A TinyML Soft-Sensor Approach for Low-Cost Detection and Monitoring of Vehicular Emissions.

Vehicles are the major source of air pollution in modern cities, emitting excessive levels of CO2 and other noxious gases. Exploiting the OBD-II interface available on most vehicles, the continuous emission of such pollutants can be indirectly measured over time, although accuracy has been an important design issue when performing this task due the nature of the retrieved data. In this scenario, soft-sensor approaches can be adopted to process engine combustion data such as fuel injection and mass air flow, processing them to estimate pollution and transmitting the results for further analyses. Therefore, this article proposes a soft-sensor solution based on an embedded system designed to retrieve data from vehicles through their OBD-II interface, processing different inputs to provide estimated values of CO2 emissions over time. According to the type of data provided by the vehicle, two different algorithms are defined, and each follows a comprehensive mathematical formulation. Moreover, an unsupervised TinyML approach is also derived to remove outliers data when processing the computed data stream, improving the accuracy of the soft sensor as a whole while not requiring any interaction with cloud-based servers to operate. Initial results for an embedded implementation on the Freematics ONE+ board have shown the proposal's feasibility with an acquisition frequency equal to 1Hz and emission granularity measure of gCO2/km.

Development of a Soft Sensor for Flow Estimation in Water Supply Systems Using Artificial Neural Networks.

A water supply system is considered an essential service to the population as it is about providing an essential good for life. This system typically consists of several sensors, transducers, pumps, etc., and some of these elements have high costs and/or complex installation. The indirect measurement of a quantity can be used to obtain a desired variable, dispensing with the use of a specific sensor in the plant. Among the contributions of this technique is the design of the pressure controller using the adaptive control, as well as the use of an artificial neural network for the construction of nonlinear models using inherent system parameters such as pressure, engine rotation frequency and control valve angle, with the purpose of estimating the flow. Among the various contributions of the research, we can highlight the suppression in the acquisition of physical flow meters, the elimination of physical installation and others. The validation was carried out through tests in an experimental bench located in the Laboratory of Energy and Hydraulic Efficiency in Sanitation of the Federal University of Paraiba. The results of the soft sensor were compared with those of an electromagnetic flux sensor, obtaining a maximum error of 10%.

State of Charge Estimation of Battery Based on Neural Networks and Adaptive Strategies with Correntropy.

Nowadays, electric vehicles have gained great popularity due to their performance and efficiency. Investment in the development of this new technology is justified by increased consciousness of the environmental impacts caused by combustion vehicles such as greenhouse gas emissions, which have contributed to global warming as well as the depletion of non-oil renewable energy source. The lithium-ion battery is an appropriate choice for electric vehicles (EVs) due to its promising features of high voltage, high energy density, low self-discharge, and long life cycles. In this context, State of Charge (SoC) is one of the vital parameters of the battery management system (BMS). Nevertheless, because the discharge and charging of battery cells requires complicated chemical operations, it is therefore hard to determine the state of charge of the battery cell. This paper analyses the application of Artificial Neural Networks (ANNs) in the estimation of the SoC of lithium batteries using the NASA's research center dataset. Normally, the learning of these networks is performed by some method based on a gradient, having the mean squared error as a cost function. This paper evaluates the substitution of this traditional function by a measure of similarity of the Information Theory, called the Maximum Correntropy Criterion (MCC). This measure of similarity allows statistical moments of a higher order to be considered during the training process. For this reason, it becomes more appropriate for non-Gaussian error distributions and makes training less sensitive to the presence of outliers. However, this can only be achieved by properly adjusting the width of the Gaussian kernel of the correntropy. The proper tuning of this parameter is done using adaptive strategies and genetic algorithms. The proposed identification model was developed using information for training and validation, using a dataset made available in a online repository maintained by NASA's research center. The obtained results demonstrate that the use of correntropy, as a cost function in the error backpropagation algorithm, makes the identification procedure using ANN networks more robust when compared to the traditional Mean Squared Error.

Adaptive Pressure Control System Based on the Maximum Correntropy Criterion.

Water supply systems are constantly improving their operation through energy efficiency actions that involve the use of advanced measurement, control, and automation techniques. The maintenance and reliability of water distribution is directly associated with hydraulic pressure control. The main challenges encountered in hydraulic pressure control are associated with random changes in the supply plant and the presence of noise and outliers in the sensor measurements. These undesired characteristics cause inefficiency and instability in the control system of the pumping stations. In this scenario, this paper proposes an indirect adaptive control methodology by reference model for modeling and controlling water supply systems. The criterion adopted in the parametric estimation mechanism and the controller adaptation is the Maximum Correntropy. Experimental results obtained with an experimental bench plant showed that the maximum tracking error was 15% during demand variation, percentage overshoot less than 5%, and steady-state error less than 2%, and the control system became robust to noise and outliers. In comparison to the Mean Squared Error criterion, when noise and outliers influence the sensor signal, the proposed methodology stands out, reducing the mean error and the standard deviation, in the worst-case scenario, by more than 1500%. The proposed methodology, therefore, allows for increased reliability and efficiency of an advanced pump control system, avoiding downtime and equipment damage.

Indirect Feedback Measurement of Flow in a Water Pumping Network Employing Artificial Intelligence.

Indirect measurement can be used as an alternative to obtain a desired quantity, whose physical positioning or use of a direct sensor in the plant is expensive or not possible. This procedure can been improved by means of feedback control strategies of a secondary variable, which can be measured and controlled. Its main advantage is a new form of dynamic response, with improvements in the response time of the measurement of the quantity of interest. In water pumping networks, this methodology can be employed for measuring the flow indirectly, which can be advantageous due to the high price of flow sensors and the operational complexity to install them in pipelines. In this work, we present the use of artificial intelligence techniques in the implementation of the feedback system for indirect flow measurement. Among the contributions of this new technique is the design of the pressure controller using the Fuzzy logic theory, which rules out the need for knowing the plant model, as well as the use of an artificial neural network for the construction of nonlinear models with the purpose of indirectly estimating the flow. The validation of the proposed approach was carried out through experimental tests in a water pumping system, fully automated and installed at the Laboratory of Hydraulic and Energy Efficiency in Sanitation at the Federal University of Paraiba (LENHS/UFPB). The results were compared with an electromagnetic flow sensor present in the system, obtaining a maximum relative error of 10%.