In modern manufacturing scenarios, detecting anomalies in production systems is pivotal to keep high-quality standards and reduce costs. Even in the Industry 4.0 context, real-world monitoring systems are often simple...
详细信息
ISBN:
(纸本)9781728129273
In modern manufacturing scenarios, detecting anomalies in production systems is pivotal to keep high-quality standards and reduce costs. Even in the Industry 4.0 context, real-world monitoring systems are often simple and based on the use of multiple univariate control charts. Data-driven technologies offer a whole range of tools to perform multivariate data analysis that allow to implement more effective monitoring procedures. However, when dealing with complex data, common data-driven methods cannot be directly used, and a feature extraction phase must be employed. Feature extraction is a particularly critical operation, especially in anomaly detection tasks, and it is generally associated with information loss and low scalability. In this paper we consider the task of Anomaly Detection with two-dimensional, image-like input data, by adopting a Deep Learning-based monitoring procedure, that makes use of convolutional autoencoders. The procedure is tested on real Optical Emission Spectroscopy data, typical of semiconductor manufacturing. The results show that the proposed approach outperforms classical feature extraction procedures.
Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all ...
详细信息
ISBN:
(纸本)9781509059102
Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however limited for requirement of large training sample size and high computational costs. In this paper we show that using small sample size, denoising autoencoders constructed using convolutional layers can be used for efficient denoising of medical images. Heterogeneous images can be combined to boost sample size for increased denoising performance. Simplest of networks can reconstruct images with corruption levels so high that noise and signal are not differentiable to human eye.
autoencoders are unsupervised neural networks that are used to process and compress input data and then reconstruct the data back to the original data size. This allows autoencoders to be used for different processing...
详细信息
ISBN:
(数字)9783031477218
ISBN:
(纸本)9783031477201;9783031477218
autoencoders are unsupervised neural networks that are used to process and compress input data and then reconstruct the data back to the original data size. This allows autoencoders to be used for different processing applications such as data compression, image classification, image noise reduction, and image coloring. Hardware-wise, re-configurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations from several domains because of their unique combination of flexibility, performance, and power efficiency. In this paper, we look at the different autoencoders available and use the convolutional autoencoder in both FPGA and GPU-based implementations to process noisy static MNIST images. We compare the different results achieved with the FPGA and GPU-based implementations and then discuss the pros and cons of each implementation. The evaluation of the proposed design achieved 80% accuracy and our experimental results show that the proposed accelerator achieves a throughput of 21.12 Giga-Operations Per Second (GOP/s) with a 5.93 W on-chip power consumption at 100 MHz. The comparison results with off-the-shelf devices and recent state-of-the-art implementations illustrate that the proposed accelerator has obvious advantages in terms of energy efficiency and design flexibility. We also discuss future work that can be done with the use of our proposed accelerator.
Rolling bearing is one of the core components of mechanical equipment, and the degradation state of its performance can directly affect the stability of the entire mechanical equipment, so the evaluation of the degrad...
详细信息
Rolling bearing is one of the core components of mechanical equipment, and the degradation state of its performance can directly affect the stability of the entire mechanical equipment, so the evaluation of the degradation state of rolling bearing is of great significance. This paper proposes a performance degradation evaluation model for rolling bearings based on the combination of convolutional autoencoder (CAE) and support vector data description (SVDD). CAE is used to process the extracted temporal features to realize dimensionality reduction of data features and re-extraction of depth features. The depth features are fed into the optimized SVDD evaluation model as training samples to achieve performance degradation evaluation. Finally, the multi-method verification is carried out using the full life data samples of bearings, and a residual life prediction method using a hybrid prediction model combining LSTM neural network and AR model is proposed. The experimental results show that the method can obtain more accurate evaluation of degradation state and prediction of remaining life.
Micro-structured films with surface riblets are used to reduce aerodynamic drag. This is especially relevant on fast and large objects such as on aircraft wings, where they are installed to increase efficiency (e.g., ...
详细信息
ISBN:
(数字)9781510649101
ISBN:
(纸本)9781510649101;9781510649095
Micro-structured films with surface riblets are used to reduce aerodynamic drag. This is especially relevant on fast and large objects such as on aircraft wings, where they are installed to increase efficiency (e.g., reduce fuel consumption). Their fuel reduction efficiency depends directly on the structural integrity of the films. Therefore, we propose a photometric inspection tool, a hardware setup and tailored analysis algorithms, which detect typical defects of riblet micro-structures occurring during their operational lifetime. We propose two inspection approaches to analyze the micro-structures, (i) a statistical data processing method and (ii) a machine learning algorithm based on convolutional autoencoders. We tested both inspection approaches on rendered and real-world data of riblet films on airplane elements, carbon-fiber parts of race cars, and wind turbine blades.
Mobile app traffic now accounts for a majority owing to the booming mobile devices and mobile apps. State-of-the-art identification methods, such as DPI and flow-based classifiers, have difficulties in designing featu...
详细信息
ISBN:
(纸本)9781728155845
Mobile app traffic now accounts for a majority owing to the booming mobile devices and mobile apps. State-of-the-art identification methods, such as DPI and flow-based classifiers, have difficulties in designing features and labeling samples manually. Motivated by the excellence of CNNs in visual object recognition, we propose convolutional autoencoder network (CAEN), a deep learning approach to mobile app traffic identification. Our contributions are two-fold. First, we propose a novel method of converting traffic flows into vision-meaningful images, and thus enable the machine to identify the traffic in a human way. Based on the method, we create an open dataset named IMTD. Second, convolutional autoencoder (CAE) algorithm is introduced into the proposed network model, realizing the automatic feature extraction and the learning from massive unlabeled samples. The experimental results show that the identification accuracy of our approach can reach 99.5%, which satisfies the practical requirement.
In this paper we introduce a low-latency monaural source separation framework using a convolutional Neural Network (CNN). We use a CNN to estimate time-frequency soft masks which are applied for source separation. We ...
详细信息
ISBN:
(纸本)9783319535463;9783319535470
In this paper we introduce a low-latency monaural source separation framework using a convolutional Neural Network (CNN). We use a CNN to estimate time-frequency soft masks which are applied for source separation. We evaluate the performance of the neural network on a database comprising of musical mixtures of three instruments: voice, drums, bass as well as other instruments which vary from song to song. The proposed architecture is compared to a Multilayer Perceptron (MLP), achieving on-par results and a significant improvement in processing time. The algorithm was submitted to source separation evaluation campaigns to test efficiency, and achieved competitive results.
Hydrogenerators operate in challenging environments, and temperature variations can significantly impact their performance. Temperature monitoring systems often rely on remote infrared and contact real-time temperatur...
详细信息
ISBN:
(纸本)9798350329940;9798350307368
Hydrogenerators operate in challenging environments, and temperature variations can significantly impact their performance. Temperature monitoring systems often rely on remote infrared and contact real-time temperature measurement of the generator. AI-based temperature monitoring systems offer a state-of-the-art solution, providing continuous, automated, and predictive maintenance capabilities. The paper presents a complex AI-based fuzzy decision-making algorithm for anomaly (overheated rotor pole) detection and failure prediction. Time-based analysis of operational parameters from SCADA systems is essential for failure prediction. The use of recurrent neural networks for time-series analysis and convolutional autoencoders for anomaly detection is especially emphasized. The paper also presents a fuzzy decision-making method that uses fuzzy logic to make decisions after analyzing the output of the AI models.
Path planning is an important function for executing autonomous moving robots, and many path planning methods that satisfy various constraints, such as avoiding obstacles and energy efficiency, have been proposed. How...
详细信息
ISBN:
(纸本)9789811303418;9789811303401
Path planning is an important function for executing autonomous moving robots, and many path planning methods that satisfy various constraints, such as avoiding obstacles and energy efficiency, have been proposed. However, these conventional methods have several difficulties for apply to the actual applications, such as the instability, low reproducibility, huge training data set required. Therefore, we propose a novel robot path planning method that combines the rapidly exploring random tree (RRT) and long short-term memory (LSTM) network. In this method, numerous and good paths are generated in the robot configuration space by the RRT method, a convolutional autoencoder and LSTM combination network is trained by them. The proposed method overcomes the difficulty of general methods with neural networks, i.e., "the acquisition of a large amount of training data." Moreover, the difficulty of general random based methods, i.e., "the reproducible path generation" is resolved with high-speed.
As renewable energy usage increases, power systems become more intricate and demand fluctuations intensify. Accurate short-term load forecasting (STLF) is vital for balancing energy supply and demand. Traditional mode...
详细信息
ISBN:
(纸本)9789819756650;9789819756667
As renewable energy usage increases, power systems become more intricate and demand fluctuations intensify. Accurate short-term load forecasting (STLF) is vital for balancing energy supply and demand. Traditional models often struggle with long input sequences, risking critical feature loss due to inadequate capture of long-period characteristics. To address these challenges, we introduce the R-VAE-Informer, a novel forecasting approach that combines Deep Residual Networks (DRN) and convolutional autoencoders (CAE). This model leverages the ProbSparse self-attention mechanism and attention distillation techniques to manage the quadratic complexity of long load sequences more efficiently. It also incorporates a Residual convolutional autoencoder (R-CAE) to produce two-dimensional representations of load data, thereby enhancing feature representation and mitigating potential feature loss. Furthermore, the TempoLocode submodule integrates time and positional data, effectively capturing long-term dependencies and periodic variations in time series. Tests on two public datasets demonstrate that our model achieves a Mean Absolute Percentage Error (MAPE) as low as 0.97%, confirming its strong generalization capabilities. Overall, this model markedly improves the precision and sophistication of STLF.
暂无评论