Automobile Fault Research Articles

Ultra-Fast BNN Analysis with the upgraded FINN Framework: Harnessing GoogLeNet and Contemporary Transfer Methods for deploying algorithms on NVidia GPU

By combining Binarized Neural Networks (BNNs) with the updated FINN framework and utilizing GoogLeNet with sophisticated transfer learning on Nvidia GPUs, this research presents a novel method for object detection. The goal is to decrease processing time and increase detection precision. TensorFlow optimization allows BNN architectures to balance efficiency and accuracy. Pretrained CNNs use supervised learning specific to each dataset and model architecture to handle a variety of datasets, including MNIST, CIFAR, and SVHN. Fast processing is made possible by the Nvidia Jetson Nano GPU, particularly in dynamic environments like automobile fault detection. Transfer learning adaptation of GoogLeNet's last layer achieves 93% accuracy for chairs, 94% accuracy for people, and 96% accuracy for mouse recognition, which is higher than standalone accuracy. Testing times as low as 4 seconds are possible with the combined technique, which reaches 18 FPS processing speed. This study establishes a new standard for neural network deployments by demonstrating the synergy between sophisticated neural network models, traditional topologies, and transfer learning inside the FINN framework. The Nvidia Jetson Nano GPU is essential for accelerating calculations, meeting both accuracy and speed objectives. In conclusion, this work highlights technological advancements in computer vision and plots future exploration trajectories by combining deep learning, GoogLeNet's strengths, transfer learning, and the FINN framework to promote neural network deployments in real-time applications.

An Intelligent Fuzzy Logic Automobile Fault Diagnostic System

The advent of intelligent transportation systems and the growing complexity of modern automobiles necessitated innovative approaches to fault detection and diagnostics. This study presents an Intelligent Fuzzy Logic Automobile Fault Diagnostic System. It is designed to enhance the safety and reliability of automotive systems. Fuzzy logic with its ability to handle imprecise and uncertain data is harnessed to develop a robust model capable of identifying and classifying faults in real-time. The system incorporates a hybrid computerized fuzzy system, to aid vehicle owners in identifying issues with their vehicles and providing sound repairs recommendations for any malfunctioning parts. The system was implemented using web technologies; ASP.Net, Bootstrap 3.5, CSS, JavaScript, JQuery and SQL server. The results indicate its potential for widespread adoption, with the ability to reduce accidents and maintenance costs while enhancing the driving experience and provides an accuracy of 73.14% in performance. The Precision 100% and F1 Score 75.72%.

ICA-Feature-Extraction-Based Fault Identification of Vehicular Starter Motor

The starter motor is responsible for providing the mechanical rotating energy for automotive operation through electromechanical conversion via battery. In case of a fault on the starter motor, the vehicle will fail to operate posing problems for the driver, especially for an emergency service vehicle like an ambulance. The starter motor and its corresponding components are prone to mechanical as well as electrical faults due to high starting torque and friction with the flywheel and gear teeth of the starter. In this paper, the focus has been given to the electrical fault of a starter motor and its effect on the operational characteristics of an automobile. The response characteristics thus obtained have been evaluated by independent component analysis (ICA) based feature extraction analysis to obtain a continuous data set for automobile fault diagnosis. The feature analysis of the response characteristics helps in easier calculation while being effective in designing a system that can help with vehicle diagnosis and quality control.

Retracted: A Self-Diagnostic Method for Automobile Faults in Multiple Working Conditions Based on SOM-BPNN.

[This retracts the article DOI: 10.1155/2021/6801161.].

Online Monitoring of Automotive Engine Lubricating Oil Based on Internet of Things Technology

In order to realize the online monitoring of automotive engine lubricating oil, a method based on Internet of Things technology is proposed. This method uses the self-organizing neural network of the Internet of Things to fuse the original multidimensional feature data to obtain the fusion value. The Parzen window method is used to formulate the limit value of fusion value, and the samples are divided into three states: normal, warning, and abnormal. Weka software is used to extract rules from oil data. This method can identify different wear state information from oil spectral data, extract knowledge rules, and use them to build the knowledge base of automobile engine wear diagnosis system, so as to realize the automation and intelligence of automobile engine fault diagnosis based on lubricating oil spectral wear data. The measurement method of the lubricating oil sensor is mainly to comprehensively reflect the relationship between oil quality and electrical signal, so as to effectively provide users with reliable information. After many studies, it is concluded that the conductivity of lubricating oil has a good linear relationship with its acid value, metal particles, moisture content, and the change of additive content. Measuring the change of conductivity is an effective means to detect the change of lubricating oil quality. The experimental results show that using the extracted knowledge rules to verify the state of samples, the recognition rate is 97.47%. In order to more fully explain the difference between important element fusion and all feature fusion, all features are extracted. At the same time, the fault diagnosis and recognition rate of all features is not high, only 62.39%. It is proved that the Internet of Things technology can effectively realize online monitoring of the automotive engine lubricating oil.

Fault Diagnosis of Automobile Engine Based on Improved BP Neutral Network

With the continuous enrichment of automobile functions and the complexity of automobile structure, the difficulty of automobile fault diagnosis is constantly increasing. The study of fault diagnosis methods with high real-time performance, accuracy, and predictability is of great significance to improve automobile safety performance and ensure driving safety. Since the convergence speed of the traditional BP neural network algorithm is slow and the accuracy is insufficient in the process of automobile engine fault diagnosis, this paper improves convergence speed of the algorithm by introducing the momentum term, and the weights and thresholds of the neural network are optimized by using GA selection, crossover, and genetic characteristics, to propose a genetic algorithm (GA) optimization BP neural network fault diagnosis method. The average absolute error of the traditional BP neural network algorithm is 0.5976, while the average absolute error of the improved BP neural network algorithm in this paper is 0.1027. The comparative simulation results show that the proposed improved algorithm is better than the traditional BP neural network algorithm in diagnosis precision, accuracy, and other key indicators.

Compiling method of automobile fault diagnosis information

Automobile fault diagnosis is the most technical content in automobile maintenance. The speed, accuracy and convenience of diagnosis directly affect the maintenance efficiency. Automobile fault diagnosis information is an important reference for finding and solving automobile faults. High quality information is the key to improve technical personnel's judgment and solving faults. In this paper, the methods and examples of fault diagnosis information compilation are given to guide the technical data writers to compile effective fault diagnosis information for automobiles.

Application Analysis of Artificial Intelligent Neural Network Based on Intelligent Diagnosis

In recent years, the continuous development of computer science and AI technology makes the application prospect of artificial intelligence in fault diagnosis emerge. As a simulation technology of human thinking pattern, intelligent diagnosis technology can check and manage the monitoring target in real time to ensure the accuracy of data information. This paper introduces the basic principles of key artificial intelligence technologies in the field of sports, such as convolutional neural network, object detection, object tracking and action recognition. Then it analyzes the application status of intelligent diagnosis technology and artificial intelligence network under intelligent diagnosis, and puts forward the application of artificial intelligence neural network in automobile fault diagnosis based on examples. In the construction of the neural network system, the real-time collection of vehicle operation data can be analyzed, once the fault is found, the driver can be notified in time to avoid safety accidents. The author summarizes the existing research results on the application of artificial intelligence algorithm in intelligent diagnosis, in order to provide help for the subsequent research.

Taking Comprehensive Experiments as the Starting Point to Improve the Quality of Training Applied Undergraduate Talents—— Taking the Automobile Detection and Fault Diagnosis Course as an Example

Taking Comprehensive Experiments as the Starting Point to Improve the Quality of Training Applied Undergraduate Talents—— Taking the Automobile Detection and Fault Diagnosis Course as an Example

A Self-Diagnostic Method for Automobile Faults in Multiple Working Conditions Based on SOM-BPNN.

Due to the complex and diverse forms of automobile emission detection faults and various interference factors, it is difficult to determine the fault types effectively and accurately use the traditional diagnosis model. In this paper, a multicondition auto fault diagnosis method based on a vehicle chassis dynamometer is proposed. 3σ method and data normalization were used to pretreat tail gas data. BPNN-RNN (Back Propagation Neural Networks-Recurrent Neural Networks) variable speed integral PID control method was used to achieve high-precision vehicle chassis dynamometer control. Accurate tail gas data were obtained. The simulation and test results of BPNN-RNN variable speed integral PID control were verified and analyzed. The PID control method can quickly adjust PID parameters (within 10 control cycles), control overshoot within 2% of the target value, eliminate the static error, and improve the control performance of the vehicle chassis dynamometer. Combined with BPNN (Back Propagation Neural Network) and SOM (Self-organizing Maps) network, a BPNN-SOM fault diagnosis model is proposed in this paper. By comparing and analyzing the fault diagnosis performance of various neural networks and SOM-BPNN algorithm, it is found that the SOM-BPNN model has the best comprehensive result, the prediction accuracy is 98.75%, the time is 0.45 seconds, and it has good real-time stability. The proposed model can effectively diagnose the vehicle fault, provide a certain direction for maintenance personnel to judge the vehicle state, and provide certain help to alleviate traffic pollution problem.

Design and Implementation of an Expert Management System for Automobile Fault Detection

A system has been developed to communicate with the On-Board Diagnostics system of a car using the Controller Area Network communication protocol. The system requests the stored trouble codes that might have been detected by the diagnostics system and sends them to a server. The information is accessed through a web interface. The web interface allows the user to find the solutions in the database together with the detected faults. The database also contains information about trouble codes, such as their symptoms, causes and how to fix them. Monitoring the communications while testing the prototype showed that the system works as intended and can communicate with cars from different manufacturers and extract the data. The prototype system was compared with a commercial scan tool and testing showed that they both produced the same results. The second module of the project deals with the design and implementation of an expert system for car faults diagnosis. The project is motivated by the need to guide car owners and learners' motor mechanics in the maintenance and troubleshooting of motor problems without having to resort to presumptions and conjectures. Particularly, it is expected that the proposed design would ensure that car owners have proper assistance in times of crisis and what’s more, will save them from the clutches of exploitative roadside mechanics. For this purpose, a rule-based artificial intelligence (AI) technique was utilized to obtain theoretical and practical expert system parameters, and then a conceptual expert system was designed. The expert system functioning is based on the database of car faults, symptoms and their correction, which make up its knowledge base. The new system was developed using PHP and MySQL database. This language was chosen because of its easy syntax and features for developing web-based applications.

Design and Development of Automobile Fault Diagnosis System Using AI Machine Learning

Design and Development of Automobile Fault Diagnosis System Using AI Machine Learning

The Research of Improved BP Neural Network in Automobile Sensor Fault Diagnosis

Fault control diagnosis object of automobile sensor has the problems of big space dimension of fault sample data and poor real-time capability of fault diagnosis, etc, in order to solve these problems, this text introduces static fuzzy control method to diagnose automobile fault based on BP neural network, first finding fault node by static fuzzy self-learning method and classifying and diagnosing intelligently by BP network. Experiments show that method in this paper improves the accuracy of automobile sensor fault diagnosis and reduces diagnosis error, thus improves the recognition and decision-making ability of diagnosis.

Automotive Remote Fault Diagnosis Using the Technology of Artificial Intelligent Neural Network

With the rapid development of automobile electronic technology, automotive interior structure and mutual communication relations are becoming increasingly complex; meanwhile,users’ requirements for timeliness and accuracy in automobile fault diagnosis are also getting higher, thus increasing the difficulty and uncertainty of automobile fault diagnosis process. The automobile fault clustering fusion system with artificial intelligent neural network as the core is established for fault diagnosis, which not only meets the requirement for timeliness, but also makes after-sale diagnosis service intelligent and user-friendly. This system will have a promising development in future.

Automotive Wire Control Steering Sensor Fault Detection Algorithm Research

This article to cancel after the mechanical connections between steering wheel and steering, wire control steering system security and reliability problems, put forward on the basis of the analytical redundancy software sensor method of wire control steering system. In order to solve the compared with the traditional steering system in terms of reliability and safety of the problems of structural changes, the wire control steering system of the main sensor fault diagnosis methods are studied. In wire control steering system associated with the vehicle dynamics model is established under the premise of hypothesis testing to double adaptive fading Kalman filtering technology as a platform, combined with according to the working state of each sensors to determine fault feature vector, to build the main sensor wire control steering automobile fault diagnosis method of residual error threshold. For fault diagnosis of automobile EPS sensor, the BP neural network is put forward to EPS sensor for auto are introduced in the fault diagnosis. For large-scale wireless sensor networks (WSN), reduce the fault detection accuracy, and larger load of communication problems, according to the spatial and temporal correlation characteristics of sensor nodes, proposes a distributed sensor fault detection algorithm based on cluster. These algorithms for sensor fault detection is of great significance.

Based on LabNIEW Environment Auto Fault Detection Research of Virtual Test System

Virtual test system based on software as the core of intelligent system based on computer technology. In LabNIEW environment are introduced, on the auto electric power steering, car trouble related performance was tested. Car trouble vary widely, the characteristics of the dynamic and uncertainty, in view of the present automobile fault detection of real-time detection of the existence of difference, the data is not convenient to undertake unity management problems, this paper used the GPS, GPRS and CAN bus technologies, design a set of automatic control system. With the development of era, the existing Petri net reasoning algorithm cannot have satisfied nowadays car diagnostic technology, aiming at this situation, this paper proposes a modified algorithm, with fuzzy reasoning algorithm of Petri net optimization, finally, the fault diagnosis. According to diagnosis, combining wavelet analysis and the principle of artificial immune system, put forward a kind of based on wavelet transform and the fault diagnosis system of the immune system. According to the characteristics of the wavelet analysis, it is used to analyze the unstable signal, signal feature vector as raw data, using the improved negative selection algorithm for himself - he analysis the original data.

Automobile Engine Fault Diagnosis and Prediction System

Aimed at the fault diagnosis and prediction of automobile engine, firstly designed a framework structure of automobile engine fault diagnosis and prediction system, and built a hardware platform; Secondly adopted the genetic algorithm neural network to fault prediction and diagnosis reasoning; Finally after analyzing automobile exhaust components, engine vibration, engine abnormal sound parameters, inferred the appeared and impending fault of automobile then made the tips for users on the screen. The results show that the performance of system is well, the accuracy of diagnosis and prediction is 95% in different conditions of experiment and debugging.

Design Car Fault Diagnosis System

Based on the domestic and foreign automobile fault diagnosis status and trends were compared in detail on Syria to study a low-power , high-precision , easy to carry and apply a wide degree of automotive fault diagnostic . This paper aims to study the C8051F020 fault diagnostic , fault depth diagnostic hardware and software design , understanding automotive fault diagnostic process .

Automotive Fault Diagnosis Based on the Fuzzy Mathematics

Automobile fault diagnosis is one of the hot issues in detection and diagnosis technology of automobile. The automobile fault has the characteristics of uncertainty and complexity problems. To solve the problems of qualitative description from drivers into quantitative, fuzzy mathematics is introduced. In addition, the fuzzy relationship of automobile fault and fault causes is expressed by setting the membership functions and fuzzy relation matrix. Finally, the qualitative analysis of real cases is present. The fuzzy theory and expert system for automobile fault diagnosis method is proved accurately through the algorithm analysis and real cases.

Development of Algorithms for Efficient Energy Management in the Industrial Common Rail Engine

In order to meet the recently enhanced emission standards at home and abroad, it is necessary to develop the CRDI ECU control algorithm that users can adjust fuel injection timing and amount in response to their needs. Therefore, this study developed the simulator for knocking analysis that enables knocking discrimination and engine balance correction applicable to the ECU exclusive to the industrial CRDI engine. The purpose of this study is to provide the driver-oriented diagnostic services that enable drivers to diagnose vehicles directly by developing diagnostic devices for vehicles with the use of the results of the developed simulator for knocking analysis according to the OBD II standards. For this purpose, this study aims to improve the fuel efficiency of vehicles by proposing the S/W design method of the OBD-II diagnosis device that can provide real-time communications with the use of wired system and bluetooth module as a wireless system to send and receive automobile fault diagnosis signal and sensor output signal, and to suggest an improvement for engine efficiency by minimizing the generation of harmful exhaust gas