A port operation optimization method based on the integration of big data and aerial rail transit technology

Abstract

The present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology, belonging to the field of intelligent ports, including: obtaining port geographical data, setting up a four-layer intelligent system, and collecting basic data based on the four-layer intelligent system; performing multi-modal data fusion processing on the basic data to obtain multi-modal fusion data, performing big data analysis based on the multi-modal fusion data, and constructing an intelligent decision-making model according to the big data analysis results; guiding the dynamic scheduling of the aerial rail transportation system based on the output of the intelligent decision-making model, and executing the dynamic scheduling, evaluating the execution results according to the real-time basic information obtained from the four-layer intelligent system, and then optimizing the port operation links according to the evaluation results; designing a continuous learning mechanism based on the optimization results to comprehensively optimize the intelligent decision-making system and the port transportation links. Enhance the competitiveness of the port and improve the level of data security and autonomy and controllability.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent ports, and particularly to a method for optimizing port operations based on the integration of big data and aerial rail transportation technology. Background Art

[0002] With the rapid growth of global trade, the importance of ports as logistics hubs has become increasingly prominent. The traditional port operation model faces bottlenecks in terms of efficiency, safety, and energy efficiency, and there is an urgent need to improve the operation level through intelligent technologies. Moreover, in the current construction of port intelligence, the awareness of data security and the autonomy and controllability of core technologies need to be improved.

[0003] Therefore, the present invention provides a method for optimizing port operations based on the integration of big data and aerial rail transportation technology. Summary of the Invention

[0004] A method for optimizing port operations based on the integration of big data and aerial rail transportation technology provided by the present invention senses the port operation status through a four-layer intelligent system, collects multi-modal data (such as video, sensor data, etc.), conducts fusion analysis, constructs an intelligent decision-making model, dynamically schedules the aerial rail transportation system, and drives the system to continuously learn based on the evaluation results, so as to optimize port operations, improve efficiency, safety, and energy efficiency, ultimately realize intelligent port operations, enhance the autonomy and controllability of core technologies, ensure data security, improve port operation efficiency, safety, and energy efficiency, enhance port competitiveness, and improve the level of data security and autonomy and controllability.

[0005] The present invention provides a method for optimizing port operations based on the integration of big data and aerial rail transportation technology, including:

[0006] Step 1: Obtain port geographical data, set up a four-layer intelligent system, and collect basic data based on the four-layer intelligent system;

[0007] Step 2: Perform multi-modal data fusion processing on the basic data to obtain multi-modal fusion data, conduct big data analysis based on the multi-modal fusion data, and construct an intelligent decision-making model according to the big data analysis results;

[0008] Step 3: Guide the dynamic scheduling of the aerial rail transportation system based on the output of the intelligent decision-making model, execute the dynamic scheduling, evaluate the execution results according to the real-time basic information obtained by the four-layer intelligent system, and then optimize the port operation links according to the evaluation results;

[0009] Step 4: Design a continuous learning mechanism based on the optimization results to comprehensively optimize the intelligent decision-making system and the port transportation link.

[0010] The present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology, which acquires port geographical data, sets up a four-layer intelligent system, and collects basic data based on the four-layer intelligent system, including:

[0011] Acquire port geographical data, deploy an aerial rail transportation system based on the port geographical data, capture port operation scenarios, install ground Internet of Things sensors and ship Beidou positioning terminals, collect port operation data, and synthesize the port operation scenarios and port operation data to obtain the perception layer;

[0012] Build a dedicated network, deploy edge computing nodes according to the port geographical data, and establish a data transmission channel to obtain the transmission layer;

[0013] Deploy a logistics optimization engine, a safety warning engine, and an energy efficiency management engine to obtain the decision-making layer;

[0014] Provide a visual command platform, a mobile terminal app, and an API open interface to view the port operation situation to obtain the application layer;

[0015] Synthesize the perception layer, the transmission layer, the decision-making layer, and the application layer, set up a four-layer intelligent system, and collect basic data.

[0016] The present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology, which performs multi-modal data fusion processing on the basic data to obtain multi-modal fusion data, and performs big data analysis based on the multi-modal fusion data. According to the big data analysis results, an intelligent decision-making model is constructed, including:

[0017] Attach a unified time stamp to all basic data and perform spatial registration based on the coordinate system of the port digital twin;

[0018] And perform standardization processing on the basic data based on the spatial registration, and extract visual features, sensor features, and operation features based on the standardization processing results;

[0019] Perform multi-modal data fusion processing on the visual features, sensor features, and operation features to obtain multi-modal fusion data;

[0020] Based on the multi-modal fusion data, use big data analysis technology to perform logistics optimization analysis, safety warning analysis, and energy efficiency management analysis, and synthesize the logistics optimization analysis results, safety warning analysis results, and energy efficiency management analysis results with the four-layer intelligent system to construct an intelligent decision-making model.

[0021] The present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology. Based on multi-modal fusion data, big data analysis technology is used for logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. An intelligent decision-making model is constructed by integrating the results of logistics optimization analysis, safety warning analysis, and energy efficiency management analysis with a four-layer intelligent system, including:

[0022] Construct a logistics optimization engine objective function according to the logistics optimization analysis results:

[0023] , where W represents the logistics optimization engine objective function; represents the weight coefficient of the ship waiting time; represents the waiting time of the ship at time tt; represents the utilization rate of port resources at time t; represents the weight coefficient of resource utilization rate; represents the maximum available capacity of port resources; T represents the overall time range for objective function calculation;

[0024] , where A represents the safety warning engine objective function; represents the weight coefficient of anomaly detection accuracy; represents the number of anomalies correctly detected by the model; represents the number of normal situations correctly detected by the object detection model in the safety warning engine; represents the number of anomalies misdetected by the object detection model in the safety warning engine; represents the number of anomalies not detected by the object detection model in the safety warning engine; represents the weight coefficient of false alarm rate.

[0025] The present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology. Based on multi-modal fusion data, big data analysis technology is used for logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. An intelligent decision-making model is constructed by integrating the results of logistics optimization analysis, safety warning analysis, and energy efficiency management analysis with a four-layer intelligent system, further including:

[0026] , where N represents the energy efficiency management engine objective function; represents the weight coefficient of energy consumption cost; represents the energy consumption cost of the port at time t; represents the energy utilization efficiency of the port at time t; represents the weight coefficient of energy utilization efficiency; represents the theoretical maximum value of port energy utilization;

[0027] Construct an intelligent decision-making model by integrating the objective functions of the logistics optimization engine, the safety warning engine, and the energy efficiency management engine.

[0028] The present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology. Guide the dynamic scheduling of the sky-rail transportation system based on the output of the intelligent decision-making model, execute the dynamic scheduling, evaluate the execution results according to the real-time basic information obtained from the four-layer intelligent system, and then optimize the port operation links according to the evaluation results, including:

[0029] Determine the corresponding scheduling situation according to the output of each engine in the intelligent decision-making model, and obtain the dynamic scheduling of the sky-rail transportation system by integrating all the scheduling situations;

[0030] Execute the dynamic scheduling, collect real-time basic information, evaluate the execution results, identify the execution problems in the evaluation results, and optimize the port operation links based on the execution problems.

[0031] The present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology. Determine the corresponding scheduling situation according to the output of each engine in the intelligent decision-making model, and obtain the dynamic scheduling of the sky-rail transportation system by integrating all the scheduling situations, including:

[0032] According to the output of the logistics optimization engine, the collaborative scheduling strategy of berth - quay crane - yard truck is obtained, the output of the safety warning engine is the abnormal behavior detection result and warning information, and the output of the energy efficiency management engine is the energy consumption hot spot prediction and energy optimization suggestions;

[0033] Dynamically adjust the sky-rail transportation path and transportation strategy according to the collaborative scheduling strategy, determine the abnormal area and adjust the transportation priority according to the abnormal behavior detection result and warning information, and optimize the energy consumption allocation of the transportation task according to the energy consumption hot spot prediction and energy optimization suggestions, so as to obtain the dynamic scheduling of the sky-rail transportation system.

[0034] The present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology. Design a continuous learning mechanism based on the optimization results to comprehensively optimize the intelligent decision-making system and the port transportation link, including:

[0035] Collect the evaluation of the optimization results by operation and maintenance personnel based on the application layer in the four-layer intelligent system, and design a continuous learning mechanism according to the evaluation;

[0036] Update the intelligent decision-making system according to the continuous learning mechanism, and comprehensively optimize the port transportation link based on the updated intelligent decision-making model.

[0037] Compared with the prior art, the beneficial effects of the present application are as follows: By means of a four-layer intelligent system to perceive the port operation status, collect multi-modal data (such as video, sensor data, etc.), conduct fusion analysis, construct an intelligent decision-making model, dynamically schedule the sky-rail transportation system, and drive the system to continuously learn based on the evaluation results, optimize port operations, improve efficiency, safety and energy efficiency, ultimately realize intelligent port operation, enhance the independent controllability of core technologies, ensure data security, improve port operation efficiency, safety and energy efficiency, enhance port competitiveness, and improve the level of data security and independent controllability.

[0038] Other features and advantages of the present invention will be described in the following specification, and part of them will be obvious from the specification or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0039] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0041] Figure 1 is a schematic flowchart of a port operation optimization method based on the integration of big data and sky-rail transportation technology provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0043] Embodiment 1:

[0044] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology, as Figure 1 shown, including:

[0045] Step 1: Obtain port geographical data, set up a four-layer intelligent system, and collect basic data based on the four-layer intelligent system;

[0046] Step 2: Perform multi-modal data fusion processing on the basic data to obtain multi-modal fusion data, conduct big data analysis based on the multi-modal fusion data, and construct an intelligent decision-making model according to the big data analysis results;

[0047] Step 3: guiding the dynamic scheduling of the air-rail transportation system based on the output of the intelligent decision-making model, and executing the dynamic scheduling, evaluating the execution results according to the real-time basic information obtained by the four-layer intelligent system, and then optimizing the port operation links according to the evaluation results;

[0048] Step 4: Design a continuous learning mechanism based on the optimization results to comprehensively optimize the intelligent decision-making system and port transportation links.

[0049] In this embodiment, the port geographic data is data describing the physical spatial characteristics of the port, including port area maps, shoreline coordinates, water depth data, berth locations and sizes, road network maps, building distribution maps, etc.

[0050] In this embodiment, the four-layer intelligent system includes a perception layer, a transmission layer, a decision layer, and an application layer.

[0051] In this embodiment, the basic data includes visual data, sensor data and operational data. Visual data: deploy low-altitude drone clusters and fixed cameras, collect 4K resolution video streams (30fps), and mark the bounding boxes and behavior labels of key targets (containers, vehicles, and personnel); sensor data: install IoT devices such as temperature and humidity, vibration, and GPS, collect device status and environmental parameters at a frequency of 1Hz, and mark abnormal events (such as equipment overload and leakage); operational data: connect to the port management system, obtain structured data (ship ETA, cargo list, operation plan), and build a spatiotemporal index table.

[0052] In this embodiment, multimodal data fusion processing is the process of integrating multiple types of data together, for example, using a deep learning model to fuse visual features, sensor features, and operational features.

[0053] In this embodiment, the specific process of big data analysis is to use the big data processing platform to perform real-time analysis on the pre-processed data. Data mining, machine learning and other algorithms are used to mine the potential value in the data and provide decision support for port operations. For example, the coordinated scheduling of berths, air rails and container trucks is realized through the logistics optimization engine to improve logistics efficiency; abnormal behavior detection is realized through the safety warning engine to warn potential safety hazards in advance; energy consumption hotspots are predicted through the energy efficiency management engine to optimize energy use.

[0054] In this embodiment, the input of the intelligent decision-making model is multimodal fusion data, and the output is logistics optimization strategy, safety warning information, energy efficiency management suggestions, and the final air-rail transportation scheduling plan. These outputs will be fed back to the four-layer intelligent system to guide port operations.

[0055] In this embodiment, dynamic scheduling is a scheduling scheme adjusted according to real-time situations rather than a pre-set static scheme, including the scheduling of the logistics optimization engine, the scheduling of the safety warning engine, and the scheduling of the energy efficiency management engine. For example, since the 'Ocean' ship arrived earlier, the system automatically adjusted the operation plans of the yard trucks and quay cranes and started unloading in advance to avoid delaying the subsequent berthing of ships, which is a real-time response to emergencies.

[0056] In this embodiment, real-time basic information is data collected in real time during the operation of the system, including the operation efficiency of quay cranes, the positions and speeds of yard trucks, the number of containers in the yard, weather conditions, energy consumption data of various equipment, etc.

[0057] In this embodiment, the execution result evaluation is an evaluation of the execution effect of dynamic scheduling, and the measurement indicators include: ship turnover time, container storage time, average driving mileage of yard trucks, energy consumption, safety accident incidence rate, etc. The system will compare the actual data with the expected goals.

[0058] In this embodiment, optimization is an improvement to the port operation links based on execution problems. For example, optimizing algorithm parameters, adjusting scheduling strategies (such as increasing the number of yard trucks or adjusting routes), improving equipment maintenance processes, strengthening safety training, or adjusting the port area layout to improve efficiency and reduce congestion.

[0059] In this embodiment, based on the output results of the three engines, the scheduling of the aerial rail transit system is coordinated. The logistics optimization engine determines the collaborative scheduling strategies of berths, quay cranes, and yard trucks; the safety warning engine identifies anomalies and adjusts the transportation priorities; the energy efficiency management engine optimizes the energy consumption allocation, integrates the outputs of the three, and forms dynamic scheduling.

[0060] In this embodiment, the setting process of the continuous learning mechanism is to design a feedback loop: taking the warning results confirmed by the operation and maintenance personnel as new labeled data and transmitting them back, using the elastic weight consolidation method to retain important parameters when updating the model to prevent catastrophic forgetting.

[0061] In this embodiment, comprehensive optimization is to use the updated intelligent decision-making model to comprehensively optimize the port transportation link, redeploy, deploy the updated intelligent decision-making model into the system, continuously monitor the operation of the system, collect new data for further optimizing the model, and repeat the process of evaluation, update, and optimization in a cycle to continuously improve the performance of the system. After deploying the updated model, the system will re-plan the AGV route and make dynamic adjustments according to real-time situations, striving to achieve the best balance among efficiency, safety, and energy conservation.

[0062] The working principle and beneficial effects of the above technical solution are as follows: By means of a four-layer intelligent system, the operating status of the port is sensed, multi-modal data (such as video, sensor data, etc.) is collected, fused and analyzed, an intelligent decision-making model is constructed, the aerial rail transportation system is dynamically scheduled, and the evaluation results drive the system to continuously learn, optimize port operations, improve efficiency, safety and energy efficiency. Ultimately, the intelligent operation of the port is realized, the independent controllability of core technologies is enhanced, data security is guaranteed, the operation efficiency, safety and energy efficiency of the port are improved, the competitiveness of the port is enhanced, and the levels of data security and independent controllability are improved.

[0063] Embodiment 2:

[0064] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology. Port geographical data is obtained, a four-layer intelligent system is set up, and basic data is collected based on the four-layer intelligent system, including:

[0065] Port geographical data is obtained, an aerial rail transportation system is deployed based on the port geographical data, the port operation scenario is captured, ground Internet of Things sensors and ship Beidou positioning terminals are installed, port operation data is collected, and the perception layer is obtained by integrating the port operation scenario and the port operation data;

[0066] A dedicated network is built, edge computing nodes are deployed according to the port geographical data, and a data transmission channel is established to obtain the transmission layer;

[0067] A logistics optimization engine, a safety warning engine and an energy efficiency management engine are deployed to obtain the decision-making layer;

[0068] A visualization command platform, a mobile terminal app and an api open interface are provided to view the port operation situation to obtain the application layer;

[0069] By integrating the perception layer, the transmission layer, the decision-making layer and the application layer, a four-layer intelligent system is set up to collect basic data.

[0070] In this embodiment, the perception layer consists of an aerial rail transportation system (equipped with high-definition cameras / LiDAR), ground Internet of Things sensors (pressure / temperature / humidity / vibration), and ship Beidou positioning terminals; the transmission layer uses a 5G private network + edge computing nodes to establish three major data transmission channels: a high-bandwidth channel for transmitting 4K video streams (50 Mbps / channel), a low-latency channel for transmitting control instructions (end-to-end latency < 10 ms), and a high-reliability channel for transmitting critical status data (99.999% availability); the decision-making layer deploys three core engines, namely, a logistics optimization engine for collaborative scheduling of berths, quay cranes, and yard trucks based on an improved genetic algorithm, a safety warning engine for abnormal behavior detection using the YOLOv7 + Transformer model, and an energy efficiency management engine for predicting energy consumption hotspots through digital twin simulation; the application layer provides a visual command platform, a mobile terminal APP, and API open interfaces.

[0071] In this embodiment, the aerial rail transportation system is an automated and highly efficient internal port transportation system that usually uses tracks for cargo transportation, including AGV (Automated Guided Vehicle) systems, gantry crane systems, light rail transportation systems, etc.

[0072] In this embodiment, the port operation scenario is a video or image record of various operation activities occurring within the port, including video surveillance footage of container loading and unloading processes, vehicle driving conditions, personnel activities, and equipment operating status.

[0073] In this embodiment, the ground Internet of Things sensors are sensors deployed on the ground for collecting various environmental and operation data, including temperature sensors, humidity sensors, pressure sensors, weight sensors, video surveillance cameras, etc.

[0074] In this embodiment, the ship Beidou positioning terminal is a device installed on the ship for real-time positioning and data transmission, including a Beidou navigation receiver with data transmission capabilities.

[0075] In this embodiment, the port operation data are various data recording the port operation status, including container throughput, ship arrival and departure times, equipment utilization rate, energy consumption data, personnel work efficiency, etc.

[0076] In this embodiment, the exclusive network is a network specially built for the port intelligent system for data transmission and communication, including 5G-based private networks, private cloud networks, etc. The edge computing nodes are computing devices deployed close to the data source for real-time data processing and analysis, including edge servers, edge gateways, etc. The data transmission channel is the path for data transmission between various devices and nodes, including network lines, wireless communication links, etc.

[0077] In this embodiment, the logistics optimization engine, the safety warning engine, and the energy efficiency management engine are software modules for performing specific tasks. The logistics optimization engine may use algorithms to optimize the loading, unloading, and transportation sequence of containers; the safety warning engine may use machine learning algorithms to detect abnormal behaviors; and the energy efficiency management engine may optimize the port energy consumption through prediction and control.

[0078] In this embodiment, the visual command platform, the mobile terminal app, and the API open interface are tools for human-computer interaction. The visual command platform may display the real-time operation status of the port; the mobile terminal app may provide mobile monitoring and management functions; and the API open interface may allow third-party systems to access port data.

[0079] In this embodiment, the port operation situation is the overall operation condition of the port, which is a comprehensive reflection of indicators such as throughput, efficiency, safety, and energy consumption.

[0080] The working principle and beneficial effects of the above technical solution are as follows: By constructing a perception layer (sensors, video monitoring), a transmission layer (private network, edge computing), a decision layer (optimization engine), and an application layer (visualization platform), a four-layer intelligent system is formed. Using the port geographical data to deploy the aerial rail system and collect multi-source data, and performing real-time analysis to achieve logistics optimization, safety warning, and energy efficiency management. Finally, through the application layer, a visual and convenient interface is provided to improve the port operation efficiency and safety.

[0081] Embodiment 3:

[0082] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology. The basic data is subjected to multi-modal data fusion processing to obtain multi-modal fusion data. Based on the multi-modal fusion data, big data analysis is performed, and an intelligent decision-making model is constructed according to the big data analysis results, including:

[0083] Attach a unified timestamp to all basic data and perform spatial registration based on the coordinate system of the port digital twin;

[0084] And perform standardization processing on the basic data based on the spatial registration, and extract visual features, sensor features, and operation features based on the standardization processing results;

[0085] Perform multi-modal data fusion processing on the visual features, sensor features, and operation features to obtain multi-modal fusion data;

[0086] Based on the multi-modal fusion data, use big data analysis technology to perform logistics optimization analysis, safety warning analysis, and energy efficiency management analysis, and construct an intelligent decision-making model by integrating the logistics optimization analysis results, safety warning analysis results, and energy efficiency management analysis results with the four-layer intelligent system.

[0087] In this embodiment, the port digital twin is a virtual and digital port model corresponding to the real port environment, which can reflect the operating status of the port in real time. For example, it is a 3D model containing digital representations of all buildings, equipment, roads, etc. in the port area, and can display information such as ship positions, container status, and equipment operating conditions in real time.

[0088] In this embodiment, spatial registration is to align data from different data sources according to a unified coordinate system so that they have a corresponding relationship in space. For example, to match the target positions in the video surveillance images with sensor data (such as GPS coordinates), or to unify the data collected by different sensors (such as temperature sensor data from different locations) under the coordinate system of the port digital twin.

[0089] In this embodiment, standardization processing is to preprocess the data to make it conform to a unified standard and format for convenient subsequent analysis and processing, including data cleaning, data normalization, data conversion, etc. For visual data: downsampling to a resolution of 1024×576 and performing histogram equalization enhancement; for sensor data: continuous parameters (such as temperature) using Z-score normalization, and discrete parameters (such as equipment ID) constructing an embedding lookup table; for operation data: categorical fields (such as cargo type) performing one-hot encoding, and numerical fields (such as tonnage) normalizing to [0,1].

[0090] In this embodiment, visual features are features extracted from video surveillance images, including the shape, color, motion trajectory, etc. of the target object; sensor features are features extracted from sensor data, including temperature, humidity, pressure, weight, etc.; operation features are features extracted from operation data, including container throughput, ship waiting time, equipment utilization rate, etc.

[0091] In this embodiment, multi-modal fusion data is to fuse data of different modalities (such as visual, sensor, operation) to obtain a more comprehensive and rich description. For example, combining the motion trajectory of the container in the video image, the weight of the container collected by the sensor, and information such as the loading and unloading time in the operation data to obtain a comprehensive description of the container loading and unloading process.

[0092] In this embodiment, the result of logistics optimization analysis is the best container loading, unloading and transportation plan, the result of safety warning analysis is the warning information of potential safety hazards and abnormal events, and the result of energy efficiency management analysis is the prediction and optimization suggestions for port energy consumption.

[0093] The working principle and beneficial effects of the above technical solution are as follows: By adding timestamps and spatial coordinates to the basic data, data standardization processing is achieved, and visual, sensor, and operation features are extracted. The multi-modal data fusion technology integrates these features, and then the big data analysis technology is used for logistics optimization, safety warning, and energy efficiency management analysis. Finally, combined with the four-layer intelligent system, an intelligent decision-making model is constructed to realize the intelligent management of port operations, optimize port logistics, and improve safety and energy efficiency.

[0094] Embodiment 4:

[0095] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and aerial rail transportation technology. Based on multi-modal fusion data, the big data analysis technology is used for logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. The intelligent decision-making model is constructed by integrating the logistics optimization analysis result, safety warning analysis result, and energy efficiency management analysis result with the four-layer intelligent system, including:

[0096] Construct the objective function of the logistics optimization engine according to the logistics optimization analysis result:

[0097] , where W represents the objective function of the logistics optimization engine; represents the weight coefficient of the ship waiting time; represents the waiting time of the ship at time tt; represents the utilization rate of port resources at time t; represents the weight coefficient of resource utilization rate; represents the maximum available capacity of port resources; T represents the overall time range for objective function calculation;

[0098] , where A represents the objective function of the safety warning engine; represents the weight coefficient of the anomaly detection accuracy; represents the number of anomalies correctly detected by the model; represents the number of normal situations correctly detected by the target detection model in the safety warning engine; represents the number of anomalies wrongly detected by the target detection model in the safety warning engine; represents the number of anomalies not detected by the target detection model in the safety warning engine; represents the weight coefficient of the false alarm rate.

[0099] The working principle and beneficial effects of the above technical solution are as follows: By constructing the objective functions of the logistics optimization and safety warning engines, the optimization objectives are quantified. The logistics optimization objective function minimizes the ship waiting time and maximizes the resource utilization rate, and the safety warning objective function maximizes the abnormal detection accuracy and minimizes the false alarm rate. By optimizing these two objective functions, the system can automatically adjust parameters to improve the efficiency and safety of port operations, increase the port throughput, reduce the ship waiting time, and improve the resource utilization rate.

[0100] Embodiment 5:

[0101] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology. Based on multi-modal fusion data, big data analysis technology is used for logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. An intelligent decision-making model is constructed by integrating the results of logistics optimization analysis, safety warning analysis, and energy efficiency management analysis with a four-layer intelligent system. It also includes:

[0102] , where N represents the objective function of the energy efficiency management engine; represents the weight coefficient of the energy consumption cost; represents the energy consumption cost of the port at time t; represents the energy utilization efficiency of the port at time t; represents the weight coefficient of the energy utilization efficiency; represents the theoretical maximum value of the port energy utilization;

[0103] An intelligent decision-making model is constructed by integrating the objective function of the logistics optimization engine, the objective function of the safety warning engine, and the objective function of the energy efficiency management engine.

[0104] The working principle and beneficial effects of the above technical solution are as follows: By constructing the objective functions of the three engines of logistics optimization, safety warning, and energy efficiency management, the efficiency, safety, and energy consumption of port operations are quantitatively evaluated respectively. The three objective functions are integrated to construct an intelligent decision-making model to achieve multi-objective optimization and reduce the energy consumption cost on the premise of ensuring safety and efficiency.

[0105] Embodiment 6:

[0106] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and sky-rail transportation technology. The dynamic scheduling of the sky-rail transportation system is guided by the output of the intelligent decision-making model, and the dynamic scheduling is executed. According to the real-time basic information obtained from the four-layer intelligent system, the execution result is evaluated, and then the port operation links are optimized according to the evaluation result, including:

[0107] Determine the corresponding scheduling situation according to the output of each engine in the intelligent decision-making model, and synthesize all the scheduling situations to obtain the dynamic scheduling of the aerial rail transit system;

[0108] Execute the dynamic scheduling, collect real-time basic information, evaluate the execution results, identify the execution problems in the evaluation results, and optimize the port operation links based on the execution problems.

[0109] In this embodiment, the scheduling situation is the specific scheduling instructions or suggestions output by each engine, including the scheduling situation of the logistics optimization engine, the safety warning engine, and the energy efficiency management engine. For example, the logistics optimization engine gives priority to arranging 100 out of 200 containers of the 'Ocean Ship' to berth 3, 50 to berth 4, and the remaining 50 to berth 5; at the same time, arrange 10 container trucks to give priority to handling the containers at berth 3, including specific allocation, priority, and sequence. The safety warning engine discovers that there is illegal operation of vehicles near yard 8, and suggests temporarily stopping the handling of containers in this area and dispatching security personnel for handling. The energy efficiency management engine predicts the electricity peak from 2 pm to 4 pm and suggests reducing the operation of empty container trucks and giving priority to arranging container trucks with sufficient battery power for operation, including suggestions on energy management.

[0110] In this embodiment, the execution problem is the problem existing in the scheduling execution discovered during the evaluation process, such as the excessive waiting time of container trucks, the excessive stacking of containers in a certain yard, the energy consumption exceeding the expectation, and a minor collision accident occurring.

[0111] The working principle and beneficial effects of the above technical solution are: The output results of the intelligent decision-making model (including the logistics optimization, safety warning, and energy efficiency management engines) are used to formulate the dynamic scheduling plan of the aerial rail transit system. After the system executes the scheduling, real-time data is collected for evaluation, execution problems are identified, and the port operation links are optimized to form a closed-loop control, realizing the refined management of the aerial rail transit system and improving the scheduling efficiency.

[0112] Embodiment 7:

[0113] The embodiment of the present invention provides a port operation optimization method based on the integration of big data and aerial rail transit technology. Determine the corresponding scheduling situation according to the output of each engine in the intelligent decision-making model, and synthesize all the scheduling situations to obtain the dynamic scheduling of the aerial rail transit system, including:

[0114] According to the logistics optimization engine, output the collaborative scheduling strategy of berth - quay crane - container truck, the safety warning engine outputs the abnormal behavior detection result and warning information, and the energy efficiency management engine outputs the energy consumption hot spot prediction and energy optimization suggestions;

[0115] Dynamically adjust the air rail transportation route and transportation strategy according to the collaborative scheduling strategy, determine the abnormal area and adjust the transportation priority according to the abnormal behavior detection result and early warning information, optimize the energy consumption allocation of the transportation task according to the energy consumption hot spot prediction and energy optimization suggestions, and then obtain the dynamic scheduling of the air rail transportation system.

[0116] In this embodiment, the berth - quay crane - yard truck collaborative scheduling strategy is an overall strategy aimed at optimizing the collaborative work of three key links: berth, quay crane (container crane), and yard truck. For example, assume a large cargo ship is docked at Berth 1. The collaborative scheduling strategy will consider the following factors: berth allocation, allocating Berth 1 to this ship; quay crane allocation, according to the loading and unloading plan of the ship, allocating a suitable quay crane (for example, a quay crane that can handle containers of different sizes) to Berth 1; yard truck scheduling: planning the routes of yard trucks to ensure that yard trucks can transport containers to the yard or other destinations in a timely manner and avoid conflicts or congestion among yard trucks, including optimizing the routes of yard trucks and arranging the waiting order of yard trucks.

[0117] In this embodiment, the abnormal behavior detection result and early warning information are the abnormal situations detected by the safety early warning engine and their corresponding early warning information. For example, abnormal behaviors include yard truck speeding, yard truck driving in a restricted area, abnormal quay crane operation, container dumping in the yard, etc. The early warning information is that the system will issue an alarm indicating the location, severity, and possible risks of the abnormal behavior. For example: The vehicle with yard truck license plate number ABC - 1234 is speeding in the yard. Please pay attention to safety! Or: Quay crane No. 5 has abnormal vibration. It is recommended to suspend operation and conduct an inspection.

[0118] In this embodiment, the energy consumption hot spot prediction and energy optimization suggestions are the predictions and optimization suggestions of the energy efficiency management engine for the energy consumption situation. For example, energy consumption hot spot prediction: It is predicted that from 3 pm to 5 pm, due to a large number of container loading and unloading operations, the power load will reach its peak. Energy optimization suggestions: It is recommended to give priority to arranging electric - driven yard truck operations during this period, reduce the use of diesel yard trucks; and adjust the operation plan of quay cranes to stagger the electricity consumption.

[0119] In this embodiment, adjusting the air rail transportation route and transportation strategy is to adjust the route and strategy of the air rail transportation system (such as AGV) according to the above - mentioned information. For example, if the safety early warning engine detects a safety hazard in a certain area, the system will automatically adjust the route of the AGV to avoid this area.

[0120] In this embodiment, the abnormal area and adjusted transportation priority are to determine the areas and tasks that need to be processed first according to the abnormal behavior detection result. For example, if it is found that a certain yard is congested, the system will give priority to arranging yard trucks to transport the containers in this yard to relieve the congestion.

[0121] In this embodiment, the energy consumption allocation for optimizing transportation tasks is to adjust the energy allocation according to the energy consumption hot spot prediction and energy optimization suggestions. For example, during peak electricity consumption periods, the system will preferentially use AGVs driven by electricity to reduce energy consumption; or select shorter transportation routes to reduce energy consumption.

[0122] The working principle and beneficial effects of the above technical solution are as follows: Based on the output results of the three engines, the operation of the aerial rail transit system is coordinated and scheduled. The logistics optimization engine determines the collaborative scheduling strategies for berths, quay cranes, and yard trucks; the safety warning engine identifies anomalies and adjusts the transportation priorities; the energy efficiency management engine optimizes the energy consumption allocation. By integrating the outputs of the three engines, a dynamic aerial rail transit scheduling plan is formed, which improves the efficiency of aerial rail transit, reduces energy consumption, and enhances safety.

[0123] Embodiment 8:

[0124] An embodiment of the present invention provides a port operation optimization method based on the integration of big data and aerial rail transit technology. Based on the optimization results, a continuous learning mechanism is designed to comprehensively optimize the intelligent decision-making system and the port transportation links, including:

[0125] Collect the evaluations of operation and maintenance personnel on the optimization results from the application layer of the four-layer intelligent system, and design a continuous learning mechanism according to the evaluations;

[0126] Update the intelligent decision-making system according to the continuous learning mechanism, and comprehensively optimize the port transportation links based on the updated intelligent decision-making model.

[0127] In this embodiment, the evaluation of the optimization results is a key step in obtaining feedback from operation and maintenance personnel from the application layer. This process is not simply asking whether it is good or bad, but requires a structured feedback mechanism. For example: data collection methods, multiple methods can be used to collect evaluations, such as questionnaires. Design standardized questionnaires to evaluate the improvements in aspects such as efficiency, safety, and energy consumption of the optimization results, and allow operation and maintenance personnel to provide specific improvement suggestions. Scoring system, set up a scoring system to allow operation and maintenance personnel to score the optimization results according to different indicators, such as a 1-5 star evaluation. Feedback system, establish an online feedback system to allow operation and maintenance personnel to submit feedback opinions and suggestions at any time. Face-to-face interviews, conduct face-to-face interviews to deeply understand the views and suggestions of operation and maintenance personnel on the optimization results. Evaluation indicators, the evaluation indicators should cover all aspects of the optimization objectives, such as: Efficiency: container turnover time, ship berthing time, AGV utilization rate, etc. Through questionnaire filling, the operation and maintenance personnel are satisfied that the average container turnover time after optimization has been shortened by 15 minutes, but are not very satisfied with the optimization effect of the AGV path in some specific areas and put forward modification suggestions.

[0128] In this embodiment, the update is based on the evaluation of operation and maintenance personnel to update the intelligent decision-making system, analyze the collected evaluation data, and identify the aspects that need improvement and specific improvement directions. For example, if most operation and maintenance personnel are not satisfied with the AGV path optimization, the reasons need to be analyzed, such as unreasonable algorithm parameter settings, inaccurate data, etc. According to the data analysis results, the parameters of the intelligent decision-making model are adjusted, or the algorithm of the model is improved. This may require the participation of data scientists to improve or replace the algorithms used in the intelligent decision-making model. For example, more advanced machine learning algorithms are used to improve the prediction accuracy and decision-making ability of the model, and the training data is updated or supplemented to improve the generalization ability of the model. If it is found that there are biases in the data, these biases need to be corrected. For example, according to the feedback of operation and maintenance personnel, the parameters of the AGV path planning algorithm are adjusted, and the prediction of traffic congestion is added to improve the effect of path optimization.

[0129] The working principle and beneficial effects of the above technical solution are as follows: the output results of the three engines coordinate the scheduling of the aerial rail transit system. The logistics optimization engine determines the collaborative scheduling strategy of berths, quay cranes, and container trucks; the safety warning engine identifies anomalies and adjusts the transportation priority; the energy efficiency management engine optimizes the energy consumption allocation, integrates the outputs of the three, and forms a dynamic aerial rail transit scheduling plan to achieve intelligent and sustainable operation of the port.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A port operation optimization method based on the integration of big data and air-rail transportation technology, characterized in that: include: Step 1: Obtain port geographic data, set up a four-layer intelligent system, and collect basic data based on the four-layer intelligent system. The four-layer intelligent system includes: perception layer, transmission layer, decision layer and application layer. The decision layer includes: logistics optimization engine, safety warning engine and energy efficiency management engine; Step 2: Perform multimodal data fusion processing on the basic data to obtain multimodal fusion data, perform big data analysis based on the multimodal fusion data, and build an intelligent decision-making model according to the big data analysis results, wherein, based on the multimodal fusion data, big data analysis technology is used to perform logistics optimization analysis, safety warning analysis and energy efficiency management analysis, and the logistics optimization analysis results, safety warning analysis results and energy efficiency management analysis results are integrated with the four-layer intelligent system to build an intelligent decision-making model; Step 3: Based on the output of the intelligent decision-making model, the dynamic scheduling of the air-rail transport system is guided and executed. According to the real-time basic information obtained by the four-layer intelligent system, the execution results are evaluated, and then the port operation links are optimized according to the evaluation results, wherein the logistics optimization engine outputs the coordinated scheduling strategy of berth-quay crane-container truck, the safety warning engine outputs the abnormal behavior detection results and warning information, and the energy efficiency management engine outputs the energy consumption hotspot prediction and energy optimization suggestions; the air-rail transport path and transport strategy are dynamically adjusted according to the coordinated scheduling strategy, the abnormal area is determined and the transport priority is adjusted according to the abnormal behavior detection results and warning information, and the energy consumption distribution of the transport task is optimized according to the energy consumption hotspot prediction and energy optimization suggestions, and then the dynamic scheduling of the air-rail transport system is obtained; Step 4: Design a continuous learning mechanism based on the optimization results to comprehensively optimize the intelligent decision-making system and port transportation links.

2. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 1 is characterized in that: Obtain port geographic data, set up a four-layer intelligent system, and collect basic data based on the four-layer intelligent system, including: Obtain port geographic data, deploy an air-to-rail transportation system based on the port geographic data, capture port operation scenes, install ground IoT sensors and ship Beidou positioning terminals, collect port operation data, and integrate the port operation scenes and port operation data to derive a perception layer; Build a dedicated network, deploy edge computing nodes according to the port geographic data, establish a data transmission channel, and derive the transport layer; Deploy logistics optimization engine, safety warning engine and energy efficiency management engine to obtain the decision-making layer; Provide visual command platform, mobile terminal app and API open interface to check port operation status and obtain application layer; Combining the perception layer, transmission layer, decision-making layer and application layer, a four-layer intelligent system is set up to collect basic data.

3. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 1 is characterized in that: Performing multimodal data fusion processing on the basic data to obtain multimodal fusion data includes: Attach a unified timestamp to all basic data and perform spatial registration based on the coordinate system of the port digital twin; and performing standardization processing on the basic data based on the spatial registration, and extracting visual features, sensor features, and operation features based on the standardization processing result; Multimodal data fusion processing is performed on the visual features, sensor features, and operation features to obtain multimodal fusion data.

4. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 1 is characterized in that: Based on multimodal fusion data, big data analysis technology is used to conduct logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. The results of logistics optimization analysis, safety warning analysis, and energy efficiency management analysis are integrated with the four-layer intelligent system to build an intelligent decision-making model, including: Construct the logistics optimization engine objective function based on the logistics optimization analysis results: , where W represents the objective function of the logistics optimization engine; Indicates the weight coefficient of the ship waiting time; represents the waiting time of the ship at time tt; represents the utilization rate of port resources at time t; The weight coefficient representing resource utilization; represents the maximum available capacity of port resources; T represents the overall time range of objective function calculation; , where A represents the objective function of the security early warning engine; The weight coefficient representing the accuracy of anomaly detection; Represents the number of anomalies correctly detected by the model; Indicates the number of normal targets correctly detected by the target detection model in the security early warning engine; Indicates the number of anomalies that are incorrectly detected by the target detection model in the security early warning engine; Indicates the number of anomalies that the target detection model in the security early warning engine failed to detect; The weight coefficient representing the false alarm rate.

5. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 4 is characterized in that: Based on multimodal fusion data, big data analysis technology is used to conduct logistics optimization analysis, safety warning analysis, and energy efficiency management analysis. The results of logistics optimization analysis, safety warning analysis, and energy efficiency management analysis are integrated with the four-layer intelligent system to build an intelligent decision-making model, which also includes: , where N represents the energy efficiency management engine objective function; Represents the weight coefficient of energy consumption cost; represents the energy consumption cost of the port at time t; represents the energy efficiency of the port at time t; Represents the weight coefficient of energy utilization efficiency; It represents the theoretical maximum value of port energy utilization; The objective function of the logistics optimization engine, the objective function of the safety warning engine and the objective function of the energy efficiency management engine are integrated with the four-layer intelligent system to build an intelligent decision-making model.

6. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 1 is characterized in that: Based on the output of the intelligent decision-making model, the dynamic scheduling of the air-rail transportation system is guided and executed. According to the real-time basic information obtained by the four-layer intelligent system, the execution results are evaluated, and then the port operation links are optimized according to the evaluation results, including: Determine the corresponding scheduling situation according to the output of each engine in the intelligent decision-making model, and obtain the dynamic scheduling of the sky rail transportation system by combining all the scheduling situations; Execute the dynamic scheduling, collect real-time basic information, evaluate the execution results, identify execution problems in the evaluation results, and optimize the port operation links based on the execution problems.

7. The port operation optimization method based on the integration of big data and sky-rail transportation technology according to claim 2 is characterized in that: Based on the optimization results, a continuous learning mechanism is designed to comprehensively optimize the intelligent decision-making system and port transportation links, including: Based on the application layer in the four-layer intelligent system, the operation and maintenance personnel's evaluation of the optimization results is collected, and a continuous learning mechanism is designed based on the evaluation; The intelligent decision-making system is updated according to the continuous learning mechanism, and the port transportation links are comprehensively optimized based on the updated intelligent decision-making model.

Images