A three-dimensional visualization operation and maintenance management system and method for building facilities

Abstract

The present invention relates to a three-dimensional visualization operation and maintenance management system and method for building facilities. The system includes a three-dimensional modeling module for equipment and facilities: based on the original design data of the equipment and facilities, the BIM technology is used for three-dimensional modeling, the structure is converted into a detailed three-dimensional space, and the three-dimensional model is rendered and displayed in real time in combination with visualization equipment, and a long short-term memory artificial neural network is used to optimize the model and generate a three-dimensional model data set. In the present invention, the long short-term memory artificial neural network is used to optimize the three-dimensional model, which improves the accuracy and detail integrity of the three-dimensional model in a complex building environment, and performs fault diagnosis and response measures. It identifies and analyzes equipment failures and potential safety hazards in real time, provides a fast and accurate response plan, improves the safety and reliability of the system, and uses collision detection and area division optimization methods to achieve a comprehensive improvement from model optimization, dynamic resource configuration to fault diagnosis and safety analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional visualization management, and in particular to a three-dimensional visualization operation and maintenance management system and method for building facilities. Background Art

[0002] The field of 3D visualization management technology focuses on using 3D graphics and models to enhance the visual representation and interaction of data. In terms of building management and operation, 3D visualization technology allows users to view complex building information and operational data in an intuitive way, improving decision-making efficiency, reducing misunderstandings, and improving the overall process of facility management.

[0003] The purpose of the three-dimensional visualization operation and maintenance management system for building facilities is to achieve high efficiency and accuracy in building operation and maintenance. Through real-time data updates and model interactions, the operation and maintenance team can quickly respond to various situations, optimize the maintenance and management of building facilities, improve the operational efficiency of building facilities, extend their service life, and ensure the safety of users.

[0004] Traditional systems are deficient in real-time fault prediction, environmental monitoring, and response capabilities. They rely on static three-dimensional models and preset operation and maintenance strategies, lack the ability to dynamically update and intelligently analyze, and are slow to respond to sudden equipment failures and environmental changes. They rely on preset thresholds and rules, making it difficult to cope with complex and changing actual operating environments, and are prone to false alarms or missed alarms, affecting the reliability and security of the system. The lack of an efficient anomaly detection mechanism makes environmental data monitoring incomplete, unable to warn of potential risks in a timely manner, resulting in delayed maintenance and management work, increased operating costs, and shortened facility life. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a three-dimensional visualization operation and maintenance management system and method for building facilities.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A three-dimensional visual operation and maintenance management system for building facilities comprises:

[0007] Equipment and facility 3D modeling module: Based on the original design data of equipment and facilities, BIM technology is used for 3D modeling, the structure is converted into a detailed 3D space, and the 3D model is rendered and displayed in real time using visualization equipment. At the same time, long short-term memory artificial neural network is used for model optimization to generate a 3D model data set;

[0008] Resource dynamic configuration module: Based on the three-dimensional model data set, it monitors the operation status of the equipment and the usage of resources in real time, dynamically adjusts resource allocation, updates monitoring records, and generates equipment operation and resource management logs;

[0009] Energy consumption optimization module: Based on the equipment operation and resource management logs, analyze the equipment operation environment, optimize resource allocation and utilization efficiency, optimize regional division and resource scheduling, and generate spatial optimization analysis results;

[0010] Real-time monitoring and response module: Based on the equipment operation and resource management logs and space optimization analysis results, it conducts real-time monitoring of equipment status and tracking of environmental variables, detects and responds to equipment failures or safety hazards, uses Bayesian networks to perform fault diagnosis and formulate response measures, and generates emergency response measures;

[0011] Equipment loss analysis module: Based on the emergency response measures and space optimization analysis results, conduct a comprehensive analysis of environmental and safety data, evaluate potential risk points, aggregate data and classify risk levels to generate a risk assessment report;

[0012] Equipment maintenance and repair strategy module: Based on the risk assessment report, optimize and adjust the equipment maintenance cycle and strategy, update the maintenance plan, optimize the cost and efficiency according to the equipment performance tracking and historical maintenance records, and generate a maintenance optimization strategy.

[0013] As a further solution of the present invention, the equipment and facility three-dimensional modeling module includes a raw data parsing submodule, a model refinement submodule and a model optimization submodule, wherein:

[0014] Original data analysis submodule: Based on the original design data of equipment and facilities, the module performs format recognition and decoding on the data, builds a primary three-dimensional framework, decomposes the framework hierarchy and identifies nodes, and generates a preliminary three-dimensional structure diagram;

[0015] Model refinement submodule: Based on the preliminary three-dimensional structure diagram, check the connection points and interfaces of each component, adjust the docking and contact surfaces of the components, and adjust the spatial relationship and size coordination between the components to generate a detailed three-dimensional model, and use visualization equipment for dynamic display;

[0016] Model optimization submodule: Based on the detailed three-dimensional model, a long short-term memory artificial neural network is used to analyze the structural characteristics and load distribution of the model, and the overall stability and load-bearing capacity of the model are enhanced by adjusting the supporting structure and heavy load points to generate a three-dimensional model data set.

[0017] As a further solution of the present invention, the long short-term memory artificial neural network is according to the formula:

[0018]

[0019] in: For time The output value of is the weight matrix between the hidden layer and the output layer, is the activation function, is the weight matrix between the input layer and the hidden layer, For time The input sequence is For time The hidden state of is the material stiffness matrix, is the damping coefficient, is the hidden layer bias vector, is the output layer bias vector.

[0020] As a further solution of the present invention, the resource dynamic configuration module includes a resource positioning submodule, a resource configuration submodule and a configuration record updating submodule, wherein:

[0021] Resource location submodule: based on the three-dimensional model data set, scans and calibrates the current location of the equipment and resources, and generates resource location information by updating the location information;

[0022] Resource configuration submodule: Based on the resource location information, monitor the status of equipment and resources in real time, and generate resource monitoring reports by analyzing resource usage and equipment operation status;

[0023] Configuration record update submodule: Based on the resource monitoring report, the existing monitoring records are revised, and the monitoring records are updated synchronously by continuously tracking the changes in device status and resource usage, and the device operation and resource management logs are generated.

[0024] As a further solution of the present invention, the energy consumption optimization module includes a layout environment analysis submodule, a resource conflict detection submodule and a regional configuration optimization submodule, wherein:

[0025] Layout environment analysis submodule: Based on the equipment operation and resource management logs, the module extracts data on the actual location and environmental conditions of the equipment. By identifying the space occupancy and resource consumption of the equipment, the module analyzes the distribution status of the equipment and resources, establishes a spatial association model between the equipment and resources, and generates the equipment distribution and environmental status.

[0026] Resource conflict detection submodule: Based on the device distribution and environmental status, it screens the data of resource usage between devices, detects resource usage conflicts between devices by identifying overlapping or insufficient areas of resource allocation, extracts data features of conflicting and inefficient areas, and generates resource conflict and utilization analysis;

[0027] Regional configuration optimization submodule: Based on resource conflict and utilization analysis, it re-divides the regions of equipment and resources, optimizes the distribution pattern of resources in space, adjusts the resource scheduling strategy, reallocates the order and priority of resource use, optimizes the operating environment of equipment, and generates spatial optimization analysis results.

[0028] As a further solution of the present invention, the real-time monitoring response module includes a state monitoring submodule, an environment tracking submodule and a fault response submodule, wherein:

[0029] Status monitoring submodule: based on the equipment operation and resource management log and the space optimization analysis results, collect real-time data on the equipment status, analyze the current operation status of the equipment by monitoring the equipment's operating parameters and performance indicators, record the equipment's real-time operation data, and generate status monitoring data;

[0030] Environmental tracking submodule: Based on the status monitoring data, it tracks the environmental variables around the equipment in real time, monitors the changes in environmental conditions, analyzes the impact of the environment on equipment operation, records dynamic changes in the environment, and generates environmental tracking data;

[0031] Fault response submodule: Based on the environmental tracking data, real-time detection of equipment failures or safety hazards is performed. By analyzing the relationship between equipment status and environmental variables, Bayesian networks are used to diagnose and assess risks of faults, and corresponding response measures are formulated and recorded to generate emergency response measures.

[0032] As a further solution of the present invention, the Bayesian network is according to the formula:

[0033]

[0034] in: For the given evidence The following failure occurs The posterior probability of For data collection in a specific environment The following failure occurs The prior probability of Environmental data collection The prior probability of For evidence The marginal probability of Environmental data collection The weight coefficient of is the severity of the fault impact, The time when the fault occurred.

[0035] As a further solution of the present invention, the equipment loss analysis module includes a data aggregation submodule, a risk assessment submodule and a level classification submodule, wherein:

[0036] Data aggregation submodule: based on the emergency response measures and the spatial optimization analysis results, collect data related to the environment and safety, remove noise and redundant information through data cleaning, organize the data into a structured format, comprehensively analyze the correlation and trend of multi-source data, and generate comprehensive environmental data;

[0037] Risk assessment submodule: Based on the comprehensive environmental data, identify potential risk points, analyze key variables in the data, quantitatively assess the probability of occurrence and possible impact of risks, combine qualitative analysis methods, identify and assess environmental and safety risks, and generate risk identification results;

[0038] Level classification submodule: Based on the risk identification results, the identified risks are classified into levels. Through multi-dimensional standards, including the scope of impact, severity, and controllability, a risk level model is established and applied to classify and prioritize risks and generate a risk assessment report.

[0039] As a further solution of the present invention, the equipment maintenance and repair strategy module includes a cycle optimization submodule, a strategy adjustment submodule and a plan update submodule, wherein:

[0040] Cycle optimization submodule: Based on the risk assessment report, analyze the current maintenance cycle of the equipment, identify potential deficiencies and risk factors in the maintenance cycle, optimize and adjust the maintenance cycle, reset the maintenance frequency and interval time of the equipment, and generate an optimized maintenance cycle;

[0041] Strategy adjustment submodule: based on the optimized maintenance cycle, re-evaluate and adjust the equipment maintenance strategy, optimize the maintenance content and measures by analyzing the equipment performance data, combined with the failure and repair conditions in the historical maintenance records, and generate an optimized maintenance strategy;

[0042] Plan update submodule: Based on the optimized maintenance strategy, update the overall maintenance plan of the equipment, combine the real-time monitoring data, refer to the historical maintenance records, adjust the schedule and resource allocation of the maintenance work, and generate a maintenance optimization plan.

[0043] A three-dimensional visualization operation and maintenance management method for building facilities, which is executed based on the above-mentioned three-dimensional visualization operation and maintenance management system for building facilities, and comprises the following steps:

[0044] Step 1: Based on the original design data of the equipment and facilities, analyze the structural information and node relationships involved in the design data, identify and decode the data format, call the parsed node information to establish a three-dimensional framework structure, and generate a preliminary three-dimensional structure diagram by decomposing the framework hierarchy and identifying the nodes;

[0045] Step 2: Based on the preliminary 3D structural diagram, combined with BIM technology, a visual display is performed on the 3D model, each connection point and interface position of the model is checked item by item, the spatial relationship and size coordination between the components are analyzed, the 3D model display status is updated, a detailed 3D model is generated, and a dynamic display is performed using a visualization device;

[0046] Step 3: Based on the detailed 3D model, by locating and analyzing the support structures and heavy load points in the 3D model, extracting and calculating parameters, determining the strength distribution of each support structure, optimizing and adjusting each heavy load point in combination with the load distribution information, gradually enhancing the overall stability of the model, and generating a 3D model data set;

[0047] Step 4: Based on the three-dimensional model data set, scan the current position of the equipment and resources in the building facilities, calibrate and integrate the positioning information of the resources and equipment by updating the position information in real time, and generate resource positioning information;

[0048] Step 5: Based on the resource location information, the device operation status and resource usage are continuously monitored, the device operation parameters are compared and analyzed with the resource usage parameters, the monitoring results are recorded, and a resource monitoring report is generated;

[0049] Step 6: Based on the resource monitoring report and the three-dimensional model data set, the resource allocation situation in the building facilities is divided into regions, and the resource usage order and priority of each region are reallocated by identifying and adjusting the configuration strategy of resource conflicts and inefficient regions, so as to generate a spatial optimization analysis result;

[0050] Step 7: Based on the spatial optimization analysis results, call the equipment status data and environmental variable data, dynamically monitor the real-time operation of the equipment, identify the wear and loss of the equipment, generate emergency response measures, and combine the emergency response measures to formulate an equipment maintenance plan, perform preventive maintenance or replacement of key components, and ensure the normal operation and safety of the equipment through diagnostic analysis.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are:

[0052] 1. In the present invention, the long short-term memory artificial neural network is used to optimize the three-dimensional model, which improves the accuracy and detail integrity of the three-dimensional model in a complex building environment, and ensures the high fidelity of the model and operability in practical applications;

[0053] 2. In the present invention, the Bayesian network is used for fault diagnosis and response measures formulation, which can identify and analyze equipment failures and potential safety hazards in real time, provide fast and accurate response solutions, and improve the safety and reliability of the system;

[0054] 3. In the present invention, collision detection and area division optimization methods are used to effectively solve the spatial conflicts between equipment, ensure the rational allocation and use of resources, enhance the intelligent level of building operation and maintenance management, achieve comprehensive improvement from model optimization, dynamic resource allocation to fault diagnosis and safety analysis, and significantly improve the operation efficiency and management effect of building facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a system flow chart of the present invention;

[0056] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0057] Figure 3 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] Embodiment 1

[0060] See also Figure 1 The present invention provides a technical solution: a three-dimensional visualization operation and maintenance management system for building facilities, comprising:

[0061] Equipment and facility 3D modeling module: Based on the original design data of equipment and facilities, BIM technology is used for 3D modeling, the structure is converted into a detailed 3D space, and the 3D model is rendered and displayed in real time using visualization equipment. At the same time, long short-term memory artificial neural network is used for model optimization to generate a 3D model data set;

[0062] Resource dynamic configuration module: Based on the 3D model data set, it monitors the operation status of the equipment and the usage of resources in real time, dynamically adjusts resource allocation, updates monitoring records, and generates equipment operation and resource management logs;

[0063] Energy consumption optimization module: Based on the equipment operation and resource management logs, analyze the equipment operation environment, optimize resource allocation and utilization efficiency, optimize regional division and resource scheduling, and generate spatial optimization analysis results;

[0064] Real-time monitoring and response module: Based on the equipment operation and resource management logs and space optimization analysis results, it conducts real-time monitoring of equipment status and tracks environmental variables, detects and responds to equipment failures or safety hazards, uses Bayesian networks to perform fault diagnosis and formulate response measures, and generates emergency response measures;

[0065] Equipment loss analysis module: Based on the emergency response measures and space optimization analysis results, conduct a comprehensive analysis of environmental and safety data, evaluate potential risk points, aggregate data and classify risk levels to generate a risk assessment report;

[0066] Equipment maintenance and repair strategy module: Based on the risk assessment report, optimize and adjust the equipment maintenance cycle and strategy, update the maintenance plan, optimize the cost and efficiency according to the equipment performance tracking and historical maintenance records, and generate maintenance optimization strategies;

[0067] See also Figure 2 The equipment and facility 3D modeling module includes a raw data analysis submodule, a model refinement submodule, and a model optimization submodule, among which:

[0068] Original data analysis submodule: Based on the original design data of equipment and facilities, the module performs format recognition and decoding on the data, builds a primary three-dimensional framework, decomposes the framework hierarchy and identifies nodes, and generates a preliminary three-dimensional structure diagram;

[0069] Model refinement submodule: Based on the preliminary 3D structure diagram, check the connection points and interfaces of each component, adjust the docking and contact surfaces of the components, and adjust the spatial relationship and size coordination between components to generate a detailed 3D model, and use visualization equipment for dynamic display;

[0070] Model optimization submodule: Based on the detailed 3D model, the long short-term memory artificial neural network is used to analyze the structural characteristics and load distribution of the model, and the overall stability and load-bearing capacity of the model are enhanced by adjusting the support structure and heavy load points to generate a 3D model data set;

[0071] In the original data parsing submodule, based on the original design data of the equipment and facilities, a data parsing algorithm is used to identify and decode the data format. During the parsing process, the input data format is defined as a CAD file, which is converted into JSON format. The parsing function is called to convert the two-dimensional plane map into three-dimensional coordinate data. By traversing each node, the node relationship and hierarchical structure in the data are identified to build a primary three-dimensional framework. The parsed node data includes node ID, node type, connection relationship, etc. A hierarchical decomposition algorithm is used to decompose the three-dimensional framework into multiple sub-frames, and each sub-frame is marked with nodes, and the node position information and connection relationship are recorded to generate a preliminary three-dimensional structure diagram.

[0072] In the model refinement submodule, based on the preliminary 3D structure diagram, the geometric adjustment algorithm is used to check the connection points and interfaces of each component. By comparing the node coordinates one by one, the alignment of each node is ensured, the docking and contact surfaces of the components are adjusted, and the spatial relationship and size coordination between the components are adjusted by using the iterative optimization method. The component size is adjusted by calling the optimization function. The parameters include the length, width and height of the component. The distance measurement function is used to calculate the minimum distance between the components, and the component position is adjusted to meet the preset spatial relationship. A detailed 3D model is generated and dynamically displayed using visualization equipment.

[0073] In the model optimization submodule, based on the detailed three-dimensional model, a long short-term memory artificial neural network is used to analyze the mechanical properties and load distribution of the model. By adjusting the support structure and overload points, the overall stability and bearing capacity of the model are optimized. The LSTM network is used for time series prediction. The input data is defined as the historical load data of the component. The number of LSTM layers is set to 2, the number of hidden layer nodes is 50, the activation function is tanh, the output layer is a fully connected layer, and the gradient descent optimizer is used to adjust the parameters of the support structure including position, angle and connection strength to generate a three-dimensional model data set.

[0074] Long short-term memory artificial neural network, according to the formula:

[0075]

[0076] in: For time The output value of is the weight matrix between the hidden layer and the output layer, is the activation function, is the weight matrix between the input layer and the hidden layer, For time The input sequence is For time The hidden state of is the material stiffness matrix, is the damping coefficient, is the hidden layer bias vector, is the output layer bias vector;

[0077] Execution process: First, collect the 3D model data of the building facilities, including the displacement and stress information of the nodes, as the input sequence At time step Input, at the same time, the hidden state of the previous time step It is used to capture long-term dependencies in the sequence. In order to improve the prediction accuracy of the model, the physical properties of the material are combined, and the material stiffness matrix At time step It represents the elastic modulus of the material under the action of external force, which is calculated through material properties and experimental data. Used to describe the energy dissipation capacity of a material under dynamic loads, usually obtained from experiments or data fitting, using a weight matrix For the input sequence , the hidden state at the previous time step And physical parameters and Perform a linear transformation and pass the bias Adjust the baseline activation level, through the activation function After the nonlinear transformation, the hidden state of the current time step is obtained, which reflects the internal characteristics of the system at the current time step. Then, the weight matrix is ​​used Map the hidden state to the output layer, combined with the bias of the output layer , generates the prediction output for the current time step , which represents the mechanical response value of the building facility under the current operating conditions, including possible deformation and stress concentration areas, through continuous adjustment The value of optimizes the accuracy of the model prediction results.

[0078] See also Figure 2 The resource dynamic configuration module includes a resource positioning submodule, a resource configuration submodule and a configuration record update submodule, wherein:

[0079] Resource location submodule: Scans and calibrates the current location of equipment and resources based on the 3D model data set, and generates resource location information by updating the location information;

[0080] Resource configuration submodule: Based on resource location information, monitor the status of equipment and resources in real time, and generate resource monitoring reports by analyzing resource usage and equipment operation status;

[0081] Configuration record update submodule: Based on the resource monitoring report, the existing monitoring records are revised, and the monitoring records are updated synchronously by continuously tracking the changes in device status and resource usage, and the device operation and resource management logs are generated;

[0082] In the resource positioning submodule, the current position of the equipment and resources is scanned and calibrated based on the three-dimensional model data set. Laser scanning technology is used to perform spatial scanning with a laser rangefinder to obtain the three-dimensional coordinate data of the equipment and resources. The scanned data is processed using a point cloud processing algorithm to convert the point cloud data into specific location information. The position of each device and resource is calibrated through triangulation, and the coordinates of each device and resource are updated and stored in the database to generate resource positioning information.

[0083] In the resource configuration submodule, the distribution of resources and equipment is analyzed based on resource location information. The simulated annealing algorithm is used to initialize the initial positions of resources and equipment, calculate the space efficiency of the current configuration scheme, simulate different configuration schemes, and continuously adjust the positions of resources and equipment to calculate the space utilization rate of each configuration scheme. The configuration scheme with the highest space efficiency is selected, the layout of resources is reallocated and adjusted, the configuration scheme is recorded in the database, and a resource monitoring report is generated.

[0084] In the configuration record update submodule, the existing configuration records are revised based on the resource configuration plan. The version control system is used to identify the changed parts by comparing the existing configuration records with the new configuration plan, record the changed parts, merge them with the existing records, and update the configuration records. By continuously tracking the changes in resource configuration, the records of each update are stored in the database to generate equipment operation and resource management logs.

[0085] See also Figure 2 ,The energy consumption optimization module includes a layout environment analysis submodule, a resource conflict detection submodule, and a regional configuration optimization submodule, where:

[0086] Layout environment analysis submodule: Based on the equipment operation and resource management logs, the module extracts data on the actual location and environmental conditions of the equipment. By identifying the space occupancy and resource consumption of the equipment, the module analyzes the distribution status of the equipment and resources, establishes a spatial association model between the equipment and resources, and generates the equipment distribution and environmental status.

[0087] Resource conflict detection submodule: Based on the device distribution and environmental status, it screens the data of resource usage between devices, detects resource usage conflicts between devices by identifying overlapping or insufficient areas of resource allocation, extracts data features of conflicting and inefficient areas, and generates resource conflict and utilization analysis;

[0088] Regional configuration optimization submodule: Based on resource conflict and utilization analysis, it re-divides the regions of equipment and resources, optimizes the distribution pattern of resources in space, adjusts the resource scheduling strategy, reallocates the use order and priority of resources, optimizes the operating environment of equipment, and generates spatial optimization analysis results;

[0089] In the layout environment analysis submodule, based on the equipment operation and resource management logs, the K-means clustering algorithm is used to perform cluster analysis on the data of the actual location and environmental conditions of the equipment. The parameters include the K value set to 5, the maximum number of iterations to 300, and the distance metric using Euclidean distance. The extracted equipment location data and environmental condition data are classified and processed. The distance from each equipment point to the cluster center is calculated through cyclic iterations, and each equipment point is reallocated to the cluster center with the smallest distance. The space occupancy of the equipment is classified and identified according to the calculation results, and the equipment and resource distribution cluster information is generated. The DBSCAN density clustering algorithm is used, and the parameters include the distance threshold set to 0.5 and the minimum number of samples to 10. The distribution status of equipment and resources is identified, the high-density areas are detected and identified, and the equipment distribution and environmental status are generated;

[0090] In the resource conflict detection submodule, based on the device distribution and environmental status, a common space mode algorithm is used. The constraints include the capacity of resource allocation, time window and spatial location constraints. Data screening is performed on the resource usage between devices. By comparing and calculating the capacity of resource allocation, the overlapping areas of resources are detected, and the conflicts between time windows and spatial locations are analyzed. The conflict detection function is called to verify whether the resource usage constraints are met item by item, and the data features of the conflict area and the inefficient area are extracted to generate resource conflict and utilization analysis.

[0091] In the regional configuration optimization submodule, based on resource conflict and utilization analysis, a genetic algorithm is used to re-divide the areas of equipment and resources. The algorithm parameters include the population size set to 100, the crossover probability to 0.8, the mutation probability to 0.05, and the fitness function to maximize resource utilization. The resource distribution pattern in the region is optimized. Specifically, selection, crossover and mutation operations are used to screen out individuals with the optimal resource distribution pattern through multiple generations of evolution, and the order and priority of resource use are reconfigured to generate spatial optimization analysis results.

[0092] See also Figure 2 The real-time monitoring response module includes a state monitoring submodule, an environment tracking submodule and a fault response submodule, wherein:

[0093] Status monitoring submodule: Based on the equipment operation and resource management logs and space optimization analysis results, it collects real-time data on the equipment status, analyzes the current operating status of the equipment by monitoring the equipment's operating parameters and performance indicators, records the equipment's real-time operating data, and generates status monitoring data;

[0094] Environmental tracking submodule: Based on the status monitoring data, it tracks the environmental variables around the equipment in real time, monitors the changes in environmental conditions, analyzes the impact of the environment on equipment operation, records the dynamic changes in the environment, and generates environmental tracking data;

[0095] Fault response submodule: Based on environmental tracking data, it performs real-time detection of equipment failures or safety hazards. By analyzing the relationship between equipment status and environmental variables, it uses Bayesian networks to diagnose and assess the risks of failures, formulates and records corresponding response measures, and generates emergency response measures.

[0096] In the status monitoring submodule, based on the conflict resolution results, the real-time monitoring of the equipment status is carried out. The data acquisition system is used to collect equipment operation data, including temperature, pressure, vibration and other parameters, through sensors installed on the equipment. The collected data is cleaned and sorted using data processing algorithms, and the sorted data is stored in the database. The data acquisition frequency and threshold parameters are defined, and the data is analyzed and processed through the real-time data stream processing framework to generate status monitoring data.

[0097] In the environmental tracking submodule, real-time tracking of environmental variables is performed based on state monitoring data. Environmental sensor networks are used to record environmental changes, including humidity, temperature, air quality and other parameters. Data fusion algorithms are used to fuse and correct multiple sensor data. The environmental monitoring system classifies and stores data, sets data update frequency and alarm thresholds, and visualizes environmental data through a real-time monitoring platform to generate environmental tracking data.

[0098] In the fault response submodule, based on the environmental tracking data, equipment failures or safety hazards are detected in real time, fault diagnosis is performed, and Bayesian networks are used for analysis and inference. By building a fault probability model, the equipment status and environmental data are jointly analyzed, the prior probability and conditional probability of faults are set, and the posterior probability is calculated using Bayesian theorem. The possible fault type and location are inferred, response measures are formulated, and the fault response system is called to process and record the detected faults, generate emergency response measures, and generate results consistent with the module.

[0099] Bayesian network, according to the formula:

[0100]

[0101] in: For the given evidence The following failure occurs The posterior probability of For data collection in a specific environment The following failure occurs The prior probability of Environmental data collection The prior probability of For evidence The marginal probability of Environmental data collection The weight coefficient of is the severity of the fault impact, is the time when the fault occurred;

[0102] Execution process: First, collect environmental tracking data through sensors and monitoring equipment, including parameters such as temperature, humidity, pressure, current, voltage, etc., as part of the environmental data set E, and calculate the environmental data set The prior probability , evaluate the data set in a specific environment The following failure occurs The prior probability , then, determine each environmental data set The weight coefficient , determined by analyzing historical data and expert scoring methods, reflects the importance of environmental data sets to the impact of faults. At the same time, the system evaluates the severity of fault impacts. , quantifying the impact of the failure on the building facilities and the time of failure It reflects the duration of the fault and combines Assess the urgency of the failure, calculating the The following failure occurs The posterior probability , For evidence The marginal probability represents the combined probability of occurrence of all possible environmental data sets, generates accurate fault diagnosis results, and formulates corresponding emergency response measures to ensure that equipment failures or safety hazards can be quickly detected and responded to during the operation and maintenance of building facilities.

[0103] See also Figure 2 The equipment loss analysis module includes a data aggregation submodule, a risk assessment submodule and a level classification submodule, among which:

[0104] Data aggregation submodule: Based on the emergency response measures and spatial optimization analysis results, collect data related to the environment and safety, remove noise and redundant information through data cleaning, organize the data into a structured format, comprehensively analyze the correlation and trend of multi-source data, and generate comprehensive environmental data;

[0105] Risk assessment submodule: Based on comprehensive environmental data, identify potential risk points, analyze key variables in the data, quantitatively assess the probability of risk and possible impact, combine qualitative analysis methods, identify and assess environmental and safety risks, and generate risk identification results;

[0106] Level classification submodule: Based on the risk identification results, the identified risks are classified into levels. Through multi-dimensional standards, including impact scope, severity, and controllability, a risk level model is established and applied to classify and prioritize risks and generate a risk assessment report.

[0107] In the data aggregation submodule, based on emergency response measures, environmental and safety data are collected and cleaned. Duplicate data is deleted and erroneous data is corrected. The data is converted into a standardized format and further processed using Python's Pandas library to ensure data format consistency. Through comprehensive data analysis, aggregation functions are called to calculate statistical indicators such as mean and sum to generate comprehensive environmental data.

[0108] In the risk assessment submodule, based on comprehensive environmental data, potential risk points are analyzed, and the analytic hierarchy process is used to identify risk factors. A quantitative assessment is conducted by building a hierarchical model of risk factors. An expert scoring method is used to assign weights to each risk factor. The relative importance of each risk factor is calculated through normalization. A qualitative analysis is conducted, and the relationship between risks is identified using the causal analysis method to generate risk identification results.

[0109] In the level classification submodule, risk level classification is carried out based on the risk identification results. The fuzzy comprehensive evaluation method is adopted to define the risk level standard, establish a risk level model, and use the fuzzy membership function in fuzzy mathematics to calculate the membership of each risk factor. The comprehensive membership is obtained through matrix operation, the level of each risk is determined, and a risk assessment report is generated.

[0110] See also Figure 2 ,The equipment maintenance and repair strategy module includes a cycle optimization submodule, a strategy adjustment submodule, and a plan update submodule, where:

[0111] Cycle optimization submodule: Based on the risk assessment report, analyze the current maintenance cycle of the equipment, identify potential deficiencies and risk factors in the maintenance cycle, optimize and adjust the maintenance cycle, reset the maintenance frequency and interval time of the equipment, and generate an optimized maintenance cycle;

[0112] Strategy adjustment submodule: Based on the optimized maintenance cycle, re-evaluate and adjust the equipment maintenance strategy, optimize the maintenance content and measures by analyzing the equipment performance data, combined with the failure and repair conditions in the historical maintenance records, and generate an optimized maintenance strategy;

[0113] Plan update submodule: Based on the optimized maintenance strategy, update the overall maintenance plan of the equipment, combine the real-time monitoring data, refer to the historical maintenance records, adjust the schedule and resource allocation of the maintenance work, and generate a maintenance optimization plan;

[0114] In the cycle optimization submodule, based on the risk assessment report, the equipment maintenance cycle is analyzed, and the historical maintenance data of the equipment is analyzed by using the time series analysis method. The maintenance cycle is predicted by calling the ARIMA model, and the model parameters are set to optimize the cycle. By calculating the frequency and time interval of equipment failures and combining the key risk points in the risk assessment, the time nodes of the maintenance cycle are adjusted to generate an optimized maintenance cycle.

[0115] In the strategy adjustment submodule, the equipment maintenance strategy is adjusted based on the optimized maintenance cycle. The decision tree algorithm is used to consider the equipment performance. By classifying the performance data and historical maintenance records of the equipment, the node splitting rules of the decision tree are used to formulate corresponding maintenance strategies for different equipment categories to generate optimized maintenance strategies.

[0116] In the plan update submodule, the maintenance plan is updated based on the optimized maintenance strategy. In combination with real-time monitoring data, a dynamic programming method is used to calculate the optimal path of the maintenance operation by comparing the real-time monitoring data with historical records, adjust the time and resource allocation in the maintenance plan, and generate a maintenance optimization plan.

[0117] See also Figure 3 A three-dimensional visualization operation and maintenance management method for building facilities is implemented based on the above-mentioned three-dimensional visualization operation and maintenance management system for building facilities, and includes the following steps:

[0118] Step 1: Based on the original design data of the equipment and facilities, analyze the structural information and node relationships involved in the design data, identify and decode the data format, call the parsed node information to establish a three-dimensional framework structure, and generate a preliminary three-dimensional structure diagram by decomposing the framework hierarchy and identifying the nodes;

[0119] Step 2: Based on the preliminary 3D structural diagram, combined with BIM technology, visualize the 3D model, check each connection point and interface position of the model item by item, analyze the spatial relationship and size coordination between components, update the 3D model display status, generate a detailed 3D model, and use visualization equipment for dynamic display;

[0120] Step 3: Based on the detailed 3D model, by locating and analyzing the support structure and heavy load points in the 3D model, parameter extraction and calculation are performed to determine the strength distribution of each support structure. Combined with the load distribution information, each heavy load point is optimized and adjusted to gradually enhance the overall stability of the model and generate a 3D model data set.

[0121] Step 4: Based on the 3D model data set, scan the current location of equipment and resources in the building facilities, calibrate and integrate the location information of resources and equipment by updating the location information in real time, and generate resource location information;

[0122] Step 5: Based on the resource location information, the device operation status and resource usage are continuously monitored, the device operation parameters are compared and analyzed with the resource usage parameters, the monitoring results are recorded, and a resource monitoring report is generated;

[0123] Step 6: Based on the resource monitoring report and 3D model dataset, divide the resource allocation situation in the building facilities into regions, identify and adjust the allocation strategy of resource conflicts and inefficient areas, reallocate the resource usage order and priority of each area, and generate spatial optimization analysis results;

[0124] Step 7: Based on the results of the spatial optimization analysis, call the equipment status data and environmental variable data, dynamically monitor the real-time operation of the equipment, identify the wear and loss of the equipment, generate emergency response measures, and combine the emergency response measures to formulate an equipment maintenance plan, perform preventive maintenance or replacement of key components, and ensure the normal operation and safety of the equipment through diagnostic analysis.

[0125] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0126] In addition, it will be understood by those skilled in the art that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0127] Those skilled in the art should understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A three-dimensional visual operation and maintenance management system for building facilities, characterized in that: The system comprises: Equipment and facility 3D modeling module: Based on the original design data of equipment and facilities, BIM technology is used for 3D modeling, the structure is converted into a detailed 3D space, and the 3D model is rendered and displayed in real time using visualization equipment. At the same time, long short-term memory artificial neural network is used for model optimization to generate a 3D model data set; Resource dynamic configuration module: Based on the three-dimensional model data set, it monitors the operation status of the equipment and the usage of resources in real time, dynamically adjusts resource allocation, updates monitoring records, and generates equipment operation and resource management logs; Energy consumption optimization module: based on the equipment operation and resource management log, analyze the equipment operation environment, optimize resource allocation and utilization efficiency, optimize regional division and resource scheduling, and generate spatial optimization analysis results; the energy consumption optimization module includes a layout environment analysis submodule, a resource conflict detection submodule and a regional configuration optimization submodule, wherein: the layout environment analysis submodule: based on the equipment operation and resource management log, extract data on the actual location and environmental conditions of the equipment, analyze the distribution status of the equipment and resources by identifying the space occupancy and resource consumption of the equipment, establish a spatial association model between equipment and resources, and generate equipment distribution and environmental status; resource conflict detection submodule: based on equipment distribution and environmental status, perform data screening on resource usage between equipment, detect resource usage conflicts between equipment by identifying overlapping or insufficient areas of resource allocation, extract data features of conflicting and inefficient areas, and generate resource conflict and utilization analysis; regional configuration optimization submodule: based on resource conflict and utilization analysis, perform regional redivision of equipment and resources, adjust resource scheduling strategies by optimizing the distribution pattern of resources in space, reallocate the order and priority of resource usage, optimize the equipment operation environment, and generate spatial optimization analysis results; Real-time monitoring and response module: Based on the equipment operation and resource management log and the spatial optimization analysis results, the real-time monitoring of equipment status and tracking of environmental variables are carried out, equipment failures or safety hazards are detected and responded to, and Bayesian network is used to perform fault diagnosis and response measures to generate emergency response measures; the real-time monitoring and response module includes a status monitoring submodule, an environmental tracking submodule and a fault response submodule, wherein: the status monitoring submodule: based on the equipment operation and resource management log and the spatial optimization analysis results, the real-time data collection of equipment status is carried out, the current operating status of the equipment is analyzed by monitoring the operating parameters and performance indicators of the equipment, the real-time operating data of the equipment is recorded, and the status monitoring data is generated; the environmental tracking submodule: based on the status monitoring data, the real-time tracking of environmental variables around the equipment is carried out, the impact of the environment on the operation of the equipment is analyzed by monitoring the changes in environmental conditions, the dynamic change data of the environment is recorded, and the environmental tracking data is generated; the fault response submodule: based on the environmental tracking data, the real-time detection of equipment failures or safety hazards is carried out, the relationship between the equipment status and the environmental variables is analyzed, the Bayesian network is used to perform fault diagnosis and risk assessment, corresponding response measures are formulated and recorded, and emergency response measures are generated; Equipment loss analysis module: Based on the emergency response measures and space optimization analysis results, conduct a comprehensive analysis of environmental and safety data, evaluate potential risk points, aggregate data and classify risk levels to generate a risk assessment report; Equipment maintenance and repair strategy module: Based on the risk assessment report, optimize and adjust the equipment maintenance cycle and strategy, update the maintenance plan, optimize the cost and efficiency according to the equipment performance tracking and historical maintenance records, and generate a maintenance optimization strategy.

2. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1 is characterized in that: The equipment and facility three-dimensional modeling module includes a raw data analysis submodule, a model refinement submodule and a model optimization submodule, wherein: Original data analysis submodule: Based on the original design data of equipment and facilities, the module performs format recognition and decoding on the data, builds a primary three-dimensional framework, decomposes the framework hierarchy and identifies nodes, and generates a preliminary three-dimensional structure diagram; Model refinement submodule: Based on the preliminary three-dimensional structure diagram, check the connection points and interfaces of each component, adjust the docking and contact surfaces of the components, and adjust the spatial relationship and size coordination between the components to generate a detailed three-dimensional model, and use visualization equipment for dynamic display; Model optimization submodule: Based on the detailed three-dimensional model, a long short-term memory artificial neural network is used to analyze the structural characteristics and load distribution of the model, and the overall stability and load-bearing capacity of the model are enhanced by adjusting the supporting structure and heavy load points to generate a three-dimensional model data set.

3. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1 is characterized in that: The long short-term memory artificial neural network is according to the formula: in: For time The output value of is the weight matrix between the hidden layer and the output layer, is the activation function, is the weight matrix between the input layer and the hidden layer, For time The input sequence is For time The hidden state of is the material stiffness matrix, is the damping coefficient, is the hidden layer bias vector, is the output layer bias vector.

4. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1, characterized in that: The resource dynamic configuration module includes a resource positioning submodule, a resource configuration submodule and a configuration record updating submodule, wherein: Resource location submodule: based on the three-dimensional model data set, scans and calibrates the current location of the equipment and resources, and generates resource location information by updating the location information; Resource configuration submodule: Based on the resource location information, monitor the status of equipment and resources in real time, and generate resource monitoring reports by analyzing resource usage and equipment operation status; Configuration record update submodule: Based on the resource monitoring report, the existing monitoring records are revised, and the monitoring records are updated synchronously by continuously tracking the changes in device status and resource usage, and the device operation and resource management logs are generated.

5. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1, characterized in that: The Bayesian network, according to the formula: in: For the given evidence The following failure occurs The posterior probability of For data collection in a specific environment The following failure occurs The prior probability of Environmental data collection The prior probability of For evidence The marginal probability of Environmental data collection The weight coefficient of is the severity of the fault impact, The time when the fault occurred.

6. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1, characterized in that: The equipment loss analysis module includes a data aggregation submodule, a risk assessment submodule and a level classification submodule, wherein: Data aggregation submodule: based on the emergency response measures and the spatial optimization analysis results, collect data related to the environment and safety, remove noise and redundant information through data cleaning, organize the data into a structured format, comprehensively analyze the correlation and trend of multi-source data, and generate comprehensive environmental data; Risk assessment submodule: Based on the comprehensive environmental data, identify potential risk points, analyze key variables in the data, quantitatively assess the probability of occurrence and possible impact of risks, combine qualitative analysis methods, identify and assess environmental and safety risks, and generate risk identification results; Level classification submodule: Based on the risk identification results, the identified risks are classified into levels. Through multi-dimensional standards, including the scope of impact, severity, and controllability, a risk level model is established and applied to classify and prioritize risks and generate a risk assessment report.

7. The three-dimensional visual operation and maintenance management system for building facilities according to claim 1, characterized in that: The equipment maintenance and repair strategy module includes a cycle optimization submodule, a strategy adjustment submodule and a plan update submodule, wherein: Cycle optimization submodule: Based on the risk assessment report, analyze the current maintenance cycle of the equipment, identify potential deficiencies and risk factors in the maintenance cycle, optimize and adjust the maintenance cycle, reset the maintenance frequency and interval time of the equipment, and generate an optimized maintenance cycle; Strategy adjustment submodule: based on the optimized maintenance cycle, re-evaluate and adjust the equipment maintenance strategy, optimize the maintenance content and measures by analyzing the equipment performance data, combined with the failure and repair conditions in the historical maintenance records, and generate an optimized maintenance strategy; Plan update submodule: Based on the optimized maintenance strategy, update the overall maintenance plan of the equipment, combine the real-time monitoring data, refer to the historical maintenance records, adjust the schedule and resource allocation of the maintenance work, and generate a maintenance optimization plan.

8. A three-dimensional visual operation and maintenance management method for building facilities, characterized in that: The three-dimensional visualization operation and maintenance management system for building facilities according to any one of claims 1 to 7 comprises the following steps: Step 1: Based on the original design data of the equipment and facilities, analyze the structural information and node relationships involved in the design data, identify and decode the data format, call the parsed node information to establish a three-dimensional framework structure, and generate a preliminary three-dimensional structure diagram by decomposing the framework hierarchy and identifying the nodes; Step 2: Based on the preliminary 3D structural diagram, combined with BIM technology, a visual display is performed on the 3D model, each connection point and interface position of the model is checked item by item, the spatial relationship and size coordination between the components are analyzed, the 3D model display status is updated, a detailed 3D model is generated, and a dynamic display is performed using a visualization device; Step 3: Based on the detailed 3D model, by locating and analyzing the support structures and heavy load points in the 3D model, extracting and calculating parameters, determining the strength distribution of each support structure, optimizing and adjusting each heavy load point in combination with the load distribution information, gradually enhancing the overall stability of the model, and generating a 3D model data set; Step 4: Based on the three-dimensional model data set, scan the current position of the equipment and resources in the building facilities, calibrate and integrate the positioning information of the resources and equipment by updating the position information in real time, and generate resource positioning information; Step 5: Based on the resource location information, the device operation status and resource usage are continuously monitored, the device operation parameters are compared and analyzed with the resource usage parameters, the monitoring results are recorded, and a resource monitoring report is generated; Step 6: Based on the resource monitoring report and the three-dimensional model data set, the resource allocation situation in the building facilities is divided into regions, and the resource usage order and priority of each region are reallocated by identifying and adjusting the configuration strategy of resource conflicts and inefficient regions, so as to generate a spatial optimization analysis result; Step 7: Based on the spatial optimization analysis results, call the equipment status data and environmental variable data, dynamically monitor the real-time operation of the equipment, identify the wear and loss of the equipment, generate emergency response measures, and combine the emergency response measures to formulate an equipment maintenance plan, perform preventive maintenance or replacement of key components, and ensure the normal operation and safety of the equipment through diagnostic analysis.

Images