Search

According to previous studies on internal combustion engine applications using deep learning, deep learning model should be individually optimized and trained to predict different phenomena. This study introduces task transfer learning to predict transient nitrogen oxides (NO $_{\mathrm {x}}$ ), soot, and total hydrocarbon (THC) emissions, which are the major emissions from diesel engines. Using the concept of task transfer learning, when there is a pretrained model relevant to the target task, the model can be transferred to predict another phenomenon by training only the last two layers with hyperparameters of the pretrained model. This concept omits the need for optimizing and training separate models that can save computational time and cost. The results of task transfer learning were evaluated using Worldwide Harmonized Light Vehicles Test Procedure (WLTP) cycle data, which are representative transient cycles of the internal combustion engine, and all possible transfer cases with NOx, soot, and THC emissions were investigated. The R2 values of pretrained NOx, soot, and THC models were 0.9780, 0.9215, and 0.9390, respectively. The R2 gaps between the pretrained and transferred models were within 0.012, with a value of 0.0015 for the NOx emission, 0.011 for the soot emission, and 0.0115 for the THC emission. The relative mean absolute errors (MAEs) to the maximum emission values were approximately 0.57-0.82% for NOx emissions, 0.69-2.02% for soot emissions, and 1.52-2.42% for THC emissions. These accuracy results were comparable to the accuracy of the emission measurement device, which was better than that of the sensors for practical use in vehicles. The results indicated that task transfer learning was valid for predicting emissions of an internal combustion engine, and it achieved efficient organization of prediction models using a pretrained model.

This paper proposes a resolver offset calibration algorithm that can detect offset with high precision just by configuring a very simple experimental environment. This use of a simple experimental environment holds a great advantage for large-capacity permanent magnet synchronous motors (PMSMs) that require substantial resources to configure an experimental environment, such as EV traction motors. The proposed algorithm is designed based on the PMSM voltage equation. The algorithm is first verified for its validity through simulation with Simulink. Subsequently, it is implemented based on the C-language and installed on an inverter for verification experiments. The implemented algorithm is very simple and requires little execution time and memory. The error in the calibrated offset is experimentally found to converge within 3-bits based on 12-bits (the resolution of the commonly used RDC), and the results have very little deviation.

To detect the three-phase current in the complex plane of a DC link shunt inverter, an algorithm for restoring the current is required. In this paper, a method of dividing the detection voltage and the compensation voltage to match the output voltage as much as possible to reduce the total harmonic distortion while restoring the current is proposed. In addition, an overmodulation algorithm for a 12-step output, which corresponds to the largest voltage in a DC link shunt inverter, is proposed, and a current recovery method in the overmodulation region is proposed. To determine how to ensure a linear output voltage, the fundamental frequency of the output voltage is analyzed through a Fourier series, and a new voltage vector whose fundamental frequency amplitude is equal to the amplitude of the command voltage is calculated. Finally, the performance of the proposed algorithm is verified through simulation and experimentation. The output of a motor was increased by using overmodulation, and the harmonics of the current based on the output voltage were analyzed through a Fourier series.

The use of coupled-bias common-mode feedback allows a low-voltage differential signaling driver, implemented in a deep-submicron process, to adjust its output common-mode voltage, as well as the output swing and equalization strength independently. This form of differential signaling driver has been incorporated in a 16-channel transmitter for the timing controller of an intra-panel interface. The flexibility of its output characteristics allows it to accommodate the range of channel characteristics commonly found in the intra-panel interface of an ultra-high-definition display. Fabricated in a 28-nm bulk CMOS process, our 16-channel transmitter occupies 1.39 mm2. Its total power consumption is 203.2 mW with a supply voltage of 1.05 V, running at 3.2 Gb/s with the maximum output swing. Measurements confirm that the transmitter can operate from 0.8 to 3.2 Gb/s with channels that replicate those encountered in an intra-panel interface. The maximum controllable range of the output swing, the output common-mode voltage, and equalization are 216-1072 mVdiff, 291-604 mV, and 0-14.6 dB, respectively.