Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery.

Reliable quality control of laser welding on power batteries is an important issue due to random interference in the production process. In this paper, a quality inspection framework based on a two-branch network and conventional image processing is proposed to predict welding quality while outputting corresponding parameter information. The two-branch network consists of a segmentation network and a classification network, which alleviates the problem of large training sample size requirements for deep learning by sharing feature representations among two related tasks. Moreover, coordinate attention is introduced into feature learning modules of the network to effectively capture the subtle features of defective welds. Finally, a post-processing method based on the Hough transform is used to extract the information of the segmented weld region. Extensive experiments demonstrate that the proposed model can achieve a significant classification performance on the dataset collected on an actual production line. This study provides a valuable reference for an intelligent quality inspection system in the power battery manufacturing industry.

Improving urban ecosystem holistic sustainability of municipal solid waste-to-energy strategy using extended exergy accounting analysis.

Waste-to-energy technologies play a crucial role in integrated waste management strategies to reduce waste mass and volume, disinfect the waste, and recover energy; different technologies have advantages and disadvantages in treating municipal solid waste under urban conditions. This paper applies the extended exergy accounting method to develop an analytical framework to identify the optimal waste-to-energy strategy from an urban ecosystem holistic sustainability perspective. In the analytical framework, urban ecosystem costs and revenues are formulated as a multi-criteria cost-benefit quantitative model. The urban ecosystem cost is divided into five categories, and the urban ecosystem revenues consist of direct and indirect parts. The direct part is the chemical exergy of the waste-to-energy plants produced product, and the indirect part includes equivalent exergy content of power generation substitution, human health risk elimination, disamenity impact removal and environmental degradation avoidance. Proposing an indicator system to evaluate the waste-to-energy strategy impact on the sustainability of the urban ecosystems and social, economic and environmental sub-ecosystem. Detailed analysis of food waste treatment scenarios of a food center in Singapore was done as a case study to illustrate this analytical framework. Base scenario is current practice that food waste disposal in incineration plant. Anaerobic digestion and gasification are proposed as potential technological solutions for on-site food waste treatment in scenario I and II respectively. In different scenarios, the urban ecosystem costs are estimated to be 71,536.01, 61,854.87 and 74,190.34MJ/year respectively, and the urban ecosystem revenues are estimated to be 135,312.66, 405,442.53 and 298,426.81MJ/year respectively. We show that the scenario where food waste is treated by anaerobic digestion outperforms both the base scenario and scenario II in terms of urban ecosystem costs and revenues, technical energy conversion efficiency, contribution to urban ecosystem holistic sustainability, and natural, social, and economic subsystems improvement, making it the optimal municipal solid waste-to-energy strategy choice.

The preliminary exploration of immune microenvironment in oral leukoplakia concomitant with oral submucosal fibrosis: A comparative immunohistochemical study.

BACKGROUND: Oral leukoplakia concomitant with oral submucous fibrosis is a high-risk oral potentially malignant disorder, but little is known about its immune microenvironment. METHODS: Thirty samples of oral leukoplakia concomitant with oral submucous fibrosis, 30 oral leukoplakia samples, and 30 oral submucous fibrosis samples were collected from two hospitals. Immunohistochemistry was performed to analyze expression of T cell biomarkers [CD3, CD4, CD8, and Forkhead box P3 (Foxp3)], a B cell biomarker (CD20), macrophage biomarkers (CD68 and CD163), an immune inhibitory receptor ligand (PD-L1), and Ki-67. RESULTS: The numbers of CD3+ (p < 0.001), CD4+ (p = 0.018), and CD8+ (p = 0.031) cells in oral leukoplakia concomitant with oral submucous fibrosis were less than those in oral leukoplakia. The number of CD4+ cells (p = 0.035) in oral leukoplakia concomitant with oral leukoplakia was higher than that in oral submucous fibrosis. More CD3+ (p < 0.001), CD4+ (p < 0.001), Foxp3+ (p = 0.019), and CD163+ (p = 0.029) cells were found in oral leukoplakia than in oral submucous fibrosis. CONCLUSION: Various levels of immune infiltration were observed among oral leukoplakia concomitant with oral submucous fibrosis, oral leukoplakia, and oral submucous fibrosis. Characterization of the immune microenvironment may contribute to personalized immunotherapy.

Advancing the bioconversion process of food waste into methane: A systematic review.

With the continuous rise of food waste (FW) throughout the world, a research effort to reveal its potential for bioenergy production is surging. There is a lack of harmonized information and publications available that evaluate the state-of-advance for FW-derived methane production process, particularly from an engineering and sustainability point of view. Anaerobic digestion (AD) has shown remarkable efficiency in the bioconversion of FW to methane. This paper reviews the current research progress, gaps, and prospects in pre-AD, AD, and post-AD processes of FW-derived methane production. Briefly, the review highlights innovative FW collection and optimization routes such as AI that enable efficient FW valorization processes. As weather changes and the FW sources may affect the AD efficiency, it is important to assess the spatio-seasonal variations and microphysical properties of the FW to be valorized. In that case, developing weather-resistant bioreactors and cost-effective mechanisms to modify the raw substrate morphology is necessary. An AI-guided reactor could have high performance when the internal environment of the centralized operation is monitored in real-time and not susceptible to changes in FW variety. Monitoring solvent degradation and fugitive gases during biogas purification is a challenging task, especially for large-scale plants. Furthermore, this review links scientific evidence in the field with full-scale case studies from different countries. It also highlights the potential contribution of ADFW to carbon neutrality efforts. Regarding future research needs, in addition to the smart collection scheme, attention should be paid to the management and utilization of FW impurities, to ensure sustainable AD operations.

Deep learning approach for bubble segmentation from hysteroscopic images.

Gas embolism is a potentially serious complication of hysteroscopic surgery. It is particularly necessary to monitor bubble parameters in hysteroscopic images by computer vision method for helping develop automatic bubble removal devices. In this work, a framework combining a deep edge-aware network and marker-controlled watershed algorithm is presented to extract bubble parameters from hysteroscopy images. The proposed edge-aware network consists of an encoder-decoder architecture for bubble segmentation and a contour branch which is supervised by edge losses. The post-processing method based on marker-controlled watershed algorithm is used to further separate bubble instances and calculate size distribution. Extensive experiments substantiate that the proposed model achieves better performance than some typical segmentation methods. Accuracy, sensitivity, precision, Dice score, and mean intersection over union (mean IoU) obtained for the proposed edge-aware network are observed as 0.859 ± 0.017, 0.868 ± 0.019, 0.955 ± 0.005, 0.862 ± 0.005, and 0.758 ± 0.007, respectively. This work provides a valuable reference for automatic bubble removal devices in hysteroscopic surgery.

Experimental and Numerical Study on Friction and Wear Performance of Hot Extrusion Die Materials.

For the aluminium alloys produced by the hot extrusion process, the profile is shaped according to the bearing at the exit of the extrusion die. The tribological process has significant effects on the die service life, profile dimensional tolerances, and profile surface finish. Recently, new technologies have been introduced to the hot extrusion die, such as cemented carbide insert die and surface coating. However, under hot extrusion working conditions, quantitative studies on their friction and wear performances are lacking. In this work, the friction and wear performances of three typical extrusion die materials, traditional hot tool steel (H13), cemented carbide (YG8), and chemical vapour deposition (CVD) coating, were studied. Macro and nano hardness tests, Pin-on-disk friction and wear tests, optical profiler and SEM observations, and experiments and simulations of hot extrusion were conducted. The results show that the coefficients of friction of CVD coatings and H13 hot work tool steel specimens were smaller under the hot extrusion condition than at room temperature. The wear mechanisms of H13, YG8, and CVD coatings at 500 °C are adhesion, abrasive, and fatigue, respectively. Moreover, the tribology results were validated by the extrusion experiments and the finite element analysis of hot extrusion. The conclusion of this manuscript is useful not only for the numerical simulation of the hot extrusion process but also for the surface finishing of the extrusion profile.

Food waste treating by biochar-assisted high-solid anaerobic digestion coupled with steam gasification: Enhanced bioenergy generation and porous biochar production.

A food waste treating system was proposed in this study by combining biochar-assisted high-solid anaerobic digestion and subsequent steam gasification of the digestate. The effect of solid level, biochar dosage in anaerobic digestion on the properties of biogas, syngas, and final biochar products were investigated. Results showed that at a high total solid level and biochar dosage of 25 g/L and 50 g/L, the accumulative methane yield reached 110.3 mL CH4/g VS and 126.7 mL CH4/g VS, respectively. From steam gasification of different digestates under 850 °C for 15 min, a maximum of 34.92 mmol/g for the hydrogen yield and 11.44 MJ/m3 for the higher heating value could be obtained for the syngas. Furthermore, the by-product produced from steam gasification was a nutrient-enriched porous biochar, which was suitable to be used as compost. This study demonstrated a pathway for food waste treating to produce methane-enriched biogas, hydrogen-enriched syngas, and nutrient-enriched biochar.

Biochar enhanced high-solid mesophilic anaerobic digestion of food waste: Cell viability and methanogenic pathways.

The underlying mechanisms of biochar enhance high-solid anaerobic digestion (HSAD) of food waste were investigated with a focus on the cell viability, microbial community, and methanogenic pathways. This study assessed the effects of different dosages of biochar in HSAD. Optimal biochar dosage was found to be 25 g/L, which produced accumulative methane yields of up to 251 mL CH4/g VS significantly promote volatile fatty acid degradations, especially in butyric acid concentrations. Effects of biochar with a dosage of 25 g/L on the cell viability showed that viable cells based on cell membrane integrity increased from 2.9% to 6.4%. Meanwhile, intact and highly active cells with high DNA content were probably involved in direct interspecies electron transfer (DIET) via membrane-bound electron transport proteins. Further analysis demonstrated that Syntrophomonas and methanogens Methanosarcina &Methanocelleus were selectively enriched by biochar, which resulted in the methanogenic pathways shifting from acetoclastic/hydrogenotrophic methanogenic pathways to more metabolically diverse methanogenic pathways. Accordingly, biochar-mediated DIET was possibly established between Syntrophomonas and Methanosarcina species due to those viable cells. In conclusion, biochar is a feasible additive in enhancing HSAD methanogenic performance.

High Temperature Behaviors of a Casting Nickel-Based Superalloy Used for 815 °C.

The hot deformation behaviors of the SJTU-1 alloy, the high-throughput scanned casting Nickel-based superalloy, was investigated by compression test in the temperature range of 900 to 1200 °C and strain rate range of 0.1-0.001 s-1. The hot processing map has been constructed with the instability zone. At the beginning of hot deformation, the flow stress moves rapidly to the peak value with the increased strain rates. Meanwhile, the peak stress is decreased with the increased temperature at the same strain rates. However, the peak stress shows the same tendency with the strain rates at the same temperature. The optimum hot deformation condition was determined in the temperature range of 1000-1075 °C, and the strain rate range of 0.005-0.1 s-1. The microstructure investigation indicates the strain rate significantly affects the characteristics of the microstructure. The deformation constitutive equation has also been discussed as well.

Biochar industry to circular economy.

Biochar, produced as a by-product of pyrolysis/gasification of waste biomass, shows great potential to reduce the environment impact, address the climate change issue, and establish a circular economy model. Despite the promising outlook, the research on the benefits of biochar remains highly debated. This has been attributed to the heterogeneity of biochar itself, with its inherent physical, chemical and biological properties highly influenced by production variables such as feedstock types and treating conditions. Hence, to enable meaningful comparison of results, establishment of an agreed international standard to govern the production of biochar for specific uses is necessary. In this study, we analyzed four key uses of biochar: 1) in agriculture and horticulture, 2) as construction material, 3) as activated carbon, and 4) in anaerobic digestion. Then the guidelines for the properties of biochar, especially for the concentrations of toxic heavy metals, for its environmental friendly application were proposed in the context of Singapore. The international status of the biochar industry code of practice, feedback from Singapore local industry and government agencies, as well as future perspectives for the biochar industry were explained.

Experimental Investigation on the Effects of Fabric Architectures on Mechanical and Damage Behaviors of Carbon/Epoxy Woven Composites.

The mechanical behaviors and damage evolutions of carbon/epoxy woven fabric composites with three different geometries, i.e., one plain weave and two twill weave patterns with different areal densities, are studied under tensile loading. The effects of weave patterns on mechanical properties are investigated by monotonic and cyclic tension tests. Remarkable variations in stress-strain curve, Poisson's ratio, residual strain and strain map exist in the three composites. Crimp ratio is found to be a critical factor to govern the mechanical properties. With smaller crimp ratio, a quasi-linear stress-strain curve with higher elastic modulus and strength is observed. The stress-strain curves of composites with higher crimp ratio contain transition stages with significant tangent modulus degradation. Elastic modulus, strength and damage initiation are all correlated with the crimp ratio linearly regardless of the fabric pattern. Dramatic nonlinear evolution in Poisson's ratio occurs in the composite with higher crimp ratio. Cyclic tension results indicate that the residual strain is a more appropriate damage indicator than the unloading elastic modulus. Microstructure examination shows that damage developments are essentially related to the fabric geometry, and result in various mechanical behaviors. This study provides important insights into the geometry-deformation mechanism-mechanical property relationship of the woven composites.

Meso-scale Modeling and Damage Analysis of Carbon/Epoxy Woven Fabric Composite under In-plane Tension and Compression Loadings.

The mechanical properties and damage behaviors of carbon/epoxy woven fabric composite under in-plane tension and compression are studied at the meso-scale level through experiment and simulation. An efficient representative volume element (RVE) modeling method with consistent mesh, high yarn volume fraction and realistic geometry is proposed. The material constitutive laws with plasticity, tension-compression asymmetry and damage evolution are established for the three components - yarn, matrix and interface, respectively. Significantly different mechanical properties and damage evolutions are observed depending on loading conditions and initial geometry characteristics. It shows a non-linear stress-strain curve with clear transition region and intensive damage in tension, while a quasi-linear behavior up to facture is observed in compression with little damage prior to final fracture. Moreover, compared to the constant Poisson's ratio with straining in compression, a dramatic increase in Poisson's ratio appears in tension. Simulation shows damage mechanisms including transverse damage, matrix damage and delamination, which all play critical roles in the property evolution. In particular, the rapid damage accumulation after elastic deformation destroys the strong bonds and causes the easy deformation of transverse yarns which results in the transition region and large Poisson's ratio in tension. All the mechanical behaviors and damage evolutions are well captured and explained with the current RVE model.

Reversible Photodriven Droplet Motion on Ti3C2 MXene Film for Diverse Liquids.

The manipulation of liquid droplets on a specific surface with reversible wettability is of great importance for various applications from science to industry. Herein, the concept of a smart, flexible photodriven droplet motion (PDM) device with programmable wettability is designed using the 2D material of MXene film. Because of the MXene photothermal property, the Vaseline layer in the device is in transition between solid and liquid states under the heat transformation due to light illumination, thus attractively producing a reversible wettability for liquid motion with respect to sliding and pinning. Multifarious pathways for liquid motion could be designed through the flexibility of light illumination, which is a revolutionary enhancement in diverse liquid motion to form the desired pathways. In addition, we demonstrated liquid motion under illumination of the back face, which has a profound influence on applications, such as microfluidic systems, microengines, and liquid manipulation.

Study on the Pressure Bearing Capability of Folded Multi-Port Flat Tube.

The pressure bearing capability of a folded multi-port flat tube (MPFT), which has the advantage of retaining the corrosion property of corrosion resistant materials, was investigated in this study with both a burst pressure test and finite element simulation. Results show that the folded tube's failure is mainly caused by the breaking of the inner ribs. Instead of detecting inner pressure, the bulging ratio, which is supposed to be small under service pressure, rises rapidly before failure. Therefore, it is suggested to use bulging ratio to visibly determine the working status of folded MPFTs. Based on FE simulations, the pressure bearing capability of the folded MPFT was improved by optimizing the relevant folding parameters. In addition, the influence of in-plane bending was also investigated. It is found that the folded MPFTs can still retain most of the pressure bearing capability after in-plane bending.

Evolution of the Material Microstructures and Mechanical Properties of AA1100 Aluminum Alloy within a Complex Porthole Die during Extrusion.

Microchannel tube (MCT) is widely employed in industry due to its excellent efficiency in heat transfer. An MCT is commonly produced through extrusion within a porthole die, where severe plastic deformation is inevitably involved. Moreover, the plastic deformation, which dramatically affects the final property of the MCT, varies significantly from location to location. In order to understand the development of the microstructure and its effect on the final property of the MCT, the viscoplastic self-consistent (VPSC) model, together with the finite element analysis and the flow line model, is employed in the current study. The flow line model is used to reproduce the local velocity gradient within the complex porthole die, while VPSC model is employed to predict the evolution of the microstructure accordingly. In addition, electron backscatter diffraction (EBSD) measurement and mechanical tests are used to characterize the evolution of the microstructure and the property of the MCT. The simulation results agree well with the corresponding experimental ones. The influence of the material's flow line on the evolution of the orientation and morphology of the grains, and the property of the produced MCT are discussed in detail.

Sensor Fusion for Myoelectric Control Based on Deep Learning With Recurrent Convolutional Neural Networks.

Electromyogram (EMG) signal decoding is the essential part of myoelectric control. However, traditional machine learning methods lack the capability of learning and expressing the information contained in EMG signals, and the robustness of the myoelectric control system is not sufficient for real life applications. In this article, a novel model based on recurrent convolutional neural networks (RCNNs) is proposed for hand movement classification and tested on the noninvasive EMG dataset. The proposed model uses deep architecture, which has advantages of dealing with complex time-series data, such as EMG signals. Transfer learning is used in the training of multimodal model. The classification performance is compared with support vector machine (SVM) and convolutional neural networks (CNNs) on the same dataset. To improve the adaptability to the effect of arm movements, we fused the EMG signals and acceleration data that are the multimodal input of the model. The parameter transferring of deep neural networks is used to accelerate the training process and avoid over-fitting. The experimental results show that time domain input and 1-dimensional convolution have higher accuracy in the RCNN model. Compared with SVM and CNNs, the proposed model has higher classification accuracy. Sensor fusion can improve the model performance in the condition of arm movements. The RCNN model is a promising decoder of EMG and the sensor fusion can increase the accuracy and robustness of the myoelectric control system.

EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks.

A novel model based on deep learning is proposed to estimate kinematic information for myoelectric control from multi-channel electromyogram (EMG) signals. The neural information of limb movement is embedded in EMG signals that are influenced by all kinds of factors. In order to overcome the negative effects of variability in signals, the proposed model employs the deep architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The EMG signals are transformed to time-frequency frames as the input to the model. The limb movement is estimated by the model that is trained with the gradient descent and backpropagation procedure. We tested the model for simultaneous and proportional estimation of limb movement in eight healthy subjects and compared it with support vector regression (SVR) and CNNs on the same data set. The experimental studies show that the proposed model has higher estimation accuracy and better robustness with respect to time. The combination of CNNs and RNNs can improve the model performance compared with using CNNs alone. The model of deep architecture is promising in EMG decoding and optimization of network structures can increase the accuracy and robustness.

A novel fabrication method of carbon electrodes using 3D printing and chemical modification process.

Three-dimensional (3D) printing is an emerging technique in the field of biomedical engineering and electronics. This paper presents a novel biofabrication method of implantable carbon electrodes with several advantages including fast prototyping, patient-specific and miniaturization without expensive cleanroom. The method combines stereolithography in additive manufacturing and chemical modification processes to fabricate electrically conductive carbon electrodes. The stereolithography allows the structures to be 3D printed with very fine resolution and desired shapes. The resin is then chemically modified to carbon using pyrolysis to enhance electrochemical performance. The electrochemical characteristics of 3D printing carbon electrodes are assessed by cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS). The specific capacitance of 3D printing carbon electrodes is much higher than the same sized platinum (Pt) electrode. In-vivo electromyography (EMG) recording, 3D printing carbon electrodes exhibit much higher signal-to-noise ratio (40.63 ± 7.73) than Pt electrodes (14.26 ± 6.83). The proposed biofabrication method is envisioned to enable 3D printing in many emerging applications in biomedical engineering and electronics.

MEMS-based system and image processing strategy for epiretinal prosthesis.

Retinal prostheses have the potential to restore some level of visual function to the patients suffering from retinal degeneration. In this paper, an epiretinal approach with active stimulation devices is presented. The MEMS-based processing system consists of an external micro-camera, an information processor, an implanted electrical stimulator and a microelectrode array. The image processing strategy combining image clustering and enhancement techniques was proposed and evaluated by psychophysical experiments. The results indicated that the image processing strategy improved the visual performance compared with direct merging pixels to low resolution. The image processing methods assist epiretinal prosthesis for vision restoration.

Application of multi-output support vector regression on EMGs to decode hand continuous movement trajectory.

Applications of neural machine interfaces have received increased attention during the last decades. It is crucial to realize the continuous control of prosthetic devices based on biological signals. In order to deal with the highly nonlinear relationship between the Electromyography (EMG) signals and motion, this study presents a novel decoding approach which employs multi-output support vector regression (M-SVR). The proposed M-SVR is compared with other popular regression techniques and the experimental results demonstrate the effectiveness of M-SVR in hand continuous movement trajectory reconstruction.