Prediction of Hole Expansion Ratio for Advanced High-Strength Steel with Image Feature Analysis of Sheared Edge.

The punching process of AHSS induces edge cracks in successive process, limiting the application of AHSS for vehicle bodies. Controlling and predicting edge quality is substantially difficult due to the large variation in edge quality, die wear induced by high strength, and the complex effect of phase distribution. To overcome this challenge, a quality prediction model that considers the variation of the entire edge should be developed. In this study, the image of the entire edge was analyzed to provide a comprehensive evaluation of its quality. Statistical features were extracted from the edge images to represent the edge quality of DP780, DP980, and MART1500 steels. Combined with punching monitoring signals, a prediction model for hole expansion ratio was developed under punch conditions of varying clearance, punch angle, and punch edge radius. It was found that the features of grayscale variation are affected by the punching conditions and are related to the double burnish and uneven burr, which degrades the edge quality. Prediction of HER was possible based on only edge image and monitoring signals, with the same performance as the prediction based solely on punching parameters and material properties. The prediction performance improved when using all the features.

Artificial Neural Networks for Predicting Plastic Anisotropy of Sheet Metals Based on Indentation Test.

This paper mainly proposes two kinds of artificial neural network (ANN) models for predicting the plastic anisotropy properties of sheet metal using spherical indentation test, which minimizes measurement time, costs, and simplifies the process of obtaining the anisotropy properties than the conventional tensile test. The proposed ANN models for predicting anisotropic properties can replace the traditional complex dimensionless analysis. Moreover, this paper is not limited to the prediction of yield strength anisotropy but also further accurately predicts the Lankford coefficient in different orientations. We newly construct an FE spherical indentation model, which is suitable for sheet metal in consideration of actual compliance. To obtain a large dataset for training the ANN, the constructed FE model is utilized to simulate pure and alloyed engineering metals with one thousand elastoplastic parameter conditions. We suggest the specific variables of the residual indentation mark as input parameters, also with the indentation load-depth curve. The profile of the residual indentation, including the height and length in different orientations, are used to analyze the anisotropic properties of the material. Experimental validations have been conducted with three different sheet alloys, TRIP1180 steel, zinc alloy, and aluminum alloy 6063-T6, comparing the proposed ANN model and the uniaxial tensile test. In addition, machine vision was used to efficiently analyze the residual indentation marks and automatically measure the indentation profiles in different orientations. The proposed ANN model exhibits remarkable performance in the prediction of the flow curves and Lankford coefficient of different orientations.

Integrated Machine Vision System for Evaluating Hole Expansion Ratio of Advanced High-Strength Steels.

In this paper, we propose a new method to estimate the hole expansion ratio (HER) using an integrated analysis system. To precisely measure the HER, three kinds of analysis methods (computer vision, punch load, and acoustic emission) were utilized to detect edge cracks during a hole expansion test. Cracks can be recognized by employing both computer vision and a punch load analysis system to determine the moment of crack initiation. However, the acoustic emission analysis system has difficulty detecting the instant of crack appearance since the magnitude of the audio signal is drowned out by noise from the press, which interrupts the differentiation of crack configuration. To enhance the accuracy for determining the HER, an integrated analysis system that combines computer vision with punch load analysis, and improves on the shortcomings of each analysis system, is newly suggested.

Energy-effective elimination of harmful microcystins by a non-thermal plasma process.

Some cyanobacteria produce toxins that threaten the aquatic ecosystem and human health. To prevent serious consequences, this study suggests a potential means of reducing microalgal toxins, microcystins (MCs) by applying non-thermal plasma (NTP) process. Quantified MC-RR, -LR, and -YR were drastically degraded and removed as much as 99.9% by reactive species generated by NTP. Results further demonstrate that NTP uses less energy based on estimated energy per order (EEO kWh m-3 order-1) than other advanced oxidation processes and requires relatively less time to remove the MCs. As a result, NTP may be a viable management option for effective MC control during severe surface water blooms.

Optimized Pretreatment of Non-Thermal Plasma for Advanced Sewage Oxidation.

This study investigates how the non-thermal plasma (NTP) process leads to advanced oxidation of sewage using response surface methodology. For environmentally viable and efficient operation of the NTP process, temperature and contact time were selected as two important independent variables. Their impacts on the performance were tested following an experimental design to figure out optimal operating conditions. Based on obtained treatment efficiency, statistically optimized conditions were derived by using an approach adapting the central composite design. Results show that coupling 40 °C of temperature and 4 h of contact time demonstrate optimal performance for total chemical oxygen demand (TCOD, 59%) and total suspended solids (85%), respectively. This implies that NTP may present efficient particulate destruction leading to organic solids dissolution. Statistical analysis reveals that the contact time shows more significant dependency than the temperature on the advanced oxidation of TCOD, possibly due to dissolved organic material. For total nitrogen removal, on the contrary, the optimal efficiency was strongly related to the higher temperature (~68 °C). This work provides an inroad to considering how NTP can optimally contribute to better oxidation of multiple pollutants.

Decentralized convolutional neural network for evaluating spinal deformity with spinopelvic parameters.

Low back pain which is caused by the abnormal spinal alignment is one of the most common musculoskeletal symptom and, consequently, is the reason for not only reduction of productivity but also personal suffering. In clinical diagnosis for this disease, estimating adult spinal deformity is required as an indispensable procedure in highlighting abnormal values to output timely warnings and providing precise geometry dimensions for therapeutic therapies. This paper presents an automated method for precisely measuring spinopelvic parameters using a decentralized convolutional neural network as an efficient replacement for current manual process which not only requires experienced surgeons but also shows limitation in ability to process large numbers of images to accommodate the explosion of big data technologies. The proposed method is based on gradually narrowing the regions of interest (ROIs) for feature extraction and leads the model to mainly focus on the necessary geometry characteristics represented as keypoints. According to keypoints obtained, parameters representing the spinal deformity are calculated, which consistency with manual measurement was validated by 40 test cases and, potentially, provided 1.45o mean absolute values of deviation for PTA as the minimum and 3.51o in case of LSA as maximum.

Statistical correlation of ecotoxicity and water quality parameters in slaughterhouse wastewater.

The major causes of toxicity in slaughterhouse wastewater are identified by analyzing the relationship between representative pollutants and the acute toxicity of Daphnia magna. Experimental results demonstrate that organic matters are strongly associated with the acute toxicity. Among many organic pollutants, proteins and carbohydrates were found to be the main toxicity inducers that cause metabolic transformation of D. magna. Statistical correlation between biodegradable soluble organics and the acute toxicity further explains how principal pollutants play potential toxin roles. Also, this study verifies that the variations of biochemical oxygen demand over total chemical oxygen demand (BOD TCOD-1) as well as total organic carbon over total carbon (TOC TC-1) can be indirect indicators explaining the acute toxicity of D. magna because the removal of non-degradable and non-soluble organic matters is connected to the toxicity removal. Overall, these results provide how the acute toxicity of D. magna is attributed to pollutants and what is the potential source of threats to society in slaughterhouse wastewater.

Evaluation of optimal reuse system for hydrofluoric acid wastewater.

The treatment of hydrofluoric acid (HF) wastewater has been an important environmental issue in recent years due to the extensive use of hydrofluoric acid in the chemical and electronics industries, such as semiconductor manufacturers. Coagulation/precipitation and ion exchange technologies have been used to treat HF wastewater, but these conventional methods are ineffective in removing organics, salts, and fluorides, limiting its reuse for water quality and economic feasibility. One promising alternative is reverse osmosis (RO) after lime treatment. Based on pilot-scale experiment using real HF wastewater discharged from semiconductor facility, the spiral wound module equipped with polyamide membranes has shown excellent flux and chemical cleaning cycles. Our results suggest that coagulation/precipitation and spiral wound RO constitute the optimal combination to reuse HF wastewater.

Nitrate reduction by green rusts modified with trace metals.

A kinetic study of nitrate reduction by green rust (GR), a group of layered Fe(II)-Fe(III) hydroxide solids, was performed using a batch reactor system. The reduction rate of nitrate by GRs was affected by the anion content in the interlayer of GRs. GR containing F(-) (GR-F) showed the fastest reduction rate while GR-SO(4) showed 9 times slower reaction rate than GR-F. The addition of 1mM Pt or Cu to GR that contained 85 mM Fe(II) improved the reduction kinetics of nitrate by up to 200 times. Pt was an effective activating agent for all GRs. The sequential step reaction model that we proposed appropriately simulated the experimental data. The fastest nitrate reduction by GR-F with Pt was achieved at pH 9 among 7.5 to 11. At that condition, 1mM nitrate transformed completely into ammonium within 23 min.