Predictive cooperative control method and system for retarder based on multi-source fusion and model prediction, electronic device and storage medium

Abstract

The application discloses a retarding device predictive collaborative control method and system based on multi-source fusion and model prediction, electronic equipment and storage medium, relates to the buffer control field, and comprises the following steps: acquiring vehicle position, vehicle running state, front road condition, road environment and traffic flow state original data in real time, and making a front road condition prediction; constructing a state equation and an observation equation, performing noise reduction, calibration, synchronization and fusion processing on the collected data, and outputting vehicle driving parameters; constructing a multi-objective optimization function, and solving an optimal retarding device braking torque and braking intervention and exit timing in real time; and dividing multiple braking working conditions according to the optimal braking torque, and realizing reasonable allocation of multiple braking resources according to preset torque distribution weight coefficients. The application can effectively solve the time delay and error problems of different sensors by selecting Kalman filtering to process multi-source sensor data, which conforms to the technical logic of multi-source heterogeneous data noise reduction and fusion.

Description

Technical Field

[0001] This invention relates to the field of buffer control, and more particularly to a retarder predictive cooperative control method based on multi-source fusion and model prediction, a retarder predictive cooperative control system based on multi-source fusion and model prediction, electronic equipment, storage media, and a vehicle retarder test bench. Background Technology

[0002] As a core auxiliary braking device for heavy commercial vehicles, retarders are mainly divided into two categories: hydraulic retarders and eddy current retarders. They are key equipment for vehicle braking safety on long downhill slopes, effectively reducing the load on the service brakes, preventing brake fade, and improving driving safety and the service life of braking components. Currently, the mainstream retarder control methods are mainly divided into two categories: one is the driver manual operation mode, where the driver manually activates and adjusts the retarder gear based on road condition experience. This relies on subjective judgment, has a delayed response, and is prone to problems such as speeding, excessive braking, or retarder overheating; the other is the basic automatic control mode, which triggers the retarder intervention through a single sensor signal of vehicle speed and acceleration, only achieving passive braking control and lacking the ability to predict road conditions.

[0003] Current status of control methods:

[0004] 1. Insufficient road condition perception dimensions, short prediction range and low accuracy, unable to adapt to complex dynamic road conditions, greatly reducing the effectiveness of predictive control.

[0005] 2. The control algorithm has a low level of intelligence, the braking torque adjustment has no smooth transition, the driving comfort is poor, and it is easy to cause shock to the vehicle's transmission system, which will lead to a shortened transmission system life.

[0006] 3. The coordination logic of multiple braking systems is chaotic, the allocation of braking resources is unreasonable, the service brake still intervenes frequently, and the wear and heat fade problems have not been completely resolved;

[0007] 4. The retarder's thermal management and control strategies are disconnected, resulting in poor stability during continuous operation and insufficient service life and adaptability to operating conditions.

[0008] 5. The energy recovery needs of new energy commercial vehicles were not taken into account, resulting in serious waste of braking energy, which contradicts the goal of energy conservation and emission reduction in vehicles.

[0009] To address the problems of existing retarder control technologies, such as single sensing, outdated algorithms, insufficient coordination, lack of thermal management, and poor energy efficiency, this invention provides a retarder predictive collaborative control strategy based on multi-source information fusion and model prediction. This strategy enables long-distance accurate road condition prediction, intelligent torque smooth adjustment, hierarchical coordination of multiple braking systems, and adaptive thermal management optimization, thereby comprehensively improving retarder braking efficiency, driving safety, ride comfort, and vehicle energy efficiency. Summary of the Invention

[0010] The purpose of this invention is to provide a retarder predictive cooperative control method based on multi-source fusion and model prediction, a retarder predictive cooperative control system based on multi-source fusion and model prediction, electronic equipment, storage medium, and vehicle retarder test bench, thereby solving at least one of a number of technical problems.

[0011] Core technical issues: Existing retarder control technologies suffer from problems such as single sensing capabilities, outdated algorithms, insufficient coordination, lack of thermal management, and poor energy efficiency.

[0012] This invention provides the following solution:

[0013] According to a first aspect of the present invention, a predictive cooperative control method for a retarder based on multi-source fusion and model prediction is provided, comprising:

[0014] Q1. Multi-source information perception: Real-time acquisition of raw data on vehicle location, vehicle operating status, road conditions ahead, road environment, and traffic flow.

[0015] Q2, Multi-source data fusion calibration: Construct state equations and observation equations, perform noise reduction, calibration, synchronization and fusion processing on the data acquired in Q1, and output vehicle driving parameters;

[0016] Q3. Model prediction of optimal torque solution: Construct a multi-objective optimization function to solve the optimal retarder braking torque and braking intervention and withdrawal timing in real time;

[0017] Q4. Multi-braking system hierarchical collaborative control: Based on the optimal braking torque, multiple braking conditions are divided, and weighting coefficients are allocated according to preset torque to achieve reasonable allocation of multiple braking resources;

[0018] Q5. Retarder adaptive thermal management control: dynamically corrects the output torque of the retarder and synchronously starts the auxiliary heat dissipation logic;

[0019] Q6. Full-process closed-loop feedback calibration: Real-time acquisition of braking execution results, vehicle driving status and retarder working status data, and closed-loop iterative correction of parameters and weight coefficients.

[0020] Furthermore, step Q2 includes: constructing the state equation and observation equation using the Kalman filter algorithm:

[0021] The state equation is: ;

[0022] The observation equation is: ;

[0023] in, Let v be the system state vector at time k, which includes vehicle speed v, acceleration a, road slope θ, and distance d from the vehicle in front.

[0024] A is the state transition matrix, and B is the control input matrix. To control the input amount, The process noise follows a normal distribution N(0,Q);

[0025] Here, H represents the observation vectors from multiple sensors, and H is the observation matrix. The observation noise follows a normal distribution N(0,R).

[0026] Furthermore, step Q3 includes: establishing discrete state-space equations based on the vehicle longitudinal dynamics model, and constructing a multi-objective optimization function that takes into account vehicle speed tracking accuracy, braking smoothness, retarder energy consumption, and thermal safety;

[0027] The construction of the discrete state-space equations for the longitudinal dynamics of the vehicle includes:

[0028] ;

[0029] in, These are system state variables, corresponding to vehicle speed and acceleration; The control variable corresponds to the retarder braking torque; These are the disturbance variables, corresponding to the slope's gravity drag and rolling resistance; Here is the state transition matrix. For the control matrix, The disturbance matrix is ​​set to a control period of 100ms.

[0030] Furthermore, step Q3 includes: constructing a multi-objective optimization function:

[0031] ;

[0032] in, To predict the time domain, Control time domain and ; , , , These are, respectively, vehicle speed tracking, braking torque, torque change rate, and retarder oil temperature weighting coefficient; Predict the vehicle speed at time k. Let k be the target vehicle speed; The rate of change of torque; To predict retarder oil temperature, This is the safe oil temperature threshold.

[0033] Furthermore, step Q3 includes: constructing a multi-objective optimization function, using the target vehicle speed, braking torque, and retarder operating temperature as constraints, and solving for the optimal retarder braking torque and braking intervention and disengagement timing in real time;

[0034] The constraints for configuring the multi-objective optimization function include:

[0035] Target speed constraint: , Speed ​​limits on roads;

[0036] Braking torque constraint: , This is the maximum rated braking torque of the retarder;

[0037] Torque change rate constraint: , The maximum braking torque change rate is 300 Nm / s;

[0038] Temperature constraints: , The critical oil temperature for the retarder is 200℃.

[0039] Furthermore, in step Q4, the multi-level braking conditions are divided according to the optimal braking torque, including:

[0040] Preset a first braking threshold T1 and a second braking threshold T2, based on the optimal total braking torque. Braking conditions are classified; the total braking torque meets the requirements. ;

[0041] in, For engine braking torque, For the power torque of the electric motor, For the retarder braking torque, For driving braking torque;

[0042] Light braking condition: The retarder and service brake are not engaged; only engine braking and regenerative braking for new energy vehicles are used.

[0043] Medium braking condition: The service brake does not intervene; the retarder brake is the core, and the engine brake and electric motor brake are used as auxiliary brakes.

[0044] Heavy braking conditions: The retarder intervention weight coefficient is not less than 0.8, and it is combined with engine braking and electric motor braking. It intervenes with the service braking as needed to complete the bottom-line braking.

[0045] Furthermore, step Q5 includes: real-time monitoring of the core operating temperature based on the retarder thermal balance equation, and dynamic correction of the retarder output torque through a temperature compensation coefficient, combined with a preset temperature safety threshold and critical threshold.

[0046] Retarder thermal balance equation: ;

[0047] Where C is the retarder heat capacity coefficient. For retarder braking power, For the retarder's heat dissipation power;

[0048] The output torque is dynamically corrected based on the temperature compensation coefficient. The correction formula is as follows: ;

[0049] The segmentation rules for the temperature compensation coefficient are as follows:

[0050] ;

[0051] in, For the braking torque after thermal management correction, This is the temperature compensation coefficient. The oil temperature safety threshold is 150℃. The critical oil temperature for the retarder is 200℃.

[0052] According to a second aspect of the present invention, a retarder predictive cooperative control system based on multi-source fusion and model prediction is provided, comprising:

[0053] Multi-source information perception module: used to acquire raw data on vehicle location, vehicle operating status, road conditions ahead, road environment, and traffic flow in real time;

[0054] Multi-source data fusion and calibration module: used to construct state equations and observation equations, perform noise reduction, calibration, synchronization and fusion processing on the collected data, and output vehicle driving parameters;

[0055] Model prediction optimal torque solution module: used to construct multi-objective optimization functions and solve for the optimal retarder braking torque and braking intervention and withdrawal timing in real time;

[0056] Multi-braking system hierarchical collaborative control module: used to divide multiple braking conditions according to the optimal braking torque, and to achieve reasonable allocation of multiple braking resources according to the preset torque allocation weight coefficient;

[0057] The retarder adaptive thermal management control module is used to monitor the core operating temperature in real time, dynamically correct the retarder output torque, and synchronously start the auxiliary heat dissipation logic.

[0058] Full-process closed-loop feedback calibration module: used to collect braking execution results, vehicle driving status and retarder working status data in real time, and to iteratively correct parameters and coefficients in a closed loop.

[0059] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0060] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps such as a predictive cooperative control method for retarders based on multi-source fusion and model prediction.

[0061] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, comprising: storing a computer program executable by an electronic device, wherein when the computer program is run on the electronic device, the electronic device performs steps such as those of a retarder predictive cooperative control method based on multi-source fusion and model prediction.

[0062] According to a fifth aspect of the present invention, a vehicle retarder test bench is provided, comprising:

[0063] Electronic devices for implementing steps such as predictive cooperative control methods for retarders based on multi-source fusion and model prediction;

[0064] The processor runs a program, and when the program runs, it executes steps such as a retarder predictive cooperative control method based on multi-source fusion and model prediction based on data output from electronic devices.

[0065] Storage medium for storing programs that, when running, execute steps such as a retarder predictive cooperative control method based on multi-source fusion and model prediction in response to data output from electronic devices.

[0066] The above solution achieves the following beneficial technical effects:

[0067] This invention selects Kalman filtering to process multi-source sensor data, which conforms to the technical logic of noise reduction and fusion of multi-source heterogeneous data, and can effectively solve the time delay and error problems of different sensors.

[0068] This invention improves the multi-objective optimization function of the MPC algorithm, taking into account vehicle speed tracking, ride comfort, and thermal load, and transforms the optimization problem into a quadratic programming solution, making the conventional implementation path of model predictive control logically sound.

[0069] This invention uses a three-level braking distribution logic that conforms to the principle of prioritizing low-loss and high-energy-saving braking sources. For example, light braking uses engine / motor braking to recover energy, medium braking mainly uses a retarder to reduce wear on the service brakes, and heavy braking uses multiple sources in synergy to ensure safety, perfectly matching the auxiliary braking needs of commercial vehicles.

[0070] This invention clearly distinguishes between new energy vehicles and traditional fuel vehicles, and addresses the issue of motor braking distribution in fuel vehicles, thus conforming to the hardware configuration differences of different vehicle models. Attached Figure Description

[0071] Figure 1This is a flowchart of a retarder predictive collaborative control method based on multi-source fusion and model prediction provided by one or more embodiments of the present invention.

[0072] Figure 2 This is a structural diagram of a retarder predictive collaborative control system based on multi-source fusion and model prediction, provided by one or more embodiments of the present invention.

[0073] Figure 3 This is a schematic diagram of a collaborative control system architecture provided in a specific embodiment of the present invention.

[0074] Figure 4 This is a schematic diagram of the control flow of a collaborative control method provided in a specific embodiment of the present invention.

[0075] Figure 5 This is a block diagram of an electronic device structure provided by one or more embodiments of the present invention, which is a predictive collaborative control method for retarders based on multi-source fusion and model prediction. Detailed Implementation

[0076] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0077] Figure 1 This is a flowchart of a retarder predictive collaborative control method based on multi-source fusion and model prediction provided by one or more embodiments of the present invention.

[0078] Example 1, such as Figure 1 The predictive cooperative control method for retarders based on multi-source fusion and model prediction, as shown, includes:

[0079] Q1. Multi-source information perception: Collect information from six types of data sources, including high-precision maps, GNSS positioning, millimeter-wave radar, vehicle cameras, vehicle load, and V2X vehicle networking, to obtain real-time raw data on vehicle location, vehicle operating status, road conditions ahead, road environment, and traffic flow, and to make long-distance road condition predictions at a distance of no less than 3km ahead.

[0080] Q2, Multi-source data fusion calibration: The Kalman filter algorithm is used to construct the state equation and observation equation. The multi-source raw data obtained in Q1 is denoised, calibrated, synchronized and fused. Redundant error data is removed, and an accurate three-dimensional / two-dimensional model of the road conditions ahead and a vehicle driving state model are constructed to output high-precision vehicle driving parameters.

[0081] Q3. Optimal torque prediction solution based on model: Based on the vehicle longitudinal dynamics model, a discrete state space equation is established, and a multi-objective optimization function is constructed that takes into account vehicle speed tracking accuracy, braking smoothness, retarder energy consumption and thermal safety. With target vehicle speed, braking torque and retarder operating temperature as constraints, the optimal retarder braking torque and braking intervention and withdrawal timing are solved in real time by combining quadratic programming interior point method with rolling optimization strategy.

[0082] Q4. Multi-braking system hierarchical collaborative control: Based on the optimal braking torque, multi-level braking conditions are divided, and according to the preset torque allocation weight coefficient, the braking torque of the retarder, engine braking, new energy vehicle motor braking and service braking are hierarchically allocated to achieve reasonable allocation of multiple braking resources.

[0083] Q5. Adaptive thermal management and control of the retarder: Based on the retarder thermal balance equation, the core operating temperature is monitored in real time. Combined with the preset temperature safety threshold and critical threshold, the output torque of the retarder is dynamically corrected through the temperature compensation coefficient. The auxiliary heat dissipation logic is activated simultaneously to avoid retarder overheating, overload, and high temperature shutdown.

[0084] Q6. Full-process closed-loop feedback calibration: Real-time acquisition of braking execution results, vehicle driving status and retarder working status data, closed-loop iterative correction of S2 Kalman filter parameters and S3 model predictive control algorithm weight coefficients to achieve full-condition adaptive and precise control.

[0085] In this embodiment, step Q2 includes: constructing the state equation and observation equation using the Kalman filter algorithm:

[0086] The state equation is: ;

[0087] The observation equation is: ;

[0088] in, Let v be the system state vector at time k, which includes vehicle speed v, acceleration a, road slope θ, and distance d from the vehicle in front.

[0089] A is the state transition matrix, and B is the control input matrix. To control the input amount, The process noise follows a normal distribution N(0,Q);

[0090] Here, H represents the observation vectors from multiple sensors, and H is the observation matrix. The observation noise follows a normal distribution N(0,R).

[0091] In this embodiment, step Q3 includes: establishing a discrete state-space equation based on the vehicle longitudinal dynamics model, and constructing a multi-objective optimization function that takes into account vehicle speed tracking accuracy, braking smoothness, retarder energy consumption and thermal safety;

[0092] The construction of the discrete state-space equations for the longitudinal dynamics of the vehicle includes:

[0093] ;

[0094] in, These are system state variables, corresponding to vehicle speed and acceleration; The control variable corresponds to the retarder braking torque; These are the disturbance variables, corresponding to the slope's gravity drag and rolling resistance; Here is the state transition matrix. For the control matrix, The disturbance matrix is ​​set to a control period of 100ms.

[0095] In this embodiment, step Q3 includes: constructing a multi-objective optimization function:

[0096] ;

[0097] in, To predict the time domain, Control time domain and ; , , , These are, respectively, vehicle speed tracking, braking torque, torque change rate, and retarder oil temperature weighting coefficient; Predict the vehicle speed at time k. Let k be the target vehicle speed; The rate of change of torque; To predict retarder oil temperature, This is the safe oil temperature threshold.

[0098] In this embodiment, step Q3 includes: constructing a multi-objective optimization function, using the target vehicle speed, braking torque, and retarder operating temperature as constraints, and solving for the optimal retarder braking torque and braking intervention and withdrawal timing in real time;

[0099] The constraints for configuring the multi-objective optimization function include:

[0100] Target speed constraint: , Speed ​​limits on roads;

[0101] Braking torque constraint: , This is the maximum rated braking torque of the retarder;

[0102] Torque change rate constraint: , The maximum braking torque change rate is 300 Nm / s;

[0103] Temperature constraints: , The critical oil temperature for the retarder is 200℃.

[0104] In this embodiment, step Q4, dividing the braking conditions into multiple levels based on the optimal braking torque, includes:

[0105] Preset a first braking threshold T1 and a second braking threshold T2, based on the optimal total braking torque. Braking conditions are classified; the total braking torque meets the requirements. ;

[0106] in, For engine braking torque, For the power torque of the electric motor, For the retarder braking torque, For driving braking torque;

[0107] Light braking condition: The retarder and service brake are not engaged; only engine braking and regenerative braking for new energy vehicles are used.

[0108] Medium braking condition: The service brake does not intervene; the retarder brake is the core, and the engine brake and electric motor brake are used as auxiliary brakes.

[0109] Heavy braking conditions: The retarder intervention weight coefficient is not less than 0.8, and it is combined with engine braking and electric motor braking. It intervenes with the service braking as needed to complete the bottom-line braking.

[0110] In this embodiment, step S5 includes: real-time monitoring of the core operating temperature based on the retarder thermal balance equation, and dynamic correction of the retarder output torque by combining the preset temperature safety threshold and critical threshold with the temperature compensation coefficient.

[0111] Retarder thermal balance equation: ;

[0112] Where C is the retarder heat capacity coefficient. For retarder braking power, For the retarder's heat dissipation power;

[0113] The output torque is dynamically corrected based on the temperature compensation coefficient. The correction formula is as follows: ;

[0114] The segmentation rules for the temperature compensation coefficient are as follows:

[0115] ;

[0116] in, For the braking torque after thermal management correction, This is the temperature compensation coefficient. The oil temperature safety threshold is 150℃. The critical oil temperature for the retarder is 200℃.

[0117] In this embodiment, the retarder predictive collaborative control method based on multi-source fusion and model prediction is integrated into the vehicle VCU controller in the form of a program or logic circuit, adapting to hydraulic retarders and electric eddy current retarders, and is compatible with traditional fuel commercial vehicles and new energy commercial vehicles.

[0118] New energy commercial vehicles utilize electric motor braking energy recovery logic, while traditional fuel-powered commercial vehicles disable electric motor braking distribution strategy.

[0119] In this embodiment, step S6, closed-loop feedback calibration, specifically involves: real-time acquisition of vehicle speed deviation, braking torque output deviation, and retarder temperature deviation data; adaptive fine-tuning of multi-objective optimization weight coefficients and Kalman filter noise parameters; and achieving adaptive iterative optimization of control parameters under different loads, gradients, and vehicle speeds.

[0120] Figure 2 This is a structural diagram of a retarder predictive collaborative control system based on multi-source fusion and model prediction, provided by one or more embodiments of the present invention.

[0121] Example 2, as Figure 2 The predictive cooperative control system for retarders based on multi-source fusion and model prediction, as shown, includes:

[0122] Multi-source information perception module: used to acquire raw data on vehicle location, vehicle operating status, road conditions ahead, road environment and traffic flow in real time, and to predict road conditions ahead;

[0123] Multi-source data fusion and calibration module: used to construct state equations and observation equations, perform noise reduction, calibration, synchronization and fusion processing on the collected raw data, and output vehicle driving parameters;

[0124] Model prediction optimal torque solution module: used to construct multi-objective optimization functions and solve for the optimal retarder braking torque and braking intervention and withdrawal timing in real time;

[0125] Multi-braking system hierarchical collaborative control module: used to divide multiple braking conditions according to the optimal braking torque, and to achieve reasonable allocation of multiple braking resources according to the preset torque allocation weight coefficient;

[0126] The retarder adaptive thermal management control module is used to monitor the core operating temperature in real time, dynamically correct the retarder output torque, and synchronously start the auxiliary heat dissipation logic.

[0127] Full-process closed-loop feedback calibration module: used to collect braking execution results, vehicle driving status and retarder working status data in real time, and to iteratively correct parameters and coefficients in a closed loop.

[0128] It is worth noting that although this system / device only discloses the above-mentioned modules / units, it does not mean that this system / device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It cannot be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0129] Example 3, in a specific embodiment, discloses a predictive collaborative control strategy for retarders based on multi-source information fusion and model prediction, relying on, for example... Figure 3 The collaborative control system architecture shown executes, as follows: Figure 4 The control flow of the collaborative control method is shown.

[0130] Example 4: The collaborative control system architecture includes: a multi-source information sensing module; a data fusion processing module; a model prediction and decision-making module; a collaborative control execution module; an adaptive thermal management module; and a feedback calibration module.

[0131] The multi-source information perception module is mainly used to identify the current vehicle's location, vehicle status, and other data based on six data sources: high-precision map, GNSS positioning, millimeter-wave radar, vehicle-mounted camera, vehicle load, and V2X vehicle network.

[0132] The data fusion processing module is mainly used to perform noise reduction, calibration, and fusion processing on the multi-source data sensed from multiple data sources by the multi-source information sensing module, and to remove redundant error data to generate an accurate road condition (3D / 2D) model and vehicle driving status model.

[0133] The model prediction and decision module is mainly used to establish a multi-objective optimization function based on the improved MPC algorithm. With the target vehicle speed, braking torque, and retarder temperature as constraints, the optimal braking torque and intervention / exit timing are solved through quadratic programming.

[0134] The collaborative control execution module is mainly used to send control commands to the retarder, engine, motor and service brake actuator according to the three-level braking condition logic and the torque distribution formula, so as to achieve precise distribution of braking torque.

[0135] The adaptive thermal management module is mainly used to monitor the core temperature parameters of the retarder in real time based on the thermal balance equation, compare them with the threshold, dynamically adjust the torque output through the temperature compensation coefficient, and start the auxiliary heat dissipation logic.

[0136] The feedback calibration module is mainly used to collect execution results and vehicle status data in real time, and to correct the weight coefficients and filtering parameters of the MPC algorithm in a closed loop to improve control accuracy.

[0137] Example 5: The control flow of the collaborative control method includes: step S1, multi-source information perception; step S2, data fusion processing; S3, step model prediction and decision-making; step S4, collaborative control execution; step S5, adaptive thermal management; and step S6, feedback calibration.

[0138] Step S1: Based on six data sources—high-precision map, GNSS positioning, millimeter-wave radar, vehicle camera, vehicle load, and V2X vehicle network—identify the current vehicle's location, vehicle status, and other data.

[0139] Step S2: To address the issues of noise, delay, and error in multi-source data, a linear Kalman filter algorithm is used for real-time data fusion and calibration, constructing a state equation (Equation 1) and an observation equation (Equation 2) to eliminate redundant errors and improve the accuracy of road condition and vehicle state parameters.

[0140]

[0141] In the formula,

[0142] The system state vector at time k includes the vehicle speed v, acceleration a, and gradient at the current time. Distance d from the vehicle in front;

[0143] The state transition matrix represents the propagation relationship of state variables over time. This is the filtering period (i.e., the data acquisition frequency);

[0144] To control the input matrix; To control the input amount; For process noise, obey .

[0145]

[0146] In the formula,

[0147] Multi-source sensor observation vectors, including GNSS vehicle speed, radar distance to the vehicle ahead, slope sensor data, V2X road condition data, etc. The observation matrix maps the relationship between state variables and observations; To observe noise, obey .

[0148] The specific filtering steps first predict the vehicle speed, gradient, and other data for the next moment (k) based on the actual vehicle state at the previous time step (k-1) and considering vehicle driving patterns (assuming no sudden changes under normal circumstances). Then, the actual measurement data acquired by the sensors at time step (k) is compared with the theoretical predictions, and a final accurate value is calculated through weighted balancing. This final value serves as the actual vehicle speed, gradient, and other parameters for the next moment, providing data support for subsequent MPC algorithms.

[0149] Step S3: Based on the vehicle longitudinal dynamics model, construct the discrete state space equation (3). With the goal of minimizing the vehicle speed tracking error, minimizing the torque change rate, and minimizing the retarder energy consumption in the prediction time domain, establish a multi-objective optimization function (4) with the target vehicle speed, braking torque, and retarder temperature as constraints, and solve the optimal retarder braking torque and intervention / exit timing in a rolling manner.

[0150]

[0151] In the formula,

[0152] : System state variables of vehicle speed and accelerator at time k;

[0153] : Control variable (retarder braking torque at time k);

[0154] : Disturbance variables (slope rolling resistance and gravity drag);

[0155] , The MPC control cycle is 100ms.

[0156] r is the wheel rolling radius, and I is the vehicle's moment of inertia (positively correlated with the load m);

[0157] Where m is the total mass of the vehicle (including load), g is the gravitational accelerator, and f is the rolling resistance coefficient. This refers to the road slope.

[0158]

[0159] In the formula,

[0160] To predict the time domain, if If we set it to 100, it means the prediction time domain is 10 seconds in the future;

[0161] To control the time domain and reduce computational load, generally ;

[0162] This refers to the weighting coefficient for vehicle speed tracking. This is the braking torque weighting coefficient;

[0163] This is the weighting coefficient for the rate of change of torque; The retarder oil temperature weighting coefficient;

[0164] Predict the vehicle speed at time k+i for time k; Predict the target vehicle speed at time k+i at time k;

[0165] , where is the rate of change of torque;

[0166] Predict the retarder oil temperature at time k+i for time k; The safe threshold for the operating oil temperature of the retarder is 150℃.

[0167] The constraints are:

[0168] ;

[0169] The above multi-objective optimization function adopts a weighted approach, taking into account vehicle speed tracking accuracy, braking smoothness, and retarder thermal load.

[0170] The multi-objective optimization problem described above is transformed into a quadratic programming mathematical problem q. The optimal braking torque at each moment in the future time domain is quickly calculated using the interior point method. Then, the optimal braking torque is solved in real time through rolling optimization. (That is, road condition data is collected again after each control cycle T, and the solution is rolled over again).

[0171] Step S4: According to the three-level braking condition logic and the torque distribution formula, control commands are sent to the retarder, engine, motor and brake pedal. The optimal braking torque calculated in step S3 can be accurately distributed.

[0172] Specifically, based on the optimal braking torque calculated in step S3 This embodiment mainly divides braking demand levels into three levels. Light braking, medium braking, and heavy braking.

[0173] ;

[0174] In the formula,

[0175] The first braking threshold; This is the second braking threshold.

[0176] The specific braking torque distribution is shown in the following formula.

[0177] ;

[0178] In the formula,

[0179] , This is the engine braking intervention weighting coefficient. This refers to the engine braking torque;

[0180] , This is the weighting coefficient for motor braking intervention. For the driving torque of the electric motor;

[0181] , This is the retarder braking intervention weighting coefficient. For the retarder braking torque;

[0182] , This is the weighting coefficient for vehicle braking intervention. For driving braking torque;

[0183] Notice: The requirements only apply to new energy vehicles; traditional fuel vehicles are not equipped with electric motor braking.

[0184] ① Under light braking requirements: This means that the service brake and retarder brake do not need to engage. Engine braking and electric motor braking (for new energy vehicles) are activated first, while the retarder remains in standby mode and does not engage.

[0185] ② Under medium braking requirements: This means that the service brakes are not required. Braking is primarily achieved through the retarder, with low-torque engine braking and electric motor braking matched according to a weighted distribution coefficient. The service brakes do not engage.

[0186] ③ Under heavy braking requirements: , , , All four values ​​are not zero, and all braking systems engage to some extent. The retarder braking engagement coefficient is at least 0.8, which, combined with engine braking and electric motor braking, slightly engages the service brakes when the vehicle speed exceeds the threshold to ensure that the vehicle speed remains within a safe range.

[0187] Step S5: Based on the thermal balance equation (5), monitor the core temperature parameters of the retarder in real time, compare with the threshold, dynamically adjust the torque output through the temperature compensation coefficient, and start the auxiliary heat dissipation logic;

[0188]

[0189] In the formula,

[0190] C is the retarder heat capacity coefficient; This refers to the braking power of the retarder; This refers to heat dissipation power.

[0191] The retarder oil temperature calculated from the heat balance equation is used to determine the adaptive adjustment of the braking torque. The adaptive adjustment formula is shown in equation (6).

[0192]

[0193]

[0194] In the formula,

[0195] For the torque after thermal management adjustment, This is the temperature compensation coefficient. The higher the temperature, the smaller the compensation coefficient, resulting in a linear decrease in torque and preventing sudden temperature rises.

[0196] Step S6: Collect execution results and vehicle status data in real time, and correct the weight coefficients in the model prediction decision module in step S3 and the filtering parameters in step S2 in a closed loop to improve control accuracy.

[0197] Figure 5 This is a block diagram of an electronic device structure provided by one or more embodiments of the present invention, which is a predictive collaborative control method for retarders based on multi-source fusion and model prediction.

[0198] Example 6, as Figure 5 As shown, the present invention provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0199] The memory stores a computer program that, when executed by the processor, causes the processor to perform steps of a predictive cooperative control method for retarders based on multi-source fusion and model prediction.

[0200] Example 7: The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a retarder predictive cooperative control method based on multi-source fusion and model prediction.

[0201] Example 8: The present invention also provides a vehicle retarder test bench, comprising:

[0202] Electronic equipment for implementing a predictive collaborative control method for retarders based on multi-source fusion and model prediction;

[0203] The processor runs a program, and when the program runs, it executes the steps of a retarder predictive cooperative control method based on multi-source fusion and model prediction from the data output by the electronic device.

[0204] Storage medium for storing programs that, when running, execute steps of a retarder predictive cooperative control method based on multi-source fusion and model prediction in response to data output from electronic devices.

[0205] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0206] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0207] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0208] Electronic devices can also obtain reset commands corresponding to storage media. These reset commands are provided by the supplier, and the reset commands for different storage media can be the same or different, which is not limited here.

[0209] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0210] For ease of description, the above apparatus is described by dividing it into various units and modules according to their functions. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0211] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0212] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0213] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0214] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions 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 predictive cooperative control method for retarders based on multi-source fusion and model prediction, characterized in that, include: Q1. Multi-source information perception: Real-time acquisition of raw data on vehicle location, vehicle operating status, road conditions ahead, road environment, and traffic flow. Q2, Multi-source data fusion calibration: Construct state equations and observation equations, perform noise reduction, calibration, synchronization and fusion processing on the data acquired in Q1, and output vehicle driving parameters; Q3. Model prediction of optimal torque solution: Construct a multi-objective optimization function to solve the optimal retarder braking torque and braking intervention and withdrawal timing in real time; Q4. Multi-braking system hierarchical collaborative control: Based on the optimal braking torque, multiple braking conditions are divided, and the weighting coefficients of the preset torque allocation are used to achieve reasonable allocation of multiple braking resources.

2. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, Also includes: Q5. Adaptive thermal management control of the retarder: Real-time monitoring of core operating temperature, dynamic correction of retarder output torque, and simultaneous activation of auxiliary heat dissipation logic; Q6. Full-process closed-loop feedback calibration: Real-time acquisition of braking execution results, vehicle driving status and retarder working status data, and closed-loop iterative correction of parameters and weight coefficients.

3. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, Step Q2 includes: The state equation and observation equation are constructed using the Kalman filter algorithm: The state equation is: ; The observation equation is: ; in, Let v be the system state vector at time k, including vehicle speed v, acceleration a, road slope θ, and distance d from the vehicle in front. A is the state transition matrix, and B is the control input matrix. To control the input amount, The process noise follows a normal distribution N(0,Q); Here, H represents the observation vectors from multiple sensors, and H is the observation matrix. The observation noise follows a normal distribution N(0,R).

4. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, Step Q3 includes: establishing discrete state-space equations based on the vehicle longitudinal dynamics model, and constructing a multi-objective optimization function that takes into account vehicle speed tracking accuracy, braking smoothness, retarder energy consumption and thermal safety; The construction of the discrete state-space equations for the longitudinal dynamics of the vehicle includes: ； in, These are system state variables, corresponding to vehicle speed and acceleration; The control variable corresponds to the retarder braking torque; These are the disturbance variables, corresponding to the slope's gravity drag and rolling resistance; Here is the state transition matrix. For the control matrix, Let be the perturbation matrix.

5. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, Step Q3 includes: constructing a multi-objective optimization function: ； in, To predict the time domain, Control time domain and ; , , , These are, respectively, vehicle speed tracking, braking torque, torque change rate, and retarder oil temperature weighting coefficient; Predict the vehicle speed at time k. Let k be the target vehicle speed; The rate of change of torque; To predict retarder oil temperature, This refers to the safe oil temperature threshold. Step Q3 further includes: constructing a multi-objective optimization function, using the target vehicle speed, braking torque, and retarder operating temperature as constraints, and solving for the optimal retarder braking torque and braking intervention and withdrawal timing in real time; The constraints configured for the multi-objective optimization function include: Target speed constraint: , Speed ​​limits on roads; Braking torque constraint: , This is the maximum rated braking torque of the retarder; Torque change rate constraint: , The maximum braking torque change rate is 300 Nm / s; Temperature constraints: , This refers to the critical oil temperature of the retarder.

6. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, In step Q4, the division of multiple braking conditions based on the optimal braking torque includes: Preset a first braking threshold T1 and a second braking threshold T2, based on the optimal total braking torque. Braking conditions are classified; the total braking torque meets the requirements. ; in, For engine braking torque, For the power torque of the electric motor, For the retarder braking torque, For driving braking torque; Light braking condition: The retarder and service brake are not engaged; only engine braking and regenerative braking for new energy vehicles are used. Medium braking condition: The service brake does not intervene; the retarder brake is the core, and the engine brake and electric motor brake are used as auxiliary brakes. Heavy braking conditions: The retarder intervention weight coefficient is not lower than the preset weight coefficient threshold. It is combined with engine braking and electric motor braking, and the service braking is intervened as needed to complete the bottom-line braking.

7. The retarder predictive cooperative control method based on multi-source fusion and model prediction according to claim 1, characterized in that, Step Q5 includes: real-time monitoring of the core operating temperature based on the retarder thermal balance equation, and dynamic correction of the retarder output torque through a temperature compensation coefficient in combination with a preset temperature safety threshold and critical threshold. The retarder heat balance equation is as follows: ; Where C is the retarder heat capacity coefficient. For retarder braking power, For the retarder's heat dissipation power; The output torque is dynamically corrected based on the temperature compensation coefficient. The correction formula is as follows: ; The segmentation rules for the temperature compensation coefficient are as follows: ； in, For the braking torque after thermal management correction, This is the temperature compensation coefficient. The oil temperature safety threshold is 150℃. This refers to the critical oil temperature of the retarder.

8. A retarder predictive cooperative control system based on multi-source fusion and model prediction, characterized in that, include: Multi-source information perception module: used to acquire raw data on vehicle location, vehicle operating status, road conditions ahead, road environment, and traffic flow in real time; Multi-source data fusion and calibration module: used to construct state equations and observation equations, perform noise reduction, calibration, synchronization and fusion processing on the collected raw data, and output vehicle driving parameters; Model prediction optimal torque solution module: used to construct multi-objective optimization functions and solve for the optimal retarder braking torque and braking intervention and withdrawal timing in real time; Multi-braking system hierarchical collaborative control module: used to divide multiple braking conditions according to the optimal braking torque, and to achieve reasonable allocation of multiple braking resources according to the preset torque allocation weight coefficient; The retarder adaptive thermal management control module is used to monitor the core operating temperature in real time, dynamically correct the retarder output torque, and synchronously start the auxiliary heat dissipation logic. Full-process closed-loop feedback calibration module: used to collect braking execution results, vehicle driving status and retarder working status data in real time, and to iteratively correct parameters and coefficients in a closed loop.

9. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the retarder predictive cooperative control method based on multi-source fusion and model prediction as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, include: The device stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the retarder predictive cooperative control method based on multi-source fusion and model prediction as described in any one of claims 1 to 7.

Images