Q-Learning-based fuzzy energy management for fuel cell/supercapacitor HEV

A novel fuzzy energy management strategy (EMS) based on improved Q-learning controller and genetic algorithm (GA) is proposed for the real-time power split between fuel cell and supercapacitor of hybrid electric vehicle (HEV). Different from driving pattern recognition–based method, Q-Learning controller takes actions by observing the driving states and compensates to fuzzy controller, that is, no need to know the driving pattern in advance. Aimed to prolong the fuel cell lifetime and decrease its energy consumption, the initial values of Q-table are optimized by GA. Moreover, to enhance the environment adaptation capability, the learning strategy of Q-learning controller is improved. Two adaptive energy management strategies have been compared, and simulation results show that current fluctuation can be reduced by 6.9% and 41.5%, and H2 consumption can be saved by 0.35% and 6.08%, respectively. Meanwhile, state of charge (SOC) of supercapacitor is sustained within the desired safe range.

Features Importance Analysis of Diesel Vehicles’ NOx and CO2 Emission Predictions in Real Road Driving Based on Gradient Boosting Regression Model

In order to have an accurate and fast prediction of the artificial intelligence (AI) model, the choice of input features is at least as important as the choice of model. The effect of input features selection on the emission models of light diesel vehicles driven on real roads was investigated in this paper. The gradient boosting regression (GBR) model was used to train and to predict the emissions of nitrogen oxide (NOx), carbon dioxide (CO2), and the fuel consumption of real driving diesel vehicles in urban scenarios, the suburbs, and on highways. A portable emissions measurement system (PEMS) system was used to collect data of vehicles as well as environmental conditions. The vehicle was run on two routes. The model was trained with the first route data and was used to predict the emissions of the second route. There were ten features related to the NOx model and nine features associated with the CO2 model. The importance of each feature was sorted, and a different number of features were used as input to train the models. The best NOx model had the coefficient of determination (R2) values of 0.99, 0.99, and 0.99 in each driving pattern (urban, suburbs, and highways). Predictions of the second route had the R2 values of 0.88, 0.89, and 0.96 respectively. The best CO2 model had the R2 values of 0.98, 0.99, and 0.99 in each driving pattern, respectively. Predictions of the second route had the R2 values are 0.79, 0.82, and 0.83, respectively. The most important features for the NOx model are mass air flow rate (g/s), exhaust flow rate (m3/min), and CO2 (ppm), while the important features for the CO2 model are exhaust flow rate (m3/min) and mass air flow rate (g/s). It is noted that the regression models based on the top three features may give predictions very close to the measured data.

The Effect of Driving Cycle Duration on its Representativeness

There is an increasing interest in properly representing local driving patterns. The most frequent alternative to describe driving patterns is through a representative time series of speed, denominated driving cycle (DC). However, the DC duration is an important factor in achieving DC representativeness. Long DCs involve high testing costs, while short DCs tend to increase the uncertainty of the fuel consumption and tailpipe emissions results. There is not a defined methodology to establish the DC duration. This study aims to study the effect of different durations of the DCs on their representativeness. We used data of speed, time, fuel consumption, and emissions obtained by monitoring for two months the regular operation of a fleet of 15 buses running in two flat urban regions with different traffic conditions. Using the micro-trips method, we constructed DCs with a duration of 5, 10, 15, 20, 25, 30, 45, 60, and 120 min for each region. For each duration, we repeated the process 500 times in order to establish the trend and dispersion of the DC characteristic parameters. The results indicate that to obtain driving pattern representativeness, the DCs must last at least 25 min. This duration also guarantees the DC representativeness in terms of energy consumption and tailpipe emissions.

MATLAB ALGORITHM FOR DRIVING PATTERN DETECTION AND ANALYSIS USING SMARTPHONE SENSORS

In countries like India and China where the population density is very high and the number of vehicles on road keep on increasing every year it presents us with a problem that is monitoring this entire situation and preventing rash driving and accidents and even if they take place there should be immediate action taken to prevent it from happening again and making the roads a safer environment for everyone. To solve this problem, utilized sensors present in the Smartphone specifically the accelerometer sensor to detect the changes in parameters, for this an app was created. The app will read the sensor data that are embedded in the Smartphone and stores the sensors data in the database, The main reason of using the Smartphone is that implementation will be very easy and cost effective as the hardware is already available with everyone and the cost of implementation will be lower when compared to producing an exclusive hardware for this purpose only. The theoretical threshold values for accelerometer sensor data to calculate sudden breaking, sudden acceleration, harsh cornering with the respective axis is used to determine the initial situation. Feeding this data in MATLAB was we use an algorithm developed for this very purpose of analyzing this data.