Method and system for predictive cruise control of commercial vehicle

Abstract

Disclosed in the present invention are a method and system for predictive cruise control of a commercial vehicle. The method comprises: acquiring as input parameters road gradient information provided by a high-precision map and a target cruise vehicle speed corrected by a deep belief network-based driving style model; on the basis of the speed and torque of an engine, using a weighted moving average algorithm to perform averaging processing on power values within a short period of time, so as to generate a current engine power; on the basis of an automobile power balance equation, predicting a driving power demand for a next slope section on the basis of gradient values of a current position and a road ahead; and in view of a high-efficiency output power range of the engine itself, and on the basis of different power demands, generating a recommended gear and an optimal throttle opening for the next slope section. Therefore, in the method for predictive cruise control of a commercial vehicle of the present invention, a gear and a throttle can be adaptively adjusted on the basis of road gradients and driving habits, thereby improving the driving efficiency and fuel economy, and enhancing the personalization of driving experience.

Description

Predictive cruise control method and system for commercial vehicles Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a predictive cruise control method and system for commercial vehicles. Background Technology

[0002] Cruise control in commercial vehicles can reduce driver fatigue during long-distance driving, allowing the vehicle to maintain a stable set speed and thus enabling the driver to relax. A relatively stable cruise speed also helps reduce the incidence of traffic accidents and avoid common incidents such as rear-end collisions. Consistent power output over a long period also improves engine fuel efficiency, thereby reducing operating costs. Predictive cruise control is a more advanced cruise function that incorporates information about the road ahead. It automatically adjusts the vehicle's speed by analyzing real-time vehicle speed, location, and road information, and utilizes advanced sensor technology and artificial intelligence algorithms to enable continuous cruise driving in a wider range of road conditions.

[0003] Existing predictive cruise solutions have the following main drawbacks:

[0004] The calculation and planning of the road ahead often relies on complex calculations and data signal processing, and on energy-intensive algorithms such as dynamic programming and model predictive control to predict and calculate the real-time state of the vehicle, which places high demands on the computing power of the controller.

[0005] In calculations, driving economy is often the primary goal of planning, with less consideration given to the identification and consideration of driving style, making it difficult to achieve the optimal combination of economy and comfort. Summary of the Invention

[0006] This invention provides a predictive cruise control method and system for commercial vehicles, which can adaptively adjust gear and throttle according to road gradient and driving habits, improving driving efficiency and fuel economy, and enhancing the personalization of the driving experience.

[0007] To achieve the above objectives, in a first aspect, the present invention provides a predictive cruise control method for commercial vehicles, comprising:

[0008] The road gradient information provided by the high-precision map and the target cruising speed corrected by the deep belief network driving style model are used as input parameters.

[0009] Based on engine speed and torque, a weighted moving average algorithm is used to average the power value over a short period of time to generate the current engine power.

[0010] Based on the vehicle power balance equation, the driving power demand for the next slope is predicted according to the current position and the slope value of the road ahead.

[0011] Based on the engine's efficient output power range and different power requirements, the recommended gear and optimal throttle opening for the next hill section are generated.

[0012] In one embodiment of the present invention, the step of averaging the power values ​​over a short period of time using a weighted moving average algorithm includes:

[0013] Obtain the predicted power value at time t, the power value at time t-1, the weighting coefficient, the engine torque at time t, and the engine speed at time t;

[0014] The current engine power is calculated based on the weighted moving average algorithm expression.

[0015] In one embodiment of the present invention, the target cruising speed corrected by the deep belief network driving style model includes:

[0016] For drivers with an aggressive driving style, a positive speed correction value is assigned;

[0017] For drivers with a normal driving style, assign a speed correction value of 0.

[0018] For drivers with a calm driving style, a negative speed correction value is assigned.

[0019] In one embodiment of the present invention, predicting the driving power demand for the next slope segment based on the vehicle power balance equation, according to the current position and the gradient of the road ahead, includes:

[0020] Obtain vehicle power output, transmission efficiency, vehicle weight, coefficient of friction, vehicle speed, gradient, drag coefficient, frontal area, and time.

[0021] Based on the vehicle power balance equation, the variable power demand for the next slope section is calculated.

[0022] In one embodiment of the present invention, the step of generating the recommended gear and optimal throttle opening for the next hill section based on the engine's own high-efficiency output power range and different power requirements includes:

[0023] Obtain the high-efficiency output power range corresponding to the engine's optimal fuel consumption range;

[0024] Based on the predicted power demand for the next uphill section, a target speed value that falls within the high-efficiency output power range is determined as the recommended speed for the next uphill section.

[0025] Based on the recommended engine speed and predicted vehicle speed, the optimal gear for the next uphill section is calculated.

[0026] Obtain the speed regulation characteristic MAP, and find the optimal torque value given the known recommended speed;

[0027] The optimal torque value is converted into a throttle opening value to obtain the optimal throttle opening for the next slope.

[0028] Secondly, this invention provides a predictive cruise control system for commercial vehicles, comprising: an acquisition module, a generation module, a prediction module, and a planning module. The acquisition module acquires road gradient information from a high-precision map and a target cruise speed corrected by a deep belief network driving style model as input parameters. The generation module averages the power value over a short period using a weighted moving average algorithm based on engine speed and torque to generate the current engine power. The prediction module predicts the power demand for the next slope segment based on the vehicle's power balance equation, the current location, and the slope of the road ahead. The planning module combines the engine's efficient output power range with different power demand conditions to generate a recommended gear and optimal throttle opening for the next slope segment.

[0029] In one embodiment of the present invention, the generation module includes a first acquisition unit and a first generation unit. The first acquisition unit is used to acquire the predicted power value at time t, the power value at time t-1, a weighting coefficient, the engine torque at time t, and the engine speed at time t. The first generation unit is used to generate the current engine power according to a weighted moving average algorithm expression.

[0030] In one embodiment of the present invention, the target cruising speed corrected by the deep belief network driving style model includes: assigning a positive speed correction value to an aggressive driver; assigning a speed correction value of 0 to a normal driver; and assigning a negative speed correction value to a neutral driver.

[0031] Thirdly, the present invention provides an electronic device, comprising:

[0032] At least one processor; and

[0033] A memory that is communicatively connected to the at least one processor;

[0034] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the predictive cruise control method for commercial vehicles as described above.

[0035] Fourthly, the present invention provides a computer-readable storage medium including a computer program and instructions, which, when the computer program or the instructions are executed on a computer, cause the computer to perform the predictive cruise control method for commercial vehicles as described above.

[0036] Compared with the prior art, the predictive cruise control method and system for commercial vehicles according to the present invention have the following advantages:

[0037] 1. By analyzing vehicle speed, location, and road information in real time, and combining this with the engine's efficient output power range, this invention can intelligently adjust gear position and throttle opening, ensuring the engine always operates within its optimal fuel consumption range. This not only reduces unnecessary fuel consumption but also improves vehicle power performance, thereby significantly improving driving efficiency and fuel economy while ensuring driving safety.

[0038] 2. This invention introduces a deep belief network driving style model, which can personalize the target cruise speed according to the driver's driving style (aggressive, normal, calm), thereby automatically adapting to the driving habits and needs of different drivers, providing a cruise control experience that is more in line with personal preferences, and thus enhancing driving comfort and satisfaction.

[0039] 3. Existing predictive cruise solutions often rely on complex calculations and data signal processing, such as energy-intensive algorithms like dynamic programming and model predictive control. This invention, however, reduces computational complexity and energy consumption by employing a weighted moving average algorithm and a physics-based prediction method, making the system more efficient and energy-saving.

[0040] 4. This invention utilizes road slope information provided by high-precision maps and combines it with the vehicle power balance equation to predict power demand, thus more accurately reflecting the actual power demand of vehicles under different road conditions. Simultaneously, by incorporating the engine's efficient output power range for gear shifting and throttle control, the system can better adapt to complex and changing real-world road conditions, improving its adaptability and robustness. Attached Figure Description

[0041] Figure 1 is a flowchart illustrating a predictive cruise control method for commercial vehicles according to Embodiment 1 of the present invention;

[0042] Figure 2 is a schematic diagram of the structure of a predictive cruise control system for commercial vehicles according to Embodiment 2 of the present invention;

[0043] Figure 3 is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention;

[0044] Figure 4 is a schematic diagram of the logic flow of a predictive cruise control method for commercial vehicles in a specific embodiment of the present invention;

[0045] Figure 5 is a schematic diagram of the high-efficiency output power range in a specific embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of the speed regulation characteristics (MAP) in a specific embodiment of the present invention. Detailed Implementation

[0047] The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and not intended to limit the scope of the invention. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the embodiments of the present invention, and not all structures.

[0048] To facilitate understanding, the main implementation concepts of the various embodiments of the present invention will be briefly described first.

[0049] Example 1: Figure 1 is a flowchart illustrating a predictive cruise control method for commercial vehicles according to Example 1 of the present invention. As shown in Figure 1, Example 1 provides a predictive cruise control method for commercial vehicles, including:

[0050] Step S100: Obtain the road slope information provided by the high-precision map and the target cruising speed corrected by the deep belief network driving style model as input parameters;

[0051] Specifically, obtaining road gradient information from high-precision maps is one of the key input parameters for predictive cruise shifting methods. High-precision maps, through precise 3D modeling and mapping techniques, can provide detailed information such as the gradient, curve radius, and speed limit of the road ahead. For example, road data is collected using sensors such as LiDAR and inertial navigation systems, and high-precision maps are generated through point cloud stitching and feature extraction algorithms. The system can obtain road gradient changes within a certain distance ahead of the vehicle from the map, such as gradient data within 500 meters ahead. The road is divided into several slope segments, each characterized by its starting mileage, segment length, and gradient value. The system obtains the vehicle's current location information in real time and queries the map database to match the gradient information of the road segment ahead, serving as one of the input conditions for subsequent power demand prediction and shifting strategy formulation. A deep belief network driving style model is used to adjust the target cruise speed to meet the personalized needs of different drivers. This model is a deep learning-based driving behavior recognition algorithm that establishes a mapping relationship between driving style characteristics and speed preferences by learning from long-term driving data of drivers. The model's input features can include statistical characteristics of signals such as accelerator pedal opening, brake pedal opening, and steering wheel angle, including values ​​like mean, standard deviation, and rate of change. By training on massive amounts of user data on a cloud service platform, a driving style recognition model with strong generalization ability is obtained. When applying this model, the system collects the driver's driving data over a period of time, extracts features, inputs them into the model for style recognition, and obtains a style level value. The style level value is then weighted and summed with a preset target cruise speed value to obtain a personalized target speed. For example, a driver with a style level of 0.8, who prefers higher speeds, might have a target speed initially set at 80 km / h, which is then adjusted to 85 km / h. This adjusted speed serves as the input value for subsequent calculations, organically combining the driver's subjective preferences with objective vehicle operating conditions to achieve personalized and intelligent predictive cruise control.

[0052] Step S200: Based on engine speed and torque, the power value over a short period of time is averaged using a weighted moving average algorithm to generate the current engine power; specifically, the weighted moving average algorithm is as follows:

[0053]

[0054] Specifically, by acquiring the engine speed n in real time （t） and torque T tq（t） And combined with the power value P from the previous moment t-1 The engine power P at the current moment is generated by combining the predicted value with the current value using a weighted moving average algorithm. (t) .in, The weighting coefficient is used to adjust the weighting of historical power values ​​and current predicted power values ​​in the calculation. This method not only considers the current engine operating state but also incorporates historical data to make power calculation smoother and more stable, reducing errors caused by instantaneous fluctuations. Specifically, by weighting the predicted power value at the current moment (calculated based on speed and torque) with the actual power value at the previous moment, it can more accurately reflect the dynamic changes in engine power, providing reliable basic data for subsequent power demand prediction and shifting strategy formulation based on the vehicle power balance equation. The application of this algorithm enables commercial vehicles to achieve more precise and economical cruise control under different road conditions and driving styles, thereby improving driving efficiency, fuel economy, and the personalization of the driving experience.

[0055] For example, a commercial vehicle is driving, and its engine speed and torque data are measured in real time by sensors. At the current time t=10 seconds, we need to calculate the engine power P at t=10 seconds. 10 First, obtain the following parameters: the predicted power value P' at t=10 seconds. (10) This value can be obtained using the power value from the previous moment and parameters such as the speed and torque at the current moment, through a certain prediction algorithm (such as Kalman filtering, neural networks, etc.). Assume P... '(10) The actual power value P at t=9 seconds is 120kW. (9) This value can be read directly from the engine control unit (ECU). Assume P... (9) The power is 100kW. The weighting coefficient, used to balance the weights of the current predicted value and the previous actual value, typically takes a value between 0 and 1. Assume... Take 0.6. The engine torque T at t=10 seconds. tq(10) Assume the engine speed is 300 Nm. The engine speed n at t=10 seconds is... (10) Let's assume it's 2000 revolutions per minute. Next, we'll calculate P using the weighted moving average algorithm formula. 10 :

[0056]

[0057] Substitute the known values:

[0058]

[0059] The calculation yielded:

[0060]

[0061] =97.13kW

[0062] Therefore, using a weighted moving average algorithm, the engine power at t=10 seconds was calculated to be 97.13 kW. This value combines the predicted power value at the current moment with the actual power value at the previous moment. By adjusting the weighting coefficients, it considers both the dynamic changes of the current state and maintains the stability and reliability of the calculation results, providing an important reference for subsequent power demand prediction and shifting strategy formulation based on the vehicle power balance equation.

[0063] Step S300: Based on the vehicle power balance equation, predict the driving power demand for the next slope segment according to the current position and the gradient of the road ahead; wherein, the vehicle power balance equation is:

[0064]

[0065] Specifically, this step utilizes the vehicle power balance equation, comprehensively considering the vehicle's current position, the slope information of the road ahead, and other relevant parameters (such as transmission efficiency, vehicle weight, friction coefficient, vehicle speed, drag coefficient, and frontal area) to predict the power required by the vehicle when driving on the next slope. The vehicle power balance equation is a complex physical model that precisely describes the various resistances that a vehicle must overcome during driving, including rolling resistance, air resistance, slope resistance, and acceleration resistance. Through this step, the system can understand the vehicle's power demand under different road conditions in advance, providing important reference for subsequent shifting strategies and throttle control. This not only ensures that the vehicle can drive optimally under different road conditions but also significantly improves driving efficiency and fuel economy, while enhancing driving comfort and safety. Therefore, power demand prediction based on the vehicle power balance equation is a core component of predictive cruise control methods for commercial vehicles, providing a solid foundation for achieving intelligent and personalized cruise control.

[0066] For example, a fully loaded heavy truck is traveling on a highway at a current speed of 70 km / h, with a transmission efficiency of 0.85, a weight of 45 tons, a friction coefficient of 0.02, a drag coefficient of 0.5, and a frontal area of ​​7 square meters. Using a high-precision map, the system obtains the road gradient information within 500 meters ahead. The current gradient is 0%, while an uphill section with a gradient of 3% begins 200 meters ahead. Based on this information, the system begins to predict the driving power demand for the next uphill section using the vehicle power balance equation. First, the known parameters are substituted into the equation:

[0067]

[0068] in, Given a transmission efficiency of 0.85, G as the vehicle weight of 45,000 kg, and f as the coefficient of friction of 0.02, The vehicle speed is 70 km / h (i.e., 70 / 3.6 m / s), i represents the gradient of 0% (current position) and 3% (next slope), and C represents the gradient of 3%. D The drag coefficient is 0.5, and A is the windward area of ​​7 square meters. This is the rotational mass conversion factor (usually taken as 1.05 for simplified calculation). This is the acceleration (assuming the current speed is constant, so it is 0).

[0069] For the current location (slope 0%):

[0070]

[0071] After simplified calculations, the driving power requirement at the current position is mainly determined by rolling resistance and air resistance.

[0072] For the next slope section (3% slope):

[0073]

[0074] Note the increase in the slope resistance term, because going uphill requires overcoming the component of gravity along the slope.

[0075] Through calculation, the system can predict that on the next slope, due to the increased gradient, the vehicle will need to provide more power to overcome the component of gravity along the slope, thereby maintaining the current speed. Assuming the calculation shows that the power requirement at the current location is 150 kW, while the power requirement increases to 170 kW on the next slope, this means that the engine needs to output more power to maintain a speed of 70 km / h uphill.

[0076] Based on this prediction, the system can further combine the engine's efficient output power range to intelligently plan the appropriate gear and throttle opening, ensuring that the vehicle can smoothly and economically pass through uphill sections. This not only improves driving efficiency but also optimizes fuel economy, while enhancing driving comfort and safety.

[0077] Step S400: Based on the engine's own high-efficiency output power range and different power requirements, generate the recommended gear and optimal throttle opening for the next slope.

[0078] Specifically, the system first obtains the efficient output power range corresponding to the engine's optimal fuel consumption range. This range is derived through experimental data and characteristic curve analysis, representing the area where the engine can convert fuel into power with the highest efficiency and produce fewer emissions under different speed and torque combinations. Next, based on the previously predicted power demand for the next uphill section, the system determines a target speed value falling within this efficient output power range as the recommended speed. This recommended speed aims to meet power demand while achieving optimal fuel economy. With the recommended speed, the system combines the current vehicle speed with the vehicle's gear ratio data to calculate the most suitable gear at the recommended speed. For example, if the current vehicle speed is 60 km / h and the recommended speed is 2500 rpm, the system may find that 4th gear is the closest to this speed and therefore determine it as the optimal gear. Finally, the system queries the engine's torque characteristic map (MAP), a pre-stored data table of the engine's torque output characteristics at different speeds and throttle openings. Knowing the recommended speed, the system can find the optimal throttle opening required to output the target torque. For example, if the recommended engine speed is 2500 rpm, and 180 Nm of torque is needed to meet the power demand, the system will find the corresponding throttle opening value, such as 40%, through the MAP table. In this way, the system generates the recommended gear (such as 4th gear) and the optimal throttle opening (such as 40%) for the next uphill section, thereby achieving precise control of engine power output, which satisfies the power demand and optimizes fuel economy.

[0079] For example, a heavy truck is traveling on a road with multiple inclines, currently traveling at 70 km / h, and is about to enter an uphill section with a 5% gradient. The system has already obtained the gradient information from a high-precision map and, using the vehicle's power balance equation, predicts that the vehicle needs to provide approximately 220 kW of power to maintain the current speed uphill. Next, the system plans its shifting strategy and throttle control based on the engine's own efficient power output range. Assuming the engine's optimal fuel consumption range corresponds to an efficient power output range of 2000-2500 rpm and a torque output of 180-220 Nm, the system calculates that at 2300 rpm and 200 Nm of torque, the engine can output 220 kW of power, and this operating point falls precisely within the efficient power output range. Therefore, the system determines 2300 rpm as the recommended speed for the next incline. Then, based on the current vehicle speed and recommended engine speed, combined with the vehicle's gear ratio data, the system calculates that the most suitable gear at 2300 rpm is 4th gear. This is because at the current vehicle speed, 4th gear brings the engine speed closest to the recommended 2300 rpm. Next, the system queries the engine's torque characteristic map (MAP) and, given the recommended engine speed of 2300 rpm, finds the throttle opening value corresponding to 200 Nm of torque output. Assuming the MAP table shows that at 2300 rpm, a throttle opening of 55% is required to output 200 Nm of torque, the system ultimately generates a recommended gear of 4th gear and an optimal throttle opening of 55% for the next uphill section. This ensures that the truck not only provides sufficient power to maintain speed when going uphill but also ensures that the engine operates within its efficient power output range, achieving optimal fuel economy. Simultaneously, by pre-planning gear shifts and throttle control, the system also ensures smooth gear shifts, improving driving comfort.

[0080] In this embodiment, the step of averaging the power value over a short period of time using a weighted moving average algorithm includes: obtaining the predicted power value at time t, the power value at time t-1, the weighting coefficient, the engine torque at time t, and the engine speed at time t; and calculating the current engine power according to the weighted moving average algorithm expression.

[0081] Specifically, a series of key parameters are first acquired, including the predicted power value at time t, the actual power value at time t-1, a coefficient used to balance the weights of old and new data (i.e., the weighting coefficient), the engine torque at time t, and the engine speed at time t. These parameters form the basis for calculating the current engine power. The predicted power value is typically derived from the power value at the previous moment, the engine torque and speed at the current moment, and other possible dynamic factors (such as vehicle acceleration, road conditions, etc.), using a specific prediction algorithm (such as Kalman filtering, neural networks, etc.). This predicted value reflects the system's real-time estimate of the current engine power. The actual power value at time t-1 is the actual power output value at the previous moment, directly read from the engine control unit (ECU). This value represents the engine's true performance at a specific instant in the past. The weighting coefficient is a constant between 0 and 1, used to adjust the relative importance of the predicted and actual power values ​​in calculating the current average power. When the weighting coefficient is large, the predicted value has a greater impact on the final result; conversely, when the weighting coefficient is small, the actual value has a more significant impact. By adjusting this coefficient, the system can find a balance between the dynamics of the predicted value and the stability of the actual value. The engine torque and speed at time t are measured in real time by sensors installed on the engine. These two parameters directly reflect the engine's current operating state and are indispensable data for power calculation. After obtaining these parameters, the system calculates power using a weighted moving average algorithm. This expression weights the predicted and actual power values ​​according to weighting coefficients, resulting in a smoother and more stable current engine power value. This value not only considers the engine's current real-time state but also incorporates the influence of historical data, making the calculation results more reliable and accurate. The advantage of this method is that it effectively integrates predicted and actual values, retaining the flexibility and foresight of the predicted values ​​while taking into account the stability and reliability of the actual values. Furthermore, by adjusting the weighting coefficients, the system can flexibly adjust the proportion of predicted and actual values ​​in the calculation according to different application scenarios and needs, thereby achieving more precise and efficient engine power control. In predictive cruise control for commercial vehicles, the application of this method can significantly improve driving efficiency and fuel economy while enhancing the personalization of the driving experience.

[0082] In this embodiment, the target cruising speed corrected by the deep belief network driving style model includes: assigning a positive speed correction value to an aggressive driver; assigning a speed correction value of 0 to a normal driver; and assigning a negative speed correction value to a calm driver.

[0083] Specifically, for aggressive drivers, a positive speed correction value is assigned, meaning the system will appropriately increase the target cruise speed. This is to satisfy aggressive drivers' pursuit of power performance. By increasing the target speed, the engine operates at higher RPMs and loads, providing stronger acceleration and hill-climbing ability. Simultaneously, the system will adjust its shift strategy accordingly, delaying upshifts to keep the engine at a higher RPM range, ensuring sufficient power output. For example, instead of shifting to a higher gear at 80 km / h, it might now be delayed until 85 km / h. This allows aggressive drivers to enjoy a more exhilarating driving experience. For normal drivers, a speed correction value of 0 is assigned, maintaining the original target cruise speed. This indicates that the system believes the current speed setting already balances power and economy well, requiring no further adjustment. Normal driving styles typically prioritize a smooth and comfortable driving experience while also aiming for good fuel economy. Therefore, maintaining the default cruise speed and shift logic can achieve a relatively ideal overall performance while meeting the driver's expectations. For drivers with a relaxed driving style, a negative speed correction value is assigned, appropriately reducing the target cruising speed. This approach aims to further optimize fuel economy while providing a more comfortable and relaxed driving experience. By reducing speed, the engine can operate at lower RPMs and loads, thereby reducing fuel consumption. Simultaneously, the system adjusts its shifting strategy accordingly, upshifting to higher gears earlier to keep the engine in the low-RPM, high-torque range as much as possible, improving fuel efficiency. For example, instead of upshifting at 90 km / h, it might now be done at 85 km / h. This allows relaxed drivers to enjoy a more comfortable and pleasant driving experience while also achieving better fuel economy. In summary, by introducing a deep belief network driving style model and making targeted adjustments to the target cruising speed based on different driving styles, the system can better adapt to the individual needs of drivers. Aggressive drivers can achieve more powerful performance, normal drivers can balance power and economy, while relaxed drivers can enjoy a more comfortable and fuel-efficient driving experience. This personalized adjustment strategy can significantly improve driver satisfaction and driving experience, while also optimizing overall vehicle performance and achieving the best balance between power, economy and comfort.

[0084] In this embodiment, the step of predicting the driving power demand for the next slope based on the vehicle power balance equation and the current position and the slope value of the road ahead includes: obtaining the vehicle driving power value, transmission efficiency, vehicle weight, friction coefficient, vehicle speed, slope, drag coefficient, frontal area and time; and calculating the variable power demand for the next slope based on the vehicle power balance equation.

[0085] Specifically, obtaining parameters such as vehicle power output, transmission efficiency, vehicle weight, coefficient of friction, vehicle speed, gradient, drag coefficient, frontal area, and time is fundamental for predicting the power demand for the next incline. Vehicle power output reflects the power required to overcome driving resistance and is closely related to factors such as vehicle speed and gradient. For example, on an uphill section, the vehicle needs to overcome greater gravitational potential energy, thus increasing the power output. Transmission efficiency represents the efficiency of transmitting engine output power to the wheels, and it is affected by the transmission system, including the gearbox and differential. Vehicle weight directly affects the vehicle's inertia and rolling resistance; under heavy loads, the vehicle's power demand increases significantly. The coefficient of friction depends on road conditions; on wet, muddy, or other low-traction surfaces, the coefficient of friction decreases, making the vehicle prone to wheel slippage and reducing the driving force transmitted to the ground. The square of vehicle speed is proportional to air resistance; the higher the speed, the greater the wind resistance the vehicle experiences, requiring more power to overcome. Gradient information can be obtained from high-precision maps; the steeper the gradient, the greater the power required for the vehicle to climb the incline. The drag coefficient and frontal area together determine the magnitude of a car's air resistance. A streamlined body design results in a lower drag coefficient and reduced driving resistance. Furthermore, since a car's power demand is time-varying, time information is needed to predict power changes over a future period. After obtaining the above parameters, the power balance equation can be used to calculate the variable power demand for the next incline. This equation considers various resistances encountered by the car, including rolling resistance, air resistance, gradient resistance, and acceleration resistance. For example, assuming a fully loaded truck weighing 40 tons, traveling at 60 km / h, with a transmission efficiency of 0.8, a friction coefficient of 0.018, a drag coefficient of 0.6, a frontal area of ​​6 square meters, a current road gradient of 5%, and a predicted gradient that will remain constant for the next 10 seconds, substituting these data into the power balance equation, we can conclude that to maintain the current speed, the car needs to provide approximately 200 kilowatts of power. If the engine is operating in its economical range with an output of 180 kW, it indicates insufficient power output. In this case, it's necessary to increase engine speed and throttle opening, or shift to a lower gear to reduce the transmission ratio and meet the power demand. Conversely, if the calculated power demand is less than the engine's current output, shifting to a higher gear and reducing throttle opening can improve fuel economy. In summary, predicting the power demand for the next uphill section based on the vehicle's power balance equation requires comprehensive consideration of vehicle parameters, road conditions, environmental conditions, and other factors. By acquiring these parameters in real-time and substituting them into the power balance equation, changes in power demand over a future period can be predicted. This provides a basis for intelligent gear shifting and throttle control, achieving comprehensive vehicle performance optimization while meeting power requirements and considering fuel economy and emissions performance. This predictive control method based on a physical model has better adaptability and robustness compared to empirical models, and can cope with complex and changing real-world road conditions.Meanwhile, the introduction of driver behavior pattern recognition can further improve prediction accuracy, making the control strategy closer to the driver's subjective intentions and enhancing the driving experience.

[0086] In this embodiment, the step of combining the engine's own high-efficiency output power range and generating the recommended gear and optimal throttle opening for the next slope based on different power requirements includes:

[0087] Obtain the high-efficiency output power range corresponding to the engine's optimal fuel consumption range;

[0088] Based on the predicted power demand for the next uphill section, a target speed value that falls within the high-efficiency output power range is determined as the recommended speed for the next uphill section.

[0089] Based on the recommended engine speed and predicted vehicle speed, the optimal gear for the next uphill section is calculated.

[0090] Obtain the speed regulation characteristic MAP, and find the optimal torque value given the known recommended speed;

[0091] The optimal torque value is converted into a throttle opening value to obtain the optimal throttle opening for the next slope.

[0092] Specifically, an engine's efficient power output range corresponds to its optimal fuel consumption range. This isn't a fixed value, but rather a region. This region is typically determined through analysis of engine experimental data and characteristic curves. An engine's fuel efficiency varies at different engine speeds and torque outputs. Under certain specific combinations of speed and torque, the engine can convert fuel into power with the highest efficiency while producing fewer emissions. This region of highest efficiency is the efficient power output range. For example, a 2.0L naturally aspirated engine operating at 2000-3000 rpm and with a torque output of 150-200 Nm might be in its optimal fuel consumption range, i.e., its efficient power output range. The reason for using this range as a reference is that keeping the engine operating within this range minimizes fuel consumption and improves fuel economy. Suppose we predict that the power demand for the next uphill section is 30 kW. By consulting the engine's characteristic curves, we find that the engine can achieve 30 kW of power output at multiple speed and torque combinations. However, to ensure fuel economy, we need to choose a speed value that falls within the efficient power output range. Assume the engine's efficient power output range corresponds to a speed range of 2200 rpm to 2800 rpm. Calculations show that at 2500 rpm, the torque output is 180 Nm, which perfectly meets the 30 kW power requirement, and the speed is within the efficient power output range. Therefore, 2500 rpm is determined as the recommended speed for the next incline. This process is not a simple matching, but rather uses an algorithm to select the speed within the efficient output range as much as possible while meeting power requirements, in order to achieve fuel economy. After determining the recommended speed, the optimal gear needs to be calculated based on the predicted vehicle speed. For example, if the current vehicle speed is 60 km / h, the recommended speed is 2500 rpm. By consulting the vehicle's gear ratio data, we can see the corresponding relationship between engine speed and vehicle speed in different gears. For example, in 3rd gear at 60 km / h, the engine speed is 3000 rpm, while in 4th gear at 60 km / h, the engine speed is 2200 rpm, and in 5th gear, the speed is even lower. Considering the recommended engine speed is 2500 rpm, and 4th gear is closest, the optimal gear is determined to be 4th gear. The shifting logic is to select a higher gear as much as possible while meeting the recommended engine speed to reduce engine speed and thus reduce fuel consumption. If calculations show that the current gear already meets the speed requirement, there is no need to shift; simply maintain the current gear. The torque characteristic map (MAP), also known as the engine torque characteristic map, is a pre-stored data table that describes the engine's torque output characteristics at different engine speeds and throttle openings. This MAP table is usually calibrated using a large amount of experimental data and reflects the engine's performance limits.Given the recommended engine speed, by consulting the MAP (Motor Performance Map) table, we can find the maximum torque the engine can output at that speed, and the corresponding throttle opening for that target torque. For example, if the recommended speed is 2500 rpm, consulting the speed regulation characteristic MAP reveals that the engine's maximum torque at 2500 rpm is 200 Nm. To meet the 30 kW power requirement, only 180 Nm of torque is needed. According to the MAP table, 180 Nm of torque corresponds to a specific throttle opening value, such as 40%. The throttle opening value is essentially the opening of the valve controlling the engine's intake air volume. The larger the throttle opening, the more air enters the cylinder, the more fuel is injected, and the greater the engine's output torque. The process of finding the optimal torque value and converting it into a throttle opening value is actually a control process, the purpose of which is to ensure the engine operates according to the calculated optimal torque output. For example, as mentioned earlier, when 180 Nm of torque is needed, consulting the MAP table reveals a throttle opening of 40%. The control system will then adjust the throttle opening to 40%, ensuring the engine outputs 180 Nm of torque. This process ensures the engine operates in the most economical way while meeting power requirements, achieving optimal fuel economy. Simultaneously, by controlling the throttle opening, precise control of engine power output can be achieved, avoiding unnecessary fuel consumption.

[0093] In this embodiment, the deep belief network driving style model is deployed on a cloud service platform and establishes a wireless communication connection with the vehicle through an in-vehicle communication module, thereby realizing personalized recognition of the user's driving style.

[0094] In practical applications, this invention utilizes road gradient information provided by high-precision maps and the target cruising speed corrected by a deep belief network driving style model as input parameters. Based on the theoretical foundation of the vehicle power balance equation, the system can predict the driving power demand for the next slope and, combined with the engine's own efficient output power range, intelligently plan the recommended gear and optimal throttle opening for the next slope. This not only achieves continuous cruise driving planning in multiple road scenarios but also fully meets users' high requirements for economy and driving comfort. As shown in Figure 4, the specific stages of this invention are described in detail below:

[0095] 1. Using engine speed and torque, a weighted moving average algorithm is used to average the power values ​​over a short period of time to obtain the current engine power. The expression for the weighted moving average algorithm is:

[0096]

[0097] The power prediction value at time t seconds. The power value at time t-1 seconds. These are the weighting coefficients. Let be the engine torque at time t. Let t be the engine speed at time t.

[0098] 2. Based on the deep belief network driving style recognition model, the speed correction value for hill crossing is assigned a positive value for aggressive style, a zero value for normal style, and a negative value for peaceful style.

[0099] 3. Obtain the current location and the slope value of the road ahead from the high-precision map terminal, and calculate the variable power demand for the next slope segment based on the vehicle power balance equation. Vehicle power balance equation:

[0100]

[0101] This is the vehicle's driving power value. For transmission efficiency, For vehicle weight, The coefficient of friction, For vehicle speed, For slope, This is the drag coefficient. For windward area, For time.

[0102] 4. After predicting the power demand for the next uphill section, and combining this with the engine's efficient output power range, the engine speed for the next uphill section is intelligently planned based on different power demands. The efficient output power range is the optimal fuel consumption range; the dark area between the two horizontal lines in the figure represents the area with the lowest fuel consumption, as shown in Figure 5.

[0103] 5. Based on the recommended engine speed and vehicle speed, the optimal gear for the next slope can be calculated; by searching the speed regulation characteristic MAP, the optimal torque value can be found under the condition of known engine speed. The engine will automatically convert the current engine speed and torque demand into the throttle opening value to obtain the optimal throttle opening for the next slope; the speed regulation characteristic MAP diagram is shown in Figure 6.

[0104] Example 2: Figure 2 is a schematic diagram of a predictive cruise control system for commercial vehicles according to Example 2 of the present invention. As shown in Figure 2, Example 2 provides a predictive cruise control system for commercial vehicles, including: an acquisition module 201, a generation module 202, a prediction module 203, and a planning module 204. The acquisition module 201 is used to acquire road slope information provided by a high-precision map and the target cruise speed corrected by a deep belief network driving style model as input parameters. The generation module 202 is used to average the power value over a short period of time based on engine speed and torque using a weighted moving average algorithm to generate the current engine power. The prediction module 203 is used to predict the driving power demand for the next slope segment based on the vehicle power balance equation, the current position, and the slope value of the road ahead. The planning module 204 is used to combine the engine's own high-efficiency output power range and generate the recommended gear and optimal throttle opening for the next slope segment according to different power demand conditions.

[0105] In this embodiment, the generation module 202 includes a first acquisition unit and a first generation unit. The first acquisition unit is used to acquire the predicted power value at time t, the power value at time t-1, the weighting coefficient, the engine torque at time t, and the engine speed at time t. The first generation unit is used to generate the current engine power according to the weighted moving average algorithm expression.

[0106] In this embodiment, the target cruising speed corrected by the deep belief network driving style model includes: a positive speed correction value for aggressive drivers; a speed correction value of 0 for normal drivers; and a negative speed correction value for neutral drivers.

[0107] In this embodiment, the prediction module 203 includes a second acquisition unit and a first calculation unit. The second acquisition unit is used to acquire the vehicle's driving power value, transmission efficiency, vehicle weight, friction coefficient, vehicle speed, gradient, drag coefficient, frontal area, and time. The first calculation unit is used to calculate the variable power demand for the next slope segment based on the vehicle's power balance equation.

[0108] In this embodiment, the planning module 204 includes: a third acquisition unit, a determination unit, a second calculation unit, a search unit, and a second generation unit. The third acquisition unit acquires the high-efficiency output power range corresponding to the engine's optimal fuel consumption range. The determination unit determines the target speed value falling within the high-efficiency output power range based on the predicted power demand for the next hill section, serving as the recommended speed for the next hill section. The second calculation unit calculates the optimal gear for the next hill section based on the recommended speed and the predicted vehicle speed. The search unit acquires the speed regulation characteristic MAP and, given the recommended speed, finds the optimal torque value. The second generation unit converts the optimal torque value into a throttle opening value, generating the optimal throttle opening for the next hill section.

[0109] In this embodiment, the deep belief network driving style model is deployed on a cloud service platform and establishes a wireless communication connection with the vehicle through an in-vehicle communication module, thereby realizing personalized recognition of the user's driving style.

[0110] The various variations and specific examples of the predictive cruise control method for commercial vehicles provided in Embodiment 1 are also applicable to the predictive cruise control system for commercial vehicles provided in this embodiment. Through the foregoing detailed description of a predictive cruise control method for commercial vehicles, those skilled in the art can clearly understand the implementation method of a predictive cruise control system for commercial vehicles in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0111] Example 3. Figure 3 is a schematic diagram of the structure of an electronic device in Example 3 of the present invention. As shown in Figure 3, Example 3 also provides an electronic device 300, which may include a processor 301 and a memory 302.

[0112] Memory 302 is used to store programs. Memory 302 may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; memory may also include non-volatile memory, such as flash memory. Memory 302 is used to store computer programs (such as application programs, functional modules, etc. that implement the above methods), computer instructions, etc. The computer programs, computer instructions, etc., can be partitioned and stored in one or more memories 302. Furthermore, the computer programs, computer instructions, data, etc., can be accessed by processor 301.

[0113] The aforementioned computer programs and instructions can be stored in one or more partitions of memory 302. Furthermore, the aforementioned computer programs and instructions can be invoked by processor 301.

[0114] The processor 301 is configured to execute the computer program stored in the memory 302 to implement the various steps in the methods described in the above embodiments.

[0115] For details, please refer to the relevant descriptions in the preceding method embodiments.

[0116] The processor 301 and the memory 302 can be independent structures or integrated structures. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 can be coupled together via bus 303.

[0117] The electronic device in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principle are the same, and will not be repeated here.

[0118] Example 4, Example 4 also provides a computer-readable storage medium including a computer program and instructions, which, when the computer program or instructions are run on a computer, cause the computer to execute the commercial vehicle predictive cruise control method of any embodiment of the present invention.

[0119] Computer-readable storage media include various media that can store program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0120] This embodiment also provides a computer program product, which includes: a computer program stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the solution provided in any of the above embodiments.

[0121] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this invention disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0122] In summary, the predictive cruise control method and system for commercial vehicles of the present invention have the following beneficial effects:

[0123] 1. By analyzing vehicle speed, location, and road information in real time, and combining this with the engine's efficient output power range, this invention can intelligently adjust gear position and throttle opening, ensuring the engine always operates within its optimal fuel consumption range. This not only reduces unnecessary fuel consumption but also improves vehicle power performance, thereby significantly improving driving efficiency and fuel economy while ensuring driving safety.

[0124] 2. This invention introduces a deep belief network driving style model, which can personalize the target cruise speed according to the driver's driving style (aggressive, normal, calm), thereby automatically adapting to the driving habits and needs of different drivers, providing a cruise control experience that is more in line with personal preferences, and thus enhancing driving comfort and satisfaction.

[0125] 3. Existing predictive cruise solutions often rely on complex calculations and data signal processing, such as energy-intensive algorithms like dynamic programming and model predictive control. This invention, however, reduces computational complexity and energy consumption by employing a weighted moving average algorithm and a physics-based prediction method, making the system more efficient and energy-saving.

[0126] 4. This invention utilizes road slope information provided by high-precision maps and combines it with the vehicle power balance equation to predict power demand, thus more accurately reflecting the actual power demand of vehicles under different road conditions. Simultaneously, by incorporating the engine's efficient output power range for gear shifting and throttle control, the system can better adapt to complex and changing real-world road conditions, improving its adaptability and robustness.

[0127] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A predictive cruise control method for commercial vehicles, characterized in that, include: The road gradient information provided by the high-precision map and the target cruising speed corrected by the deep belief network driving style model are used as input parameters. Based on engine speed and torque, a weighted moving average algorithm is used to average the power value over a short period of time to generate the current engine power. Based on the vehicle power balance equation, the driving power demand for the next slope is predicted according to the current position and the slope value of the road ahead. Based on the engine's efficient output power range and different power requirements, the recommended gear and optimal throttle opening for the next hill section are generated.

2. The predictive cruise control method for commercial vehicles as described in claim 1, characterized in that, The step of averaging the power values ​​over a short period of time using a weighted moving average algorithm includes: Obtain the predicted power value at time t, the power value at time t-1, the weighting coefficient, the engine torque at time t, and the engine speed at time t; The current engine power is calculated based on the weighted moving average algorithm expression.

3. The predictive cruise control method for commercial vehicles as described in claim 1, characterized in that, The target cruising speed, corrected by the deep belief network driving style model, includes: For drivers with an aggressive driving style, a positive speed correction value is assigned; For drivers with a normal driving style, assign a speed correction value of 0. For drivers with a calm driving style, a negative speed correction value is assigned.

4. The predictive cruise control method for commercial vehicles as described in claim 1, characterized in that, The method of predicting the driving power demand for the next uphill section based on the vehicle power balance equation, according to the current location and the slope of the road ahead, includes: Obtain vehicle power output, transmission efficiency, vehicle weight, coefficient of friction, vehicle speed, gradient, drag coefficient, frontal area, and time. Based on the vehicle power balance equation, the variable power demand for the next slope section is calculated.

5. The predictive cruise control method for commercial vehicles as described in claim 1, characterized in that, The process of combining the engine's own high-efficiency output power range and generating recommended gears and optimal throttle openings for the next uphill section based on different power demands includes: Obtain the high-efficiency output power range corresponding to the engine's optimal fuel consumption range; Based on the predicted power demand for the next uphill section, a target speed value that falls within the high-efficiency output power range is determined as the recommended speed for the next uphill section. Based on the recommended engine speed and predicted vehicle speed, the optimal gear for the next uphill section is calculated. Obtain the speed regulation characteristic MAP, and find the optimal torque value given the known recommended speed; The optimal torque value is converted into a throttle opening value to obtain the optimal throttle opening for the next slope.

6. A predictive cruise control system for commercial vehicles, characterized in that, include: The acquisition module is used to acquire road slope information provided by high-precision maps and target cruising speed corrected by a deep belief network driving style model as input parameters. The generation module is used to average the power value over a short period of time based on engine speed and torque using a weighted moving average algorithm to generate the current engine power. The prediction module is used to predict the driving power demand for the next slope based on the vehicle power balance equation, the current location, and the slope value of the road ahead. The planning module is used to combine the engine's own efficient output power range and generate the recommended gear and optimal throttle opening for the next slope based on different power requirements.

7. The predictive cruise control system for commercial vehicles as described in claim 6, characterized in that, The generation module includes: The first acquisition unit is used to acquire the power prediction value at time t, the power value at time t-1, the weighting coefficient, the engine torque at time t, and the engine speed at time t. The first generation unit is used to generate the current engine power according to the weighted moving average algorithm expression.

8. The predictive cruise control system for commercial vehicles as described in claim 6, characterized in that, The target cruising speed, corrected by the deep belief network driving style model, includes: For drivers with an aggressive driving style, a positive speed correction value is assigned; For drivers with a normal driving style, assign a speed correction value of 0. For drivers with a calm driving style, a negative speed correction value is assigned.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the commercial vehicle predictive cruise control method according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, It includes computer programs and instructions that, when the computer program or the instructions are run on a computer, cause the computer to perform the predictive cruise control method for commercial vehicles as described in any one of claims 1-5.

Images