NSGA-II-trained neural network approach to the estimation of prediction intervals of scale deposition rate in oil & gas equipment

Scale deposition can damage equipment in the oil & gas production industry. Hence, the reliable and accurate prediction of the scale deposition rate is critical for production availability. In this study, we consider the problem of predicting the scale deposition rate, providing an indication of the associated prediction uncertainty. We tackle the problem using an empirical modeling approach, based on experimental data. Specifically, we implement a multi-objective genetic algorithm (namely, non-dominated sorting genetic algorithm–II (NSGA-II)) to train a neural network (NN) (i.e. to find its parameters, that is its weights and biases) to provide the prediction intervals (PIs) of the scale deposition rate. The PIs are optimized both in terms of accuracy (coverage probability) and dimension (width). We perform k-fold cross-validation to guide the choice of the NN structure (i.e. the number of hidden neurons). We use hypervolume indicator metric to evaluate the Pareto fronts in the validation step. A case study is considered, with regards to a set of experimental observations: the NSGA-II-trained neural network is shown capable of providing PIs with both high coverage and small width.     

Transparent,Flexible, and Conductive 2D Titanium Carbide (MXene) Films with High Volumetric Capacitance

2D transition‐metal carbides and nitrides, known as MXenes, have displayed promising properties in numerous applications, such as energy storage, electromagnetic interference shielding, and catalysis. Titanium carbide MXene (Ti₃C₂T_x ), in particular, has shown significant energy‐storage capability. However, previously, only micrometer‐thick, nontransparent films were studied. Here, highly transparent and conductive Ti₃C₂T_x films and their application as transparent, solid‐state supercapacitors are reported. Transparent films are fabricated via spin‐casting of Ti₃C₂T_x nanosheet colloidal solutions, followed by vacuum annealing at 200 °C. Films with transmittance of 93% (≈4 nm) and 29% (≈88 nm) demonstrate DC conductivity of ≈5736 and ≈9880 S cm^?1, respectively. Such highly transparent, conductive Ti₃C₂T_x films display impressive volumetric capacitance (676 F cm^?3) combined with fast response. Transparent solid‐state, asymmetric supercapacitors (72% transmittance) based on Ti₃C₂T_x and single‐walled carbon nanotube (SWCNT) films are also fabricated. These electrodes exhibit high capacitance (1.6 mF cm^?2) and energy density (0.05 µW h cm^?2), and long lifetime (no capacitance decay over 20 000 cycles), exceeding that of graphene or SWCNT‐based transparent supercapacitor devices. Collectively, the Ti₃C₂T_x films are among the state‐of‐the‐art for future transparent, conductive, capacitive electrodes, and translate into technologically viable devices for next‐generation wearable, portable electronics.     

Interconnected Metallic Membrane Enabled by MXene Inks Toward High-Rate Anode and High-Voltage Cathode for Li-Ion Batteries

The ever-increasing popularity of smart electronics demands advanced Li-ion batteries capable of charging faster and storing more energy, which in turn stimulates the innovation of electrode additives. Developing single-phase conductive networks featuring excellent mechanical strength/integrity coupled with efficient electron transport and durability at high-voltage operation should maximize the rate capability and energy density, however, this has proven to be quite challenging. Herein, it is shown that a 2D titanium carbide (known as MXene) metallic membrane can be used as single-phase interconnected conductive binder for commercial Li-ion battery anode (i.e., Li₄Ti₅O₁₂) and high-voltage cathodes (i.e., Ni_0.8Mn_0.1Co_0.1O₂). Electrodes are fabricated directly by slurry-casting of MXene aqueous inks composited with active materials without any other additives or solvents. The interconnected metallic MXene membrane ensures fast charge transport and provides good durability, demonstrating excellent rate performance in the Li//Li₄Ti₅O₁₂ cell (90 mAh g⁻¹ at 45 C) and high reversible capacity (154 mAh g⁻¹ at 0.2 C/0.5 C) in Li//Ni_0.8Mn_0.1Co_0.1O₂ cell coupled with high-voltage operation (4.3 V vs Li/Li⁺). The LTO//NMC full cell demonstrates promising cycling stability, maintaining capacity retention of 101.4% after 200 cycles at 4.25 V (vs Li/Li⁺) operation. This work provides insights into the rational design of binder-free electrodes toward acceptable cyclability and high-power density Li-ion batteries.     

Intelligent environment recognition and prediction for NDT inspection through autonomous climbing robot

This paper presents a novel approach to environment mapping prediction with focus on autonomous climbing robot to NDT (Non-Destructive Technique) inspection. In industrial installations, the inspection of non-planar surfaces requires that NDT probes passe on whole surface, while the autonomous robot navigates over an unknown environment based only on its perception abilities. However, the path planning of inspection is not a trivial task specially when there is no precise information about environment. In this work, a special kind of climbing robot is used to inspect large metallic surfaces such as spherical pressure vessels used to store Liquified Petroleum Gas (LPG). The robot has adherence skills that allow it to safely navigate through the internal and external surface of the vessel. As a result, robot mobility suffers from hard magnetic adhesion constraints. A new approach is proposed to environment detailed prediction, including specific characteristic (like weld beads and plates) of inspected surface. The goal is the automatic extraction of some environment characteristics to predict the storage tank dimensions and robot localization, based on a group of 3D perception sources (laser rangefinder, light detection and ranging and depth camera) mounted over a rolling platform to improve its reach. The environment prediction is carried out after the robot visually detects two or more weld beads corners. A multi-measuring environment is firstly build by Fuzzy data fusion of the different perception measurements allowing to estimate plates and weld beads based on design and safety standards. Virtual and real experiments are carried out to illustrate proposed method performance.     

Side reactions in the synthesis of triblock copolymers of nylon‐6 with telechelic oligomers

BACKGROUND: The polymerization of hexanelactam (HL) is complicated by numerous side reactions: chain transfer to monomer, termination of the polymer chain, exchange as transamidation and formation of β‐ketoimides and β‐ketoamides. The generation of by‐products and their effect on the anionic polymerization of HL in the bulk in the presence of functionalized tetrahydrofuran oligomers as polymeric activators (PACs) were investigated. RESULTS: In order to consider how side reactions influence the process of HL polymerization, qualitative and quantitative determination of the by‐products obtained and their exhaustion were carried out. An investigation of the polymerization kinetics and the formation of low molecular weight by‐products through the polymerization was performed. The products are further involved in the polymerization process and consumed until an equilibrium level is reached. The mechanism of their generation is discussed. These processes were followed during the first polymerization stage by means of gel permeation chromatography. A mechanism of by‐product formation and consumption is proposed. CONCLUSION: The investigation of the polymerization kinetics and the formation of low molecular weight by‐products through the polymerization has shown that the side reaction yields oligomeric HL‐based products. The products are further involved in the polymerization process and consumed until an equilibrium level is reached. The equilibrium values depend on the HL/PACs ratio. Copyright © 2008 Society of Chemical Industry     

Luteinizing hormone (LH) levels in male workers exposed to urban stressors

The aim of the study is to evaluate if occupational exposure to urban stressors could cause alterations in luteinizing hormone (LH) plasma levels in male traffic policemen vs. administrative staff of Municipal Police.After excluding the subjects with the main confounding factors, male traffic police and administrative staff of Municipal Police were matched by age, working life, body mass index (BMI), alcohol drinking habit, cigarette smoking habit and habitual consumption of Italian coffee.In 166 male traffic police mean LH values were significantly higher compared to 166 male administrative employees. The distribution of LH values in traffic police and in administrative employees was statistically significant.Our results suggest that recent exposure to urban stressors (chemical, physical and psycho-social) can alter the plasma concentration of LH. In agreement with our previous research, levels of plasma LH may be used as early biological markers, valuable for the group, used in occupational set before the appearance of the disease.     

In-line control of the lyophilization process. A gentle PAT approach using software sensors

A lyophilization process is usually only specified in terms of a ‘recipe’ (shelf temperature and chamber pressure vs. time); according to the recent PAT guidelines issued by FDA, there is the need to develop in-line tools to enable better monitoring and control freeze-drying. In this work an advanced Manometric Temperature Measurement approach, called DPE (Dynamic Parameters Estimation) is first presented, based on a detailed mathematical model. In alternative, the “smart vial” concept is proposed, a Kalman filter based observer allowing an almost continuous monitoring without probes physically inserted into the product. Results obtained for pharmaceutical products in vial in a small industrial prototype equipped with the DPE-based LyoDriver control software, are presented. The software is capable to determine the optimal shelf temperature for primary drying, ensuring the fastest drying time without overcoming the maximum allowable product temperature both in scouting and production cycles. Finally, the two complementary monitoring systems, the DPE and the “smart vial”, are combined in an even more robust hybrid control system.