A Novel Optimised Inter-Locking Connection For Steel Modular Building Systems To Enable Re-Use

Hot-rolled steel Modular Building Systems (MBS) represent the highest level of Off-Site Con-struction (OSC) in which prefabricated, and often prefinished steel modules are delivered to site on a ‘just-in-time’ basis and assembled into complete building systems. Besides the already well-known advantages such as tight tolerance control, reduced on-site human intervention and speedier construction times, the context of the ongoing climate emergency has brought forward the connection between circular economy (CE) and opportunities of steel MBS for disassembly and reuse. However, the use of hybrid structural systems, the functionality of inter-modular connections, and the effects of complex and demanding load transfer paths often question the actual prospects of deconstruction, repair, relocation, or reuse. So far, inter-module connections have been heavily influenced by conventional design methods, relying on bolts, welds or even prestressing strands, which require laborious on-site tasks and simplifying design assumptions, often raising uncertainty about structural behaviour of modular buildings.In an attempt to mitigate limitations of existing systems, a new inter-module connection was envisaged, inspired from the inter-locking method of joining. At the forefront of the develop-ment process, topology optimisation (TO) was adopted in the conceptual design of the main component of the joint, assisting the morphogenesis process which provided the final configu-ration of the novel system. The structural performance of the newly proposed connection was assessed through a series of static monotonic and quasi-static cyclic FE analyses. Results re-vealed that in terms of load-bearing capacity, ductility and energy dissipation ability, the struc-tural behaviour of the new connection was comparable to that of other inter-module joints in literature, while managing to tackle their limitations by introducing both an easy-to-install and easy-to-disassemble configuration with promising opportunities for reuse, further demonstrat-ing that inter-locking joints could be worthy competitors for traditional means of attachment in the future of modular construction.

Comparative evaluation of performance and scalability of convolutional neural network implementations on a multisystem HPC architecture

The convolutional neural network training algorithm has been implemented for a central processing unit based high performance multisystem architecture machine. The multisystem or the multicomputer is a parallel machine model which is essentially an abstraction of distributed memory parallel machines. In actual practice, this model corresponds to high performance computing clusters. The proposed implementation of the convolutional neural network training algorithm is based on modeling the convolutional neural network as a computational pipeline. The various functions or tasks of the convolutional neural network pipeline have been mapped onto the multiple nodes of a central processing unit based high performance computing cluster for task parallelism. The pipeline implementation provides a first level performance gain through pipeline parallelism. Further performance gains are obtained by distributing the convolutional neural network training onto the different nodes of the compute cluster. The two gains are multiplicative. In this work, the authors have carried out a comparative evaluation of the computational performance and scalability of this pipeline implementation of the convolutional neural network training with a distributed neural network software program which is based on conventional multi-model training and makes use of a centralized server. The dataset considered for this work is the North Eastern University’s hot rolled steel strip surface defects imaging dataset. In both the cases, the convolutional neural networks have been trained to classify the different defects on hot rolled steel strips on the basis of the input image. One hundred images corresponding to each class of defects have been used for the training in order to keep the training times manageable. The hyperparameters of both the convolutional neural networks were kept identical and the programs were run on the same computational cluster to enable fair comparison. Both the convolutional neural network implementations have been observed to train to nearly 80% training accuracy in 200 epochs. In effect, therefore, the comparison is on the time taken to complete the training epochs.

Smoothing Complete Feature Pyramid Networks for Roll Mark Detection of Steel Strips

Steel strip acts as a fundamental material for the steel industry. Surface defects threaten the steel quality and cause substantial economic and reputation losses. Roll marks, always occurring periodically in a large area, are put on the top of the list of the most serious defects by steel mills. Essentially, the online roll mark detection is a tiny target inspection task in high-resolution images captured under harsh environment. In this paper, a novel method—namely, Smoothing Complete Feature Pyramid Networks (SCFPN)—is proposed for the above focused task. In particular, the concept of complete intersection over union (CIoU) is applied in feature pyramid networks to obtain faster fitting speed and higher prediction accuracy by suppressing the vanishing gradient in training process. Furthermore, label smoothing is employed to promote the generalization ability of model. In view of lack of public surface image database of steel strips, a raw defect database of hot-rolled steel strip surface, CSU_STEEL, is opened for the first time. Experiments on two public databases (DeepPCB and NEU) and one fresh texture database (CSU_STEEL) indicate that our SCFPN yields more competitive results than several prestigious networks—including Faster R-CNN, SSD, YOLOv3, YOLOv4, FPN, DIN, DDN, and CFPN.

Design of Multi-Receptive Field Fusion-Based Network for Surface Defect Inspection on Hot-Rolled Steel Strip Using Lightweight Dataset

With the advancement of industrial intelligence, defect recognition has become an indispensable part of facilitating surface quality in the steel manufacturing process. To assure product quality, most previous studies were typically trained with many defect samples. Nonetheless, a large quantity of defect samples is difficult to obtain, owing to the rare occurrence of defects. In general, deep learning-based methods underperformed as they have inherent limitations due to inadequate information, thereby restraining the application of models. In this study, a two-level Gaussian pyramid is applied to decompose raw data into different resolution levels simultaneously filtering the noises to acquire compact and representative features. Subsequently, a multi-receptive field fusion-based network (MRFFN) is developed to learn the hierarchical features and synthesize the respective prediction scores to form the final recognition result. As a result, the proposed method is capable of exhibiting an outstanding performance of 99.75% when trained using a lightweight dataset. In addition, the experiments conducted using the disturbance defect dataset showed the robustness of the proposed MRFFN against common noises and motion blur.