US 2026/0145662 A1 · Intelligent multimode hybrid powertrain and autonomous connected electrified heavy truck

Abstract

An AI-connected-electrified (ACE) heavy truck system equipped with an intelligent multi-mode hybrid (iMMH) powertrain system and a vehicle supervision control strategy based on machine learning (ML) or reinforcement learning (RL) paradigm are presented. This system ensures industry-leading power and braking performance of the ACE heavy truck while automatically optimizes both energy saving and emission reduction based on the vehicle's dynamic driving data and 3D electronic map information of roads for any transport event. In this application, the conventional analog electronic control (AEC) method is replaced by a novel digital pulse control (DPC) method on the instantaneous power function of the engine. The DPC method converts the complex surface working conditions of the AEC engine of the hybrid vehicles into simpler pre-defined working condition lines of the DPC engine. Consequently, the multi-variable nonlinear technical problem of simultaneously optimizing real driving environment (RDE) fuel consumption and pollutant emissions of the ACE heavy truck is simplified into two decoupled quasi-liner optimization problems, and ensures the reduction of on-vehicle computing resources for real-time AI inference computation and the improvement of the optimal performance, the convergent rate, and the robustness of the corresponding fuel-saving algorithm for the trained ML model or the learned RL model. Ultimately, the ACE truck achieves in the engineering sense the global minimum RDE fuel consumption and pollutant emissions meeting the standard consistently at high performance to cost ratio for any transport event and the RDE fuel consumption is decoupled from the vehicle configuration parameters and the human driver.

Claims20

Dependent claims

-9. (canceled)

A method to implement a hybrid vehicle supervisory-control-strategy (SCS) based on digital-pulse-control (DPC) method-set and reinforcement-learning (RL) or machine-learning (ML) paradigm,

wherein the hybrid vehicle comprises:
an engine, a traction motor (MG2), a clutch placed between the engine and the traction motor, a transmission mechanically connected with the traction motor in a central-drive system, a battery pack, an electric power-splitting-device (ePSD), the battery pack is electrically connected with the MG2 through the ePSD, a vehicle controller (VCU) configured to make the hybrid vehicle, under normal operations, to operate stably in series-hybrid or parallel-hybrid mode;
wherein the DPC method-set comprises:
a fast-control-loop for instantaneous-power functions and a slow-control-loop for average-power functions, the fast-control-loop includes the series-hybrid intelligent stop-start (iSS) control or the parallel-hybrid intelligent power-switching (iPS) control for the DPC engine, the slow-control-loop includes predicative state of charge (SoC) control (PSC) for the battery pack, the fast-control-loop and the slow-control-loop are mutually decoupled and can be controlled independently to ensure the DPC engine and the battery pack to work in their respective high-efficiency zones stably almost always and independent of the working conditions of the hybrid vehicle;
I) in the fast-control-loop, applying the intelligent stop-start (iSS) control when the hybrid vehicle operates stably in series-hybrid mode or the intelligent power-switch (iPS) control when the hybrid vehicle operates stably in parallel-hybrid mode, thereby transforming the engine instantaneous-power function from an analog time-varying function into a bi-polar pulse-width-modulation (PWM) time series function, at the same time directing the instantaneous-power function of the battery pack to track in real-time the difference-function between the hybrid vehicle road-load instantaneous-power function and the DPC engine instantaneous-power function to satisfy the vehicle dynamic equation and the series-hybrid or parallel-hybrid power balance equation, the duty-cycle function of the DPC engine is the most important control variable of the DPC method;
II) in the slow-control-loop, the PSC method includes the following steps:
1) within the electronic-horizon, setting the vehicle nominal cruising speed dynamically, computing on-vehicle quickly and continuously the function-distributions of the vehicle road-load instantaneous-power and average-power according to the vehicle dynamic equation, the moving average equation, the hybrid vehicle parameters and its dynamic operational data;
2) predictively shaping the difference-function-distribution between the vehicle road-load average-power function-distribution and the engine average-power function-distribution through independent dynamic control of the DPC engine duty-cycle function and adjusting the battery charging/discharging electric power to track closely the average-power difference-function in real-time in order to satisfy the series-hybrid or parallel-hybrid power balance equation;
3) in a time section when the absolute value of the battery average-power function-distribution is always less than a pre-set positive threshold and the simple average value of the function-distribution is close to zero, the battery pack is defined to operate stably in the charge-sustaining mode (CS) for the time section;
when the function-distribution is mostly larger than a pre-set positive threshold and always lager than zero and the simple average value of the function-distribution is much larger than zero, the battery pack is defined to operate stably in the charge-depleting mode (CD);
when the function-distribution is mostly less than a pre-set negative threshold and always less than zero and the simple average value of the function-distribution is much less than zero, the battery pack is defined to operate stably in the charge-increasing mode (CI);
4) directing the battery pack to operate stably in one out of three modes of CD/CS/CI or to switch dynamically among these three modes through predicative shaping of the battery average-power function-distribution, thereby ensuring the battery pack to operate stably in its high-efficiency zone most of the time and to maximize the regen-charge turnover rate for any transport event.

9 more elements

A hybrid vehicle comprises,

an engine, a traction motor mechanically connected to a transmission box in a central-drive system, at least one high-power battery pack supplying the electric power to the traction motor through an electric power-splitting device (ePSD), a clutch placed between the engine and the traction motor;
a vehicle controller (VCU) configured to make the hybrid vehicle, under normal operations, only operates stably in either the series-hybrid or the parallel-hybrid mode, the vehicle controller (VCU) configured to implement on-vehicle the method according to at least one of claims 1, 4, 8, 9, or 12 for the hybrid vehicle supervisory control strategy based on the DPC method-set and the RL or ML paradigm in order to optimize the hybrid vehicle RDE fuel-consumption and pollutant-emissions for any transport event.

Dependencies are inferred from the claim text.

Intelligent multimode hybrid powertrain and autonomous connected electrified heavy truck

Life of this patent

Intelligent multimode hybrid powertrain and autonomous connected electrified heavy truck

Life of this patent

Abstract

Claims20