Low-Cost Data Acquisition System for Automotive Electronic Control Units

Bedretchuk, João Paulo; Garcia, Sergio Arribas; Igarashi, Thiago Nogiri Nogiri; Canal, Rafael; Spengler, Anderson Wedderhoff; Gracioli, Giovani

doi:10.3390/s23042319

Cited by 15 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the same acquisition system explained by [2,11], where real data was collected from a car (Renault Sandero 2019) by connecting it with a developed acquisition hardware that communicates with the engine ECU. The communication between the hardware and ECU occurs through the Controller Area Network (CAN) bus, utilizing the CAN Calibration Protocol, with limited sampling rates for variable acquisition, which include intervals of 4, 5, 10, and 100 milliseconds [3]. Each data acquisition experiment can retrieve approximately 160 variables using these designated sampling rates.…”

Section: Data Acquisition Methodologymentioning

confidence: 99%

“…Guarantee the efficiency and performance of a vehicle in operation are crucial, and monitoring the combustion engine (CE) is essential to avoid problems that can cause damage, decrease the lifetime, and increase gas emissions and fuel consumption [2]. By reading data from the vehicle's Electronic Control Unit (ECU), it is possible to monitor different engine variables at runtime during the vehicle development phases, thus ensuring and improving its quality [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Torque Regression Using Machine Learning Techniques in Automotive ECUs

Canal,

Bonomo,

de Carvalho

et al. 2024

Preprint

View full text Add to dashboard Cite

With the modernization of the automotive industry, a large amount of data is generated by vehicles during operation. When interpreted analytically, it can result in advances in several areas, such as safety, durability, production efficiency, fuel consumption, and gas emissions. In this work, we focus on engine torque and its regression, to enable the understanding of its behavior and help improve the performance of engines and vehicles, mainly in product development and testing. In addition, it highlights the relationship between torque and misfire for optimizing engine components by showing their impacts, as it is a common failure in combustion engines that impairs engine performance. After a rigorous process of feature selection relevant to torque, we collect data directly from a vehicle's ECU to train and evaluate machine learning algorithms to perform torque regression without relying on synthetic data or public datasets, using misfire detection as one of the inputs to the algorithms. In a car that reaches a torque of 144 Nm, our results reached up to an RMSE of 3.3830 (Nm)², MAE of 2.1620 (Nm), and R² of 0.99. Furthermore, our methodology acquired and processed data in real-time at a cloud server, that detects faults and calculates torque with the vehicle in motion, using less computationally demanding algorithms. These findings not only highlight our ability to predict the engine's torque and its relation with misfires but also our competence in analyzing additional parameters essential to vehicle performance.

show abstract

Section: Data Acquisition Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Torque Regression Using Machine Learning Techniques in Automotive ECUs

Canal,

Bonomo,

de Carvalho

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite the undeniable benefits of monitoring systems, their implementation is not without challenges. Financial constraints [21], technological complexities [22], and resistance within organizational structures are among the prominent barriers faced in adopting these systems [23]. The financial implications of investing in monitoring technologies, coupled with uncertainties regarding the return on investment, often deter organizations from taking proactive measures [24][25][26].…”

Section: Integration Of Monitoring Systems For Environmental Compliancementioning

confidence: 99%

Overcoming Barriers to Digital Transformation towards Greener Supply Chains in Automotive Paint Shop Operations

Carpitella

2024

Sustainability

View full text Add to dashboard Cite

Given the resource-intensive nature of automotive manufacturing processes and their potential to substantially contribute to ecological footprints, the integration of sustainable logistic practices in the context of digital transformation becomes imperative. This paper focuses on the implementation of green supply chain strategies within the automotive sector, targeting significant risks associated with environmental impact, specifically in the critical domain of automotive paint shops. Automotive paint shops indeed play a significant part in determining the overall sustainability of automotive production. Recognized for their role in vehicle esthetics and corrosion protection, the sustainable integration of these facilities is crucial in the pursuit of a greener automotive future. A comprehensive multi-criteria decision-making framework is herein proposed as a valuable tool in pinpointing the most critical barriers to digital transformation and simultaneously prioritizing suitable green logistic strategies in the context of automotive paint shop risk-management procedures. The practical utility of the model extends to practitioners in the automotive paint shop supply chain, particularly those engaged in digitalizing critical operations, facilitating well-informed decision-making aligned with environmental sustainability goals. The findings of this research highlight the critical importance of implementing tailored strategies, including crisis preparedness, transparent communication, proactive outreach, and strategic investments in technology and partnerships, to address barriers and enhance sustainability practices within automotive paint shop operations, thereby contributing to the overall resilience and long-term viability of automotive supply chains.

show abstract

“…Techniques Metrics [11] Vehicle's work period, latitude, longitude, altitude, barometric pressure, engine coolant temperature, fuel level, ambient, air temperature, engine rotation per minute, intake manifold pressure, amount of air entering the engine, air intake temperature, speed, ECU signaling response according to the chances of oxygen levels, throttle position, timing advance, air/fuel ratio Therefore, this study employed the acquisition system described by [5,9]. To ensure the integrity of the analyses proposed in this research, authentic data was collected from a Renault Sandero 2019, provided by Renault do Brasil, using custom acquisition hardware connected to the engine's ECU as described by [4]. Importantly, we exclusively rely on real vehicle data, avoiding simulated or public datasets, a distinctive feature from similar studies.…”

Section: Source Featuresmentioning

confidence: 99%

“…T O guarantee the efficiency and performance of a vehicle during operation, it is crucial to monitor the combustion engine to avoid problems that can cause damage, decrease the lifetime, and increase its gas emissions and fuel consumption. By reading data from the vehicle's Electronic Control Unit (ECU), it is possible to monitor different engine variables at runtime during vehicle development phases, thus ensuring and improving its quality [4].…”

mentioning

confidence: 99%

Machine Learning for Real-Time Fuel Consumption Prediction and Driving Profile Classification Based on ECU Data

Canal,

Riffel,

Gracioli

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Data extracted directly from a vehicle's electronic control unit (ECU) play a crucial role in the automotive industry because they contain valuable information from the engine and electronic parts. These data have the potential to enable compliance analysis, detect faults and errors, and guarantee driver and car safety as well as product quality. Among the possible uses of the data from the ECUs, driving profile analysis and fuel consumption prediction stand out, which enable analyses for insurers and transportation companies, and help to reduce fuel consumption and greenhouse gases, in addition to providing feedback to the driver. In this work, we apply machine learning algorithms to real data from an engine ECU to examine the driver's driving behavior and accurately classify their fuel efficiency. Moreover, we develop regression models that predict fuel consumption for vehicles in operation. To ensure the effectiveness of our models, we carefully select variables strongly correlated with fuel consumption using a feature selection process. Compared to related works, both our profile classification results in precision, recall, and accuracy metrics, and our regression models result in the metrics of mean square errors, mean absolute error, and coefficient of determination, which are superior or similar. Notably, our algorithms exhibit lower computational costs and enable real-time analysis by utilizing a cloud server.INDEX TERMS Machine learning, driving profile analysis, fuel consumption prediction, electronic control unit (ECU).

show abstract

Low-Cost Data Acquisition System for Automotive Electronic Control Units

Cited by 15 publications

References 31 publications

Torque Regression Using Machine Learning Techniques in Automotive ECUs

Torque Regression Using Machine Learning Techniques in Automotive ECUs

Overcoming Barriers to Digital Transformation towards Greener Supply Chains in Automotive Paint Shop Operations

Machine Learning for Real-Time Fuel Consumption Prediction and Driving Profile Classification Based on ECU Data

Contact Info

Product

Resources

About