Real-time acquisition of large amounts of machine operating data is now increasingly common due to recent advances in Industry 4.0 technologies. A key benefit to factory operators of this large scale data acquisition is in the ability to perform real-time condition monitoring and early-stage fault detection and diagnosis on industrial machinery—with the potential to reduce machine down-time and thus operating costs. The main contribution of this work is the development of an intelligent fault diagnosis method capable of operating on these real-time data streams to provide early detection of developing problems under variable operating conditions. We propose a novel dual-path recurrent neural network with a wide first kernel and deep convolutional neural network pathway (RNN-WDCNN) capable of operating on raw temporal signals such as vibration data to diagnose rolling element bearing faults in data acquired from electromechanical drive systems. RNN-WDCNN combines elements of recurrent neural networks (RNNs) and convolutional neural networks (CNNs) to capture distant dependencies in time series data and suppress high-frequency noise in the input signals. Experimental results on the benchmark Case Western Reserve University (CWRU) bearing fault dataset show RNN-WDCNN outperforms current state-of-the-art methods in both domain adaptation and noise rejection tasks.

The food industry, academia, food technologists, and consumers have become more interested in using faba bean seeds in the formulation of new products because of their nutritional content, accessibility, low costs, environmental advantages, and beneficial impacts on health. In this review, a systematic and up-to-date report on faba bean seeds’ antinutrients and bioactive and processing techniques is comprehensively presented. The chemical composition, including the oil composition and carbohydrate constituents, is discussed. Factors influencing the reduction of antinutrients and improvement of bioactive compounds, including processing techniques, are discussed. Thermal treatments (cooking, autoclaving, extrusion, microwaving, high-pressure processing, irradiation) and non-thermal treatments (soaking, germination, extraction, fermentation, and enzymatic treatment) are identified as methods to reduce the levels of antinutrients in faba bean seeds. Appropriate processing methods can reduce the antinutritional factors and enrich the bioactive components, which is useful for the seeds’ efficient utilization in developing functional foods. As a result, this evaluation focuses on the technologies that are employed to reduce the amounts of toxins in faba bean seeds. Additionally, a comparison of these methods is performed in terms of their advantages, disadvantages, viability, pharmacological activity, and potential for improvement using emerging technologies. Future research is expected in this area to fill the knowledge gap in exploiting the nutritional and health benefits of faba bean seeds and increase the utilization of faba bean seeds for different applications.

Environmental concerns linked to animal-based protein production have intensified interest in sustainable alternatives, with a focus on underutilized plant proteins. Faba beans, primarily used for animal feed, offer a high-quality protein source with promising bioactive compounds for food applications. This study explores the efficacy of ultrasound-assisted extraction under optimal conditions (123 W power, 1:15 g/mL solute/solvent ratio, 41 min sonication, 623 mL total volume) to isolate faba bean protein (U-FBPI). The ultrasound-assisted method achieved a protein extraction yield of 19.75 % and a protein content of 92.87 %, outperforming the control method's yield of 16.41 % and protein content of 89.88 %. Electrophoretic analysis confirmed no significant changes in the primary structure of U-FBPI compared to the control. However, Fourier-transform infrared spectroscopy revealed modifications in the secondary structure due to ultrasound treatment. The U-FBPI demonstrated superior water and oil holding capacities compared to the control protein isolate, although its foaming capacity was reduced by ultrasound. Thermal analysis indicated minimal impact on the protein's thermal properties under the applied ultrasound conditions. This research highlights the potential of ultrasound-assisted extraction for improving the functional properties of faba bean protein isolates, presenting a viable approach for advancing plant-based food production and contributing to sustainable protein consumption.

Faba beans as an alternative source of protein have received significant attention from consumers and the food industry. Flavor represents a major driving force that hinders the utilization faba beans in various products due to off-flavor. Off-flavors are produced from degradation of amino acids and unsaturated fatty acids during seed development and post-harvest processing stages (storage, dehulling, thermal treatment, and protein extraction). In this review, we discuss the current state of knowledge on the aroma of faba bean ingredients and various aspects, such as cultivar, processing, and product formulation that influence flavour. Germination, fermentation, and pH modulation were identified as promising methods to improve overall flavor and bitter compounds. The probable pathway in controlling off-flavor evolution during processing has also been discussed to provide efficient strategies to limit their impact and to encourage the use of faba bean ingredients in healthy food design.

Shock waves and granular vacua are important phenomena for studying the behavior of granular materials due to the dramatic change in flow properties across shock wave and the particle-free feature at the boundary of granular vacuum. In this paper, we use experiment and numerical simulation to study the granular free-surface flow past a cylindrical obstacle in an inclined chute, where the time-dependent development of the granular flow impacting the obstacle is analyzed at both microscopic and macroscopic scales using the discrete element method (DEM) and the depth-averaged granular model, respectively. Using high-speed camera results as a benchmark solution, the shock solutions are compared between experiment and simulation. The DEM simulation shows better agreement for its shock formation as it is capable of capturing solid, liquid, and gas behaviors for the shock region, while the depth-averaged model provides closer and simpler agreement for the jump solution across the shock. It is shown from the experiment and simulation that the granular shock wave can give rise to a solid–liquid–gas behavior following the propagation of the flow around the obstacle, where, at the front of the obstacle, the shock region can be regarded as a solid regime as the flow becomes stationary during the primary course of the granular flow. With the flow propagating to the downstream, the shock region extends significantly and exhibits strong liquid and gas behavior. Another mixed liquid and gas behavior of granular flow is also observed following the appearance of the granular vacuum, where a localized $\mu (I)$ -rheology is shown to be effective in resolving the vacuum boundary in the numerical simulation.

The food manufacturing sector is one of the most dominant consumers of energy across the globe. Food processing methods such as drying, baking, frying, malting, roasting, etc. rely heavily on the heat released from burning fossil fuels, mainly natural gas or propane. Less than half of this heat contributes to the actual processing of the product and the remaining is released to the surroundings as waste heat, primarily through exhaust gases at 150 to 250 °C. Recovering this waste heat can deliver significant fuel, cost and CO₂ savings. However, selecting an appropriate sink for this waste heat is challenging due to the relatively low source temperature. This study investigates a novel application of gas-to-air low temperature waste heat recovery technology for a confectionary manufacturing process, through a range of experiments. The recovered heat is used to preheat a baking oven’s combustion air at inlet before it enters the fuel-air mixture. The investigated technology is compared with other waste heat recovery schemes involving Regenerative Organic Rankine Cycles (RORC), Vapour Absorption Refrigeration (VAR) and hot water production. The findings indicate that utilising an oven’s exhaust gases to preheat combustion air can deliver up to 33% fuel savings, provided a sufficiently large heat sink in the form of oven combustion air is available. Due to a lower investment cost, the technology also offers a payback period of only 1.57 years, which makes it financially attractive when compared to others. The studied waste heat recovery technologies can deliver a CO₂ savings of 28–356 tonnes per year from a single manufacturing site. The modelling and comparison methodology, observations and outcomes of this study can be extended to a variety of low temperature food manufacturing processes.