Safety redundancy method and system for motor driving failure of unmanned container truck and medium

Abstract

The invention relates to a safety redundancy method and system for motor driving failure of an unmanned container truck and a medium, and the method comprises the steps: R1, collecting the data information of parameters of a historical motion state of a vehicle in the braking process of the unmanned container truck, and obtaining the data information of the position of the vehicle and the data information of the speed of the vehicle in real time; and R2, on the basis of the data information of the parameters of the historical motion state of the vehicle, constructing a prediction model of the motion state of the vehicle based on ridge regression, and predicting the motion state of the vehicle to obtain the data information of the predicted motion state of the vehicle. According to the invention, a safety redundancy system of motor driving failure is added, operation accidents of the unmanned container truck caused by faults of an existing brake system can be avoided, damage to vehicles and port facilities is reduced, and the operation safety of the unmanned container truck is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned container trucks, and in particular to a safety redundancy method, system and medium for failure of motor drive of an unmanned container truck. Background Art

[0002] As a new energy transport carrier, the unmanned container truck has braking methods including motor-driven reverse drag, service brake, and parking brake. The motor drive can provide driving power for the unmanned container truck, and the motor reverse drag is achieved by requesting the motor speed to be zero, thereby achieving the braking of the unmanned container truck. The braking deceleration of this method is small and the braking process is relatively gentle. Service braking is mainly performed by hydraulic brake calipers, and its braking deceleration is linear. Different decelerations can be sent to the chassis according to demand. The parking brake is mainly used to lock the vehicle when the unmanned container truck is parking to ensure the safety of the operation.

[0003] Due to the special working conditions of unmanned container trucks in ports, the large mass and heavy load of the vehicles, unmanned container trucks usually use the strategy of requesting the motor speed to be zero to brake the vehicle. However, in the automatic driving state, once the motor drive system of the unmanned container truck fails, the vehicle faces the safety risk of being unable to brake, resulting in serious accident consequences. Summary of the invention

[0004] In view of the above problems, the present invention provides a safety redundancy method, system and medium for motor drive failure of unmanned container trucks, which not only increases the safety redundancy system of motor drive failure, but also avoids operational accidents caused by failure of the existing brake system of unmanned container trucks, and reduces damage to vehicles and port facilities, thereby improving the safety of unmanned container truck operations.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A safety redundancy method for failure of motor drive of unmanned container trucks, the method comprising:

[0007] R1. During the braking process of the unmanned container truck, the data information of the parameters of the historical motion state of the vehicle is collected, and the data information of the vehicle's position and speed are obtained in real time;

[0008] R2. Based on the data information of the parameters of the historical motion state of the vehicle, a prediction model of the vehicle motion state based on ridge regression is constructed to predict the motion state of the vehicle to obtain the data information of the predicted motion state of the vehicle;

[0009] R3. Based on the data information of the predicted vehicle motion state, the data information of the vehicle position and the data information of the vehicle speed, a vehicle speed difference model based on a probability distribution function is constructed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference;

[0010] R4. Based on the data information of the speed difference of the vehicle, a safety redundant control function S of the unmanned container truck is constructed, the safety redundant control matrix of the vehicle is characterized, and the data information of the safety redundant control matrix of the vehicle is obtained.

[0011] Furthermore, the safety redundancy control function S of the unmanned container truck is:

[0012]

[0013] Among them, x is the data information of the vehicle's speed difference, and α1, α2 and α3 are control factors of vehicle safety redundancy.

[0014] Furthermore, the control factors of the vehicle safety redundancy α1, α2 and α3 are,

[0015]

[0016] Among them, x is the data information of the speed difference of the vehicle, and x0 is the data information of the equilibrium value of the speed difference of the vehicle.

[0017] Furthermore, in step R2, the prediction model of the vehicle motion state based on ridge regression is constructed to predict the vehicle motion state, including:

[0018] R21. Based on the data information of the parameters of the historical motion state of the vehicle, a ridge regression function Q of the parameters of the historical motion state of the vehicle is established,

[0019]

[0020] Among them, y is the data information of the parameters of the historical motion state of the vehicle, β1, β2 and β3 are the loss factors of the parameters of the historical motion state of the vehicle, f is the loss function of the ridge regression of the parameters of the historical motion state of the vehicle, δ1, δ2 and δ3 are the penalty factors of the parameters of the historical motion state of the vehicle, and the historical motion state parameters of the vehicle are curve-fitted to obtain the data information of the curve of the historical motion state parameters of the vehicle after fitting;

[0021] R22. Based on the data information of the curve of the historical motion state parameters of the vehicle after fitting, a prediction function W of the motion state of the vehicle is constructed.

[0022]

[0023] Among them, z is the data information of the curve of the historical motion state parameters of the vehicle after fitting, γ1, γ2 and γ3 are the weight coefficients of the motion state of the vehicle;

[0024] R23. Based on the prediction function W of the vehicle's motion state, the vehicle's motion state is predicted to obtain data information on the predicted vehicle's motion state.

[0025] Furthermore, the constraints of the weight coefficients γ1, γ2 and γ3 of the vehicle's motion state are:

[0026]

[0027] The constraint function g of the loss factors β1, β2 and β3 of the parameters of the historical motion state of the vehicle is,

[0028]

[0029] Among them, the value range of the constraint function g is (1,2).

[0030] Furthermore, in step R3, the constructing of the vehicle speed difference model based on the probability distribution function and the calculation of the value of the vehicle speed difference include:

[0031] R31. Based on the data information of the predicted vehicle's motion state and the data information of the vehicle's position, construct an estimation function P of the vehicle's speed,

[0032]

[0033] Among them, r1 is the data information of the predicted vehicle's motion state, r2 is the data information of the vehicle's position, and the vehicle's speed is estimated to obtain the data information of the estimated vehicle's speed;

[0034] R32. Based on the estimated vehicle speed data information and the vehicle speed data information, establish a vehicle speed probability distribution function F,

[0035]

[0036] Among them, v1 is the data information of the estimated vehicle speed, v2 is the data information of the vehicle speed, λ1, λ2 and λ3 are probability distribution factors of the vehicle speed, and the probability distribution of the vehicle speed is characterized to obtain the data information of the probability distribution of the vehicle speed;

[0037] R33. Based on the data information of the probability distribution of the vehicle speed, a vehicle speed difference function G is established,

[0038]

[0039] Among them, q is the data information of the probability distribution of the vehicle, μ1, μ2 and μ3 are the difference factors of the vehicle speed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference.

[0040] Furthermore, the difference factors μ1, μ2 and μ3 of the vehicle speed are:

[0041]

[0042] Among them, q is the data information of the probability distribution of the vehicle.

[0043] Furthermore, the constraint function H of the probability distribution factors λ1, λ2 and λ3 of the vehicle speed is,

[0044]

[0045] Among them, the value range of the constraint function H is (3,5), the value range of the vehicle speed probability distribution factor is (0,1), the value range of the vehicle speed probability distribution factor is (0,1), and the value range of the vehicle speed probability distribution factor is (0,1).

[0046] In order to achieve the above-mentioned and other related purposes, the present invention also provides a safety redundancy system for unmanned container truck motor drive failure, including a computer device, which is programmed or configured to execute the steps of any one of the safety redundancy methods for unmanned container truck motor drive failure.

[0047] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the safety redundancy methods for unmanned container truck motor drive failure.

[0048] The present invention has the following positive effects:

[0049] 1. The present invention predicts the motion state of the vehicle by constructing a prediction model of the vehicle motion state based on ridge regression, and in combination with constructing a vehicle speed difference model based on a probability distribution function, the value of the vehicle speed difference is calculated to obtain data information of the vehicle speed difference. It can not only accurately predict the motion state of the vehicle and accurately estimate the speed difference to ensure the accuracy of vehicle safety redundant control, but also increase the safety redundant system of motor drive failure, which can avoid operation accidents caused by failure of the existing brake system of unmanned container trucks, reduce damage to vehicles and port facilities, and improve the safety of unmanned container truck operations.

[0050] 2. The present invention constructs a safety redundant control function S of an unmanned container truck, characterizes the safety redundant control matrix of the vehicle, and obtains data information of the safety redundant control matrix of the vehicle, which can not only reduce the occurrence of operating accidents, thereby improving the operating efficiency of the unmanned container truck, but also reduce the maintenance costs caused by collisions, and greatly improve the economy of the unmanned container truck operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0052] Figure 2 It is a flow chart of the prediction model of vehicle motion state based on ridge regression of the present invention;

[0053] Figure 3 The figure is a flow chart of constructing a vehicle speed difference model based on a probability distribution function according to the present invention. DETAILED DESCRIPTION

[0054] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0055] Example 1: Figure 1 As shown, a safety redundancy method for failure of motor drive of unmanned container trucks is provided, the method comprising:

[0056] R1. During the braking process of the unmanned container truck, the data information of the parameters of the historical motion state of the vehicle is collected, and the data information of the vehicle's position and speed are obtained in real time;

[0057] R2. Based on the data information of the parameters of the historical motion state of the vehicle, a prediction model of the vehicle motion state based on ridge regression is constructed to predict the motion state of the vehicle to obtain the data information of the predicted motion state of the vehicle;

[0058] R3. Based on the data information of the predicted vehicle motion state, the data information of the vehicle position and the data information of the vehicle speed, a vehicle speed difference model based on a probability distribution function is constructed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference;

[0059] R4. Based on the data information of the speed difference of the vehicle, a safety redundant control function S of the unmanned container truck is constructed, the safety redundant control matrix of the vehicle is characterized, and the data information of the safety redundant control matrix of the vehicle is obtained.

[0060] In this embodiment, the safety redundancy control function S of the unmanned container truck is:

[0061]

[0062] Among them, x is the data information of the vehicle's speed difference, and α1, α2 and α3 are control factors of vehicle safety redundancy.

[0063] In this embodiment, the control factors of the vehicle safety redundancy α1, α2 and α3 are:

[0064] Among them, x is the data information of the speed difference of the vehicle, and x0 is the data information of the equilibrium value of the speed difference of the vehicle.

[0065] In this embodiment, if Figure 2 As shown, in step R2, the prediction model of the vehicle motion state based on ridge regression is constructed to predict the vehicle motion state, including:

[0066] R21. Based on the data information of the parameters of the historical motion state of the vehicle, a ridge regression function Q of the parameters of the historical motion state of the vehicle is established,

[0067]

[0068] Among them, y is the data information of the parameters of the historical motion state of the vehicle, β1, β2 and β3 are the loss factors of the parameters of the historical motion state of the vehicle, f is the loss function of the ridge regression of the parameters of the historical motion state of the vehicle, δ1, δ2 and δ3 are the penalty factors of the parameters of the historical motion state of the vehicle, and the historical motion state parameters of the vehicle are curve-fitted to obtain the data information of the curve of the historical motion state parameters of the vehicle after fitting;

[0069] R22. Based on the data information of the curve of the historical motion state parameters of the vehicle after fitting, a prediction function W of the motion state of the vehicle is constructed.

[0070]

[0071] Among them, z is the data information of the curve of the historical motion state parameters of the vehicle after fitting, γ1, γ2 and γ3 are the weight coefficients of the motion state of the vehicle;

[0072] R23. Based on the prediction function W of the vehicle's motion state, the vehicle's motion state is predicted to obtain data information on the predicted vehicle's motion state.

[0073] In this embodiment, the constraints of the weight coefficients γ1, γ2 and γ3 of the vehicle's motion state are:

[0074]

[0075] The constraint function g of the loss factors β1, β2 and β3 of the parameters of the historical motion state of the vehicle is,

[0076]

[0077] Among them, the value range of the constraint function g is (1,2).

[0078] Embodiment 2: Based on the safety redundancy method for motor drive failure of an unmanned container truck in Embodiment 1, the present invention is further illustrated and described below.

[0079] like Figure 1 As shown, a safety redundancy method for failure of motor drive of unmanned container trucks is provided, the method comprising:

[0080] R1. During the braking process of the unmanned container truck, the data information of the parameters of the historical motion state of the vehicle is collected, and the data information of the vehicle's position and speed are obtained in real time;

[0081] R2. Based on the data information of the parameters of the historical motion state of the vehicle, a prediction model of the vehicle motion state based on ridge regression is constructed to predict the motion state of the vehicle to obtain the data information of the predicted motion state of the vehicle;

[0082] R3. Based on the data information of the predicted vehicle motion state, the data information of the vehicle position and the data information of the vehicle speed, a vehicle speed difference model based on a probability distribution function is constructed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference;

[0083] R4. Based on the data information of the speed difference of the vehicle, a safety redundant control function S of the unmanned container truck is constructed, the safety redundant control matrix of the vehicle is characterized, and the data information of the safety redundant control matrix of the vehicle is obtained.

[0084] In this embodiment, if Figure 3 As shown, in step R3, the vehicle speed difference model based on the probability distribution function is constructed to estimate the value of the vehicle speed difference, including:

[0085] R31. Based on the data information of the predicted vehicle's motion state and the data information of the vehicle's position, construct an estimation function P of the vehicle's speed,

[0086]

[0087] Among them, r1 is the data information of the predicted vehicle's motion state, r2 is the data information of the vehicle's position, and the vehicle's speed is estimated to obtain the data information of the estimated vehicle's speed;

[0088] R32. Based on the estimated vehicle speed data information and the vehicle speed data information, establish a vehicle speed probability distribution function F,

[0089]

[0090] Among them, v1 is the data information of the estimated vehicle speed, v2 is the data information of the vehicle speed, λ1, λ2 and λ3 are probability distribution factors of the vehicle speed, and the probability distribution of the vehicle speed is characterized to obtain the data information of the probability distribution of the vehicle speed;

[0091] R33. Based on the data information of the probability distribution of the vehicle speed, a vehicle speed difference function G is established,

[0092]

[0093] Among them, q is the data information of the probability distribution of the vehicle, μ1, μ2 and μ3 are the difference factors of the vehicle speed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference.

[0094] In this embodiment, the difference factors μ1, μ2 and μ3 of the vehicle speed are:

[0095]

[0096] Among them, q is the data information of the probability distribution of the vehicle.

[0097] In this embodiment, the constraint function H of the probability distribution factors λ1, λ2 and λ3 of the vehicle speed is,

[0098]

[0099] Among them, the value range of the constraint function H is (3,5), the value range of the vehicle speed probability distribution factor is (0,1), the value range of the vehicle speed probability distribution factor is (0,1), and the value range of the vehicle speed probability distribution factor is (0,1).

[0100] In this embodiment, the present invention also provides a safety redundancy system for unmanned container truck motor drive failure, including a computer device programmed or configured to execute any one of the steps of the safety redundancy method for unmanned container truck motor drive failure.

[0101] 1) This system is mainly composed of three parts: AD system, gateway controller, and chassis system. The AD system mainly includes perception module, positioning module, planning module, and control module. The perception module is mainly composed of sensors such as lidar, camera, millimeter wave radar, and ultrasonic radar; the positioning module is mainly composed of combined navigation hardware and laser odometer, lane line positioning and other algorithm coupling; the planning module mainly plans the predicted driving trajectory of the unmanned container truck according to the constraints of the high-precision map based on the perception and positioning information; the control module mainly controls the horizontal and vertical signals of the unmanned container truck according to the planned path and speed.

[0102] The gateway controller mainly receives the command signal of the AD system and transmits it to the various subsystems of the chassis system.

[0103] The chassis system includes but is not limited to the parking brake system, VCU module, service brake system, steering system, etc. The VCU module is connected to the motor drive module.

[0104] 2) The brake control logic of the unmanned container truck designed by the present invention is:

[0105] Normal working mode: The vehicle is in the automatic driving mode. The control module of the AD system sends a control signal of "requesting the motor speed to be zero". The signal is transparently transmitted to the VCU module of the chassis by the gateway. The VCU module controls the motor speed to zero, thereby achieving the braking of the vehicle.

[0106] Safety redundancy mode: When the unmanned container truck brakes in the "normal operation mode", the AD system detects the actual speed of the vehicle through the positioning module (combined navigation) > 3.6 km / h and lasts for 1 second, then it is judged that the braking of mode 1 fails, and the AD system (without going through the planning module and the control module) issues a braking signal (-5 m / s 2 ) to the gateway controller, and then transmitted to the chassis's service brake system, using calipers to brake the vehicle.

[0107] 2.2.2 Signal transmission description

[0108] 1) The signal flow in the normal working mode is: AD system (perception module → positioning module → planning module → control module) → gateway → chassis system (VCU → motor drive). The signal is a control signal of "requesting the motor speed to be zero".

[0109] 2) The signal flow of the safety redundancy mode is: AD system (sensing module → positioning module) → gateway → chassis system (driving brake system). The signal is "deceleration -5m / s 2 ” control signal.

[0110] In this embodiment, the present invention further provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the safety redundancy methods for motor drive failure of unmanned container trucks.

[0111] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0112] In summary, the present invention not only adds a safety redundancy system for motor drive failure, thereby avoiding operational accidents caused by failure of the existing brake system of unmanned container trucks, but also reduces damage to vehicles and port facilities, thereby improving the safety of unmanned container truck operations.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A safety redundancy method for unmanned container truck motor drive failure, characterized in that: The method comprises: R1. During the braking process of the unmanned container truck, the data information of the parameters of the historical motion state of the vehicle is collected, and the data information of the vehicle's position and speed are obtained in real time; R2. Based on the data information of the parameters of the historical motion state of the vehicle, a prediction model of the vehicle motion state based on ridge regression is constructed to predict the motion state of the vehicle to obtain the data information of the predicted motion state of the vehicle; R3. Based on the data information of the predicted vehicle motion state, the data information of the vehicle position and the data information of the vehicle speed, a vehicle speed difference model based on a probability distribution function is constructed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference; R4. Based on the data information of the speed difference of the vehicle, a safety redundant control function S of the unmanned container truck is constructed, the safety redundant control matrix of the vehicle is characterized, and the data information of the safety redundant control matrix of the vehicle is obtained.

2. The safety redundancy method for unmanned container truck motor drive failure according to claim 1 is characterized in that: The safety redundancy control function S of the unmanned container truck is: Among them, x is the data information of the vehicle's speed difference, and α1, α2 and α3 are control factors of vehicle safety redundancy.

3. The safety redundancy method for unmanned container truck motor drive failure according to claim 2 is characterized in that: The control factors of the vehicle safety redundancy α1, α2 and α3 are, Among them, x is the data information of the speed difference of the vehicle, and x0 is the data information of the equilibrium value of the speed difference of the vehicle.

4. The safety redundancy method for unmanned container truck motor drive failure according to claim 1 is characterized in that: In step R2, the construction of a prediction model for the vehicle motion state based on ridge regression and the prediction of the vehicle motion state include: R21. Based on the data information of the parameters of the historical motion state of the vehicle, a ridge regression function Q of the parameters of the historical motion state of the vehicle is established, Among them, y is the data information of the parameters of the historical motion state of the vehicle, β1, β2 and β3 are the loss factors of the parameters of the historical motion state of the vehicle, f is the loss function of the ridge regression of the parameters of the historical motion state of the vehicle, δ1, δ2 and δ3 are the penalty factors of the parameters of the historical motion state of the vehicle, and the historical motion state parameters of the vehicle are curve-fitted to obtain the data information of the curve of the historical motion state parameters of the vehicle after fitting; R22. Based on the data information of the curve of the historical motion state parameters of the vehicle after fitting, a prediction function W of the motion state of the vehicle is constructed. Among them, z is the data information of the curve of the historical motion state parameters of the vehicle after fitting, γ1, γ2 and γ3 are the weight coefficients of the motion state of the vehicle; R23. Based on the prediction function W of the vehicle's motion state, the vehicle's motion state is predicted to obtain data information on the predicted vehicle's motion state.

5. The safety redundancy method for unmanned container truck motor drive failure according to claim 4 is characterized in that: The constraints of the weight coefficients γ1, γ2 and γ3 of the vehicle's motion state are: The constraint function g of the loss factors β1, β2 and β3 of the parameters of the historical motion state of the vehicle is, Among them, the value range of the constraint function g is (1,2).

6. The safety redundancy method for unmanned container truck motor drive failure according to claim 1 is characterized in that: In step R3, the constructing of the vehicle speed difference model based on the probability distribution function and the calculation of the value of the vehicle speed difference include: R31. Based on the data information of the predicted vehicle's motion state and the data information of the vehicle's position, construct an estimation function P of the vehicle's speed, Among them, r1 is the data information of the predicted vehicle's motion state, r2 is the data information of the vehicle's position, and the vehicle's speed is estimated to obtain the data information of the estimated vehicle's speed; R32. Based on the estimated vehicle speed data information and the vehicle speed data information, establish a vehicle speed probability distribution function F, Among them, v1 is the data information of the estimated vehicle speed, v2 is the data information of the vehicle speed, λ1, λ2 and λ3 are probability distribution factors of the vehicle speed, and the probability distribution of the vehicle speed is characterized to obtain the data information of the probability distribution of the vehicle speed; R33. Based on the data information of the probability distribution of the vehicle speed, a vehicle speed difference function G is established, Among them, q is the data information of the probability distribution of the vehicle, μ1, μ2 and μ3 are the difference factors of the vehicle speed, and the value of the vehicle speed difference is calculated to obtain the data information of the vehicle speed difference.

7. The safety redundancy method for unmanned container truck motor drive failure according to claim 6 is characterized in that: The differential factors μ1, μ2 and μ3 of the vehicle speed are, Among them, q is the data information of the probability distribution of the vehicle.

8. The safety redundancy method for unmanned container truck motor drive failure according to claim 6 is characterized in that: The constraint function H of the probability distribution factors λ1, λ2 and λ3 of the vehicle's speed is, Among them, the value range of the constraint function H is (3,5), the value range of the vehicle's speed probability distribution factor is (0,1), the value range of the vehicle's speed probability distribution factor is (0,1), and the value range of the vehicle's speed probability distribution factor is (0,1).

9. A safety redundancy system for motor drive failure of unmanned container trucks, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the safety redundancy method for failure of the motor drive of an unmanned container truck as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the safety redundancy method for motor drive failure of an unmanned container truck as described in any one of claims 1 to 8.

Images