Port safety supervision and risk identification early warning system and method

Abstract

The invention relates to the technical field of port safety supervision, and particularly discloses a port safety supervision and risk identification early warning system and method, and the system comprises a data collection module, a global state sensing module, a risk identification module, an operation rule base, and a risk early warning module. The method has the beneficial effects that 1, various types of data are fused, the road side is fused to perceive the vehicle state, and a traffic real-time state diagram is restored through established scene simulation, so that the accurate pre-judgment of the risk is realized, and the problem of insufficient prediction capability of single equipment is solved; and 2, the real-time vehicle motion state of the road is sensed through roadside fusion, meanwhile, the unmanned vehicle state and the port machine operation state are accessed, the safety risks of the vehicle and the port machine and the safety risks of the unmanned vehicle and the manned vehicle are judged respectively, and the accuracy and reliability of port risk identification and early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of port safety supervision, and in particular to a port safety supervision and risk identification and early warning system and method. Background Art

[0002] In the process of port operation, there are many potential safety threats due to its complex operation scenarios, high-intensity logistics flow, cross-operation of various mechanical equipment, and harsh natural environmental factors, such as high-level sea breeze, high-intensity light, and high corrosiveness. Once these threats are triggered, they may lead to major safety accidents, resulting in serious consequences such as casualties, property losses, and environmental pollution. Therefore, effective monitoring and intelligent identification of high-risk links in port operations are extremely important for improving the safety performance and operating efficiency of port operations.

[0003] In the traditional port safety management process, most of the means rely on manual intuitive observation and empirical judgment, such as manual routine inspection (manual inspection according to the checklist). This method lacks systematization and immediacy, and it is difficult to accurately evaluate and warn potential high-risk operations. With the continuous advancement of information technology, especially the increasing maturity of big data and artificial intelligence technology, new solutions are provided for the safety monitoring of high-risk operations in ports. However, the existing monitoring systems often focus only on a single risk source, or use large models to predict risks. The use of large models is heavily dependent on data quality and quantity, and many prediction models are built based on certain assumptions. If the actual situation does not meet these assumptions, the model's prediction may be biased. In addition, the model is also based on one or more algorithms. Different algorithms have different advantages, disadvantages and scope of application. If the selected algorithm is not suitable for the specific problem, the prediction performance of the model may be limited, resulting in deviations in the accuracy and authenticity of the warning signal, resulting in a high false alarm rate of the warning signal.

[0004] In addition, the port operation environment is changeable and complex, and various risk factors are intertwined. Traditional methods are powerless in the face of complex risk identification and assessment. For example, the patent with application number CN202411162155.5 discloses a method for safety monitoring and intelligent risk identification of high-risk operations in ports, which relates to the field of port management and operation technology. The present invention aims to analyze the potential high-risk operation scenarios identified by quantitative analysis, so as to further identify and locate the risk sources in the potential high-risk operation scenarios, improve the pertinence and efficiency of risk identification, and the scientificity and accuracy of risk identification. At the same time, based on the quantitative scoring obtained by the quantitative analysis of the potential high-risk operation scenarios, the data-driven approach is more scientific and effective as the generation standard of the real-time risk level warning signal, that is, the real-time risk level warning signal can be accurately generated, so that the generated real-time risk level warning signal can effectively prompt relevant personnel to take corresponding measures according to the risk level to avoid or reduce the impact of potential accidents, and avoid excessive intervention and waste of resources. The above patents cover a wide range of content, the model prediction has a certain false alarm rate, and it relies more on manually input data, which is not friendly to automation improvement. Therefore, there is an urgent need for a new method that can comprehensively consider various risk indicators, realize intelligent identification of risks and accurately generate early warning signals. At the same time, it is necessary to reduce the false alarm rate to improve the accuracy of early warning signals, so as to enhance the safety management level of port operations, reduce the probability of accidents, and ensure the rational allocation of resources to avoid unnecessary cost losses. Summary of the invention

[0005] The present invention proposes a port safety supervision and risk identification and early warning system and method in order to solve the above problems.

[0006] The technical solution of the present invention is achieved in this way:

[0007] Port safety supervision and risk identification and early warning system, including data collection module, global status perception module, risk identification module, operation rule library, and risk early warning module;

[0008] The data acquisition module is used to connect with the TOS port operating system, ECS port automation equipment control system, TCS port cloud control dispatching system, external container truck management dispatching system, vehicle-mounted sensing equipment, and road test sensing equipment to obtain the parameters and status data of unmanned vehicles, manned vehicles, and port machinery equipment in the port area;

[0009] The global state perception module is used to integrate and analyze various types of traffic data collected by the data acquisition module to generate a real-time traffic state map to provide data support for traffic management, scheduling and decision-making;

[0010] The risk identification module is used to perform calculations and logical analysis based on the data from the data acquisition module and the global state perception module, identify and evaluate potential risk factors, and provide support for subsequent risk management and decision-making;

[0011] The operation rule library stores various rules and standards that are crucial to port operations, providing support for vehicle travel predictions and port machinery equipment operation predictions within the port;

[0012] The risk warning module is used to rate the risk factors identified by the risk identification module, and to issue different warning reminders according to the risk level, so as to provide timely risk information to managers. At the same time, it provides decision-making guidance according to the risk status and helps to formulate effective risk response strategies.

[0013] Furthermore, when the risk level is at the highest, the risk warning module can directly issue instructions to vehicles in the port area to reduce the occurrence of safety risk accidents.

[0014] Furthermore, the operation rules and standards in the operation rule library can be modified, supplemented and deleted in real time.

[0015] The present invention also discloses a port safety supervision and risk identification and early warning method, which includes the following steps:

[0016] Step 1: Build a virtual traffic real-time status diagram,

[0017] Step 1.1: Virtual environment scene simulation, collect and establish port infrastructure model, including yard, berth, road, roadside facilities, port machinery equipment, roadside sensing equipment model;

[0018] Step 1.2: Business action scenario simulation, establish container and port machinery circulation process models, unmanned vehicle and manned vehicle transportation process models, and construct business motion scenario models from the circulation process model and operation process model;

[0019] Step 1.3, simulate the virtual traffic real-time state diagram, establish the vehicle-to-vehicle safety conflict mechanism, vehicle-to-port machinery conflict handling mechanism, vehicle anomaly handling mechanism, and port machinery anomaly handling mechanism, and provide an operating mechanism for the virtual traffic real-time state diagram;

[0020] Step 2: The data collected by the data collection module is restored to a real-time traffic status map, and the risk identification module determines the type of safety risk.

[0021] Step 2.1, receive real-time business data, obtain the operation status of port machinery, ships, containers, real-time transportation status of unmanned vehicles and manned vehicles, and roadside fusion perception data, map the data to the risk warning module, and determine whether to trigger the early warning alarm. If yes, output it to the risk warning module and then go to the next step. If not, directly go to the next step loop;

[0022] Step 2.2: Safety scheduling simulation to determine the horizontal and longitudinal operation of each port machinery and the conflicts between the routes of unmanned vehicles and manned vehicles and identify potential collision risks;

[0023] Step 2.2.1, extract the motion state and operation motion route of each port machinery, the motion state includes relative position (x, y, z), speed v, direction h, the motion state of each unmanned vehicle Pos_i (lon_i, lat_i, ele_i), speed vi, acceleration ai, direction heading_i and planned path {pt_j (lon_j, lat_j, ele_j)}, the motion state of each manned vehicle Pos_ii (lon_ii, lat_ii, ele_ii), speed vii, acceleration aii, direction heading_ii and planned path {pt_jj (lon_jj, lat_jj, ele_jj)};

[0024] Step 2.2.2, convert the port machinery motion state and route into three-dimensional space coordinate system coordinate points with the port machinery high-precision equipment positioning installation point as the center, the three-dimensional coordinate position of the port machinery operating arm pt0 (lon0, lat0, ele0), speed v0, direction heading0, and the port machinery motion route point set {pt_k (lon_k, lat_k, ele_k)};

[0025] Step 2.2.3, identify the safety risks of vehicles and port machinery, calculate the early warning TTC0 of a port machinery, TTC0 = min{TTCi}, i = 1 ~ N, N is the unmanned vehicle close to the port machinery at the current moment, TTCi is the potential collision time between the port machinery and each unmanned vehicle and manned vehicle calculated according to the current position, speed, direction and trajectory, where TTC refers to the collision time, and whether to trigger the vehicle and port machinery safety warning threshold is determined based on the collision time TTC;

[0026] Step 2.2.4, vehicle-to-vehicle safety risk identification: calculate the warning TTC1 of the unmanned vehicle and other vehicles, TTC1 = min{TTCi}, i = 1 ~ N, N is the number of other vehicles close to the unmanned vehicle, TTCi is the potential collision time between the unmanned vehicle and other vehicles calculated based on the current position, speed, direction and trajectory, and determine whether to trigger the vehicle-to-vehicle safety warning threshold based on the collision time TTC;

[0027] Step 2.2.5, Risk Safety Identification of Single Harbour Crane Equipment: Based on traversing and retrieving the entries in the rule base to determine whether to trigger a safety warning for the single harbour crane. If the motion state and self - state inspection results of the harbour crane are different from the rules and standards in the rule base, a safety warning is triggered;

[0028] Step 2.2.6, Risk Safety Identification of Single Vehicle: Based on traversing and retrieving the entries in the rule base to determine whether to trigger a safety warning for the single vehicle. If the motion state and self - state inspection results of the vehicle are different from the rules and standards in the rule base, a safety warning is triggered;

[0029] Step 3: Output the warning risks and warning levels, and repeat to execute the next loop for monitoring and determination.

[0030] Furthermore, the vehicle and harbour crane safety risk identification in step 2.2.3 includes the following steps:

[0031] Step a: Establish a safety warning potential field for the harbour crane, that is, a spherical safety warning field with a warning radius R0 centered on the operation arm of the harbour crane, where the warning radius R0=(Rmax < K / TTC0)? Rmax : K / TTC0, where Rmax is the maximum warning radius value preset according to the characteristics of the harbour crane, and K is the warning radius constant set according to the actual situation;

[0032] Step b: Calculate the warning level WarnL0 and warning radius R0 of the harbour crane, WarnL0=(L1≥K / TTC0)? 1 : ((L2≥K / TTC0)? 2 : 3), where L1 is the first - level warning threshold, L2 is the second - level warning threshold, K is the warning radius constant set according to the actual situation, and the maximum is the third - level warning;

[0033] Step c: Judge the current safety collision level. If there is a safety warning, generate a hierarchical safety scheduling strategy according to the warning level. When there is a first - level warning, relevant driverless vehicles and manned vehicles decelerate or the driverless vehicle adjusts its route to run; when there is a second - level warning, the relevant driverless vehicles and manned vehicles involved in the collision suspend running; when there is a third - level warning, the relevant harbour crane, driverless vehicles, and manned vehicles involved in the collision suspend running; if there is no safety warning, enter the next loop for detection.

[0034] Furthermore, the vehicle - to - vehicle safety risk identification in step 2.2.4 includes the following steps:

[0035] Step ①: Establish a virtual circular range for vehicle safety warning, that is, a circular safety warning range with a warning radius R1 centered on the geometric center of the vehicle, where the warning radius R1=(Rmax < K / TTC1)? Rmax : K / TTC1, where Rmax is the maximum warning radius value preset according to the vehicle type, and K is the warning radius constant set according to the actual situation;

[0036] Step ②, calculate the vehicle safety warning level WarnL and warning radius R1, WarnL = (L1 ≥ K / TTC1)? 1: ((L2 ≥ K / TTC1)? 2: 3), where L1 is the level 1 warning threshold, L2 is the level 2 warning threshold, and K is the warning radius constant, which is set according to the actual situation, with a maximum of level 3 warning;

[0037] Step 3: Determine the current safety collision level. If there is a safety warning, generate a graded safety scheduling strategy according to the warning level. When the warning is level 1, the relevant autonomous driving vehicles slow down or adjust their routes; when the warning is level 2, the collision-related autonomous driving vehicles suspend operation; when the warning is level 3, the collision-related autonomous driving vehicles and non-autonomous driving vehicles suspend operation; if there is no safety warning, enter the next step of cyclic detection.

[0038] Definition: In the field of traffic safety and autonomous driving, Time To Collision (TTC) is a crucial indicator that measures the time interval between two objects before they collide, thus providing a basis for decision-making to avoid collisions. The TTC value is calculated by dividing the relative distance between two objects by their relative speed. The following is a detailed introduction to its calculation method:

[0039] Determine the reference point: A reference point needs to be determined, usually the front edge of a relatively stationary object or a reference point, to calculate the distance.

[0040] Calculate relative speed: Get the speed of two objects, and then calculate the relative distance between them based on the current positions of the objects.

[0041] Calculate TTC value: When relative speed and distance are known, TTC can be calculated by the formula TTC = (Relative_Distance / Relative_Velocity), where relative distance is the distance between the reference point and the other object, and relative velocity is the difference between the velocities of the two objects.

[0042] By adopting the above technical solution, the beneficial effects of the present invention are as follows:

[0043] 1. It integrates various types of data and roadside fusion perception of vehicle status, and restores the established scene simulation to a real-time traffic status diagram, thereby achieving accurate risk prediction and solving the problem of insufficient prediction capability of a single device;

[0044] 2. Through roadside fusion, the real-time vehicle movement status of the road is perceived. At the same time, the status of unmanned vehicles and port machinery operation status are connected to judge the safety risks of vehicles and port machinery, and the safety risks of unmanned vehicles and manned vehicles respectively, so as to make the risks specific and improve the accuracy and reliability of port risk identification and early warning;

[0045] 3. Use the rule library to replace the model library to concretize and instantiate the uncertain and possibly biased predictions, use the rule items that have been verified in actual production to be effective for risk warning, and do not rely on the prediction model of specific conditions. The risk warning has high accuracy and low false alarm rate;

[0046] 4. The rules in the rule base can be flexibly adjusted to be modified, supplemented, and deleted according to the actual verification situation, so that risk identification can be accurate and efficient, reduce the misjudgment rate, and improve the certainty of risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0048] Figure 1 It is a framework diagram of the early warning system of the present invention;

[0049] Figure 2 It is a flow chart of the early warning method of the present invention;

[0050] Figure 3 It is a schematic diagram of a real-time traffic status diagram in the early warning method of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, the port safety supervision and risk identification and early warning system includes a data acquisition module, a global status perception module, a risk identification module, an operation rule library, and a risk early warning module;

[0053] The data acquisition module is used to obtain the parameters and status data of unmanned vehicles, manned vehicles and port machinery equipment in the port area through network connection with TOS port operating system, ECS port automation equipment control system, TCS port cloud control dispatching system, external container truck management dispatching system, vehicle-mounted sensing equipment and road test sensing equipment;

[0054] The data of unmanned vehicles includes key information such as the vehicle’s location coordinates, travel speed, direction of travel, and various sensor data;

[0055] The data of manned vehicles includes detailed information such as the driving status, fuel consumption, and fault alarms of the vehicles;

[0056] The data of port machinery equipment includes key data such as the operating status, operating efficiency, and fault warning of port machinery equipment such as cranes and loaders.

[0057] The global state perception module is used to integrate and analyze various types of traffic data collected by the data acquisition module to generate a real-time traffic state diagram to provide data support for traffic management, scheduling and decision-making; various types of traffic data include but are not limited to vehicle location, speed, driving direction, sensor data, fuel consumption, fault information, and the operating status and operating efficiency of port machinery equipment. The traffic state diagram can comprehensively and intuitively reflect the overall operating status of the current traffic system, providing strong data support for traffic management, scheduling and decision-making;

[0058] The risk identification module is used to perform calculations and logical analysis based on the data from the data acquisition module and the global state perception module, identify and evaluate potential risk factors, and provide support for subsequent risk management and decision-making;

[0059] The operation rule library stores various rules and standards that are crucial to port operations, providing support for vehicle driving predictions and port machinery equipment operation predictions in the port. The operation rule library contains detailed port traffic rules to guide the safe driving and dispatching of vehicles in the port area; at the same time, it also includes port machinery operation rules, providing clear guiding principles and operating procedures for the operation of key equipment such as cranes and loaders, so as to ensure the smooth progress and efficient management of port operations;

[0060] The risk warning module is used to rate the risk factors identified by the risk identification module, and to issue different warning reminders according to the risk level, so as to provide timely risk information to managers. At the same time, it provides decision-making guidance according to the risk status and helps to formulate effective risk response strategies.

[0061] In this embodiment, when the risk level is at the highest, the risk warning module can directly issue instructions to vehicles in the port area to reduce the occurrence of safety risk accidents.

[0062] In this embodiment, the operating rules and standards in the operating rule library can be modified, supplemented and deleted in real time, ensuring the perfection of the operating rule library, making the overall risk prediction in the best state, and improving the risk recognition rate and accuracy.

[0063] The port safety supervision and risk identification and warning system of the present invention is deployed in the same network as the road test sensing system. The safety supervision and risk warning are connected with the vehicle-mounted sensing equipment and the road test sensing equipment through the local area network to obtain real-time equipment data and port machinery status data, and the movement status of unmanned vehicles and manned vehicles is sensed through the roadside sensing system. Among them, the business status data of unmanned vehicles and manned vehicles are directly connected to the port safety supervision and risk identification and warning system.

[0064] like Figure 2-Figure 3 As shown in the figure, the port safety supervision and risk identification and early warning method includes the following steps:

[0065] Step 1: Build a virtual traffic real-time status diagram,

[0066] Step 1.1: Virtual environment scene simulation, collect and establish port infrastructure model, including yard, berth, road, roadside facilities, port machinery equipment, roadside sensing equipment model;

[0067] Step 1.2: Business action scenario simulation, establish container and port machinery circulation process models, unmanned vehicle and manned vehicle transportation process models, and construct business motion scenario models from the circulation process model and operation process model;

[0068] Step 1.3, simulate the virtual traffic real-time state diagram, establish the vehicle-to-vehicle safety conflict mechanism, vehicle-to-port machinery conflict handling mechanism, vehicle anomaly handling mechanism, and port machinery anomaly handling mechanism, and provide an operating mechanism for the virtual traffic real-time state diagram;

[0069] Step 2: The data collected by the data collection module is restored to a real-time traffic status map, and the risk identification module determines the type of safety risk.

[0070] Step 2.1, receive real-time business data, obtain the operation status of port machinery, ships, containers, real-time transportation status of unmanned vehicles and manned vehicles, and roadside fusion perception data, map the data to the risk warning module, and determine whether to trigger the early warning alarm. If yes, output it to the risk warning module and then go to the next step. If not, directly go to the next step loop;

[0071] Step 2.2: Safety scheduling simulation to determine the horizontal and longitudinal operation of each port machinery and the conflicts between the routes of unmanned vehicles and manned vehicles and identify potential collision risks;

[0072] Step 2.2.1, extract the motion state and operation motion route of each port machinery, the motion state includes relative position (x, y, z), speed v, direction h, the motion state of each unmanned vehicle Pos_i (lon_i, lat_i, ele_i), speed vi, acceleration ai, direction heading_i and planned path {pt_j (lon_j, lat_j, ele_j)}, the motion state of each manned vehicle Pos_ii (lon_ii, lat_ii, ele_ii), speed vii, acceleration aii, direction heading_ii and planned path {pt_jj (lon_jj, lat_jj, ele_jj)};

[0073] Step 2.2.2, convert the port machinery motion state and route into three-dimensional space coordinate system coordinate points with the port machinery high-precision equipment positioning installation point as the center, the three-dimensional coordinate position of the port machinery operating arm pt0 (lon0, lat0, ele0), speed v0, direction heading0, and the port machinery motion route point set {pt_k (lon_k, lat_k, ele_k)};

[0074] Step 2.2.3, identify the safety risks of vehicles and port machinery, calculate the early warning TTC0 of a port machinery, TTC0 = min{TTCi}, i = 1 ~ N, N is the unmanned vehicle close to the port machinery at the current moment, TTCi is the potential collision time between the port machinery and each unmanned vehicle and manned vehicle calculated according to the current position, speed, direction and trajectory, where TTC refers to the collision time, and whether to trigger the vehicle and port machinery safety warning threshold is determined based on the collision time TTC;

[0075] Step 2.2.4, vehicle-to-vehicle safety risk identification: calculate the warning TTC1 of the unmanned vehicle and other vehicles, TTC1 = min{TTCi}, i = 1 ~ N, N is the number of other vehicles close to the unmanned vehicle, TTCi is the potential collision time between the unmanned vehicle and other vehicles calculated based on the current position, speed, direction and trajectory, and determine whether to trigger the vehicle-to-vehicle safety warning threshold based on the collision time TTC;

[0076] Step 2.2.5, single port machinery equipment risk safety identification: based on the rule base entry traversal search to determine whether to trigger a single port machinery safety warning, if the port machinery movement state, its own state inspection results and the rules and standards in the rule base, then trigger a safety warning;

[0077] Step 2.2.6, single-vehicle risk safety identification, based on the rule base entry traversal search to determine whether to trigger a single-vehicle safety warning, if the vehicle's motion state and its own state inspection results are different from the rules and standards in the rule base, a safety warning is triggered;

[0078] Step 3: Output the warning risk and warning level, and repeat to execute the next loop for monitoring and determination.

[0079] In this embodiment, the vehicle and port crane safety risk identification in step 2.2.3 includes the following steps:

[0080] Step a: Establish a safety warning potential field for the port crane, that is, a spherical safety warning potential field with a warning radius R0 centered on the operating arm of the port crane, where the warning radius R0 = (Rmax < K / TTC0)? Rmax: K / TTC0, where Rmax is the maximum warning radius value preset according to the characteristics of the port crane, and K is the warning radius constant set according to the actual situation;

[0081] Step b: Calculate the warning level WarnL0 and warning radius R0 of the port crane, WarnL0 = (L1 ≥ K / TTC0)? 1: ((L2 ≥ K / TTC0)? 2: 3), where L1 is the first-level warning threshold, L2 is the second-level warning threshold, K is the warning radius constant set according to the actual situation, and the maximum is the third-level warning;

[0082] Step c: Judge the current safety collision level. If there is a safety warning, generate a hierarchical safety scheduling strategy according to the warning level. When there is a first-level warning, relevant driverless vehicles and manned vehicles decelerate or the driverless vehicle adjusts its route to run; when there is a second-level warning, the relevant driverless vehicles and manned vehicles involved in the collision suspend operation; when there is a third-level warning, the relevant port crane, driverless vehicles, and manned vehicles involved in the collision suspend operation; if there is no safety warning, enter the next loop detection.

[0083] In this embodiment, the vehicle and vehicle safety risk identification in step 2.2.4 includes the following steps:

[0084] Step ①: Establish a virtual circular range for vehicle safety warning, that is, a circular safety warning range with a warning radius R1 centered on the geometric center of the vehicle, where the warning radius R1 = (Rmax < K / TTC1)? Rmax: K / TTC1, where Rmax is the maximum warning radius value preset according to the vehicle type, and K is the warning radius constant set according to the actual situation;

[0085] Step ②: Calculate the vehicle safety warning level WarnL and warning radius R1, WarnL = (L1 ≥ K / TTC1)? 1: ((L2 ≥ K / TTC1)? 2: 3), where L1 is the first-level warning threshold, L2 is the second-level warning threshold, K is the warning radius constant set according to the actual situation, and the maximum is the third-level warning;

[0086] Step 3: Determine the current safety collision level. If there is a safety warning, generate a graded safety scheduling strategy according to the warning level. When the warning is level 1, the relevant autonomous driving vehicles slow down or adjust their routes; when the warning is level 2, the collision-related autonomous driving vehicles suspend operation; when the warning is level 3, the collision-related autonomous driving vehicles and non-autonomous driving vehicles suspend operation; if there is no safety warning, enter the next step of cyclic detection.

[0087] In this embodiment, the risk safety identification of single port machinery equipment in step 2.2.5 is judged and identified based on the rules in the rule base. The rules for single port machinery equipment in the rule base include the working swing amplitude P, the hoisting equipment stress F value, whether it is moving during lifting, whether the gantry crane camera is online, whether the gantry crane wind speed sensor is online, whether the gantry crane laser alignment instrument is online, whether the bridge crane camera is online, whether the bridge crane plc is online, whether the corresponding lanes are closed during the operation of the bridge crane / gantry crane, etc. By comparing the movement of the single port machinery equipment with the rules in the rule base, it is determined whether the safety warning of the single port machinery is triggered. Specific rules can be added, modified, and deleted according to the actual operation of the port.

[0088] The criteria for judging several situations are as follows:

[0089] (i) The swing amplitude P when a single device is working. When the swing amplitude exceeds the threshold value P>P0 when a single device is working, an early warning message is triggered, where P0 is a constant;

[0090] (ii) The stress F value of the sling. When the stress F value of the sling clamp is abnormal when the goods are being lifted, it is determined that there is a risk of the goods falling, and an early warning message is issued; for example: F<Fmin,F> Fmax, where Fmin is the minimum threshold of fixture stress and Fmax is the maximum threshold of fixture stress;

[0091] (iii) Whether the clamp is holding the goods when it is lifted or lowered during movement is judged. If the single-unit equipment in motion is grabbing the goods, an early warning message is issued.

[0092] In this embodiment, the step 2.2.6, the single-vehicle risk safety identification, is judged and identified based on the rules in the rule base. The rules for vehicles in the rule base include whether there is an abnormality in the frequency of data reported by the vehicle-side equipment, whether the value reported by the vehicle-side equipment is within the range set by the rule base, whether the vehicle driving conflicts with the operating rules, etc. to determine whether to trigger a single-vehicle safety warning. Specific rules can be added, modified, and deleted according to the actual operation of the port.

[0093] The criteria for judging several situations are as follows:

[0094] (1) If the vehicle-side equipment reports data at an abnormal frequency, such as the original reporting frequency of 1s / time, but now no reporting occurs, or the reporting frequency is abnormal, an early warning message may be issued;

[0095] (2) If the value reported by the vehicle-side device does not meet the range set by the rule library, a warning message can be issued;

[0096] (3) If the vehicle's driving conflicts with the operating rules, an early warning message can be issued, such as: the vehicle does not drive according to the signs, drives in the wrong direction, occupies a turn, or changes lanes illegally.

[0097] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. Port safety supervision and risk identification and early warning system, characterized by: It includes data collection module, global status perception module, risk identification module, operation rule library and risk warning module; The data acquisition module is used to connect with the TOS port operating system, ECS port automation equipment control system, TCS port cloud control dispatching system, external container truck management dispatching system, vehicle-mounted sensing equipment, and road test sensing equipment to obtain the parameters and status data of unmanned vehicles, manned vehicles, and port machinery equipment in the port area; The global state perception module is used to integrate and analyze various types of traffic data collected by the data acquisition module to generate a real-time traffic state map to provide data support for traffic management, scheduling and decision-making; The risk identification module is used to perform calculations and logical analysis based on the data from the data acquisition module and the global state perception module, identify and evaluate potential risk factors, and provide support for subsequent risk management and decision-making; The operation rule library stores various rules and standards that are crucial to port operations, providing support for vehicle travel predictions and port machinery equipment operation predictions within the port; The risk warning module is used to rate the risk factors identified by the risk identification module, and to issue different warning reminders according to the risk level, so as to provide timely risk information to managers. At the same time, it provides decision-making guidance according to the risk status and helps to formulate effective risk response strategies.

2. The port safety supervision and risk identification and early warning system according to claim 1 is characterized by: When the risk level is at the highest, the risk warning module can directly issue instructions to vehicles in the port area to reduce the occurrence of safety risk accidents.

3. The port safety supervision and risk identification and early warning system according to claim 1 is characterized by: The operation rules and standards in the operation rule library can be modified, supplemented and deleted in real time.

4. Port safety supervision and risk identification and early warning system, characterized by: The following steps are involved: Step 1: Build a virtual traffic real-time status diagram, Step 1.1: Virtual environment scene simulation, collect and establish port infrastructure model, including yard, berth, road, roadside facilities, port machinery equipment, roadside sensing equipment model; Step 1.2: Business action scenario simulation, establish container and port machinery circulation process models, unmanned vehicle and manned vehicle transportation process models, and construct business motion scenario models from the circulation process model and operation process model; Step 1.3, simulate the virtual traffic real-time state diagram, establish the vehicle-to-vehicle safety conflict mechanism, vehicle-to-port machinery conflict handling mechanism, vehicle anomaly handling mechanism, and port machinery anomaly handling mechanism, and provide an operating mechanism for the virtual traffic real-time state diagram; Step 2: The data collected by the data collection module is restored to a real-time traffic status map, and the risk identification module determines the type of safety risk. Step 2.1, receive real-time business data, obtain the operation status of port machinery, ships, containers, real-time transportation status of unmanned vehicles and manned vehicles, and roadside fusion perception data, map the data to the risk warning module, and determine whether to trigger the early warning alarm. If yes, output it to the risk warning module and then go to the next step. If not, directly go to the next step loop; Step 2.2: Safety scheduling simulation to determine the horizontal and longitudinal operation of each port machinery and the conflicts between the routes of unmanned vehicles and manned vehicles and identify potential collision risks; Step 2.2.1, extract the motion state and operation motion route of each port machinery, the motion state includes relative position (x, y, z), speed v, direction h, the motion state of each unmanned vehicle Pos_i (lon_i, lat_i, ele_i), speed vi, acceleration ai, direction heading_i and planned path {pt_j (lon_j, lat_j, ele_j)}, the motion state of each manned vehicle Pos_ii (lon_ii, lat_ii, ele_ii), speed vii, acceleration aii, direction heading_ii and planned path {pt_jj (lon_jj, lat_jj, ele_jj)}; Step 2.2.2, convert the port machinery motion state and route into three-dimensional space coordinate system coordinate points with the port machinery high-precision equipment positioning installation point as the center, the three-dimensional coordinate position of the port machinery operating arm pt0 (lon0, lat0, ele0), speed v0, direction heading0, and the port machinery motion route point set {pt_k (lon_k, lat_k, ele_k)}; Step 2.2.3, identify the safety risks of vehicles and port machinery, calculate the early warning TTC0 of a port machinery, TTC0 = min{TTCi}, i = 1 ~ N, N is the unmanned vehicle close to the port machinery at the current moment, TTCi is the potential collision time between the port machinery and each unmanned vehicle and manned vehicle calculated according to the current position, speed, direction and trajectory, where TTC refers to the collision time, and whether to trigger the vehicle and port machinery safety warning threshold is determined based on the collision time TTC; Step 2.2.4, vehicle-to-vehicle safety risk identification: calculate the warning TTC1 of the unmanned vehicle and other vehicles, TTC1 = min{TTCi}, i = 1 ~ N, N is the number of other vehicles close to the unmanned vehicle, TTCi is the potential collision time between the unmanned vehicle and other vehicles calculated based on the current position, speed, direction and trajectory, and determine whether to trigger the vehicle-to-vehicle safety warning threshold based on the collision time TTC; Step 2.2.5, single port machinery equipment risk safety identification: based on the rule base entry traversal search to determine whether to trigger a single port machinery safety warning, if the port machinery movement state, its own state inspection results and the rules and standards in the rule base, then trigger a safety warning; Step 2.2.6, single-vehicle risk safety identification, based on the rule base entry traversal search to determine whether to trigger a single-vehicle safety warning, if the vehicle's motion state and its own state inspection results are different from the rules and standards in the rule base, a safety warning is triggered; Step 3: Output the alarm risk and alarm level, and repeat the next cycle monitoring judgment.

5. The port safety supervision and risk identification and early warning method according to claim 4 is characterized by: The vehicle and port machinery safety risk identification in step 2.2.3 includes the following steps: Step a: Establish a safety warning potential field for the port machine, that is, a spherical safety warning potential field with a warning radius R0 centered on the operation arm of the port machine. Here, the warning radius R0 = (Rmax < K / TTC0)? Rmax : K / TTC0, where Rmax is the maximum warning radius value preset according to the characteristics of the port machine, and K is the warning radius constant set according to the actual situation; Step b: Calculate the warning level WarnL0 and warning radius R0 of the port machine. WarnL0 = (L1 ≥ K / TTC0)? 1 : ((L2 ≥ K / TTC0)? 2 : 3), where L1 is the first-level warning threshold, L2 is the second-level warning threshold, K is the warning radius constant set according to the actual situation, and the maximum is the third-level warning; Step c: Judge the current safety collision level. If there is a safety warning, generate a hierarchical safety scheduling strategy according to the warning level. When there is a first-level warning, relevant driverless vehicles and manned vehicles decelerate or the driverless vehicle adjusts its route to run; when there is a second-level warning, the relevant driverless vehicles and manned vehicles involved in the collision suspend operation; when there is a third-level warning, the relevant port machines, driverless vehicles, and manned vehicles involved in the collision suspend operation; if there is no safety warning, enter the next cycle of detection.

6. The port safety supervision and risk identification and early warning method according to claim 4 is characterized by: In the vehicle-vehicle safety risk identification in step 2.2.4, it includes the following steps: Step ①: Establish a virtual circular range for vehicle safety warning, that is, a circular safety warning range with a warning radius R1 centered on the geometric center of the vehicle. Here, the warning radius R1 = (Rmax < K / TTC1)? Rmax : K / TTC1, where Rmax is the maximum warning radius value preset according to the vehicle type, and K is the warning radius constant set according to the actual situation; Step ②: Calculate the vehicle safety warning level WarnL and warning radius R1. WarnL = (L1 ≥ K / TTC1)? 1 : ((L2 ≥ K / TTC1)? 2 : 3), where L1 is the first-level warning threshold, L2 is the second-level warning threshold, K is the warning radius constant set according to the actual situation, and the maximum is the third-level warning; Step ③: Judge the current safety collision level. If there is a safety warning, generate a hierarchical safety scheduling strategy according to the warning level. When there is a first-level warning, the relevant autonomous vehicles decelerate or adjust their routes to run; when there is a second-level warning, the relevant autonomous vehicles involved in the collision suspend operation; when there is a third-level warning, the relevant autonomous vehicles and non-autonomous vehicles involved in the collision suspend operation; if there is no safety warning, enter the next cycle of detection.

Images