Torque distribution method for a distributed electric drive based loader and related apparatus
By combining a two-degree-of-freedom vehicle model with an online learning neural network model, the switching gain value was optimized, solving the oscillation problem in torque distribution of distributed electric drive loaders, and achieving smoother control and reduced energy consumption.
Patent Information
- Application Number
- CN202611278112.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-21
- Publication Date
- 2026-11-17
AI Technical Summary
In existing distributed electric drive loaders, improper switching gain settings can cause the system to be unable to effectively overcome external disturbances or generate high-frequency oscillations, resulting in increased mechanical wear and energy consumption.
The target yaw rate is analyzed using a two-degree-of-freedom vehicle model. The optimal switching gain value is predicted using an online learning neural network model. The switching gain term in the sliding mode control law is determined. The expected additional yaw moment is calculated based on the vehicle yaw dynamics equation, and wheel torque is distributed accordingly.
It reduces control oscillations in loader torque, improves the smoothness of vehicle control, and reduces mechanical wear and energy consumption.
Smart Images

Figure CN123104416A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle automatic control technology, and in particular to a torque distribution method and related equipment for a loader based on distributed electric drive. Background Technology
[0002] Current torque distribution schemes for distributed electric drive loaders typically determine the loader's current operating conditions based on the weight of the material carried in the bucket. Then, based on this, they analyze the torque required for the loader to operate stably. Finally, they combine the vertical load distribution ratio of the front and rear axles of the loader to distribute the wheel torque, achieving dynamic optimal distribution of all-wheel drive torque.
[0003] In related technologies, when analyzing the desired torque process during the stable motion of a loader, a sliding mode control law can be constructed using the vehicle's actual state variables and target state variables to calculate the desired torque, enabling the system to approach and maintain a stable state. The switching gain is the core parameter of the switching control term in sliding mode control. It acts as a discontinuous control mechanism, driving the system state from any initial position to the sliding surface, and determines the system's ability to resist disturbances and uncertainties. In related technologies, the switching gain is typically configured with a fixed value. If the switching gain is set too small, the system cannot effectively overcome external disturbances, reducing robustness. If the switching gain is set too large, after the state trajectory reaches the sliding mode surface, it is difficult to strictly slide along the sliding mode surface to the equilibrium point; instead, it traverses back and forth on both sides, generating high-frequency oscillations, which in turn causes mechanical wear and increased energy consumption. Summary of the Invention
[0004] The main objective of this application is to propose a torque distribution method and related equipment for loaders based on distributed electric drive, which aims to reduce control oscillations of loader torque, thereby improving the smoothness of vehicle control and reducing mechanical wear and energy consumption.
[0005] To achieve the above objectives, one aspect of this application proposes a torque distribution method for a loader based on distributed electric drive, comprising the following steps: The loader's current motion state is balanced and force-dependent by using a two-degree-of-freedom vehicle model to determine the target yaw rate. The sliding surface state of the sliding mode variable structure control system is determined based on the target yaw rate and the actual yaw rate. The optimal switching gain value is obtained by predicting the switching gain of the sliding surface state using an online-learned neural network model. The switching gain term in the sliding mode control law is determined based on the optimal switching gain value, and the desired additional yaw moment is determined based on the sliding mode control law and the vehicle yaw dynamics equation. The desired additional yaw moment is distributed to the wheels to obtain the desired torque for each wheel of the loader.
[0006] In some embodiments, determining the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate includes the following steps: The system tracking error is determined based on the difference between the target yaw rate and the actual yaw rate. The sliding surface state of the sliding mode variable structure control system is determined based on the first derivative of the target yaw rate, the first derivative of the actual yaw rate, and the system tracking error.
[0007] In some embodiments, the neural network model is a radial basis function neural network model; the step of predicting the switching gain of the sliding surface state using an online-learned neural network model to obtain the optimal switching gain value includes the following steps: The sliding surface state and its derivative are input into the radial basis function neural network model to calculate the hidden layer radial basis function, thus obtaining the hidden layer output vector; The optimal switching gain value is obtained by weighted summation of the hidden layer output vector based on the output layer weight vector; wherein, the output layer weight vector is updated online by an adaptive law constructed based on the Lyapunov stability condition.
[0008] In some embodiments, under driving conditions, the wheel torque distribution of the desired additional yaw moment to obtain the desired torque of each wheel of the loader includes the following steps: The dynamic loads of the front and rear axles are calculated based on the current motion state of the loader to obtain the dynamic loads of the front and rear axles. The inter-axle torque distribution coefficient is determined based on the front axle dynamic load and the rear axle dynamic load. The total drive torque is distributed between shafts according to the inter-shaft torque distribution coefficient to obtain the basic drive torque of the front axle and the basic drive torque of the rear axle. Based on the desired additional yaw moment, the front axle base drive torque is distributed between the front axle wheels, and based on the desired additional yaw moment, the rear axle base drive torque is distributed between the rear axle wheels, thereby obtaining the desired torque for each wheel of the loader.
[0009] In some embodiments, determining the inter-axle torque distribution coefficient based on the front axle dynamic load and the rear axle dynamic load includes the following steps: The front axle adhesion rate calculation equation is constructed based on the effective longitudinal force of the front axle and the dynamic load of the front axle. The equation for calculating the rear axle adhesion rate is constructed based on the effective longitudinal force of the rear axle and the dynamic load of the rear axle. With the constraint that the front and rear axle adhesion rates are the same, the inter-axle torque distribution ratio is calculated by combining the front axle adhesion rate calculation equation and the rear axle adhesion rate calculation equation, and the inter-axle torque distribution coefficient is obtained.
[0010] In some embodiments, under braking conditions, the wheel torque distribution of the desired additional yaw moment to obtain the desired torque of each wheel of the loader includes the following steps: Based on the ideal braking force distribution curve, the total braking force is distributed between axles to obtain the basic braking torque of the front axle and the basic braking torque of the rear axle. Based on the desired additional yaw moment, the front axle base braking torque is distributed between the front axle wheels, and based on the desired additional yaw moment, the rear axle base braking torque is distributed between the rear axle wheels, thereby obtaining the desired torque for each wheel of the loader.
[0011] To achieve the above objectives, another aspect of this application proposes a loader torque distribution system based on distributed electric drive, comprising: The first module uses a two-degree-of-freedom vehicle model to perform a balance force analysis on the loader in its current motion state and determine the target yaw rate. The second module is used to determine the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate. The third module is used to predict the switching gain of the sliding surface state through an online learning neural network model to obtain the optimal switching gain value. The fourth module is used to determine the switching gain term in the sliding mode control law based on the optimal switching gain value, and to determine the desired additional yaw moment based on the sliding mode control law and the vehicle yaw dynamics equation. The fifth module is used to distribute the wheel torques to the desired additional yaw moment, thereby obtaining the desired torque of each wheel of the loader.
[0012] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.
[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.
[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0015] The embodiments of this application include at least the following beneficial effects: This application provides a torque distribution method and related equipment for a loader based on distributed electric drive. This scheme uses a two-degree-of-freedom vehicle model to perform a balance force analysis on the loader in its current motion state, determines the target yaw rate, determines the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate, then uses an online learning neural network model to predict the switching gain of the sliding surface state, obtains the optimal switching gain value, uses the optimal switching gain value to determine the switching gain term in the sliding mode control law, and then determines the desired additional yaw moment based on the sliding mode control law and the vehicle yaw dynamics equation. By adaptively predicting the optimal switching gain value through a neural network, the sliding mode control law can output a smooth desired additional yaw moment. Then, the desired additional yaw moment is used to distribute the wheel torque to determine the desired torque of each wheel of the loader, which can reduce the control oscillation of the loader torque, improve the smoothness of the overall vehicle control, and reduce mechanical wear and energy consumption. Attached Figure Description
[0016] Figure 1 This is a flowchart of a loader torque distribution method based on distributed electric drive provided in an embodiment of this application; Figure 2 This is a force diagram of a distributed loader provided in an embodiment of this application; Figure 3 This is a schematic diagram of the radial basis function neural network model provided in the embodiments of this application; Figure 4 This is a schematic diagram of the loader's motion state provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.
[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.
[0019] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.
[0020] The I-curve (ideal braking force distribution curve) is a curve showing the relationship between the braking forces of the front and rear wheels in order to achieve simultaneous wheel lock-up when braking on surfaces with different coefficients of adhesion. Each point on this curve corresponds to the ideal braking force distribution state when the front and rear wheels lock up simultaneously on a specific coefficient of adhesion surface.
[0021] In related technologies, when analyzing the desired torque process during the stable motion of a loader, a sliding mode control law can be constructed using the vehicle's actual state variables and target state variables to calculate the desired torque, enabling the system to approach and maintain a stable state. The switching gain is the core parameter of the switching control term in sliding mode control. It acts as a discontinuous control mechanism, driving the system state from any initial position to the sliding surface, and determines the system's ability to resist disturbances and uncertainties. In related technologies, the switching gain is typically configured with a fixed value. If the switching gain is set too small, the system cannot effectively overcome external disturbances, reducing robustness. If the switching gain is set too large, after the state trajectory reaches the sliding mode surface, it is difficult to strictly slide along the sliding mode surface to the equilibrium point; instead, it traverses back and forth on both sides, generating high-frequency oscillations, which in turn causes mechanical wear and increased energy consumption.
[0022] In view of this, this application provides a torque distribution method and related equipment for a loader based on distributed electric drive. This scheme uses a two-degree-of-freedom vehicle model to perform a balance force analysis on the loader in its current motion state, determines the target yaw rate, determines the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate, and then uses an online learning neural network model to predict the switching gain of the sliding surface state to obtain the optimal switching gain value. The optimal switching gain value is used to determine the switching gain term in the sliding mode control law, and then the desired additional yaw moment is determined based on the sliding mode control law and the vehicle yaw dynamics equation. The optimal switching gain value is adaptively predicted by the neural network, so that the sliding mode control law can output a smooth desired additional yaw moment. Then, the desired additional yaw moment is used to distribute the wheel torque to determine the desired torque of each wheel of the loader, which can reduce the control oscillation of the loader torque, improve the smoothness of the overall vehicle control, and reduce mechanical wear and energy consumption.
[0023] The torque distribution method for loaders based on distributed electric drive provided in this application relates to the field of vehicle automatic control technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster consisting of multiple physical servers, or a distributed system. It can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network.
[0024] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0025] Figure 1 This is an optional flowchart of a loader torque distribution method based on distributed electric drive provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.
[0026] S101, using a two-degree-of-freedom vehicle model, performs a balance force analysis on the loader in its current motion state to determine the target yaw rate; S102, Determine the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate; S103, the optimal switching gain value is obtained by predicting the switching gain of the sliding surface state through an online learning neural network model; S104, determine the switching gain term in the sliding mode control law based on the optimal switching gain value, and determine the desired additional yaw moment based on the sliding mode control law and the vehicle yaw dynamics equation; S105 distributes the wheel torque to the desired additional yaw moment, thus obtaining the desired torque of each wheel of the loader.
[0027] Steps S101 to S105 as shown in the embodiments of this application use a neural network to adaptively predict the optimal switching gain value, enabling the sliding mode control law to output a smooth expected additional yaw moment. Then, the expected torque of each wheel of the loader is determined by wheel torque distribution based on the expected additional yaw moment, which can reduce the control oscillation of the loader torque, improve the smoothness of the vehicle control, and reduce mechanical wear and energy consumption.
[0028] In step S101 of some embodiments, a balance force analysis is performed on the loader in its current motion state using a two-degree-of-freedom vehicle model to determine the target yaw rate. The two-degree-of-freedom vehicle model linearizes the complex mechanical relationships of a vehicle system, retaining both lateral and yaw degrees of freedom, and clearly describing the vehicle's center of gravity position, yaw response, and related parameters of sideslip motion. Please refer to... Figure 2 The force diagram of the distributed loader shown is used to establish the vehicle's equilibrium equations based on Newton's second law, i.e., the two-degree-of-freedom model of the vehicle is represented as follows: ; in, For the overall vehicle weight; This refers to the longitudinal speed of the vehicle. Lateral speed; This refers to the yaw rate; It is the centroid sideslip angle; Let be the moment of inertia about the Z-axis; These are the distances from the center of mass to the front and rear axles, respectively. , These are the front and rear axle lateral stiffness, respectively. For the front wheel steering angle, The first derivative of the lateral vehicle speed. It is the first derivative of the yaw rate.
[0029] Using the aforementioned two-degree-of-freedom vehicle model as a reference model, the driver's front wheel steering angle and current vehicle speed are input into the model to calculate the ideal dynamic response of the vehicle under stable driving conditions (i.e., the target yaw rate). Subsequently, based on the target yaw rate, the desired additional yaw moment required to maintain vehicle stability is solved in real time using a sliding mode control algorithm.
[0030] In step S102 of some embodiments, in the sliding mode control algorithm, the sliding surface state of the sliding mode variable structure control system is determined based on the target yaw rate and the actual yaw rate. The sliding surface state refers to the sliding variable... The value of itself and its derivative is a scalar function that changes over time, reflecting the degree to which the system currently deviates from the sliding surface.
[0031] In some embodiments, the step S102 of determining the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate may include, but is not limited to, the following steps: S201, determine the system tracking error based on the difference between the target yaw rate and the actual yaw rate; S202. Based on the first derivative of the target yaw rate, the first derivative of the actual yaw rate, and the system tracking error, determine the sliding surface state of the sliding mode variable structure control system.
[0032] In this embodiment, the target yaw rate is denoted as . The actual yaw rate is denoted as The system tracking error is expressed as follows: ; The sliding surface function (i.e., the sliding surface state) is represented as follows: ; in, These are the weighting coefficients for the sliding surface. The first derivative of the target's yaw rate. This is the first derivative of the actual yaw rate.
[0033] This embodiment transforms the vehicle stability control problem into a quantifiable, disturbance-insensitive, and dynamically convergent sliding mode tracking problem, laying the foundation for the subsequent design of high-performance, highly robust control laws.
[0034] In step S103 of some embodiments, online learning refers to the process whereby the neural network model outputs the optimal switching gain value and provides it to the sliding mode control law for expected yaw moment prediction and loader control, and then updates the model parameters in real time based on system stability. The neural network model can be any type of neural network structure; in this embodiment, a radial basis function neural network model, also known as an RBF network model, can be used.
[0035] In some embodiments, step S103, which involves predicting the switching gain of the sliding surface state using an online-learned neural network model to obtain the optimal switching gain value, may include, but is not limited to, the following steps: S301, input the sliding surface state and its derivative into the radial basis function neural network model to calculate the hidden layer radial basis function, and obtain the hidden layer output vector; S302, the hidden layer output vector is weighted and summed according to the output layer weight vector to obtain the optimal switching gain value; wherein, the output layer weight vector is updated online through an adaptive law constructed based on the Lyapunov stability condition.
[0036] In this embodiment, the structure of the radial basis function neural network model is as follows: Figure 3 As shown, the model input is the sliding surface state. The hidden layer uses a Gaussian function to control the range of the radial basis functions. The Gaussian function is expressed as follows: ; in, For width parameter, It is the center vector of the i-th neuron.
[0037] Model output layer output adaptive gain (i.e., optimal switching gain value): ; in, This is the output layer weight vector. This is the output of the hidden layer.
[0038] The online learning RBF network updates its weights online using the Lyapunov stability descent method: first, the current sliding surface is... and its derivative Input the network and calculate the output of the hidden layer radial basis functions. Then, using the current weights Calculate adaptive gain The adaptive gain is applied to control the loader and obtain a new sliding surface state. Then, based on the Lyapunov function-type arrival condition, an adaptive law is designed to update the weights of the RBF network. The adaptive law for weight update is expressed as follows: ; in, It is a positive diagonal learning rate matrix, based on the current... and Update network weights and adjust them in real time. The dynamic output smoothly switches the gain value, which not only ensures the ability to suppress load fluctuations and road surface disturbances, but also avoids torque chattering caused by fixed high gain.
[0039] If the Lyapunov functional arrival condition is satisfied, it indicates that the system is stable. The Lyapunov functional arrival condition is: ; ; Where s(x) is the designed sliding surface function, s(x) = 0 when the system state moves onto the target sliding surface, and V(x) is always positive when the state is not on the sliding surface; when When the value is less than 0, the system state will continue to move closer to the sliding surface and then move on the sliding surface according to the preset stable law, ultimately achieving stable control of the entire system.
[0040] In step S104 of some embodiments, the switching gain term in the sliding mode control law is determined based on the optimal switching gain value, and the desired additional yaw moment is determined based on the sliding mode control law and the vehicle yaw dynamics equation. Specifically, the vehicle yaw dynamics equation is obtained from the moment balance of the vehicle's two-degree-of-freedom model around the Z-axis: ; in, This is the longitudinal distance from the center of gravity to the front axle. The longitudinal distance from the center of mass to the rear axle The lateral force on the left wheel of the front axle The lateral force on the right wheel of the front axle, The lateral force on the left rear wheel, The lateral force on the right rear wheel, The longitudinal force on the right wheel of the front axle The longitudinal force on the left wheel of the front axle The longitudinal force on the right rear wheel, The longitudinal force on the left rear wheel, The distance between the left and right wheels on the same axle; the first and second items on the right are the basic yaw moment generated by the lateral force. The third item is the additional yaw moment generated by the difference in longitudinal forces between the four wheels. Therefore, we can conclude that: ; ; Substituting into the sliding surface function, we get: ; Equivalent control conditions of sliding mode Equivalent control items are obtained : ; ; Introducing the optimal switching gain calculated using the RBF network, we get: ; in, .
[0041] In summary, the equation for the desired additional yaw moment is expressed as: ; in, It is a symbolic function.
[0042] Substituting the equation for the desired additional yaw moment into the vehicle yaw dynamics equation, we obtain the vehicle yaw motion control law derived from RBF adaptive sliding mode control: ; The desired additional yaw torque can be output in real time using the above-mentioned vehicle yaw motion control law.
[0043] In step S105 of some embodiments, the desired additional yaw moment is distributed to the wheels to obtain the desired torque for each wheel of the loader. In this embodiment, torque is the same as force. The wheel torque distribution can be divided into driving conditions and braking conditions, as detailed below: In some embodiments, under driving conditions, step S105, which involves distributing the desired additional yaw moment to the wheels to obtain the desired torque for each wheel of the loader, may include, but is not limited to, the following steps: S401, calculate the dynamic load of the front and rear axles based on the current motion state of the loader, and obtain the dynamic load of the front axle and the dynamic load of the rear axle; S402, determine the inter-axle torque distribution coefficient based on the dynamic load of the front axle and the dynamic load of the rear axle; S403, the total drive torque is distributed between shafts according to the inter-shaft torque distribution coefficient to obtain the basic drive torque of the front axle and the basic drive torque of the rear axle; S404, based on the desired additional yaw moment, performs torque distribution between the front axle wheels on the front axle base drive torque, and based on the desired additional yaw moment, performs torque distribution between the rear axle wheels on the rear axle base drive torque, to obtain the desired torque for each wheel of the loader.
[0044] In this embodiment, the dynamic vertical load is calculated in real time based on the current motion state of the loader to adapt to the working conditions where the center of gravity fluctuates drastically during operation, thereby improving the balance of torque distribution and traction efficiency.
[0045] In step S401 of some embodiments, considering different driving conditions, the dynamic (vertical) loads of the front and rear axles can be calculated in a simplified or precise manner.
[0046] The simplified method uses the principle of torque balance and the calculation formula for the dynamic load of the front and rear axles under longitudinal acceleration and deceleration on a straight road surface. The dynamic load of the front and rear axles is calculated as follows: ; ; in, , For dynamic loads on the front and rear axles; , This is the distance from the center of mass to the front and rear axles; The longitudinal acceleration of the vehicle; The first term is the vehicle wheelbase; the second term is the static axle load, and the third term is the axle load transfer caused by acceleration and deceleration.
[0047] The precise approach involves considering real-vehicle factors such as ramps, air resistance, rolling resistance, and the inertia of rotating components. A torque extension is performed on the basic model to obtain the dynamic vertical load expressions for the front and rear axles under all operating conditions, as follows: ; in, This refers to the tire rolling resistance coefficient. This is the rotational mass conversion factor; This refers to the air drag coefficient; The vehicle's frontal area; The vehicle's center of gravity is the height above the ground. The height of the wind resistance center; The slope angle; The vehicle's speed; , This represents the static load offset between the front and rear axles. The force of gravity on the vehicle, This is the wheel's rolling radius.
[0048] In step S404 of some embodiments, determining the inter-axle torque distribution coefficient based on the front axle dynamic load and the rear axle dynamic load may include, but is not limited to, the following steps: S501, the front axle adhesion rate calculation equation is constructed based on the effective longitudinal force and dynamic load of the front axle; S502, construct the calculation equation for the rear axle adhesion rate based on the effective longitudinal force and dynamic load of the rear axle; S503, with the constraint that the front and rear axle adhesion rates are the same, the inter-axle torque distribution ratio is calculated by combining the front axle adhesion rate calculation equation and the rear axle adhesion rate calculation equation, and the inter-axle torque distribution coefficient is obtained.
[0049] In this embodiment, by constructing a calculation equation for the front and rear axle adhesion ratio and using the constraint that the front and rear axle adhesion ratios are the same, the inter-axle torque distribution coefficient to avoid loader slippage can be quickly calculated, as follows: Ideally, the adhesion ratio of the front and rear axles of a loader should be equal, i.e. ; In this case, the gradient that can be overcome is the greatest. Conversely, if the adhesion rate of a certain axle is relatively high, the wheel on that axle will slip first, and the resistance that the wheel on the other axle has to overcome will be too great, causing it to slip as well, resulting in the vehicle being unable to move forward.
[0050] Total drive torque of the whole machine for: ; In the formula, The radius of the wheel's rolling radius; For rolling resistance; For air resistance; For ramp resistance; To increase resistance.
[0051] Let the inter-shaft torque distribution coefficient be We can obtain: Front axle base torque: ; Rear axle base torque: .
[0052] According to vehicle dynamics theory, axle adhesion rate Defined as the effective longitudinal force of the axle With dynamic vertical load on this axis The ratio, the basic calculation formula is: ; The equation for calculating the front axle adhesion rate can be expressed as follows: ; The formula for calculating the rear axle adhesion rate is as follows: ; in, This is the torque distribution coefficient. For the wheel's rotational inertia, For the angular acceleration of the front axle wheels, For the front axle frictional resistance torque, For the angular acceleration of the rear axle wheels, This is the frictional resistance torque of the rear axle.
[0053] Under the condition of maintaining equal front and rear axle adhesion rates, the inter-axle torque distribution coefficient can be obtained according to the above formula. .
[0054] In step S403 of some embodiments, after obtaining the inter-shaft torque distribution coefficient... Then, according to the front axle base torque and rear axle base torque For total drive torque Perform torque distribution between shafts.
[0055] In step S404 of some embodiments, regarding the torque distribution between the left and right wheels on the same axle, the effect of wheel slippage is ignored, and the outer wheel rotates faster than the inner wheel when the vehicle turns. Please refer to... Figure 4 The diagram shown illustrates the motion of a loader, assuming the loader moves at a speed of... As the inner wheel passes through a curve of radius R, its angular velocity... and the angular velocity of the outer wheel They are respectively: ; ; The above formula represents the kinematic relationship of a wheel rolling purely based on geometric relationships when no torque is applied to the wheel.
[0056] The above formula is modified to account for the effects of tire dynamics. Considering that applying torque to the wheel will cause wheel slippage / displacement, a tire slip ratio s is introduced. ,in The angular velocity of the wheel rotation; The radius of the wheel's rolling radius; Let be the longitudinal velocity of the wheel. Based on this, the corrected angular velocities of the inner and outer wheels are: ; ; In the formula, The slip ratio of the inner wheel. The slip ratio of the outer wheel.
[0057] When a vehicle turns, due to Ackermann geometry constraints, there is a natural theoretical speed difference between the inner and outer wheels on the same axle. This speed difference can be controlled by the tire slip ratio. , Adaptive compensation enables coordinated movement. For four-wheel independent drive loaders without a mechanical differential structure, when the vehicle controller sends the same torque command to the motors of the left and right wheels on the same axle (average distribution of base torque), the motors allow the wheels on both sides to autonomously form a speed difference, relying on slight tire slippage to achieve flexible differential. If a difference is actively applied to the base torque of the same axle, an unexpected yaw moment will be introduced, interfering with the target additional yaw moment output by the upper stability controller. Therefore, in the base distribution stage without stability correction, the base torque of the wheels on both sides of the same axle adopts an average distribution strategy.
[0058] The base torque for the four wheels is: ; Additional yaw moment introduced from the upper sliding mode controller output The torque difference between the left and right wheels is obtained. ; The final driving torque of the four wheels (i.e., the expected torque under driving conditions) is: ; in, The desired torque for the left front wheel. The desired torque for the right front wheel. The desired torque for the left rear wheel. This represents the desired torque for the left rear wheel. It's understandable that in a right turn, the torque distribution formulas for the left and right wheels would be reversed.
[0059] In some embodiments, under braking conditions, step S105, which involves distributing the desired additional yaw moment to the wheels to obtain the desired torque for each wheel of the loader, may include, but is not limited to, the following steps: S601, based on the ideal braking force distribution curve, performs inter-axle torque distribution of the total braking force to obtain the basic braking torque of the front axle and the basic braking torque of the rear axle; S602, based on the desired additional yaw moment, performs torque distribution between the front axle wheels to the front axle base braking torque, and based on the desired additional yaw moment, performs torque distribution between the rear axle wheels to the rear axle base braking torque, thereby obtaining the desired torque for each wheel of the loader.
[0060] In this embodiment, after the basic braking force distribution between the front and rear axles is completed based on the I curve, the wheel braking force distribution can be carried out in the same way as in the embodiment of step S404 above. That is, the basic braking force of each axle is first evenly distributed to the left and right wheels of the same axle, and then combined with the desired additional yaw moment output by the upper RBF adaptive sliding mode controller. The differential braking force of the left and right wheels on the same axle is corrected to generate the required yaw moment while keeping the total braking force of a single axle constant, thus taking into account both anti-lock braking and steering stability.
[0061] Please refer to the diagram. The I-curve is a non-linear front-to-rear axle braking force distribution curve, appearing as a downward-opening parabola passing through the origin. When a vehicle brakes, dynamic axle load transfer occurs due to inertial forces. To prevent wheel lock-up, under any road surface adhesion coefficient, both front and rear wheels should simultaneously reach the road surface adhesion limit, i.e., the I-curve. Distributing braking force according to the I-curve ensures that both front and rear wheels lock up simultaneously on any road surface with any adhesion coefficient, maximizing the utilization of ground adhesion conditions. The front and rear axle braking forces satisfy the following relationship (i.e., the explicit formula of the I-curve): ; In the formula, and These are the front and rear axle braking forces, respectively. The total mass of the vehicle; The height of the car's center of gravity; This refers to the wheelbase; This is the distance from the car's center of gravity to the rear axle.
[0062] Specifically, based on braking deceleration The ratio of braking intensity to gravitational acceleration is used to calculate braking strength. The total braking torque is calculated based on the braking intensity and vehicle mass. The total braking torque is then distributed to the front and rear axles using the inter-axle braking force distribution coefficient calculated from the I curve above.
[0063] In addition, an energy recovery strategy is introduced into the inter-shaft torque distribution process, that is, constraints are imposed on motor speed, motor external characteristics, and energy storage unit SOC. If the motor speed is low, the regenerative braking torque is small, or the energy storage unit SOC is too high or too low, then energy recovery is not required.
[0064] This embodiment employs an adaptive sliding mode control algorithm based on an RBF neural network, enabling precise and smooth calculation of the yaw moment required to maintain vehicle stability. This effectively avoids the chattering phenomenon of traditional sliding mode control, significantly improving vehicle handling stability under extreme conditions such as double lane change and step steering. Considering load transfer during acceleration, a torque distribution method based on wheel vertical load is designed. This ensures that wheels with larger vertical loads have greater traction, preventing wheel slippage due to smaller vertical loads and improving vehicle motion stability.
[0065] This application also provides a loader torque distribution system based on distributed electric drive, including: The first module uses a two-degree-of-freedom vehicle model to perform a balance force analysis on the loader in its current motion state and determine the target yaw rate. The second module is used to determine the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate. The third module is used to predict the switching gain of the sliding surface state through an online learning neural network model to obtain the optimal switching gain value. The fourth module is used to determine the switching gain term in the sliding mode control law based on the optimal switching gain value, and to determine the desired additional yaw moment based on the sliding mode control law and the vehicle yaw dynamics equation. The fifth module is used to distribute the wheel torque to the desired additional yaw moment, thereby obtaining the desired torque of each wheel of the loader.
[0066] It is understood that the methods described in the above method embodiments are applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.
[0067] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.
[0068] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0069] Please see Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901. The 903 input / output interface is used to implement information input and output. The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.
[0070] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.
[0071] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.
[0072] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0073] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0074] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0075] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.
[0076] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.
[0077] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0078] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.
[0079] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0080] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.
[0081] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0082] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0083] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.
[0084] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0085] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.
Claims
1. A torque distribution method for a loader based on distributed electric drive, characterized in that, Includes the following steps: The loader's current motion state is balanced and force-dependent by using a two-degree-of-freedom vehicle model to determine the target yaw rate. The sliding surface state of the sliding mode variable structure control system is determined based on the target yaw rate and the actual yaw rate. The optimal switching gain value is obtained by predicting the switching gain of the sliding surface state using an online-learned neural network model. The switching gain term in the sliding mode control law is determined based on the optimal switching gain value, and the desired additional yaw moment is determined based on the sliding mode control law and the vehicle yaw dynamics equation. The desired additional yaw moment is distributed to the wheels to obtain the desired torque for each wheel of the loader.
2. The loader torque distribution method based on distributed electric drive according to claim 1, characterized in that, The process of determining the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate includes the following steps: The system tracking error is determined based on the difference between the target yaw rate and the actual yaw rate. The sliding surface state of the sliding mode variable structure control system is determined based on the first derivative of the target yaw rate, the first derivative of the actual yaw rate, and the system tracking error.
3. The loader torque distribution method based on distributed electric drive according to claim 1, characterized in that, The neural network model is a radial basis function neural network model; the online-learned neural network model predicts the switching gain of the sliding surface state to obtain the optimal switching gain value, including the following steps: The sliding surface state and its derivative are input into the radial basis function neural network model to calculate the hidden layer radial basis function, thus obtaining the hidden layer output vector; The optimal switching gain value is obtained by weighted summation of the hidden layer output vector based on the output layer weight vector; wherein, the output layer weight vector is updated online by an adaptive law constructed based on the Lyapunov stability condition.
4. The loader torque distribution method based on distributed electric drive according to claim 1, characterized in that, Under driving conditions, the process of distributing wheel torques to the desired additional yaw moment to obtain the desired torque for each wheel of the loader includes the following steps: The dynamic loads of the front and rear axles are calculated based on the current motion state of the loader to obtain the dynamic loads of the front and rear axles. The inter-axle torque distribution coefficient is determined based on the front axle dynamic load and the rear axle dynamic load. The total drive torque is distributed between shafts according to the inter-shaft torque distribution coefficient to obtain the basic drive torque of the front axle and the basic drive torque of the rear axle. Based on the desired additional yaw moment, the front axle base drive torque is distributed between the front axle wheels, and based on the desired additional yaw moment, the rear axle base drive torque is distributed between the rear axle wheels, thereby obtaining the desired torque for each wheel of the loader.
5. The loader torque distribution method based on distributed electric drive according to claim 4, characterized in that, Determining the inter-axle torque distribution coefficient based on the front axle dynamic load and the rear axle dynamic load includes the following steps: The front axle adhesion rate calculation equation is constructed based on the effective longitudinal force of the front axle and the dynamic load of the front axle. The equation for calculating the rear axle adhesion rate is constructed based on the effective longitudinal force of the rear axle and the dynamic load of the rear axle. With the constraint that the front and rear axle adhesion rates are the same, the inter-axle torque distribution ratio is calculated by combining the front axle adhesion rate calculation equation and the rear axle adhesion rate calculation equation, and the inter-axle torque distribution coefficient is obtained.
6. The loader torque distribution method based on distributed electric drive according to claim 1, characterized in that, Under braking conditions, the process of distributing wheel torques to the desired additional yaw moment to obtain the desired torque for each wheel of the loader includes the following steps: Based on the ideal braking force distribution curve and energy recovery strategy, the total braking force is distributed between axles to obtain the basic braking torque of the front axle and the basic braking torque of the rear axle. Based on the desired additional yaw moment, the front axle base braking torque is distributed between the front axle wheels, and based on the desired additional yaw moment, the rear axle base braking torque is distributed between the rear axle wheels, thereby obtaining the desired torque for each wheel of the loader.
7. A loader torque distribution system based on distributed electric drive, characterized in that, include: The first module uses a two-degree-of-freedom vehicle model to perform a balance force analysis on the loader in its current motion state and determine the target yaw rate. The second module is used to determine the sliding surface state of the sliding mode variable structure control system based on the target yaw rate and the actual yaw rate. The third module is used to predict the switching gain of the sliding surface state through an online learning neural network model to obtain the optimal switching gain value. The fourth module is used to determine the switching gain term in the sliding mode control law based on the optimal switching gain value, and to determine the desired additional yaw moment based on the sliding mode control law and the vehicle yaw dynamics equation. The fifth module is used to distribute the wheel torques to the desired additional yaw moment, thereby obtaining the desired torque of each wheel of the loader.
8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.
