Controller Area Network Bus System Research Articles

Smart Intrusion Detection System for CAN Network Implemented using LSTM Strategy

In today's cars, communication between electronic control units is managed via the Controller Area Network (CAN) bus system. Nevertheless, the CAN bus system lacks means for authentication and authorisation, making it susceptible to attacks like denial-of-service, fuzzing, and spoofing. To identify and counteract CAN bus network intrusions, this study suggests an intrusion detection system based on a Long Short-Term Memory (LSTM) model. Extraction of attack-free data and attack injection produced the dataset used for testing and training. Findings show that the suggested LSTM model has a greater detection rate than the Survival Analysis approach and is efficient in defending current automobiles from assaults on the CAN bus network. The ability to identify these sorts of assaults is limited by the constraints of conventional intrusion detection systems (IDS) for CAN bus networks, such as statistical analysis, frequency-based analysis, and Hidden Markov Model (HMM). Using a Long Short-Term Memory (LSTM) based strategy, the objective of this article is to build a reliable IDS that can efficiently identify and counteract these assaults on the CAN bus network.

Detecting in-vehicle intrusion via semi-supervised learning-based convolutional adversarial autoencoders

With the development of autonomous vehicle technology, the controller area network (CAN) bus has become the de facto standard for an in-vehicle communication system because of its simplicity and efficiency. However, without any encryption and authentication mechanisms, the in-vehicle network using the CAN protocol is susceptible to a wide range of attacks. Many studies, which are mostly based on machine learning, have proposed installing an intrusion detection system (IDS) for anomaly detection in the CAN bus system. Although machine learning methods have many advantages for IDS, previous models usually require a large amount of labeled data, which results in high time and labor costs. To handle this problem, we propose a novel semi-supervised learning-based convolutional adversarial autoencoder model in this paper. The proposed model combines two popular deep learning models: autoencoder and generative adversarial networks. First, the model is trained with unlabeled data to learn the manifolds of normal and attack patterns. Then, only a small number of labeled samples are used in supervised training. The proposed model can detect various kinds of message injection attacks, such as DoS, fuzzy, and spoofing, as well as unknown attacks. The experimental results show that the proposed model achieves the highest F1 score of 0.9984 and a low error rate of 0.1% with limited labeled data compared to other supervised methods. In addition, we show that the model can meet the real-time requirement by analyzing the model complexity in terms of the number of trainable parameters and inference time. This study successfully reduced the number of model parameters by five times and the inference time by eight times, compared to a state-of-the-art model.

Using Deep Learning Networks to Identify Cyber Attacks on Intrusion Detection for In-Vehicle Networks

With rapid advancements in in-vehicle network (IVN) technology, the demand for multiple advanced functions and networking in electric vehicles (EVs) has recently increased. To enable various intelligent functions, the electrical system of existing vehicles incorporates a controller area network (CAN) bus system that enables communication among electrical control units (ECUs). In practice, traditional network-based intrusion detection systems (NIDSs) cannot easily identify threats to the CAN bus system. Therefore, it is necessary to develop a new type of NIDS—namely, on-the-move Intrusion Detection System (OMIDS)—to categorise these threats. Accordingly, this paper proposes an intrusion detection model for IVNs, based on the VGG16 classifier deep learning model, to learn attack behaviour characteristics and classify threats. The experimental dataset was provided by the Hacking and Countermeasure Research Lab (HCRL) to validate classification performance for denial of service (DoS), fuzzy attacks, spoofing gear, and RPM in vehicle communications. The proposed classifier’s performance was compared with that of the XBoost ensemble learning scheme to identify threats from in-vehicle networks. In particular, the test cases can detect anomalies in terms of accuracy, precision, recall, and F1-score to ensure detection accuracy and identify false alarm threats. The experimental results show that the classification accuracy of the dataset for HCRL Car-Hacking by the VGG16 and XBoost classifiers (n = 50) reached 97.8241% and 99.9995% for the 5-subcategory classification results on the testing data, respectively.

Smart in-cylinder pressure sensor for closed-loop combustion control

Abstract. Our approach of a closed-loop combustion control is built on an intensively evaluated robust cylinder pressure sensor with integrated smart electronics and an openly programmed engine control unit. The presented pressure sensor consists of a steel membrane and a highly strain-sensitive thin film with laser-welded electrical contacts. All components are optimized for reliable operation at high temperatures. The sensor setup safely converts the in-cylinder pressure of a combustion engine at temperatures of up to 200 ∘C into the desired electrical values. Furthermore, the embedded smart electronics provides a fast analogue to digital conversion and subsequently computes significant combustion parameters in real time, based on implemented thermodynamic equations, namely the 50 % mass fraction burned, the indicated mean effective pressure, the maximum pressure and a digital value, which represents the intensity of knocking. Only these aggregated parameters – not the running pressure values – are sent to the engine control unit. The data communication between the smart sensor and the engine control unit is based on the controller area network bus system, which is widely spread in the automotive industry and allows a robust data transfer minimizing electrical interferences. The established closed-loop combustion control is able to control the ignition angle in accordance with the 50 % mass fraction burned at a certain crankshaft angle. With this loop, the combustion engine is controlled and run efficiently even if the ignition angle is intentionally incorrectly adjusted. The controlled and automatic correction of simulated ageing effects is demonstrated as well as the self-adjustment of an efficient operation when different fuels are used. In addition, our approach saves the computing capacity of the engine control unit by outsourcing the data processing to the sensor system.

LSTM-Based Intrusion Detection System for In-Vehicle Can Bus Communications

The modern automobile is a complex piece of technology that uses the Controller Area Network (CAN) bus system as a central system for managing the communication between the electronic control units (ECUs). Despite its central importance, the CAN bus system does not support authentication and authorization mechanisms, i.e., CAN messages are broadcast without basic security features. As a result, it is easy for attackers to launch attacks at the CAN bus network system. Attackers can compromise the CAN bus system in several ways including Denial of Service (DoS), Fuzzing and Spoofing attacks. It is imperative to devise methodologies to protect modern cars against the aforementioned attacks. In this paper, we propose a Long Short-Term Memory (LSTM)-based Intrusion Detection System (IDS) to detect and mitigate the CAN bus network attacks. We generate our own dataset by first extracting attack-free data from our experimental car and by injecting attacks into the latter and collecting the dataset. We use the dataset for testing and training our model. With our selected hyper-parameter values, our results demonstrate that our classifier is efficient in detecting the CAN bus network attacks, we achieved an overall detection accuracy of 99.995%. We also compare the proposed LSTM method with the Survival Analysis for automobile IDS dataset which is developed by the Hacking and Countermeasure Research Lab, Korea. Our proposed LSTM model achieves a higher detection rate than the Survival Analysis method.

Modeling and Verification of CAN Bus with Application Layer using UPPAAL

Controller Area Network (CAN) is a high-speed serial bus system with real-time capability. In this paper, we present a formal model of the CAN bus protocol, mainly focusing on the arbitration process, transmission process, and fault confinement mechanism. Moreover, 11 important properties are formalized in terms of the protocol. Based on the verification tool UPPAAL, we describe the system model and properties for performing verification work of the CAN bus protocol. The verification results indicate that some properties are not satisfied in CAN bus system, most of which are caused by the starvation and bus-off nodes. On this basis, the dynamic priority scheduling algorithm and bus-off recovery mechanism are applied, which indicates that some problems can be solved on the application layer.

Study of Non-Normal Distribution Time Parameters Data Transmission Reliability in CAN Bus

The message transmission reliability is very important for the design of the CAN (Controller Area Network) bus system, which is related to the normal operation of the bus control system. The bus message transmission time parameters are analyzed based on the CAN bus scheduling theory. The formula is a derived by means of probability analysis based on the fourth-moment method. An example is calculated to get its message reliability and the result is contrasted with the MONTE-CARLO method simulation, and then the bus message transmission reliability can be got. It has great practical significance.

Performance Analysis of Controller Area Network

Controller Area Network (CAN) is widely used in automotive and industrial areas. To give guidance in the design process, CAN bus communication model is established using Matlab/SimulinkTM. Considering the error frames on the bus, the formula that calculating CAN response time and bus load is revised. The relating performance indexes of CAN bus is gained separately through calculation and simulation, it concludes that the CAN bus communication model can efficiently simulate the message transfer sequences in the real bus, and achieves an exact result of the performance analysis of the CAN bus system.

Design and Evaluation of Controller Area Network for Automotive Applications

Now-a-days, as computerization of automotive increases, the need for more/advanced electronic control units (ECUs) is growing. Vehicles are increasingly behaving like computers with wheels. Due to the abundance use of ECUs in cars, electronic system design is becoming complicated day by day. As a consequence, information processing in such complex systems faces interruptions. Therefore, there is a need for a system which will be the connective tissue between a vehicle's computers and different sensors. Controller Area Network (CAN) is such an embedded system to bring communication and connectivity in automobile system together. Optimization of CAN bus is a concerning issue because of the recent demands such as hybrid, electric propulsion, or driver assistance that involves more stringent real-time constraints. In this paper, we introduce an optimized CAN bus for vehicle automation through microcontroller based design and implementation. Multiple modules of a vehicle are modeled using CAN bus. The proposed CAN bus system is evaluated by analyzing the frame response time using “RTaW-Sim:” a CAN simulation and configuration tool. Experimental results show that the proposed CAN system helps decrease the frame response time by up to 45% when compared with a traditional system. The CAN bus simulation platform using RTaW-Sim also helps reduce the design cost and improve the systems quality.

A Co-Simulation-and-Test Method for CAN Bus System

Simulation and test are important for the development and validation of automotive ECU (Electronic Control Unit). However, problems arise in the combination of today's automotive control algorithm development and function test. There are lots of professional tools for simulation and test, but lack of interfacing capability between them, especially in the simulation and test of today's automotive network. The approach of COM (Component Object Model) technology is used to solve this problem, and a complete co-simulation-and- test system is introduced in this article, which is made up of CAN (Controller Area Network) Bus Simulation Environment - AutoCAN, and CAN Bus Disturbance Generator - CANspider and MATLAB. AutoCAN and CANspider have great advantages in simulation and test of automotive CAN bus, while MATLAB has superior performance in modeling. The integration of these tools makes it possible to realize the internal communication between them, and combine their respective advantages and increase the efficiency of engineering application. Experiments are performed to prove the effectiveness of the platform for developing and testing the automotive network system based on automotive CAN Bus.  Index Terms—AutoCAN, CANspider, MATLAB, COM, Co- simulation-and-test

Research and Development of Hybrid Electric Vehicles CAN-Bus Data Monitor and Diagnostic System through OBD-II and Android-Based Smartphones

With the rapid development of the smartphone market, future cars seem to have more connections with intelligent cell phone and Internet. Intelligent transportation system (ITS) and telematics system have become research focus in recent years. There is an increasing demand for remote monitoring and diagnostic system as the further research of hybrid electric vehicle (HEV) goes on. In this paper, a remote controller area network bus (CAN-Bus) data monitor and diagnostic system for HEV is presented using on board diagnostic version-II (OBD-II) and Android-based smartphone. It is low-cost, convenient, and extensible with smartphone used in the system to realize communication with ELM327 and remote monitoring center wirelessly. The prototype of client and server is developed in Java language, and it is proved by the test that the system works stably and the collected data have practical values.

Stochastic and deterministic performance evaluation of automotive CAN communication

The performance of communication systems can be evaluated using various distinct techniques and paradigms, e.g. queuing theory, simulation or worst case analysis. Mean values for performance measures like transmission delay, queue length or system utilization are valuable information for network dimensioning. However, in many cases, quantile-based approaches or deterministic upper bounds are indispensable, especially for systems that need real-time guarantees. A typical application area are safety-critical functions in automotive environments, where hard real-time transmission deadlines have to be met to assure safe operation of the vehicle. In this paper, we investigate a contemporary automotive in-car communication system, the Controller Area Network (CAN). A simulation study of the system yields stochastic quantile-related use case performance measures for non-time-critical communication. It is complemented by a deterministic evaluation using Network Calculus, which allows to determine worst case transmission times and provides closed and easily applicable formulas for delay bounds of messages on all priority levels. Comprising the outcomes from this dual evaluation approach supports the design, dimensioning and parameterization of the overall CAN bus system with respect to both hard real-time demands and performance characteristics in typical use case scenarios.

Methodology to Predict EME Effects in CAN Bus Systems Using VHDL-AMS

The electromagnetic emissions (EME) of integrated circuits (ICs) are of increasing importance in the selection of automotive components. Although the IC is treated as the main cause for these emissions, the electrical environment, i.e., the application of an IC including the minimal circuitry on the application board and its layout, as well as the global connection terminals (i.e., supply pins and bus signals) representing the load of an IC are crucial in determining the emission behavior of the entire system. This paper provides application engineers information about different aspects related to the EME of a controller area network (CAN) bus system and how emissions are generated and transformed within the application environment. It presents a methodology to investigate and predict the effects by using Very High-Speed IC Hardware Description Language-Analog Mixed Signal (VHDL-AMS). The description focuses on the interaction between the CAN transceivers and the twisted pair transmission line connecting them. Both common mode and differential mode as well as mode conversion aspects are considered. It highlights the fact that EMEs from a CAN bus system highly depend on the application environment.

Design and Implementation of a Vehicular Controller Area Network Bus System with an Application of Active Noise Control for Engine Exhaust System

Design and Implementation of a Vehicular Controller Area Network Bus System with an Application of Active Noise Control for Engine Exhaust System

Design and Implementation of a Vehicular Controller Area Network Bus System with an Application of Active Noise Control for Engine Exhaust System

This paper describes the design of a vehicular controller area network (CAN) bus system with an application of active noise control (ANC) for engine exhaust systems. The work includes two parts: the first part is the design and implementation of a CAN bus platform system; the second is an application of ANC to an engine exhaust system which utilizes the CAN network implementation. The proposed ANC uses the adaptive control algorithm with engine speed as a reference. Most of the conventional methods for ANC involve primarily an adaptive filter with the least-mean-square (LMS) error algorithm. Unfortunately, convergence speed is often limited when a sound source or a filtering plant varies, because the learning process of the adaptive algorithm fails to respond quickly to the changing operational conditions. In this study, a variable step-size affine-projection algorithm (VSS-APA) is proposed. The proposed VSS-APA filtering algorithm is a combination of the variable step-size convergence algorithm and the affine-projection algorithm (APA). The controller is implemented on the proposed CAN bus system. Experiments are carried out to evaluate the noise attenuation performance at various engine speeds. The experimental results indicated that the ANC system achieved the noise attenuation in an engine exhaust system by using the proposed CAN bus system.