Large recreation facility operation monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a large recreation facility operation monitoring method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a facility three-dimensional model of a recreation facility; establishing a basic failure model of the recreation facility; based on the model and the three-dimensional model, identifying a key risk part; generating a multi-dimensional health assessment framework; key risk parts are detected, and operation parameters and structure health conditions are monitored; the recreation facility is automatically patrolled, and video images are collected; carrying out deep fusion on the nondestructive testing data, the operation parameters, the structure health condition data and the video images to obtain monitoring data; monitoring data are analyzed, and automatic fault recognition, diagnosis and prediction are achieved; evaluating the remaining service life of the key risk part of the recreation facility, and performing trend analysis in combination with historical data; and performing quantitative evaluation on the health state of the facility, generating dynamic risk early warning and maintenance suggestions, and making a maintenance plan. According to the scheme, the safety and the maintenance efficiency of the equipment are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a method, device, electronic equipment and storage medium for monitoring the operation of a large-scale amusement facility. Background Art

[0002] With the rapid development of economy and technology, the amusement industry is also booming. In recent years, with the increase in the number of amusement parks, whether indoor or outdoor, water or land, the incidence of safety accidents has also been increasing year by year. This phenomenon has attracted widespread attention from the society. Failure or improper operation of amusement equipment may lead to serious accidents and injuries. Therefore, the operation monitoring system for amusement facilities is particularly important. However, the existing operation monitoring system is not comprehensive enough and inefficient. Summary of the invention

[0003] Based on the above problems, the present invention proposes a method, device, electronic device and storage medium for monitoring the operation of large-scale amusement facilities. By constructing a dynamic health management indicator system, combining a variety of advanced technologies for data collection, fusion and intelligent analysis, and using deep learning and big data analysis technologies for fault diagnosis, prediction and remaining life assessment, it realizes comprehensive monitoring and quantitative evaluation of the operating status of large-scale amusement facilities, significantly improving the safe operation level and maintenance efficiency of the equipment.

[0004] In view of this, one aspect of the present invention provides a method for monitoring the operation of a large-scale amusement facility, comprising: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; Acquire historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; Use non-destructive testing technology to test the key risk areas and obtain non-destructive testing data; Arrange a variety of intelligent sensors at the key risk locations to monitor operating parameters and structural health data in real time; Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic identification, diagnosis and prediction of faults; According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; A multi-index comprehensive evaluation method is used in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility, and to generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

[0005] Optionally, the step of establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data comprises: The historical working data are classified and sorted according to the parameters of operation time, load, speed, and fault occurrence frequency, and a first correlation relationship matrix among the operation time, load, speed, and fault occurrence frequency is established; Normalizing the historical working environment data according to environmental factors such as temperature, humidity, wind speed, rain and snow weather, and analyzing to obtain a first interactive influence relationship between different environmental factors; Performing statistical analysis on the fault type, frequency and location of the historical maintenance data, and establishing a first correspondence between the occurrence of the fault and the operating state and / or environmental conditions; Structuring the product attribute data, and constructing a mapping relationship between material performance, structural characteristics and service life to establish a material-structure-performance association database; Use the fault tree analysis method to identify the root causes of various failures, use the failure mode and effect analysis (FMEA) method to determine the severity, frequency and detection difficulty of the failure mode, establish a fault-symptom association matrix, quantify the characteristic performance of different failure modes, and output the failure mode analysis results; The life distribution model of key components is established based on Weibull distribution, the Cox proportional risk model is used to analyze the impact of environmental factors on failure, and a failure prediction model based on time series is established; Establish fatigue damage accumulation model, corrosion degradation evolution model, and component wear degradation model to construct failure mechanism model; The model is cross-validated using historical data, and model parameters are continuously updated and optimized through actual operation data to establish a model accuracy evaluation index system.

[0006] Optionally, the step of identifying key risk locations of the target amusement facility based on the basic failure model and the facility three-dimensional model includes: Integrate the failure modes in the basic failure model with the structural features in the 3D model of the facility, and identify risk areas by comparing the features of the failure modes with the structural components in the 3D model of the facility; According to the risk characteristic indicators defined in the basic failure model, corresponding risk assessment indicators are set for each risk area in the 3D model of the facility; According to the risk assessment indicators, risk analysis is performed on key components in the three-dimensional model of the facility, and the stress, deformation and fatigue of each component in each risk area under different working conditions and environmental factors are evaluated by computer simulation and finite element analysis technology to obtain risk analysis data; Based on the risk analysis data, identify key risk locations that have a risk of failure under specific operating conditions; Compare the identified key risk areas with historical failure data to verify the accuracy of the identification results. Based on the feedback information, adjust the basic failure model or risk assessment indicators to improve the accuracy of identification; Generate a report containing key risk areas and their risk assessment results to provide a basis for subsequent maintenance decisions and risk management.

[0007] Optionally, the step of developing dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework includes: Conduct in-depth analysis of the established basic failure models to identify different failure modes and their corresponding characteristics; For each failure mode, a corresponding risk characteristic indicator system is constructed; Establish a coupling relationship model between the indicators of the risk characteristic indicator system, calculate the contribution weight of each indicator to the failure state, analyze the interaction mechanism between the indicators, and obtain the indicator correlation analysis results; Establish the benchmark value of each indicator based on the reference indicator data, set the dynamic fluctuation range according to the impact of the environment and working conditions to determine the dynamic threshold, and establish a multi-level early warning threshold system; Based on the risk characteristic indicator system, the indicator correlation analysis results and the multi-level warning threshold system, a multi-dimensional health assessment framework is constructed.

[0008] Optionally, the step of performing intelligent analysis on the fused monitoring data based on the deep learning model and the expert system to realize automatic identification, diagnosis and prediction of faults includes: Design and train the first deep learning model and select a suitable network architecture to process the fused monitoring data; Develop expert systems to embed domain knowledge and empirical rules into the system to enhance the accuracy of fault identification and diagnosis; The expert system is integrated with the first deep learning model to form an intelligent recognition system; The intelligent recognition system is used to analyze the integrated monitoring data to realize automatic identification and prediction of faults, analyze the causes and impacts of faults, and identify potential fault risks.

[0009] Optionally, the step of evaluating the remaining service life of the key risk parts according to the load, structural characteristics, material properties and monitoring data of the target amusement facility by using a life assessment method based on mechanics, probability statistics and information technology, and performing trend analysis in combination with historical data includes: Collect load data of target amusement facilities, including dynamic load and static load during operation; Collect structural characteristics data, record the geometry, connection method and stress conditions of key risk parts; Collect material property data, including material strength, fatigue limit, toughness and corrosion resistance; Collect real-time monitoring data to obtain strain, temperature, and vibration data of key risk areas; Establishing a corresponding mechanical model based on the load data, the structural characteristic data, the material property data and the monitoring data to simulate the stress conditions of key risk parts under different loads; Finite element analysis is used to calculate the mechanical model and evaluate the stress distribution and deformation of the components under actual operating conditions; Select a life assessment model based on mechanics, probability statistics and information technology, input the collected loads, material properties and monitoring data into the selected life assessment model, and calculate the remaining service life of key risk parts.

[0010] Optionally, the step of using a multi-index comprehensive evaluation method in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility and generate dynamic risk warnings and maintenance recommendations includes: The evaluation index system is constructed by adopting a multi-index comprehensive evaluation method, including: constructing an index hierarchy based on the health assessment framework; dividing the indicators into several dimensions such as structural safety, operating status, and performance parameters; establishing a logical correlation between indicators; setting the evaluation criteria and calculation methods for each indicator; Determine the weight of each indicator in the evaluation index system, including: constructing a judgment matrix using the analytic hierarchy process; calculating the relative weight of each layer of indicators; conducting consistency checks and corrections; and establishing a dynamic weight adjustment mechanism; Constructing a fuzzy evaluation model, including: establishing the membership function of each indicator; constructing a fuzzy relationship matrix; determining fuzzy operation rules; calculating comprehensive evaluation results; Evaluate health status, including: real-time calculation of the health of each indicator; use fuzzy evaluation model to perform multi-level fuzzy comprehensive calculation; determine the health status level of the whole machine; generate health status evaluation report; Construct a risk warning mechanism, including: setting multi-level warning thresholds; establishing a warning rule base; constructing a warning level determination model; and realizing real-time warning information push.

[0011] Generate maintenance recommendations, including: establishing a mapping relationship between health status and maintenance strategy; designing a maintenance plan generator based on case reasoning; building a maintenance priority ranking model; and forming a standardized maintenance recommendation output.

[0012] Another aspect of the present invention provides a large-scale amusement facility operation monitoring device for executing a large-scale amusement facility operation monitoring method, comprising: a data acquisition module and a control processing module; wherein, The data acquisition module is configured as follows: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; Acquire historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; The control processing module is configured as follows: Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; Use non-destructive testing technology to test the key risk areas and obtain non-destructive testing data; Arrange a variety of intelligent sensors at the key risk locations to monitor operating parameters and structural health data in real time; Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic identification, diagnosis and prediction of faults; According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; A multi-index comprehensive evaluation method is used in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility, and to generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

[0013] Another aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for monitoring the operation of a large amusement facility when executing the computer program.

[0014] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of a method for monitoring the operation of a large-scale amusement facility are implemented.

[0015] By adopting the technical solution of the present invention, the operation monitoring method of large-scale amusement facilities includes: obtaining the three-dimensional facility data of the target amusement facility, and constructing a three-dimensional facility model based on the three-dimensional facility data; obtaining the historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; establishing a basic failure model of the target amusement facility based on the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; identifying the key risk parts of the target amusement facility based on the basic failure model and the three-dimensional facility model; developing dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; using non-destructive testing technology to detect the key risk parts and obtain non-destructive testing data; arranging a variety of intelligent sensors at the key risk parts to monitor the operating parameters and structural health status data in real time; and controlling intelligent inspection robots or drones to perform automatic inspections. and detection, and obtain video images collected by intelligent inspection robots or drones; deeply fuse the non-destructive testing data, the operating parameters, the structural health data and the video images to obtain monitoring data; based on the deep learning model and expert system, intelligently analyze the fused monitoring data to realize automatic identification, diagnosis and prediction of faults; according to the load, structural characteristics, material properties and monitoring data of the target amusement facility, adopt a life assessment method based on mechanics, probability statistics and information technology to assess the remaining service life of the key risk parts, and conduct trend analysis in combination with historical data; adopt a multi-indicator comprehensive evaluation method, combined with the health assessment framework, to quantitatively evaluate the health status of the whole machine of the target amusement facility, and generate dynamic risk warnings and maintenance suggestions; according to the dynamic risk warnings and maintenance suggestions, formulate maintenance and repair plans, and implement dynamic management to ensure the safe operation and performance optimization of the target amusement facility. By building a dynamic health management indicator system, combining a variety of advanced technologies for data collection, fusion and intelligent analysis, and using technologies such as deep learning and big data analysis for fault diagnosis, prediction and remaining life assessment, we have achieved comprehensive monitoring and quantitative evaluation of the operating status of large-scale amusement facilities, significantly improving the safe operation level and maintenance efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a large-scale amusement facility operation monitoring method provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of a large-scale amusement facility operation monitoring device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0019] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] Refer to the following Figure 1 to Figure 2 A method, device, electronic device and storage medium for monitoring the operation of a large-scale amusement facility provided according to some embodiments of the present invention will be described.

[0022] like Figure 1 As shown, one embodiment of the present invention provides a large-scale amusement facility operation monitoring method, comprising: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; In this step, the 3D data of the target amusement facility is obtained using technologies such as 3D laser scanning, photogrammetry, or RGB-D cameras, which can accurately capture the geometry and surface features of the facility; the collected 3D data is preprocessed, including denoising, data cleaning, and data registration. Ensure the accuracy and consistency of the data for subsequent modeling; use professional 3D modeling software (such as Blender, Maya, or 3ds Max) to import the processed data and build a 3D model of the facility (in this process, details and textures can be added as needed to improve the realism of the model); optimize the constructed 3D model, including simplifying the number of polygons and adjusting the topology of the model to improve the rendering efficiency and real-time interactive performance of the model; compare the constructed 3D model with the actual facility to verify the accuracy and completeness of the model. Make adjustments when necessary to ensure that the model can truly reflect the physical characteristics of the facility; store the final 3D model in an appropriate format for subsequent use, such as virtual reality (VR) display, simulation testing, or maintenance management. Through high-precision 3D data collection and processing, we ensure that the model can accurately reflect the actual structure and characteristics of the target amusement facilities; the constructed 3D model provides intuitive visual effects, which is convenient for design review, customer communication and market promotion; the 3D model provides important data support for subsequent risk assessment, maintenance management and facility optimization, helping decision makers make more scientific judgments.

[0023] Obtain historical working data, historical working environment data, historical maintenance data and product attribute data (including material, structure, effective use data, etc.) of the target amusement facility; In this step, historical working data acquisition: the control system and monitoring equipment of the amusement facilities automatically record the operation data of the facilities, including operating time, load conditions, speed, frequency, etc. These data can be stored and managed in real time through the data acquisition system (such as SCADA system). Historical working environment data acquisition: environmental data related to the operation of the amusement facilities, such as temperature, humidity, wind speed, precipitation, etc., can be collected by controlling the environmental monitoring sensors. These sensors can regularly record data and upload them to the central database. Historical maintenance data acquisition: sorting and archiving the maintenance records of the amusement facilities, including maintenance date, maintenance content, materials used, maintenance personnel, fault description and processing results, etc., which are usually stored in the maintenance management system. Product attribute data acquisition: collect product attribute data of amusement facilities, including material properties (such as strength, corrosion resistance), structural design parameters (such as size, shape), effective use data (such as design life, frequency of use), etc. These data can be obtained through product manuals, design documents and information provided by manufacturers. Data integration and storage: the above acquired data are integrated to form a comprehensive database, and the database management system (such as SQL database) is used to store and manage these data for subsequent analysis and query. Data verification and cleaning: Verify and clean the collected data to ensure data accuracy and consistency, remove duplicate data and outliers to improve data quality.

[0024] Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model (different failure modes in the basic failure model correspond to different indicators, including but not limited to: structural thickness, crack size, deformation, vibration acceleration, acoustic emission signal, voltage, current, arc signal, control function, etc.), forming a multi-dimensional health assessment framework; Use non-destructive testing technology (such as ultrasonic phased array technology, pulsed eddy current technology, infrared imaging technology, and drone visual detection technology, etc.) to detect the key risk areas and obtain non-destructive testing data; In this step, the key risk areas that need to be inspected are determined based on the previous risk assessment and health monitoring results; appropriate non-destructive testing technologies are selected, such as: ultrasonic phased array technology is suitable for detecting internal defects (such as cracks and pores). This technology can provide high-resolution imaging results by transmitting and receiving ultrasonic signals; pulsed eddy current technology is mainly used to detect surface and near-surface defects of conductive materials, and is suitable for the inspection of metal structures; infrared imaging technology can identify temperature anomalies caused by defects by detecting the temperature distribution on the surface of an object, and is suitable for the inspection of electrical equipment and mechanical components; drone visual inspection technology uses the camera carried by the drone for high-altitude shooting, which is suitable for surface defect detection of large structures and can quickly cover large areas. According to the selected detection technology, prepare the corresponding detection equipment and sensors to ensure that the equipment is in good condition; conduct on-site inspections at key risk locations, collect data according to the equipment operating procedures, and ensure that all relevant parameters are recorded during the inspection process, such as environmental conditions, equipment settings, etc.; organize the collected non-destructive testing data to ensure the integrity and accuracy of the data; apply the corresponding signal processing algorithm to analyze the test data and extract useful information, such as defect location, size and type; compare the test results with historical data to verify the accuracy and reliability of the test; generate a test report to record the test process, results and suggestions in detail to provide a basis for subsequent maintenance decisions. Through this step, non-destructive testing can be effectively performed on key risk locations and accurate non-destructive testing data can be obtained, thereby providing support for the safety management of facilities.

[0025] Arrange a variety of intelligent sensors (such as strain sensors, acceleration sensors, temperature sensors, etc.) at the key risk locations to monitor operating parameters and structural health data in real time (and use edge computing technology to achieve real-time data processing); In this step, according to the monitoring requirements and the characteristics of the key risk parts (such as structure, shape, material, etc.), select appropriate sensor types (such as strain sensors: used to monitor the strain changes of the structure and evaluate the stress of the material; acceleration sensors: used to monitor vibration and dynamic response and evaluate the dynamic characteristics of the structure; temperature sensors: used to monitor temperature changes and evaluate the impact of the environment on the structure; etc.); design the sensor layout plan according to the structural characteristics and risk assessment results to ensure that all key risk parts are covered; install sensors at the determined locations to ensure that they are fixed firmly and can work normally; sensors should have real-time data collection functions and regularly record operating parameters and structural health data; transmit the collected data to the data processing center through wireless or wired networks; deploy edge computing devices near the sensors to reduce data transmission delays and bandwidth consumption; use edge computing technology to process real-time data, including data filtering, feature extraction and preliminary analysis, which can achieve rapid response to data and timely detection of abnormal situations; establish a real-time monitoring platform to centrally display the data and analysis results of each sensor, so as to facilitate management personnel to monitor and make decisions. Through this step, smart sensors can be effectively deployed at key risk parts to achieve real-time monitoring and data processing of operating parameters and structural health.

[0026] Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; In this step, according to the requirements of the inspection task, select drones or intelligent inspection robots with high-altitude operation capabilities. These devices should have high-definition cameras and stable flight control systems to ensure the quality of image acquisition in high-altitude environments; configure necessary sensors on the drone, such as high-definition cameras, infrared sensors, etc., to facilitate multi-dimensional data acquisition; use geographic information systems (GIS) or special software to plan the inspection route of the drone to ensure that all high-altitude parts that need to be inspected are covered; set parameters such as inspection height, speed, and image acquisition frequency according to specific needs; use the drone's automatic flight control system to write inspection programs to ensure that the drone can automatically fly along the predetermined route and collect images; during the inspection process, monitor the status of the drone and image acquisition in real time through the ground control station to ensure the smooth progress of the task; the drone automatically obtains video images of high-altitude parts during the inspection process to ensure that the image quality meets the needs of subsequent analysis; the collected video images are transmitted to the ground control station in real time or stored in the drone's storage device for subsequent analysis and processing. Through this step, intelligent inspection robots or drones can be effectively used to automatically inspect and detect difficult-to-reach high-altitude areas, obtain high-quality video images, and provide important support for subsequent maintenance and safety management.

[0027] Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; In this step, various non-destructive testing technologies (such as ultrasound, X-ray, infrared thermal imaging, etc.) are used to obtain the internal defect information (non-destructive testing data) of the structure; the operating parameters of the equipment are monitored in real time, including parameters such as temperature, pressure, vibration, etc.; the structural health status data collected by sensors (such as strain gauges, accelerometers, etc.) are obtained; real-time video images of high altitude or difficult-to-reach parts are obtained through drones or intelligent inspection robots; the collected data are cleaned to remove noise and outliers to ensure the accuracy of the data; data from different sources are standardized to make them comparable and facilitate subsequent fusion; Extract key features from the data, which can be achieved through machine learning or deep learning algorithms, such as using convolutional neural networks (CNNs) to extract features from video images; using deep learning models (such as multimodal neural networks) to fuse different types of data (by designing a suitable network architecture, the features of non-destructive testing data, operating parameters, structural health data, and video images are comprehensively analyzed; weighted average, feature splicing, or more complex fusion strategies (such as attention mechanisms) can be used to achieve deep fusion of data); through the fused data, comprehensive monitoring data is generated, which can be used to assess the health of the structure, predict potential failures, and provide support for decision-making. Through this step, the deep fusion of non-destructive testing data, operating parameters, structural health data, and video images can be achieved, and finally comprehensive monitoring data can be obtained, providing strong support for the safety management of the structure.

[0028] Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic fault identification, diagnosis and prediction (improving the accuracy of fault prediction and response speed); According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; Using a multi-index comprehensive evaluation method (such as hierarchical analysis method, fuzzy comprehensive evaluation method, etc.), combined with the health assessment framework, quantitatively evaluate the overall health status of the target amusement facility, and generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

[0029] The embodiments of the present invention, by constructing a dynamic health management indicator system, combining a variety of advanced technologies for data collection, fusion and intelligent analysis, and using technologies such as deep learning and big data analysis to perform fault diagnosis, prediction and remaining life assessment, achieve comprehensive monitoring and quantitative evaluation of the operating status of large-scale amusement facilities, and significantly improve the safe operation level and maintenance efficiency of the equipment.

[0030] In some possible implementations of the present invention, the step of establishing a basic failure model of the target amusement facility based on the historical working data, the historical working environment data, the historical maintenance data and the product attribute data includes: The historical working data are classified and sorted according to the parameters of operation time, load, speed, and fault occurrence frequency, and a first correlation relationship matrix among the operation time, load, speed, and fault occurrence frequency is established; Normalizing the historical working environment data according to environmental factors such as temperature, humidity, wind speed, rain and snow weather, and analyzing to obtain a first interactive influence relationship between different environmental factors; Performing statistical analysis on the historical maintenance data (including maintenance frequency, maintenance type and fault description, etc.) in terms of fault type, frequency and location, and establishing a first correspondence between the occurrence of the fault and the operating state and / or environmental conditions; Structuring the product attribute data (including material properties, structural parameters and design life, etc.), and constructing a mapping relationship between material performance, structural characteristics and service life to establish a material-structure-performance association database; Use the fault tree analysis method (FTA) to identify the root causes of various failures, use the failure mode and effect analysis (FMEA) method to determine the severity, frequency and detection difficulty of the failure mode, establish a fault-symptom association matrix, quantify the characteristic performance of different failure modes, and output the failure mode analysis results; In this step, a fault tree analysis is performed based on the historical maintenance data processed as described above to identify the key factor chain that causes the failure; the structured product attribute data is used to evaluate the impact of the failure on the product system; the frequency of occurrence of the failure mode is quantified in combination with the historical working data; and the environmental data analysis is used to evaluate the promoting effect of environmental factors on each failure mode.

[0031] The life distribution model of key components is established based on Weibull distribution, the Cox proportional risk model is used to analyze the impact of environmental factors on failure, and a failure prediction model based on time series is established; In this step, the failure mode analysis results are used as input parameters of the Weibull distribution model; the normalization results of environmental data are used to optimize the covariates of the Cox proportional hazard model; and the feature space of the failure prediction model is constructed based on the time series characteristics of historical data.

[0032] Establish fatigue damage accumulation model, corrosion degradation evolution model, and component wear degradation model to construct failure mechanism model; In this step, the fatigue damage accumulation model needs to integrate the prediction results of the failure probability model, the corrosion degradation evolution model needs to consider the probability distribution characteristics of environmental factors, and the wear degradation model needs to be combined with the qualitative conclusions of the failure mode analysis.

[0033] The model is cross-validated using historical data, and model parameters are continuously updated and optimized through actual operation data to establish a model accuracy evaluation index system.

[0034] In this step, the data preprocessing method is reversely optimized through cross-validation results; the weight coefficient of the failure mode is dynamically updated based on the actual operation data; and the model accuracy evaluation results are used to adjust the parameters of the probability model and the mechanism model.

[0035] In this embodiment, by establishing a basic failure model, potential failure modes can be identified in advance, thereby improving the accuracy of failure prediction and reducing unexpected downtime; based on the analysis results of the model, a more scientific maintenance plan can be formulated to reduce maintenance costs and improve the efficiency of equipment use; through the identification and analysis of failure modes, preventive measures can be taken in advance to improve the safety of amusement facilities and ensure the safety of tourists.

[0036] In some possible implementations of the present invention, the step of identifying the key risk parts of the target amusement facility based on the basic failure model and the facility three-dimensional model includes: Integrate the failure modes in the basic failure model with the structural features in the 3D model of the facility, and identify risk areas by comparing the characteristics of the failure modes (such as stress concentration, fatigue points, etc.) with the structural components in the 3D model of the facility; This step specifically includes: dividing the three-dimensional model of the facility into functional blocks such as the drive system area, the bearing structure area, and the control system area according to function; meshing each functional block and establishing a local coordinate system; building a connection relationship database between the functional blocks; establishing a corresponding relationship between various failure modes in the basic failure model and the functional blocks; calculating the failure probability of each component in each functional block; analyzing the failure propagation path and impact range, and determining the risk area where risks exist.

[0037] According to the risk characteristic indicators defined in the basic failure model (such as structural thickness, crack size, deformation, etc.), set corresponding risk assessment indicators for each risk area in the 3D model of the facility (these indicators will be used to quantify the risk level of each component); According to the risk assessment indicators, risk analysis is performed on key components in the three-dimensional model of the facility, and the stress, deformation and fatigue of each component in each risk area under different working conditions and environmental factors are evaluated by computer simulation and finite element analysis (FEA) technology to obtain risk analysis data; In this step, finite element analysis is performed based on the three-dimensional model to obtain the static stress distribution; dynamic load simulation is performed to obtain the stress time history under key working conditions; a stress concentration factor distribution diagram is established; a "failure probability-failure consequence" risk matrix is ​​established; the risk index of each area is calculated by combining the stress distribution and failure probability; the risk index is normalized to form risk analysis data.

[0038] Based on the risk analysis data, identify key risk locations that have a risk of failure under specific operating conditions (these locations are usually areas of stress concentration, fatigue damage or greater environmental impact); In this step, it specifically includes: setting risk level thresholds and preliminarily screening high-risk areas; analyzing the accessibility and detectability of high-risk areas; and determining the final list of key risk areas; Compare the identified key risk areas with historical failure data to verify the accuracy of the identification results. Based on the feedback information, adjust the basic failure model or risk assessment indicators to improve the accuracy of identification; Generate a report containing key risk areas and their risk assessment results to provide a basis for subsequent maintenance decisions and risk management.

[0039] In this embodiment, the partition information provides a spatial position reference for the failure model, the functional block division affects the classification of the failure mode, and the connection relationship data is used for failure propagation analysis; the failure mode is located based on the functional block, the local failure probability is calculated using the grid model, and the failure impact range is analyzed through the connection relationship; the partition information guides the establishment of the finite element model, the failure mode affects the selection of the load condition, and the stress distribution assists the failure probability assessment; the failure probability and stress distribution results are combined, and the importance weight of the functional block is considered to establish a multi-dimensional risk assessment system; the parts are screened based on the risk level, and verified in combination with actual maintenance experience to form a dynamically updated risk part library. By combining the basic failure model and the three-dimensional model of the facility, the key risk parts in the amusement facility can be more accurately identified, and the effectiveness of risk management can be improved; the identified key risk parts can be used as the object of key monitoring and maintenance, thereby reducing the probability of failure and enhancing the safety of the amusement facility; based on the risk assessment results, targeted maintenance and overhaul plans can be formulated, resources can be reasonably allocated, and maintenance efficiency can be improved; through a systematic risk identification process, a scientific decision-making basis is provided for managers to help them make more reasonable choices in operation and maintenance.

[0040] In some possible implementations of the present invention, the step of developing dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework includes: Conduct in-depth analysis of the established basic failure models to identify different failure modes and their corresponding characteristics (these failure modes may include material fatigue, structural damage, control system failure, etc.); In this step, the physical characteristics of each failure mode are analyzed, a corresponding relationship matrix between failure modes and measurable parameters is established, and the dominant and secondary characteristic indicators of each failure mode are determined.

[0041] For each failure mode, a corresponding risk characteristic indicator system is constructed; In this step, these indicators should cover multiple dimensions, including but not limited to: structural indicators (such as structural thickness, crack size, deformation, etc.), dynamic response indicators (such as vibration acceleration, acoustic emission signals, etc.), electrical characteristic indicators (such as voltage, current, arc signal, etc.), control function indicators (such as control system response time and functional integrity, etc.), etc. Establish quantitative standards for structural indicators; formulate measurement specifications for dynamic response indicators (such as vibration, acoustic emission); determine monitoring requirements for electrical characteristic indicators; and establish performance evaluation standards for control function indicators.

[0042] Establish a coupling relationship model between the indicators of the risk characteristic indicator system, calculate the contribution weight of each indicator to the failure state, analyze the interaction mechanism between the indicators, and obtain the indicator correlation analysis results; Establish the benchmark value of each indicator based on the reference indicator data, set the dynamic fluctuation range according to the impact of the environment and working conditions to determine the dynamic threshold, and establish a multi-level early warning threshold system; Based on the risk characteristic indicator system, the indicator correlation analysis results and the multi-level warning threshold system, a multi-dimensional health assessment framework is constructed (the framework should be able to comprehensively consider the impact of different indicators to form an assessment of the overall health status of the amusement facilities).

[0043] In this step, based on the risk characteristic indicator system, the indicator correlation analysis results and the multi-level warning threshold system, a multi-level indicator evaluation structure is designed, a health calculation model based on fuzzy comprehensive evaluation is established, and a visual health status display interface is developed to construct a health assessment framework.

[0044] In this embodiment, through multi-dimensional dynamic risk characteristic indicators, the health status of amusement facilities can be comprehensively monitored and potential risks can be discovered in a timely manner; the introduction of dynamic monitoring indicators can enhance the early warning capability of faults and reduce the occurrence of unexpected downtime and safety accidents; based on the analysis results of the health assessment framework, more scientific maintenance strategies can be formulated to improve maintenance efficiency and resource utilization; by timely identifying and handling potential risks, the safety of amusement facilities can be improved and the safety of tourists can be guaranteed.

[0045] In some possible implementations of the present invention, the steps of performing intelligent analysis on the fused monitoring data based on the deep learning model and the expert system to realize automatic identification, diagnosis and prediction of faults include: Design and train the first deep learning model and select a suitable network architecture (such as convolutional neural network (CNN), long short-term memory (LSTM), etc.) to process the fused monitoring data; In this step, the first deep learning model is constructed, including: designing a multi-layer temporal convolutional neural network to extract local features, constructing a long short-term memory network (LSTM) to capture long-term dependencies, designing an attention mechanism to highlight key temporal features, and establishing a multi-task learning framework to achieve fault classification and prediction. During the training process, supervised learning is performed using labeled data to optimize model parameters and improve the model's ability to identify fault features.

[0046] Develop expert systems to embed domain knowledge and empirical rules into the system to enhance the accuracy of fault identification and diagnosis; In this step, the expert system knowledge base construction steps include: establishing a fault symptom-cause association rule base; building an equipment maintenance experience knowledge graph; designing diagnosis rules based on case reasoning; and establishing a fault evolution path model.

[0047] Merge the expert system with the first deep learning model to form an intelligent recognition system (using deep learning for data-driven analysis and expert system for rule-based reasoning); In this step, it specifically includes: designing a result fusion strategy for deep learning models and expert systems; establishing a confidence-based multi-model voting mechanism; building a dynamic weight adaptive adjustment mechanism; and generating the final fault diagnosis and prediction results.

[0048] The intelligent recognition system is used to analyze the integrated monitoring data to realize automatic identification and prediction of faults, analyze the causes and impacts of faults, and identify potential fault risks.

[0049] In this embodiment, the deep learning results are used as the input of the expert system, and the expert rules guide the feature selection and model design. The advantages of the two complement each other to improve the accuracy of diagnosis. Deep learning and expert knowledge are comprehensively utilized to dynamically adjust the weights of different models to achieve optimal decision-making of multi-source information. The system can monitor and automatically identify equipment failures in real time, reduce manual intervention, and improve work efficiency. Combining the advantages of deep learning and expert systems, it can more accurately diagnose the cause of failures and reduce the misdiagnosis rate. Through the analysis of historical and real-time data, the system can predict potential failures in advance, improve the accuracy and response speed of failure prediction, thereby reducing downtime and maintenance costs.

[0050] In some possible implementations of the present invention, the steps of evaluating the remaining service life of the key risk parts according to the load, structural characteristics, material properties and monitoring data of the target amusement facility using a life assessment method based on mechanics, probability statistics and information technology, and performing trend analysis in combination with historical data include: Collect load data of target amusement facilities, including dynamic load and static load during operation; Collect structural characteristics data, record the geometry, connection method and stress conditions of key risk parts; Collect material property data, including material strength, fatigue limit, toughness and corrosion resistance; Collect real-time monitoring data to obtain strain, temperature, and vibration data of key risk areas; Establishing a corresponding mechanical model based on the load data, the structural characteristic data, the material property data and the monitoring data to simulate the stress conditions of key risk parts under different loads; Finite element analysis is used to calculate the mechanical model and evaluate the stress distribution and deformation of the components under actual operating conditions; Select a life assessment model based on mechanics, probability statistics and information technology, input the collected loads, material properties and monitoring data into the selected life assessment model, and calculate the remaining service life of key risk parts.

[0051] In this step, commonly used methods include: fatigue life assessment (based on SN curve and Miner's law, assessing the fatigue life of materials under cyclic loads), (probabilistic life model: using probability statistics methods such as Weibull distribution to assess the failure probability and remaining service life of components), etc.

[0052] The solution of this embodiment, combined with mechanical analysis and probability statistics, can accurately evaluate the remaining service life of key risk parts and help managers make scientific decisions.

[0053] In some possible implementations of the present invention, the step of using a multi-index comprehensive evaluation method in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility and generate dynamic risk warnings and maintenance recommendations includes: The evaluation index system is constructed by adopting a multi-index comprehensive evaluation method, including: constructing an index hierarchy based on the health assessment framework; dividing the indicators into several dimensions such as structural safety, operating status, and performance parameters; establishing a logical correlation between indicators; setting the evaluation criteria and calculation methods for each indicator; Determine the weight of each indicator in the evaluation index system, including: constructing a judgment matrix using the analytic hierarchy process; calculating the relative weight of each layer of indicators; conducting consistency checks and corrections; and establishing a dynamic weight adjustment mechanism; Constructing a fuzzy evaluation model, including: establishing the membership function of each indicator; constructing a fuzzy relationship matrix; determining fuzzy operation rules; calculating comprehensive evaluation results; Evaluate health status, including: real-time calculation of the health of each indicator; use fuzzy evaluation model to perform multi-level fuzzy comprehensive calculation; determine the health status level of the whole machine; generate health status evaluation report; Construct a risk warning mechanism, including: setting multi-level warning thresholds; establishing a warning rule base; constructing a warning level determination model; and realizing real-time warning information push.

[0054] Generate maintenance recommendations, including: establishing a mapping relationship between health status and maintenance strategy; designing a maintenance plan generator based on case reasoning; building a maintenance priority ranking model; and forming a standardized maintenance recommendation output.

[0055] In this embodiment, the core indicators in the indicator system inheritance framework are used to expand the evaluation dimensions and levels, and maintain the consistency of the indicator system; weights are assigned based on the importance of indicators, and the weights reflect the strength of correlation between indicators, and are dynamically adjusted to adapt to state changes; weights participate in the fuzzy operation process, and the fuzzy results affect the weight adjustment to achieve scientific evaluation; multi-level evaluation results are integrated to generate a quantitative health index to support state classification judgment; warnings are triggered based on health status, and the warning level corresponds to the health level to achieve real-time warnings; maintenance strategies are determined based on health assessments, and maintenance plans are formulated in combination with warning information to optimize maintenance resource allocation. The solution of this embodiment can comprehensively and accurately evaluate the health status of the entire machine of amusement facilities through a multi-indicator comprehensive evaluation method; the dynamic risk warning mechanism can identify potential risks in a timely manner, reduce the probability of accidents, and ensure the safe operation of amusement facilities; maintenance suggestions generated based on quantitative evaluation and risk analysis can help managers formulate scientific and reasonable maintenance plans to improve the efficiency and safety of facility use.

[0056] See also Figure 2 Another embodiment of the present invention provides a large-scale amusement facility operation monitoring device for executing a large-scale amusement facility operation monitoring method, including: a data acquisition module and a control processing module; wherein, The data acquisition module is configured as follows: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; Acquire historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; The control processing module is configured as follows: Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; Use non-destructive testing technology to test the key risk areas and obtain non-destructive testing data; Arrange a variety of intelligent sensors at the key risk locations to monitor operating parameters and structural health data in real time; Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic identification, diagnosis and prediction of faults; According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; A multi-index comprehensive evaluation method is used in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility, and to generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

[0057] It should be known that Figure 2 The block diagram of the large-scale amusement facility operation monitoring device shown is for illustration only, and the number of modules shown does not limit the protection scope of the present invention. The large-scale amusement facility operation monitoring device provided in this embodiment can be used to execute the corresponding large-scale amusement facility operation monitoring method. For the specific implementation process, please refer to the description of each method embodiment, which will not be repeated here.

[0058] Another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for monitoring the operation of a large amusement facility when executing the computer program.

[0059] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a method for monitoring the operation of a large-scale amusement facility.

[0060] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0061] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0063] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0065] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0066] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0067] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0068] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A method for monitoring the operation of a large-scale amusement facility, characterized in that: include: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; Acquire historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; Use non-destructive testing technology to test the key risk areas and obtain non-destructive testing data; Arrange a variety of intelligent sensors at the key risk locations to monitor operating parameters and structural health data in real time; Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic identification, diagnosis and prediction of faults; According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; A multi-index comprehensive evaluation method is used in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility, and to generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

2. The large-scale amusement facility operation monitoring method according to claim 1, characterized in that: The step of establishing the basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data comprises: The historical working data are classified and sorted according to the parameters of operation time, load, speed, and fault occurrence frequency, and a first correlation relationship matrix among the operation time, load, speed, and fault occurrence frequency is established; Normalizing the historical working environment data according to environmental factors such as temperature, humidity, wind speed, rain and snow weather, and analyzing to obtain a first interactive influence relationship between different environmental factors; Performing statistical analysis on the fault type, frequency and location of the historical maintenance data, and establishing a first correspondence between the occurrence of the fault and the operating state and / or environmental conditions; Structuring the product attribute data, and constructing a mapping relationship between material performance, structural characteristics and service life to establish a material-structure-performance association database; Use the fault tree analysis method to identify the root causes of various failures, use the failure mode and effect analysis (FMEA) method to determine the severity, frequency and detection difficulty of the failure mode, establish a fault-symptom association matrix, quantify the characteristic performance of different failure modes, and output the failure mode analysis results; The life distribution model of key components is established based on Weibull distribution, the Cox proportional risk model is used to analyze the impact of environmental factors on failure, and a failure prediction model based on time series is established; Establish fatigue damage accumulation model, corrosion degradation evolution model, and component wear degradation model to construct failure mechanism model; The model is cross-validated using historical data, and model parameters are continuously updated and optimized through actual operation data to establish a model accuracy evaluation index system.

3. The large-scale amusement facility operation monitoring method according to claim 2, characterized in that: The step of identifying the key risk parts of the target amusement facility based on the basic failure model and the facility three-dimensional model includes: Integrate the failure modes in the basic failure model with the structural features in the 3D model of the facility, and identify risk areas by comparing the features of the failure modes with the structural components in the 3D model of the facility; According to the risk characteristic indicators defined in the basic failure model, corresponding risk assessment indicators are set for each risk area in the 3D model of the facility; According to the risk assessment indicators, risk analysis is performed on key components in the three-dimensional model of the facility, and the stress, deformation and fatigue of each component in each risk area under different working conditions and environmental factors are evaluated by computer simulation and finite element analysis technology to obtain risk analysis data; Based on the risk analysis data, identify key risk locations that have a risk of failure under specific operating conditions; Compare the identified key risk areas with historical failure data to verify the accuracy of the identification results. Based on the feedback information, adjust the basic failure model or risk assessment indicators to improve the accuracy of identification; Generate a report containing key risk areas and their risk assessment results to provide a basis for subsequent maintenance decisions and risk management.

4. The large-scale amusement facility operation monitoring method according to claim 3 is characterized in that: The step of developing dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework includes: Conduct in-depth analysis of the established basic failure models to identify different failure modes and their corresponding characteristics; For each failure mode, a corresponding risk characteristic indicator system is constructed; Establish a coupling relationship model between the indicators of the risk characteristic indicator system, calculate the contribution weight of each indicator to the failure state, analyze the interaction mechanism between the indicators, and obtain the indicator correlation analysis results; Establish the benchmark value of each indicator based on the reference indicator data, set the dynamic fluctuation range according to the impact of the environment and working conditions to determine the dynamic threshold, and establish a multi-level early warning threshold system; Based on the risk characteristic indicator system, the indicator correlation analysis results and the multi-level warning threshold system, a multi-dimensional health assessment framework is constructed.

5. The large-scale amusement facility operation monitoring method according to claim 4, characterized in that: The steps of intelligently analyzing the fused monitoring data based on the deep learning model and the expert system to realize automatic identification, diagnosis and prediction of faults include: Design and train the first deep learning model and select a suitable network architecture to process the fused monitoring data; Develop expert systems to embed domain knowledge and empirical rules into the system to enhance the accuracy of fault identification and diagnosis; The expert system is integrated with the first deep learning model to form an intelligent recognition system; The intelligent recognition system is used to analyze the integrated monitoring data to realize automatic identification and prediction of faults, analyze the causes and impacts of faults, and identify potential fault risks.

6. The large-scale amusement facility operation monitoring method according to claim 5, characterized in that: The steps of evaluating the remaining service life of the key risk parts according to the load, structural characteristics, material properties and monitoring data of the target amusement facility by using a life assessment method based on mechanics, probability statistics and information technology, and performing trend analysis in combination with historical data include: Collect load data of target amusement facilities, including dynamic load and static load during operation; Collect structural characteristics data, record the geometry, connection method and stress conditions of key risk parts; Collect material property data, including material strength, fatigue limit, toughness and corrosion resistance; Collect real-time monitoring data to obtain strain, temperature, and vibration data of key risk areas; Establishing a corresponding mechanical model based on the load data, the structural characteristic data, the material property data and the monitoring data to simulate the stress conditions of key risk parts under different loads; Finite element analysis is used to calculate the mechanical model and evaluate the stress distribution and deformation of the components under actual operating conditions; Select a life assessment model based on mechanics, probability statistics and information technology, input the collected loads, material properties and monitoring data into the selected life assessment model, and calculate the remaining service life of key risk parts.

7. The large-scale amusement facility operation monitoring method according to claim 6, characterized in that: The step of using the multi-index comprehensive evaluation method, combined with the health assessment framework, to quantitatively evaluate the overall health status of the target amusement facility and generate dynamic risk warnings and maintenance suggestions includes: The evaluation index system is constructed by adopting a multi-index comprehensive evaluation method, including: constructing an index hierarchy based on the health assessment framework; dividing the indicators into several dimensions such as structural safety, operating status, and performance parameters; establishing a logical correlation between indicators; setting the evaluation criteria and calculation methods for each indicator; Determine the weight of each indicator in the evaluation index system, including: constructing a judgment matrix using the analytic hierarchy process; calculating the relative weight of each layer of indicators; conducting consistency checks and corrections; and establishing a dynamic weight adjustment mechanism; Constructing a fuzzy evaluation model, including: establishing the membership function of each indicator; constructing a fuzzy relationship matrix; determining fuzzy operation rules; calculating comprehensive evaluation results; Evaluate health status, including: real-time calculation of the health of each indicator; use fuzzy evaluation model to perform multi-level fuzzy comprehensive calculation; determine the health status level of the whole machine; generate health status evaluation report; Construct risk warning mechanism, including: setting multi-level warning thresholds; establishing warning rule base; constructing warning level determination model; realizing real-time warning information push; Generate maintenance recommendations, including: establishing a mapping relationship between health status and maintenance strategy; designing a maintenance plan generator based on case reasoning; building a maintenance priority ranking model; and forming a standardized maintenance recommendation output.

8. A large-scale amusement facility operation monitoring device, used to execute the large-scale amusement facility operation monitoring method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module and control processing module; wherein, The data acquisition module is configured as follows: Acquire the three-dimensional data of the target amusement facility, and construct a three-dimensional model of the facility according to the three-dimensional data of the facility; Acquire historical working data, historical working environment data, historical maintenance data and product attribute data of the target amusement facility; The control processing module is configured as follows: Establishing a basic failure model of the target amusement facility according to the historical working data, the historical working environment data, the historical maintenance data and the product attribute data; Based on the basic failure model and the facility three-dimensional model, identifying key risk locations of the target amusement facility; Develop dynamic risk characteristic indicators for the basic failure model to form a multi-dimensional health assessment framework; Use non-destructive testing technology to test the key risk areas and obtain non-destructive testing data; Arrange a variety of intelligent sensors at the key risk locations to monitor operating parameters and structural health data in real time; Control intelligent inspection robots or drones to conduct automatic inspections and tests, and obtain video images captured by the intelligent inspection robots or drones; Deeply fusing the nondestructive testing data, the operating parameters, the structural health data and the video image to obtain monitoring data; Based on deep learning models and expert systems, intelligent analysis is performed on the integrated monitoring data to achieve automatic identification, diagnosis and prediction of faults; According to the load, structural characteristics, material properties and monitoring data of the target amusement facilities, a life assessment method based on mechanics, probability statistics and information technology is used to assess the remaining service life of the key risk parts, and trend analysis is performed in combination with historical data; A multi-index comprehensive evaluation method is used in combination with the health assessment framework to quantitatively evaluate the overall health status of the target amusement facility, and to generate dynamic risk warnings and maintenance recommendations; Based on the dynamic risk warnings and maintenance recommendations, a maintenance and repair plan is developed, and dynamic management is implemented to ensure the safe operation and performance optimization of the target amusement facilities.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the large-scale amusement facility operation monitoring method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the large-scale amusement facility operation monitoring method as described in any one of claims 1 to 7 are implemented.

Images