Search Results (9)

Longitudinal cutting is the most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules. However, currently, the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low. In this study, we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication. The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques, Pearson correlation coefficient for feature selection, and the Random Forest Regression (RFR) for prediction. Compared with the other three Machine-Learning (ML) algorithms, the Random Forest algorithm has the best performance. The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy so it is suitable for man-hours prediction. Full article

To facilitate the integration of autonomous unmanned air vehicles (UAVs) in day-to-day life, it is imperative that safe navigation can be demonstrated in all relevant scenarios. For UAVs using a navigational protocol driven by artificial neural networks, training and testing data from multiple environmental contexts are needed to ensure that bias is minimised. The reduction in predictive capacity when faced with unfamiliar data is a common weak point in trained networks, which worsens the further the input data deviates from the training data. However, training for multiple environmental variables dramatically increases the man-hours required for data collection and validation. In this work, a potential solution to this data availability issue is presented through the generation and evaluation of photo-realistic image datasets from a simulation of 3D-scanned physical spaces which are theoretically linked in a digital twin (DT) configuration. This simulation is then used to generate environmentally varied iterations of the target object in that physical space by two contextual variables (weather and daylight). This results in an expanded dataset of bicycles that contains weather and time-varied components of the same images which are then evaluated using a generic build of the YoloV3 object detection network; the response is then compared to two real image (night and day) datasets as a baseline. The results reveal that the network response remained consistent across the temporal axis, maintaining a measured domain shift of approximately 23% between the two baselines. Full article

The precise prediction of painting man-hours is significant to ensure the efficient scheduling of shipyard production and maintain a stable production pace, which directly impacts shipbuilding cycles and costs. However, traditional forecasting methods suffer from issues such as low efficiency and poor accuracy. To solve this problem, this paper proposes a selective integrated learning model (ISA-SE) based on an improved simulated annealing algorithm to predict ship painting man-hours. Firstly, the improved particle swarm optimization (MPSO) algorithm and data grouping techniques are employed to achieve the optimal selection and hyperparameter optimization of base learners, constructing a candidate set of base learners. Subsequently, the simulated annealing algorithm is improved by adding random perturbations and using a parallel perturbation search mechanism to enhance the algorithm’s global search capability. Finally, an optimal set of base learners is composed of the candidate set utilizing the ISA-SE model, and a heterogeneous ensemble learning model is constructed with the optimal set of base learners to achieve the precise prediction of ship painting man-hours. The results indicate that the proposed ISA-SE model demonstrates improvements in accuracy, mean absolute error, and root mean square error compared to other models, validating the effectiveness and robustness of ISA-SE in predicting ship painting man-hours. Full article

Globally, natural and man-made disasters continue to force the displacement of masses of people. Existing studies show that several aspects have not been integrated into constructing refugee camps and shelters to achieve sustainability, such as long lifespan, indoor thermal comfort and air quality, energy efficiency, socio-cultural aspects, integration with local planning and design systems, and environmental impact. This study integrates the above factors in six refugee core shelters, designed based on the Middle Eastern cultural context using locally available sustainable construction materials and techniques. The prototypes are situated on two different building plots, i.e., terraced and end-of-terrace, and undergo three development phases, known as the incremental improvement strategy. The study focuses on their energy and indoor environment performance and provides empirical assessments undertaken using dynamic building simulations. It shows that the adopted approach to design and construction leads to remarkable improvements in their overall performance. Concerning energy use, compared to the base case scenarios built with conventional materials, the proposed prototypes show an opportunity to save energy up to 10,000 kWh per unit per year, equivalent to almost 2500 USD savings in energy bills. This is while achieving accepted level for almost 89–94% of thermal comfort hours and 74–85% predicted mean vote (PMV), respectively. However, the CO₂ concentration level remains relatively low, ranging from 29 to 51%. Full article

Thermoforming is a process where the laminated sheet is pre-heated to the desired forming temperature before being pressed and cooled between the molds to give the final formed part. Defects such as wrinkles, matrix-smear or ply-splitting could occur if the process is not optimized. Traditionally, for thermoforming of fiber-reinforced composites, engineers would either have to perform numerous physical trial and error experiments or to run a large number of high-fidelity simulations in order to determine satisfactory combinations of process parameters that would yield a defect-free part. Such methods are expensive in terms of equipment and raw material usage, mold fabrication cost and man-hours. In the last decade, there has been an ongoing trend of applying machine learning methods to engineering problems, but none for woven composite thermoforming. In this paper, two applications of artificial neural networks (ANN) are presented. The first is the use of ANN to analyze full-field contour results from simulation so as to predict the process parameters resulting in the quality of the formed product. Results show that the developed ANN can predict some input parameters reasonably well from just inspecting the images of the thermoformed laminate. The second application is to optimize the process parameters that would result in a quality part through the objectives of minimizing the maximum slip-path length and maximizing the regions of the laminate with a predesignated shear angle range. Our results show that the ANN can provide reasonable optimization of the process parameters to yield improved product quality. Overall, the results from the ANNs are encouraging when compared against experimental data. The image analysis method proposed here for machine learning is novel for composite manufacturing as it can potentially be combined with machine vision in the actual manufacturing operation to provide active feedback to ensure quality products. Full article

To secure technological competitiveness in shipbuilding and offshore industries, the continuous application and development of various technologies is essential. Efficient scheduling in shipyards is an important management task, whereby materials and manpower are allocated at the appropriate time and to the correct workspace. Although some large shipyards ensure effective scheduling and production management through simulations employing advanced technologies, most shipbuilding industries, including small- and medium-sized shipyards, continue to use an index based on past experiences. However, this legacy index, termed the basic unit, involves poor engineering logic; therefore, it does not appropriately reflect a shipyard’s working environment, which changes rapidly in response to technological developments. Although this has led to a demand for improvements in the basic unit, a clear solution has not been presented thus far. In this study, a method for calculating the man-hours required for assembly, which is the basis for preparing the basic unit, is proposed. First, the assembly process is analyzed, and individual activities involved in the assembly process are quantified and formulated into working hours, which is defined as a production metric. Based on a ship’s computerized block model, the geometric properties and production information required for calculating the metric are generated automatically as far as possible; this is to establish a convenient production metric calculation system. The proposed method features complete applicability in new shipyards through a customization. It also serves as a tool for predicting the metric of new ships or comparisons with those of existing ships. Full article

Automated collection of on-vehicle sensor data allows the development of artificial intelligence (AI) techniques for vehicular systems’ diagnostic and prognostic processes to better assess the state-of-health, predict faults and evaluate residual life of ground vehicle systems. One of the vital subsystems, in terms of safety and mission criticality, is the power train, (comprising the engine, transmission, and final drives), which provides the driving torque required for vehicle acceleration. In this paper, a novel health and usage monitoring system (HUMS) architecture is presented, together with dedicated diagnosis/prognosis algorithms that utilize data gathered from a sensor network embedded in an armoured personnel carrier (APC) vehicle. To model the drivetrain, a virtual dynamometer is introduced, which estimates the engine torque output for successive comparison with the measured torque values taken from the engine control unit. This virtual dynamometer is also used in conjunction with other sensed variables to determine the maximum torque output of the engine, which is considered to be the primary indicator of engine health. Regression analysis is performed to capture the effect of certain variables such as engine hours, oil temperature, and coolant temperature on the degradation of maximum engine torque. Degradations in the final drives system were identified using a comparison of the temperature trends between the left-hand and right-hand final drives. This research lays foundations for the development of real-time diagnosis and prognosis functions for an integrated vehicle health management (IVHM) system suitable for safety critical manned and unmanned vehicle applications. Full article

In a shipyard, large numbers of temporary pieces are used to align welding lines of a block joint and prevent welding deformations in the block assembly stage. The use of many temporary pieces requires a great number of working man-hours, causing low productivity. In this study, experiments and numerical analyses of welding deformations were carried out in order to optimize the number of temporary pieces used. The quantitative relationship between the welding deformations and the temporary piece setting was established experimentally. In order to predict welding deformations considering temporary piece setting, a numerical method was proposed. The simulation results were verified through experiments. The optimal number of twenty-one temporary pieces needed to increase the productivity was calculated with the proposed numerical analysis method. Moreover, the proposed numerical analysis method could be used to establish guidelines and plans for a proper use of temporary pieces on the panel block assembly stage. Full article

Estimating the vehicle crashworthiness experimentally is expensive and time-consuming. For these reasons, different modelling approaches are utilised to predict the vehicle behaviour and reduce the need for full-scale crash testing. The earlier numerical methods used for vehicle crashworthiness analysis were based on the use of lumped parameters models (LPM), a combination of masses and nonlinear springs interconnected in various configurations. Nowadays, the explicit nonlinear finite element analysis (FEA) is probably the most widely recognised modelling technique. Although informative, finite element models (FEM) of vehicle crash are expensive both in terms of man-hours put into assembling the model and related computational costs. A simpler analytical tool for preliminary analysis of vehicle crashworthiness could greatly assist the modelling and save time. In this paper, the authors investigate whether a simple piecewise LPM can serve as such a tool. The model is first calibrated at an impact velocity of 56 km/h. After the calibration, the LPM is applied to a range of velocities (40, 48, 64 and 72 km/h) and the crashworthiness parameters such as the acceleration severity index (ASI) and the maximum dynamic crush are calculated. The predictions for crashworthiness parameters from the LPM are then compared with the same predictions from the FEA. Full article