Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Internal Combustion Engine01:20

Internal Combustion Engine

1.3K
The internal combustion engine is a heat engine that uses the byproducts of combustion as the working fluid instead of using a heat transfer medium to transfer heat. The combustion is done in a way that produces high-pressure combustion products that can be expanded through a turbine or piston to create work. Internal combustion engines can again be categorized into three kinds: (1) spark ignition gasoline engines, most commonly used in automobiles, (2) compression ignition diesel engines that...
1.3K
PD Controller: Design01:26

PD Controller: Design

276
In automotive engineering, car suspension systems often employ Proportional Derivative (PD) controllers to enhance performance. PD controllers are utilized to adjust the damping force in response to road conditions. A controller, acting as an amplifier with a constant gain, demonstrates proportional control, with output directly mirroring input.
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
276
Otto and Diesel Cycle01:27

Otto and Diesel Cycle

1.8K
An Otto engine is a four-stroke engine that uses a mixture of gasoline and air as the working fuel. The fuel is injected into the cylinder, and the piston is moved completely down so that the cylinder is at maximum volume. By moving the piston up, adiabatic compression takes place. The spark plug ignites the gasoline-air mixture, and the burning fuel adds heat to the system at a constant volume. The heated mixture expands adiabatically and gets further cooled by exhausting heat, and this cyclic...
1.8K
Reinforcement01:23

Reinforcement

273
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
273
Rolling Resistance: Problem Solving01:17

Rolling Resistance: Problem Solving

370
Rolling resistance, also known as rolling friction, is the force that resists the motion of a rolling object, such as a wheel, tire, or ball, when it moves over a surface. It is caused by the deformation of the object and the surface in contact with each other, as well as other factors like internal friction, hysteresis, and energy losses within the materials. Rolling resistance opposes the object's motion, requiring additional energy to overcome it and maintain movement. In practical...
370
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

127
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
127

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Histopathological and duplex characteristics of deep venous stents: A novel microsurgical small animal model.

Vascular medicine (London, England)·2026
Same author

Dynamic Bayesian networks to predict loss of kidney function: a cross-institution use case in a large cohort with or at-risk of CKD.

BMC medical informatics and decision making·2026
Same author

Does the Timing of USMLE Step 1 Affect Performance? A Comparison of Pre- and Post-Clerkship Timing in the Pass/Fail Era.

Teaching and learning in medicine·2026
Same author

In Stent Re-stenosis Biopsy Findings and Stent Failure Risk Factors in Iliofemoral Venous Stenting: Analysis of 151 Biopsy Samples in 84 Patients and Long Term Outcomes.

European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery·2026
Same author

Feasibility and Form Factor Validation of Reflective Shoulder-Mounted Pulse Oximeter in Patients with Suspected Sleep Apnea.

Sensors (Basel, Switzerland)·2026
Same author

Mutant TDP-43 drives impairments in axonal transport and glycolysis in a mouse stem-cell-derived motor neuron model of amyotrophic lateral sclerosis (ALS).

Cell death & disease·2026
See all related articles

Related Experiment Video

Updated: Jul 16, 2025

Implementation of Portable Emissions Measurement Systems PEMS for the Real-driving Emissions RDE Regulation in Europe
09:34

Implementation of Portable Emissions Measurement Systems PEMS for the Real-driving Emissions RDE Regulation in Europe

Published on: December 4, 2016

28.2K

Safe deep reinforcement learning in diesel engine emission control.

Armin Norouzi1, Saeid Shahpouri1, David Gordon1

  • 1Department of Mechanical Engineering, University of Alberta, Edmonton, AB, Canada.

Proceedings of the Institution of Mechanical Engineers. Part I, Journal of Systems and Control Engineering
|September 11, 2023
PubMed
Summary
This summary is machine-generated.

A novel safe reinforcement learning approach effectively reduces diesel engine nitrogen oxide emissions and fuel use. This method outperforms traditional controllers by learning optimal control without a full system model, though it requires a basic model for safety constraints.

Keywords:
Machine learningdeep learningdiesel engineemission controliterative learning controlreinforcement learningsafe learning

More Related Videos

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.5K
A Rapid Method for Modeling a Variable Cycle Engine
04:58

A Rapid Method for Modeling a Variable Cycle Engine

Published on: August 13, 2019

7.6K

Related Experiment Videos

Last Updated: Jul 16, 2025

Implementation of Portable Emissions Measurement Systems PEMS for the Real-driving Emissions RDE Regulation in Europe
09:34

Implementation of Portable Emissions Measurement Systems PEMS for the Real-driving Emissions RDE Regulation in Europe

Published on: December 4, 2016

28.2K
Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.5K
A Rapid Method for Modeling a Variable Cycle Engine
04:58

A Rapid Method for Modeling a Variable Cycle Engine

Published on: August 13, 2019

7.6K

Area of Science:

  • * Internal Combustion Engines
  • * Artificial Intelligence in Engineering
  • * Environmental Control Technologies

Background:

  • * Controlling emissions in compression ignition diesel engines is critical for environmental compliance and fuel efficiency.
  • * Traditional control methods face limitations in adapting to dynamic engine conditions and complex emission reduction targets.
  • * Deep reinforcement learning (DRL) offers a promising avenue for adaptive and optimized engine control.

Purpose of the Study:

  • * To investigate a deep reinforcement learning application for controlling diesel engine emissions.
  • * To reduce engine-out nitrogen oxide (NOx) emissions and minimize fuel consumption.
  • * To achieve accurate tracking of a reference engine load.

Main Methods:

  • * Development and calibration of a physics-based engine simulation model in GT-Power using experimental data.
  • * Implementation of a deep deterministic policy gradient algorithm within a GT-Power/Simulink co-simulation environment.
  • * Integration of a safety filter to enforce output constraints during the DRL training process.

Main Results:

  • * The safe reinforcement learning (SRL) controller demonstrated superior NOx reduction compared to nonlinear model predictive control (NMPC).
  • * SRL accurately tracked arbitrary reference load inputs, surpassing the limitations of iterative learning controllers (ILC).
  • * While SRL achieved lower emissions, it exhibited slightly higher load tracking error and fuel consumption than NMPC.

Conclusions:

  • * Safe reinforcement learning is a viable and effective strategy for reducing NOx emissions and fuel consumption in diesel engines.
  • * SRL can learn optimal control policies directly, reducing reliance on complex system models, but requires a simplified model for constraint enforcement.
  • * SRL offers advantages over ILC and NMPC in adaptability and direct learning, despite minor trade-offs in load tracking and fuel efficiency.