A convolutional neural network (CNN)-based direct method to detect stiction in control valves

Control valves are considered important capital assets in any process industry. A properly maintained control valve can have a significant impact on how well the process is controlled as well as the overall cost of the plant. However, control valves can suffer from poor control performance due to valve non-linearities. One of the main reasons for non-linearity is control valve stiction. Stiction not only causes oscillations in the process variables but also shortens the life of the control valve, resulting in an economic loss for the process. In a process plant, a control engineer generally analyzes the time series plot of process value (PV), set point (SP), and controller output (OP) data and identifies stiction based on the typical shape pattern of PV/SP/OP plot. In this study, the same shape pattern methodology is adapted to identify stiction using convolutional neural network (CNN) technique. A one-dimensional convolution neural network (Conv1D) algorithm is developed, which works directly on PV/SP/OP time series data for stiction detection. The proposed CNN algorithm is tested on both simulated and industrial control loop data. The suggested method provides promising results with a combined stiction prediction accuracy of 92% (92.2% in predicting non-sticky and 91.53% in predicting sticky loops) for the industrial loops data studied.     

Structure and properties of PP/SBS/glass fiber hybrid composites. Past II: Property measurement

The mechanical properties viz. impact and tensile modulus of hybrid composites of PP/SBS/glass in the composition range 0‐40 wt% of glass fibers (GF) were studied. Both impact and tensile modulus increased with respect to glass content at a certain composition of the blend. Synergistic effects were seen in the value of elongation and toughness at a certain composition of the glass content. The above findings could be associated with the high aspect ratio and nucleation ability of GF together with good interfacial adhesion between the GF and SBS, rather than the PP matrix. These have been supported by the investigations on structures and morphologies of the hybrid composites.     

Thermo-Oxidative Degradation of Polybutadiene Binders

Thermo-oxidative degradation of hydroxy-terminated polybutadiene (HTPB) and poly(butadiene-acrylonitrile-acrylic acid) terpolymer (PBAN) binders was studied in the presence of varying amounts of ammonium perchlorate (AP). It was found that the effect of AP on the nature and composition of the pyrolyzates was similar to the effect of increase in pyrolysis temperature. Activation energy for thermal degradation was found to be about 52 kJ/mol for both the polymers. The results are discussed in terms of a linear pyrolysis model.     

Missing data estimation and IoT-based flyby monitoring of a water distribution system: Conceptual and experimental validation

Achieving uninterrupted water supply to the consumer node is considered to be the significant aspect for urban water distribution system (WDS). Under circumstances such as sensor failures or large sampling interval, the intermittent vital data are ignored, which lead to the missing data problem. In this work, an enhanced version of Kalman filter (KF) is proposed termed to be customized KF (CKF). The proposed CKF is equipped to handle the state- and input-dependent noises, which are amplified based on the input and states in WDS. These noises corrupt the measured response from the WDS added to the conventional sensor and model uncertainties. In this case, a real-world-existing WDS is considered to test the credibility of the proposed algorithm. This reduces the complexity of the computation and the sampling rate of the measured head level, and the flows are considered to be random. The study indicates that the proposed CKF performs better in estimating the missing data voids with the noise-corrupted measurements. To have the continuous monitoring accessible in remote sections, the vital parameters are monitored through Internet of Things (IoT) in android platform. The estimated data from the MATLAB and the sensor data of the consumer demands are monitored through user-defined android application. This technique provides the advantage of monitoring the WDS in flyby condition and also even in the presence of any sensor failures, which also helps to localize the fault location.     

Study on the effect of atmospheric and low-pressure plasma and its combination on the microbial reduction and quality of milk

This study is aimed to identify the effects of atmospheric and low-pressure plasma on milk individually and in combination, as the plasma generated and applied at different conditions have variations in the effect on food. Plasma bubbling unit (200 V and 0.24 A) was used for atmospheric plasma and Dielectric Barrier Discharge discharge plasma (70 Pa) with milk passing between the electrodes was used for low-pressure plasma. After treatment, the initial coliform load of 7.62 log CFU/ml was decreased by a maximum of 1.26, 1.58, and 2.2 log reduction, when milk was treated using low-pressure plasma (2 kV and 3 ml/min milk flow rate), plasma bubbling (10 min) and combination of both atmospheric bubbling and low-pressure plasma application (10 min bubbling +2 kV and 3 ml/min milk flow rate) respectively. The conductivity (significantly increased) and pH (slight reduction) of milk supported the presence of reactive species. However, alkaline phosphatase activity was not eliminated in plasma-treated milk; the initial activity in terms of mg phenols/ml of milk was 23.20 which was reduced to 22.57 in low-pressure plasma and 22.35 in plasma bubbling, however, it increased while both the treatments were combined. The sodium dodecyl sulfate–polyacrylamide gel electrophoresis analysis uncovered that the plasma processing didn't have any prominent impact on the protein fractions in milk. Though plasma bubbling was effective compared to low-pressure plasma, the combination was proved to have a synergistic effect on milk. However, the enzyme structure needs to be studied in the future for analyzing the exact change in the activity.     

Investigating the effectiveness of immersive VR skill training and its link to physiological arousal

Virtual Reality - This paper details the motivations, design, and analysis of a study using a fine motor skill training task in both VR and physical conditions. The objective of this...     

Magneto-hydrodynamic mixing: A new technique for preparing carbomer hydrogels

Magnetohydrodynamic mixing was evaluated as an alternative to conventional high shear mixing (HSM) in the preparation of carbomer hydrogels containing 1.22 wt% Carbopol® 980 NF. Neutralization of the carbomer dispersion (pH = 2.74) with triethanolamine (TEA) enabled to adjust the pH of the mixture and tune the viscosity of the hydrogel. Using HSM, this approach was limited to 0.2 wt% TEA (pH = 3.83) as the gel became too viscous and the recirculation flow dropped from 12 to 0.3 m³/h. Magnetohydrodynamic mixing enabled to reach TEA concentrations up to 1.0 wt% (pH = 5.31). Apparent viscosity measurements on samples having 0.2 wt% TEA revealed lower viscosities for carbomer hydrogels prepared with HSM, that is, 6800 mPa s versus 8800 mPa for magneto-hydrodynamic mixing. Based on ¹H NMR evidence, this decrease in apparent viscosity was attributed to structural damage to the carbomer backbone in combination with mechanochemical degradation of the added TEA.