A logistics site safety inspection intelligent inspection system, method and device

Abstract

The present invention provides an intelligent inspection system, method, and device for logistics site safety inspections, relating to the technical field of logistics site safety inspections. The system primarily comprises a data acquisition module, a data processing module, and a result generation module. The data acquisition module includes a road condition image unit, a GPS navigation unit, a three-dimensional model unit, an IMU inertial unit, and a sensor unit. The data processing module includes a cargo overturning risk assessment unit and a curve passability risk assessment unit. This solution enables intelligent inspection and early warning of safety issues at logistics sites, and is particularly suitable for providing early warning of risks such as cargo overturning, curve passability, overheight, and overweight during the transportation of large cargo, thereby effectively preventing major safety accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics site safety inspection, and in particular to an intelligent inspection system, method and device for logistics site safety inspection. Background Art

[0002] Logistics site safety refers to the comprehensive state of protecting personnel, goods, equipment and the environment from harm through systematic risk management and control measures in logistics operation sites such as cargo transportation, loading and unloading, warehousing, and transit.

[0003] In large-scale logistics scenarios (such as wind turbine blades, tunnel boring machines, chemical reaction towers, etc.), tractors and trailers are often required for low-speed, long-distance transportation, and higher requirements are placed on on-site safety. This requires consideration of the physical risks of the goods themselves (such as overturning due to failure of cargo fixation), dynamic risks during transportation (such as obstructions when turning on bends, etc.), and transportation compliance risks (such as overheight, overweight, etc.).

[0004] How to comprehensively consider the risk factors of large-scale logistics and provide effective and rapid early warnings for risk accidents, thereby avoiding major accidents and quality problems, is a major issue that needs to be urgently addressed in this field. Summary of the Invention

[0005] The object of the present invention is to provide a logistics site safety inspection intelligent inspection system, method and device to solve at least one of the above-mentioned technical problems existing in the prior art.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a logistics site safety inspection intelligent inspection system, including a data acquisition module, a data processing module and a result generation module;

[0007] The data acquisition module includes a road condition image unit, a GPS (Global Positioning System) navigation unit, a three-dimensional model unit, an IMU (Inertial Measurement Unit) inertial unit and a sensor unit;

[0008] The road condition image unit is used to collect road condition images at preset inspection locations; the road condition images include bridge images, tunnel images, and curve images, etc.; the preset inspection locations include bridge entrances, tunnel entrances, and curve entrances, etc.;

[0009] The GPS navigation unit is used to collect the transportation route, coordinates and speed of the transportation vehicle;

[0010] The three-dimensional model unit is used to receive a three-dimensional model of cargo and a three-dimensional model of a transport vehicle; the three-dimensional model of cargo includes cargo dimensions, cargo weight, and cargo center of gravity; the three-dimensional model of the transport vehicle includes transport vehicle dimensions, transport vehicle weight, transport vehicle center of gravity, minimum turning radius, tractor wheelbase (distance from the tractor front axle to the hinge point), and trailer wheelbase (distance from the hinge point to the trailer rear axle).

[0011] The IMU inertial unit is used to collect inertial data of the transport vehicle; the inertial data of the transport vehicle includes acceleration, angular velocity and road slope angle, etc.;

[0012] The sensor unit is used to collect displacement sensor data and angle sensor data; the displacement sensor is used to detect the relative displacement between the cargo and the transport vehicle; the angle sensor is used to detect the angle between the tractor and the trailer in the transport vehicle;

[0013] The data processing module includes a cargo overturning risk assessment unit and a curve passability risk assessment unit;

[0014] The cargo overturning risk assessment unit is used to calculate the cargo center of gravity offset based on the cargo three-dimensional model and the transport vehicle three-dimensional model, combined with the transport vehicle inertia data and displacement sensor data collected in real time, through the center of gravity deviation model, determine the cargo overturning risk and generate corresponding instructions, so as to avoid the dangerous situation of cargo overturning;

[0015] The curve passability risk assessment unit is used to calculate the inner and outer diameters of the curve based on the real-time collected road condition images through image recognition methods, and then, based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route and the angle sensor data, and through the turn warning model, determine the risk of the transport vehicle being unable to pass the curve ahead and generate corresponding instructions, thereby avoiding the dangerous situation of the transport vehicle being stuck in the curve ahead;

[0016] The result generation module is used to send the output results of the data processing module.

[0017] In a feasible implementation manner, the road condition image unit collects road condition images through a binocular camera disposed on the head of the transport vehicle.

[0018] In a feasible embodiment, the displacement sensor is divided into a cargo end and a vehicle end, the cargo end is installed on the surface of the cargo, and the vehicle end is installed on the surface of the transport vehicle; the corresponding linear displacement between the two is measured through the principle of electromagnetic induction; in this way, by flexibly deploying multiple displacement sensors at multiple contact positions between the cargo and the transport vehicle, the relative displacement between the cargo and the transport vehicle can be detected in real time, thereby forming a closed-loop feedback for cargo overturning warning.

[0019] In a feasible implementation manner, the angle sensor is installed at a hinge point between a tractor and a trailer of a transport vehicle.

[0020] In a feasible implementation manner, the center of gravity deviation model includes:

[0021] The static center of gravity calculation formula is as follows:

[0022] ;

[0023] in, Indicates the static center of gravity of the cargo; 、 and They respectively represent the coordinates of the static center of gravity position in the world coordinate system; the x direction represents the front and rear direction of the transport vehicle; the y direction represents the left and right direction of the transport vehicle; and the z direction represents the up and down direction of the transport vehicle;

[0024] The inertia force offset formula is:

[0025] ;

[0026] in, Indicates the inertial force offset of the cargo; Indicates the quality of goods; Indicates the real-time acceleration of the transport vehicle; Indicates the suspension damping coefficient of the transport vehicle;

[0027] The centrifugal force offset formula is:

[0028] ;

[0029] in, Indicates the centrifugal force offset of the cargo (unit: kilogram), and the offset direction is perpendicular to the turning radius, pointing to the right when turning left and to the left when turning right; Indicates the speed of the transport vehicle (unit: m / s); Indicates the turning radius of the transport vehicle (unit: meter); Indicates the road slope angle (unit: rad, which can be read from the inertial data of the transport vehicle); is the magnitude of the centrifugal force; To take into account the slope correction factor of the curve;

[0030] The calculation formula for the total center of gravity position is as follows:

[0031] ;

[0032] in, Indicates the total center of gravity of the cargo;

[0033] The calculation formula of critical overturning angle is as follows:

[0034] ;

[0035] in, represents the critical overturning angle;

[0036] The real-time inclination calculation formula is as follows:

[0037] ;

[0038] in, Indicates the real-time inclination angle; Indicates the total center of gravity of the cargo in the y direction (transverse direction of the vehicle);

[0039] The formula for evaluating the cargo overturning risk level is as follows:

[0040] ;

[0041] in, Indicates the level of risk of cargo overturning.

[0042] In a feasible implementation, the center of gravity deviation model further includes mapping response strategies for risks at various levels, specifically including:

[0043] For level 0 risk, generate a proceed instruction;

[0044] For level 1 risk, a recommended deceleration instruction is generated;

[0045] For level 2 risks, generate audible and visual alarm instructions and automatic weak speed limit instructions (for example, less than 40km / h);

[0046] For level 3 risk, an automatic strong speed limit (e.g., less than 20 km / h) instruction is generated;

[0047] For level 4 risk, an emergency braking command and a cargo overturning rescue command are generated.

[0048] In a feasible implementation manner, the center of gravity deviation model further includes a displacement sensor collaborative verification formula, specifically:

[0049] ;

[0050] in, Indicates the final cargo overturning risk after the displacement sensor collaborative verification; Represents displacement sensor data; Indicates the baseline threshold of the displacement sensor data; Indicates the incremental step size of the risk level; in this way, the displacement sensor data (slippage) can be accurately mapped to the incremental risk of cargo overturning through a step function, ensuring that the risk level does not exceed level 4 risk.

[0051] In a feasible embodiment, the It is set to 5mm, which means that every 5mm of slippage corresponds to a level 1 increase in the risk of cargo overturning.

[0052] In a feasible implementation manner, the center of gravity deviation model further includes a displacement sensor data calibration formula, specifically:

[0053] ;

[0054] in, Represents the real data of the displacement sensor; Represents the original data of the displacement sensor; Indicates the temperature compensation coefficient (e.g. 1.0-1.2); Indicates zero drift compensation.

[0055] In a feasible implementation manner, the center of gravity deviation model further includes a dynamic threshold adjustment formula for displacement sensor data, specifically:

[0056] ;

[0057] in, Represents the lateral acceleration of the transport vehicle; this allows for automatic reduction of threshold sensitivity during high-speed cornering.

[0058] In a feasible implementation, the center of gravity deviation model further includes a historical data analysis formula for displacement sensor data and a corresponding cargo overturning risk level, specifically including:

[0059] ;

[0060] in, Indicates the trend value of displacement sensor data; Indicates the Displacement sensor data of historical sampling points (unit: mm); Indicates the Timestamp of each historical sampling point (unit: second); Indicates the current time; represents the time attenuation coefficient (can be 0.02); Indicates the total number of historical sampling points within the analysis window (60 is acceptable); Indicates the starting index of the sliding window; in this way, it is possible to focus on recent data and calculate the trend value of the displacement sensor data rather than the instantaneous value through exponentially weighted moving average, thereby suppressing data noise and avoiding false alarms;

[0061] ;

[0062] in, Indicates the rate of change of the trend value of the displacement sensor data; Indicates the calculation interval (10 seconds is acceptable); Indicates time;

[0063] And when When the trend value change rate is greater than the preset threshold, the second level of risk in the cargo overturning risk level is triggered.

[0064] In a feasible implementation manner, the time decay coefficient includes a vehicle speed compensation formula, specifically:

[0065] ;

[0066] in, represents the initial value of the time attenuation coefficient; Indicates the time attenuation coefficient compensation value; Indicates the speed of the transport vehicle (unit: km / h); in this way, when the speed is very fast, the historical weight can be reduced, thereby achieving the effect of early warning and increasing safety.

[0067] In a feasible implementation, the specific method for calculating the inner diameter and outer diameter of the curve includes:

[0068] Step a1: Construct the conversion relationship between the image coordinate system and the world coordinate system. The specific expression is:

[0069] ;

[0070] in, Represents the homography matrix (which can be obtained through camera calibration) and satisfies:

[0071] ;

[0072] in, Indicates the x-axis rotation scaling factor; Indicates the y-axis rotation scaling factor; Indicates the x-axis translation; Indicates the amount of translation in the y direction; Represents the x-direction perspective distortion coefficient; Indicates the y-direction perspective distortion coefficient; represents the xy coupling rotation coefficient; represents the yx coupling rotation coefficient;

[0073] Represents the x-coordinate value in the world coordinate system. The specific expression is:

[0074] ;

[0075] in, Represents the pixel coordinate value in the u direction (horizontally to the right) in the image coordinate system; Represents the pixel coordinate value in the v direction (vertically downward) in the image coordinate system;

[0076] Represents the coordinate value of the y direction in the world coordinate system. The specific expression is:

[0077] ;

[0078] Step a2: Based on the curved road image, extract the curved road contour through Canny edge detection; detect the straight line boundary through Hough transform; and fit the curve boundary equation through RANSAC algorithm. The specific expression is:

[0079] Left boundary equation: ;

[0080] Right boundary equation: ;

[0081] in, 、 and Parameters representing the left boundary equation; 、 and represents the parameters of the right boundary equation;

[0082] Step a3: At the bottom of the winding road image, Calculate the road width. The specific formula includes:

[0083] ;

[0084] in, Indicates the pixel width of the road; Indicates the right boundary of the bottom of the curved road image; Indicates the left boundary of the bottom of the curved road image;

[0085] ;

[0086] in, Indicates the actual width of the road; Indicates the scaling factor between pixels and meters (obtained through camera calibration);

[0087] Step a4: Calculate the curvature radius based on the trajectory point sequence of the transportation route. The specific formula includes:

[0088] Three-point curvature formula:

[0089] ;

[0090] in, represents curvature; Indicates the current track point With the previous trajectory point The Euclidean distance between Indicates the current track point and the next track point The Euclidean distance between represents the Euclidean distance between the previous trajectory point and the next trajectory point;

[0091] Curvature radius formula:

[0092] ;

[0093] in, represents the radius of curvature;

[0094] Step a5: Calculate the inner diameter of the curve and outer diameter , the specific formulas include:

[0095] ;

[0096] ;

[0097] in, Indicates safety margin (0.5 meters is acceptable).

[0098] In a feasible implementation, the turn warning model includes:

[0099] The instantaneous center of rotation equation is:

[0100] ;

[0101] in, Indicates the turning radius of the tractor; Indicates the turning radius of the trailer; Indicates the wheelbase of the tractor; Indicates the trailer wheelbase; Indicates the steering angle of the tractor (left turn is positive); Indicates the angle between the tractor and the trailer (angle sensor data can be read);

[0102] The dynamic equation of the hinge angle is:

[0103] ;

[0104] in, represents the rate of change of the articulation angle; Indicates time Derivative;

[0105] Left front corner of tractor ( , ) trajectory equation, specifically:

[0106] ;

[0107] in, It represents the turning angle of the tractor around the instantaneous turning center; Indicates the width of the tractor; represents the x-projection of the instantaneous turning center to the center of the tractor's front axle; represents the y-projection of the instantaneous turning center to the center of the tractor's front axle; Represents the projection of the tractor vehicle width component on the x-axis; It represents the projection of the tractor vehicle width component on the y-axis;

[0108] Right front corner of tractor ( , ) trajectory equation, specifically:

[0109] ;

[0110] Trailer left rear corner ( , ) trajectory equation, specifically:

[0111] ;

[0112] in, Indicates trailer width; represents the x-projection from the hinge point to the center of the trailer's rear axle (the negative sign indicates the rear); Represents the y-projection from the hinge point to the center of the trailer's rear axle; Represents the projection of the trailer width component on the x-axis (negative on the right); Represents the projection of the trailer width component on the y-axis;

[0113] Right rear corner of trailer ( , ) Trajectory equation:

[0114] ;

[0115] Safety pass judgment conditions, specifically:

[0116] ;

[0117] in, Indicates the The distance from the key points to the instantaneous turning center; the key points include the left front corner of the tractor, the right front corner of the tractor, the left rear corner of the trailer, and the right rear corner of the trailer;

[0118] Instruction generation strategy, specifically:

[0119] When the safety passing judgment conditions cannot be met, it means that the detour cannot be passed, and an instruction to change the transportation route is generated;

[0120] When the safe passing judgment condition is met, it means that the detour can be passed and a continue forward instruction is generated;

[0121] In this way, through the above-mentioned turning warning model, the tractor and trailer can be simplified into two rectangles connected by a hinge point. Then, the trajectory of the transport vehicle is simulated and a swept envelope of the front corner of the tractor and the rear corner of the trailer is generated. By judging whether the envelope line is within the safe area of ​​the road curve, it is determined whether the curve can be safely passed.

[0122] In a feasible embodiment, the data processing module also includes a bridge passability risk assessment unit, which is used to calculate the total weight based on the three-dimensional model of the cargo and the three-dimensional model of the transport vehicle, and then identify the weight limit signs in the road condition image through an image recognition method, determine the overweight risk of passing the bridge and generate corresponding instructions, thereby avoiding the dangerous situation of the transport vehicle exceeding the load-bearing capacity of the bridge.

[0123] In a feasible embodiment, the data processing module also includes a tunnel passability risk assessment unit, which is used to calculate the total height and total width based on the three-dimensional model of the cargo and the three-dimensional model of the transport vehicle, and then identify the height limit sign, the tunnel entrance outline and the distance between the transport vehicle and the tunnel entrance in the road condition image through an image recognition method; after calculating the actual height and actual width of the tunnel entrance, compare them with the total height and the total width, determine the risk of excessive height and excessive width when passing through the tunnel and generate corresponding instructions, so as to avoid the dangerous situation of cargo and transport vehicles colliding with the tunnel.

[0124] In a second aspect, based on the same inventive concept, the present application also provides a logistics site safety inspection intelligent inspection method, comprising:

[0125] Collecting road condition images at preset inspection locations through a road condition image unit;

[0126] Collect the transport route, coordinates and speed of the transport vehicle through the GPS navigation unit;

[0127] Receiving a three-dimensional model of the cargo and a three-dimensional model of the transport vehicle through a three-dimensional model unit;

[0128] Collect inertial data of transport vehicles through IMU inertial unit;

[0129] Collect displacement sensor data and angle sensor data through the sensor unit;

[0130] The cargo overturning risk assessment unit calculates the cargo center of gravity offset based on the cargo 3D model and the transport vehicle 3D model, combined with the real-time collected transport vehicle inertia data and displacement sensor data, and uses the center of gravity deviation model to determine the cargo overturning risk and generate corresponding instructions.

[0131] The curve passability risk assessment unit uses image recognition methods to calculate the inner and outer diameters of the curve based on real-time road condition images. Based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route, and angle sensor data, the curve warning model determines the risk of the transport vehicle being unable to pass the curve ahead and generates corresponding instructions.

[0132] The output results of the data processing module are sent out through the result generation module.

[0133] On the third aspect, based on the same inventive concept, the present application also provides a logistics site safety patrol intelligent inspection device, including a processor, a memory and a bus, the memory stores instructions and data read by the processor, the processor is used to call the instructions and data in the memory to realize the logistics site safety patrol intelligent inspection system as described above, and the bus connects the functional components for transmitting information.

[0134] In a feasible embodiment, the device further includes a binocular camera, which is arranged on the head of the transport vehicle and is used to collect road condition images.

[0135] In a feasible implementation manner, the device further includes a GPS module.

[0136] In a feasible implementation manner, the device further includes an IMU module.

[0137] In a feasible embodiment, the device also includes several displacement sensors; each displacement sensor is divided into a cargo end and a vehicle end; the cargo end is installed on the surface of the cargo, and the vehicle end is installed on the surface of the transport vehicle; the corresponding linear displacement between the two is measured through the principle of electromagnetic induction.

[0138] In a feasible embodiment, the device further includes an angle sensor installed at a hinge point between a tractor and a trailer of the transport vehicle.

[0139] By adopting the above technical solution, the present invention has the following beneficial effects:

[0140] The present invention provides an intelligent inspection system, method and device for logistics site safety inspections, which can perform intelligent inspections and early warnings on logistics site safety issues. It is particularly suitable for providing early warnings of risks such as cargo overturning, detour risks, overheight risks, and overweight risks during the transportation of large cargo, thereby effectively avoiding the occurrence of major safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0141] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0142] Figure 1 A diagram of an intelligent inspection system for on-site logistics safety inspections provided by an embodiment of the present invention;

[0143] Figure 2 A flowchart of a specific method for calculating the inner and outer diameters of a curve provided in an embodiment of the present invention;

[0144] Figure 3 A schematic diagram of a curve provided by an embodiment of the present invention;

[0145] Figure 4 A diagram of another intelligent inspection system for on-site logistics safety inspections provided by an embodiment of the present invention;

[0146] Figure 5 A diagram of another intelligent inspection system for logistics on-site safety inspections provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0147] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0148] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0149] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0150] The present invention will be further explained below with reference to specific embodiments.

[0151] It should also be noted that the following specific embodiments or specific implementations are a series of optimized settings listed in the present invention to further explain the specific content of the invention, and these settings can be combined or used in association with each other.

[0152] Example 1:

[0153] like Figure 1 As shown, this embodiment provides a logistics site safety inspection intelligent inspection system, including a data acquisition module, a data processing module and a result generation module;

[0154] The data acquisition module includes a road condition image unit, a GPS navigation unit, a three-dimensional model unit, an IMU inertial unit and a sensor unit;

[0155] The road condition image unit is used to collect road condition images at preset inspection locations; the road condition images include bridge images, tunnel images, and curve images, etc.; the preset inspection locations include bridge entrances, tunnel entrances, and curve entrances, etc.;

[0156] The GPS navigation unit is used to collect the transportation route, coordinates and speed of the transportation vehicle;

[0157] The three-dimensional model unit is used to receive a three-dimensional model of cargo and a three-dimensional model of a transport vehicle; the three-dimensional model of cargo includes cargo dimensions, cargo weight, and cargo center of gravity; the three-dimensional model of the transport vehicle includes transport vehicle dimensions, transport vehicle weight, transport vehicle center of gravity, minimum turning radius, tractor wheelbase (distance from the tractor front axle to the hinge point), and trailer wheelbase (distance from the hinge point to the trailer rear axle).

[0158] The IMU inertial unit is used to collect inertial data of the transport vehicle; the inertial data of the transport vehicle includes acceleration, angular velocity and road slope angle, etc.;

[0159] The sensor unit is used to collect displacement sensor data and angle sensor data; the displacement sensor is used to detect the relative displacement between the cargo and the transport vehicle; the angle sensor is used to detect the angle between the tractor and the trailer in the transport vehicle;

[0160] The data processing module includes a cargo overturning risk assessment unit and a curve passability risk assessment unit;

[0161] The cargo overturning risk assessment unit is used to calculate the cargo center of gravity offset based on the cargo three-dimensional model and the transport vehicle three-dimensional model, combined with the transport vehicle inertia data and displacement sensor data collected in real time, through the center of gravity deviation model, determine the cargo overturning risk and generate corresponding instructions, so as to avoid the dangerous situation of cargo overturning;

[0162] The curve passability risk assessment unit is used to calculate the inner and outer diameters of the curve based on the real-time collected road condition images through image recognition methods, and then, based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route and the angle sensor data, and through the turn warning model, determine the risk of the transport vehicle being unable to pass the curve ahead and generate corresponding instructions, thereby avoiding the dangerous situation of the transport vehicle being stuck in the curve ahead;

[0163] The result generation module is used to send the output results of the data processing module.

[0164] Furthermore, the road condition image unit collects road condition images through a binocular camera arranged on the head of the transport vehicle.

[0165] Furthermore, the displacement sensor is divided into a cargo end and a vehicle end, the cargo end is installed on the surface of the cargo, and the vehicle end is installed on the surface of the transport vehicle; the corresponding linear displacement between the two is measured through the principle of electromagnetic induction; in this way, by flexibly arranging multiple displacement sensors at multiple contact positions between the cargo and the transport vehicle, the relative displacement between the cargo and the transport vehicle can be detected in real time, thereby forming a closed-loop feedback for cargo overturning warning.

[0166] Furthermore, the angle sensor is installed at a hinge point between a tractor and a trailer of a transport vehicle.

[0167] Furthermore, the center of gravity deviation model includes:

[0168] The static center of gravity calculation formula is as follows:

[0169] ;

[0170] in, Indicates the static center of gravity of the cargo; 、 and They respectively represent the coordinates of the static center of gravity position in the world coordinate system; the x direction represents the front and rear direction of the transport vehicle; the y direction represents the left and right direction of the transport vehicle; and the z direction represents the up and down direction of the transport vehicle;

[0171] The inertia force offset formula is:

[0172] ;

[0173] in, Indicates the inertial force offset of the cargo; Indicates the quality of goods; Indicates the real-time acceleration of the transport vehicle; Indicates the suspension damping coefficient of the transport vehicle;

[0174] The centrifugal force offset formula is:

[0175] ;

[0176] in, Indicates the centrifugal force offset of the cargo (unit: kilogram), and the offset direction is perpendicular to the turning radius, pointing to the right when turning left and to the left when turning right; Indicates the speed of the transport vehicle (unit: m / s); Indicates the turning radius of the transport vehicle (unit: meter); Indicates the road slope angle (unit: rad, which can be read from the inertial data of the transport vehicle); is the magnitude of the centrifugal force; To take into account the slope correction factor of the curve;

[0177] The calculation formula for the total center of gravity position is as follows:

[0178] ;

[0179] in, Indicates the total center of gravity of the cargo;

[0180] The calculation formula of critical overturning angle is as follows:

[0181] ;

[0182] in, represents the critical overturning angle;

[0183] The real-time inclination calculation formula is as follows:

[0184] ;

[0185] in, Indicates the real-time inclination angle; Indicates the total center of gravity of the cargo in the y direction (transverse direction of the vehicle);

[0186] The formula for evaluating the cargo overturning risk level is as follows:

[0187] ;

[0188] in, Indicates the level of risk of cargo overturning.

[0189] Furthermore, the center of gravity deviation model also includes response strategies for mapping risks at various levels, specifically including:

[0190] For level 0 risk, generate a proceed instruction;

[0191] For level 1 risk, a recommended deceleration instruction is generated;

[0192] For level 2 risks, generate audible and visual alarm instructions and automatic weak speed limit instructions (for example, less than 40km / h);

[0193] For level 3 risk, an automatic strong speed limit (e.g., less than 20 km / h) instruction is generated;

[0194] For level 4 risk, an emergency braking command and a cargo overturning rescue command are generated.

[0195] Furthermore, the center of gravity deviation model also includes a displacement sensor collaborative verification formula, specifically:

[0196] ;

[0197] in, Indicates the final cargo overturning risk after the displacement sensor collaborative verification; Represents displacement sensor data; Indicates the baseline threshold of the displacement sensor data; Indicates the incremental step size of the risk level; in this way, the displacement sensor data (slippage) can be accurately mapped to the incremental risk of cargo overturning through a step function, ensuring that the risk level does not exceed level 4 risk.

[0198] Furthermore, the It is set to 5mm, which means that every 5mm of slippage corresponds to a level 1 increase in the risk of cargo overturning.

[0199] Furthermore, the center of gravity deviation model also includes a displacement sensor data calibration formula, specifically:

[0200] ;

[0201] in, Represents the real data of the displacement sensor; Represents the original data of the displacement sensor; Indicates the temperature compensation coefficient (e.g. 1.0-1.2); Indicates zero drift compensation.

[0202] Furthermore, the center of gravity deviation model also includes a dynamic threshold adjustment formula for displacement sensor data, specifically:

[0203] ;

[0204] in, Represents the lateral acceleration of the transport vehicle; this allows for automatic reduction of threshold sensitivity during high-speed cornering.

[0205] Furthermore, the center of gravity deviation model also includes a historical data analysis formula for displacement sensor data and a corresponding cargo overturning risk level, specifically including:

[0206] ;

[0207] in, Indicates the trend value of displacement sensor data; Indicates the Displacement sensor data of historical sampling points (unit: mm); Indicates the Timestamp of each historical sampling point (unit: second); Indicates the current time; represents the time attenuation coefficient (can be 0.02); Indicates the total number of historical sampling points within the analysis window (60 is acceptable); Indicates the starting index of the sliding window; in this way, it is possible to focus on recent data and calculate the trend value of the displacement sensor data rather than the instantaneous value through exponentially weighted moving average, thereby suppressing data noise and avoiding false alarms;

[0208] ;

[0209] in, Indicates the rate of change of the trend value of the displacement sensor data; Indicates the calculation interval (10 seconds is acceptable); Indicates time;

[0210] And when When the trend value change rate is greater than the preset threshold, the second level of risk in the cargo overturning risk level is triggered.

[0211] Furthermore, the time decay coefficient includes a vehicle speed compensation formula, specifically:

[0212] ;

[0213] in, represents the initial value of the time attenuation coefficient; Indicates the time attenuation coefficient compensation value; Indicates the speed of the transport vehicle (unit: km / h); in this way, when the speed is very fast, the historical weight can be reduced, thereby achieving the effect of early warning and increasing safety.

[0214] Further, if Figure 2 As shown in the figure, the specific method for calculating the inner and outer diameters of the curve includes:

[0215] Step a1: Construct the conversion relationship between the image coordinate system and the world coordinate system. The specific expression is:

[0216] ;

[0217] in, represents the homography matrix (obtained by camera calibration) and satisfies:

[0218] ;

[0219] in, Indicates the x-axis rotation scaling factor; Indicates the y-axis rotation scaling factor; Indicates the x-axis translation; Indicates the amount of translation in the y direction; Represents the x-direction perspective distortion coefficient; Indicates the y-direction perspective distortion coefficient; represents the xy coupling rotation coefficient; represents the yx coupling rotation coefficient;

[0220] Represents the x-coordinate value in the world coordinate system. The specific expression is:

[0221] ;

[0222] in, Represents the pixel coordinate value in the u direction (horizontally to the right) in the image coordinate system; Represents the pixel coordinate value in the v direction (vertically downward) in the image coordinate system;

[0223] Represents the coordinate value of the y direction in the world coordinate system. The specific expression is:

[0224] ;

[0225] Step a2: Based on the curved road image, extract the curved road contour through Canny edge detection; detect the straight line boundary through Hough transform; and fit the curve boundary equation through RANSAC algorithm. The specific expression is:

[0226] Left boundary equation: ;

[0227] Right boundary equation: ;

[0228] in, 、 and Parameters representing the left boundary equation; 、 and represents the parameters of the right boundary equation;

[0229] Step a3: At the bottom of the winding road image, Calculate the road width. The specific formula includes:

[0230] ;

[0231] in, Indicates the pixel width of the road; Indicates the right boundary of the bottom of the curved road image; Indicates the left boundary of the bottom of the curved road image;

[0232] ;

[0233] in, Indicates the actual width of the road; Indicates the scaling factor between pixels and meters (obtained through camera calibration);

[0234] Step a4: Calculate the curvature radius based on the trajectory point sequence of the transportation route. The specific formula includes:

[0235] Three-point curvature formula:

[0236] ;

[0237] in, represents curvature; Indicates the current track point With the previous trajectory point The Euclidean distance between Indicates the current track point and the next track point The Euclidean distance between represents the Euclidean distance between the previous trajectory point and the next trajectory point;

[0238] Curvature radius formula:

[0239] ;

[0240] in, represents the radius of curvature;

[0241] Step a5: Calculate the inner diameter of the curve and outer diameter , the specific formulas include:

[0242] ;

[0243] ;

[0244] in, Indicates safety margin (0.5 meters is acceptable).

[0245] Further, if Figure 3 As shown, the turn warning model includes:

[0246] The instantaneous center of rotation equation is:

[0247] ;

[0248] in, Indicates the turning radius of the tractor; Indicates the turning radius of the trailer; Indicates the wheelbase of the tractor; Indicates the trailer wheelbase; Indicates the steering angle of the tractor (left turn is positive); Indicates the angle between the tractor and the trailer (angle sensor data can be read);

[0249] The dynamic equation of the hinge angle is:

[0250] ;

[0251] in, represents the rate of change of the articulation angle; Indicates time Derivative;

[0252] Left front corner of tractor ( , ) trajectory equation, specifically:

[0253] ;

[0254] in, It represents the turning angle of the tractor around the instantaneous turning center; Indicates the width of the tractor; represents the x-projection of the instantaneous turning center to the center of the tractor's front axle; represents the y-projection of the instantaneous turning center to the center of the tractor's front axle; Represents the projection of the tractor vehicle width component on the x-axis; It represents the projection of the tractor vehicle width component on the y-axis;

[0255] Right front corner of tractor ( , ) trajectory equation, specifically:

[0256] ;

[0257] Trailer left rear corner ( , ) trajectory equation, specifically:

[0258] ;

[0259] in, Indicates trailer width; represents the x-projection from the hinge point to the center of the trailer's rear axle (the negative sign indicates the rear); Represents the y-projection from the hinge point to the center of the trailer's rear axle; Represents the projection of the trailer width component on the x-axis (negative on the right); Represents the projection of the trailer width component on the y-axis;

[0260] Right rear corner of trailer ( , ) Trajectory equation:

[0261] ;

[0262] Safety pass judgment conditions, specifically:

[0263] ;

[0264] in, Indicates the The distance from the key points to the instantaneous turning center; the key points include the left front corner of the tractor, the right front corner of the tractor, the left rear corner of the trailer, and the right rear corner of the trailer;

[0265] Instruction generation strategy, specifically:

[0266] When the safety passing judgment conditions cannot be met, it means that the detour cannot be passed, and an instruction to change the transportation route is generated;

[0267] When the safe passing judgment condition is met, it means that the detour can be passed and a continue forward instruction is generated;

[0268] In this way, through the above-mentioned turning warning model, the tractor and trailer can be simplified into two rectangles connected by a hinge point. Then, the trajectory of the transport vehicle is simulated and a swept envelope of the front corner of the tractor and the rear corner of the trailer is generated. By judging whether the envelope line is within the safe area of ​​the road curve, it is determined whether the curve can be safely passed.

[0269] Example 2:

[0270] like Figure 4 As shown, based on the first embodiment, this embodiment adds a bridge passability risk assessment unit to the data processing module, which is used to calculate the total weight based on the three-dimensional model of the cargo and the three-dimensional model of the transport vehicle, and then use conventional image recognition methods to identify the weight limit signs in the road condition image, determine the overweight risk of passing the bridge and generate corresponding instructions, so as to avoid the dangerous situation of the transport vehicle exceeding the load-bearing capacity of the bridge.

[0271] Example 3:

[0272] like Figure 5 As shown, based on the second embodiment, this embodiment adds a tunnel passability risk assessment unit to the data processing module, which is used to calculate the total height and total width based on the three-dimensional model of the cargo and the three-dimensional model of the transport vehicle, and then identify the height limit sign, the tunnel entrance outline and the distance between the transport vehicle and the tunnel entrance in the road condition image through a conventional image recognition method; after calculating the actual height and actual width of the tunnel entrance, compare them with the total height and the total width, determine the risk of excessive height and excessive width when passing through the tunnel and generate corresponding instructions, thereby avoiding the dangerous situation of cargo and transport vehicles colliding with the tunnel.

[0273] Example 4:

[0274] This embodiment provides a logistics site safety inspection intelligent inspection method, including:

[0275] Collecting road condition images at preset inspection locations through a road condition image unit;

[0276] Collect the transport route, coordinates and speed of the transport vehicle through the GPS navigation unit;

[0277] Receiving a three-dimensional model of the cargo and a three-dimensional model of the transport vehicle through a three-dimensional model unit;

[0278] Collect inertial data of transport vehicles through IMU inertial unit;

[0279] Collect displacement sensor data and angle sensor data through the sensor unit;

[0280] The cargo overturning risk assessment unit calculates the cargo center of gravity offset based on the cargo 3D model and the transport vehicle 3D model, combined with the real-time collected transport vehicle inertia data and displacement sensor data, and uses the center of gravity deviation model to determine the cargo overturning risk and generate corresponding instructions.

[0281] The curve passability risk assessment unit uses image recognition methods to calculate the inner and outer diameters of the curve based on real-time road condition images. Based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route, and angle sensor data, the curve warning model determines the risk of the transport vehicle being unable to pass the curve ahead and generates corresponding instructions.

[0282] The output results of the data processing module are sent out through the result generation module.

[0283] Embodiment 5:

[0284] This embodiment provides an intelligent inspection device for logistics site safety inspection, including a processor, a memory and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory to implement the logistics site safety inspection intelligent inspection system as described above. The bus connects the functional components to transmit information.

[0285] Furthermore, the device also includes a binocular camera, which is arranged on the head of the transport vehicle and is used to collect road condition images.

[0286] Furthermore, the device also includes a GPS module.

[0287] Furthermore, the device also includes an IMU module.

[0288] Furthermore, the device also includes several displacement sensors; each displacement sensor is divided into a cargo end and a vehicle end; the cargo end is installed on the surface of the cargo, and the vehicle end is installed on the surface of the transport vehicle; the corresponding linear displacement between the two is measured through the principle of electromagnetic induction.

[0289] Furthermore, the device also includes an angle sensor installed at the hinge point between the tractor and the trailer of the transport vehicle.

[0290] Furthermore, the device also includes a display screen.

[0291] In another embodiment, this solution can be implemented using a portable, integrated device that can include modules for performing each or several of the steps described in the above embodiments. The device can also be temporarily secured within the cab of a transport vehicle. The modules can be one or more hardware modules specifically configured to perform the corresponding steps, or implemented by a processor configured to perform the corresponding steps, or stored on a computer-readable medium for execution by the processor, or implemented by some combination thereof.

[0292] The processor performs the various methods and processes described above. For example, the method implementation in this solution can be implemented as a software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods by any other appropriate means (e.g., by means of firmware).

[0293] The device can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus connects various circuits including one or more processors, memories, and / or hardware modules. The bus can also connect various other circuits such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0294] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0295] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logistics site safety inspection intelligent inspection system, characterized by: It includes data acquisition module, data processing module and result generation module; The data acquisition module includes a road condition image unit, a GPS navigation unit, a three-dimensional model unit, an IMU inertial unit and a sensor unit; The road condition image unit is used to collect road condition images at preset inspection locations; the road condition images include bridge images, tunnel images, and curve images; the preset inspection locations include bridge entrances, tunnel entrances, and curve entrances; The GPS navigation unit is used to collect the transport route, coordinates and speed of the transport vehicle; The three-dimensional model unit is used to receive a three-dimensional model of cargo and a three-dimensional model of a transport vehicle; the three-dimensional model of cargo includes cargo size, cargo weight and cargo center of gravity; the three-dimensional model of transport vehicle includes transport vehicle size, transport vehicle weight, transport vehicle center of gravity, minimum turning radius, tractor wheelbase and trailer wheelbase; The IMU inertial unit is used to collect inertial data of the transport vehicle; the inertial data of the transport vehicle includes acceleration, angular velocity and road slope angle; The sensor unit is used to collect displacement sensor data and angle sensor data; the displacement sensor is used to detect the relative displacement between the cargo and the transport vehicle; the angle sensor is used to detect the angle between the tractor and the trailer in the transport vehicle; The data processing module includes a cargo overturning risk assessment unit and a curve passability risk assessment unit; The cargo overturning risk assessment unit is used to calculate the cargo center of gravity offset based on the cargo three-dimensional model and the transport vehicle three-dimensional model, combined with the transport vehicle inertia data and displacement sensor data collected in real time, through the center of gravity deviation model, to determine the cargo overturning risk and generate corresponding instructions; The center of gravity deviation model includes: The static center of gravity calculation formula is as follows: ； in, Indicates the static center of gravity of the cargo; 、 and They respectively represent the coordinates of the static center of gravity position in the world coordinate system; the x direction represents the front and rear direction of the transport vehicle; the y direction represents the left and right direction of the transport vehicle; and the z direction represents the up and down direction of the transport vehicle; The inertia force offset formula is: ； in, Indicates the inertial force offset of the cargo; Indicates the quality of goods; Indicates the real-time acceleration of the transport vehicle; Indicates the suspension damping coefficient of the transport vehicle; The centrifugal force offset formula is: ； in, Indicates the centrifugal force offset of the cargo, and the offset direction is perpendicular to the turning radius, pointing to the right when turning left and to the left when turning right; Indicates the speed of the transport vehicle; Indicates the turning radius of the transport vehicle; Indicates the road slope angle; is the magnitude of the centrifugal force; To take into account the slope correction factor of the curve; The calculation formula for the total center of gravity position is as follows: ； in, Indicates the total center of gravity of the cargo; The calculation formula of critical overturning angle is as follows: ； in, represents the critical overturning angle; The real-time inclination calculation formula is as follows: ； in, Indicates the real-time inclination angle; Indicates the total center of gravity of the cargo in the y direction; The curve passability risk assessment unit is used to calculate the inner and outer diameters of the curve based on the real-time collected road condition images through image recognition methods, and then determine the risk of the transport vehicle being unable to pass the curve ahead through a turn warning model based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route and the angle sensor data, and generate corresponding instructions; The result generation module is used to send the output results of the data processing module.

2. The system according to claim 1, wherein: The road condition image unit collects road condition images through a binocular camera arranged on the head of the transport vehicle.

3. The system according to claim 2, characterized in that The displacement sensor is divided into a cargo end and a vehicle end. The cargo end is installed on the surface of the cargo, and the vehicle end is installed on the surface of the transport vehicle. The corresponding linear displacement between the two is measured through the principle of electromagnetic induction. The angle sensor is installed at the hinge point between the tractor and trailer of the transport vehicle.

4. The system according to claim 3, characterized in that The center of gravity deviation model also includes: The formula for evaluating the cargo overturning risk level is as follows: ； in, Indicates the level of risk of cargo overturning.

5. The system according to claim 4, characterized in that The center of gravity deviation model also includes response strategies for mapping risks at various levels, including: For level 0 risk, generate a proceed instruction; For level 1 risk, a recommended deceleration instruction is generated; For level 2 risk, generate audible and visual alarm instructions and automatic weak speed limit instructions; For level 3 risk, an automatic strong speed limit instruction is generated; For level 4 risk, an emergency braking command and a cargo overturning rescue command are generated.

6. The system according to claim 5, characterized in that The center of gravity deviation model also includes a displacement sensor collaborative verification formula, specifically: ； in, Indicates the final cargo overturning risk after the displacement sensor collaborative verification; Represents displacement sensor data; Indicates the baseline threshold of the displacement sensor data; Indicates the incremental step of risk level.

7. The system according to claim 5, characterized in that The specific methods for calculating the inner and outer diameters of the curve include: Step a1: Construct the conversion relationship between the image coordinate system and the world coordinate system. The specific expression is: ; in, Represents the homography matrix and satisfies: ； in, Indicates the x-axis rotation scaling factor; Indicates the y-axis rotation scaling factor; Indicates the x-axis translation; Indicates the amount of translation in the y direction; Represents the x-direction perspective distortion coefficient; Indicates the y-direction perspective distortion coefficient; represents the xy coupling rotation coefficient; represents the yx coupling rotation coefficient; Represents the x-coordinate value in the world coordinate system. The specific expression is: ； in, Represents the pixel coordinate value in the u direction in the image coordinate system; Represents the pixel coordinate value of the v direction in the image coordinate system; Represents the coordinate value of the y direction in the world coordinate system. The specific expression is: ； Step a2: Based on the curved road image, extract the curved road contour through Canny edge detection; detect the straight line boundary through Hough transform; and fit the curve boundary equation through RANSAC algorithm. The specific expression is: Left boundary equation: ; Right boundary equation: ; in, 、 and Parameters representing the left boundary equation; 、 and represents the parameters of the right boundary equation; Step a3: At the bottom of the winding road image, Calculate the road width. The specific formula includes: ； in, Indicates the pixel width of the road; Indicates the right boundary of the bottom of the curved road image; Indicates the left boundary of the bottom of the curved road image; ； in, Indicates the actual width of the road; Indicates the scaling factor between pixels and meters; Step a4: Calculate the curvature radius based on the trajectory point sequence of the transportation route. The specific formula includes: Three-point curvature formula: ； in, represents curvature; Indicates the current track point With the previous trajectory point The Euclidean distance between Indicates the current track point and the next track point The Euclidean distance between represents the Euclidean distance between the previous trajectory point and the next trajectory point; Curvature radius formula: ； in, represents the radius of curvature; Step a5: Calculate the inner diameter of the curve and outer diameter , the specific formulas include: ； ； in, Indicates safety margin.

8. The system according to claim 7, characterized in that The turn warning model includes: The instantaneous center of rotation equation is: ； in, Indicates the turning radius of the tractor; Indicates the turning radius of the trailer; Indicates the wheelbase of the tractor; Indicates the trailer wheelbase; Indicates the steering angle of the tractor; Indicates the angle between the tractor and the trailer; The dynamic equation of the hinge angle is: ； in, represents the rate of change of the articulation angle; Indicates time Derivative; Left front corner of tractor ( , ) trajectory equation, specifically: ； in, It represents the turning angle of the tractor around the instantaneous turning center; Indicates the width of the tractor; represents the x-projection of the instantaneous turning center to the center of the tractor's front axle; represents the y-projection of the instantaneous turning center to the center of the tractor's front axle; It represents the projection of the tractor vehicle width component on the x-axis; It represents the projection of the tractor vehicle width component on the y-axis; Right front corner of tractor ( , ) trajectory equation, specifically: ； Trailer left rear corner ( , ) trajectory equation, specifically: ； in, Indicates trailer width; Represents the x-projection from the hinge point to the center of the trailer's rear axle; Represents the y-projection from the hinge point to the center of the trailer's rear axle; Represents the projection of the trailer width component on the x-axis; Represents the projection of the trailer width component on the y-axis; Right rear corner of trailer ( , ) Trajectory equation: ； Safety pass judgment conditions, specifically: ； in, Indicates the The distance from the key points to the instantaneous turning center; the key points include the left front corner of the tractor, the right front corner of the tractor, the left rear corner of the trailer, and the right rear corner of the trailer; Instruction generation strategy, specifically: When the safety passing judgment conditions cannot be met, it means that the detour cannot be passed, and an instruction to change the transportation route is generated; When the safety passing judgment condition is met, it means that the detour can be passed and a continue forward instruction is generated.

9. An intelligent inspection method for on-site logistics safety inspection using the system as claimed in any one of claims 1 to 8, characterized in that: include: Collecting road condition images at preset inspection locations through a road condition image unit; Collect the transport route, coordinates and speed of the transport vehicle through the GPS navigation unit; Receiving a three-dimensional model of the cargo and a three-dimensional model of the transport vehicle through a three-dimensional model unit; Collect inertial data of transport vehicles through IMU inertial unit; Collect displacement sensor data and angle sensor data through the sensor unit; The cargo overturning risk assessment unit calculates the cargo center of gravity offset based on the cargo 3D model and the transport vehicle 3D model, combined with the real-time collected transport vehicle inertia data and displacement sensor data, and uses the center of gravity deviation model to determine the cargo overturning risk and generate corresponding instructions. The curve passability risk assessment unit uses image recognition methods to calculate the inner and outer diameters of the curve based on real-time road condition images. Based on the three-dimensional model of the cargo, the three-dimensional model of the transport vehicle, the transport route, and angle sensor data, the curve warning model determines the risk of the transport vehicle being unable to pass the curve ahead and generates corresponding instructions. The output results of the data processing module are sent out through the result generation module.

10. An intelligent inspection device for logistics site safety inspection, characterized in that: It includes a processor, a memory and a bus, the memory stores instructions and data read by the processor, the processor is used to call the instructions and data in the memory to implement the system as described in any one of claims 1 to 8, and the bus connects the functional components to transmit information.

Images