Intelligent control system for bulk cargo port full-process equipment

Abstract

The invention relates to the technical field of port intelligent control, in particular to a bulk and general cargo port full-process equipment intelligent control system which comprises an intelligent identification and monitoring subsystem, an information analysis and processing subsystem, a port planning and scheduling subsystem and a safety monitoring and early warning subsystem. Obtaining multi-dimensional dynamic monitoring information in a port operation process based on the intelligent identification and monitoring subsystem; constructing a multi-level information processing mechanism in the information analysis and processing subsystem, and processing the multi-dimensional dynamic monitoring information based on the mechanism to obtain multi-dimensional feature information in the port operation process; the port planning and scheduling subsystem sets port scheduling constraint conditions based on the multi-dimensional feature information, and formulates an operation planning scheme of the bulk and general cargos of the port according to the constraint conditions and the multi-dimensional feature information; and the safety monitoring and early warning subsystem carries out visual display and safety early warning on the operation plan scheme so as to realize intelligent monitoring and control of the whole process of the bulk and general cargo port.

Description

Technical Field

[0001] The present invention relates to the technical field of port intelligent control, and in particular to an intelligent control system for full-process equipment in a bulk cargo port. Background Art

[0002] As an important hub connecting inland and ocean, the operational efficiency, safety standards and environmental protection level of bulk cargo ports are currently the focus of attention. However, the process control model of traditional bulk cargo ports has many shortcomings, especially in data processing and utilization, logistics facilities and equipment optimization. At the data processing level, bulk cargo ports have a wide range of business and many management departments, which leads to confusion and inconsistency in the process of port data collection, storage, processing and analysis, which directly affects the effective integration and in-depth analysis of port data, and also affects the effectiveness and accuracy of intelligent control systems in decision-making. Therefore, it is difficult to achieve scientific adjustment and control of bulk cargo port processes.

[0003] In addition, for the logistics facilities and equipment in bulk cargo ports, the existing port process control mode cannot adjust the port process plan or optimize the operating conditions based on the bulk cargo situation, resulting in a mismatch between the actual port operation plan and the current equipment status, making it impossible to fully guarantee the port's safe operation standards. Therefore, the operating efficiency of bulk cargo ports is difficult to be substantially improved, and safety performance is also facing challenges. In order to respond to and solve the above challenges, it is urgent to innovate and optimize the intelligent control system of the entire process equipment of bulk cargo ports. Summary of the invention

[0004] In view of the shortcomings of existing methods and the needs of practical applications, in order to solve the problems of bulk cargo port data processing, logistics plan adjustment and operation condition optimization, multiple intelligent subsystems, information processing mechanisms and port constraints are set up to optimize the intelligent control system of the whole process equipment of the port, which will help to improve the operating efficiency of bulk cargo ports, enhance safety and optimize resource allocation. On the one hand, the present invention provides an intelligent control system for the whole process equipment of a bulk cargo port, and the above system includes: an intelligent identification and monitoring subsystem, an information analysis and processing subsystem, a port planning and scheduling subsystem, and a safety monitoring and early warning subsystem; based on the intelligent identification and monitoring subsystem, multi-dimensional dynamic monitoring information in the port operation process is obtained; a multi-level information processing mechanism is constructed in the information analysis and processing subsystem, and the multi-dimensional dynamic monitoring information is processed based on the multi-level information processing mechanism to obtain multi-dimensional feature information in the port operation process; the port planning and scheduling subsystem sets port scheduling constraints based on the multi-dimensional feature information, and formulates a port bulk cargo operation plan based on the port scheduling constraints and the multi-dimensional feature information; the safety monitoring and early warning subsystem visualizes the operation plan and provides safety warnings to realize intelligent monitoring and control of the whole process of the bulk cargo port. The present invention sets up multiple intelligent subsystems, which not only helps to continuously improve the intelligence level of bulk cargo ports, but also helps to improve the operation efficiency and management level of ports, and promote the sustainable development of bulk cargo ports.

[0005] Optionally, constructing a multi-level information processing mechanism in the information analysis and processing subsystem includes: obtaining time series information in the port operation process based on the multi-dimensional dynamic monitoring information; constructing a multi-level information processing mechanism based on the time series information, and the multi-level information processing mechanism includes a hidden information analysis model and a time-space convolutional network processing model. The multi-level information processing mechanism of the present invention can conduct a comprehensive and in-depth analysis of port operation data, which helps to improve the integrity and accuracy of port data, and thus more comprehensively understand the actual operation status and process implementation of bulk cargo ports.

[0006] Optionally, the hidden information analysis model satisfies the following relationship:

[0007] in, The hidden information representing the time series information of different virtual machines in the bulk cargo port, Indicates the fusion node information corresponding to different virtual machines. express The weight matrix of An operator representing the spatiotemporal information convolutional network model, Represents the spatial features in the time series information of different virtual machines, Represents the feature matrix corresponding to different virtual machine monitoring nodes, express The diagonal matrix of express The present invention uses a model to obtain hidden information in time series information, and further captures the spatiotemporal correlation in the time series information, so that the extracted hidden information is more comprehensive and accurate.

[0008] Optionally, the temporal-spatial convolutional network processing model satisfies the following relationship:

[0009] in, Represents the output of the temporal-spatial convolutional network processing model, represents the model activation function, represents the weight coefficient of the causal convolutional layer, represents the causal convolution kernel parameters, Indicates Time series information of virtual machines, Indicates Hidden information in the time series information of virtual machines, represents the weight coefficient of the first dilated convolutional layer, represents the dilation coefficient of the first dilated convolutional layer, represents the weight coefficient of the second dilated convolutional layer, represents the dilation coefficient of the second dilated convolutional layer, The time-space convolutional network processing model of the present invention can process and analyze time series information from different virtual machines, and promote the effective integration and sharing of port internal data.

[0010] Optionally, the multi-dimensional dynamic monitoring information is processed based on the multi-level information processing mechanism to obtain multi-dimensional feature information in the port operation process, including: using the hidden information analysis model to analyze the time series information and obtain hidden information in the time series information; the time-space convolution network processing model processes the hidden information and the time series information to obtain multi-dimensional feature information in the port operation process. The present invention analyzes the multi-dimensional feature information to achieve accurate judgment of the port operation status, which helps the port management to formulate response strategies and optimize resource allocation.

[0011] Optionally, the port planning and scheduling subsystem sets port scheduling constraints based on the multi-dimensional feature information, including: setting port scheduling constraints based on the multi-dimensional feature information and bulk cargo port operation requirements, and the port scheduling constraints include: bulk cargo location constraints, port vehicle load constraints, and port vehicle volume constraints. The present invention sets bulk cargo port constraints, which can reduce the degree of wear and damage of port equipment based on reasonable load and volume, further extend the service life of port equipment, and reduce maintenance costs.

[0012] Optionally, the port planning and scheduling subsystem sets the port scheduling constraints based on the multi-dimensional feature information and further includes: analyzing the initial center of gravity position coordinates of the port bulk cargo based on the bulk cargo position constraints in the port scheduling constraints; limiting the transport weight of the port bulk cargo according to the port vehicle load constraints in the port scheduling constraints; and adjusting the carrying volume of the port bulk cargo according to the port vehicle volume constraints in the port scheduling constraints. The present invention collects and analyzes the multi-dimensional feature information of the port through the port planning and scheduling subsystem, sets scheduling constraints, and performs cargo stacking and transportation planning accordingly, which reflects the development direction of data-driven decision-making.

[0013] Optionally, the bulk cargo location constraint condition satisfies the following relationship:

[0014] in, Indicates the initial center of gravity coordinates of bulk cargo in the port, Indicates the coordinates of the center of gravity of the port bulk cargo after it is loaded into the vehicle. Respectively represent the length, width and height of the cargo along the X-axis, Y-axis and Z-axis after loading. Respectively represent the length, width and height of the port bulk cargo loading vehicle, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the X-axis direction, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the Y-axis direction. The invention sets the position constraint conditions for bulk cargo, based on which the stacking position of the cargo can be accurately planned to ensure that the cargo does not exceed the load range of the vehicle during loading, thereby improving the loading efficiency of the port.

[0015] Optionally, the port vehicle load constraint condition satisfies the following relationship:

[0016] in, Indicates the weight of bulk cargo loaded into the vehicle port. Indicates the safe expansion factor of the loaded vehicle. Indicates the recorded weight of vehicles loaded with bulk cargo at the port; The port vehicle volume constraint condition satisfies the following relationship:

[0017] in, Indicates the statistical volume of bulk cargo loaded into the vehicle port, Indicates the proportion of ineffective space for bulk cargo in ports. Indicates the effective volume of vehicles loaded with bulk cargo at the port.

[0018] The present invention calculates the vehicle load and volume of the port through mathematical functions, which helps the port to reasonably allocate vehicles according to the weight and volume of the goods, avoids resource waste and empty driving, and helps to optimize resource allocation and reduce port transportation costs.

[0019] Optionally, the safety monitoring and early warning subsystem performs visual display and safety warning on the operation plan to realize intelligent monitoring and control of the whole process of the bulk cargo port, including: adding a visualization device and a port safety early warning device to the safety monitoring and early warning subsystem; the safety monitoring and early warning subsystem performs visual display of the whole process of the operation plan through the visualization device; the safety monitoring and early warning subsystem performs intelligent safety early warning on the whole process of the operation plan through the port safety early warning device; the safety monitoring and early warning subsystem realizes intelligent monitoring and control of the whole process of the bulk cargo port based on the visualization display results and intelligent safety early warning information. The safety monitoring and early warning subsystem of the present invention can improve the transparency and visualization of port operations, enhance port safety and emergency response capabilities, and promote the intelligent and sustainable development of ports, and jointly promote the intelligent development of ports and the improvement of management levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the intelligent control system for the whole process equipment of the bulk cargo port of the present invention; Figure 2 It is a schematic diagram of the multi-level information processing mechanism in the intelligent control system of the whole process equipment of the bulk cargo port of the present invention; Figure 3 This is a structural diagram of the intelligent control system for the entire process equipment of a bulk cargo port according to the present invention. DETAILED DESCRIPTION

[0021] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0022] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0023] See also Figure 1 In order to solve the problems of bulk cargo ports in data processing, logistics plan adjustment and control condition optimization, the present invention introduces multiple intelligent subsystems, information processing mechanisms and port constraints, which are helpful to achieve the sharing and in-depth analysis of bulk cargo port information, effective improvement of operational efficiency, significant enhancement of safety, and optimization of resource allocation, thereby comprehensively improving the operational efficiency and safety management level of bulk cargo ports. The present invention provides an intelligent control system for the whole process equipment of bulk cargo ports, and the above system includes the following steps: The intelligent control system of the whole process equipment in the bulk cargo port is equipped with: intelligent identification and monitoring subsystem, information analysis and processing subsystem, port planning and scheduling subsystem, and safety monitoring and early warning subsystem.

[0024] S1. Based on the above identification and monitoring subsystem, multi-dimensional dynamic monitoring information of the port operation process is obtained. The specific implementation steps and related contents are as follows: In this embodiment, the identification and monitoring subsystem is mainly used to obtain multi-dimensional real-time dynamic information of port operations. The above subsystem integrates advanced monitoring and identification technologies, including but not limited to RFID technology, high-definition cameras and various sensors, to intelligently identify and monitor in real time the cargo, vehicles, operating equipment and staff in the bulk cargo port, and can continuously monitor the core status of various operations in the port, mainly including the location of the cargo, the real-time operating status of the loading and unloading equipment, the progress of different processes and the work status of the port staff.

[0025] In addition, the identification and monitoring subsystem also has the function of process task monitoring and display. It can fully monitor and display detailed information of various tasks in the port, including but not limited to task plans, operation processes, machinery usage, cargo stacking arrangements, and personnel configuration. In order to further enhance the actual use experience of the intelligent control system, the system has also designed an intuitive and easy-to-use information query interface. This interface can update the status of the entire process of bulk cargo ports in real time, ensuring that port-related personnel can quickly obtain the latest developments of different tasks in bulk cargo ports. At the same time, the interface design fully considers user interactivity, ensuring that different port managers can quickly query and obtain relevant information about bulk cargo ports according to their actual needs.

[0026] Furthermore, the method for obtaining multi-dimensional dynamic monitoring information of the port in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the method for obtaining multi-dimensional dynamic monitoring information can be adjusted according to the actual situation and data monitoring objectives of the bulk cargo port. Different bulk cargo ports have different operating modes and business needs. Adjusting the method for obtaining monitoring information is conducive to meeting the actual needs of each port and ensuring the effectiveness and practicality of the monitoring system.

[0027] S2. A hierarchical information processing mechanism is constructed in the above information analysis and processing subsystem. Based on the multi-level information processing mechanism, the multi-dimensional dynamic monitoring information is processed to obtain the multi-dimensional characteristic information in the port operation process. The specific implementation contents are as follows: Firstly, the time series information of the port operation process is obtained based on the multi-dimensional dynamic monitoring information.

[0028] In this embodiment, the data structure of the bulk cargo port is combined with the time series data, which is helpful for the comprehensive and accurate analysis and representation of the subsequent time series information. In the above-mentioned intelligent identification and monitoring subsystem, multiple virtual machines are deployed. As a software simulation environment running on physical hardware, the above-mentioned virtual machines can completely simulate the various functions of the intelligent control system, including but not limited to core components such as the central processing unit (CPU), internal memory, hard disk drive and network interface card (NIC).

[0029] Each virtual machine interacts efficiently with the underlying physical hardware through an advanced hypervisor, thereby building multiple independent and securely isolated operating system environments on a single physical server. Under this architecture, a multi-dimensional dynamic monitoring information generated by different virtual machines is formed inside the intelligent control system. The time series data set in the intelligent control system is further analyzed by combining the data collection time point and the preset monitoring time interval, and marked as T.

[0030] Specifically, for different virtual machines in the time series data set, their unique time series data are recorded separately and marked as , this time series data contains different time series information, among which Representing specific data points or time interval fragments in the time series, the above time series information not only reflects the dynamic changes of the virtual machine during operation, but is also closely related to the overall operation status of the port system and the real-time update of target task data.

[0031] The time series data set of different virtual machines in the intelligent control system is T, and the time series of the nth virtual machine is , and the time series information corresponding to different virtual machines is .

[0032] The time series of different virtual machines need to satisfy the following relationship:

[0033] in, Represents the time series corresponding to different virtual machines, represents the first time interval in the time series, represents the second time interval in the time series, Indicates the first time interval.

[0034] Then the time series information of different virtual machines satisfies the following relationship:

[0035] in, Represents the time series information of different virtual machines, express Timing information of the time interval, express Timing information of the time interval, express Timing information of the time interval.

[0036] Based on the time series information of different virtual machines, the time series information of all virtual machines in the bulk cargo port system can be obtained, that is, the time series information of the port operation process can be obtained. In this embodiment, the intelligent control system is preset to have n virtual machines:

[0037] in, Represents the time series information set of all virtual machines in the bulk cargo port system, Represents the time series information of the first virtual machine, Represents the time series information of the second virtual machine, Indicates Time series information of a virtual machine.

[0038] In the operation process of bulk cargo ports, multi-dimensional dynamic monitoring technology can capture the change information of each process operation parameter in real time, such as cargo throughput, port entry and exit time, port yard utilization rate, etc. Processing and analyzing the multi-dimensional dynamic monitoring information and converting it into corresponding time series number information is conducive to reflecting the operation status of bulk cargo ports at different time points and the implementation status of processes.

[0039] In order to accurately obtain the time series information of bulk cargo ports, multiple virtual machines are deployed in the bulk cargo port system. Each virtual machine is responsible for obtaining data from a specific monitoring source or subsystem, and performing preliminary processing and storage on it. By integrating the time series data on different virtual machines, a comprehensive time series information set of the entire port operation process can be obtained, thereby improving the efficiency of data collection and being able to obtain comprehensive time series information of the entire port process more quickly.

[0040] Then, a multi-level information processing mechanism is constructed based on the above time series information. The multi-level information processing mechanism in the embodiment mainly includes a hidden information analysis model and a time-space convolutional network processing model. The structure of the multi-level information processing mechanism is shown in Figure 2 .

[0041] Since different virtual machines in the intelligent control system of the whole process equipment of bulk cargo ports have complex interactive relationships in the network hierarchical topology, their operating status performance indicators also show a high degree of dynamics. The above dynamics are not only reflected in the real-time fluctuations of indicators such as CPU usage, memory occupancy, and disk I / O within a single virtual machine, but also in the mutual influence between virtual machines due to resource competition, communication delays and other factors. Therefore, in this embodiment, a multi-level information processing mechanism is constructed based on time series information to analyze the multi-dimensional dynamic monitoring information in the port operation process.

[0042] An optional embodiment sets up a hidden information analysis model in a multi-level information processing mechanism.

[0043] The above hidden information analysis model satisfies the following relationship:

[0044] in, The hidden information representing the time series information of different virtual machines in the bulk cargo port, Indicates the fusion node information corresponding to different virtual machines. express The weight matrix of An operator representing the spatiotemporal information convolutional network model, Represents the spatial features in the time series information of different virtual machines, Represents the feature matrix corresponding to different virtual machine monitoring nodes, express The diagonal matrix of express The network bias.

[0045] In the intelligent control system of the entire process of bulk cargo ports, the hidden information of the time series information of different virtual machines refers to the information that is not directly revealed on the surface and needs to be mined and analyzed through specific methods or models to obtain. The above information is related to the operating status, performance, and mutual interaction of the system virtual machines.

[0046] In the bulk cargo port system, the fusion node information corresponding to different virtual machines refers to the port information involved and contained when each virtual machine, as an information source or data processing node, interacts and integrates with each other through specific fusion structures and methods during the data fusion or information fusion process.

[0047] In the spatiotemporal information convolutional network model, operators refer to functions or modules that perform specific calculations or operations. The above operators can be used to process spatiotemporal data, such as video frames, time series data, or other data with spatial and temporal dimensions, to capture the temporal distribution characteristics of multi-dimensional dynamic monitoring information.

[0048] In the spatiotemporal information convolutional network model, the weight matrix of the operator refers to the parameter matrix used to perform operations such as convolution, pooling, and full connection. The above weight matrix is ​​learned by the network during the training process, which determines how the network extracts hidden information features from the input data.

[0049] The spatial features in the time series information of different virtual machines refer to the time intervals, location shapes, and spatial relationships with adjacent virtual machines or resources associated with the virtual machines during operation. In the time series information, the above-mentioned interaction features can be manifested as changes in parameters such as the frequency of communication between virtual machines, the transmission speed of data packets, and network delays.

[0050] The feature matrix corresponding to different virtual machine monitoring nodes can be used to describe and record the data structure of the status, performance and other related attributes of each virtual machine monitoring node in the technical field of virtualization technology and system monitoring. This feature matrix can be a two-dimensional array or table, in which each row represents a virtual machine monitoring node and each column represents a specific port feature or process attribute.

[0051] A diagonal matrix is ​​a matrix in which all elements outside the main diagonal are zero. When referring to the diagonal matrix of the feature matrix corresponding to different virtual machine monitoring nodes, if some elements or performance indicators in the feature matrix are equal on all virtual machine monitoring nodes, then these equal elements can form a quantity matrix, which is also a special diagonal matrix, in which the elements on the main diagonal are equal and the other elements are 0. In fact, a special case is taken into account, that is, some specific time information in the feature matrix is ​​extracted to form a diagonal matrix.

[0052] In the spatiotemporal information convolutional network model, the network bias of the operator is a parameter corresponding to the weight matrix, which is used to adjust the output of the hidden information analysis model and help the model better fit the training data. In this way, the hidden information of the time series information of different virtual machines in the bulk cargo port can be accurately obtained.

[0053] In an optional embodiment, before inputting the time series information of different virtual machines into the hidden information analysis model, the relevant information needs to be fused and preprocessed first, including integrating the feature matrix, adjacency matrix and undirected information graph of each monitoring node to form an input set containing a complete topological structure and time series data. The above steps are crucial for the subsequent extraction of hidden information, and further ensure that the model can simultaneously capture the dynamic characteristics of the time series and the network relationship between virtual machines.

[0054] The hidden information analysis model receives a preprocessed input set, namely the time series information of different virtual machines and the corresponding topological information. The model analyzes and mines the input information through algorithms and calculations. Then, it identifies the hidden correlation information between different levels in the time series information. The above information can be manifested as the mutual influence between virtual machines, the imbalance of resource allocation, or the chain reaction caused by certain specific events. Finally, the hidden information analysis model will output the hidden information in the time series information of different virtual machines.

[0055] In an optional embodiment, a temporal-spatial convolutional network processing model is set up in a multi-level information processing mechanism.

[0056] In this embodiment, the time-space convolutional network processing model is responsible for further integrating and analyzing the features extracted by the hidden information analysis model. This model combines the advantages of the time-series analysis model and the spatial convolutional network, and can simultaneously capture the time dependency and spatial correlation of the virtual machine's operating status. By optimizing the network structure and parameter settings, it can obtain multi-dimensional feature information in the port operation process.

[0057] In the embodiment, the convolutional neural network (CNN) structure is improved to make it suitable for processing time series data, and then the time-space convolutional network model of the present invention is constructed. The above-mentioned time-space convolutional network model has a unique structural design and can efficiently process dynamic monitoring information in the bulk cargo port system. The model cleverly combines causal convolution and dilated convolution to achieve in-depth analysis of port process information and dynamic monitoring information.

[0058] In the time-space convolutional network model, a causal convolutional layer is first set up. Its main function is to ensure that the model can strictly follow the time order when processing time series information, that is, only use the current and previous time point information to avoid the leakage of future port dynamic monitoring information, which helps to more accurately simulate and predict the actual changes in port processes and task operation status.

[0059] Next, the time-space convolutional network model includes two dilated convolutional layers, namely the first dilated convolutional layer and the second dilated convolutional layer in the embodiment. The dilated convolution effectively expands the processing volume of the convolution by inserting additional intervals between the convolution kernel elements, thereby increasing the model's capture range of port process information and monitoring information while keeping the convolution kernel size unchanged. The above design enables the model to capture more port process details, including but not limited to the mutual influence and dependency between system virtual machines, the interactive overlapping relationship of multi-dimensional monitoring information, and the distribution status of timing information.

[0060] Finally, the processed port time series and spatial series feature information are extracted through the output layer of the time-space convolutional network model. The above information not only includes the basic data in the port process, but also includes the hidden information and interdependencies in the time series information, which provides information support for the subsequent process management and equipment control scheme optimization of bulk cargo ports.

[0061] Compared with the temporal recurrent neural network, the temporal-spatial convolutional network model can process the basic data and hidden information in all time series in parallel, greatly improving the computational efficiency. This enables the model to obtain more comprehensive and accurate information analysis results when processing large-scale port process data and multi-dimensional monitoring information, providing a decision-making basis for bulk cargo port operations and full-process equipment control.

[0062] The operation flow and related contents of the multi-level information processing mechanism in this embodiment are as follows: Input a time series information set into the hidden information analysis model, and the input information satisfies the following relationship:

[0063] in, Represents the time series information set of all virtual machines in the bulk cargo port system, Represents the time series information of the first virtual machine, Represents the time series information of the second virtual machine, Indicates Time series information of a virtual machine.

[0064] Then the hidden information analysis model outputs a hidden information set, which satisfies the following relationship:

[0065] in represents the hidden information set in the time series information of all virtual machines in the bulk cargo port system, represents the hidden information in the time series information of the first virtual machine, represents the hidden information in the time series information of the second virtual machine, Indicates Hidden information in the time series information of virtual machines.

[0066] Then, the temporal-spatial convolutional network processing model is used to obtain the output results of different virtual machines. Combining all the output results can obtain the multi-dimensional feature information of the port operation process. The above temporal-spatial convolutional network processing model satisfies the following relationship:

[0067] in, Represents the output of the temporal-spatial convolutional network processing model, represents the model activation function, represents the weight coefficient of the causal convolutional layer, represents the causal convolution kernel parameters, Indicates Time series information of virtual machines, Indicates Hidden information in the time series information of virtual machines, represents the weight coefficient of the first dilated convolutional layer, represents the dilation coefficient of the first dilated convolutional layer, represents the weight coefficient of the second dilated convolutional layer, represents the dilation coefficient of the second dilated convolutional layer, Represents the bias term of the temporal-spatial convolutional network.

[0068] The activation function in the model refers to a nonlinear mapping in the neural network, which converts input information into corresponding output results. The introduction of nonlinear factors can increase the expressive power of the time-space convolutional network processing model.

[0069] The weight coefficient of the causal convolution layer refers to the coefficient for weighted summation of input information in the causal convolution layer. The above weight coefficient is learned during the training process of the convolutional neural network, which determines the contribution of each input information to the output result. Causal convolution is a special convolution method mainly used to process sequence data. In causal convolution, the value of the previous layer at time t only depends on the value of the next layer at time t and before. The above convolution method ensures that the output result only depends on the input sequence, which conforms to the causal nature of the time sequence.

[0070] The causal convolution kernel parameters refer to specific values ​​that can be used to define the convolution kernel characteristics in the causal convolution operation. The above parameters determine how the causal convolution kernel weights and sums the input information, thereby affecting the relevant characteristics of the output result. In this embodiment, each element in the convolution kernel corresponds to a weight coefficient, which is obtained through learning during the training process and can be used to capture the features in the input information. In the causal convolution, the update of the weight coefficient needs to follow the causal constraint, that is, it only depends on the current and previous data.

[0071] The weight coefficients of different dilated convolutional layers refer to the weight coefficients used by each convolution kernel in the convolutional layers with different dilation rates. Dilated convolution is a special convolution operation that increases the receptive field by inserting intervals between the convolution kernel elements while keeping the actual size of the convolution kernel unchanged. The above operation enables the temporal-spatial convolutional network processing model to capture a wider range of port process monitoring information and time series information without increasing the computational complexity.

[0072] The dilation rate of different dilated convolutional layers refers to the different number of intervals used by each layer with dilated convolution operations in the convolutional neural network. This parameter determines the size of the interval between the convolution kernel elements, thereby affecting the receptive field and feature information extraction capabilities of the convolutional layer.

[0073] The dilated convolution is also called dilated convolution or expanded convolution. It injects holes into the standard convolution kernel to increase the receptive field of the processing model. Compared with the original normal convolution operation, the dilated convolution has one more parameter, the dilation coefficient. The above dilation coefficient defines the spacing between the values ​​​​when the convolution kernel processes data, that is, it determines the distance between adjacent valid elements (non-zero elements) in the convolution kernel.

[0074] The bias term in the time-space convolutional network refers to the additional parameters added to the output channel corresponding to each convolution kernel. This bias term translates or offsets the input information, thereby adjusting the output range of the processing model. In the time-space convolutional network, the bias term can fit the data more flexibly, further improving the expressiveness of the model.

[0075] Finally, the hidden information analysis model is used to analyze the time series information and obtain the hidden information in the time series information; and the above hidden information and time series information are processed by the time-space convolutional network processing model to obtain the multi-dimensional feature information in the port operation process.

[0076] In the intelligent analysis process of the port's full-process operation management, a comprehensive multi-level information processing mechanism is adopted. The above mechanism first mines the hidden information in the port time series information through the hidden information analysis model. The above hidden information contains the key details and potential rules in the port operation process.

[0077] Next, the time-space convolutional network processing model is used to receive the feature input from the hidden information analysis model, and the port information is deeply processed and analyzed by combining the original time series information and dynamic monitoring information. The above steps aim to comprehensively capture the multi-dimensional feature information in the port operation process, including but not limited to logistics efficiency, equipment status, personnel scheduling and other aspects.

[0078] In addition, the various models in the multi-level information processing mechanism are not isolated, but cooperate with each other and work together to obtain multi-dimensional feature information. The hidden information analysis model provides rich feature inputs for the time-space convolutional network processing model, and the time-space convolutional network processing model, through its powerful processing capabilities, converts relevant features into multi-dimensional feature information in the port operation process, which is conducive to the accurate prediction, intelligent control and fault warning of the operating status of the entire process equipment in the bulk cargo port. This synergistic relationship enables the multi-level information processing mechanism to more efficiently process the complex and changeable monitoring data and operating status information in the port system.

[0079] Through a multi-level information processing mechanism, the complex and changeable port operation status information in the port system can be efficiently processed, and the accurate prediction and fault warning of the operating status of each equipment or component in the port operation management system can be achieved. Based on this, it not only improves the intelligence level of port operation management, but also provides decision makers with more comprehensive and accurate data support, which helps to operate and manage processes of bulk cargo ports more efficiently and safely.

[0080] Furthermore, the method for obtaining multi-dimensional characteristic information of ports in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the method for obtaining multi-dimensional characteristic information of ports can be adjusted according to the actual situation of port monitoring data and the requirements of equipment intelligent control. Different ports differ in operating scale, equipment configuration, business model, etc. The method for obtaining characteristic information is adjusted according to the actual situation, so that the present invention can better adapt to the actual needs of various ports and ensure the accuracy and practicality of the analysis results.

[0081] S3. The above-mentioned port planning and scheduling subsystem sets port scheduling constraints based on multi-dimensional feature information, and further formulates the port bulk cargo operation plan based on the above-mentioned port scheduling constraints and multi-dimensional feature information. The specific implementation contents are as follows: Port scheduling constraints are set based on multi-dimensional feature information and bulk cargo port operation requirements. In this embodiment, the port scheduling constraints mainly include: bulk cargo location constraints, port vehicle load constraints and port vehicle volume constraints.

[0082] Based on multi-dimensional feature information and the complex and changeable operational requirements of bulk cargo ports, a series of port scheduling constraints are set to ensure the normal operation of bulk cargo port processes and the scientific and efficient control of scheduling plans. In this embodiment, the above constraints not only cover the basic operational management elements, but also go deep into the details of the actual operation level.

[0083] In order to ensure that the bulk cargo port implements the operation process according to the optimal strategy, relevant information conditions for bulk cargo and carrying vehicles are pre-set in this embodiment. The above conditions are intended to ensure the safety and efficiency of the bulk cargo port loading process through precise mathematical expressions.

[0084] First, an initial center of gravity position coordinate is defined , which represents the center of gravity of bulk cargo before loading. When bulk cargo is loaded into the vehicle, its center of gravity will change, and the new center of gravity position is To show, the above changes play an important role in assessing the stability and safety of loaded cargo.

[0085] In addition, the dimensions of the cargo along the X-axis, Y-axis and Z-axis after loading are defined, respectively. These dimensions help to understand the actual space occupied by the cargo in the vehicle, thereby avoiding space waste or overloading during loading.

[0086] At the same time, the specific parameters of the load-bearing vehicle c are also considered, including but not limited to its length ,width and height These parameters are key to determining the vehicle's loading capacity. In addition to size parameters, the vehicle's load capacity is also considered. and effective volume , which respectively limit the maximum weight and volume that a vehicle can carry, and are important information to ensure the safety and compliance of the bulk cargo port loading process.

[0087] The location constraints of bulk cargo require that the specific storage location of each batch of bulk cargo must be accurately grasped during scheduling in order to formulate the optimal handling and loading plan and reduce unnecessary handling costs and time waste.

[0088] The above-mentioned bulk cargo location constraints satisfy the following relationship:

[0089] in, Indicates the initial center of gravity coordinates of bulk cargo in the port, Indicates the coordinates of the center of gravity of the port bulk cargo after it is loaded into the vehicle. Respectively represent the length, width and height of the cargo along the X-axis, Y-axis and Z-axis after loading. Respectively represent the length, width and height of the port bulk cargo loading vehicle, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the X-axis direction, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the Y-axis direction. Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the Z-axis direction.

[0090] When loading port cargo onto a carrying vehicle, it is necessary to ensure that the size, weight and volume of the cargo do not exceed the maximum allowed by the vehicle. Specifically, the length, width and height of the cargo should be strictly controlled within the corresponding dimensions of the vehicle to avoid overflow or overloading of the vehicle. At the same time, the total weight of the cargo must not exceed the load capacity of the vehicle to ensure safety and stability during transportation. In addition, the total volume of the cargo should also be less than or equal to the effective volume of the vehicle to prevent overloading from causing unreasonable use of vehicle space or safety hazards.

[0091] The port vehicle load constraints need to take into account the safety and operational efficiency of port transport vehicles. In the embodiment, a clear maximum load is set for each type of vehicle. During the port process optimization and scheduling, it is necessary to ensure that the total weight of the allocated cargo is controlled within the vehicle load capacity to prevent safety hazards and reduced transportation efficiency caused by overloading.

[0092] The above-mentioned port vehicle load constraints satisfy the following relationship:

[0093] in, Indicates the weight of bulk cargo loaded into the vehicle port. Indicates the safe expansion factor of the loaded vehicle. Indicates the recorded weight of vehicles loaded with bulk cargo at the port; In addition to the load limit, the port vehicle volume constraint conditions are also reasonably set and planned. During the port operation process and plan adjustment process, it is necessary to reasonably allocate transport vehicles according to the size and shape characteristics of the cargo to ensure that the cargo can be fully and compactly loaded in the vehicle, thereby improving transportation efficiency and reducing transportation costs.

[0094] The above port vehicle volume constraints satisfy the following relationship:

[0095] in, Indicates the statistical volume of bulk cargo loaded into the vehicle port, Indicates the proportion of ineffective space for bulk cargo in ports. Indicates the effective volume of vehicles loaded with bulk cargo at the port.

[0096] In addition, these constraints can be further expanded and improved according to the actual situation and specific needs of port operations, such as considering cargo loading and unloading time restrictions, transportation route optimization, port congestion, etc., so as to comprehensively improve the high efficiency of bulk cargo port equipment and the intelligence and refinement of the port dispatching system.

[0097] In an optional embodiment, the initial center of gravity position coordinates of the port bulk cargo are analyzed based on the bulk cargo position constraints in the port scheduling constraints; the transportation weight of the port bulk cargo is limited according to the port vehicle load constraints in the port scheduling constraints; the carrying volume of the port bulk cargo is adjusted according to the port vehicle volume constraints in the port scheduling constraints, and then the loading process and operation process of the port bulk cargo are carefully planned.

[0098] Firstly, based on the bulk cargo location constraints in the port scheduling constraints, the initial center of gravity coordinates of the port bulk cargo are analyzed. This step aims to determine the specific location of the cargo in the port so that it can be efficiently and accurately transported to the designated location during the subsequent loading process, while ensuring the stability and safety of the loading process.

[0099] Secondly, according to the port vehicle load constraint in the port scheduling constraint, the transportation weight of bulk cargo at the port is restricted. During the loading process of port cargo, it is always ensured that the total weight of the allocated cargo does not exceed the load capacity of the carrying vehicle to prevent safety hazards and reduced transportation efficiency caused by overloading.

[0100] Finally, according to the port vehicle volume constraints in the port scheduling constraints, the carrying volume of the port's bulk cargo is flexibly adjusted. Mainly based on the volume size and shape characteristics of the bulk cargo, as well as the volume limitations of the carrying vehicles, the port transport vehicles are reasonably allocated, and the loading plan is optimized to ensure that the goods can be fully and compactly loaded in the vehicle, thereby improving transportation efficiency and reducing transportation costs.

[0101] Through meticulous planning and flexible adjustments, efficient, precise and intelligent management of the bulk cargo loading process at the port is achieved while ensuring safety and compliance, further ensuring the actual application effect of the intelligent control system of the entire process equipment at the bulk cargo port.

[0102] Furthermore, in the present embodiment, the method for obtaining the port operation plan and the control steps are only an optional condition of the present invention. In one or some other embodiments, the method for obtaining the port operation plan and the control steps can be optimized according to the safety requirements of the bulk cargo port and the intelligent control conditions of the port equipment, which is helpful to realize the real-time monitoring and intelligent scheduling of the port equipment, so as to more accurately grasp the progress of cargo loading and unloading, the vehicle operation status and the utilization of port resources, and further provide strong support for the continuous optimization of the port operation plan.

[0103] S4. The safety monitoring and early warning subsystem visualizes the above operation plans and provides safety early warnings to achieve intelligent monitoring and control of the entire process of the bulk cargo port. The specific implementation contents are as follows: The intelligent control system for the entire process of bulk cargo port equipment also includes the configuration of visualization devices and port safety warning devices in the safety monitoring and early warning subsystem.

[0104] The visualization device can capture and display the entire process and operation status of the bulk cargo port in real time. Through image processing and display technology, port operation data, multi-dimensional feature information and operation plan can be converted into intuitive and easy-to-understand graphics, schematic diagrams or animations, so that port managers can quickly grasp the process and operation status of the bulk cargo port, including but not limited to the progress of cargo loading and unloading, vehicle scheduling, and equipment operation status. The above real-time visualization display method not only improves the operational transparency of the bulk cargo port, but also provides decision-making basis for managers, so that more accurate and efficient equipment control and decision adjustments can be made according to actual conditions.

[0105] The visualization device also has the function of pushing and notifying internal messages of the port, which can fully cover all aspects of task management, including but not limited to key nodes such as task issuance, change, start, pause and fault notification, so that the bulk cargo port messages can be presented in the form of instant messaging to ensure that the information can be quickly conveyed to relevant personnel. At the same time, the past message records of the port can be consulted, and the message overview interface clearly distinguishes between read and unread messages, which is convenient for quickly grasping the processing of messages. In order to display the content of the message more intuitively, the system uses a table format for arrangement. For details, see Table 1, which makes each message clear at a glance, further improving the efficiency and accuracy of message management, and thus improving the overall performance and user satisfaction of the intelligent control system of the whole process equipment of the bulk cargo port.

[0106] Table 1 Bulk cargo port information table Message Type Information specific parameters Task distribution Issuer, issue time, ship name, loading and unloading type, etc. Mission Changes Operator, operation time, ship name, etc. Task Deletion Operator, operation time, ship name, etc. Mechanical failure Machine code, machine name, occurrence time Mechanical recovery Machine code, machine name, occurrence time Mechanical changes Machine code, machine name, operator, operation time, etc. Start of work Name of transport equipment, operator, operation time, etc. Job Suspension Name of transport equipment, operator, operation time, etc. Job Stop Name of transport equipment, operator, operation time, etc. Homework Completed Name of transport equipment, operator, operation time, etc. The port safety early warning device integrates a variety of sensors and data analysis algorithms, and can monitor in real time the fluctuations and changing trends of various safety parameters in the port operation process, such as the stability of cargo, the load and speed of transport vehicles, and the wear and tear of port equipment. Once the relevant parameters exceed the preset safety range, the early warning device will be activated immediately, and send early warning information to relevant personnel through sound, light or text messages, reminding port management personnel to take timely measures to prevent potential safety risks from turning into actual accidents.

[0107] In summary, the safety monitoring and early warning subsystem in the intelligent control system of the whole process equipment of the bulk cargo port, through the configuration of visualization devices and port safety early warning devices, realizes the comprehensive monitoring and intelligent early warning of the port operation status and equipment operation status, and provides technical guarantee for the safe and efficient operation of the bulk cargo port.

[0108] The above-mentioned safety monitoring and early warning subsystem uses a visualization device to visualize the entire process of the operation plan; and uses the port safety early warning device to provide intelligent safety early warnings for the entire process of the operation plan. The safety monitoring and early warning subsystem can realize intelligent monitoring and control of the entire process of the bulk cargo port based on the visualization results and intelligent safety early warning information.

[0109] First, the subsystem uses visualization devices to present the entire process of the bulk cargo port operation plan in an intuitive and vivid way, so that port managers can clearly understand the port's operating status. Whether it is real-time mission status, space status, bill of lading information, or the operating status of key modules such as yards, gantry cranes, horizontal transportation, and clamping vehicles, they can all be displayed in detail in the visualization interface.

[0110] At the same time, the port safety early warning device can provide intelligent safety early warning for the entire process of the operation plan. Through real-time monitoring and data comparison and analysis, the early warning device can promptly detect and warn of potential safety risks, including but not limited to equipment failures, abnormal task execution, and process sequence errors, thereby ensuring the safety and stability of bulk cargo port operations.

[0111] On this basis, the intelligent control system for the whole process of bulk cargo port equipment further strengthens the monitoring capability of the system, which can not only monitor the overall task execution of the port, but also conduct operation status statistics and real-time status monitoring for different types of equipment such as gantry cranes, horizontal transport vehicles, clamping vehicles, etc. In addition, the task status monitoring function enables managers to track the tasks that have been executed and are to be executed in real time, including but not limited to basic task information, status information, machinery information, stacking position information, etc., so as to achieve accurate control of the whole process and execution process of bulk cargo port tasks.

[0112] When an abnormal situation occurs, the system will immediately issue a safety warning and early warning signal using the abnormal alarm monitoring function, and send a warning signal to port managers through page reminders, wireless communications, and telephone reminders. At the same time, the abnormal alarm statistics function can also provide abnormal alarm analysis and real-time monitoring of various indicators based on grouping methods such as cycle and type, providing decision support for port managers.

[0113] In summary, the safety monitoring and early warning subsystem realizes the intelligent monitoring and control of the whole process of bulk cargo port through a series of functions such as visual display, intelligent safety early warning, real-time monitoring, task status monitoring and abnormal alarm monitoring. The system of the present invention not only improves the safety and efficiency of port operations, but also lays a solid foundation for the sustainable development of the port.

[0114] See also Figure 3 In an optional embodiment, the present invention further provides an intelligent control system for the whole process equipment of bulk cargo port, the system includes an intelligent identification and monitoring subsystem, an information analysis and processing subsystem, a port planning and scheduling subsystem, and a safety monitoring and early warning subsystem, the intelligent identification and monitoring subsystem, the information analysis and processing subsystem, the port planning and scheduling subsystem, and the safety monitoring and early warning subsystem are interconnected, and the specific steps of the relevant embodiments of the intelligent control system for the whole process equipment of bulk cargo port provided by the present invention are implemented. The intelligent control system for the whole process equipment of bulk cargo port of the present invention has a complete structure, objective stability, and improves the overall applicability and practical application ability of the present invention.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. Intelligent control system for the whole process equipment of bulk cargo port, characterized by: The intelligent control system for the whole process equipment of the bulk cargo port includes: intelligent identification and monitoring subsystem, information analysis and processing subsystem, port planning and scheduling subsystem and safety monitoring and early warning subsystem; Based on the intelligent identification and monitoring subsystem, multi-dimensional dynamic monitoring information during port operation is obtained; Constructing a multi-level information processing mechanism in the information analysis and processing subsystem, and processing the multi-dimensional dynamic monitoring information based on the multi-level information processing mechanism to obtain multi-dimensional feature information in the port operation process; The port planning and scheduling subsystem sets port scheduling constraints based on the multi-dimensional feature information, and formulates a port bulk cargo operation plan according to the port scheduling constraints and the multi-dimensional feature information; The safety monitoring and early warning subsystem performs visual display and safety early warning of the operation plan to achieve intelligent monitoring and control of the entire process of the bulk cargo port.

2. The intelligent control system for the whole process equipment of bulk cargo port according to claim 1 is characterized in that: The multi-level information processing mechanism constructed in the information analysis and processing subsystem includes: Obtaining time series information during port operation based on the multi-dimensional dynamic monitoring information; A multi-level information processing mechanism is constructed based on the time series information, and the multi-level information processing mechanism includes a hidden information analysis model and a time-space convolutional network processing model.

3. The intelligent control system for the whole process equipment of bulk cargo port according to claim 2 is characterized in that: The hidden information analysis model satisfies the following relationship: ， in, The hidden information representing the time series information of different virtual machines in the bulk cargo port, Indicates the fusion node information corresponding to different virtual machines. express The weight matrix of An operator representing the spatiotemporal information convolutional network model, Represents the spatial features in the time series information of different virtual machines, Represents the feature matrix corresponding to different virtual machine monitoring nodes, express The diagonal matrix of express The network bias.

4. The intelligent control system for the whole process equipment of bulk cargo port according to claim 2 is characterized in that: The temporal-spatial convolutional network processing model satisfies the following relationship: ， in, Represents the output of the temporal-spatial convolutional network processing model, represents the model activation function, represents the weight coefficient of the causal convolutional layer, represents the causal convolution kernel parameters, Indicates Time series information of virtual machines, Indicates Hidden information in the time series information of virtual machines, represents the weight coefficient of the first dilated convolutional layer, represents the dilation coefficient of the first dilated convolutional layer, represents the weight coefficient of the second dilated convolutional layer, represents the dilation coefficient of the second dilated convolutional layer, Represents the bias term of the temporal-spatial convolutional network.

5. The intelligent control system for the whole process equipment of bulk cargo port according to claim 2 is characterized in that: The processing of the multi-dimensional dynamic monitoring information based on the multi-level information processing mechanism to obtain multi-dimensional feature information in the port operation process includes: Analyze the time series information using the hidden information analysis model and obtain the hidden information in the time series information; The temporal-spatial convolutional network processing model processes the hidden information and the time series information to obtain multi-dimensional feature information in the port operation process.

6. The intelligent control system for the whole process equipment of bulk cargo port according to claim 1 is characterized in that: The port planning and scheduling subsystem sets the port scheduling constraint conditions based on the multi-dimensional feature information, including: Port scheduling constraints are set based on the multi-dimensional feature information and the bulk cargo port operation requirements, and the port scheduling constraints include: bulk cargo location constraints, port vehicle load constraints and port vehicle volume constraints.

7. The intelligent control system for the whole process equipment of bulk cargo port according to claim 6 is characterized in that: The port planning and scheduling subsystem further includes: Analyze the initial center of gravity coordinates of bulk cargo in the port based on the bulk cargo location constraints in the port scheduling constraints; According to the port vehicle load constraint in the port dispatch constraint, the transportation weight of bulk cargo at the port is limited; The carrying volume of bulk cargo at the port is adjusted according to the port vehicle capacity constraints in the port scheduling constraints.

8. The intelligent control system for the whole process equipment of bulk cargo port according to claim 6 is characterized in that: The bulk cargo location constraints satisfy the following relationship: ， in, Indicates the initial center of gravity coordinates of bulk cargo in the port, Indicates the coordinates of the center of gravity of the port bulk cargo after it is loaded into the vehicle. Respectively represent the length, width and height of the cargo along the X-axis, Y-axis and Z-axis after loading. Respectively represent the length, width and height of the port bulk cargo loading vehicle, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the X-axis direction, Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the Y-axis direction. Indicates the allowable deviation coefficient of the center of gravity of bulk cargo in the port in the Z-axis direction.

9. The intelligent control system for the whole process equipment of bulk cargo port according to claim 6 is characterized in that: The port vehicle load constraint condition satisfies the following relationship: ， in, Indicates the weight of bulk cargo loaded into the vehicle port. Indicates the safe expansion factor of the loaded vehicle. Indicates the recorded weight of vehicles loaded with bulk cargo at the port; The port vehicle volume constraint condition satisfies the following relationship: ， in, Indicates the statistical volume of bulk cargo loaded into the vehicle port, Indicates the proportion of ineffective space for bulk cargo in ports. Indicates the effective volume of vehicles loaded with bulk cargo at the port.

10. The intelligent control system for the whole process equipment of bulk cargo port according to claim 1 is characterized in that: The safety monitoring and early warning subsystem visualizes the operation plan and provides safety early warning to achieve intelligent monitoring and control of the entire process of the bulk cargo port, including: Adding a visualization device and a port safety warning device to the safety monitoring and warning subsystem; The safety monitoring and early warning subsystem uses a visualization device to visualize the entire process of the operation plan; The safety monitoring and early warning subsystem provides intelligent safety early warning for the entire process of the operation plan through the port safety early warning device; The safety monitoring and early warning subsystem realizes intelligent monitoring and control of the entire process of the bulk cargo port based on visual display results and intelligent safety early warning information.

Images