Failures in propulsion components, such as propellers, can critically affect flight safety; thus, early failure detection, preferably before flight, is essential. Traditional fault-diagnosis methods typically rely on additional sensors or operational data, which may not be available or practical in all situations. This study addresses these challenges by introducing motor-electric-signal-based fault diagnosis that is independent of airframe configuration and can detect faults, even when the aircraft is not in operation. However, difficulties arise owing to poor class variance in motor-electric-signal data and the challenge of obtaining fault data. To overcome these issues, a semi-supervised learning model based on a modified variational autoencoder-generative adversarial network (VAE-GAN) is proposed, which predicts faults using only normal motor-electric-signal data. Additionally, a new preprocessing method and patch-based ensemble inference technique are introduced to improve the poor class-variance characteristics of the data, thereby enhancing the prediction performance. This work demonstrates that propeller faults can be successfully diagnosed using motor-electric signals without the need for additional sensors or fault-data acquisition. • Motor-electric-signal-based fault diagnosis for propellers without extra sensors. • Modified VAE-GAN model successfully detects faults using only normal signal data. • Event matrix preprocessing and patch ensemble achieve 91.8% accuracy and 98.4% AUROC.

Automating the monitoring of machine tools poses a significant challenge, with previous studies relying on machine vision to address this issue, primarily focusing on measuring specific tool wear using custom algorithms. In this study, we introduce an automated tool wear monitoring process capable of assessing wear across various tools. Utilizing deep neural network models for image classification and segmentation, our proposed process effectively masks areas where tool wear occurs. The image classification model selects the best-performing backbone model based on the highest score. To account for varying depths-of-cut lines among different tools in the masked area, we introduce an algorithm that utilizes the Hough transform to determine the horizontal angle with the cut line. By systematically measuring the maximum flank wear of diverse tools, including indexable, ball, and solid endmills, using this method, we can replace conventional manual processes. This approach can be extended and automated for various machine tools, offering substantial potential for enhancing manufacturing tool monitoring processes.

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, i.e. domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, called self-supervised contrastive regularization (SelfReg). The proposed approach use only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives.

This paper presents a programmable DSP platform for digital still cameras based on the Texas Instruments TMS320C54x family. One major advantage of this platform is that, after capturing an image from a CCD sensor, processing the raw image, and compressing the image for storage is performed on the digital signal processor (DSP). This provides a short shot-to-shot delay and a high degree of flexibility. The system realized also allows instant viewing and selective storing of captured images. This paper outlines the various processing stages necessary to take the raw CCD data and produce a JPEG compressed bit stream and highlighting the advantages of DSPs for this application. The programmable nature of this platform allows for the exploration of different image processing and compression techniques. The low power nature of the digital signal processor provides long battery life.

Transform coding techniques are popular for their excellent lossy compression for natural images but fall short with "simple" images, i.e. images represented by a sparse subset of the available intensity values. In this paper we propose a novel image-domain compression technique aiming at simple images. The proposed method is a context-adaptive bitplane coder where each bitplane is encoded using a binary arithmetic coder. Our novel context modeling scheme allows to exploit the strong correlation across the bitplanes of simple images. Together with the scalable bitplane reduction technique proposed for increased compression efficiency, our bitplane coder produces an SNR-scalable embedded bitstream that is lossless when completely decoded.

Adaptive compression methods have been a key component of many proposed subband (or wavelet) image coding techniques. This paper deals with a particular type of adaptive subband image coding where we focus on the image coder's ability to adjust itself "on the fly" to the spatially varying statistical nature of image contents. This backward adaptation is distinguished from more frequently used forward adaptation in that forward adaptation selects the best operating parameters from a predesigned set and thus uses considerable amount of side information in order for the encoder and the decoder to operate with the same parameters. Specifically, we present backward adaptive quantization using a new context-based classification technique which classifies each subband coefficient based on the surrounding quantized coefficients. We couple this classification with online parametric adaptation of the quantizer applied to each class. A simple uniform threshold quantizer is employed as the baseline quantizer for which adaptation is achieved. Our subband image coder based on the proposed adaptive classification quantization idea exhibits excellent rate-distortion performance, in particular at very low rates. For popular test images, it is comparable or superior to most of the state-of-the-art coders in the literature.

A key part of any efficient source coder involves the optimal allocation of bit rate among a discrete set of competing quantization choices, as employed in the selected coding paradigm. This can be classified under the general label of budget-constrained discrete optimization, with coding applications including optimal bit allocation in scalar or vector quantizer based frameworks, entropy-constrained quantization frameworks, and codebook search for scalar-vector quantization (SVQ). For this class of problems dynamic programming (DP) methods (such as the Viterbi algorithm) provide the optimal solution. However DP is typically very costly computationally. An alternate technique to solving this class of problems uses Lagrange multipliers. This approach is much more efficient than DP but cannot guarantee optimality in general as it limits itself to convex-hull operating points, which may be sparse in many applications. We propose a novel hybrid technique that combines the speed of the Lagrangian approach with the versatility of the DP technique that is aimed at extracting the "best of both worlds". We present an application of our hybrid technique to the codebook search problem for SVQ, demonstrating significantly improved speed over the previously proposed DP-based search methods while mitigating the suboptimality of the Lagrangian based approach.

Subband image coding techniques owe much of their success to an effective use of adaptive quantization and adaptive entropy coding. It is often the case that adaptive quantization is achieved by defining a discrete set of quantizers from which one is chosen for a given set of coefficients. This type of forward adaptation thus requires that overhead information (the choice of quantizer) be sent to the decoder. Then, the quantized coefficients are transmitted using adaptive entropy coding, typically through backward adaptive arithmetic coding. We show that a combination of forward and backward adaptation methods can be used to update the quantizers thus reducing the overhead requirements while still providing good performance. Specifically, we present an algorithm where each coefficient is classified into several classes based on the past quantized data and where the quantizer to be used for each class can itself be adapted on the fly.