Intelligent Fault Detection and Classification Based on Hybrid Deep Learning Methods for Hardware-in-the-Loop Test of
Mohammad Abboush1, Daniel Bamal1, Christoph Knieke1
1Institute for Software and Systems Engineering, Technische Universität Clausthal, 38678 Clausthal-Zellerfeld, Germany.
Sensors (Basel, Switzerland)
|June 10, 2022
Summary
This study introduces a novel hybrid deep learning model for automotive software system fault detection and classification using Hardware-in-the-Loop testing. The model achieves high accuracy in identifying and categorizing sensor faults, enhancing automotive safety.
Area of Science:
- Automotive Engineering
- Software Reliability
- Artificial Intelligence
Background:
- Hardware-in-the-Loop (HIL) is crucial for automotive software system (ASS) safety validation per ISO 26262.
- Conventional data analysis of HIL test data is insufficient due to complexity and volume.
- Data-driven fault diagnosis is promising but selecting appropriate Deep Learning (DL) techniques and obtaining fault data are challenging.
Purpose of the Study:
- To propose a novel intelligent fault detection and classification (FDC) model for ASSs during system integration testing.
- To address the challenge of rare and confidential automotive fault data by generating it via HIL real-time fault injection.
- To develop an effective data-driven approach for analyzing HIL test records.
Main Methods:
- Utilized a Hardware-in-the-Loop (HIL) based real-time fault injection framework to generate diverse automotive fault data.
- Developed a hybrid Deep Learning (DL) model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architectures.
- Considered eight common sensor fault types within automotive software systems for comprehensive testing.
Main Results:
- The proposed hybrid DL model demonstrated superior fault detection and classification performance compared to standalone DL methods.
- Achieved high detection accuracy with precision at 98.86%, recall at 98.90%, and F1-score at 98.88%.
- Exhibited excellent classification performance on unseen test data, with an average accuracy of 98.8%.
Conclusions:
- The novel hybrid CNN-LSTM model effectively detects and classifies automotive software system faults using HIL-generated data.
- The approach enhances the reliability and safety analysis of automotive software during the V-cycle development.
- This method offers a robust and accurate solution for data-driven fault diagnosis in safety-critical automotive systems.
Related Concept Videos
01:26PD Controller: Design
360
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,...
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
360
01:26Classification of Systems-I
326
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
326
01:14Design Example: Automobile Ignition System
314
The automobile's ignition system plays a vital role by ensuring the timely ignition of the fuel-air mixture in each cylinder. This ignition is facilitated by a spark plug, which is composed of two electrodes separated by an air gap. A spark forms across this air gap when a substantial voltage is generated between the electrodes, leading to the ignition of the fuel.
One can generate a large voltage using a car battery of 12 volts with the help of inductors. Inductors are known for opposing...
One can generate a large voltage using a car battery of 12 volts with the help of inductors. Inductors are known for opposing...
314
01:22Multi-input and Multi-variable systems
157
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...
In the absence...
157
01:31Classification of Systems-II
245
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
245
01:26Feedback control systems
442
Feedback control systems are categorized in various ways based on their design, analysis, and signal types.
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
442