Direct 3D printing of piezoelectret with the designed structure for accurate control of morphology and piezoelectric sensor sensitivity and sensing range.
1 April 2024 in IEEE Transactions on Vehicular Technology
Model-free learning-based control methods have recently shown significant advantages over traditional control methods in avoiding complex vehicle characteristic estimation and parameter tuning. As a primary policy learning method, imitation learning (IL) is capable of learning control policies directly from expert demonstrations. However, the performance of IL policies is highly dependent on the data sufficiency and quality of the demonstrations. To alleviate the above problems of IL-based policies, a lifelong policy learning (LLPL) framework is proposed in this paper, which extends the IL scheme with lifelong learning (LLL). First, a novel IL-based model-free control policy learning method for path tracking is introduced. Even with imperfect demonstration, the optimal control policy can be learned directly from historical driving data. Second, by using the LLL method, the pre-trained IL policy can be safely updated and fine-tuned with incremental execution knowledge. Third, a knowledge evaluation method for policy learning is introduced to avoid learning redundant or inferior knowledge, thus ensuring the performance improvement of online policy learning. Experiments are conducted using a high-fidelity vehicle dynamic model in various scenarios to evaluate the performance of the proposed method. The results show that the proposed LLPL framework can continuously improve the policy performance with collected incremental driving data, and achieves the best accuracy and control smoothness compared to other baseline methods after evolving on a 7 km curved road. Through learning and evaluation with noisy real-life data collected in an off-road environment, the proposed LLPL framework also demonstrates its applicability in learning and evolving in real-life scenarios.
This paper introduces a new planar matrix pulsed eddy current sensor for non-destructive testing. The sensor consists of multiple independent excitation poles and an array of induction coils. Each induction coil can be regarded as an independent pixel unit. The simulation model of matrix pulsed eddy current sensor is established by finite element simulation software, and the characteristics of the sensor are analyzed. The excitation pole is driven by the pulse generator, and the voltage pulse signal of a certain induction coil in the array is selected by the multiplexer. Then the FPGA is used to perform fast Fourier transform on the collected pulse signal to obtain the frequency domain signal, and the processed signal is amplified and collected. In the experiment, the detected data corresponds to the pixel point to form the defect image of the detected object.
At present, the electromagnetic compatibility test of direct tire monitoring system is usually carried out by means of pressure tank activation sensor. The disadvantage of this method is that it can only provide a constant pressure value, which is inconvenient to observe the phenomenon, and it is difficult to simulate the real car environment. In this paper, a set of EMC test adjustable auxiliary device for direct tire pressure monitoring system is designed to simulate the tire pressure environment in the process of real vehicle driving. Built in an existing laboratory environment, the device can provide varying air pressure from 0 to 6bar, providing more accurate test conditions for tire pressure tests that are closer to the actual working environment.