Convolutional Neural Networks for Raw Signal Classification in CNC Turning Process Monitoring

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators-average roughness, peak-to-valley roughness, and diameter deviation-are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model's ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology.

Compressor Issues for Hydrogen Production and Transmission Through a Long Distance Pipeline Network

A hydrogen energy system will require the production of hydrogen from coal-based gasification plants and its transmission through long distance pipelines at 70 � 100 bar. To overcome some problems of current gasifiers, which are limited in pressure capability, two options are explored, in-plant compression of the syngas and compression of the hydrogen at the plant exit. It is shown that whereas in-plant compression using centrifugal machines is practical, this is not a solution when compressing hydrogen at the plant exit. This is because of the low molecular weight of the hydrogen. It is also shown that if centrifugal compressors are to be used in a pipeline system, pressure drops will need to be restricted as even an advanced two-stage centrifugal compressor will be limited to a pressure ratio of 1.2. High strength steels are suitable for the in-plant compressor, but aluminium alloy will be required for a hydrogen pipeline compressor.