Commercial vehicle within-sight-distance energy management method, device and equipment and storage medium

Abstract

The invention discloses an energy management method, device and equipment for a commercial vehicle within a sight distance, and a storage medium, and relates to the technical field of new energy vehicles, and the method comprises the steps: obtaining energy constraint information, power forecast information and energy information of the commercial vehicle within the sight distance; inputting the energy constraint information, the power forecast information and the energy information into a vehicle end prediction model to predict an output current in a predefined period, and determining an output current control instruction, the vehicle end prediction model is obtained by correcting a voltage tracking item, a control smooth item and a life loss item of a corresponding target optimization function according to the energy constraint information, the power forecast information and the energy information; and controlling the vehicle to perform pre-charging on a low-voltage bus based on the output current control instruction to complete energy management of the commercial vehicle within the sight distance. According to the application, the cloud energy pipe gallery and the vehicle end power forecast are combined, and the control instruction is optimized in a rolling manner by using the prediction model, so that electricity is supplemented in advance and voltage drop is avoided.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to methods, devices, equipment and storage media for energy management within line of sight of commercial vehicles. Background Technology

[0002] With the rapid development of new energy commercial vehicles, their low-voltage power supply systems need to provide stable power to high-power sensitive devices such as intelligent driving domain controllers, steer-by-wire / brake actuators, and lidar. These devices are extremely sensitive to voltage fluctuations; a momentary voltage drop may cause the intelligent driving system to restart, leading to serious safety accidents during high-speed driving. Therefore, it is necessary to ensure that the low-voltage bus voltage remains stable under sudden load changes.

[0003] Currently, existing practices employ feedback mechanisms based on PID or rule-based control. These mechanisms only adjust the DC-DC converter output to compensate for voltage drops when an actual voltage dip is detected, or allow the DC-DC converter to continuously output a high voltage or frequently perform high-current charging and discharging, sacrificing battery life for system stability. However, because the current control method is a feedback mechanism, the DC-DC converter's adjustment always lags behind actual load changes, failing to respond in advance. This makes transient voltage drops unavoidable, triggering undervoltage protection and restarting the system. This can cause the vehicle to briefly lose control while driving, posing a significant safety risk. Furthermore, continuously maintaining a high DC-DC output or frequently performing high-current charging and discharging significantly accelerates the aging of low-voltage batteries, reduces their health, and increases maintenance costs throughout the vehicle's lifecycle. Therefore, how to achieve safer and more effective energy management within line of sight for commercial vehicles has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for line-of-sight energy management of commercial vehicles, aiming to solve the technical problem of how to perform line-of-sight energy management of commercial vehicles more safely and effectively.

[0006] To achieve the above objectives, this application proposes a method for energy management within line of sight of commercial vehicles, the method comprising: Acquire energy constraint information, power prediction information, and energy information within the line of sight of commercial vehicles; Based on the energy constraint information, the power forecast information, and the energy information, the vehicle-side prediction model predicts the output current within a predefined period and determines the output current control command. The vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function according to the energy constraint information, power forecast information, and energy information. Based on the output current control command, the vehicle is controlled to pre-charge the low-voltage bus, thus completing the energy management within the line of sight of the commercial vehicle.

[0007] In one embodiment, the step of obtaining energy constraint information within the line of sight of a commercial vehicle includes: Obtain navigation path information and load information within the line of sight of commercial vehicles; Based on the navigation path information, the road slope features and vehicle speed features within the predefined slice segment range are extracted to determine the road slope information and vehicle speed information; Based on the load information, road slope information, and vehicle speed information, a predefined full vehicle energy consumption model is input to predict the energy trajectory and determine the energy trajectory information. Based on the energy trajectory information, corresponding energy constraint information is generated.

[0008] In one embodiment, the step of generating corresponding energy constraint information based on the energy trajectory information includes: Acquire energy recovery constraint information and physical hard constraint information; The corresponding soft constraints of the utility tunnel are determined based on the energy recovery constraint information and the energy trajectory information. Energy constraint information is determined based on the physical hard constraints and the cloud-based utility tunnel soft constraints.

[0009] In one embodiment, the step of predicting the output current within a predefined period based on the energy constraint information, the power forecast information, and the energy information input to the vehicle-side prediction model, and determining the output current control command, includes: The corresponding state vector is determined based on the capacitor voltage, inductor current, battery open-circuit voltage, and battery polarization voltage in the energy information. Based on the speed change information and braking information in the power prediction information, the disturbance vector in the predefined prediction step is determined; Based on the energy constraint information, the state vector, and the disturbance vector, the vehicle-end prediction model predicts the output current within a predefined period to obtain the output current control command.

[0010] In one embodiment, the step of predicting the output current within a predefined period based on the energy constraint information, the state vector, and the disturbance vector input to the vehicle-end prediction model to obtain the output current control command includes: Obtain shadow mode information; The vehicle-side prediction model is simulated and verified based on the shadow pattern information to determine the target vehicle-side prediction model. Based on the energy constraint information, the state vector, and the disturbance vector, the target vehicle-side prediction model is input to correct the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding target optimization function, and to determine the control vector. Based on the control vector, the control quantity of the output current within a predefined period is calculated to obtain the output current control command.

[0011] In one embodiment, after the step of calculating the control quantity corresponding to the predefined period based on the target control vector to obtain the output current control command, the method further includes: Obtain the actual bus voltage; The target control vector is calibrated and updated online using the Kalman filter algorithm and the actual bus voltage to determine the updated control vector. The control quantity corresponding to the predefined period is calculated based on the updated control vector to obtain the output current control command.

[0012] In one embodiment, after the step of controlling the vehicle to pre-charge the low-voltage bus based on the output current control command to complete the energy management within the line of sight of the commercial vehicle, the method further includes: Obtain monitoring fault information and timeout fault information; In response to the output current control command, the corresponding control strategy information is determined based on the monitored fault information and the timeout fault information; The vehicle is controlled to perform emergency power replenishment or maintain basic power based on the control strategy information.

[0013] Furthermore, to achieve the above objectives, this application also proposes a commercial vehicle line-of-sight energy management device, the commercial vehicle line-of-sight energy management device comprising: The acquisition module is used to acquire energy constraint information, power forecast information, and energy information within the line of sight of commercial vehicles; The processing module is used to predict the output current within a predefined period based on the energy constraint information, the power forecast information and the energy information input to the vehicle-end prediction model, and determine the output current control command. The vehicle-end prediction model is obtained by correcting the voltage tracking term, control smoothing term and lifetime loss term of the corresponding objective optimization function according to the energy constraint information, the power forecast information and the energy information. The execution module is used to control the vehicle to pre-charge the low-voltage bus based on the output current control command, thereby completing the energy management within the line of sight of the commercial vehicle.

[0014] In addition, to achieve the above objectives, this application also proposes a commercial vehicle line-of-sight energy management device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the commercial vehicle line-of-sight energy management method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the commercial vehicle line-of-sight energy management method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This embodiment proposes a line-of-sight energy management method for commercial vehicles. It acquires energy constraint information, power forecast information, and energy information within the line-of-sight range of the commercial vehicle. Based on the energy constraint information, power forecast information, and energy information, it inputs the data into a vehicle-side prediction model to predict the output current within a predefined period, determining the output current control command. The vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function based on the energy constraint information, power forecast information, and energy information. Based on the output current control command, it controls the vehicle to pre-charge the low-voltage bus, completing the line-of-sight energy management for the commercial vehicle. This application generates a long-line-of-sight energy-constrained tunnel based on high-precision maps and operating condition information through a cloud-based shadow controller. It also connects to the power prediction signal of the intelligent driving system and builds a multi-objective prediction model on the vehicle side that integrates voltage tracking, control smoothing, and battery life loss. It continuously solves for the optimal current command and controls the DC-DC converter to perform pre-charge in advance, completing energy storage before load changes. This completely avoids the risk of undervoltage in intelligent driving and prevents the battery from being subjected to unnecessary shocks, significantly extending battery life. It takes into account both global planning and real-time response, improving the overall energy efficiency and adaptability of the system. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the system architecture for the commercial vehicle line-of-sight energy management method of this application; Figure 2 This is a flowchart illustrating an embodiment of the commercial vehicle line-of-sight energy management method of this application. Figure 3 This is a flowchart illustrating Embodiment 2 of the commercial vehicle line-of-sight energy management method of this application; Figure 4 This is a schematic diagram of the module structure of the commercial vehicle line-of-sight energy management device according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the energy management method for commercial vehicles within line of sight in the embodiments of this application.

[0020] Explanation of icon numbers: k, discrete time step index; State vector, i.e., the internal state of the system; 1. Control input vector, i.e., DC-DC control quantity; Output vector, i.e., the observable output of the system; Disturbance vector, i.e., external load current; Prediction Horizon; Sampling time; Low-voltage bus voltage; Reference voltage, i.e., the target desired voltage; State weight matrix; Control weight matrix; The lower limit of the voltage corridor issued by the cloud; The upper limit of voltage corridor issued by the cloud; Road slope; Vehicle speed; SOC predicts trajectory; DC-DC output current command; Load current; Battery life loss function; Battery aging weighting coefficient; Battery current; 1. Battery rated capacity; Δt, forecast lead time; ε, soft constraint relaxation factor; , System state matrix; The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is as follows: acquiring energy constraint information, power forecast information, and energy information within the line of sight of a commercial vehicle; inputting the energy constraint information, power forecast information, and energy information into a vehicle-side prediction model to predict the output current within a predefined period, and determining the output current control command. The vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function based on the energy constraint information, power forecast information, and energy information; and controlling the vehicle to pre-charge the low-voltage bus based on the output current control command to complete the energy management within the line of sight of the commercial vehicle.

[0024] In this embodiment, for ease of description, the following description will focus on identifying energy management devices within the line of sight of commercial vehicles.

[0025] Because existing technologies use a feedback control mechanism, the adjustment actions of DC-DC converters always lag behind the actual changes in load, failing to respond in advance. This makes it difficult to avoid transient voltage drops, which will trigger the system's undervoltage protection and restart, causing the vehicle to briefly lose control while driving, posing a significant safety risk. Furthermore, continuous high-level output from the DC-DC converter or frequent high-current charging and discharging will significantly accelerate the aging of low-voltage batteries, reduce their health, and increase the maintenance costs throughout the vehicle's life cycle.

[0026] This application provides a solution, such as Figure 1 As shown, Figure 1This is a schematic diagram of the system architecture for the commercial vehicle line-of-sight energy management method of this application. It adopts a two-layer model predictive control (MPC) architecture that combines cloud-based long-line-of-sight planning with vehicle-side short-line-of-sight control. The cloud layer uses slope and curvature information provided by high-precision maps, real-time traffic flow speed, weather conditions, and historical vehicle energy consumption models to run a shadow controller. It predicts the vehicle's power demand for the next 10-30 minutes and generates a coarse-grained energy demand corridor. This corridor is sent to the vehicle via a 4G / 5G network in the form of dynamic constraints on voltage or SOC. The vehicle layer receives the energy corridor constraints sent from the cloud and the power forecast signals issued in advance by the intelligent driving system. It also combines real-time collected millisecond-level voltage and current feedback to run a high-speed MPC solver to handle transient load changes. This ensures that the bus voltage remains stable while meeting the cloud constraints and outputs the PWM duty cycle or current command to the DC-DC converter, achieving precise and forward-looking energy regulation. Specifically, the cloud can act as a global planner, predicting the vehicle's power demand based on long-range information, such as predicting the vehicle's power demand based on high-precision maps and real-time weather over the next ten kilometers, and calculating the safe operating range that the low-voltage battery's SOC should maintain, i.e., the energy corridor. This information is then sent to the vehicle via 4G / 5G networks. The vehicle acts as a front-line commander, receiving the cloud corridor constraints while simultaneously acquiring power forecast signals issued by the intelligent driving system hundreds of milliseconds before the action is executed. Combined with real-time voltage, current, and other vehicle status, the MPC controller continuously solves for the optimal control command, thereby instructing the DC-DC converter to preemptively replenish power before a sudden increase in load. It also continuously re-predicts and adjusts using a high-frequency closed loop, achieving precise energy management that stabilizes voltage, ensures safety, and balances energy efficiency and battery life.

[0027] As can be seen from the above embodiments, this application generates a long line-of-sight energy-constrained tunnel based on high-precision maps and operating condition information through a cloud-based shadow controller. At the same time, it connects to the power prediction signal of the intelligent driving system and builds a multi-objective prediction model that integrates voltage tracking, control smoothing, and battery life loss on the vehicle side. It continuously solves for the optimal current command and controls the DC-DC converter to perform pre-charge in advance, completing energy storage before load changes. This completely avoids the risk of undervoltage in intelligent driving while preventing the battery from being subjected to unnecessary shocks, significantly extending battery life, taking into account both global planning and real-time response, and improving the overall energy efficiency and adaptability of the system.

[0028] Based on this, embodiments of this application provide a method for energy management within line of sight of commercial vehicles, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the commercial vehicle line-of-sight energy management method of this application.

[0029] In this embodiment, the commercial vehicle line-of-sight energy management method includes steps S10 to S30: Step S10: Obtain energy constraint information, power prediction information, and energy information within the line of sight of the commercial vehicle; It should be noted that the energy constraint information is a dynamic boundary condition generated by the cloud shadow controller based on long line-of-sight prediction to constrain the energy management behavior of the vehicle. The power prediction information is a load prediction signal sent by the autonomous driving domain controller to the energy management system in advance before executing a high-power action, such as before steer-by-wire or emergency braking. The energy information is the real-time status data of the vehicle's low-voltage power supply system during operation, representing the current actual energy status of the system.

[0030] Understandably, the energy constraint information can be represented as an energy demand corridor. By integrating high-precision maps, traffic flow speed, weather conditions, and historical vehicle energy consumption models, the system predicts the vehicle's power demand for the next 10-30 minutes and calculates the allowable operating range of the low-voltage battery voltage or SOC, i.e., the upper and lower limits of the corridor. This information is then transmitted to the vehicle controller via a 4G / 5G network as a red line that must be followed when executing control, ensuring that energy scheduling is carried out within a safe and efficient range. The power forecast information can be issued approximately 200 milliseconds before the action occurs, clearly informing the system of sudden changes in load power at a certain future moment, such as a sudden increase in steering motor power from 200W to 2000W. This allows the energy management system to detect and prepare for the upcoming power surge in advance, ensuring voltage stability and system safety. The energy information can include physical quantities such as bus voltage, load current, battery SOC, capacitor voltage, inductor current, battery open-circuit voltage, and polarization voltage, used to describe the actual energy state of the system, ensuring that control commands match the actual system state, and improving the accuracy and adaptability of control.

[0031] In a specific embodiment, navigation path information and load information within the line of sight of the commercial vehicle are acquired; based on the navigation path information, road slope features and vehicle speed features within a predefined slice segment range are extracted to determine road slope information and vehicle speed information; based on the load information, road slope information, and vehicle speed information, a predefined full-vehicle energy consumption model is input to predict the energy trajectory to determine energy trajectory information; energy recovery constraint information and physical hard constraint information are acquired; based on the energy recovery constraint information and energy trajectory information, the corresponding utility tunnel soft constraint is determined; based on the physical hard constraint and the cloud-based utility tunnel soft constraint, energy constraint information is determined. That is, the acquisition of energy constraint information can be achieved through the vehicle-cloud communication module, which periodically receives dynamic energy demand utility tunnels generated based on long-term domain prediction from the cloud shadow controller, transmits them to the vehicle-side gateway in the form of serialized data packets via a 4G / 5C network, and provides them to the energy management controller after security verification. For example, based on the vehicle's navigation path, the road for the next 10 kilometers can be divided into continuous segments, and the slope of each segment can be extracted. With predicted vehicle speed Based on this, load prediction is performed. The power steering load is calculated proportionally to the road curvature, while the cooling fan load is correlated with the duration of continuous uphill driving and the ambient temperature. The predicted load data and operating condition information are input into a pre-trained vehicle energy consumption model to calculate the reference trajectory of the low-voltage battery SOC in the future period. To ensure energy recovery during long downhill runs, safety operation constraints are set, requiring the State of Charge (SOC) to remain above 80% at all times. This generates a time-series sequence of voltage or SOC constraint boundaries. The power forecast information is transmitted to the vehicle via the network, serving as a dynamic guideline boundary for vehicle energy management. This power forecast information is obtained by subscribing to forecast messages published by the intelligent driving domain controller on the vehicle's Ethernet network, such as the SOME / IP protocol. When the autonomous driving domain controller plans a high-power action to be executed, it sends a signal via the vehicle's Ethernet network Δt (e.g., 200ms) in advance. This signal can include the event type, the magnitude of the power surge, and accurate time offset information. For example, Event A (lane change / cornering) predicts that the power of the steer-by-wire motor will surge from 200W to 2000W after 200ms; Event B (emergency braking) predicts that the power of the brake-by-wire pump will surge from 0W to 1500W after 100ms. The MPC controller converts this information into a disturbance vector in the future prediction step. The energy management system monitors and parses the message in real time to know the future transient load. At the same time, the acquisition of energy information relies on the sensor network deployed in the vehicle's low-voltage electrical system. The high-precision ADC synchronously samples the bus voltage and current at a millisecond frequency. The battery management system (BMS) provides battery open-circuit voltage, polarization voltage, and temperature status parameters in real time through communication interfaces such as SMBus or I2C. All sensor data is transmitted to the central controller through the CAN bus or vehicle Ethernet in a high-bandwidth, low-latency manner and is fused to form the state vector of the system's instantaneous energy state.

[0032] In one feasible implementation, step S10 may include steps A11 to A14: Step A11: Obtain navigation path information and load information within the line of sight of the commercial vehicle; It should be noted that the navigation path information is a high-precision data set of the future driving route planned by the vehicle navigation system, and the load information is the power demand characteristics of various electrical devices under different operating conditions during vehicle operation.

[0033] It is understood that the navigation path information may include the geographical coordinate sequence of the path, the road slope, curvature and altitude changes provided by the high-precision map, and combined with real-time or predicted traffic flow conditions to form an estimate of the vehicle's future speed, acceleration and driving conditions. The load information may include the current and torque correspondence of the steer-by-wire system in curves, the pump power consumption of the braking system during deceleration, and the fan power curve of the cooling system under different ambient temperatures and motor loads, which are used to build or calibrate the whole vehicle energy consumption model to accurately predict the vehicle's low-voltage power demand in future periods.

[0034] Step A12: Based on the navigation path information, extract the road slope features and vehicle speed features within the predefined slice segment range to determine the road slope information and vehicle speed information; It should be noted that the road slope information is based on the longitudinal inclination of the future driving segment extracted from the high-precision map based on the vehicle's planned path. It is expressed as an angle or percentage slope value and is divided into segments according to the path location to characterize the uphill or downhill conditions faced by the vehicle on different road segments.

[0035] It is understood that the vehicle speed information is a predicted sequence of the vehicle's future driving speed in the energy management prediction time domain. It is generated by comprehensively considering real-time traffic flow status, route speed limits, traffic light phases, and vehicle dynamic characteristics. It exists in the form of a speed value sequence indexed by time or location and is used to characterize the vehicle's future motion state and driving conditions, directly affecting the prediction accuracy of the vehicle's low-voltage power demand.

[0036] Step A13: Based on the load information, road slope information, and vehicle speed information, input a predefined full vehicle energy consumption model to predict the energy trajectory and determine the energy trajectory information; It should be noted that the energy trajectory information is a predicted change curve of the low-voltage battery state of charge in a future driving cycle, which is obtained by calculating the full vehicle energy consumption model in the cloud and is represented in the form of a time series.

[0037] Step A14: Generate corresponding energy constraint information based on the energy trajectory information.

[0038] It is understood that the energy trajectory information is ordered over time and represents the future evolution trend of the battery's energy state, providing a forward-looking energy state reference trajectory for short-term vehicle control, thereby enabling long-term prediction and global planning of system energy changes.

[0039] In one feasible implementation, step A14 may include steps B11 to B13: Step B11: Obtain energy recovery constraint information and physical hard constraint information; It should be noted that the energy recovery constraint information is a pre-set energy management boundary condition that can effectively recover braking energy. For example, it requires that the state of charge of the low-voltage battery not be lower than a certain threshold before entering the downhill section. The physical hard constraint information is an insurmountable operating limit parameter determined by the hardware characteristics of the vehicle's low-voltage electrical system.

[0040] It is understood that the energy recovery constraint information is used to reserve sufficient storage space for energy recovery, so as to avoid the inability to absorb recovered energy due to battery saturation, thereby improving the overall energy efficiency of the system. The physical hard constraint information may include the maximum output current and voltage range of the DC-DC converter, the maximum allowable charging and discharging current of the low-voltage battery, and the safe upper and lower limits of the bus voltage. As hard boundaries that the control system must comply with, it ensures that all energy management commands are executed within the hardware safety tolerance, preventing equipment overload or damage.

[0041] Step B12: Determine the corresponding soft constraints of the utility tunnel based on the energy recovery constraint information and the energy trajectory information; It should be noted that the soft constraint of the utility tunnel is the boundary of the low-voltage system voltage or SOC operating range given in time series form by the cloud, i.e., the energy demand utility tunnel. In the vehicle-side MPC optimization problem, this constraint is modeled as a soft constraint that allows for a small amount of relaxation, that is, it allows the actual state to temporarily deviate from the boundary within a limited range. Thus, under the premise of strictly following the physical hard constraints, it ensures that the optimization problem always has a feasible solution under dynamic and uncertain operating conditions, and realizes flexible control under the guidance of global optimization.

[0042] Step B13: Determine energy constraint information based on the physical hard constraints and the cloud-based utility tunnel soft constraints.

[0043] Understandably, the control algorithm uses physical hard constraints as insurmountable absolute boundaries, and within these boundaries, it uses cloud-based soft constraints as the optimization tracking target, approximating it within an allowable relaxation range to form comprehensive constraints that both ensure hardware safety and reflect the cloud-based long-line-of-sight optimization intent, which can be directly used for real-time rolling optimization on the vehicle side.

[0044] Step S20: Based on the energy constraint information, the power forecast information, and the energy information, the vehicle-side prediction model is input to predict the output current within a predefined period and determine the output current control command. The vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function according to the energy constraint information, the power forecast information, and the energy information. It should be noted that the output current control command is a control quantity calculated by the vehicle-side MPC controller in each control cycle after rolling the solution of a multi-objective optimization problem that integrates voltage tracking, control smoothing, and battery life. This quantity is used to directly adjust the operating state of the DC-DC converter.

[0045] Understandably, the vehicle-side predictive model is a model deployed in the vehicle controller to characterize the dynamic characteristics of the low-voltage power supply system. It can predict the evolution of the system state in the short time domain within each control cycle, thereby achieving voltage stability and energy regulation.

[0046] In a specific embodiment, the corresponding state vector is determined based on the capacitor voltage, inductor current, battery open-circuit voltage, and battery polarization voltage in the energy information; the disturbance vector in the predefined prediction step is determined based on the speed change information and braking information in the power forecast information; the output current within the predefined period is predicted based on the energy constraint information, the state vector, and the disturbance vector input to the vehicle-side prediction model to obtain the output current control command, thus establishing a discrete state-space model of the low-voltage power supply system at the vehicle end. x k+1 =A sys ·x k +B sys ·u k +B dist ·w k y k =C sys x k Where, x k This is a state vector, containing [capacitor voltage] v cap Inductor current i ind Battery open circuit voltage v ocv Battery polarization voltage v pol ], u k For control vector, i.e., DC-DC output current command w k The disturbance vector is the load current. .

[0047] Therefore, an optimization objective function is constructed. In each control cycle, the following quadratic programming (QP) problem is constructed, where the objective function is... Represented as: ) Among them, voltage tracking term for:

[0048] The bus voltage must closely follow the reference value (e.g., 28V).

[0049] Control smoothing term for:

[0050] The control quantity should change smoothly (Δu) to reduce jitter.

[0051] Lifespan loss item for:

[0052] Defined as:

[0053] That is, minimize high-rate charging and discharging of the battery. .

[0054] The constraints are as follows: Physical hard constraints are represented as: u min ≤ u k ≤ u max Δ u min ≤( u k u k 1)≤Δ u max The soft constraints of the cloud-based utility tunnel are represented as follows: tunnel min,k ε ≤ y k ≤tunnel max,k + ε Among them, tunnel min,k The lower limit of the voltage tunnel is issued from the cloud. max,k The upper limit of the voltage corridor is issued from the cloud, and slight relaxation is allowed. ε To ensure the feasibility of the solution.

[0055] The above problem is solved on a microprocessor using an embedded QP solver to obtain the optimal control sequence. Uopt =[ u 0, u 1, ..., u Np 1], which is the output current control command.

[0056] Following this, shadow mode verification can be performed. Upon initial deployment or upon receiving updated model parameters via OTA, the system does not immediately switch controllers but enters shadow mode. The existing verified MPC model or safety rule base continues to serve as the main controller to drive the DC-DC converter. Simultaneously, the new model receives the same state inputs in parallel in the background, performs real-time simulation calculations, and outputs virtual control commands and corresponding virtual voltage trajectories. Within the set verification period (e.g., 24 hours or covering typical operating conditions), the new model must meet strict admission criteria, and its simulation cumulative cost function... It must be lower than the original model Furthermore, the virtual voltage does not fall below the safety lower limit in all simulation steps. This ensures performance improvements without any safety violations. After successful verification, the system performs hot-swapping deployment when the vehicle is in a low-load steady-state condition (such as constant-speed cruising), seamlessly updating the operating parameters of the MPC controller to the new version. This avoids control disturbances that may be caused by switching during dynamic processes, achieving a smooth and safe capability upgrade.

[0057] Step S30: Based on the output current control command, control the vehicle to pre-charge the low-voltage bus to complete the energy management within the line of sight of the commercial vehicle.

[0058] Understandably, upon receiving the output current control command calculated by the MPC controller, the DC-DC converter is immediately driven to pre-charge the low-voltage bus. In essence, based on the power forecast signal and the cloud energy corridor, the optimal current setpoint is pre-calculated through rolling optimization. Before the actual occurrence of load surges, the bus voltage is proactively increased. The energy storage effect of the bus capacitor and the battery polarization capacitor is used to pre-store electrical energy. When the high-power load of the intelligent driving system is actually put into operation, although the voltage will drop momentarily, because the starting point has been raised, its minimum value can still be kept above the safety threshold, thereby completely avoiding the risk of undervoltage. Furthermore, by continuously re-predicting and optimizing based on the real-time status, while ensuring voltage stability and system safety, the transient high current impact of the battery is significantly reduced, achieving forward-looking and stable energy management within line of sight.

[0059] In a specific embodiment, since a future load surge was anticipated, the first control variable obtained by the MPC controller was calculated. Before the actual load arrives, the DC-DC converter will gradually increase its output voltage to preemptively replenish power. Essentially, this utilizes the energy storage characteristics of the bus capacitor and battery polarization capacitor to pre-store some energy in the system. When a high-power load is instantly applied, although the bus voltage will drop due to the load connection, it will remain above the safe threshold after the drop because the starting point has been actively raised. This effectively avoids the risk of voltage sag. During this process, the system only executes the first action in the optimal control sequence. The data is sent to the DC-DC driver layer for execution, and then immediately transitions to the next cycle of rolling optimization. Simultaneously, the actual bus voltage after DC-DC execution is collected using a high-frequency sensor. And combined with the control input from the previous moment Input either an extended Kalman filter (EKF) or an unscented Kalman filter (UKF) to the system's internal state vector. Online calibration and updates are performed to compensate for model errors and parameter drift in real time, forming a closed-loop observation and correction mechanism to ensure that the prediction model always keeps in line with the dynamics of the actual system.

[0060] The system acquires monitoring fault information and timeout fault information; responds to the output current control command, determines the corresponding control strategy information based on the monitoring fault information and the timeout fault information; and controls the vehicle to perform emergency power replenishment or maintain basic power based on the control strategy information. In other words, the hardware safety fence and the strategy degradation mechanism together construct the system's safety defense. The hardware safety fence, as a low-level hardware protection unit independent of the upper-level MPC algorithm, is implemented by an MCU or FPGA and continuously monitors the bus voltage through a high-speed voltage comparison circuit. and its drop rate dtdv, once the bus voltage is detected Below the preset safety threshold If the voltage drops to 23.0V or the drop rate (dtdv) exceeds the limit, the circuit will immediately take over control, block the MPC output commands, and force the DC-DC converter to perform emergency power replenishment at maximum power. At the same time, it will send a fault alarm to the upper-level system. The strategy degradation is when the system recognizes anomalies such as cloud communication interruption, failure of key sensors, or continuous timeout of the MPC solver. It will automatically degrade along a preset path, retreating from the cloud-coordinated two-layer MPC to the single-vehicle MPC that only relies on vehicle-side information, then switching to PID control, and finally downgrading to the most basic rule base control. This ensures that the system can maintain a minimum voltage stability function under any abnormal operating conditions, ensuring that the system is always in a safe and controlled state.

[0061] In one feasible implementation, after step S30, steps C11 to C13 may also be included: Step C11: Obtain monitoring fault information and timeout fault information; It should be noted that the monitored fault information is a real-time abnormal status signal directly detected and reported by the system hardware safety fence or the underlying sensors. It may include fault types such as bus voltage below the safety threshold, voltage drop rate exceeding the limit, invalid sensor data or communication interruption, which are used to trigger the system's most urgent protection response.

[0062] It is understood that the timeout fault information is a performance anomaly signal diagnosed by the control algorithm layer during operation. That is, the MPC solver fails to converge to a feasible solution multiple times within the set calculation cycle, or the execution time of the optimization routine exceeds the allowable real-time threshold. This indicates that the algorithm cannot meet the real-time control requirements under the current operating conditions or system state. It is identified through software timers or solver status flags and is used to trigger a smooth degradation of the control strategy.

[0063] Step C12: In response to the output current control command, determine the corresponding control strategy information based on the monitored fault information and the timeout fault information; It should be noted that the control strategy information is a set of response decision instructions generated after the system detects a monitoring fault or timeout fault, which specifies the specific control mode to be triggered in the corresponding fault scenario, such as maximum power emergency power replenishment directly triggered by a hardware safety fence, or gradual degradation to PID or rule control triggered by communication or solution anomalies.

[0064] It is understood that the control strategy information is used to coordinate the system to smoothly and safely switch from the high-performance optimization mode to the appropriate backup control strategy while ensuring real-time performance, so as to maintain a minimum voltage stability and system safety under any abnormal circumstances.

[0065] Step C13: Control the vehicle to perform emergency power replenishment or maintain basic power level according to the control strategy information.

[0066] Understandably, once the system makes a decision based on the control strategy information, it will immediately execute the corresponding control action. If the strategy determines that emergency power replenishment needs to be initiated, the system will bypass the conventional optimization algorithm and directly command the DC-DC converter to output maximum power to quickly raise the bus voltage to cope with the risk of severe voltage drops. If the strategy indicates that basic power is to be maintained, the system will switch to a degraded control mode, such as PID or rule-based control, to maintain power supply in a lower-performance but stable and reliable manner while ensuring that the voltage does not drop below the minimum safety line. By dynamically calling different control algorithms and execution logic, the system ensures that the vehicle can achieve minimum energy safety under various fault scenarios, thereby ensuring the continuous operation of the vehicle.

[0067] This embodiment proposes a line-of-sight energy management method for commercial vehicles. It acquires energy constraint information, power forecast information, and energy information within the line-of-sight range of the commercial vehicle. Based on the energy constraint information, power forecast information, and energy information, it inputs the data into a vehicle-side prediction model to predict the output current within a predefined period, determining the output current control command. The vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function based on the energy constraint information, power forecast information, and energy information. Based on the output current control command, it controls the vehicle to pre-charge the low-voltage bus, completing the line-of-sight energy management for the commercial vehicle. This invention addresses the technical challenge of safer and more effective energy management within line of sight for commercial vehicles. Compared to existing technologies, this application utilizes a cloud-based shadow controller to generate a long-line-of-sight energy constraint corridor based on high-precision maps and operating condition information. Simultaneously, it integrates the power forecast signal from the intelligent driving system. On the vehicle side, a multi-objective prediction model is constructed that integrates voltage tracking, control smoothing, and battery life loss. The optimal current command is solved in a rolling manner, allowing for pre-charge of the DC-DC converter and ensuring energy reserves are completed before load surges. This approach completely avoids the risk of undervoltage in intelligent driving while preventing unnecessary impacts on the battery, significantly extending battery life. It also balances global planning and real-time response, improving the overall energy efficiency and adaptability of the system.

[0068] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter.

[0069] In this embodiment, refer to Figure 3 , Figure 3 This is a flowchart illustrating Embodiment 2 of the commercial vehicle line-of-sight energy management method of this application. Step S20 specifically includes steps S21 to S23: Step S21: Determine the corresponding state vector based on the capacitor voltage, inductor current, battery open-circuit voltage, and battery polarization voltage in the energy information. It should be noted that the state vector is a set of physical quantities used in the state-space model describing the dynamic behavior of a low-voltage power supply system to fully characterize the instantaneous state of the energy storage elements inside the system, and to characterize the energy distribution and dynamic characteristics of the system at any time.

[0070] It is understood that the capacitor voltage is the instantaneous voltage across the supporting capacitor supporting the low-voltage bus in the system. This voltage characterizes the amount of electric field energy stored in the capacitor, and its dynamic changes directly affect the transient response speed of the bus voltage and its ability to smooth out load changes. The inductor current is the instantaneous current flowing through the output filter inductor of the DC-DC converter, characterizing the instantaneous power flow that transfers energy from the high-voltage side to the low-voltage side. Its rate of change is controlled by the DC-DC switch state and duty cycle. The battery open-circuit voltage is the potential difference between the positive and negative electrodes of the low-voltage battery when it is at rest or without load. This voltage is monotonically correlated with the battery's state of charge and is used to estimate the remaining usable capacity of the battery in energy management. The battery polarization voltage is the overpotential generated during the charging and discharging process of the battery due to the limited electrochemical reaction rate at the electrode interface and the delay in ion diffusion, characterizing the degree of dynamic polarization inside the battery.

[0071] In a specific embodiment, during each sampling cycle of the vehicle-side MPC controller, a high-precision analog-to-digital converter (ADC) can be used to collect the voltage across the supporting capacitor on the low-voltage bus in real time as the capacitor voltage, and simultaneously sample the inductor current in the DC-DC output filter inductor. At the same time, the battery open-circuit voltage and battery polarization voltage estimated or directly measured by the battery management system (BMS) are read from the controller local area network (CAN) or a dedicated communication interface, and combined into a state vector at discrete time points, thereby characterizing the dynamic energy state of the energy storage components inside the low-voltage power system at the current moment.

[0072] Step S22: Determine the disturbance vector in the predefined prediction step based on the speed change information and braking information in the power prediction information; It should be noted that the disturbance vector is defined in the vehicle-side MPC prediction model as a deterministic input sequence characterizing the dynamic impact of future external load current on the system. It is obtained by real-time conversion of power forecast information released in advance by the intelligent driving domain controller, such as the power step corresponding to an upcoming steering or braking event. Each element corresponds to a load current prediction value of one step in the prediction time domain, which is used to actively offset the impact of external power disturbance on the system voltage and energy state.

[0073] In a specific embodiment, when the intelligent driving domain controller publishes power forecast information through the vehicle Ethernet, the MPC's communication interface parses the power forecast information, extracts the event type, power mutation amount, and time offset, and converts the forecast power value into an equivalent load current change amount according to the predefined load power and current mapping relationship. Based on the sampling period and prediction time domain length of the control system, the current change amount is allocated to the corresponding time step in the future, thereby generating a deterministic sequence of load current changes in the next few sampling periods, i.e., the disturbance vector.

[0074] Step S23: Based on the energy constraint information, the state vector, and the disturbance vector, the vehicle-end prediction model is input to predict the output current within a predefined period to obtain the output current control command.

[0075] It is understood that the output current control command is sent to the DC-DC drive layer in digital form, such as current setpoint or PWM duty cycle command, so that the output current of the DC-DC can compensate for the predicted load power changes in advance while meeting the cloud corridor constraints and system physical limits. This allows for pre-power replenishment before load changes occur, achieving the control objectives of stabilizing the low-voltage bus voltage, optimizing system energy efficiency, and extending battery life.

[0076] In a specific embodiment, shadow mode information is acquired; the vehicle-side prediction model is simulated and verified based on the shadow mode information to determine the target vehicle-side prediction model; based on the energy constraint information, the state vector, and the disturbance vector, the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding target optimization function are corrected in the target vehicle-side prediction model to determine the control vector; based on the control vector, the control quantity of the output current within a predefined period is calculated to obtain the output current control command, which allows shadow mode verification to be executed. Upon initial deployment or when updated model parameters are received via OTA, the system does not immediately switch controllers but enters shadow mode, using the existing verified MPC model or safety rule base as the main controller to actually drive the DC-DC converter. Simultaneously, the new model receives the same state input in parallel in the background, performs simulation calculations in real time, and outputs virtual control commands and corresponding virtual voltage trajectories. Within the set verification period (e.g., 24 hours or covering typical operating conditions), the new model must meet strict admission criteria, and its simulation cumulative cost function... It must be lower than the original model Furthermore, the virtual voltage does not fall below the safety lower limit in all simulation steps. This ensures performance improvements without any safety violations. After successful verification, the system performs hot-swapping deployment when the vehicle is in a low-load steady-state condition (such as constant-speed cruising), seamlessly updating the operating parameters of the MPC controller to the new version. This avoids control disturbances that may be caused by switching during dynamic processes, achieving a smooth and safe capability upgrade.

[0077] Obtain the actual bus voltage; use the Kalman filter algorithm and the actual bus voltage to perform online calibration and update of the target control vector, and determine the updated control vector; calculate the control quantity corresponding to the predefined period based on the updated control vector to obtain the output current control command, which can be obtained by acquiring the actual bus voltage after DCDC execution through a high-frequency sensor. And combined with the control input from the previous moment Input either an extended Kalman filter (EKF) or an unscented Kalman filter (UKF) to the system's internal state vector. Online calibration and updates are performed to compensate for model errors and parameter drift in real time, forming a closed-loop observation and correction mechanism to ensure that the prediction model always keeps in line with the actual system dynamics and to obtain output current control commands.

[0078] In one feasible implementation, step S23 may include steps D11-D14: Step D11: Obtain shadow mode information; It should be noted that the shadow mode information is a set of data and rules used during the model security verification and deployment phase to support the parallel operation and performance comparison of the old and new controllers.

[0079] It is understood that the shadow mode information is identified by the code and parameter versions of the new and old MPC models or rule bases. The control commands and state prediction trajectories calculated by the two models under the same real-time vehicle state input are as well as the verification criteria used to determine whether the new model is allowed to go online. For example, the cumulative cost function of the new model during the verification period must be lower than that of the old model, and its simulated predicted voltage trajectory must not be lower than the safety threshold throughout the entire process. This ensures that any update is allowed to be deployed only after sufficient performance and safety verification without affecting real-time control.

[0080] Step D12: Based on the shadow pattern information, perform simulation verification on the vehicle-side prediction model to determine the target vehicle-side prediction model; It should be noted that the target vehicle-side prediction model is a vehicle-side predictive control model that has been fully verified in shadow mode and meets all performance and safety access criteria before being allowed by the system to be deployed and used in actual control.

[0081] It is understood that the target vehicle prediction model is a new version obtained by cloud OTA update or local parameter optimization based on the original vehicle prediction model. In simulation verification, it shows a lower overall cost than the old model, such as better voltage tracking, smoother control and lower battery loss. Moreover, it can ensure that the voltage does not fall below the safety threshold under all test conditions. Therefore, it is authorized to replace the old model by hot switching at an appropriate time.

[0082] Step D13: Based on the energy constraint information, the state vector, and the disturbance vector, the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding target optimization function are corrected in the target vehicle prediction model to determine the control vector; It should be noted that the control vector is the control input sequence used to directly drive the actuator, which needs to be solved in each prediction time domain during the model predictive control rolling optimization process.

[0083] It is understood that the control vector can be composed of the instruction values ​​of the DC-DC output current or the equivalent PWM duty cycle at multiple future time steps. It is a decision variable determined by MPC through solving a multi-objective optimization problem. It is used to transform the model-based forward optimization results into specific, time-sequential action instructions, in which only the first element is immediately issued and executed, thereby achieving preemptive energy regulation. It is also updated in each control cycle to continuously respond to dynamic changes.

[0084] Step D14: Based on the control vector, calculate the control quantity of the output current within a predefined period to obtain the output current control command.

[0085] Understandably, after the vehicle-side MPC controller completes the rolling optimization for each control cycle, it extracts the first control quantity in the sequence that is precisely aligned with the current execution time based on the instruction sequence of the DC-DC output current in the next few sampling cycles. Then, it performs signal conversion and encapsulation according to the specific interface protocol of the DC-DC converter to generate an output current control instruction that can be directly recognized and executed by the underlying drive circuit.

[0086] In one possible implementation, steps E11 to E13 may be included after step D14: Step E11: Obtain the actual bus voltage; It should be noted that the actual bus voltage is the physical voltage value of the system's instantaneous power supply capacity and load status, which is collected in real time by a high-precision voltage sensor on the DC bus of the vehicle's low-voltage power supply system.

[0087] It is understood that the actual bus voltage is the real-time energy balance result under the interaction of all power sources and loads, used to correct the internal state of the prediction model and ensure that the control system can accurately sense and respond to the real dynamics of the system.

[0088] Step E12: Use the Kalman filter algorithm and the actual bus voltage to perform online calibration and update of the target control vector, and determine the updated control vector; It should be noted that the updated control vector is a modified sequence of control commands, which is used to make the control commands more closely match the actual dynamic characteristics of the current system. In each control cycle, real-time feedback information is integrated into the look-ahead optimization process, thereby generating more accurate and adaptive control quantities and improving the control accuracy of the system under model uncertainty and external disturbances.

[0089] Step E13: Based on the updated control vector, the control quantity corresponding to the predefined period is calculated to obtain the output current control command.

[0090] It is understood that the first optimized control quantity that precisely corresponds to the current control cycle can be extracted from the updated control vector, and the signal can be converted and encapsulated according to the protocol specification of the DCDC drive interface to generate a new output current control command, thereby more accurately reflecting the current system dynamics and optimization goals, and realizing continuous and precise regulation under closed loop.

[0091] This embodiment proposes a commercial vehicle line-of-sight energy management method, which determines the corresponding state vector based on the capacitor voltage, inductor current, battery open-circuit voltage, and battery polarization voltage in the energy information; determines the disturbance vector in a predefined prediction step based on the speed change information and braking information in the power forecast information; and predicts the output current in a predefined period based on the energy constraint information, the state vector, and the disturbance vector input into the vehicle-side prediction model to obtain the output current control command. This invention addresses the technical challenge of safer and more effective energy management within line of sight for commercial vehicles. Compared to existing technologies, this application constructs a state vector characterizing the system's internal dynamics by real-time acquisition of capacitor voltage, inductor current, battery open-circuit voltage, and polarization voltage. Simultaneously, it transforms power forecast information into a deterministic disturbance vector within the prediction time domain. Combined with energy constraint information from the cloud, this data is input into the vehicle-side prediction model to continuously solve for the optimal output current sequence over a future period, generating an immediate output current control command. This achieves a leap from passive response to proactive anticipation in energy management. By accurately modeling system dynamics through state vectors and proactively sensing load changes through disturbance vectors, multi-objective optimization is performed within the global boundary of energy constraints. This enables the DC-DC converter to preemptively replenish power before load surges actually occur, fundamentally avoiding transient voltage drops at the bus and ensuring the continuity and safety of the intelligent driving system's power supply. Furthermore, the optimization process balances control smoothness with battery life loss, significantly reducing unnecessary current surges and extending the lifespan of low-voltage batteries.

[0092] This application also provides a commercial vehicle line-of-sight energy management device; please refer to... Figure 4 The commercial vehicle line-of-sight energy management device includes: The acquisition module 10 is used to acquire energy constraint information, power forecast information and energy information within the line of sight of commercial vehicles; Processing module 20 is used to predict the output current within a predefined period based on the energy constraint information, the power forecast information and the energy information input to the vehicle-end prediction model, and determine the output current control command. The vehicle-end prediction model is obtained by correcting the voltage tracking term, control smoothing term and lifetime loss term of the corresponding objective optimization function according to the energy constraint information, the power forecast information and the energy information. The execution module 30 is used to control the vehicle to pre-charge the low-voltage bus based on the output current control command, thereby completing the energy management within the line of sight of the commercial vehicle.

[0093] The acquisition module 10 is also used to acquire navigation path information and load information within the line of sight of the commercial vehicle; Based on the navigation path information, the road slope features and vehicle speed features within the predefined slice segment range are extracted to determine the road slope information and vehicle speed information; Based on the load information, road slope information, and vehicle speed information, a predefined full vehicle energy consumption model is input to predict the energy trajectory and determine the energy trajectory information. Based on the energy trajectory information, corresponding energy constraint information is generated.

[0094] The acquisition module 10 is also used to acquire energy recovery constraint information and physical hard constraint information; The corresponding soft constraints of the utility tunnel are determined based on the energy recovery constraint information and the energy trajectory information. Energy constraint information is determined based on the physical hard constraints and the cloud-based utility tunnel soft constraints.

[0095] The processing module 20 is also used to determine the corresponding state vector based on the capacitor voltage, inductor current, battery open-circuit voltage and battery polarization voltage in the energy information. Based on the speed change information and braking information in the power prediction information, the disturbance vector in the predefined prediction step is determined; Based on the energy constraint information, the state vector, and the disturbance vector, the vehicle-end prediction model predicts the output current within a predefined period to obtain the output current control command.

[0096] The processing module 20 is also used to acquire shadow mode information; The vehicle-side prediction model is simulated and verified based on the shadow pattern information to determine the target vehicle-side prediction model. Based on the energy constraint information, the state vector, and the disturbance vector, the target vehicle-side prediction model is input to correct the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding target optimization function, and to determine the control vector. Based on the control vector, the control quantity of the output current within a predefined period is calculated to obtain the output current control command.

[0097] The processing module 20 is also used to obtain the actual bus voltage; The target control vector is calibrated and updated online using the Kalman filter algorithm and the actual bus voltage to determine the updated control vector. The control quantity corresponding to the predefined period is calculated based on the updated control vector to obtain the output current control command.

[0098] The execution module 30 is used to acquire monitoring fault information and timeout fault information; In response to the output current control command, the corresponding control strategy information is determined based on the monitored fault information and the timeout fault information; The vehicle is controlled to perform emergency power replenishment or maintain basic power based on the control strategy information.

[0099] The commercial vehicle line-of-sight energy management device provided in this application, employing the commercial vehicle line-of-sight energy management method described in the above embodiments, can solve the technical problem of how to perform line-of-sight energy management for commercial vehicles more safely and effectively. Compared with the prior art, the beneficial effects of the commercial vehicle line-of-sight energy management device provided in this application are the same as those of the commercial vehicle line-of-sight energy management method provided in the above embodiments, and other technical features in the commercial vehicle line-of-sight energy management device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0100] This application provides a commercial vehicle line-of-sight energy management device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the commercial vehicle line-of-sight energy management method in Embodiment 1 above.

[0101] The following is for reference. Figure 5 This document illustrates a structural schematic diagram suitable for implementing a commercial vehicle line-of-sight energy management device according to embodiments of this application. The commercial vehicle line-of-sight energy management device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The commercial vehicle line-of-sight energy management device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0102] like Figure 5As shown, the commercial vehicle's line-of-sight energy management device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the commercial vehicle's line-of-sight energy management device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the commercial vehicle's line-of-sight energy management device to exchange data with other devices wirelessly or via wired communication. Although the figure shows a commercial vehicle's line-of-sight energy management device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0103] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0104] The commercial vehicle line-of-sight energy management device provided in this application, employing the commercial vehicle line-of-sight energy management method described in the above embodiments, can solve the technical problem of how to perform commercial vehicle line-of-sight energy management more safely and effectively. Compared with the prior art, the beneficial effects of the commercial vehicle line-of-sight energy management device provided in this application are the same as those of the commercial vehicle line-of-sight energy management method provided in the above embodiments, and other technical features of the commercial vehicle line-of-sight energy management device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0105] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0106] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0107] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the commercial vehicle line-of-sight energy management method in the above embodiments.

[0108] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0109] The aforementioned computer-readable storage medium may be included in the line-of-sight energy management device of a commercial vehicle; or it may exist independently and not be installed in the line-of-sight energy management device of a commercial vehicle.

[0110] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the commercial vehicle line-of-sight energy management device, the commercial vehicle line-of-sight energy management device: acquires energy constraint information, power forecast information, and energy information within the commercial vehicle's line of sight; based on the energy constraint information, power forecast information, and energy information, it inputs the vehicle-side prediction model to predict the output current within a predefined period, determines the output current control command, wherein the vehicle-side prediction model is obtained by correcting the voltage tracking term, control smoothing term, and lifetime loss term of the corresponding objective optimization function based on the energy constraint information, power forecast information, and energy information; and controls the vehicle to pre-charge the low-voltage bus based on the output current control command, thereby completing the commercial vehicle line-of-sight energy management.

[0111] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0113] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0114] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described commercial vehicle line-of-sight energy management method, thereby solving the technical problem of how to perform commercial vehicle line-of-sight energy management more safely and effectively. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the commercial vehicle line-of-sight energy management method provided in the above embodiments, and will not be repeated here.

[0115] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for managing energy in the line of sight of a commercial vehicle, characterized in that, The method comprises: acquiring energy constraint information, power pre-announcement information and energy information within the visual range of the commercial vehicle; inputting the energy constraint information, the power pre-announcement information and the energy information into a vehicle-end prediction model to predict the output current in a predefined period, determine the output current control instruction, and the vehicle-end prediction model is obtained by modifying the voltage tracking term, the control smoothing term and the life loss term of the corresponding target optimization function according to the energy constraint information, the power pre-announcement information and the energy information; controlling the vehicle to pre-charge the low-voltage bus based on the output current control instruction, and completing the energy management within the visual range of the commercial vehicle.

2. The method of claim 1, wherein, The step of acquiring the energy constraint information within the visual range of the commercial vehicle comprises: acquiring navigation path information and load information within the visual range of the commercial vehicle; extracting road slope characteristics and vehicle speed characteristics within the range of a predefined slice section based on the navigation path information, and determining road slope information and vehicle speed information; inputting the load information, the road slope information and the vehicle speed information into a predefined whole-vehicle energy consumption model to predict an energy trajectory, and determining energy trajectory information; generating corresponding energy constraint information based on the energy trajectory information.

3. The method of claim 2, wherein, The step of generating corresponding energy constraint information based on the energy trajectory information comprises: acquiring electric energy recovery constraint information and physical hard constraint information; determining corresponding pipe gallery soft constraints based on the electric energy recovery constraint information and the energy trajectory information; determining energy constraint information based on the physical hard constraint and the cloud pipe gallery soft constraint.

4. The method of claim 1, wherein, The step of inputting the energy constraint information, the power pre-announcement information and the energy information into the vehicle-end prediction model to predict the output current in the predefined period, and determining the output current control instruction, comprises: determining a corresponding state vector based on the capacitance voltage, the inductance current, the battery open-circuit voltage and the battery polarization voltage in the energy information; determining a disturbance vector in a predefined prediction step based on the variable speed information and the braking information in the power pre-announcement information; inputting the energy constraint information, the state vector and the disturbance vector into the vehicle-end prediction model to predict the output current in the predefined period, and obtaining the output current control instruction.

5. The method of claim 4, wherein, The step of inputting the energy constraint information, the state vector and the disturbance vector into the vehicle-end prediction model to predict the output current in the predefined period, and obtaining the output current control instruction, comprises: acquiring shadow mode information; simulating and verifying the vehicle-end prediction model based on the shadow mode information, and determining a target vehicle-end prediction model; modifying the voltage tracking term, the control smoothing term and the life loss term of the corresponding target optimization function based on the energy constraint information, the state vector and the disturbance vector input into the target vehicle-end prediction model, and determining a control vector; calculating the control amount of the output current in the predefined period based on the control vector, and obtaining the output current control instruction.

6. The method of claim 5, wherein, After the step of calculating the control amount corresponding to the predefined period based on the target control vector to obtain the output current control instruction, the method further comprises: acquiring an actual bus voltage; The Kalman filtering algorithm is used to calibrate and update the target control vector online according to the actual bus voltage, and an updated control vector is determined; According to the updated control vector, the control amount corresponding to the predefined period is calculated to obtain an output current control instruction.

7. The method of claim 1, wherein, After the step of controlling the vehicle to pre-charge the low-voltage bus based on the output current control instruction and completing the line-of-sight energy management of the commercial vehicle, the method further comprises: obtaining monitoring fault information and timeout fault information; determining corresponding control strategy information according to the monitoring fault information and the timeout fault information in response to the output current control instruction; controlling the vehicle to perform emergency charging or maintain basic power according to the control strategy information.

8. A commercial vehicle sight distance energy management device characterized by, The device comprises: an acquisition module configured to acquire energy constraint information, power prediction information, and energy information within the line of sight of the commercial vehicle; a processing module configured to input the energy constraint information, the power prediction information, and the energy information into a vehicle-end prediction model to predict output current in a predefined period and determine an output current control instruction, the vehicle-end prediction model being obtained by modifying voltage tracking items, control smoothing items, and life loss items of a corresponding target optimization function according to the energy constraint information, the power prediction information, and the energy information; an execution module configured to control the vehicle to pre-charge the low-voltage bus based on the output current control instruction and complete the line-of-sight energy management of the commercial vehicle.

9. A commercial vehicle sight distance energy management device characterized by, The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the line-of-sight energy management method of the commercial vehicle according to any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the line-of-sight energy management method of the commercial vehicle according to any one of claims 1 to 7.

Images