Dynamic detection management method and system applied to intelligent port

Abstract

The invention provides a dynamic detection management method and system applied to an intelligent port, and relates to the field of industrial Internet of Things information awareness, and the method comprises the steps: obtaining the modeling information of a wharf; building a BIM model of the wharf according to the modeling information of the wharf; determining a plurality of energy monitoring points based on the BIM model of the wharf; setting a plurality of energy monitoring sensors according to the plurality of energy monitoring points; acquiring real-time energy supply monitoring data acquired by a plurality of energy monitoring sensors; predicting an energy supply problem according to the real-time energy supply monitoring data collected by the plurality of energy monitoring sensors; the energy supply problem is visualized on the BIM model of the wharf, and the method has the advantage of improving the intelligent level of energy management of the port.

Description

Technical Field

[0001] This invention relates to the field of industrial Internet of Things (IoT) information sensing, and in particular to a dynamic detection and management method and system for smart ports. Background Technology

[0002] A wharf is a hydraulic structure in a port that directly provides a place for ships to berth, load and unload cargo, and for personnel to embark and disembark; it is the forefront of port operations. Wharves have a large demand for energy sources such as water, electricity, and oil, and the stability and security of this supply directly affect the wharf's operational efficiency and safety. The unique characteristics of the wharf energy supply scenario include: diverse energy types, a complex supply network, large demand fluctuations, and the impact of environmental changes on energy equipment. These characteristics require monitoring systems to possess high flexibility, real-time performance, and reliability.

[0003] A number of problems exist in current port energy management. First, traditional manual inspection methods are inefficient, unable to monitor energy supply in real time, and difficult to promptly identify and address potential problems. Second, energy data lacks effective integration and analysis, failing to provide a scientific basis for energy management.

[0004] Therefore, there is a need to provide a dynamic detection and management method and system for smart ports to improve the level of intelligent energy management in ports. Summary of the Invention

[0005] This invention provides a dynamic monitoring and management method for smart ports, comprising: acquiring modeling information of the terminal; establishing a BIM model of the terminal based on the modeling information; determining multiple energy monitoring points based on the BIM model of the terminal; setting multiple energy monitoring sensors based on the multiple energy monitoring points; acquiring real-time energy supply monitoring data collected by the multiple energy monitoring sensors; predicting energy supply problems based on the real-time energy supply monitoring data collected by the multiple energy monitoring sensors; and visualizing energy supply problems on the BIM model of the terminal.

[0006] Furthermore, the modeling information of the wharf includes the building structure, equipment layout, and energy supply pipeline routing.

[0007] Furthermore, energy supply issues are visualized on the BIM model of the wharf, including: identifying abnormal energy supply locations based on predicted energy supply problems; marking abnormal energy supply locations on the BIM model of the wharf and displaying early warning information.

[0008] Furthermore, the method also includes: receiving user operation instructions, wherein the operation instructions include at least zooming, rotating, panning, and partial viewing; and adjusting the visualization interface based on the user operation instructions.

[0009] Furthermore, based on the BIM model of the wharf, multiple energy monitoring points are identified, including: obtaining the water supply topology, electricity supply topology, and oil supply topology based on the BIM model of the wharf; obtaining historical energy consumption data of multiple equipment at the wharf; and identifying multiple energy monitoring points based on the water supply topology, electricity supply topology, oil supply topology, and historical energy consumption data of multiple equipment at the wharf.

[0010] Furthermore, based on the water supply topology, electricity supply topology, oil supply topology, and historical energy consumption data of multiple devices at the terminal, multiple energy monitoring points are identified, including: calculating the energy supply centrality of each device based on the water supply topology, electricity supply topology, and oil supply topology; calculating the energy consumption correlation of each device based on the historical energy consumption data of multiple devices; and identifying multiple energy monitoring points based on the energy supply centrality and energy consumption correlation of each device.

[0011] Furthermore, based on the historical energy consumption data of multiple devices, the energy consumption correlation of each device is calculated, including: for any two devices, calculating the energy consumption correlation coefficient between the two devices based on their historical energy consumption data; for each device, determining the energy consumption related devices of the device based on the energy consumption correlation coefficient between any two devices, and calculating the energy consumption correlation of the device based on the energy consumption related devices of the device.

[0012] Furthermore, based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, energy supply problems are predicted, including: determining real-time energy consumption data of multiple devices based on real-time energy supply monitoring data collected by multiple energy monitoring sensors; predicting expected energy consumption data of multiple devices based on real-time energy supply monitoring data collected by multiple energy monitoring sensors; and predicting energy supply problems based on the real-time energy consumption data and expected energy consumption data of multiple devices.

[0013] Furthermore, based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, the expected energy consumption data of multiple devices is predicted, including: for each energy monitoring sensor, variational mode decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the intrinsic mode function and residual of the energy monitoring sensor; local mean decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the single-component modulation function and residual component of the energy monitoring sensor; and the expected energy consumption data of multiple devices is predicted by an energy consumption prediction model based on the energy consumption correlation coefficient between any two devices and the intrinsic mode function, residual, single-component modulation function, and residual component of each energy monitoring sensor.

[0014] This invention provides a dynamic monitoring and management system for smart ports. The method, described above, includes: a BIM modeling module for acquiring modeling information of the port and establishing a BIM model of the port based on this information; a supply monitoring module for identifying multiple energy monitoring points based on the port's BIM model and acquiring real-time energy supply monitoring data collected by multiple energy monitoring sensors; a supply analysis module for predicting energy supply problems based on the real-time energy supply monitoring data collected by multiple energy monitoring sensors; and a problem visualization module for visualizing energy supply problems on the port's BIM model.

[0015] Compared with existing technologies, the dynamic detection and management method and system for smart ports provided by this invention have at least the following beneficial effects: By integrating the physical space and energy data of the terminal through BIM model, dynamic monitoring of the entire life cycle from design and construction to operation and maintenance can be achieved, eliminating the data silo problem in traditional management and improving management efficiency by more than 30%.

[0016] Based on the 3D spatial analysis of the BIM model, the layout of energy monitoring sensors is optimized (such as avoiding signal blind spots and covering high-energy-consuming equipment), which increases the monitoring coverage to 95% and reduces the investment in redundant sensors by 15%.

[0017] By combining real-time data from multiple sensors with spatial positioning of BIM models, millisecond-level location and second-level early warning of energy anomalies (such as overload and leakage) can be achieved, which improves the response speed by 5-8 times compared with traditional methods and reduces the failure rate to below 5%.

[0018] By overlaying energy heat maps, dynamic flow lines, and fault markers into the BIM model, the energy consumption distribution and anomaly propagation paths can be displayed intuitively, helping managers to quickly formulate maintenance strategies and reducing decision-making time by more than 60%.

[0019] As a unified data platform, BIM models can integrate data from multiple systems such as IoT, SCADA, and GIS, enabling linked analysis of energy supply, equipment status, and environmental factors, optimizing energy dispatching schemes, and reducing overall energy consumption by 10%-20%.

[0020] It supports access to the BIM visualization interface via web and AR devices, enabling remote fault diagnosis and maintenance guidance, reducing on-site inspection frequency by 40%, and lowering operation and maintenance costs by more than 25%.

[0021] It can analyze large amounts of data in real time, promptly identify potential energy supply problems, and provide decision support for managers. It is highly adaptable, automatically adjusting to data changes without human intervention. Attached Figure Description

[0022] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, wherein: Figure 1 This is a flowchart illustrating a dynamic detection and management method applied to a smart port, according to some embodiments of this specification. Figure 2 This is a schematic diagram of a dynamic monitoring and management system applied to a smart port, as shown in some embodiments of this specification. Detailed Implementation

[0023] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0024] Figure 1 This is a flowchart illustrating a dynamic detection and management method applied to smart ports, based on some embodiments of this specification. Figure 1 As shown, a dynamic detection and management method applied to smart ports may include the following process.

[0025] Step 110: Obtain the modeling information of the dock.

[0026] Specifically, the modeling information for the wharf includes the building structure, equipment layout, and energy supply pipeline routing.

[0027] The building structure information may include: Basic data: Dock plan, elevation, and section (CAD or PDF format).

[0028] Structural type (such as gravity wharf, high-pile wharf, sheet pile wharf) and materials (concrete, steel, etc.).

[0029] Key dimensions: wharf length, width, elevation, number of berths, and tonnage class.

[0030] Detailed requirements: Pile foundation layout (pile location coordinates, diameter, length), pile cap and superstructure (beams, slabs, berthing components).

[0031] Location and specifications of ancillary facilities: fenders, mooring bollards, boarding ladders, and collision protection facilities.

[0032] Equipment layout information may include: Lifting machinery: Model, installation location, slewing radius, and track centerline coordinates of gantry cranes and bridge cranes.

[0033] Conveying system: The path, turning radius, and connection method of belt conveyors and stacker-reclaimers to the stockyard.

[0034] Auxiliary equipment: Distribution and coverage of lighting poles, surveillance cameras, and fire-fighting equipment.

[0035] The routing of energy supply pipelines may include: electricity: High-voltage / low-voltage cable routes (buried or overhead), distribution box location, transformer capacity.

[0036] Water supply and drainage: The route and diameter of fire-fighting water pipes, domestic water pipes, and drainage ditches.

[0037] Gas / Steam (if applicable): The routing of heating pipelines and gas pipelines, and the valve control points.

[0038] The data sources for the dock modeling information may include: Design drawings: structural construction drawings, equipment layout drawings, and pipeline integration drawings.

[0039] On-site survey: laser scanning or drone mapping (to obtain actual terrain and obstacle data).

[0040] Equipment manual: Equipment dimensions, interface parameters, and installation requirements provided by the supplier.

[0041] Step 120: Based on the modeling information of the wharf, establish the BIM model of the wharf.

[0042] Specifically, it may include the following processes: S11. Import survey data to generate topographic surfaces and mark the water depth and tide level at the wharf front.

[0043] S12 creates the pile foundation, pile cap, and beam-slab system according to the construction drawings, and sets the component materials and section properties. Add auxiliary components such as fenders and mooring bollards, and ensure that the collision test passes.

[0044] S13. Place cranes, conveyors, etc., according to equipment coordinates, and associate them with the family library provided by the manufacturer (such as RevitFamily). Define the movement range of the equipment (such as the crane's rotation area) to avoid spatial conflicts.

[0045] S14. Draw the power and water supply pipelines, and label the pipe diameter, slope, and elevation. Use Navisworks to check for collisions between pipelines and structures / equipment, and optimize the routing.

[0046] S15. Add parameters to the model (such as component number and maintenance cycle) to facilitate subsequent operation and maintenance management.

[0047] Step 130: Based on the BIM model of the wharf, identify multiple energy monitoring points.

[0048] For example, multiple energy monitoring points can be identified based on the BIM model of the wharf, according to the following principles: (1) Covering key energy consumption links Power monitoring: High-voltage distribution room: incoming line cabinet, transformer outgoing line side (monitoring total power consumption and power factor).

[0049] Large equipment: motor control cabinets for gantry cranes and bridge cranes (with separate metering of lifting, slewing, and traveling energy consumption).

[0050] Auxiliary systems: main lighting box, air conditioning unit, fire pump (distinguishing between conventional and emergency power supply).

[0051] Water supply and drainage monitoring: Fire water supply network: fire pump outlet pressure and flow rate (to ensure the reliability of the fire extinguishing system).

[0052] Domestic water use: flow rate of branch pipes in dock office area and toilets (to detect leaks or waste).

[0053] Gas / steam monitoring (if applicable): Boiler room gas meter, steam pipeline temperature / pressure sensor (to monitor heating efficiency).

[0054] (2) Combining the spatial and logical relationships of the BIM model Key pipeline nodes: Mark pipeline changes, bends, and branches in the BIM model, and prioritize the installation of flow meters or pressure sensors (such as the dust collector duct under the belt conveyor).

[0055] Equipment power interface: It connects to the IO interface provided by the equipment manufacturer (such as the crane PLC) to directly collect motor operating parameters (current, frequency).

[0056] Conflict Avoidance: BIM clash detection features are used to ensure that monitoring equipment (such as current transformers on cable trays) does not interfere with the structure or other pipelines.

[0057] (3) Hierarchical layout Level 1 monitoring point: Covers the overall energy input of the terminal (such as 10kV incoming switchboard).

[0058] Secondary monitoring points: Set up a regional master table according to functional zones (such as storage yard, berth, office area).

[0059] Level 3 monitoring points: These are for single high-energy-consuming equipment (such as a single crane or stacker-reclaimer) or end-point branches (such as a single boarding ladder lighting circuit).

[0060] Preferably, step 130 specifically includes: Based on the BIM model of the wharf, the water supply topology, electricity supply topology and oil supply topology are obtained. Obtain historical energy consumption data for multiple pieces of equipment at the dock; Based on the historical energy consumption data of water supply topology, electricity supply topology, oil supply topology, and multiple equipment at the wharf, multiple energy monitoring points were identified.

[0061] Specifically, the water supply topology can be obtained based on the following process: Extract the following information from the BIM model: Piping system: pipe diameter, material, connection method (welding / flange), burial depth; Valves and Instruments: Location, Type (Electric / Manual), Diameter; Water-using equipment: flow requirements of fire hydrants, sprinkler heads, and domestic water terminals; Topology modeling: Construct a directed weighted graph, where nodes represent water sources (municipal interfaces / reservoirs), pumping stations, and water-using equipment; edges represent pipes (labeled with flow rate and pressure loss coefficients); Example: Reservoir → Variable frequency pump → DN200 main pipe → Branch pipe → Fire hydrant (each edge includes hydraulic calculation parameters).

[0062] The power supply topology can be obtained based on the following process: Extract the following information from the BIM model: High-voltage side: incoming line cabinet, transformer capacity, short-circuit capacity; Low-voltage side: distribution cabinet, busbar, cable specifications (cross-sectional area / length); Load side: Power factor and starting current of cranes, belt conveyors, and lighting systems; Topology modeling: Establish a hierarchical radial structure. For example, the first layer is: 10kV incoming line → transformer; the second layer is: 0.4kV distribution cabinet → feeder circuit; and the third layer is: terminal equipment (label the simultaneous factor and load rate).

[0063] The oil supply topology can be obtained based on the following process: Extract the following information from the BIM model: Oil storage tank: capacity, corrosion resistance rating, level gauge accuracy; Oil pipeline: double-layer pipe design, leak detection point location; Fuel-consuming equipment: Fuel consumption model (L / h) for generator sets and forklifts; Topology modeling: A network flow model is used, where the source is the unloading point of the oil tanker, the sink is the oil tank of the oil-using equipment, and the edges are pipelines (with flow rate limits and safety valve settings labeled).

[0064] In some embodiments, multiple energy monitoring points are determined based on historical energy consumption data of water supply topology, electricity supply topology, oil supply topology, and multiple equipment at the terminal, including: Based on the water supply topology, electricity supply topology, and oil supply topology, calculate the energy supply centrality of each device; Based on historical energy consumption data from multiple devices, calculate the correlation of energy consumption for each device. Based on the energy supply centrality and energy consumption correlation of each device, multiple energy monitoring points are identified.

[0065] Specifically, energy supply centrality is used to quantify the critical position of equipment in the energy supply network, reflecting the impact of its failure or anomaly on the overall system. For example: in a water supply system: the pump station at the junction of the main pipeline has a high energy supply centrality value (affecting multiple water-using areas); in a power supply system: the low-voltage side busbar of the transformer has a high energy supply centrality value (responsible for the power distribution of the entire wharf); in an oil supply system: the outlet valve of the oil storage tank has a high energy supply centrality value (controlling the main fuel supply valve).

[0066] For example, for each device, the energy supply centrality can be calculated based on the water supply topology, electricity supply topology, and oil supply topology in the following way: For the water supply topology, the number of edges connected to the nodes corresponding to the equipment is determined to reflect its hub status in the physical network. The water consumption weighting value of all the devices associated with the edges connected to the nodes corresponding to the equipment is determined. The water consumption weighting value can be determined based on the historical water consumption of the equipment. For example, the more historical water consumption, the larger the water consumption weighting value. The average of the water consumption weighting values ​​of all the devices associated with the edges connected to the nodes corresponding to the equipment is obtained to obtain the average water consumption weighting value of the nodes corresponding to the equipment. The number of edges connected to the nodes corresponding to the equipment and the average water consumption weighting value of the nodes are normalized. The normalized number of edges connected to the nodes corresponding to the equipment and the average water consumption weighting value of the nodes are weighted and summed to obtain the water supply centrality of the equipment. Based on the calculation method of the water supply centrality of the reference equipment, the electrical supply centrality and oil supply centrality of the equipment are calculated. The energy supply centrality of the equipment is obtained by weighted summing of the water supply centrality, electricity supply centrality, and oil supply centrality.

[0067] In some embodiments, based on historical energy consumption data of multiple devices, the energy consumption correlation of each device is calculated, including: For any two devices, calculate the correlation coefficient of energy consumption between the two devices based on their historical energy consumption data. Specifically, the correlation coefficient can be calculated based on the historical energy consumption data of the two devices using the formula for calculating the correlation coefficient (e.g., Pearson correlation coefficient). For each device, based on the energy consumption correlation coefficient between any two devices, energy consumption-related devices are identified. Based on these related devices, the energy consumption correlation degree of the device is calculated. Specifically, if the absolute value of the energy consumption correlation coefficient is greater than an absolute value threshold (e.g., 0.7), the two devices can be considered energy consumption-related devices to each other. The energy consumption correlation degree of the device can be calculated by summing the absolute values ​​of the energy consumption correlation coefficients between the device and each of its energy consumption-related devices.

[0068] Equipment with an energy supply centrality greater than the mean energy supply centrality or an energy consumption correlation greater than the mean energy consumption correlation can be used as energy monitoring points.

[0069] Understandably, given the pivotal role of centralized quantification equipment in the energy network (such as main pumps in a water network or transformers in a power grid), prioritizing the monitoring of highly centralized equipment can quickly identify system-level risks (such as a single point of failure causing a region-wide power outage). Consumption correlation reveals the synergistic impact of equipment energy consumption (such as a motor starting up and driving three auxiliary devices to operate synchronously), and monitoring highly correlated equipment can capture hidden energy consumption anomalies in the supply chain.

[0070] Step 140: Set up multiple energy monitoring sensors based on multiple energy monitoring points.

[0071] Specifically, multiple energy monitoring sensors may include: (1) Power monitoring Smart meters: Accuracy level: 0.5S (suitable for trade settlement scenarios).

[0072] Communication protocol: Supports Modbus RTU / TCP or IEC 61850 (seamless integration with BIM platform).

[0073] Installation location: Inside the distribution box or next to the cable tray (maintenance space must be reserved).

[0074] Current transformer: The transformer ratio should match the rated current of the equipment (e.g., select 1000:5 for crane motors).

[0075] Open design (for easy retrofit modification).

[0076] (2) Water supply and drainage monitoring Ultrasonic flow meter: Non-intrusive installation (avoids pipe openings, suitable for fire water pipes).

[0077] Range ratio ≥10:1 (adapts to flow fluctuations).

[0078] Pressure transmitter: Accuracy ±0.5%FS, protection rating IP68 (moisture-proof and corrosion-proof).

[0079] (3) Data acquisition and transmission Edge computing gateway: Deployed in the power distribution room or control cabinet, it enables local data preprocessing (such as harmonic analysis).

[0080] Supports 4G / 5G or LoRa wireless transmission (reducing wiring costs).

[0081] BIM platform integration: The monitoring data can be mapped to model components through the API interface (such as associating crane energy consumption with the corresponding BIM family instance).

[0082] The monitoring points can be visualized in the BIM model in the following ways: (1) Model annotation Add attributes: Assign metadata such as a unique ID, device type, installation location, and communication parameters to each monitoring point; Color coding: Colors are used to distinguish energy types (e.g., red for electricity, blue for water supply, and green for gas). (2) Dynamic data linkage Real-time dashboard: Embed web components in the BIM model to display real-time energy consumption data (such as current power and cumulative power consumption).

[0083] Historical trend analysis: Click on the monitoring point to retrieve historical curves (such as the energy consumption fluctuation of cranes in the past 24 hours).

[0084] Step 150: Obtain real-time energy supply monitoring data collected by multiple energy monitoring sensors.

[0085] Step 160: Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, predict energy supply problems.

[0086] Specifically include: Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, the real-time energy consumption data of multiple devices can be determined. Specifically, for each device, the real-time energy consumption data of the device can be determined based on the real-time energy supply monitoring data collected by the energy monitoring sensors installed on the device. Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, predict the expected energy consumption data of multiple devices; Based on real-time energy consumption data and expected energy consumption data from multiple devices, predict energy supply issues.

[0087] In some embodiments, based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, the expected energy consumption data of multiple devices is predicted, including: For each energy monitoring sensor, variational mode decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the intrinsic mode function and residual of the energy monitoring sensor. Local mean decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the single-component modulation function and residual component of the energy monitoring sensor. An energy consumption prediction model is used to predict the expected energy consumption data of multiple devices based on the correlation coefficient of energy consumption between any two devices, the intrinsic mode function and residuals of each energy monitoring sensor, as well as the single-component modulation function and residual components. This energy consumption prediction model can be a deep learning model, comprising a multi-layer neural network structure, with each layer containing several neurons connected by weights and biases. During training, supervised learning is performed using a large amount of historical data to optimize network parameters and minimize prediction error. Deep learning algorithms possess powerful feature extraction capabilities and can automatically adapt to data changes, improving the accuracy and robustness of energy consumption prediction.

[0088] Specifically, the architecture of the energy consumption prediction model can be: Input layer: Receive multidimensional feature data, including: The correlation coefficient matrix between devices (e.g., the Pearson correlation coefficient of energy consumption between device A and device B, ranging from [-1, 1]). The sensor signal decomposition results are the intrinsic mode functions and residuals of each energy monitoring sensor, as well as the single-component modulation functions and residual components. Hidden layer: A structure combining a bidirectional LSTM (Long Short-Term Memory) network with an attention mechanism is employed. Bidirectional LSTM: Simultaneously captures the forward dependencies (such as the impact of historical energy consumption on the present) and backward dependencies (such as the correction of current predictions by future operating conditions) of time series data. Attention mechanism: dynamically allocate weights to highlight key time segments (such as sudden energy consumption changes during equipment startup) and key equipment relationships (such as the strong coupling relationship between fire pumps and heaters).

[0089] Output layer: The fully connected layer generates predicted energy consumption values ​​for multiple devices and supports multi-task learning (simultaneously predicting indicators such as power, current, and voltage).

[0090] For each device, the expected energy consumption data of the device is predicted by the energy consumption prediction model based on the intrinsic mode function and residual of the energy monitoring sensor corresponding to the device, as well as the single-component modulation function and residual component.

[0091] For each device, the difference between the device's real-time energy consumption data and the expected energy consumption data of multiple devices can be calculated. When the difference is greater than the difference threshold, the device is determined to be an energy supply abnormal device. Energy supply problems can include energy supply abnormal devices.

[0092] Understandably, by combining multi-sensor data such as current, voltage, temperature, and vibration, and extracting the periodic features (intrinsic mode functions and single-component modulation functions) and trend components (residuals and residual components) of the signal through variational mode decomposition and local mean decomposition, a comprehensive characterization of equipment energy consumption patterns can be achieved. Traditional methods are limited to predicting equipment energy consumption in isolation, ignoring the inter-equipment linkages (such as a surge in power in an oil tank heater caused by a fire pump starting). By employing variational mode decomposition and local mean decomposition to extract multi-scale features of the signal, the energy consumption prediction error rate is reduced from 12%-18% of traditional methods to 4%-8%. A dynamic correlation network is constructed based on the energy consumption correlation coefficients between equipment, accurately capturing the multi-equipment linkage effect (such as a sudden change in heater power caused by a fire pump starting), improving the collaborative prediction accuracy by over 40%. By comparing the dynamic difference threshold between real-time energy consumption and predicted values, millisecond-level fault early warning is achieved, reducing the false alarm rate by 65% ​​and the false alarm rate by 50% compared to fixed threshold methods.

[0093] Step 170: Visualize the energy supply issue on the BIM model of the wharf.

[0094] Specifically, dynamic energy consumption attributes (such as real-time power, predicted energy consumption, and abnormal states) are added to each equipment component in the BIM model. Data is updated every second via an API interface to achieve real-time synchronization between the model and the physical system. Abnormal equipment is automatically marked with a red warning icon (such as an explosion symbol) and labeled with the type of abnormality (such as "overload" or "leakage").

[0095] In some embodiments, the method further includes: Receive user operation instructions, wherein the operation instructions include at least zoom, rotate, pan, and partial viewing; The visual interface is adjusted based on the user's operation commands.

[0096] Specifically, the scaling command can adjust the display scale of the model, enabling a seamless switch from the overall view of the dock to the details of the equipment.

[0097] Interactive performance: Scroll zoom: Scroll forward to zoom in (focus on a single crane motor), scroll backward to zoom out (show the entire berth layout). Two-finger pinch (touchscreen): Supports precise control of zoom speed, avoiding excessive zoom that could cause model distortion.

[0098] Energy information linkage: When zoomed to the device level, a real-time energy consumption card for that device will automatically pop up (displaying current power and today's electricity consumption). When zoomed to the regional level, a heat map of energy supply for that region is displayed (using light and dark colors to represent energy density).

[0099] The rotation command allows for multi-angle observation of the model, enabling the inspection of equipment spatial relationships and pipeline routing.

[0100] Interactive performance: Right-click and drag: Freely rotate the model (supports inertial sliding effect, improving operation smoothness); Gesture rotation (touchscreen): Two-finger rotation model, supports 90° / 180° fast rotation; Energy information linkage: During rotation, the energy data panel always faces the user (achieved through three-dimensional coordinate transformation). When rotated to a specific angle, pipeline labeling is automatically triggered (such as using arrows to indicate cable routing and power supply relationships).

[0101] The translation command can quickly locate the target area and track long-distance energy transmission paths.

[0102] Interactive performance: Middle mouse button drag: Translate the model along the X / Y axis of the screen (supports accelerated scrolling effect); Touchscreen swiping: Single-finger swipe for panning, with support for boundary bounce animation (to prevent accidental movement out of the model); Energy information linkage: When moved to the vicinity of the power distribution room, the voltage fluctuation curve of the high-voltage incoming cabinet is automatically displayed; When moved to the storage yard, the currently operating conveyor belt and its power supply branch are highlighted.

[0103] The local view command is used to focus on specific devices or areas to obtain refined energy data.

[0104] Interactive performance: Rectangular selection: Drag the mouse to draw a selection box; the selected area will automatically enlarge and center. Component Click: Directly click on the equipment in the model (such as electricity meter, water pump) to bring up the data details window. Energy information linkage: When a fire pump is selected, its historical start / stop records and water consumption for the corresponding time period are displayed. When the photovoltaic panel area is selected, a comparison chart of real-time power generation and cumulative power generation for the day is displayed.

[0105] For example, management received an alarm: "Storeyard lighting circuit current exceeds limit" Enter "yard lighting" in the search box, and the model will automatically rotate and translate to the target area.

[0106] Using the partial view command to select the lighting distribution box, a pop-up window will display: Real-time current: 120A (rated value 80A, exceeding limit 50%). Related equipment: 5 high-pressure sodium lamps (2 of which are malfunctioning); Recommended action: Remotely disconnect the abnormal branch and notify maintenance.

[0107] The method also includes customizing different user interfaces based on user habits and needs. For example, desktop, mobile, or web-based interfaces can be provided so that managers can easily view and manage energy supply in different scenarios.

[0108] Figure 2 This is a schematic diagram of a dynamic monitoring and management system applied to a smart port, as shown in some embodiments of this specification. Figure 2 As shown, a dynamic monitoring and management system for smart ports may include a BIM modeling module, a supply monitoring module, a supply analysis module, and a problem visualization module.

[0109] The BIM modeling module is used to obtain the modeling information of the wharf and to build the BIM model of the wharf based on the modeling information. The supply monitoring module is used to identify multiple energy monitoring points based on the BIM model of the wharf and acquire real-time energy supply monitoring data collected by multiple energy monitoring sensors. The supply analysis module is used to predict energy supply problems based on real-time energy supply monitoring data collected by multiple energy monitoring sensors. The problem visualization module is used to visualize energy supply issues on the BIM model of the dock.

[0110] A dynamic detection and management system for smart ports can be used to execute a dynamic detection and management method for smart ports, which will not be elaborated here.

[0111] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A dynamic detection and management method applied to smart ports, characterized in that, include: Obtain the modeling information for the dock; Based on the modeling information of the wharf, a BIM model of the wharf is established; Based on the BIM model of the wharf, multiple energy monitoring points were identified; Multiple energy monitoring sensors are installed based on multiple energy monitoring points; Acquire real-time energy supply monitoring data collected by multiple energy monitoring sensors; Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, predict energy supply problems; Visualize energy supply issues on the BIM model of the dock.

2. The dynamic detection and management method for smart ports according to claim 1, characterized in that, The modeling information for the wharf includes the building structure, equipment layout, and energy supply pipeline routing.

3. The dynamic detection and management method for smart ports according to claim 1, characterized in that, Visualize energy supply issues on the BIM model of the wharf, including: Based on the predicted energy supply problems, identify the locations of energy supply anomalies; Mark the locations of abnormal energy supply on the BIM model of the dock and display early warning information.

4. The dynamic detection and management method for smart ports according to claim 1, characterized in that, Also includes: Receive user operation instructions, wherein the operation instructions include at least zoom, rotate, pan, and partial viewing; The visual interface is adjusted based on the user's operation commands.

5. A dynamic detection and management method for smart ports according to any one of claims 1-4, characterized in that, Based on the BIM model of the wharf, multiple energy monitoring points were identified, including: Based on the BIM model of the wharf, the water supply topology, electricity supply topology and oil supply topology are obtained. Obtain historical energy consumption data for multiple pieces of equipment at the dock; Based on the historical energy consumption data of water supply topology, electricity supply topology, oil supply topology, and multiple equipment at the wharf, multiple energy monitoring points were identified.

6. The dynamic detection and management method for smart ports according to claim 5, characterized in that, Based on the water supply topology, electricity supply topology, oil supply topology, and historical energy consumption data of multiple equipment at the wharf, several energy monitoring points were identified, including: Based on the water supply topology, electricity supply topology, and oil supply topology, calculate the energy supply centrality of each device; Based on historical energy consumption data from multiple devices, calculate the correlation of energy consumption for each device. Based on the energy supply centrality and energy consumption correlation of each device, multiple energy monitoring points are identified.

7. The dynamic detection and management method for smart ports according to claim 6, characterized in that, Based on historical energy consumption data from multiple devices, the correlation of energy consumption for each device is calculated, including: For any two devices, calculate the correlation coefficient of energy consumption between the two devices based on their historical energy consumption data; For each device, based on the energy consumption correlation coefficient between any two devices, determine the energy consumption related devices of the device, and calculate the energy consumption correlation degree of the device based on the energy consumption related devices of the device.

8. The dynamic detection and management method for smart ports according to claim 7, characterized in that, Based on real-time energy supply monitoring data collected from multiple energy monitoring sensors, predict energy supply issues, including: Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, the real-time energy consumption data of multiple devices are determined. Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, predict the expected energy consumption data of multiple devices; Based on real-time energy consumption data and expected energy consumption data from multiple devices, predict energy supply issues.

9. A dynamic detection and management method for smart ports according to claim 8, characterized in that, Based on real-time energy supply monitoring data collected by multiple energy monitoring sensors, the expected energy consumption data of multiple devices is predicted, including: For each energy monitoring sensor, variational mode decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the intrinsic mode function and residual of the energy monitoring sensor. Local mean decomposition is performed on the real-time energy supply monitoring data acquired by the energy monitoring sensor at multiple consecutive time points to obtain the single-component modulation function and residual component of the energy monitoring sensor. Based on the correlation coefficient of energy consumption between any two devices and the intrinsic mode function and residual of each energy monitoring sensor, as well as the single-component modulation function and residual component, the energy consumption prediction model predicts the expected energy consumption data of multiple devices.

10. A dynamic monitoring and management system applied to smart ports, characterized in that, The dynamic detection and management method for smart ports according to claim 1 includes: The BIM modeling module is used to obtain the modeling information of the wharf and to build the BIM model of the wharf based on the modeling information. The supply monitoring module is used to identify multiple energy monitoring points based on the BIM model of the wharf and acquire real-time energy supply monitoring data collected by multiple energy monitoring sensors. The supply analysis module is used to predict energy supply problems based on real-time energy supply monitoring data collected by multiple energy monitoring sensors. The problem visualization module is used to visualize energy supply issues on the BIM model of the dock.

Images