Indirect Tire Monitoring System - Machine Learning Approach

Svensson, Oskar Alexander; Thelin, Simon Gunnar Alexander; Byttner, Stefan; Fan, Yuantao

doi:10.1088/1757-899x/252/1/012018

Cited by 13 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are utilised in the calculation of tyre circumference and related pressure through the use of a tree-based classification system. (Svensson et al 2017) To calculate tyre pressure in the vehicle using existing sensors, Svnsson and colleagues (thelin, bytther, and fan) present a supervised machine learning model that they developed. (Vanjire and Patil, n.d.) To demonstrate a decision rule-based approach for tyre monitoring, Egaji, Chakhar, and Brown created a video.…”

Section: Literature Surveymentioning

confidence: 99%

Predictive Models for ABS and TPMS based on Gaussian Naïve Bays

Vanjire

Patil²

2022

IJRITCC

View full text Add to dashboard Cite

The car industry is currently preoccupied with the issue of safety. The increasing number of accidents occurring around the world as a result of automobile problems is a major contributing factor to these incidents. The amount of complicated electronics that is used in vehicles is becoming more prevalent every day. A great effort has been made in evaluating vehicle features in relation to vehicle components. Through such systems, a smart architecture and complex function designs are involved. During all of this vehicle transformation and evolution, the automotive industry recognises a high demand for vehicle safety. While designing and manufacturing this system, automotive experts understand a need for a strict monitoring and feedback system for complex vehicle architecture, which can notify the end user if there is any indication of a failure ahead of time. In order to effectively participate in vehicle design activities, it is critical to grasp the significance of safety features. Tire system failures and braking system failures have played a large role in several recent traffic accidents. The failures of the tyre system and the braking system in the vehicle are addressed in this study. While investigating this system, it is discovered that it is supported by complex electrical systems, which include an ECU (electronic controller unit), sensors, and a wire system. Through the use of these technologies, censored data can be processed in a timely manner and made available for diagnostic purposes. Nevertheless, car diagnostics is needed after any vehicle failure but that does not serve the aim of maintaining vehicle safety. As a result, predictive analysis or predictive diagnostics may be a viable option for informing the driver about the health of a particular vehicle component in advance. In this study, the author discusses the concepts of vehicle prognostics for the tyre pressure monitor system and the antilock braking system, which are accomplished using a statistical method of machine learning. In today's world, machine learning is expanding in breadth, and the world is becoming more aware of its enormous potential in the field of data analytics. It is the purpose of this study to introduce methodologies by which machine learning can assist vehicle predictive analytics to attain the intended goal of vehicle safety.The author of this article discusses how Bayesian statistics may be used to produce predictions in the form of probability estimation. The prediction's outcome is thoroughly analysed.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Predictive Models for ABS and TPMS based on Gaussian Naïve Bays

Vanjire

Patil²

2022

IJRITCC

View full text Add to dashboard Cite

show abstract

“…The study focused on comparing various types of pressure transducers, their measuring accuracy and power consumptions. Svensson et al (2017) designed and developed an iTPMS using a supervised machine learning approach. The system permits to detect both incorrect tyre pressure and thread depth for different type of vehicles within a fleet without the need for additional physical sensors or vehicle specific parameters.…”

Section: Some Existing Approachesmentioning

confidence: 99%

An innovative decision rule approach to tyre pressure monitoring

Egaji

Chakhar

Brown

2019

Expert Systems with Applications

View full text Add to dashboard Cite

“…The bestperforming classifier for every feature set was determined. Data driven KNN Air [16] Data Driven Random Forest Air [17] Data Driven Gaussian Naive Bayes Algorithm Air [18] Data Driven Random Forest and Hoeffding Tree Algorithm Air [19] Statistical J48 Decision Tree Algorithm Nitrogen [20] Statistical Random Forest Algorithm Nitrogen…”

Section: Introductionmentioning

confidence: 99%

Application of feature fusion strategy for monitoring the condition of nitrogen filled tires using tree family of classifiers

Parihar,

Naveen Venkatesh,

Anoop

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

The tire pressure monitoring systems (TPMS) are dedicated vehicle systems that calculate the tire pressure under various conditions. Proper maintenance of tire pressure can have a significant impact on enhancing the vehicle handling, vehicle performance, occupant safety, comfort and fuel efficiency. Recent years have seen the shift in the preference for nitrogen filled tires over air filled due to the superior thermal stability and uniform pressure management characteristics displayed by nitrogen filled tires. The present article details the application of machine learning in TPMS for providing more insights on the tire behaviour for four different tire conditions (puncture, idle, high and normal). This paper specifically focuses on the collaborative approach that combines various features extracted with tree-based classifiers. Vertical wheel hub vibrations were captured using an accelerometer from which distinct features like autoregressive moving average (ARMA), statistical and histogram were extracted. With the application of J48, the most significant and contributing features were identified for every feature set extracted that were fed into tree-based classifiers. The best performing classifier for every feature set was determined to be 95.83% (statistical – random forest), 93.75% (histogram- optimized forest) and 93.75% (ARMA – random forest). Furthermore, an extensive analysis was carried out to determine the impact of feature fusion approach for feature combinations like statistical-histogram, histogram-ARMA, statistical-ARMA and statistical-histogram-ARMA. The experimental results indicate a commendable classification accuracy of 97.92% for a feature fusion of statistical-histogram-ARMA features with forest penalizing attributes algorithm.

show abstract

Indirect Tire Monitoring System - Machine Learning Approach

Cited by 13 publications

References 3 publications

Predictive Models for ABS and TPMS based on Gaussian Naïve Bays

Predictive Models for ABS and TPMS based on Gaussian Naïve Bays

An innovative decision rule approach to tyre pressure monitoring

Application of feature fusion strategy for monitoring the condition of nitrogen filled tires using tree family of classifiers

Contact Info

Product

Resources

About