extract multiple features such as performance plot adaptation features and performance equipment installation accuracy features, generate accurate risk-related parameters and early warning thresholds, and improve the accuracy of risk identification. At the same time, the WBS algorithm combines the narrative logic of the performance plot to divide the construction stages, the task generation algorithm configures resources and arranges time periods and embeds performance equipment installation parameters and program control interface requirements, ensuring that the construction tasks meet the needs of high precision and coherent process of the project, avoiding progress delays caused by task disconnection, and historical data can assist in the stage acceptance to judge compliance and the performance equipment operation test compliance, update the experience base, and reduce the trial and error costs of subsequent similar projects.

[0023] In step S102, based on the basic construction data, construction equipment data, technical standard data, historical similar project data, cultural content association data, and performance plot data of the performance project, a project risk early warning database is constructed using a fusion early warning algorithm, stored in the cloud data center, and the early warning thresholds and data are sent to the edge computing gateway to complete the communication adaptation with the construction equipment sensors, performance equipment controllers, and team terminals.

[0024] Among them, the edge computing gateway refers to the intermediate device that connects the cloud data center with the construction equipment sensors and team terminals. It can receive the early warning thresholds and related data issued by the cloud data center, as well as the vibration data collected by the IMU. It can also issue progressive construction task sheets, early warning information and updated task sheets to the team terminals, and complete communication adaptation, data interaction and instruction transmission.

[0025] It should be noted that to complete the communication adaptation with the construction equipment sensors, the simulation equipment controller, and the team terminal, firstly, a communication protocol matching the construction equipment sensors and the simulation equipment controller is loaded to establish a two-way data interaction link between the gateway and the sensors and the simulation equipment controller. This ensures that the sensors can upload collected data in real time, the simulation equipment controller can upload operating parameters, and the gateway can issue parameter configuration commands. Secondly, the connection adaptation with the team terminal is completed through a standardized interface. The stability of the terminal receiving early warning information issued by the gateway, simulation equipment calibration and program control synchronization adjustment information, and construction task update content is verified. Finally, the communication linkage between the edge computing gateway and the equipment sensors, simulation equipment controller, and team terminal is completed.

[0026] It is understood that this application embodiment, by completing communication adaptation with construction equipment sensors, simulation equipment controllers, and work team terminals, avoids data transmission gaps caused by incompatible communication protocols or unstable connections. This ensures that data collected by construction equipment sensors regarding equipment operation and construction status, as well as operating parameters uploaded by the simulation equipment controller, are smoothly transmitted to subsequent management and control stages. This provides a stable channel for data-driven management and control throughout the entire process of the mobile simulation project, adapting to the complex and continuous nature of project scenarios. Simultaneously, it ensures that early warning information, simulation equipment calibration and programmable control synchronization adjustment information, and adjusted construction task sheets are accurately and promptly delivered to the work team terminals, avoiding delayed or missed instructions. This helps work teams respond quickly to needs, meeting the project's high precision, schedule, and cultural presentation requirements, reducing construction deviations or schedule delays caused by communication problems, and improving construction management efficiency and project quality.

[0027] In this embodiment of the application, a project risk early warning database is constructed using a fusion early warning algorithm, including: constructing a fusion early warning algorithm; The processed construction basic data, construction equipment data, technical standard data, historical similar project data, cultural content correlation data, and performance plot data are input into the fusion early warning algorithm to extract trend features, mutation features, spectrum features, correlation features, performance plot adaptation features, and performance equipment installation accuracy features. Importance assessment and screening are then performed to output comprehensive risk correlation parameters. Based on the comprehensive risk correlation parameters, combined with technical standard data and historical similar project data, multi-level early warning thresholds and corresponding early warning levels, triggering conditions, and handling suggestions are set and integrated into risk early warning rules, which are then uploaded to the cloud data center to form a project risk early warning library.

[0028] Among them, the comprehensive risk correlation parameter refers to the core parameter output by the fusion early warning algorithm. It is used to compare with the preset multi-level early warning thresholds to determine whether the corresponding level of early warning is triggered during the construction of the project. It is a key basis for assessing the degree of project risk.

[0029] It should be noted that the multi-level early warning threshold settings are based on the basic safety parameters in the technical standard data and the conventional safety threshold ranges in historical data of similar projects. First, an initial threshold is set to form a basic threshold framework adapted to the general scenarios of progressively evolving projects. Simultaneously, relying on the calculated comprehensive risk correlation parameters, and using the initial threshold as a reference, the risk level is stratified and refined based on the comprehensive risk correlation parameters. According to the actual risk characteristics of the current project, the interval division of the initial threshold is adjusted to determine the specific thresholds corresponding to low, medium, and high levels. The core of setting the standards is always the dual constraint of technical standard data and historical data of similar projects, ensuring that the adjusted thresholds neither deviate from compliance requirements nor fail to fit the complexity and process continuity of the current project scenario. Ultimately, a multi-level early warning threshold system adapted to the current project is formed, providing accurate and practical judgment basis for subsequent full-process risk early warning.

[0030] It is understandable that this application's embodiments, by setting multi-level early warning thresholds, provide clear and hierarchical judgment criteria for risk identification in progressive deductive projects. Combined with the comprehensive risk correlation parameters output by the fusion early warning algorithm, it distinguishes different levels of risk severity, avoiding the drawbacks of traditional single thresholds and shifting risk judgment from vague experience to data-driven approaches. Secondly, this setting is adapted to the complex and sequential nature of project scenarios. Low-level early warnings can prompt work teams to fine-tune construction details, preventing small engineering risks and cultural compatibility risks from accumulating into major problems. Medium- and high-level early warnings can promptly trigger work stoppages for inspection and adjustment plan pushes, ensuring that construction accuracy does not deviate from technical standards and cultural presentation requirements, and preventing schedule delays due to delayed risk handling. Simultaneously, the triggering conditions and handling suggestions corresponding to the multi-level thresholds can also provide clear risk classification criteria for phase acceptance and full-process review, helping to summarize the handling records of engineering risks and cultural compliance risks, update the project experience database, and accumulate reusable templates for risk management in subsequent similar projects.

[0031] For example, in the construction of a steel structure corridor for an outdoor walking performance project, a fusion early warning algorithm was built. This algorithm can process multi-source data, extract features, and output risk parameters. Then, the processed data is input: basic data includes the corridor span of 20m and the steel type Q355; equipment data includes the lifting speed and load-bearing capacity of the hoisting machinery; technical standard deflection limits (≤10mm); historical data includes six hoisting risk cases from four similar projects; performance plot data (e.g., the corridor needs to adapt to the "intangible cultural heritage parade" plot movement, and the load-bearing capacity needs to be compatible with the passage of actors and props), and cultural content... The relevant data (material vibration resistance value and display angle requirements of the adjacent intangible cultural heritage themed scenery) are cleaned and then input into the algorithm to extract trend features (72-hour change in hoisting speed), abrupt change features (instantaneous fluctuations in load-bearing capacity), spectral features (peak noise of mechanical operation), correlation features (correlation between hoisting speed and deflection), performance plot adaptation features (correlation between corridor load-bearing capacity and the passage requirements of plot props), and performance equipment installation accuracy features (correlation between the location of the adjacent projection equipment bracket and the corridor construction). After evaluation and screening, comprehensive risk correlation parameters (values ​​from 0 to 12) are output. Subsequently, thresholds were set: the initial threshold reference standards, historical data, performance plot data, and cultural content-related data. The thresholds for equipment (hoisting machinery) were 3-6 / 6-9 / >9, construction objects (steel structures) were 2-5 / 5-8 / >8, performance equipment (side projection equipment) were 1-3 / 3-5 / >5, and the surrounding environment (side intangible cultural heritage themed scenery) were 1-4 / 4-7 / >7. Considering the current project's characteristics of lightweight steel structures, fragile intangible cultural heritage scenery, and the need to ensure the cultural display effect, the optimized thresholds were 2.5-5.5 / 5.5-8.5 / >8.5, construction objects were 1.5-4.5 / 4.5-7.5 / >7.5, performance equipment were 0.8-2.8 / 2.8-4.8 / >4.8, and the environment was 0.8-3.8 / 3.8-6.8 / >6.8. Corresponding rules: Yellow equipment warning (parameter 2.5-5.5, lifting speed exceeding rated speed by 10%), the recommended action is to record data every 5 minutes and fine-tune the speed; Orange warning (5.5-8.5, exceeding rated speed by 20%), stop the machine and check the winch; Red warning (>8.5, exceeding rated speed by 30%), immediately stop lifting and replace with backup machinery; Construction object warnings match corresponding trigger conditions (e.g., steel structure deflection exceeding 5mm triggers a yellow warning, the recommended action is to increase monitoring); Performance equipment warnings match corresponding trigger conditions (e.g., projection bracket vibration parameter exceeding 4.8 triggers a red warning, the recommended action is to suspend construction and calibrate the bracket); Environmental warnings match corresponding trigger conditions (e.g., scenery vibration parameter exceeding 3.8 triggers an orange warning, the recommended action is to slow down the lifting pace to avoid scenery collapse or damage to cultural elements). Finally, the rules will be uploaded to the cloud data center to form a project risk warning database.

[0032] In this embodiment of the application, the formula for the fusion early warning algorithm is: ; ; ; ; ; ; in, This is the processed multi-source fusion feature matrix; D is the preprocessing function; D is the original multi-source dataset. As a trend feature; It is a mutation characteristic; Spectral characteristics; It is a relevance feature; Features adapted to the performance's storyline; To demonstrate the installation accuracy characteristics of the equipment; The degree of anomaly in the output of the statistical learning model; These are the parameters for the statistical model. The risk score output by machine learning; For machine learning model parameters; For comprehensive risk-related parameters; These are the weighting coefficients; is the threshold for the k-th warning level; k is the warning level number.

[0033] It should be noted that the weighting coefficients are determined based on the basic range set by technical standard data, optimized by referring to the actual early warning errors of statistical learning models and machine learning models in similar historical projects, and fine-tuned by combining phase acceptance data.

[0034] It is understood that the embodiments of this application, by integrating early warning algorithm formulas, transform multi-source raw data of the project into a fusion feature matrix containing trend, mutation, spectrum, and correlation characteristics, breaking the limitations of fragmented single data and providing comprehensive and systematic feature support for risk assessment; by integrating the anomaly output of the statistical learning model and the risk score of the machine learning model, and adjusting the proportion of the two with weight coefficients, taking into account the objective laws of data and historical construction experience, the comprehensive risk correlation parameters are accurate and reliable; based on the comparison results of the comprehensive risk correlation parameters and multi-level early warning thresholds, corresponding early warnings are triggered, clarifying the triggering logic of different early warning levels, providing a scientific calculation basis for the project risk early warning library, adapting to the needs of progressive deductive project risk layering and control, and ensuring that risk early warning decisions are more targeted and operable.

[0035] In step S103, based on the edge computing gateway and cloud data center, and combined with the narrative logic of the performance plot and scene transition requirements, the process is divided into the basic, main structure, and final acceptance stages using the WBS algorithm. A task generation algorithm is then used to issue a progressive construction task book containing process flow, quality standards, performance equipment installation parameters, programmable interface requirements, and cultural presentation requirements to each stage. At the same time, three IMUs are deployed to collect vibration data of the equipment actuators, construction objects, and the surrounding environment.

[0036] It is understood that this application embodiment uses the WBS algorithm combined with the narrative logic of the performance plot and cultural content to divide the process into the basic, main structure, and final acceptance stages, clarifying the boundaries and sequential logic of the construction stages, avoiding confusion in the procedures. A task generation algorithm is used to issue task sheets containing procedures, quality standards, performance equipment installation parameters, programmable interface requirements, and cultural presentation requirements to each stage, directly guiding the work teams to construct according to specifications. This ensures the orderly progress of construction quality, schedule, and cultural content presentation. By simultaneously deploying three IMUs to collect vibration data from the actuators of the performance equipment, the construction objects, the cultural performance carriers, and the surrounding environment, real-time dynamic data of key construction links, cultural performance carriers, and performance equipment is obtained. This provides core data support for subsequent comparison of data with risk warning thresholds, performance plot adaptation thresholds, and cultural compliance thresholds, and for timely triggering of risk warnings. The overall approach adapts to the needs of continuous management throughout the entire process of a moving performance project, ensuring a clear and controllable construction process, and laying a data foundation for risk monitoring, early warning, and cultural content presentation.

[0037] For example, taking the construction of a mobile steel structure stage for an outdoor mobile performance project as an example, the project needs to complete the construction of 3 sets of mobile stages within 12 days (the stages need to be adapted to intangible cultural heritage themed performances, including intangible cultural heritage display racks and performance equipment (performance lighting)). The entire process relies on edge computing gateways and cloud data centers for collaborative management: First, the construction process is divided into three stages: foundation (3 days), main structure (5 days), and final acceptance (4 days) by combining the narrative logic of the performance plot and cultural content (such as the stage functional zoning rhythm and plot movement requirements of intangible cultural heritage performance scenes) through WBS algorithm. The cloud data center pre-stores the steel structure engineering construction quality acceptance standards, equipment parameters (25T truck crane, QTZ6021 tower crane), construction records of 2 similar projects, performance plot data (such as the requirements of the intangible cultural heritage performance scene movement lines for the stage movement trajectory), and cultural content related data (intangible cultural heritage display rack load-bearing requirements, performance equipment (stage lighting) installation spacing). Based on data such as cultural scene adaptation standards, the task generation algorithm automatically generates progressive construction task books for each stage. The task book for the foundation stage specifies the process as "foundation survey → reinforced concrete independent foundation pouring → curing", with quality standards requiring a foundation bearing capacity ≥150kPa and a foundation flatness deviation ≤3mm. The task book for the main structure stage specifies the process as "truss ground pre-assembly → segmented hoisting → node welding", with welding quality requiring 100% UT flaw detection qualification. It also includes cultural presentation requirements and installation parameters for performance equipment (truss spacing is reserved at 30cm to adapt to the suspension of performance equipment (lighting) for intangible cultural heritage performances, and welding nodes avoid the installation area of ​​intangible cultural heritage decorations). The task book for the finishing and acceptance stage includes cultural presentation requirements (stage surface flatness meets the standards for actor movement safety and stable placement of intangible cultural heritage props). These task books are distributed in real time to the mobile terminals of the two steel structure teams via edge computing gateways, and the construction progress nodes are updated synchronously. Meanwhile, three high-precision IMUs were deployed according to the plan: the first channel was installed on the boom actuator of the 25T truck crane, with a sampling frequency of 50Hz and a range of ±10m / s², to collect vibration acceleration and attitude data during hoisting in real time; the second channel was fixed at the main beam node of the main stage truss to monitor the vibration response during structural splicing, with a sensitivity of 0.01m / s²; the third channel was deployed to the LED screen scenery support, intangible cultural heritage display rack and performance equipment (lighting controller) actuators 5m around the stage to record the impact of construction vibration on surrounding equipment, cultural performance carriers and performance equipment.The raw data collected by the three-channel IMU is preprocessed by the edge gateway (removing outliers and standardizing the format), and then synchronized to the cloud data center via a 4G network. Among them, the maximum vibration acceleration monitored by the IMU of the truck crane is 0.42 m / s² in the foundation stage, the instantaneous vibration of 0.35 m / s² is captured by the IMU of the truss during the main hoisting, and the maximum vibration acceleration monitored by the IMU of the intangible cultural heritage display stand and the performance equipment is 0.18 m / s². All are compared with the safety threshold, the performance plot adaptation threshold (such as the stage movement accuracy matching the requirements of the performance act transition) and the cultural compliance threshold (the vibration acceleration of the intangible cultural heritage display stand ≤ 0.2 m / s²) attached to the task book through the gateway to ensure that the construction operations meet the stage quality requirements and the cultural presentation needs, providing dual support for the coherent progress and risk warning of the progressive construction.

[0038] In the embodiment of this application, based on the edge computing gateway and the cloud data center, the process is divided into the foundation, main structure, and final acceptance stages through the WBS algorithm, and a progressive construction task book containing the process flow and quality standards is issued to each stage by using the task generation algorithm, including: constructing the WBS algorithm and the task generation algorithm; inputting the relevant requirements in the construction basic data, technical standard data, performance plot data, performance equipment technical specifications, cultural content association data, and risk warning library stored in the cloud data center into the WBS algorithm, and combining the narrative logic of the performance plot to define the stage boundaries, sequence the processes, and map the quality indicators, so as to obtain the stage division result including stages, processes, quality indicators, installation nodes of performance equipment, risk thresholds, and cultural adaptation requirements; based on the stage division result, using the task generation algorithm and combining the technical standard data and resource constraints, perform resource allocation and construction time period arrangement. At the same time, embed the risk warning rules into the process execution link to generate a progressive construction task book; issue the progressive construction task book to the edge computing gateway, and the edge computing gateway distributes it to the corresponding team terminals.

[0039] Among them, the WBS algorithm refers to a structured method that hierarchically disassembles a complex project into specific task units that can be defined, executed, and managed from top to bottom.

[0040] It should be noted that the task generation algorithm refers to a method that automatically outputs an executable task list or task plan that meets the requirements through logical calculation based on conditions such as project goals, resource limitations, and task dependencies.

[0041] It is understood that the WBS algorithm in this application embodiment is based on an edge computing gateway and a cloud data center. It combines basic project construction data, performance plot data, cultural content-related data, and the narrative logic of the performance plot and cultural content to divide the process into basic, main structure, and final acceptance stages. This clarifies stage boundaries, process sequencing, and quality indicator mapping, avoiding process confusion. The task generation algorithm, based on the WBS stage division results and combined with technical standard data, performance plot data, cultural content-related data, and resource constraints, generates a progressive construction task sheet containing process flow, quality standards, performance equipment installation parameters and programmable interface requirements, cultural presentation requirements, and embedded risk warning rules. This guides the work teams in standardized construction and distributes the task sheet to the work team terminals and performance equipment debugging terminals via the edge computing gateway to ensure information synchronization. Both work together to adapt to the entire project process management, ensuring orderly construction progress and meeting cultural content presentation standards, and providing process and execution support for risk warning.

[0042] For example, taking the construction of a temporary steel structure grandstand for an outdoor immersive performance project as an example (which needs to be adapted to the perspective of the audience and the layout of the interactive area for the intangible cultural heritage performance), the project relies on an edge computing gateway and a cloud data center. First, the WBS algorithm is used to combine the narrative logic of the performance plot and cultural content (such as prioritizing the completion of the basic construction of the interactive area) to divide the 20-day construction process into the stages of foundation (3 days), main structure (12 days), and final acceptance (5 days). The input data includes the grandstand design dimensions (50m long × 15m wide), Q235 steel material parameters, steel structure engineering construction quality acceptance standards, construction records of two similar projects, performance plot data (such as the requirements of the intangible cultural heritage performance movement line for the grandstand perspective), and the size requirements of the interactive area of ​​the intangible cultural heritage performance grandstand. The algorithm clarifies the sequence of the foundation stage "site compaction → concrete cushion pouring" and the main stage "steel column hoisting → truss splicing", maps the quality indicators (foundation bearing capacity ≥ 120kPa, steel structure welding qualification rate 100%) and cultural presentation requirements (interactive area foundation flatness deviation ≤ 2mm), and outputs the stage division results. Subsequently, based on this result, the task generation algorithm, combined with technical standards, resource constraints (2 25T cranes, 3 construction teams), performance plot data, and cultural content-related data, generates a progress-oriented construction task book for each stage. The main stage task book specifies the daily hoisting of 3 steel columns and welding of 10 nodes, including cultural presentation requirements, performance equipment installation parameters, and programmable interface requirements (such as reserving installation space for the intangible cultural heritage display platform at the edge of the grandstand and the installation position of performance equipment (sound / lighting)). It embeds a "hoisting angle exceeding 85° triggers an early warning" rule and distributes it to the team terminals and performance equipment debugging terminals via the edge computing gateway to guide the teams to construct according to specifications. The two work together to ensure the orderly progress of construction and the implementation of cultural needs, adapting to the project's progress-oriented management requirements.

[0043] In this embodiment, three IMUs are deployed to collect vibration data from the device actuators, construction objects, and the surrounding environment. This includes: using an STM32F407 main control chip to connect the three inertial measurement units via three independent SPI buses; using the STM32F407's TIM2 and TIM3 timers to control the acquisition timing, synchronously collecting vibration data from the device actuators, performance equipment components, the performance stage, and the surrounding environment at a default sampling rate of 800Hz; expanding the SD card via the SDIO interface, generating segmented TXT files every 5 seconds based on the FATFS file system for storage, and transmitting the vibration data in real time to the edge computing gateway and the performance equipment control console via the USB 2.0 CDC protocol.

[0044] Among them, the STM32F407 main control chip is the core control unit for collecting vibration data of equipment actuators, performance stages and surrounding environment in construction scenarios.

[0045] It should be noted that the data acquisition process is as follows: The timing control module (including TIM2 and TIM3 timers, providing time bases at 42MHz and 21MHz respectively) sends a timing signal to the STM32F407 main control unit. Based on this signal, the main control unit initiates the identification of three ICM45686 inertial measurement units (compatible with ADIS16470 and SCH16_K10). If the identification is successful, the IMU is initialized. Subsequently, the main control unit cyclically reads the vibration data of the equipment actuators, the performance stage, and the surrounding environment in the construction scene collected by the three IMUs. On the one hand, it stores the data to an SD card with a FATFS file system mounted via the SDIO interface. The system uses a card (which automatically generates segmented TXT files every 5 seconds) to transmit real-time vibration data to an edge computing gateway via the USB 2.0 CDC protocol. After receiving the data, the edge computing gateway can further forward it to a host computer (which acts as a data receiving and processing terminal, receiving vibration data and performing analysis, display, storage, and management). At the same time, the main control unit can also set parameters and troubleshoot faults through the reserved USART1 / USART2 debugging and expansion interfaces. The edge computing gateway can also connect to a cloud data center. The host computer's analysis results of the vibration data are combined with the threshold values ​​of the cloud data center's risk warning database to provide support for construction risk warning, adjustment plan formulation, and generation of phased acceptance reports.

[0046] It is understood that the embodiments of this application, through the acquisition of vibration data from three IMUs, provide a high-quality data foundation for subsequent comparison with risk warning database thresholds, timely identification of equipment anomalies or construction deviations, improve the integration and reliability of the overall monitoring system, and provide stable data support for dynamic project management and risk warning.

[0047] For example, in the construction project of a steel structure support for an outdoor mobile light show, three IMUs were deployed to collect vibration data. The device structure is as follows:Figure 2 As shown, IMU1 is fixed to the 25T tower crane boom actuator, IMU2 is installed at a key node of the main beam of the steel structure support, and IMU3 is deployed to the LED screen support frame 3m around the support. The three IMUs are connected to the main control unit with the STM32F407 chip as the core via connecting cables. The timing control module (with built-in TIM2 and TIM3 timers, providing time bases at 42MHz and 21MHz respectively) sends timing signals to the main control unit via inter-board communication. The main control unit then interacts with the storage module (externally connected to a 32GB SD card with a FATFS file system) and the communication module via inter-board communication. The debugging expansion interface module (including USART1 / USART2 interfaces) is also connected to the main control unit via inter-board communication. The communication module finally transmits data to the host computer via a connecting cable. During project implementation, the device's workflow is as follows: Figure 3 As shown: First, initialization is performed (including parameter configuration of the main control unit and each module). Then, the main control unit initiates IMU identification, sequentially identifying and verifying IMU1, IMU2, and IMU3 (the selected IMU is ICM45686 and compatible with ADIS16470 and SCH16_K10). If identification fails, it is marked as "NEWIMU" and re-identified. After successful identification, the corresponding IMU is initialized (configuring parameters such as vibration range ±16g and angular velocity range ±2000dps). After initialization, the main control unit cyclically reads the construction scene vibration data collected by the three IMUs. On one hand, the data is transmitted to the storage module through inter-board communication, and the storage module automatically generates a file named "Construction Date_Timestamp_IMU Number.txt" every 5 seconds. On the one hand, the system stores TXT files, and on the other hand, it outputs data to the host computer in real time via the USB 2.0 CDC protocol at a baud rate of 115200bps through the communication module. After receiving the data, the host computer analyzes it in conjunction with the risk warning database threshold of the cloud data center. For example, if the IMU1 collects a tower crane boom vibration acceleration of 0.5m / s² at a certain moment (the warning threshold is set to 0.45m / s²), a construction risk warning is triggered, providing data support for adjusting the tower crane lifting speed and other plans, as well as generating phased acceptance reports. At the same time, on-site engineers can connect to the debugging terminal through the USART1 interface of the debugging expansion interface module to adjust the IMU sampling rate (such as adjusting it from the default 800Hz to 1000Hz), or check the SPI bus connection fault through the USART2 interface to ensure stable system operation.

[0048] In step S104, the construction is carried out in the moving phase according to the moving construction task book, and the data collected in real time by the IMU is compared with the threshold of the risk warning database. If the data exceeds the threshold, an early warning is triggered, the adjustment plan is pushed to the project management terminal, and the construction task book is updated and distributed to the team terminal.

[0049] It is understood that, by comparing the data collected in real time by the IMU with the threshold of the risk warning database, this embodiment of the application can ensure that the construction during the moving phase strictly follows the preset process flow and quality standards. At the same time, it can dynamically monitor and quickly handle construction risks, promptly detect abnormal risks in construction, and quickly activate the handling mechanism to prevent risks from escalating and affecting construction safety and quality. In addition, the adjustment plan is directly sent to the management terminal, and the updated task book is directly sent to the team terminal, reducing information transmission losses, improving the efficiency of risk handling and construction adjustment, ensuring that the entire moving construction process is always under control, and ensuring that the project proceeds in an orderly manner according to specifications.

[0050] For example, in the construction project of the mechanical installation of an indoor immersive theater stage, after the project entered the main mechanical installation phase, the construction team proceeded with the work according to the progress-oriented construction task book. The task book clearly stated that the core procedures of this phase were "mechanical track laying → lifting platform installation → lighting rig fixing", and stipulated that the flatness deviation of the track laying must be ≤2mm, the noise of the lifting platform during no-load operation must be ≤55dB, and the verticality deviation of the lighting rig installation must be ≤1.5mm. During the construction process, three IMUs were deployed to continuously collect data—the first was installed on the actuator of the track laying trolley (monitoring equipment vibration), the second was fixed to the main frame of the lifting platform (monitoring structural vibration of the construction object), and the third was deployed to the audience seating railing around the stage (monitoring environmental vibration). The edge computing gateway synchronously transmitted the real-time data from the three IMUs to the system, and communicated with the wind... The system compares preset thresholds in the hazard warning database (such as the vibration acceleration threshold for the track laying trolley ≤ 0.3 m / s² and the vibration displacement threshold for the lifting platform ≤ 0.5 mm). When the IMU data of the track laying trolley shows an acceleration of 0.42 m / s² at a certain moment, exceeding the threshold, an early warning is triggered. An adjustment plan is then generated (suggesting reducing the track laying trolley's propulsion speed from 0.5 m / min to 0.3 m / min and adding buffer pads at the trolley wheels), and pushed to the project management terminal. After the management team confirms the feasibility of the plan, the system automatically updates the mobile construction task book, adding the requirement of "adjusting the trolley's propulsion speed and adding buffer pads" to the track laying procedure description, and immediately sends it to the mechanical installation team's terminal. The team adjusts the operation according to the updated task book to ensure that the construction of the stage machinery meets quality and safety standards.

[0051] In step S105, after the construction of the project is completed, a phase acceptance is carried out based on the collected and stored construction data, adjustment records, performance equipment operation test data and cultural content presentation compliance data, and a phase acceptance report is generated. After the entire project process is completed, the acceptance reports of each phase, risk handling records, and resource consumption data are summarized, a full process review is carried out, and the data is updated to the project experience database.

[0052] The full-process review involves retrieving and collecting complete data from the cloud data center, including compliance of procedures, quality standards, cultural content presentation standards, and acceptance conclusions recorded in each stage's acceptance reports; early warning trigger times, data exceeding limits and cultural compliance exceeding limits, adjustment plan content and cultural adaptation deviation adjustments, and execution effects from risk management records; and resource consumption data such as manpower input time, equipment usage frequency, and material consumption, ensuring data coverage of key aspects of the entire construction cycle and dimensions related to cultural content implementation. Multi-dimensional analysis is conducted on the collected data to verify whether the construction process strictly follows the WBS algorithm's division of the basic, main, and final acceptance stages based on the narrative logic of the performance plot and cultural content. The analysis also examines the execution deviation rate and causes of each stage's task book, including cultural presentation requirements, performance equipment installation parameters, and programmable interface requirements. Simultaneously, it assesses the rationality of the risk warning database thresholds, cultural compliance thresholds, performance plot adaptation thresholds, the effectiveness of adjustment plans, and the cultural adaptation correction effects. Finally, it analyzes the matching degree between resource consumption and budget, identifying areas of resource waste or under-allocation. Based on the analysis results, successful experiences and cultural and technological adaptation experiences throughout the entire process, as well as areas for improvement, are extracted to form a structured debriefing conclusion. The experiences, improvement suggestions, optimized risk management strategies, cultural compliance risk management strategies, equipment calibration and program control synchronization adjustment strategies, and resource allocation plans derived from the debriefing are structured and entered into the project experience database according to its storage specifications. This updates the project experience database and provides data support, process references, and cultural implementation guidance for subsequent similar mobile debriefing projects.

[0053] It is understandable that this application embodiment, through a full-process review, analyzes the entire lifecycle of the construction of the mobile performance project, evaluates the effectiveness of task execution at each stage, the actual role of risk warning and handling mechanisms, the rationality of resource allocation, the adaptation effect of the performance plot, the installation and synchronization effect of performance equipment, and the achievement of cultural content presentation standards. This allows for the timely identification of process loopholes, resource waste, insufficient risk handling, cultural and technological mismatches, and performance equipment synchronization deviations, thus identifying areas for improvement and preventing repeated pitfalls in subsequent construction. Furthermore, the review results are updated to the project experience database, providing valuable experience for similar mobile performance projects, reducing the cost of solution exploration, improving project construction efficiency, compliance, and cultural transmission quality, and ensuring that subsequent projects are more scientific in terms of process planning, risk control, resource allocation, performance plot adaptation, performance equipment management, and cultural content implementation.

[0054] For example, in the construction project of an indoor immersive historical exhibition installation (the installation needs to restore the architectural style of the Song Dynasty, support the display of cultural relics and interactive interpretation functions, and meet the requirements of the performance plot (such as the logic of displaying Song Dynasty historical scenes in different areas)), the process is divided into three stages: basic construction, installation of the main equipment, and debugging of the performance equipment (interactive interpretation equipment, exhibition lighting). After the first "basic construction stage" is completed, the staff retrieves the construction data (ground leveling, verticality of the exhibition wall, foundation load-bearing capacity, accuracy of Song Dynasty pattern carving on the exhibition wall, load-bearing capacity of the cultural relic display stand, performance plot adaptation data (matching degree of Song Dynasty scene zoning with the function of the exhibition wall), and basic parameters for the installation of the performance equipment (accuracy of the wiring points of the interpretation equipment)) and adjustment records (correction of verticality deviation of the exhibition wall by 0.8mm, filling of hollow areas on the ground, correction of deviation of the exhibition wall pattern by 0.5mm) from the cloud data center, and conducts further work based on technical standards, cultural presentation standards (restoreability of Song Dynasty architectural style, adaptability of cultural relic display stand), and performance plot adaptation standards (matching degree of scene zoning with the function of the exhibition wall). Upon acceptance, after confirming that the foundation is stable, the dimensions meet the standards, the pattern accuracy is high, the load-bearing capacity of the exhibition stand is satisfactory, and the installation foundation of the performance equipment meets the requirements, a basic acceptance report is generated, including the acceptance conclusion, the qualified items (restoration of Song Dynasty architecture, adaptation of the exhibition stand, and adaptation of the performance plot foundation), and details to be noted (protection of the edges of the cultural relic exhibition stand from bumps). After the subsequent stages are completed, an acceptance report is generated according to the same logic based on the corresponding construction data (equipment assembly accuracy, alignment accuracy of Song Dynasty patterns, parameters of the interpretation equipment, signal synchronization data, programmable synchronization data of the performance equipment (interactive interpretation equipment, exhibition lighting)) and adjustment records (tightness of connectors, misalignment of patterns, optimization of signal / interpretation synchronization, calibration of programmable parameters of the performance equipment). After the entire project is completed, staff will compile the three-stage acceptance reports, risk handling records (handling issues such as excessive motor vibration, vibration of artifact display stands exceeding cultural compliance thresholds, equipment signal interruption, narration-equipment asynchrony, and performance equipment synchronization deviation (narration and lighting asynchrony)), and resource consumption data (working hours at each stage, consumption of steel / electronic components / artifact protection materials, equipment rental duration, and performance equipment debugging hours). A post-project review will then be conducted to assess task execution deviations, cultural presentation compliance rate, performance plot adaptation compliance rate, performance equipment synchronization pass rate, early warning response efficiency, and resource allocation efficiency. The process involved rational analysis, extracting key lessons learned such as "improving efficiency in the prefabrication of Song Dynasty pattern components during the basic stage," "adding electrical and cultural relic protection materials during the debugging stage," and "pre-emptive synchronous debugging of performance equipment." Improvement directions were recorded, including "combining motor selection with booth vibration damping, pre-emptive synchronous debugging of interpretation and equipment, and performance equipment selection with scene-zoned programmable control requirements." The final analysis results were entered into the experience database, updating process suggestions, resource standards, cultural adaptation standards (alignment tolerances for Song Dynasty patterns, booth vibration damping parameters), and performance equipment programmable control parameters (synchronous delay threshold for interpretation and lighting) for "immersive exhibition construction," providing a reference for similar projects in the future.

[0055] In this embodiment, phased acceptance is carried out based on collected and stored construction data and adjustment records, and a phased acceptance report is generated. This includes: constructing a report generation algorithm; inputting collected and stored construction data, adjustment records, quality inspection data, installation accuracy data of the performance equipment, synchronous test data of the program control system, compliance data of cultural content presentation, and compliance evidence into the report generation algorithm, and combining the threshold requirements of the cloud data center risk warning database to conduct indicator evaluation, deviation analysis, and compliance verification of cultural content presentation, thereby generating a phased acceptance report; and uploading the phased acceptance report to the cloud data center as the basis for generating the next phase of construction tasks and optimizing the program control of the performance equipment.

[0056] Among them, the report generation algorithm refers to a technical method that can automatically process input data or information, analyze and integrate key content, and organize it according to preset logic or format to generate a structured report that meets specific needs.

[0057] Understandably, the implementation of this application generates standardized phase acceptance reports through a report generation algorithm, providing support for the generation of the next phase of construction tasks, reducing human error, improving the efficiency and accuracy of phase acceptance, ensuring consistency of acceptance standards across different phases and stages, and guaranteeing the continuity and compliance of each phase of the construction process.

[0058] According to the embodiments of this application, a construction method for the entire process of a mobile performance project is proposed. This method acquires basic project construction data, construction equipment data, technical standard data, historical data from similar projects, cultural content-related data, and performance plot data. It integrates performance equipment parameters, breaking the limitations of isolated multi-source data in traditional construction management and providing comprehensive and coherent data support for full-process control. A fusion early warning algorithm is used to extract trend, mutation, spectrum, correlation features, performance plot adaptation features, and performance equipment installation accuracy features. Through weighted fusion of statistical learning and machine learning models, comprehensive risk correlation parameters are output, constructing a project risk early warning library containing multi-level early warning thresholds, cultural compliance thresholds, performance plot adaptation thresholds, and disposal suggestions. This improves the accuracy of risk identification and the targeted nature of disposal. Simultaneously, early warning data is distributed to an edge computing gateway to complete communication adaptation with construction equipment sensors, performance equipment controllers, and team terminals, ensuring efficient linkage. The construction process is divided into foundation, main structure, and final acceptance stages using a WBS algorithm combined with the performance plot narrative logic. A task generation algorithm is used to distribute process flow, quality standards, performance equipment installation parameters, and other relevant information. The programmable interface requires a progressive construction task book, enabling refined breakdown of the construction process and precise task assignment. Simultaneously, three IMUs are deployed, utilizing an STM32F407 main control chip, an independent SPI bus, and dual timers to synchronously collect vibration data from equipment actuators, performance equipment components, and the surrounding environment. Stable data storage and real-time transmission are achieved through SDIO interface and USB 2.0 CDC protocol, overcoming the shortcomings of traditional monitoring methods, such as single-dimensional monitoring and lagging data processing. During construction, IMU data is compared in real-time with early warning thresholds. Exceeding thresholds triggers an alert and pushes adjustment plans, including performance equipment calibration and programmable synchronization, to the management terminal. The construction task book is simultaneously updated and distributed to the work team terminals, achieving dynamic optimization of construction and ensuring construction accuracy, progress, and the presentation of the performance storyline. Phase acceptance and full-process review generate reports based on collected data, adjustment records, performance equipment operation test data, and cultural content presentation compliance data. Summarized handling records and resource consumption data are updated to the experience database, refining the adaptation experience between the performance storyline, performance equipment, and engineering construction. This provides support for subsequent similar projects, continuously improving the level of intelligent construction management and the overall project quality. This solves the problems of difficult management of moving-type deductive projects, limited early warning, and weak monitoring capabilities in existing technologies.

[0059] The following will illustrate a construction method for the entire process of a moving-style project through a specific embodiment, including: In a project to construct an outdoor, mobile, live-action intangible cultural heritage performance stage (the performance is titled "Intangible Cultural Heritage: The Story of Craftsmen," comprising a three-act narrative structure: "Prologue: Origin," "Middle Act: Inheritance," and "Final Act: Rebirth"), the project team obtained six core data points. According to the following: First, the basic construction data: The project site is located in an urban park, with a construction area of ​​200m × 80m and a total construction period of 60 days. Geological surveys show that the surface soil bearing capacity is 120kPa and the groundwater level is 2.5m deep. The core stage facilities include 5 mobile performance platforms (15m × 8m × 1.2m, adapted to the movement of the "middle section" skill demonstration), 10 sets of lifting lighting rigs (maximum height 10m, matching the lighting angle of the "final chapter"), 3 actor passageways (3m wide × 180m long), and basic locations for performance equipment (pre-embedded positions for projection screen brackets and laser emitter installation). The specifications include: 1) platform, wire track embedded parts, and speaker wall mount anchor points; 2) construction and performance equipment data, including two 25T truck cranes (QY25V type, maximum lifting height 32m, allowable vibration acceleration ≤0.45m / s²) and three mini excavators (PC60-8 type, bucket capacity 0.3m³); and performance equipment parameters (projector PX700 type, resolution 1920×1080, projection distance 5-15m; laser LS-500 type, power 5W, projection angle ±15°; wire track WY-300 type, load capacity 300kg, transport... The performance must meet the following requirements: a walking speed of 0.5-1m / s; a YX-800 sound system with a sound field radius of 20m and a delay of ≤0.3 seconds; and technical standards, including engineering standards such as "steel structure welding flaw detection pass rate ≥98%", "mobile platform stability deviation ≤0.5mm / m", and "concrete curing ≥7 days", as well as performance equipment installation / programming standards (projection lens and screen center deviation ≤5cm, laser level deviation ≤0.5°, wire track straightness ≤1mm / 10m, and "final chapter" wire and lighting timing error ≤0.2 seconds); Fourth, historical data of similar projects, including records of construction period, cost, and risk management of outdoor real-scene projects in neighboring cities (construction period of 58 days, tower crane vibration exceeding limits twice, and "final chapter" wire and lighting not synchronized once), and provincial intangible cultural heritage projects (mobile platform installation delayed by 4 days, laser projection deviation twice); Fifth, performance plot data, with the three acts allocated as the prologue 8 minutes, the middle act 12 minutes, and the final act 10 minutes, and the program control logic of the performance equipment for each act is clear—the "prologue" projection is divided into 3 areas according to the ancient workshop scene, and the "middle act" laser follows the technique. The process is outlined in five sections. The "Final Chapter" wirework follows a "Blooming" trajectory, with sound volume adjusted to match the emotional tone of the story. Sixthly, it includes data related to cultural content, such as the performance's movement diagram, lighting projection angles (30° to highlight costume patterns in the "Middle Chapter"), display board installation dimensions, and the requirements for adapting the performance equipment to the storyline (lasers must align with the "Middle Chapter" skill demonstration area, and sound coverage must match the "Prologue" ancient workshop scene). Records of adjusting the transmitter angle by 0.8° after laser deviation and calibrating control parameters after wirework timing deviations from historical projects are also included.

[0060] Based on the above six types of data, the project team used a fusion early warning algorithm to construct a project risk early warning database: The first step involved cleaning the raw data using a preprocessing function, removing abnormal cost overruns from historical projects, and correcting errors in construction equipment parameters and deviations in the program control parameters of the performance equipment. The second step extracted multi-dimensional features, including project progress trend features, equipment operation spectrum features, data correlation features, and cultural adaptation features, adding performance plot adaptation features (such as the timing deviation trend of the wirework and lighting in the "Final Chapter") and performance equipment installation / program control features (projection screen offset trend, laser projection angle deviation trend). For example, the team focused on extracting the synchronization deviation features between the laser and narration in the "Middle Chapter" and the projection screen switching delay features in the "Prologue". The third step combined statistical learning (linear regression analysis of historical data patterns) and machine learning (random forest model to identify real-time anomalies) to set three levels of early warning thresholds: Level 1 warning corresponds to low risk, such as the vibration acceleration of the mobile platform between 0.3-0.4 m / s², and the projection screen offset of the "Prologue" by 3- Level 1: 5cm. Triggering conditions are comprehensive risk parameters 1-4. Recommended action: "Strengthen real-time monitoring, no construction adjustments required, record data every 5 minutes, and simultaneously check the projected image offset." Level 2: Medium risk. Triggering conditions include tower crane boom vibration acceleration between 0.45-0.6m / s², lighting rig angle deviating 5° from the intangible cultural heritage design value, and a 0.3-0.5 second deviation between the "Final Chapter" wirework and lighting timing. Triggering conditions are comprehensive risk parameters 5-8. Recommended action: "Reduce equipment operating parameters, suspend construction for 10-15 minutes for verification, resume after data returns to normal, and simultaneously correct the lighting rig angle and recalibrate the wirework timing." Level 3: High risk. Triggering conditions include foundation bearing capacity below 100kPa, and the "Middle Chapter" laser projection angle deviating 10° from the design value (risk of burning the audience area). Triggering conditions are comprehensive risk parameters 9-12. Recommended action: "Immediately stop construction, activate the emergency plan for reinforcement, invite a professional testing agency for on-site verification, and urgently shut down the laser equipment and adjust the angle."After the early warning rules are integrated, they are stored in the Alibaba Cloud data center (server configuration: 8 cores, 16GB memory, 1000GB storage capacity, supports simultaneous retrieval by multiple terminals, response latency ≤1 second). Then, the early warning thresholds, equipment parameters, technical standard clauses, cultural compliance requirements, performance plot adaptation requirements, and performance equipment program control parameters are sent to the edge computing gateway (ECG-500 model, supports 4G / 5G communication, including 4 RS485 interfaces and 2 Ethernet ports) to complete communication adaptation. The gateway connects to the construction equipment sensors and performance equipment controllers (projection console, laser console, wire control cabinet, and audio mixing console) through the RS485 interface. Tests show that the data transmission latency is ≤0.5 seconds, and the continuous 24-hour data acquisition success rate is ≥99.8%. It connects to 12 team terminals (industrial tablet PAD-810, Android 11 system, battery life ≥8 hours) and 2 performance equipment debugging terminals through the Ethernet port. The terminal response time to receive task sheets and early warning information is ≤2 seconds, and the information transmission accuracy is 100%.

[0061] Based on edge computing gateways and cloud data centers, and using the WBS algorithm combined with the narrative logic of the "Intangible Cultural Heritage: The Ingenuity of Craftsmen" performance (the scene connection requirements of "Prologue-Middle Chapter-Final Chapter") and the narrative logic of cultural content, the construction process is divided into three core stages: the foundation stage (15 days), including site leveling (3 days, flatness deviation ≤5mm, excavator vibration ≤0.3m / s², daily operation 8:00-18:00), foundation pouring (7 days, bearing capacity ≥120kPa, pouring vibration displacement ≤0.2mm, curing 7 days), and foundation embedded part installation (5 days, embedded part position deviation ≤2mm, reserved installation holes for intangible cultural heritage display boards, embedded parts for performance equipment (projection bracket)). The main structure phase (30 days) includes: steel structure fabrication for the mobile performance platform (8 days, welding flaw detection pass rate ≥98%, reserved fixing slots for intangible cultural heritage props, vibration frequency of processing equipment ≤200Hz, reserved laser projection avoidance slots for the "middle chapter" to prevent obstruction); installation of the lifting lighting rig (10 days, verticality deviation ≤1mm / m, light projection angle deviation ≤2°, tower crane boom vibration ≤0.45m / s², no more than 1 set of hoisting per day, and a 3-meter distance between the lighting rig and the "final chapter" wire track). Anti-interference), installation of performance equipment (7 days) (projection screen bracket installation, horizontal deviation ≤0.3°; laser emitter fixing, alignment deviation with the "Middle Chapter" display area ≤5cm; wire track splicing, straightness ≤1mm / 10m; speaker wall mount installation, matching the "Prologue" sound effect coverage area, vibration acceleration during installation ≤0.3m / s²), actor passage laying (3 days, anti-slip coefficient ≥0.6, display board hole position deviation ≤2mm, equipment vibration displacement ≤0.3mm), equipment pipeline connection (2 days, interface sealing 100%, vibration angular velocity ≤0.15rad / s); final acceptance stage (15 days), including single-machine debugging (5 days, construction equipment noise ≤ 60dB, single-unit performance equipment meets the following standards: projection clarity ≥1080P, laser power 5W±0.2W, wire speed deviation ≤0.1m / s, sound without noise, "prologue" projection switching delay ≤0.5 seconds, debugging vibration ≤0.35m / s²), linkage debugging (5 days, construction equipment coordination delay ≤1 second, multi-unit performance equipment linkage: "final chapter" wire and lighting timing error ≤0.2 seconds, sound and plot sound effect switching deviation ≤0.3 seconds, linkage vibration displacement ≤0.4mm), and final acceptance (5 days, overall pass rate ≥98%, cultural presentation meets the standards, performance plot adaptation meets the standards: three-act equipment trigger node accuracy 100%, environmental vibration ≤0.2m / s²).Subsequently, a task generation algorithm (based on a genetic algorithm, with the objective function of "shortest construction period + optimal resources + cultural compliance + performance plot adaptation compliance", and constraints including technical standards, equipment capacity, and performance equipment control requirements) was used in conjunction with resource constraints (25T tower crane operating for 8 hours per day, steel structure team of 10 people / day, daily cement supply ≤15 tons, performance equipment debugging workers of 4 people / day) to generate a progress-oriented construction task book. Taking the "installation of lifting lighting scaffold" in the main structure stage as an example, the task book includes the process flow (inspection of lighting scaffold components upon arrival, verification of dimensions, welds and laser clearance grooves; tower crane positioning inspection of torque limiters and wire ropes; verification of the "final chapter" wire track position to ensure...) 3-meter spacing; hoisting 2 columns daily, from east to west, with simultaneous angle checks; beam splicing and fixing, 2 people working together with an electric wrench, pre-reserved laser projection hole aligned with the "middle section" display area), quality standards (vertical deviation of column ≤0.8mm / m, light projection angle deviation ≤2°, beam gap ≤0.3mm, laser projection hole deviation from the center of the display area ≤5cm), resource allocation (1 25T tower crane, 6 hoisting team members / day, 2 electric wrenches, 1 performance equipment debugging worker / day to verify the position), risk points (monitoring tower crane vibration ≤0.45m / s², light frame angle deviation exceeding 5° requires adjustment, spacing less than 2.8 meters requires re-hoisting). Simultaneously deploy three IMUs (ICM45686 type, acceleration ±16g, angular velocity ±2000dps, sampling rate 800Hz): the first channel is fixed at the base of the tower crane boom (15 meters from the top) to measure the vertical vibration of the boom; the second channel is attached to the top of the lighting rig, the top of the projection bracket, and the middle section of the wire track to measure the vibration and angular deviation of the construction objects (compared with the adaptation value of the performance plot); the third channel is buried in the surrounding 5-meter green belt, the bottom of the laser mounting platform, and the back of the speaker wall mount to measure the vibration of the environment and the performance equipment (laser horizontality, speaker verticality). The IMU is connected to the STM32F407 main control chip (168MHz) via an independent SPI bus. The TIM2 timer controls the acquisition timing, and the TIM3 timer manages the buffering. The data is stored on a 32GB SD card (FATFS system, generating a TXT file every 5 seconds, containing timestamps, vibration / angle data, and installation deviation data of the simulation equipment) via the SDIO interface. At the same time, it is transmitted to the edge gateway via the USB 2.0 CDC protocol (115200bps baud rate). The gateway filters abnormal data and provides it for risk monitoring and simulation equipment program calibration.

[0062] The construction team advances according to the task sheet. Taking the "lighting rack installation + performance equipment installation" in the main structure stage as an example: The material team inspects the lighting rack columns (9m × 0.3m, Q235 steel, including laser avoidance grooves), projection brackets (6m, load-bearing 50kg), and wire rope hoist tracks (10m, load-bearing 500kg). Use a caliper to measure the dimensional deviation (±0.5mm), the levelness of the projection bracket (±0.3°), and the straightness of the wire rope hoist track (±0.5mm / 10m). Visually inspect that there are no defects in the welds. All are qualified; The machinery team positions the tower crane at the lifting point (X = 120m, Y = 50m), checks the torque limiter (25T・m), height limiter (30m), and the wear of the wire rope (2.5% < 3%). After passing the inspection, record it; The lifting team starts the column lifting, and the performance equipment team synchronously fixes the projection bracket. At this time, the IMU data shows that the vibration of the tower crane jib is 0.32m / s², the angle deviation of the lighting rack is 1.5°, the levelness deviation of the projection bracket is 0.2°, and the levelness deviation of the laser installation platform is 0.2°. All are lower than the thresholds. After the gateway uploads the data, there is no warning. 2 columns and 1 set of projection brackets are installed on the same day, and all parameters meet the standards. During a certain column lifting and wire rope hoist track splicing, a sudden gust of wind of 6m / s occurs. The IMU measures that the vibration of the tower crane jib suddenly rises to 0.58m / s², the angle deviation of the lighting rack is 6°, and the straightness of the wire rope hoist track is 1.2mm / 10m, triggering a secondary warning - the gateway red light flashes and the buzzer alarms. The adjustment plan is pushed to the project manager's terminal and the performance equipment debugging terminal. The content is "Reduce the lifting speed of the tower crane to 0.4m / min, stop for 15 minutes until the gust weakens, adjust the angle of the jib to 25°, correct the angle of the lighting rack and the straightness of the wire rope hoist track, and check that the spacing ≥ 3m"; The project manager confirms the plan in 5 minutes, updates the task sheet to supplement "lifting speed 0.4m / min, check the real-time wind speed ≤ 4m / s before lifting", and issues it to the team terminal. The team makes adjustments in 10 minutes: reduce the speed, stop the operation for 15 minutes (the gust reduces to 3m / s), adjust the angle of the jib, use a jack to correct the straightness of the wire rope hoist track to 0.8mm / 10m. After checking that the IMU data meets the standards, continue construction. 1 column and 1 section of track splicing are completed on the same day. When carrying out the crossbeam splicing and laser emitter calibration, the IMU measures the angular velocity of the X-axis to be 0.14rad / s (close to the threshold of 0.15rad / s), and the laser angle deviation is 4° (close to the threshold of 5°). The terminal prompts "Slow down the splicing speed, clean the rust on the components, and finely adjust the laser angle". The team reduces the rotational speed of the electric wrench to 200r / min. After cleaning the rust, the angular velocity stabilizes at 0.12rad / s. The debugger uses a calibrator to adjust the laser angle deviation to 1.2°. 3 crossbeams and 2 laser emitters are calibrated on the same day, and the parameters meet the standards.

[0063] After each stage, acceptance is conducted based on construction data, adjustment records, performance equipment installation / programming data, and cultural and performance plot adaptation data: For the foundation stage acceptance, site leveling data (maximum deviation 4mm from 200 points), foundation bearing capacity (average 126.4kPa ≥ 120kPa from 5 points), embedded part data (maximum deviation 1.8mm from 30 points, maximum deviation 0.8mm for performance equipment embedded parts), and concrete slump adjustment records (180mm → 165mm) are retrieved. A report generation algorithm is then invoked, and data, material certificates, performance equipment certificates, and testing qualification documents are input. Combined with early warning thresholds and adaptation standards, an acceptance report is generated, clearly stating "15-day construction period, all indicators met." It is recommended to avoid gusts of wind between 2 PM and 4 PM during the main construction phase, and to verify the plot location map before installing the performance equipment. During the main construction phase acceptance, the steel structure welding pass rate was 99.2% (only 1 out of 200 joints required rework), the lighting rig verticality was 0.8mm / m, and the performance equipment installation met standards (projection horizontality ≤0.3°, laser alignment deviation ≤2°, wire track straightness ≤0.8mm / 10m), with effective early warning and handling. During the final phase acceptance, single-machine debugging showed a projection switching delay of 0.3 seconds and a laser power of 5.1W. In the coordinated debugging, the timing error between the wire and lighting in the "Final Chapter" was 0.15 seconds. The final acceptance pass rate was 99.5% (only 2 out of 400 items required rectification), the performance plot was perfectly matched, and the project was completed on schedule within 60 days. A full-process review was conducted, summarizing the acceptance report, risk records (one Level 2 warning, response time 5 minutes, handling time 25 minutes including 8 minutes for wire harness parameter calibration), and resource data (125 tons of steel, saving 3.8%; 82 tons of cement, exceeding budget by 2.5%; 310 man-days of labor, saving 3.1%; 18 man-days of performance equipment debugging, saving 10%). Compared with historical projects, the current risk response is 50% faster, and the performance equipment deviation rate is 0%, lower than the past 5%. The key takeaways were "IMU synchronous monitoring of performance equipment parameters improves adaptability, and WBS combined with the plot optimizes resources." Improvement points were identified, such as "concrete mix ratio needs to be adjusted according to sand and gravel moisture content, and multi-machine linkage debugging of performance equipment needs to be coordinated with the performance team." Finally, the review results were entered into the experience database according to the specifications, and the "outdoor performance construction" content was updated, such as "IMU deployment includes key positions of performance equipment, real-time wind speed is checked before hoisting, and performance equipment installation is verified at plot points," to provide a reference for subsequent projects.

[0064] In summary, this application's embodiments acquire multiple types of core data, utilize a fusion early warning algorithm to construct a risk early warning library and complete communication adaptation, divide construction stages, generate task sheets, and deploy three IMUs to collect vibration data. During construction, data is compared with early warning thresholds in real time to trigger early warnings and adjust tasks. Finally, stage acceptance and full-process review are carried out to achieve standardized management and dynamic risk monitoring throughout the entire project lifecycle. This approach can promptly avoid construction risks, ensure construction quality and efficiency, accumulate project experience, provide reliable references for subsequent similar projects, and promote continuous optimization of the mobile construction process.

[0065] Next, referring to the accompanying drawings, a construction system for a progressive project execution process according to an embodiment of this application is described.

[0066] Figure 4 This is a structural diagram of a construction system for a progressive project execution process according to an embodiment of this application.

[0067] like Figure 4 As shown, the construction system 10 for a progressive project execution process includes: an acquisition module 100, a construction module 200, a generation module 300, an adjustment module 400, and an update module 500.

[0068] The system comprises the following modules: Acquisition module 100, which acquires basic construction data, construction equipment data, technical standard data, historical data of similar projects, cultural content association data, and performance plot data for the performance project; Construction module 200, which, based on the basic construction data, construction equipment data, technical standard data, historical data of similar projects, cultural content association data, and performance plot data, uses a fusion early warning algorithm to construct a project risk early warning database, stores it in a cloud data center, and distributes early warning thresholds and data to an edge computing gateway to complete communication adaptation with construction equipment sensors, performance equipment controllers, and team terminals; and Generation module 300, based on the edge computing gateway and cloud data center, and combined with the narrative logic of the performance plot and scene transition requirements, uses a WBS algorithm to divide the process into basic, main structure, and final acceptance stages, and uses a task generation algorithm to distribute process flows containing procedures for each stage. The project includes a progressive construction task book outlining quality standards, installation parameters for the performance equipment, programmable interface requirements, and cultural presentation requirements. Simultaneously, three IMUs are deployed to collect vibration data from the equipment actuators, the work objects, and the surrounding environment. The adjustment module 400 performs the progressive construction phase according to the task book, comparing the real-time IMU data with risk warning thresholds. If the data exceeds the threshold, an alert is triggered, and the adjustment plan is pushed to the project management terminal. The construction task book is also updated and distributed to the work team terminals. The update module 500, after the progressive construction phase is completed, conducts phase acceptance based on the collected and stored construction data, adjustment records, performance equipment operation test data, and cultural content presentation compliance data, generating a phase acceptance report. At the end of the entire project, the acceptance reports, risk management records, and resource consumption data from each phase are summarized for a full-process review, and the results are updated to the project experience database.

[0069] It should be noted that the foregoing explanation of an embodiment of a construction method for a complete process of a moving-type deductive project also applies to a construction system for a complete process of a moving-type deductive project in this embodiment, and will not be repeated here.

[0070] According to the embodiments of this application, a construction method for the entire process of a mobile performance project is proposed. By acquiring basic construction data, construction equipment data, technical standard data, historical data of similar projects, cultural content-related data, and performance plot data, and integrating performance equipment parameters, the method breaks through the limitations of multi-source data silos in traditional construction management, providing comprehensive and coherent data support for full-process control. The method uses a fusion early warning algorithm to extract trend, mutation, spectrum, correlation features, performance plot adaptation features, and performance equipment installation accuracy features. Through weighted fusion of statistical learning and machine learning models, a comprehensive risk correlation parameter is output, constructing a project risk early warning library containing multi-level early warning thresholds, cultural compliance thresholds, performance plot adaptation thresholds, and disposal suggestions. This improves the accuracy of risk identification and the targeting of disposal. At the same time, the early warning data is sent to the edge computing gateway to complete the communication adaptation with construction equipment sensors, performance equipment controllers, and team terminals, ensuring efficient linkage. By combining the WBS algorithm with the narrative logic of the performance plot, the construction process is divided into the foundation, main structure, and final acceptance stages. In conjunction with the task generation algorithm, a progressive construction task book containing process flow, quality standards, performance equipment installation parameters, and programmable interface requirements is issued. This achieves refined breakdown of the construction process and precise task assignment. Simultaneously, three IMUs are deployed, utilizing an STM32F407 main control chip, an independent SPI bus, and dual timers to synchronously collect vibration data from equipment actuators, performance equipment components, and the surrounding environment. Stable data storage and real-time transmission are achieved through the SDIO interface and USB 2.0 CDC protocol, overcoming the limitations of traditional monitoring methods that suffer from single-dimensionality and slow data processing. Post-construction defects are addressed through real-time comparison of IMU data with early warning thresholds. Exceeding thresholds triggers an alert and pushes an adjustment plan, including equipment calibration and programmable synchronization, to the management terminal. Simultaneously, the construction task sheet is updated and distributed to the work team terminals, enabling dynamic optimization of construction and ensuring construction accuracy, progress, and the presentation of the performance's storyline. Phase acceptance and full-process review generate reports based on collected data, adjustment records, performance equipment operation and testing data, and cultural content presentation compliance data. These reports summarize handling records and resource consumption data, updating them to the experience database. The adaptation experience between the performance storyline, performance equipment, and construction is refined to support subsequent similar projects, continuously improving the level of intelligent construction management and the overall project quality. This solves the problems of difficult management, limited early warning systems, and weak monitoring capabilities in existing technologies for mobile performance projects.

[0071] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0072] When the processor 502 executes the program, it implements a construction method for the entire process of a progressive deductive project provided in the above embodiments.

[0073] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0074] The memory 501 is used to store computer programs that can run on the processor 502.

[0075] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0076] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0077] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0078] The processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0079] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for the construction of a progressively unfolding project.

[0080] Furthermore, this application also provides a computer program product, including a computer program or instructions, which, when executed, implement the aforementioned method for a progressive, deductive project construction process.

[0081] In the description of this specification, the references to "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0082] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0083] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0084] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0085] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0086] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A construction method for a project that involves a continuous, step-by-step process, characterized in that: include: Obtain basic construction data, construction equipment data, technical standard data, historical data of similar projects, cultural content association data, and performance plot data for the performance project; Based on the basic construction data, construction equipment data, technical standard data, historical similar project data, cultural content association data, and performance plot data of the performance project, a project risk early warning database is constructed using a fusion early warning algorithm. This database is stored in a cloud data center, and the early warning thresholds and data are sent to the edge computing gateway to complete the communication adaptation with construction equipment sensors, performance equipment controllers, and team terminals. Based on the aforementioned edge computing gateway and cloud data center, and combined with the narrative logic of the performance plot and scene transition requirements, the process is divided into the basic, main structure, and final acceptance stages using the WBS algorithm. A task generation algorithm is used to issue a progressive construction task book containing process flow, quality standards, performance equipment installation parameters, program control interface requirements, and cultural presentation requirements for each stage. At the same time, three IMUs are deployed to collect vibration data of equipment actuators, construction objects, and the surrounding environment. According to the described construction task book, the construction is carried out in the construction phase, and the data collected in real time by the IMU is compared with the threshold of the risk warning database. If the data exceeds the threshold, an early warning is triggered, the adjustment plan is pushed to the project management terminal, and the construction task book is updated and distributed to the team terminal. After the construction of the aforementioned phase is completed, phase acceptance is carried out based on the collected and stored construction data, adjustment records, performance equipment operation test data, and cultural content presentation compliance data, and a phase acceptance report is generated. After the entire project process is completed, the acceptance reports of each phase, risk management records, and resource consumption data are summarized, a full-process review is carried out, and the results are updated to the project experience database.

2. The construction method for the entire process of a moving, interactive project according to claim 1, characterized in that, Using a fusion-based early warning algorithm, a project risk early warning database is constructed, including: Construct a fusion early warning algorithm; The processed basic construction data, construction equipment data, technical standard data, historical similar project data, cultural content association data, and performance plot data of the performance project are input into the fusion early warning algorithm to extract trend features, mutation features, spectrum features, correlation features, performance plot adaptation features, and performance equipment installation accuracy features. The algorithm then performs importance assessment and screening and outputs comprehensive risk association parameters. Based on comprehensive risk correlation parameters, combined with technical standard data and historical data of similar projects, multi-level early warning thresholds and corresponding early warning levels, triggering conditions and handling suggestions are set, integrated into risk early warning rules and uploaded to the cloud data center to form a project risk early warning library.

3. The construction method for the entire process of a moving, interactive project according to claim 1, characterized in that, The formula for the fusion early warning algorithm is as follows: ； ； ； ； ； ； in, This is the processed multi-source fusion feature matrix; D is the preprocessing function; D is the original multi-source dataset. As a trend feature; It is a mutation characteristic; Spectral characteristics; It is a relevance feature; Features adapted to the performance's storyline; To demonstrate the installation accuracy characteristics of the equipment; The degree of anomaly in the output of the statistical learning model; These are the parameters for the statistical model. The risk score output by machine learning; For machine learning model parameters; For comprehensive risk-related parameters; These are the weighting coefficients; is the threshold for the k-th warning level; k is the warning level number.

4. The construction method for the entire process of a moving, interactive project according to claim 1, characterized in that, Based on the aforementioned edge computing gateway and cloud data center, the process is divided into three stages—foundation, main structure, and final acceptance—using a WBS algorithm. A task generation algorithm is then used to issue a progressive construction task sheet, including process flow and quality standards, to each stage, including: Construct the WBS algorithm and task generation algorithm; The WBS algorithm is input into the basic construction data, technical standard data, performance plot data, performance equipment technical specifications, cultural content related data and relevant requirements in the risk warning database of the performance project stored in the cloud data center. The WBS algorithm is then combined with the narrative logic of the performance plot to define the stage boundaries, sort the procedures and map the quality indicators, and obtain the stage division results including stages, procedures, quality indicators, performance equipment installation nodes, risk thresholds and cultural adaptation requirements. Based on the stage division results, a task generation algorithm is used, combined with technical standard data and resource constraints, to allocate resources and arrange construction periods. At the same time, risk warning rules are embedded in the process execution stage to generate a moving construction task book. The mobile construction task sheet is sent to the edge computing gateway, which then distributes it to the corresponding work team terminals.

5. The construction method for the entire process of a moving, interactive project according to claim 1, characterized in that, Three IMUs are deployed to collect vibration data from the equipment actuators, the construction object, and the surrounding environment, including: It uses an STM32F407 main control chip and connects three inertial measurement units through three independent SPI buses; The TIM2 and TIM3 timers of the STM32F407 are used to control the acquisition timing, and vibration data of the device actuator, the performance device actuator, the performance stage and the surrounding environment are acquired synchronously at a default sampling rate of 800Hz. The vibration data is expanded via the SDIO interface using an SD card. Based on the FATFS file system, segmented TXT files are generated and stored every 5 seconds. The data is then transmitted in real time to the edge computing gateway and the programmable control console of the performance device via the USB 2.0 CDC protocol.

6. The construction method for the entire process of a moving, interactive project according to claim 1, characterized in that, Based on the collected and stored construction data and adjustment records, phase acceptance is carried out, and a phase acceptance report is generated, including: Build a report generation algorithm; The collected and stored construction data, adjustment records, quality inspection data, installation accuracy data of the performance equipment, program-controlled synchronous test data, cultural content presentation compliance data, and compliance evidence are input into the report generation algorithm. Combined with the threshold requirements of the cloud data center risk warning library, the algorithm performs indicator evaluation, deviation analysis, and cultural content presentation compliance verification to generate a phase acceptance report. Upload the aforementioned phase acceptance report to the cloud data center as the basis for generating the next phase of construction tasks and optimizing the equipment control program.

7. A construction system for a project that demonstrates the entire process in a mobile manner, characterized in that, include: The acquisition module is used to acquire basic construction data, construction equipment data, technical standard data, historical data of similar projects, cultural content association data, and performance plot data for the performance project. The construction module is used to build a project risk early warning database based on the basic construction data, construction equipment data, technical standard data, historical similar project data, cultural content association data and performance plot data of the performance project, using a fusion early warning algorithm. The database is stored in the cloud data center, and the early warning thresholds and data are sent to the edge computing gateway to complete the communication adaptation with the construction equipment sensors, performance equipment controllers and team terminals. The generation module, based on the edge computing gateway and cloud data center, combines the narrative logic of the performance plot and scene transition requirements. It divides the process into the basic, main structure, and final acceptance stages using the WBS algorithm. It also uses the task generation algorithm to issue a progressive construction task book containing the process flow, quality standards, performance equipment installation parameters, program control interface requirements, and cultural presentation requirements for each stage. At the same time, it deploys three IMUs to collect vibration data of the equipment actuators, construction objects, and the surrounding environment. The adjustment module performs construction in the advancing phase according to the advancing construction task book, and compares the data collected in real time by the IMU with the threshold of the risk warning database. If the data exceeds the threshold, an early warning is triggered, the adjustment plan is pushed to the project management terminal, and the construction task book is updated and distributed to the team terminal. The update module, after the completion of the construction phase, conducts phase acceptance based on the collected and stored construction data, adjustment records, performance equipment operation test data, and cultural content presentation compliance data, and generates a phase acceptance report. After the completion of the entire project process, it summarizes the acceptance reports of each phase, risk handling records, and resource consumption data, conducts a full process review, and updates the project experience database.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the construction method for the entire process of a progressive deductive project as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When a computer program or instruction is executed, it implements a construction method for the entire process of a progressive deductive project as described in any one of claims 1-6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When a computer program or instruction is executed, it implements a construction method for the entire process of a progressive deductive project as described in any one of claims 1-6.

Images