Almost all rotating machinery in the industry has bearings as their key building block and most of these machines run 24 × 7. This makes bearing health prediction an active research area for predictive maintenance solutions. Many state of the art Deep Neural Network (DNN) models have been proposed to solve this. However, most of these high performance models are computationally expensive and have high memory requirements. This limits their use to very specific industrial applications with powerful hardwares deployed close the the machinery. In order to bring DNN-based solutions to a potential use in the industry, we need to deploy these models on Microcontroller Units (MCUs) which are cost effective and energy efficient. However, this step is typically neglected in literature as it poses new challenges. The primary concern when inferencing the DNN models on MCUs is the on chip memory of the MCU that has to fit the model, the data and additional code to run the system. Almost all the state of the art models fail this litmus test since they feature too many parameters. In this paper, we show the challenges related to the deployment, review possible solutions and evaluate one of them showing how the deployment can be realized and what steps are needed. The focus is on the steps required for the actual deployment rather than finding the optimal solution. This paper is among the first to show the deployment on MCUs for a predictive maintenance use case. We first analyze the gap between State Of The Art benchmark DNN models for bearing defect classification and the memory constraint of two MCU variants. Additionally, we review options to reduce the model size such as pruning and quantization. Afterwards, we evaluate a solution to deploy the DNN models by pruning them in order to fit them into microcontrollers. Our results show that most models under test can be reduced to fit MCU memory for a maximum loss of $3\%$ in average accuracy of the pruned models in comparison to the original models. Based on the results, we also discuss which methods are promising and which combination of model and feature work best for the given classification problem.

Manual ultrasonic inspection is a widely used Nondestructive Testing (NDT) technique due to its simplicity and compatibility with complex structures. However, in contrast to the data acquired using a robotic positioner, manual measurements suffer from perturbations caused by a variable coupling and a varying scanning density. Imaging techniques like the synthetic aperture focusing technique rely on an unperturbed dense measurement from an equidistant measurement grid. Consequently, imaging based on freehand measurements leads to artifacts. This work aims at reducing such artifacts by preprocessing the manual measurements using Deep Neural Networks (DNN). The training of a DNN requires a large set of labeled measurements which is difficult to obtain in NDT. In this work, we present a technique to train the DNN using only synthetic data. We show that the resulting DNN generalizes well on real measurements. We present an improvement in Generalized Contrast to Noise Ratio by a factor of 20 and 3 compared to omitting the preprocessing for synthetic and measurement data, respectively.

To build robust condition monitoring solutions, it is important to identify signals that capture relevant information. However, how a degradation affects a given part of machinery might not be clear at the beginning. As a result, exploration measurement campaigns collecting large amounts of data are needed for initial evaluation. Vibration signals are typical examples of such data. Although, for explorative measurement campaigns, the battery-powered wireless node brings extra flexibility in terms of positioning the sensor at the desired location and facilitates retrofitting, the limited energy posed by them is the major downside. Sending high-sampled data over wireless channels is costly energy-wise if all samples are to be sent. When multiple sensor nodes transmit real-time measurement data concurrently over a wireless channel, the risk of channel saturation increases significantly. Avoiding this requires identifying an optimal balance between sampling time, transmission duration, and payload size. This can be done by processing and compressing data before transmission, on the sensor node close to the data acquisition and later reconstructing the received samples on the central node. In this paper, we analyze two compression mechanisms to ensure a good compression ratio and still allow good signal reconstruction for later analysis. We study two approaches, one based on the Fast Fourier Transform and one on Singular Value Decomposition, and discuss the pros and cons of each variant.

Predictive Maintenance (PdM) helps to determine the condition of in-service industrial equipment and components and their timely replacement. This can be achieved by Artificial Intelligence (AI) enabled information systems. AI has been used extensively in addressing the condition monitoring problems. Most existing Deep Neural Network (DNN) models which are capable of solving PdM problems have a large memory foot print and are functional on remote machines using cloud based infrastructure only. In order to inference them close to the process, they need to run on memory constrained devices like microcontrollers (MCUs). In this work, we propose a weighted pruning algorithm to reduce the number of trainable parameters in the DNN model for bearing fault classification to enable its execution on the MCU. In addition to the pruning, we reduce the trainable model parameters by making an extensive filter size search. The model size is reduced without compromising on the performance of the pruned models by using the magnitude based method. In case of AlexNet, LeNet and Autoencoder we could reduce the model size upto 89%, 39% and 54% respectively with the new approach in comparison to the magnitude based state of the art approach.

In this paper, we formulate an efficient progressive version of 3-D SAFT by exploiting the block Toeplitz structure of the matrix unfolding of the underlying tensor. This reduces the calculation to a simple striding operation followed by a matrix-vector product of the corresponding submatrix per measured A-scan. Our approach enables to feedback 3-D SAFT images to the engineer during the measurement, e.g., by using augmented reality techniques. The usefulness of the progressive updates is illustrated by presenting snapshots of the iterative SAFT reconstruction of ultrasound measurement data of a steel specimen.

This paper deals with the recognition of different hand gestures through machine learning approaches and principal component analysis. A Bio-Medical signal amplifier is built after doing a software simulation with the help of NI Multisim. At first a couple of surface electrodes are used to obtain the Electro-Myo-Gram (EMG) signals from the hands. These signals from the surface electrodes have to be amplified with the help of the Bio-Medical Signal amplifier. The Bio-Medical Signal amplifier used is basically an Instrumentation amplifier made with the help of IC AD 620.The output from the Instrumentation amplifier is then filtered with the help of a suitable Band-Pass Filter. The output from the Band Pass filter is then fed to an Analog to Digital Converter (ADC) which in this case is the NI USB 6008.The data from the ADC is then fed into a suitable algorithm which helps in recognition of the different hand gestures. The algorithm analysis is done in MATLAB. The results shown in this paper show a close to One-hundred per cent (100%) classification result for three given hand gestures.