•Deep learning is applied to recognize the hot-rolled steep strip surface defects.•A DARCNN, which combines channel attention and residual blocks, is proposed.•The results indicate that the DARCNN ...can achieve state-of-the-art performance.
Generally, the existence of surface defects in hot-rolled steel strip can lead to adverse influences on the appearance and quality of industrial products. Therefore, it is significant to timely recognize the surface defects for hot-rolled steel strip. In order to improve the efficiency and accuracy of surface defects, a deep neural network, namely, deep attention residual convolutional neural network (DARCNN), is proposed to automatically distinguish 6 kinds of hot-rolled steep strip surface defects. In this network, a channel attention mechanism is combined with residual blocks so that the network can focus on the significant feature channels without information loss. The experimental results show that the accuracy, precision and area under curve (AUC) of DARCNN reach 99.5%, 99.51% and 99.98%, respectively, and the application of DARCNN can improve the accuracy, precision and AUC for surface defect recognition tasks by 1.17%, 1.03% and 0.58%, respectively, which verifies the applicability of deep learning technologies to materials.
A field paper-based heavy metal strip was designed and implemented for simultaneous detection of the heavy metals Zn, Cr, Cu, Pb and Mn in wastewater samples. The colorimetric paper strip was ...fabricated by drop-casting of chromogenic reagents onto detection zones. When the fabricated paper strip was exposed to Zn, Cr, Cu, Pb and Mn, multiple colors appeared that were then recorded with a smartphone followed by processing in the Color Picker application. After optimizing the analytical parameters, such as the chromogenic concentration, pH and reaction time, the paper strip achieved detection limits of 0.63, 0.07, 0.17, 0.03 and 0.11 mg/L for Zn, Cr, Cu, Pb and Mn, respectively. Five heavy metals analyses were able to be performed within 1 min on one paper strip. This paper strip is accurate with recoveries from 87 to 107%. The results of the proposed paper strip correlated well with those determined by inductively coupled plasma-optical emission spectrometry of wastewater samples. The use of a single paper strip integrated with a smartphone for the detection of five heavy metals in wastewater represents an all-in-one device with on-site detection, leading to cost-effective and rapid assays that show a great application potential for on-site environmental monitoring.
Graphical abstract
This article proposes a novel transferable manifold projection embedded dictionary learning (TMPDL)-based scheme with domain transfer for multimode process (MP) monitoring, where the new modes in ...evolving scenarios can be rapidly modeled. Considering that only new measurements are necessary for updating the model parameters, the proposed method elevates engineering applicability. First, in order to quantitatively analyze the discrepancy between the new and previous modes, the common features are extracted by TMPDL, upon which new modes can be modeled using domain transfer, saving storage resources and ensuring scalability. Then, the corresponding optimization process is fully discussed, which incorporates feature selection and extraction to select specific features for updating while enhancing the interpretability of the model. Concurrently, consistency and independence constraints are imposed on dictionary learning (DL), which makes the features extracted by the proposed method more discriminative. Finally, the monitoring model is developed by feature reconstruction error (FRE), which can derive monitoring results prior to mode identification. Experiments on the real hot strip mill process (HSMP) reveal that the fault detection ability of TMPDL is highly robust against MP, achieving a 94.8% monitoring accuracy rate for the newly arriving mode.
Shape setup model (SSM) plays a critical role to achieve satisfactory precision of strip shape in hot strip mill process (HSMP). However, for the design of shape model, the lack of systematic shape ...theory restricts the high accuracy of strip shape. In this paper, the procedure of SSM will be generally introduced and practically demonstrated with a real HSMP producing system. The mechanism of shape modeling and design strategy of SSM is introduced. Special concentration is placed on modeling and calculating the thermal extension and wear of the roll, and mathematical model of roll gap profile is set up on this basis. Then the mechanism of strip profile and flatness is introduced by revealing the shape forming process. Furthermore, the setup strategy of SSM is proposed, whose target is to calculate reference values for shape control actuators. The other focus of this paper concerns on the applicable issue of SSM integrated with the presented design approach. An Ansteel 1,700-mm HSMP line will be employed for the experimental background.
Membrane-based lateral flow immunochromatographic strip (LFICS) is widely used in various fields because of its simplicity, rapidity (detection within 10min), and low cost. However, early designs of ...membrane-based LFICS for preliminary screening only provide qualitative (“yes/no” signal) or semi-quantitative results without quantitative information. These designs often suffer from low-signal intensity and poor sensitivity and are only capable of single analyte detection, not simultaneous multiple detections. The performance of existing techniques used for detection using LFICS has been considerably improved by incorporating different kinds of nanoparticles (NPs) as reporters. NPs can serve as alternative labels and improve analytical sensitivity or limit of detection of LFICS because of their unique properties, such as optical absorption, fluorescence spectra, and magnetic properties. The controlled manipulation of NPs allows simultaneous or multiple detections by using membrane-based LFICS. In this review, we discuss how colored (e.g., colloidal gold, carbon, and colloidal selenium NPs), luminescent (e.g., quantum dots, up-converting phosphor NPs, and dye-doped NPs), and magnetic NPs are integrated into membrane-based LFICS for the detection of target analytes. Gold NPs are also featured because of their wide applications. Different types and unique properties of NPs are briefly explained. This review focuses on examples of NP-based LFICS to illustrate novel concepts in various devices with potential applications as screening tools. This review also highlights the superiority of NP-based approaches over existing conventional strategies for clinical analysis, food safety, and environmental monitoring. This paper is concluded by a short section on future research trends regarding NP-based LFICS.
•This review discusses how various novel nanoparticles improve the performance of traditional LFICS.•This review illustrates some novel concepts in various nanoparticles integrated devices as excellent screening methods.•This review also provides a short future trends section on NPs-based LFICS.
Pathogenic bacteria invade plant tissues and proliferate in the extracellular space. Plants have evolved the immune system to recognize and limit the growth of pathogens. Despite substantial progress ...in the study of plant immunity, the mechanism by which plants limit pathogen growth remains unclear. Here, we show that lignin accumulates in Arabidopsis leaves in response to incompatible interactions with bacterial pathogens in a manner dependent on Casparian strip membrane domain protein (CASP)‐like proteins (CASPLs). CASPs are known to be the organizers of the lignin‐based Casparian strip, which functions as a diffusion barrier in roots. The spread of invading avirulent pathogens is prevented by spatial restriction, which is disturbed by defects in lignin deposition. Moreover, the motility of pathogenic bacteria is negatively affected by lignin accumulation. These results suggest that the lignin‐deposited structure functions as a physical barrier similar to the Casparian strip, trapping pathogens and thereby terminating their growth.
Synopsis
Plants employ a multilayered immune system, but the exact mechanisms of how plants restrict pathogen growth remain unclear. In this study, the phenolic polymer and cell wall component lignin is shown to form a mechanical barrier against avirulent pathogens, thereby conferring disease resistance in plants.
Lignification is induced during incompatible plant‐pathogen interactions in Arabidopsis.
Lignin spatially restricts and encompasses bacteria in the extracellular space
Lignin deposition enhances disease resistance.
Casparian strip organizer proteins CASPL1D1 and CASPL4D1 are required for pathogen‐induced lignification.
Lignin deposition is required for innate immune defense during incompatible plant‐pathogen interactions in a manner dependent on Casparian strip organizer proteins.
A disposable lateral flow-through strip was developed for smartphone to fast one-step quantitatively detect alkaline phosphatase (ALP) activity in raw milk. The strip comprises two functional ...components, a conjugation pad loaded with phosphotyrosine-coated gold nanoparticles (AuNPs@Cys-Try-p) and a testing line coated with anti-phosphotryosine antibody (anti-Tyr-p mAb). The dephosphorylation activity of ALP at the testing zone can be quantitatively assayed by monitoring the accumulated AuNPs-induced color changes by smartphone camera, thus providing a highly convenient portable detection method. A trace amount of ALP as low as 0.1UL−1 with a linear dynamic range of 0.1–150UL−1 (R2=0.999) in pasteurized milk and raw milk can be one-step detected by the developed flow-through strip within 10min, demonstrating the potential of smartphone-based portable sensing device for pathogen detection. This bio-hazards free lateral flow-through testing strip can be also used to fabricate rapid, sensitive and inexpensive enzyme or immunosensors for broad portable clinic diagnosis and food contamination analysis, particularly in point-of-care and daily food quality inspection.
•A disposable lateral flow strip quantitatively detects alkaline phosphatase in milk.•No biohazard reagent is utilized in strip, avoiding production of harmful wastes.•Smartphone-based image and analyze strengthen the in-field application potential.
Over the last few years, advanced deep learning-based computer vision algorithms are revolutionizing the manufacturing field. Thus, several industry-related hard problems can be solved by training ...these algorithms, including flaw detection in various materials. Therefore, identifying steel surface defects is considered one of the most important tasks in the steel industry. In this paper, we propose a deep learning-based model to classify six of the most common steel strip surface defects using the NEU-CLS dataset. We investigate the effectiveness of two state-of-the-art CNN architectures (MobileNet-V2 and Xception) combined with the transfer learning approach. The proposed approach uses an ensemble of two pre-trained state-of-the-art Convolutional Neural Networks, which are MobileNet-V2 and Xception. To perform a comparative analysis of the proposed architectures, several evaluation metrics are adopted, including loss, accuracy, precision, recall, F1-score, and execution time. The experimental results show that the proposed deep ensemble learning approach provides higher performance achieving an accuracy of 99.72% compared to MobileNet-V2 (98.61%) and Xception (99.17%) while preserving fast execution time and small models’ size.