A remote monitoring system for port machinery groups based on virtual reality

Abstract

The present invention discloses a remote monitoring system for port machinery groups based on virtual reality. The BIM model is embedded in the virtual reality interface, so that the operator can view the detailed three-dimensional model and facility information of the port in the virtual reality environment, and realize more intuitive operation and monitoring; through the group intelligence module and the virtual reality interface, the operation of port machinery equipment is coordinated in real time, and the tasks and paths of the equipment are dynamically adjusted according to the facility information and environmental data provided by the BIM model; the environmental simulation data provided by the BIM platform is used to enhance the environmental perception ability of the virtual reality system, and realize more accurate environmental monitoring and early warning; a highly intelligent and dynamically adaptive remote monitoring system for port machinery groups is constructed. Not only the efficient collaborative operation, intelligent maintenance and dynamic adaptation of port machinery equipment are realized, but also the refinement and intelligence level of port management are significantly improved, and strong technical support and guarantee are provided.

Description

Technical Field

[0001] The invention belongs to the field of port management and mechanical equipment monitoring, and in particular is a remote monitoring system for a port machinery group based on virtual reality. Background Art

[0002] Although existing technologies have made some progress in port machinery and equipment monitoring and management, there are still many deficiencies, which are mainly manifested in the following aspects:

[0003] Limitations of monitoring methods: Traditional port machinery and equipment monitoring mainly relies on manual inspections and fixed monitoring cameras, which cannot fully and comprehensively grasp the operating status of the equipment and environmental changes. This monitoring method is not only inefficient, but also prone to missed detections and false alarms, making it difficult to meet the requirements of modern ports for efficient and safe management.

[0004] Insufficient data integration capabilities: The existing system has bottlenecks in data collection and integration. Data from various sensors and devices are often scattered in different systems, making it difficult to achieve unified management and comprehensive analysis. This data island phenomenon leads to information asymmetry and low data utilization, making it difficult to support intelligent decision-making and management.

[0005] Poor real-time performance and response speed: Traditional port management systems often rely on centralized data processing and analysis models. Data needs to be transmitted to a central server for processing, which is easily affected by network delays and bandwidth limitations. It is difficult to respond to emergencies and dynamic changes in a timely manner, reducing the real-time performance and reliability of the system.

[0006] Low level of intelligence and automation: Existing technologies have limited development in intelligence and automation. Many operations still require manual intervention and decision-making, and it is impossible to achieve fully automatic equipment scheduling and path optimization. Especially in complex port environments, it is difficult for existing systems to dynamically adjust the tasks and paths of equipment based on real-time data, resulting in low operating efficiency and waste of resources.

[0007] Limited environmental perception: The existing system has insufficient perception and simulation capabilities for the port environment, making it difficult to provide comprehensive and accurate environmental data support. Changes in environmental conditions (such as weather, terrain, traffic, etc.) have a significant impact on port operations, and the lack of effective environmental perception and adaptation mechanisms will lead to operational risks and reduced efficiency.

[0008] Imperfect maintenance management: Existing technologies lack foresight and initiative in equipment maintenance management. They mainly rely on regular maintenance and post-failure repairs, and are unable to predict and prevent equipment failures in advance, resulting in long equipment downtime and high maintenance costs, affecting the continuity and stability of port operations.

[0009] Inadequate user interaction experience: The user interface and interaction methods of the existing system are relatively traditional and single, and cannot provide an immersive and intuitive operation experience. Operators need to switch between multiple systems and interfaces, which is cumbersome and error-prone. In addition, there is a lack of effective training and simulation tools, which affects operational efficiency and accuracy. Summary of the invention

[0010] In order to solve the problems raised in the above background technology, the present invention provides a remote monitoring system for port machinery groups based on virtual reality; by integrating virtual reality, BIM, Internet of Things, swarm intelligence, edge computing and big data analysis technology, a highly intelligent and dynamically adaptable remote monitoring system for port machinery groups is constructed. The system not only realizes the efficient collaborative operation, intelligent maintenance and dynamic adaptation of port machinery and equipment, but also significantly improves the refinement and intelligence level of port management, and provides strong technical support and guarantee. These beneficial effects make the present invention have important application value and broad market prospects in the field of port management and machinery equipment monitoring.

[0011] To achieve the above object, the present invention provides the following technical solutions:

[0012] A remote monitoring system for port machinery groups based on virtual reality, comprising:

[0013] A virtual port model platform based on BIM technology, using BIM technology to build a three-dimensional model of the port; embedding facility information in the BIM model to achieve full life cycle management of the facility; simulating the environmental conditions of the port through the BIM model to provide environmental data support;

[0014] A virtual reality interface configured to provide an immersive three-dimensional environment that enables operators to view and monitor the operating status of all port machinery and equipment and the overall layout of the port in real time;

[0015] Multiple smart sensors installed on port machinery and equipment are configured to collect equipment operating status and environmental data and transmit this data through the IoT network;

[0016] A central data processing system configured to receive and process data transmitted from smart sensors, identify equipment operation patterns, predict potential failures, and optimize operating processes through big data analysis technology, and provide data-driven decision support;

[0017] An autonomous maintenance module, configured to generate maintenance plans based on big data analysis results, automatically adjust equipment operating parameters, perform preventive maintenance in advance, and automatically shut down when potential failures are detected;

[0018] a multi-dimensional data visualization module configured to present analysis results and real-time data through a virtual reality interface and a multi-dimensional data visualization tool, enabling operators to view equipment status and analysis results through three-dimensional models, heat maps, and charts;

[0019] A real-time feedback system configured to adjust the operation strategy of the equipment in real time according to the monitoring and analysis results, and to feed back the operator's instructions to the equipment in real time;

[0020] A swarm intelligence module, which is configured to coordinate the operation of all mechanical equipment in the port through swarm intelligence algorithms, dynamically adjust the tasks and paths of each equipment based on equipment status, task requirements and environmental conditions, and achieve efficient collaborative operations;

[0021] Embedding the BIM model into the virtual reality interface enables operators to view the detailed three-dimensional model and facility information of the port in the virtual reality environment, achieving more intuitive operation and monitoring; through the swarm intelligence module and virtual reality interface, the operation of port machinery and equipment can be coordinated in real time, and the tasks and paths of the equipment can be dynamically adjusted according to the facility information and environmental data provided by the BIM model; using the environmental simulation data provided by the BIM platform, the environmental perception capability of the virtual reality system can be enhanced to achieve more accurate environmental monitoring and early warning.

[0022] The central data processing system integrates blockchain technology and edge computing technology, including:

[0023] Multiple edge computing node modules are deployed at the port site and configured to pre-process, filter and analyze data locally. Machine learning algorithms are used to perform preliminary data analysis, detect abnormal situations, and generate early warning information. The pre-processed data is transmitted to the blockchain node through an encrypted channel for storage and further processing;

[0024] A plurality of blockchain node modules configured to record and verify data collected from sensors and edge computing nodes to ensure the immutability and security of the data, each blockchain node verifies the validity of the data through a consensus mechanism and stores the data in the blockchain, wherein the consensus mechanism includes proof of stake or practical Byzantine fault tolerance;

[0025] A distributed computing module, which is configured to use the computing resources in the blockchain network to perform complex data processing and analysis, split large computing tasks into small pieces, and assign them to various nodes in the blockchain network for parallel processing. The processing results are summarized and verified through the blockchain network to ensure the accuracy and efficiency of the calculation;

[0026] A data storage and synchronization module, configured to ensure that the data in the blockchain and the data of the edge computing nodes are consistent, realize real-time synchronization and update of data, use distributed storage technology to ensure the data consistency of each node, and update the data of the edge computing nodes to all blockchain nodes in real time through the synchronization mechanism of the blockchain network;

[0027] A smart contract module configured to automatically execute and manage rules and tasks related to port equipment operations, automatically generating maintenance instructions and notifying relevant personnel when equipment sensor data exceeds set thresholds.

[0028] Wherein, the autonomous maintenance module includes:

[0029] An adaptive control module configured to automatically adjust the equipment operating parameters using an adaptive control algorithm based on the equipment operating status and environmental data collected in real time by the intelligent sensor to ensure that the equipment operates in an optimal state;

[0030] A machine learning model configured to be trained based on historical data and real-time data, predict possible equipment failures by analyzing the data, and generate maintenance plans in advance;

[0031] a dynamic maintenance plan generation module configured to dynamically optimize maintenance strategies based on prediction results, intelligently allocate maintenance resources, and automatically shut down and initiate maintenance procedures when potential failures are detected;

[0032] The adaptive control module comprises:

[0033] A data acquisition unit, used to collect equipment operation status and environmental data in real time using intelligent sensors;

[0034] A parameter adjustment unit, used to automatically adjust the operating parameters of the equipment according to real-time data through an adaptive control algorithm;

[0035] Condition monitoring unit, which continuously monitors the status of equipment and identifies potential problems using anomaly detection algorithms;

[0036] Predictive maintenance unit, which is used to analyze historical and real-time data through machine learning models to predict possible equipment failures;

[0037] The machine learning model includes:

[0038] Data preprocessing unit, used to clean, denoise and standardize the collected data;

[0039] A model training unit, used to train a machine learning model using historical data;

[0040] Fault prediction unit, used to analyze real-time data using trained models to predict potential faults;

[0041] A maintenance plan generation unit, used for dynamically generating a maintenance plan according to the prediction results;

[0042] The dynamic maintenance plan generation module includes:

[0043] Maintenance strategy optimization unit, used to dynamically optimize maintenance strategies and determine the optimal maintenance time and method based on the predicted fault type and severity;

[0044] Resource management unit, used to intelligently allocate maintenance resources according to the maintenance plan to ensure efficient maintenance work;

[0045] Automatic execution unit, used to automatically shut down and start maintenance procedures when potential faults are detected, ensuring safe and efficient operation of equipment.

[0046] Wherein, the real-time feedback system comprises:

[0047] a data fusion unit configured to integrate data from different sensor nodes for local processing and preliminary analysis via edge computing nodes;

[0048] Intelligent analysis engine, configured to use machine learning and big data analysis technology to conduct in-depth analysis of the fused data, extract key information and predict the equipment operation status;

[0049] A self-organizing control unit configured to achieve coordination among edge computing nodes and dynamically adjust device operation strategies through a self-organizing algorithm;

[0050] A risk assessment unit configured to assess the risk level of the adjustment instruction generated by the self-organizing control unit and submit it to an operator for approval if the risk exceeds a threshold;

[0051] A strategy optimization unit configured to adjust the device operation strategy in real time based on data analysis results and self-organizing control algorithms to ensure that the device maintains optimal operating status in a changing environment;

[0052] A risk assessment mechanism is configured to assess the risk level of the optimization strategy and submit it to the operator for approval if the risk exceeds the preset threshold;

[0053] An operation instruction transmission module, configured to transmit an operator's instruction to the device via low-latency wireless communication;

[0054] An equipment status feedback module configured to feed back the equipment's operating status and operation results to the operator in real time;

[0055] Wherein, the swarm intelligence module includes:

[0056] An equipment status monitoring unit configured to monitor the operating status of port machinery and equipment in real time, including position, speed and load, using intelligent sensors;

[0057] A task requirement analysis unit configured to analyze the task requirements of each device based on port operation requirements and the current status of the device;

[0058] an environmental condition sensing unit configured to collect real-time environmental data using environmental sensors, including factors such as weather, terrain, and traffic;

[0059] A dynamic task allocation unit, configured to allocate tasks to each device in real time through a swarm intelligence algorithm to ensure balanced task load and efficient completion;

[0060] A path optimization unit configured to dynamically optimize the operation path of the device based on the device status and environmental conditions to reduce interference and conflict between devices;

[0061] A device behavior modeling unit configured to model the behavior of the device using a deep neural network to simulate the response of the device under different environmental conditions;

[0062] A reinforcement learning training unit configured to train the device's optimal strategy under different tasks and environmental conditions through a deep reinforcement learning algorithm;

[0063] A policy update unit configured to dynamically update the device's operating policy based on real-time data and mission requirements to ensure that the system maintains optimal operating status in a changing environment;

[0064] an environment perception fusion unit configured to integrate multi-source environment data using data fusion technology to generate a comprehensive environment perception map;

[0065] The dynamic adaptation mechanism unit is configured to dynamically adjust the tasks and paths of the equipment according to the environmental perception map and the equipment status, so as to ensure that the equipment can operate efficiently under changing environmental conditions.

[0066] The virtual reality interface further includes gesture recognition and voice control functions, enabling operators to control devices and interfaces through natural interaction.

[0067] Among them, the intelligent sensors include temperature sensors, vibration sensors, pressure sensors, humidity sensors and wind speed sensors, which are configured to comprehensively monitor the equipment operating status and port environment.

[0068] The multidimensional data visualization module supports a variety of data display modes, including three-dimensional models, heat maps, line charts, bar charts and pie charts, so that operators can choose the appropriate display method according to their needs.

[0069] Among them, the three-dimensional model of the port built using BIM technology includes docks, warehouses, roads and pipeline facilities; the information of the facilities includes equipment specifications, maintenance records and operating status; and the environmental conditions include weather, tides and hydrology.

[0070] Wherein, the application method of the remote monitoring system of the port machinery group is:

[0071] 1. System startup and initialization

[0072] Step 1: Start the VR device

[0073] The operator puts on the VR headset and starts the VR application; the system loads the virtual port environment, showing the 3D model of the port and its current status;

[0074] Step 2: Connect to BIM Model

[0075] The system loads a BIM-based virtual port model platform to display a detailed 3D model of the port;

[0076] Step 3: Data collection and transmission

[0077] The system collects the operating status and environmental data of port machinery and equipment in real time through intelligent sensors, and transmits the data to edge computing nodes through the Internet of Things network;

[0078] 2. Data Processing and Analysis

[0079] Step 4: Edge computing

[0080] Edge computing nodes perform local data processing and analysis at the port site, filter and pre-process sensor data, reduce data transmission delays, and improve the system's real-time response capabilities;

[0081] Step 5: Big Data Analysis

[0082] The data pre-processed by the edge computing node is transmitted to the central data processing system; the system uses big data analysis technology to process and analyze the data, identify equipment operation modes, predict potential failures, optimize operation processes, and provide data-driven decision support through machine learning and artificial intelligence algorithms;

[0083] 3. Virtual reality and BIM fusion interface

[0084] Step 6: Virtual Reality Display

[0085] The operator can view the 3D model of the port through the VR interface and monitor the operating status of the port machinery and equipment and the overall layout of the port in real time. Through gesture recognition and voice control, the operator can freely navigate in the VR environment and view detailed information of different equipment and facilities.

[0086] Step 7: Facility Information Display

[0087] In the virtual reality interface, the system integrates the BIM model, allowing operators to view detailed information on each facility, including equipment specifications, maintenance records, and operating status. Operators can also select different facilities to view their 3D models and related data.

[0088] 4. Real-time monitoring and dynamic adjustment

[0089] Step 8: Equipment status monitoring

[0090] The system monitors the operating status of port machinery and equipment in real time, and displays the current status, historical data and trend analysis of the equipment; operators can view the specific location, operating parameters and environmental conditions of the equipment through the virtual reality interface;

[0091] Step 9: Swarm Intelligence Control

[0092] The system coordinates the operation of all mechanical equipment in the port through swarm intelligence algorithms; based on equipment status, task requirements and environmental conditions, it dynamically adjusts the tasks and paths of each device to achieve efficient collaborative operations;

[0093] Step 10: Task allocation and path optimization

[0094] Based on real-time data and analysis results, the system uses swarm intelligence algorithms to dynamically assign tasks to each device to ensure balanced task load and efficient completion. Through the path optimization algorithm, the system generates the optimal operation path for each device to reduce interference and conflict between devices.

[0095] 5. Autonomous maintenance and intelligent feedback

[0096] Step 11: Autonomous Maintenance

[0097] The system generates maintenance plans based on big data analysis results, automatically adjusts equipment operating parameters, and performs preventive maintenance in advance; when a potential fault is detected, the system automatically shuts down and starts the maintenance program, notifying maintenance personnel to perform repairs;

[0098] Step 12: Multidimensional Data Visualization

[0099] The system displays analysis results and real-time data through a virtual reality interface and multi-dimensional data visualization tools; operators can view equipment status and analysis results through 3D models, heat maps and charts, helping them understand complex information and make more accurate decisions;

[0100] Step 13: Real-time feedback and adjustments

[0101] The system adjusts the equipment's operating strategy in real time based on monitoring and analysis results, and feeds back the operator's instructions to the equipment in real time; the operator can issue instructions directly through the virtual reality interface, and the system transmits the instructions to the equipment through low-latency wireless communication, ensuring the immediacy and efficiency of the operation;

[0102] Step 14: Operator Interaction and Approval

[0103] When the system detects that certain operation strategies may bring higher risks, the system will suspend execution and prompt the operator to approve. The operator reviews the risk assessment results through the virtual reality interface and decides whether to approve the operation strategy to ensure the safety and reliability of system operation.

[0104] 6. Environmental perception and intelligent adaptation

[0105] Step 15: Environmental Sensing

[0106] The system uses environmental sensors to collect real-time environmental data, including weather, terrain and traffic factors, and integrates multi-source data through data fusion technology to generate a comprehensive environmental perception map;

[0107] Step 16: Smart Adaptation

[0108] The system dynamically adjusts the equipment's tasks and paths based on the environmental perception map and equipment status to ensure that the equipment can operate efficiently under changing environmental conditions. In severe weather conditions, the system will adjust the equipment's operating speed and path to ensure safe operations.

[0109] Compared with the prior art, the present invention has the following beneficial effects:

[0110] 1. All-round real-time monitoring:

[0111] Using VR technology to create an immersive three-dimensional environment, operators can view and monitor the operating status of all port machinery and equipment and the overall layout of the port in real time in virtual reality;

[0112] Through gesture recognition and voice control, operators can navigate and operate freely, improving the comprehensiveness and real-time nature of monitoring;

[0113] Through smart sensors and IoT technology, equipment operation status and environmental data are collected in real time, and local processing and analysis are performed through edge computing nodes, reducing data transmission delays and improving system response speed;

[0114] 2. Data integration and comprehensive analysis:

[0115] Build a detailed 3D model of port facilities through BIM technology and embed detailed information of the facilities to achieve full life cycle management of the facilities. The system can integrate multi-source data, achieve unified management and comprehensive analysis of data, and provide accurate reference for equipment operation and maintenance;

[0116] Use big data analysis technology to process and analyze massive amounts of data collected from sensors, identify equipment operation modes, predict potential failures, optimize operating processes, and provide data-driven decision support through machine learning and artificial intelligence algorithms;

[0117] 3. Intelligent collaborative work:

[0118] Through swarm intelligence algorithms, the system can coordinate the operation of all mechanical equipment in the port, dynamically adjust the tasks and paths of each equipment based on equipment status, task requirements and environmental conditions, and achieve efficient collaborative operations and resource optimization;

[0119] Use deep reinforcement learning (DRL) algorithms to train the device's optimal strategy under different tasks and environmental conditions, and dynamically update the device's operating strategy based on real-time data to ensure the flexibility and robustness of the system;

[0120] 4. Autonomous maintenance and preventive management:

[0121] The system generates maintenance plans based on big data analysis results, automatically adjusts equipment operating parameters, and performs preventive maintenance in advance. When a potential fault is detected, the system automatically shuts down and starts the maintenance program, notifying maintenance personnel to perform repairs, reducing equipment downtime and maintenance costs;

[0122] Autonomous maintenance functions include real-time monitoring of equipment status, automatic adjustment of operating parameters and execution of preventive maintenance, which improves equipment reliability and service life;

[0123] 5. Multidimensional data visualization:

[0124] Display analysis results and real-time data through VR interface and multi-dimensional data visualization tools. Operators can view equipment status and analysis results through 3D models, heat maps, charts, etc., helping them understand complex information and make more accurate decisions;

[0125] The intuitive visual interface improves the operator's user experience and operating efficiency, and reduces the risk of misoperation;

[0126] 6. Environmental perception and dynamic adaptation:

[0127] The system uses environmental sensors to collect real-time environmental data and integrates multi-source data through data fusion technology to generate a comprehensive environmental perception map. According to the environmental perception map and equipment status, the system dynamically adjusts the tasks and paths of the equipment to ensure that the equipment can operate efficiently under changing environmental conditions.

[0128] In severe weather conditions, the system can adjust the speed and path of the equipment to ensure safe and efficient operations;

[0129] 7. User Interaction and Operator Participation:

[0130] The operator can intuitively operate and monitor through the VR interface, and the system can feed back the operator's instructions to the equipment in real time through low-latency wireless communication, ensuring the immediacy and efficiency of the operation;

[0131] When the system detects a high-risk operation strategy, it will suspend execution and prompt the operator for approval to ensure the safety and reliability of system operations.

[0132] In general, the present invention has built a highly intelligent and dynamically adaptable remote monitoring system for port machinery groups by integrating virtual reality, BIM, the Internet of Things, swarm intelligence, edge computing and big data analysis technologies. The system not only realizes efficient collaborative operation, intelligent maintenance and dynamic adaptation of port machinery and equipment, but also significantly improves the refinement and intelligence level of port management, and provides strong technical support and guarantee. These beneficial effects make the present invention have important application value and broad market prospects in the field of port management and machinery and equipment monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0133] Figure 1 The present invention is a flow chart of the application method. DETAILED DESCRIPTION

[0134] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0135] The present invention provides a remote monitoring system for a port machinery group based on virtual reality, comprising:

[0136] A virtual port model platform based on BIM technology, which uses BIM technology to build a detailed 3D model of the port; embed detailed information of the facilities in the BIM model to achieve full life cycle management of the facilities; simulate the environmental conditions of the port through the BIM model to provide accurate environmental data support;

[0137] A virtual reality interface configured to provide an immersive three-dimensional environment that enables operators to view and monitor the operating status of all port machinery and equipment and the overall layout of the port in real time;

[0138] Multiple smart sensors installed on port machinery and equipment are configured to collect equipment operating status and environmental data and transmit this data through the IoT network;

[0139] A central data processing system configured to receive and process data transmitted from smart sensors, identify equipment operation patterns, predict potential failures, optimize operating processes, and provide data-driven decision support through big data analysis technology;

[0140] An autonomous maintenance module, configured to generate maintenance plans based on big data analysis results, automatically adjust equipment operating parameters, perform preventive maintenance in advance, and automatically shut down when potential failures are detected;

[0141] a multi-dimensional data visualization module configured to present analysis results and real-time data through a virtual reality interface and a multi-dimensional data visualization tool, enabling operators to view equipment status and analysis results through three-dimensional models, heat maps, and charts;

[0142] A real-time feedback system configured to adjust the operation strategy of the equipment in real time according to the monitoring and analysis results, and to feed back the operator's instructions to the equipment in real time;

[0143] A swarm intelligence module, which is configured to coordinate the operation of all mechanical equipment in the port through swarm intelligence algorithms, dynamically adjust the tasks and paths of each equipment based on equipment status, task requirements and environmental conditions, and achieve efficient collaborative operations;

[0144] Embedding the BIM model into the virtual reality interface enables operators to view the detailed three-dimensional model and facility information of the port in the virtual reality environment, achieving more intuitive operation and monitoring; through the swarm intelligence module and virtual reality interface, the operation of port machinery and equipment can be coordinated in real time, and the tasks and paths of the equipment can be dynamically adjusted according to the facility information and environmental data provided by the BIM model; using the environmental simulation data provided by the BIM platform, the environmental perception capability of the virtual reality system can be enhanced to achieve more accurate environmental monitoring and early warning.

[0145] Among them, the formula for integrating BIM and virtual reality is: ;

[0146] in, It is the integrated interface of virtual reality and BIM. VR is the virtual reality system and BIM is the building information model.

[0147] The intelligent collaborative control formula is: ;

[0148] in, is the optimal operation strategy at time t, is the utility of strategy s at time t and environment state E, is the cost of strategy s at time t, is the set of all optional strategies.

[0149] Furthermore, the virtual reality interface further includes gesture recognition and voice control functions, enabling the operator to control the equipment and interface through natural interaction; the intelligent sensors include temperature sensors, vibration sensors, pressure sensors, humidity sensors and wind speed sensors, which are configured to comprehensively monitor the equipment operating status and port environment; the multidimensional data visualization module supports multiple data display modes, including three-dimensional models, heat maps, line charts, bar charts and pie charts, so that the operator can choose the appropriate display method according to needs.

[0150] Furthermore, the central data processing system integrates blockchain technology and edge computing technology, including: multiple blockchain node modules, configured to record and verify data collected from sensors and edge computing nodes to ensure the immutability and security of the data, each blockchain node verifies the validity of the data through a consensus mechanism and stores the data in the blockchain, the consensus mechanism includes proof of stake or practical Byzantine fault tolerance;

[0151] Multiple edge computing node modules are deployed at the port site and configured to pre-process, filter and analyze data locally. Machine learning algorithms are used to perform preliminary data analysis, detect abnormal situations, and generate early warning information. The pre-processed data is transmitted to the blockchain node through an encrypted channel for storage and further processing;

[0152] A smart contract module configured to automatically execute and manage rules and tasks related to port equipment operations, automatically generating maintenance instructions and notifying relevant personnel when equipment sensor data exceeds set thresholds;

[0153] A data storage and synchronization module, configured to ensure that the data in the blockchain and the data of the edge computing nodes are consistent, realize real-time synchronization and update of data, use distributed storage technology to ensure the data consistency of each node, and update the data of the edge computing nodes to all blockchain nodes in real time through the synchronization mechanism of the blockchain network;

[0154] A distributed computing module is configured to use the computing resources in the blockchain network to perform complex data processing and analysis, split large computing tasks into small pieces, and assign them to various nodes in the blockchain network for parallel processing. The processing results are summarized and verified through the blockchain network to ensure the accuracy and efficiency of the calculation.

[0155] Furthermore, the central data processing system includes a blockchain node module, an edge computing node module, a smart contract module, a data storage and synchronization module, and a distributed computing module.

[0156] The blockchain node module is used to record and verify data collected from sensors and edge computing nodes to ensure the immutability and security of the data.

[0157] Implementation process:

[0158] Data collection: The data of each port machinery and equipment is transmitted to the adjacent edge computing nodes through the Internet of Things.

[0159] Data packaging: The edge computing node packages the pre-processed data and generates transactions.

[0160] Data broadcast: The packaged data is broadcast to other nodes in the blockchain network through the P2P network.

[0161] Consensus mechanism: Blockchain nodes verify the validity of data through a consensus mechanism (such as PoS or PBFT).

[0162] Data storage: After verification, the data is recorded in the blockchain and distributedly stored on multiple nodes.

[0163] Among them, the data packaging formula is: ;

[0164] Among them, T is the packaged transaction, is the i-th data point, and the value range of i is 1≤i≤n.

[0165] Consensus mechanism (PBFT): ; View Change is the minimum number of nodes required to successfully reach a consensus; Total Nodes is the total number of nodes participating in the PBFT consensus mechanism. This value represents the number of all nodes in the entire network and is used to calculate the minimum number of nodes required to reach a consensus.

[0166] Specifically, the edge computing node module is used to pre-process, filter and analyze data locally.

[0167] Implementation process:

[0168] Data collection: Edge computing nodes collect data from sensors.

[0169] Data preprocessing: denoising and standardization.

[0170] Anomaly detection: Use machine learning algorithms to perform preliminary data analysis, detect anomalies, and generate early warning information.

[0171] Data encryption: Use symmetric encryption algorithms to encrypt data.

[0172] Data transmission: The encrypted data is transmitted to the blockchain node through an encrypted channel.

[0173] Data normalization formula: ;in, is the standardized data, X is the original data, μ is the mean of the data, is the standard deviation of the data.

[0174] Data encryption formula (AES): ; Where C is the encrypted data, is the encryption function, D is the original data, and k is the encryption key.

[0175] The smart contract module is used to automatically execute and manage rules and tasks related to port equipment operations.

[0176] Implementation process:

[0177] Contract writing: Write smart contracts based on operating rules and tasks.

[0178] Contract deployment: deploy smart contracts on the blockchain.

[0179] Contract trigger: When the device sensor data exceeds the set threshold, the smart contract automatically generates maintenance instructions and notifies relevant personnel.

[0180] Contract trigger conditions: ;

[0181] Among them, T is the trigger condition, S is the sensor data, is the threshold value, V is the device status, is the status threshold.

[0182] The data storage and synchronization module is used to ensure that the data in the blockchain and the data in the edge computing node are consistent.

[0183] Implementation process:

[0184] Data synchronization: Utilize the synchronization mechanism of the blockchain network to update the data of edge computing nodes to all blockchain nodes in real time.

[0185] Data storage: Use distributed storage technology to ensure data consistency among nodes.

[0186] Data synchronization formula: ;

[0187] Among them, H(D) is the hash value of data D, is the hash value of the data block, and the value range of i is 1 to n, that is, , where n is the total number of data blocks; Represents the exclusive OR operation of hash values.

[0188] The distributed computing module is used to utilize computing resources in the blockchain network to perform complex data processing and analysis.

[0189] Implementation process:

[0190] Task decomposition: Split large computing tasks into smaller chunks.

[0191] Task allocation: Assigned to each node in the blockchain network for parallel processing.

[0192] Result aggregation: The processing results are aggregated and verified through the blockchain network.

[0193] Task allocation formula: ;

[0194] in, The probability of assigning a task from node i to node j, where node i is the starting node of the task and node j is the target node of the task. is the pheromone intensity from task i to node j, is the heuristic information from task i to node j, α and β are algorithm parameters, and N is the node set; This means multiplying the combined value of pheromone intensity and heuristic information: ;

[0195] Furthermore, the autonomous maintenance module includes:

[0196] An adaptive control module configured to automatically adjust the equipment operating parameters using an adaptive control algorithm based on the equipment operating status and environmental data collected in real time by the intelligent sensor to ensure that the equipment operates in an optimal state;

[0197] A machine learning model configured to be trained based on historical data and real-time data, predict possible equipment failures by analyzing the data, and generate maintenance plans in advance;

[0198] a dynamic maintenance plan generation module configured to dynamically optimize maintenance strategies based on prediction results, intelligently allocate maintenance resources, and automatically shut down and initiate maintenance procedures when potential failures are detected;

[0199] Specifically, the adaptive control module includes:

[0200] Data acquisition unit, parameter adjustment unit, condition monitoring unit and predictive maintenance unit;

[0201] Implementation process:

[0202] Data collection: Use smart sensors to collect equipment operating status and environmental data in real time.

[0203] Parameter adjustment: Through adaptive control algorithms, the operating parameters of the equipment are automatically adjusted according to real-time data to ensure that the equipment operates in the best condition.

[0204] Condition Monitoring: Continuously monitors equipment status and uses anomaly detection algorithms to identify potential problems.

[0205] Predictive maintenance: Analyze historical and real-time data through machine learning models to predict possible equipment failures and generate maintenance plans in advance.

[0206] Adaptive control formula: ;

[0207] Among them, u(t) is the control input, K is the adaptive gain matrix, and e(t) is the error signal (the difference between the target value and the actual value).

[0208] Specifically, the machine learning model includes: a data preprocessing unit, a model training unit, a fault prediction unit, and a maintenance plan generation unit;

[0209] Implementation process:

[0210] Data preprocessing: Clean, denoise and standardize the collected data.

[0211] Model training: Use historical data to train machine learning models (such as LSTM, random forest).

[0212] Fault prediction: Use trained models to analyze real-time data and predict potential faults.

[0213] Maintenance plan: Dynamically generate a maintenance plan based on the prediction results, including maintenance time, steps, and required tools.

[0214] Using LSTM prediction model:

[0215] formula: ;

[0216] ;

[0217] ;

[0218] Among them, β represents the activation function, which usually adopts the Sigmoid function or other nonlinear functions. The activation function is used to introduce nonlinear characteristics so that the model can learn and represent more complex functional relationships. In LSTM, the activation function is usually used in gated units (such as input gate, forget gate, and output gate) to regulate information flow;

[0219] Represents the output of time step t. The output is the result of the LSTM unit at the current time step and is usually used in subsequent prediction or decision-making processes. The output can be a direct prediction result or an intermediate result for further processing;

[0220] represents the hidden state at time step t. The hidden state is the internal state in the LSTM network, capturing information from the input sequence to the current time step. It is passed to the next time step as output, helping the network remember long-term dependencies;

[0221] Represents the cell state at time step t. The cell state is the internal storage state of the LSTM unit that stores long-term information. The storage, update, and output of information are controlled by the gating mechanism;

[0222] Represents the input data at time step t. The input data is the external information received by the LSTM unit at each time step and processed as the input of the model;

[0223] represents the forget gate at time step t. The forget gate controls which parts of the cell state need to be forgotten;

[0224] Represents the input gate at time step t. The input gate controls which parts of the current input data need to be stored in the cell state;

[0225] Represents the output gate at time step t. The output gate controls which parts of the cell state need to be output as hidden states;

[0226] is the weight matrix of the hidden state;

[0227] is the weight matrix of the cell state;

[0228] is the bias vector of the hidden state;

[0229] is the bias vector of the cell state;

[0230] is the hidden state of the previous time step and the current input splicing;

[0231] Cell state The result of applying the hyperbolic tangent function;

[0232] Specifically, the dynamic maintenance plan generation module includes: a maintenance strategy optimization unit, a resource management unit and an automatic execution unit.

[0233] Implementation process:

[0234] Maintenance strategy optimization: Dynamically optimize maintenance strategies based on predicted fault types and severity to determine the optimal maintenance time and method.

[0235] Resource management: Intelligently allocate maintenance resources (such as personnel, tools, and spare parts) according to the maintenance plan to ensure efficient maintenance work.

[0236] Automatic execution: When a potential failure is detected, the machine is automatically shut down and maintenance procedures are initiated to ensure safe and efficient operation of the equipment.

[0237] Maintenance strategy optimization formula: ;

[0238] Among them, M(t) is the optimal maintenance strategy at time, U(m,t) is the utility of maintenance strategy m at time t, C(m,t) is the cost of maintenance strategy m at time t, and M is the set of all optional maintenance strategies.

[0239] The working process of the autonomous maintenance module is:

[0240] 1. Data collection and preprocessing:

[0241] Sensor data: collects equipment operating parameters, such as temperature, pressure, vibration, etc. Data cleaning: removes noise and outliers, and standardizes processing;

[0242] 2. Adaptive control:

[0243] According to the error signal, the control input is adjusted through the adaptive gain matrix to ensure that the equipment operating parameters are stable within the target range;

[0244] 3. Machine learning model training and fault prediction

[0245] Train the LSTM model and use historical data to learn the operation mode of the equipment. Predict the operation status of the equipment in real time and identify potential failures;

[0246] 4. Dynamic maintenance plan generation and optimization:

[0247] Generate maintenance plans based on the prediction results of the LSTM model. Dynamically optimize maintenance strategies and intelligently allocate maintenance resources to ensure timely and efficient maintenance work;

[0248] 5. Automatic maintenance execution:

[0249] When a potential fault is detected, the machine will be automatically shut down and maintenance procedures will be initiated to execute the optimized maintenance plan;

[0250] Furthermore, the real-time feedback system includes: a self-organizing feedback network, real-time data fusion and analysis, dynamic strategy optimization and risk assessment, and an instant feedback and execution module;

[0251] Specifically, the self-organizing feedback network includes a self-organizing control unit and a risk assessment unit.

[0252] Implementation process:

[0253] Self-organizing control unit: Each edge computing node coordinates with each other through a self-organizing algorithm, dynamically adjusts the device operation strategy, and realizes autonomous control;

[0254] Risk assessment unit: assesses the risk level of the adjustment instructions generated by the self-organizing control unit, and submits them to the operator for approval if the risk exceeds the threshold;

[0255] The self-organizing control unit realizes the self-organizing control between nodes through the following formula:

[0256] ;

[0257] in, is the velocity of the ith node at time t, is the control coefficient, The overall center location. For all The sum of j in the set is calculated. Represents the set of neighbor nodes at node i. The summation symbol represents the accumulation of each item calculated for all neighbor nodes j. is the position vector of node i, indicating the spatial position of node i at time t. is the position vector of node j, indicating the spatial position of neighbor node j at time t.

[0258] Specifically, real-time data fusion and analysis includes a data fusion unit and an intelligent analysis engine;

[0259] Implementation process:

[0260] Data fusion unit: integrates data from different sensor nodes and performs local processing and preliminary analysis through edge computing nodes;

[0261] Intelligent analysis engine: Use machine learning and big data analysis technology to conduct in-depth analysis of the fused data, extract key information and predict the equipment operation status;

[0262] The data fusion unit realizes data fusion through the Kalman filter formula:

[0263] ;

[0264] ;

[0265] in,

[0266] Represents all observations at time k based on time k An estimate of the system state, which is the best estimate of the current state at time k, updated by combining the previous prediction and the current observation;

[0267] represents the system state at time k predicted at time k-1, which is the predicted value of the state at time k based on all previous observations at time k-1;

[0268] represents the Kalman gain at time k. The Kalman gain determines the weight between the predicted state and the observed value and adjusts the update process of the state estimation;

[0269] represents the observed value or measurement at time k, which is the data observed from the system at time k and is used to update the state estimate;

[0270] H represents the measurement matrix, which maps the system state to the observation space;

[0271] represents the prediction error covariance at time k based on all information at time k-1. This is the error covariance of the state prediction at time k, reflecting the uncertainty of the prediction;

[0272] Q represents the covariance matrix of the measurement noise, which describes the statistical characteristics of the noise in the observations.

[0273] Specifically, dynamic strategy optimization and risk assessment include strategy optimization unit and risk assessment mechanism;

[0274] Implementation process:

[0275] Strategy optimization unit: Based on data analysis results and self-organizing control algorithms, it adjusts the equipment operation strategy in real time to ensure that the equipment maintains the best operating state in a changing environment;

[0276] Risk assessment mechanism: Evaluate the risk level of the optimization strategy and submit it to the operator for approval if the risk exceeds the preset threshold;

[0277] The strategy optimization unit implements dynamic strategy optimization through the Q-learning algorithm:

[0278] ;

[0279] Among them, Q (s, a) is the value of taking action a in state s, is the learning rate, For instant rewards, is the discount factor, For the next state, For the status The best action under

[0280] Risk assessment formula: ;

[0281] Where R is the risk value, is the weight of the i-th risk factor, is the value of the ith risk factor, and n is the number of risk factors.

[0282] Specifically, the instant feedback and execution module includes operation instruction transmission, equipment status feedback, and operator approval mechanism;

[0283] Implementation process:

[0284] Operation instruction transmission: The operator's instructions are converted into equipment operation commands and transmitted to the equipment through low-latency wireless communication;

[0285] Equipment status feedback: Feedback the equipment's operating status and operation results to the operator in real time, displayed through an augmented reality (AR) interface;

[0286] Operator approval mechanism: When the risk assessment result exceeds the threshold, the system pauses execution and prompts the operator for approval;

[0287] Furthermore, the swarm intelligence module includes swarm intelligence algorithms, deep reinforcement learning, and environmental perception and dynamic adaptation.

[0288] Specifically, the swarm intelligence algorithm includes equipment status monitoring, task requirement analysis, environmental condition perception, dynamic task allocation and path optimization.

[0289] Implementation process:

[0290] Equipment status monitoring: Use smart sensors to monitor the operating status of each mechanical equipment in real time, including position, speed, load, etc.;

[0291] Mission requirement analysis: Analyze the mission requirements of each equipment based on port operation requirements and the current status of the equipment;

[0292] Environmental condition perception: using environmental sensors to collect real-time environmental data, including weather, terrain, traffic and other factors;

[0293] Dynamic task allocation: Use swarm intelligence algorithms (such as ant colony algorithm and particle swarm optimization) to allocate tasks to each device in real time to ensure balanced task load and efficient completion;

[0294] Path optimization: Dynamically optimize the operation path of equipment based on equipment status and environmental conditions to reduce interference and conflicts between equipment;

[0295] Using ant colony algorithm: ;

[0296] in, is the probability of assigning a task from node i to node j, is the pheromone intensity from task i to node j, is the heuristic information from task i to node j, α and β are algorithm parameters, and N is the node set;

[0297] Path optimization formula f(n)=g(n)+y(n);

[0298] Among them, f(n) is the total cost of node n, g(n) is the actual cost from the starting point to node n, and y(n) is the estimated cost from node n to the target node (heuristic function).

[0299] Specifically, the deep reinforcement learning includes device behavior modeling, reinforcement learning training and strategy updating;

[0300] Implementation process:

[0301] Device behavior modeling: Use deep neural networks (DNNs) to model the behavior of devices and simulate the responses of devices under different environmental conditions;

[0302] Reinforcement learning training: Through deep reinforcement learning (DRL) algorithms (such as DQN, DDPG), the device is trained to have the optimal strategy under different tasks and environmental conditions;

[0303] Strategy update: Dynamically update the device's operating strategy based on real-time data and task requirements to ensure that the system maintains optimal operating status in a changing environment;

[0304] Reinforcement Learning Value Function (DQN): ;

[0305] Among them, Q(s,a) is the value of taking action a in state s, For instant rewards, is the discount factor, For the next state, For the status The best action under .

[0306] Specifically, the environment perception and dynamic adaptation include an environment perception unit and a dynamic adaptation mechanism;

[0307] Implementation process:

[0308] Environmental perception unit: uses environmental sensors to collect real-time environmental data, integrates multi-source data through data fusion technology, and generates a comprehensive environmental perception map;

[0309] Dynamic adaptation mechanism: Dynamically adjust the tasks and paths of equipment according to the environmental perception map and equipment status to ensure that the equipment can adapt to changing environmental conditions and achieve efficient operation;

[0310] Environmental perception fusion formula (Bayesian fusion): ;

[0311] in, is the probability of the environment state E under the condition of data D, is the probability of observing data D under environmental state E, P(E) is the prior probability of environmental state E, and P(D) is the probability of data D.

[0312] Further, such as Figure 1 As shown, the application method of the remote monitoring system of port machinery group based on virtual reality is:

[0313] 1. System startup and initialization

[0314] Step 1: Start the VR device

[0315] The operator puts on the VR headset and starts the VR application. The system loads the virtual port environment, showing the 3D model of the port and its current status;

[0316] Step 2: Connect to BIM Model

[0317] The system loads a virtual port model platform based on building information modeling (BIM) to display a detailed three-dimensional model of the port, including facilities such as docks, warehouses, roads, pipelines, etc.

[0318] Step 3: Data collection and transmission

[0319] The system uses smart sensors to collect real-time operating status and environmental data of port machinery and equipment, including equipment location, speed, load, ambient temperature, humidity, etc. These data are transmitted to edge computing nodes through the Internet of Things (IoT) network;

[0320] 2. Data Processing and Analysis

[0321] Step 4: Edge computing

[0322] Edge computing nodes perform local data processing and analysis at the port site, filter and pre-process sensor data, reduce data transmission delays, and improve the system's real-time response capabilities;

[0323] Step 5: Big Data Analysis

[0324] The data pre-processed by the edge computing node is transmitted to the central data processing system. The system uses big data analysis technology to process and analyze massive data, identify equipment operation modes, predict potential failures, optimize operation processes, and provide data-driven decision support through machine learning and artificial intelligence algorithms;

[0325] 3. Virtual reality and BIM fusion interface

[0326] Step 6: Virtual Reality Display

[0327] The operator can view the 3D model of the port through the VR interface and monitor the operating status of the port machinery and equipment and the overall layout of the port in real time. Through gesture recognition and voice control, the operator can freely navigate in the VR environment and view detailed information of different equipment and facilities;

[0328] Step 7: Facility Information Display

[0329] In the virtual reality interface, the system integrates the BIM model, and the operator can view the detailed information of each facility, including equipment specifications, maintenance records, operating status, etc. The operator can also view the 3D model and related data of different facilities by selecting them;

[0330] 4. Real-time monitoring and dynamic adjustment

[0331] Step 8: Equipment status monitoring

[0332] The system monitors the operating status of port machinery and equipment in real time, and displays the current status, historical data and trend analysis of the equipment. Operators can view the specific location, operating parameters and environmental conditions of the equipment through the virtual reality interface;

[0333] Step 9: Swarm Intelligence Control

[0334] The system coordinates the operation of all mechanical equipment in the port through swarm intelligence algorithms (such as ant colony algorithm and A* algorithm). Based on the equipment status, task requirements and environmental conditions, the system dynamically adjusts the tasks and paths of each equipment to achieve efficient collaborative operations.

[0335] Step 10: Task allocation and path optimization

[0336] Based on real-time data and analysis results, the system uses swarm intelligence algorithms to dynamically assign tasks to each device to ensure balanced task load and efficient completion. Through the path optimization algorithm, the system generates the optimal operation path for each device to reduce interference and conflict between devices;

[0337] 5. Autonomous maintenance and intelligent feedback

[0338] Step 11: Autonomous Maintenance

[0339] The system generates maintenance plans based on big data analysis results, automatically adjusts equipment operating parameters, and performs preventive maintenance in advance. When a potential fault is detected, the system automatically shuts down and starts the maintenance program, notifying maintenance personnel to perform repairs;

[0340] Step 12: Multidimensional Data Visualization

[0341] The system displays analysis results and real-time data through a virtual reality interface and multi-dimensional data visualization tools. Operators can view equipment status and analysis results through 3D models, heat maps, charts, etc., helping them understand complex information and make more accurate decisions;

[0342] Step 13: Real-time feedback and adjustments

[0343] The system adjusts the equipment's operating strategy in real time based on monitoring and analysis results, and feeds back the operator's instructions to the equipment in real time. The operator can issue instructions directly through the virtual reality interface, and the system transmits the instructions to the equipment through low-latency wireless communication, ensuring the immediacy and efficiency of the operation;

[0344] Step 14: Operator Interaction and Approval

[0345] When the system detects that certain operation strategies may bring higher risks, the system will suspend execution and prompt the operator for approval. The operator reviews the risk assessment results through the virtual reality interface and decides whether to approve the operation strategy to ensure the safety and reliability of system operation;

[0346] 6. Environmental perception and intelligent adaptation

[0347] Step 15: Environmental Sensing

[0348] The system uses environmental sensors to collect real-time environmental data, including weather, terrain, traffic and other factors, and integrates multi-source data through data fusion technology to generate a comprehensive environmental perception map;

[0349] Step 16: Smart Adaptation

[0350] The system dynamically adjusts the tasks and paths of the equipment based on the environmental perception map and equipment status to ensure that the equipment can operate efficiently under changing environmental conditions. For example, in severe weather conditions, the system will adjust the speed and path of the equipment to ensure safe operation.

[0351] Through the operation process of the above-mentioned virtual reality-based port machinery remote monitoring system, the system realizes efficient collaborative operation, intelligent maintenance and dynamic adaptation of port machinery and equipment, providing unprecedented technical support and operational efficiency for port management. The system integrates virtual reality and BIM technology, provides detailed facility information and environmental data, and improves the refinement and intelligence level of port management. Operators can monitor equipment status, adjust operation strategies, perform facility maintenance and environmental adaptation in real time through the virtual reality interface, realizing comprehensive digital management and intelligent control;

[0352] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A remote monitoring system for port machinery groups based on virtual reality, It is characterized in that include: A virtual port model platform based on BIM technology, using BIM technology to build a three-dimensional model of the port; embedding facility information in the BIM model to achieve full life cycle management of the facility; simulating the environmental conditions of the port through the BIM model to provide environmental data support; A virtual reality interface configured to provide an immersive three-dimensional environment that enables operators to view and monitor the operating status of all port machinery and equipment and the overall layout of the port in real time; Multiple smart sensors installed on port machinery and equipment are configured to collect equipment operating status and environmental data and transmit this data through the IoT network; A central data processing system configured to receive and process data transmitted from smart sensors, identify equipment operation patterns, predict potential failures, and optimize operating processes through big data analysis technology, and provide data-driven decision support; An autonomous maintenance module, configured to generate maintenance plans based on big data analysis results, automatically adjust equipment operating parameters, perform preventive maintenance in advance, and automatically shut down when potential failures are detected; a multi-dimensional data visualization module configured to present analysis results and real-time data through a virtual reality interface and a multi-dimensional data visualization tool, enabling operators to view equipment status and analysis results through three-dimensional models, heat maps, and charts; A real-time feedback system configured to adjust the operation strategy of the equipment in real time according to the monitoring and analysis results, and to feed back the operator's instructions to the equipment in real time; A swarm intelligence module, which is configured to coordinate the operation of all mechanical equipment in the port through swarm intelligence algorithms, dynamically adjust the tasks and paths of each equipment based on equipment status, task requirements and environmental conditions, and achieve efficient collaborative operations; Embedding BIM models into the virtual reality interface enables operators to view detailed 3D models and facility information of the port in a virtual reality environment, achieving more intuitive operation and monitoring. Through the swarm intelligence module and virtual reality interface, the operation of port machinery and equipment can be coordinated in real time, and the tasks and paths of the equipment can be dynamically adjusted according to the facility information and environmental data provided by the BIM model. Using the environmental simulation data provided by the BIM platform, the environmental perception ability of the virtual reality system can be enhanced to achieve more accurate environmental monitoring and early warning. The real-time feedback system includes: a self-organizing feedback network, real-time data fusion and analysis, dynamic strategy optimization and risk assessment, and an instant feedback and execution module; Specifically, the self-organizing feedback network includes a self-organizing control unit and a risk assessment unit; Implementation process: Self-organizing control unit: Each edge computing node coordinates with each other through a self-organizing algorithm, dynamically adjusts the device operation strategy, and realizes autonomous control; Risk assessment unit: assesses the risk level of the adjustment instructions generated by the self-organizing control unit, and submits them to the operator for approval if the risk exceeds the threshold; The self-organizing control unit realizes the self-organizing control among nodes through the following formula: in, is the velocity of the ith node at time t, c 1 , c 2 , c 3 is the control coefficient, It is the overall central location; For all N i The sum of j in the set, N i represents the set of neighbor nodes at node i; the summation symbol represents the accumulation of each item calculated for all neighbor nodes j; is the position vector of node i, indicating the spatial position of node i at time t; is the position vector of node j, indicating the spatial position of neighbor node j at time t; Specifically, real-time data fusion and analysis includes a data fusion unit and an intelligent analysis engine; Implementation process: Data fusion unit: integrates data from different sensor nodes and performs local processing and preliminary analysis through edge computing nodes; Intelligent analysis engine: Use machine learning and big data analysis technology to conduct in-depth analysis of the fused data, extract key information and predict the equipment operation status; The data fusion unit realizes data fusion through the Kalman filter formula: K k =P k|k-1 H T (HP k|k-1 H T +Q) -1 ; in, Indicates that at time k, all observations z based on time k k An estimate of the system state, which is the best estimate of the current state at time k, updated by combining the previous prediction and the current observation; represents the system state at time k predicted at time k-1, which is the predicted value of the state at time k based on all previous observations at time k-1; K k represents the Kalman gain at time k. The Kalman gain determines the weight between the predicted state and the observed value and adjusts the update process of the state estimation; z k represents the observed value or measurement at time k, which is the data observed from the system at time k and is used to update the state estimate; H represents the measurement matrix, which maps the system state to the observation space; P k|k-1 represents the prediction error covariance at time k based on all information at time k-1. This is the error covariance of the state prediction at time k, reflecting the uncertainty of the prediction; Q represents the covariance matrix of the measurement noise, which describes the statistical characteristics of the noise in the observations; Specifically, dynamic strategy optimization and risk assessment include strategy optimization unit and risk assessment mechanism; Implementation process: Strategy optimization unit: Based on data analysis results and self-organizing control algorithms, it adjusts the equipment operation strategy in real time to ensure that the equipment maintains the best operating state in a changing environment; Risk assessment mechanism: Evaluate the risk level of the optimization strategy and submit it to the operator for approval if the risk exceeds the preset threshold; The strategy optimization unit implements dynamic strategy optimization through the Q-learning algorithm: Where Q(s, a) is the value of taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s′ is the next state, and a′ is the optimal action in state s′; Risk assessment formula: Among them, R is the risk value, w i is the weight of the i-th risk factor, r i is the value of the ith risk factor, and n is the number of risk factors; Specifically, the instant feedback and execution module includes operation instruction transmission, equipment status feedback, and operator approval mechanism; Implementation process: Operation instruction transmission: The operator's instructions are converted into equipment operation commands and transmitted to the equipment through low-latency wireless communication; Equipment status feedback: Feedback the equipment's operating status and operation results to the operator in real time, displayed through an augmented reality interface; Operator approval mechanism: When the risk assessment result exceeds the threshold, the system pauses execution and prompts the operator for approval; Among them, the swarm intelligence module includes swarm intelligence algorithm, deep reinforcement learning, and environmental perception and dynamic adaptation; Specifically, the swarm intelligence algorithm includes equipment status monitoring, task requirement analysis, environmental condition perception, dynamic task allocation, and path optimization; Implementation process: Equipment status monitoring: Use smart sensors to monitor the operating status of each mechanical equipment in real time, including position, speed, load, etc.; Mission requirement analysis: Analyze the mission requirements of each equipment based on port operation requirements and the current status of the equipment; Environmental condition perception: using environmental sensors to collect real-time environmental data, including weather, terrain, traffic and other factors; Dynamic task allocation: Allocate tasks to each device in real time through swarm intelligence algorithms to ensure balanced task load and efficient completion; Path optimization: Dynamically optimize the operation path of equipment based on equipment status and environmental conditions to reduce interference and conflicts between equipment; Using ant colony algorithm: Among them, P ij is the probability of assigning a task from node i to node j, τ ij is the pheromone strength from task i to node j, η ij is the heuristic information from task i to node j, α and β are algorithm parameters, and N is the node set; Path optimization formula f(n)=g(n)+y(n); Among them, f(n) is the total cost of node n, g(n) is the actual cost from the starting point to node n, and y(n) is the estimated cost from node n to the target node; Specifically, the deep reinforcement learning includes device behavior modeling, reinforcement learning training and strategy updating; Implementation process: Device behavior modeling: Use deep neural networks to model the behavior of devices and simulate the response of devices under different environmental conditions; Reinforcement learning training: Through deep reinforcement learning algorithms, the device is trained to develop optimal strategies under different tasks and environmental conditions; Strategy update: Dynamically update the device's operating strategy based on real-time data and task requirements to ensure that the system maintains optimal operating status in a changing environment; Reinforcement learning value function: Where Q(s, a) is the value of taking action a in state s, r is the immediate reward, γ is the discount factor, s′ is the next state, and a′ is the optimal action in state s′; Specifically, the environment perception and dynamic adaptation include an environment perception unit and a dynamic adaptation mechanism; Implementation process: Environmental perception unit: uses environmental sensors to collect real-time environmental data, integrates multi-source data through data fusion technology, and generates a comprehensive environmental perception map; Dynamic adaptation mechanism: Dynamically adjust the tasks and paths of equipment according to the environmental perception map and equipment status to ensure that the equipment can adapt to changing environmental conditions and achieve efficient operation; Environmental perception fusion formula: Among them, P(E / D) is the probability of environmental state E under the condition of data D, P(D / E) is the probability of observing data D under environmental state E, P(E) is the prior probability of environmental state E, and P(D) is the probability of data D.

2. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The central data processing system integrates blockchain technology and edge computing technology, including: Multiple edge computing node modules are deployed at the port site and configured to pre-process, filter and analyze data locally. Machine learning algorithms are used to perform preliminary data analysis, detect abnormal situations, and generate early warning information. The pre-processed data is transmitted to the blockchain node through an encrypted channel for storage and further processing; A plurality of blockchain node modules configured to record and verify data collected from sensors and edge computing nodes to ensure the immutability and security of the data, each blockchain node verifies the validity of the data through a consensus mechanism and stores the data in the blockchain, wherein the consensus mechanism includes proof of stake or practical Byzantine fault tolerance; A distributed computing module, which is configured to use the computing resources in the blockchain network to perform complex data processing and analysis, split large computing tasks into small pieces, and assign them to various nodes in the blockchain network for parallel processing. The processing results are summarized and verified through the blockchain network to ensure the accuracy and efficiency of the calculation; A data storage and synchronization module, configured to ensure that the data in the blockchain and the data of the edge computing nodes are consistent, realize real-time synchronization and update of data, use distributed storage technology to ensure the data consistency of each node, and update the data of the edge computing nodes to all blockchain nodes in real time through the synchronization mechanism of the blockchain network; A smart contract module configured to automatically execute and manage rules and tasks related to port equipment operations, automatically generating maintenance instructions and notifying relevant personnel when equipment sensor data exceeds set thresholds.

3. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The autonomous maintenance module comprises: An adaptive control module configured to automatically adjust the equipment operating parameters using an adaptive control algorithm based on the equipment operating status and environmental data collected in real time by the intelligent sensor to ensure that the equipment operates in an optimal state; A machine learning model configured to be trained based on historical data and real-time data, predict possible equipment failures by analyzing the data, and generate maintenance plans in advance; a dynamic maintenance plan generation module configured to dynamically optimize maintenance strategies based on prediction results, intelligently allocate maintenance resources, and automatically shut down and initiate maintenance procedures when potential failures are detected; The adaptive control module comprises: A data acquisition unit, used to collect equipment operation status and environmental data in real time using intelligent sensors; A parameter adjustment unit, used to automatically adjust the operating parameters of the equipment according to real-time data through an adaptive control algorithm; Condition monitoring unit, which continuously monitors the status of equipment and identifies potential problems using anomaly detection algorithms; Predictive maintenance unit, which is used to analyze historical and real-time data through machine learning models to predict possible equipment failures; The machine learning model includes: Data preprocessing unit, used to clean, denoise and standardize the collected data; A model training unit, used to train a machine learning model using historical data; Fault prediction unit, used to analyze real-time data using trained models to predict potential faults; A maintenance plan generating unit, used for dynamically generating a maintenance plan according to the prediction results; The dynamic maintenance plan generation module includes: Maintenance strategy optimization unit, used to dynamically optimize maintenance strategies and determine the optimal maintenance time and method based on the predicted fault type and severity; Resource management unit, used to intelligently allocate maintenance resources according to the maintenance plan to ensure efficient maintenance work; Automatic execution unit, used to automatically shut down and start maintenance procedures when potential faults are detected, ensuring safe and efficient operation of equipment.

4. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The virtual reality interface further includes gesture recognition and voice control capabilities, enabling operators to control devices and interfaces through natural interaction.

5. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The intelligent sensors include temperature sensors, vibration sensors, pressure sensors, humidity sensors and wind speed sensors, which are configured to comprehensively monitor the equipment operating status and port environment.

6. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The multidimensional data visualization module supports a variety of data display modes, including three-dimensional models, heat maps, line graphs, bar graphs and pie charts, so that operators can choose the appropriate display method according to their needs.

7. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, Features: The three-dimensional model of the port constructed using BIM technology includes docks, warehouses, roads and pipeline facilities; the information of the facilities includes equipment specifications, maintenance records and operating status; and the environmental conditions include weather, tides and hydrology.

8. A remote monitoring system for port machinery groups based on virtual reality as claimed in claim 1, It is characterized in that The application method of the port machinery group remote monitoring system is:

1. System startup and initialization Step 1: Start the VR device The operator puts on the VR headset and starts the VR application; the system loads the virtual port environment, showing the 3D model of the port and its current status; Step 2: Connect to BIM Model The system loads a BIM-based virtual port model platform to display a detailed 3D model of the port; Step 3: Data collection and transmission The system collects the operating status and environmental data of port machinery and equipment in real time through intelligent sensors, and transmits the data to edge computing nodes through the Internet of Things network; 2. Data Processing and Analysis Step 4: Edge computing Edge computing nodes perform local data processing and analysis at the port site, filter and pre-process sensor data, reduce data transmission delays, and improve the system's real-time response capabilities; Step 5: Big Data Analysis The data pre-processed by the edge computing node is transmitted to the central data processing system; the system uses big data analysis technology to process and analyze the data, identify equipment operation modes, predict potential failures, optimize operation processes, and provide data-driven decision support through machine learning and artificial intelligence algorithms; 3. Virtual Reality and BIM Fusion Interface Step 6: Virtual Reality Display The operator can view the 3D model of the port through the VR interface and monitor the operating status of the port machinery and equipment and the overall layout of the port in real time. Through gesture recognition and voice control, the operator can freely navigate in the VR environment and view detailed information of different equipment and facilities. Step 7: Facility Information Display In the virtual reality interface, the system integrates the BIM model, allowing operators to view detailed information on each facility, including equipment specifications, maintenance records, and operating status. Operators can also select different facilities to view their 3D models and related data.

4. Real-time monitoring and dynamic adjustment Step 8: Equipment status monitoring The system monitors the operating status of port machinery and equipment in real time, and displays the current status, historical data and trend analysis of the equipment; operators can view the specific location, operating parameters and environmental conditions of the equipment through the virtual reality interface; Step 9: Swarm Intelligence Control The system coordinates the operation of all mechanical equipment in the port through swarm intelligence algorithms; based on equipment status, task requirements and environmental conditions, it dynamically adjusts the tasks and paths of each device to achieve efficient collaborative operations; Step 10: Task allocation and path optimization Based on real-time data and analysis results, the system uses swarm intelligence algorithms to dynamically assign tasks to each device to ensure balanced task load and efficient completion. Through the path optimization algorithm, the system generates the optimal operation path for each device to reduce interference and conflict between devices.

5. Autonomous maintenance and intelligent feedback Step 11: Autonomous Maintenance The system generates maintenance plans based on big data analysis results, automatically adjusts equipment operating parameters, and performs preventive maintenance in advance; when a potential fault is detected, the system automatically shuts down and starts the maintenance program, notifying maintenance personnel to perform repairs; Step 12: Multidimensional Data Visualization The system displays analysis results and real-time data through a virtual reality interface and multi-dimensional data visualization tools; Operators can view equipment status and analysis results through 3D models, heat maps and charts, helping them understand complex information and make more accurate decisions; Step 13: Real-time feedback and adjustments The system adjusts the equipment's operating strategy in real time based on monitoring and analysis results, and feeds back the operator's instructions to the equipment in real time; the operator can issue instructions directly through the virtual reality interface, and the system transmits the instructions to the equipment through low-latency wireless communication, ensuring the immediacy and efficiency of the operation; Step 14: Operator Interaction and Approval When the system detects that certain operation strategies may bring higher risks, the system will suspend execution and prompt the operator to approve. The operator reviews the risk assessment results through the virtual reality interface and decides whether to approve the operation strategy to ensure the safety and reliability of system operation.

6. Environmental Perception and Intelligent Adaptation Step 15: Environmental Sensing The system uses environmental sensors to collect real-time environmental data, including weather, terrain and traffic factors, and integrates multi-source data through data fusion technology to generate a comprehensive environmental perception map; Step 16: Smart Adaptation The system dynamically adjusts the equipment's tasks and paths based on the environmental perception map and equipment status to ensure that the equipment can operate efficiently under changing environmental conditions. In severe weather conditions, the system will adjust the equipment's operating speed and path to ensure safe operations.

Images