Automatic Production Research Articles

Animating Truth: Documentary and Visual Culture in the 21st Century

Animating Truth: Documentary and Visual Culture in the 21st Century

Automatic football video production system with edge processing

Automatic football video production system with edge processing

Research on optimization and simulation of sand casting production line based on VSM

Purpose This paper aims to provide feasible countermeasures for the application of lean manufacturing in automatic sand casting workshops to optimize production line balance. Design/methodology/approach A production line balance optimization model for sand casting workshops is proposed. The value stream mapping (VSM) approach is applied to diagnose the problems in the production process. An optimization scheme is established based on eliminate, combine, rearrange, simplify and increase theory and Kanban management method. Further, simulation is done to compare current VSM and future VSM. Findings After implementing the proposed model, findings indicated that the idle time of equipment was effectively reduced, the line of balance of the production line was increased by 44.7%, the production lead time was shortened by 60.3% and the production capacity was increased by 50.0%. Research limitations/implications Application of the optimization model in this study is limited to sand casting workshops that have realized automatic or semi-automatic production. Originality/value This paper provides an optimization model for the implementation of lean manufacturing in sand casting workshops and provides a reference case that reflects the actual application of lean manufacturing tools in a real situation.

Research on the active pressurized forced lubrication deep drawing process and evaluation of the lubrication effect

Friction and lubrication are important parameters that affect the quality of sheet metal forming; excellent lubrication conditions and less harmful friction can reduce local thinning, delay fracture, and improve surface quality. Aiming at the poor friction conditions and difficult lubrication in the flange area during deep drawing, an active pressurized forced lubrication deep drawing (FLDD) process was proposed in this paper. A hydraulic system was employed to flush high-pressure lubricating oil into the contact gap between the die and sheet in the flange area. The high-pressure hydrostatic oil film in the contact gap can reduce the real contact area and effectively improve the lubrication conditions. The equipment is simple, the cost is low, and the lubricating oil pressure can be measured and controlled. Under the conditions of 20-kN, 35-kN, and 50-kN blank holder force (BHF), FLDD testing of box parts was carried out with 5-MPa and 9-MPa pressure using water-based lubricating oil. The horizontal comparison experiment was conducted with vegetable oil and water-based lubricating oil under the same process conditions. The test results illustrated that the lubrication effect of vegetable oil was the worst, whereas the lubrication effect of water-based mineral lubricant was significantly improved after pressurization. The maximum forming height was increased by 17.97%, the maximum forming force was reduced by 8.9%, the maximum wall thickness thinning rate was decreased by 7%, and the lubrication effect at 9-MPa pressure was superior to that of 5 MPa. The FLDD process has definite application value in improving the production environment, pollution control, and automatic production.

Automatic Production Technology of Data News Based on Machine Learning Model

Data news does not appear out of nowhere. It is the result of the press’s ongoing exploration and innovation as part of the ongoing development of information technology. It is based on early computer-assisted news reporting, statistical news and precise news. In terms of theory and technology, it is a game-changer. The media industry is most sensitive to new technologies and is most willing to apply new technologies in the entire process of news reporting, such as information acquisition, content production and management, and content release, in an era of great changes in the popularity of the Internet and the in-depth application of data processing technology in all walks of life. The data news intelligent production platform investigated and designed in this paper, when combined with current emerging technologies, such as big data, cloud computing, and machine learning algorithms, realizes intelligent and automatic news production, ushering traditional news into an era of intelligence, knowledge, and digitization. Machine learning has made significant progress in the automatic production of data news technology and will continue to do so in the future information society.

Learning-based object detection and localization for a mobile robot manipulator in SME production

Increasing research attention has been attracted to automatic production processes in small and medium-sized enterprises (SMEs) using collaborative robotic systems. In this work, we develop an object detection solution based on deep learning on 3D point clouds for a collaborative mobile robot manipulator to automate SME production. In this solution, a 3D point cloud technology is adopted to measure the shape and depth information of targeted objects in SME production, for instance, name tags production and plug-in charging. Deep learning is then employed to deal with the uncertainty in 3D detection, such as inconsistent light conditions and the irregular distribution and structural ambiguity of point clouds. A 2D camera is employed to calibrate the relative positions of the mobile manipulator to workstations. The mobile robot manipulator is equipped with cameras, an in-house developed adaptive gripper, and a learning-based computer vision system developed in this work. The principle and procedures of the proposed 3D object detection and 2D calibration are presented in detail. The automatic name tags production and plug-in charging experiments are conducted to validate the object detection, localization algorithms, and tools developed and employed in production cases using the mobile robot manipulator.

Dancing pen: The ultimate test of graphically matured skilled writer

Unconscious and automatic rhythmic production of handwriting by graphically matured skilled writers through perfect synchronization of muscular body parts is an activity that resembles a pen dancing on paper, analogous to a dancer performing on stage. This analogy can lead to beginners in the profession better understanding the complex and intricate writing process.
 There are several routine activities requiring various complex coordinations of mental, sensory, and motor factors by humans, such as walking, talking, writing, dressing, drawing, sewing, using a typewriter, playing a piano or violin, riding a bicycle, driving a car, handling a tool, a tennis racket, or a golf club, etc., which are performed habitually, unconsciously, and automatically once they are learnt and practiced. One of these activities is (hand)writing, which is a complex learned motor behavior generally developed in a person in three stages: formative, impressionable, and graphic maturity. The stage of “graphic maturity” is finally reached when the writing has fully developed, resulting in unique individual characteristics that become habitual in execution, most of which remain relatively constant throughout much of the writer’s active life. The complexities and intricacies of the writing process can be better understood by a beginner in the profession by comparing it with dancing, which is also a similar activity requiring perfect synchronization and coordination of all the body parts involved in the exercise.

Functional differentiation and scalable production of renal proximal tubular epithelial cells from human pluripotent stem cells in a dynamic culture system.

ObjectiveTo provide a standardized protocol for large‐scale production of proximal tubular epithelial cells (PTEC) generated from human pluripotent stem cells (hPSC).MethodsThe hPSC were expanded and differentiated into PTEC on matrix‐coated alginate beads in an automated levitating fluidic platform bioLevitator. Differentiation efficacy was evaluated by immunofluorescence staining and flow cytometry, ultrastructure visualized by electron microscopy. Active reabsorption by PTEC was investigated by glucose, albumin, organic anions and cations uptake assays. Finally, the response to cisplatin‐treatment was assessed to check the potential use of PTEC to model drug‐induced nephrotoxicity.ResultshPSC expansion and PTEC differentiation could be performed directly on matrix‐coated alginate beads in suspension bioreactors. Renal precursors arose 4 days post hPSC differentiation and PTEC after 8 days with 80% efficiency, with a 10‐fold expansion from hPSC in 24 days. PTEC on beads, exhibited microvilli and clear apico‐basal localization of markers. Functionality of PTECs was confirmed by uptake of glucose, albumin, organic anions and cations and expression of KIM‐1 after Cisplatin treatment.ConclusionWe demonstrate the efficient expansion of hPSC, controlled differentiation to renal progenitors and further specification to polarized tubular epithelial cells. This is the first report employing biolevitation and matrix‐coated beads in a completely defined medium for the scalable and potentially automatable production of functional human PTEC.

Moving Object Grasping Method of Mechanical Arm Based on Deep Deterministic Policy Gradient and Hindsight Experience Replay

The mechanical arm is an important component in many types of robots; however, in certain production lines, the conventional grasp strategy cannot satisfy the demands of modern production because of several interference factors such as vibration, noise, and light pollution. This paper proposes a new grasping method for manipulators in stamping automatic production lines. Considering the factors that affect grasping in the production environment, the deep deterministic policy gradient (DDPG) method is selected in this study as the basic reinforcement-learning algorithm, and this algorithm is used to grasp moving objects in stamping automatic production lines. Owing to the low success rate of the conventional DDPG algorithm, the hindsight experience replay (HER) is used to improve the sample utilization efficiency of the agent and learn more effective tracking strategies. Simulation results show an 82% mean success rate of the optimized DDPG-HER algorithm, which is 31% better than that of the conventional DDPG algorithm. This method provides ideas for the research and design of the sorting system used in stamping automation production lines.

Industrial object and defect recognition utilizing multilevel feature extraction from industrial scenes with Deep Learning approach

Modern industry requires modern solutions for monitoring the automatic production of goods. Smart monitoring of the functionality of the mechanical parts of technology systems or machines is mandatory for a fully automatic production process. Although Deep Learning has been advancing, allowing for real-time object detection and other tasks, little has been investigated about the effectiveness of specially designed Convolutional Neural Networks for defect detection and industrial object recognition. In the particular study, we employed six publically available industrial-related datasets containing defect materials and industrial tools or engine parts, aiming to develop a specialized model for pattern recognition. Motivated by the recent success of the Virtual Geometry Group (VGG) network, we propose a modified version of it, called Multipath VGG19, which allows for more local and global feature extraction, while the extra features are fused via concatenation. The experiments verified the effectiveness of MVGG19 over the traditional VGG19. Specifically, top classification performance was achieved in five of the six image datasets, while the average classification improvement was 6.95%.

Circuit Design for Predictive Maintenance

Industry 4.0 has become a driver for the entire manufacturing industry. Smart systems have enabled 30% productivity increases and predictive maintenance has been demonstrated to provide a 50% reduction in machine downtime. So far, the solution has been based on data analytics which has resulted in a proliferation of sensing technologies and infrastructure for data acquisition, transmission and processing. At the core of factory operation and automation are circuits that control and power factory equipment, innovative circuit design has the potential to address many system integration challenges. We present a new circuit design approach based on circuit level artificial intelligence solutions, integrated within control and calibration functional blocks during circuit design, improving the predictability and adaptability of each component for predictive maintenance. This approach is envisioned to encourage the development of new EDA tools such as automatic digital shadow generation and product lifecycle models, that will help identification of circuit parameters that adequately define the operating conditions for dynamic prediction and fault detection. Integration of a supplementary artificial intelligence block within the control loop is considered for capturing nonlinearities and gain/bandwidth constraints of the main controller and identifying changes in the operating conditions beyond the response of the controller. System integration topics are discussed regarding integration within OPC Unified Architecture and predictive maintenance interfaces,providing real-time updates to the digital shadow that help maintain an accurate, virtual replica model of the physical system.

Combinatorial Optimization Solver Using Annealing Method and Application to Automatic Production Scheduling in Printing Factory

Combinatorial Optimization Solver Using Annealing Method and Application to Automatic Production Scheduling in Printing Factory

On-the-fly bare die bonding based on laser induced forward transfer (LIFT)

Die bonders are faster than ever at 42,000 units per hour (UPH) these days. However, the die transfer process is often the limiting time constraint due to the inertia of the mechanical actuators. In addition, the mechanical die ejection physically limits the minimum possible die dimensions. To overcome these limitations we developed a laser-induced on-the-fly bare die bonding technology. Experimental results verify, this technology significantly accelerates the die ejection process and enables up to 108,000 UPH. Further, this technology opens up possibilities for efficient and novel concepts for automatable production, e.g. for flexible ultra-thin wafers.

TAL: Topography-Aware Multi-Resolution Fusion Learning for Enhanced Building Footprint Extraction

Automatic building footprint extraction from remote sensing imagery is a challenging task with important applications in geomatics and environmental science. Significant advances have been made in this field as a result of the emergence of deep convolutional neural networks (CNNs) designed for semantic segmentation. Although CNNs have demonstrated state-of-the-art performance in coarse annotation and identification of buildings, the accuracy of extracted building footprints is still insufficient for high-precision applications such as mapping and navigation. We propose the topography-aware multi-resolution fusion learning strategy tailored to the problem of enhanced building footprint extraction. More specifically, we introduce a topography-aware loss (TAL) for enhancing a deep CNN’s ability to learn heterogeneous building features for better boundary preservation during segmentation. We then incorporate the proposed TAL loss within a multi-resolution fusion architecture to boost high-resolution segmentation performance. Finally, we introduce a novel metric named average thresholded contour accuracy (tCA) which specifically measures the accuracy of segmentation boundaries. The experimental results on the SpaceNet buildings dataset show significant improvements in boundary integrity of extracted building footprints when compared with previously proposed methods. Hence, this method enables accurate boundary annotation toward automatic production of building footprint maps for high-precision applications.

A Scalable High-Performance Unsupervised System for Producing Large-Scale HR Land Cover Maps: The Italian Country Case Study

This paper presents an operational system for the automatic production of HR large-scale Land Cover (LC) maps in a fast, efficient and unsupervised manner. This is based on a scalable and parallelizable tile-based approach, which does not require the collection of new training data. The method leverages the complementary information provided by existing LC maps and recent acquisitions of HR Earth Observation (EO) images to: (i) identify map units that have the highest probability of being correctly associated with their labels, and (ii) exploit the obtained “weak” training set to produce an updated HR LC map by classifying the recently acquired EO data. Both steps, performed at tile level, can be implemented on a High Performance Computing (HPC) environment, which simultaneously process all required tiles (independently of each other) for the entire study area. The method was tested considering the publicly available 2018 Corine Land Cover (CLC) Map having a minimum mapping unit of 25Ha and the Sentinel-2 images to generate a HR LC map of Italy. The obtained map has a spatial resolution of 10 m and presents the nine major LC types (i.e., “Artificial Land,” “Bareland,” “Grassland,” “Cropland,” “Broadleaves,” “Conifers,” “Snow,” “Water” and “Shrubland”). Validation was performed using the 2018 European Land Use and Coverage Area Frame Survey (LUCAS) database made up of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-situ</i> data. The Overall Accuracy (OA) achieved for the Northern, Southern and Central part of Italy and Italian Islands are 91.29%, 91.63%, 92.21% and 91.06%, respectively.

Workers benchmarking using multi-directional efficiency analysis in a manufacturing production system

The human factor plays a relevant role in all manual or partially automatic production systems, specially, the ones showing reliable and balanced dynamics. In the literature, parametric or survey-based models are quite common for performance evaluation of production workers. In this work, multi-directional efficiency analysis is used instead, for root cause analysis of product reworks and bottlenecks occurrence, according to four worker-related parameters: experience time, wage, delay time and response time. The approach allows to identify individual inefficiencies per tuple worker/working shift and to cluster them according to similar inefficiency parameters. In addition, this work opens a path to new applications of multi-directional efficiency analysis to problems in the manufacturing industry.

An Experimental Training Production Line to Demonstrate the Basics of Industry 4.0

The paper deals with appropriate possibilities, instrumentation, and technologies for purposes of education, presentation, teaching and research, and development of technologies and procedures of Industry 4.0 ideas, and their implementation in case studies of Factories of the Future. Through the physical module-based production lines of a FESTO Didactic company authors present technologies, standards, and principles of Industry 4.0. They are persuaded, that after some years of simple presentation of ideas and visions, it is necessary to provide a step from theory to the praxis of the Industry 4.0 technologies in the fully standardized matter. Paper presents a state of the art of an enhanced Experimental Education production line, the Cyber-Physical (CP) Factory of the company Festo Didactic. They show existing properties of the technology, stemming from 2016, its disadvantages and provide a proposal on how to enhance CP Factory towards a physical system, implementing and providing properties of fully decentralized control of automatic production systems in a standardized way.

Research on the Process Simulation of robot automatic production line

Industrial robot is a high-tech product of modern society. It plays an important role in the operation of economic development. Especially in the manufacturing industry, industrial robots can replace manual labor to perform a variety of complex tasks, in order to intelligently build industrial automation, and improve the service of automated production lines.

Thermal Fault Diagnosis of Transmission System in Automatic Production Machinery and Equipment and Reliability Analysis

Thermal Fault Diagnosis of Transmission System in Automatic Production Machinery and Equipment and Reliability Analysis

Design and Implementation of Spring Cable Shaping Method Based on Fuzzy Control

In order to improve the production efficiency and elastic quality of spring cable, and meet the market demand of automatic mass production, based on the market research and experimental analysis of common spring cable shaping methods, a rapid shaping method of coil bar current heating spring cable is innovatively proposed. After the spring cable is wound on the coil bar once, the coil bar is directly heated to realize the spring wire temperature rising and setting. The process temperature is input from the man-machine interface, and the temperature control is based on a fuzzy algorithm, which is automatically adjusted by PLC. The experimental results show that, compared with the traditional sizing method, the current heating method proposed in this paper can greatly shorten the product sizing time and has good sizing effect, which can well meet the market requirement of high-quality mass production of spring cable.