To solve problems underlying design and manufacturing we often rely on methodologies of computational intelligence such as machine learning, artificial neural networks, fuzzy logic, fuzzy inference systems and smart optimization algorithms. In this Special Issue of the International Journal of Automation Technology, original articles are presented with reference to the engagement of intelligent computation in diverse application areas of design and manufacturing, including manufacturing process monitoring, manufacturing systems management, scheduling, design theory and methodology.
The six research papers in this Special Issue propose the use of intelligent computation methodologies to deal with various topics related to manufacturing and design. In particular, the first three papers focus on manufacturing process monitoring with reference to different manufacturing technologies, including tool wear monitoring in drilling of composite materials, sensor monitoring in CNC turning and residual stress prediction in welding. Diverse intelligent approaches such as artificial neural networks and adaptive neuro-fuzzy inference systems are proposed to support manufacturing process monitoring. The fourth paper deals with the manufacturing system level, proposing the employment of a solution algorithm combining metaheuristics and operation simulation for scheduling of production processes. The fifth paper aims at developing tools to guide the manufacturers to manage the technology investment and cost saving target for customer satisfaction based on the application of internet of things. The last paper proposes a methodology to support the introduction of customer requirements in product and service design via a decision support system which exploits artificial intelligence algorithms (machine learning) based on inductive inference, allowing knowledge related to product/service to be mapped, structured and managed to design the service and product semantic model.
The editors deeply appreciate all the authors and anonymous reviewers for their effort and excellent work to make this Special Issue unique. We hope that future research on intelligent computation in manufacturing and design will advance manufacturing technology and systems as well as design methodologies.
An intelligent sensor monitoring procedure was implemented to monitor the drilling of carbon fiber reinforced plastic (CFRP)/CFRP stacks used in the assembly of aircraft fuselage panels; the signals from these sensors were then used to develop an artificial neural network-based cognitive paradigm to predict tool wear, which would allow on-line decision making regarding tool replacement. A multiple sensor system, capable of acquiring signals relative to thrust force, torque, and acoustic emission RMS, was employed during experimental drilling tests, under different rotational speed and feed conditions. Advanced sensor signal processing techniques, including signal conditioning and segmentation, as well as statistical feature extraction and data fusion, were implemented on the acquired signals. Selected statistical features extracted from the multiple sensor signals in the time domain were combined via sensor fusion techniques to construct sensor fusion pattern vectors. These were then fed to artificial neural networks for pattern recognition, with the goal of finding correlations which would allow the prediction of the corresponding tool wear. The tool wear prediction performed by the artificial neural network can be utilized to support decision making at the appropriate time for worn tool replacement, which is extremely useful for drilling automation, as well as for estimating the quality of the drilled holes.
Tool condition monitoring, such as tool wear and breakage, is an essential feature in smart manufacturing system. One of most potential sensors that can be used in tool monitoring is vibration sensor, which usually assembled at tool shank. However, in case of CNC turning with rotating tool turret, it is impossible to assemble the vibration sensor at the tool shank because wire of the sensor will be damaged when the turret rotated. This paper is addressed to compare thoroughly alternative sensor positions. Ten sensor positions including tool shank, as a reference, are investigated. The signals from three types of cutting, namely; normal cutting, abnormal cutting with tool wear and abnormal cutting when tool breakage occurred, are investigated. Based on the magnitude of the output signals and their capability to predict tool wear and breakage, a suggestion on vibration sensor positions is proposed.
This work is an investigation into the applicability of the adaptive neuro-fuzzy inference system (ANFIS), a machine learning technique, to develop a model of the relation of residual stress distribution in a single weld bead-on-plate part to weld heat input and distance from the center of the weld line. Residual stress distributions required to train the ANFIS model were obtained through thermal elastic-plastic finite element analysis. Appropriate conditions for training the ANFIS model were investigated by evaluating the prediction error of the ANFIS model developed under various conditions. Afterward, residual stress distributions obtained by the developed ANFIS model trained under the appropriate conditions were compared with those obtained through thermal elastic-plastic finite element analysis. Discrepancies between the residual stresses obtained through the ANFIS model and thermal elastic-plastic finite element analysis were smaller than ±40 MPa in all regions. The results suggest that the ANFIS modeling had the ability to learn and generalize residual weld stress distributions in single weld bead-on-plate parts.
This paper proposes scheduling algorithms using metaheuristics for production processes in which cranes can interfere with each other. There are many production processes that involve cranes in manufacturing industry, such as in the steel industry, so a general purpose algorithm for this problem can be of practical use. The scheduling problem for this process is very complicated and difficult to solve because the cranes must avoid interfering with each other plus each machine has its own operational constraints. Although several algorithms have been proposed for a specific problem or small-scale problem, general purpose algorithms that can be solved in real time (about 30 minutes or less) in the company’s production planning work have not been developed for large-scale problems. This paper develops some metaheuristic algorithms to obtain suboptimal solutions in a short time, and it confirms their effectiveness through computer experiments.
This study uses two separate surveys to reveal the mean willingness to pay (WTP) for different attributes of Internet of Vehicles (IoV). It uses conjoint analysis for the first survey with 437 respondents to find the most important attribute among seven attributes of IoV. It uses the contingent value method (CVM) for second survey to reveal the mean WTP of the main attributes from the first survey. The estimated method used is the binomial logit model. The result shows significant concern among people in China about security and willingness to pay an additional CNY 1000 for an IoV product with advanced security features, when other attributes are constant. These results can guide manufacturers in managing technology investments and cost saving targets.
This research aims to develop a system that examines and reacts to the changing behaviors and emotions of individuals in order to improve their shopping experience. The system is able to track emotions in real time at different touchpoints in a store and control a set of networked devices to configure the sensing space and all provided services responsive to the customers’ needs. This paper describes the general approach adopted to design the overall system and illustrates in detail the module prototyped to understand the users’ emotions through the analysis of facial expressions.
Recently, terrestrial laser scanners have been significantly improved in terms of accuracy, measurement distance, measurement speed, and resolution. They enable us to capture dense 3D point clouds of large-scale objects and fields, such as factories, engineering plants, large equipment, and transport ships. In addition, the mobile mapping system, which is a vehicle equipped with laser scanners and GPSs, can be used for capturing large-scale point clouds from a wide range of roads, buildings, and roadside objects. Large-scale point clouds are useful in a variety of applications, such as renovation and maintenance of facilities, engineering simulation, asset management, and 3D mapping. To realize these applications, new techniques must be developed for processing large-scale point clouds. So far, point processing has been studied mainly for relatively small objects in the field of computer-aided design and computer graphics. However, in recent years, the application areas of point clouds are not limited to conventional domains, but also include manufacturing, civil engineering, construction, transportation, forestry, and so on. This is because the state-of-the-art laser scanner can be used to represent large objects or fields as dense point clouds. We believe that discussing new techniques and applications related to large-scale point clouds beyond the boundaries of traditional academic fields is very important.
This special issue addresses the latest research advances in large-scale point cloud processing. This covers a wide area of point processing, including shape reconstruction, geometry processing, object recognition, registration, visualization, and applications. The papers will help readers explore and share their knowledge and experience in technologies and development techniques.
All papers were refereed through careful peer reviews. We would like to express our sincere appreciation to the authors for their submissions and to the reviewers for their invaluable efforts for ensuring the success of this special issue.
Efficient registration of point clouds from terrestrial laser scanners enables us to move from scanning to point cloud applications immediately. In this paper, a new efficient rough registration method of laser-scanned point clouds of bridges is proposed. Our method relies on straight-line edges as linear features, which often appear in many bridges. Efficient edge-line extraction and line-based registration methods are described in this paper. In our method, first, sampled regular point clouds based on the azimuth and elevation angles are created, and planar regions are extracted using the region growing on the regular point clouds. Then, straight lines of the edges of the planar regions are extracted as linear features. Next, vertical and horizontal line clusters are created according to the direction of the lines. To align the position and orientation of two point clouds, two corresponding nonparallel line pairs from line clusters are used. In the registration process, the RANSAC approach with a hash table of line pairs is used. In this process, the hash table is used for finding candidates of corresponding line pairs efficiently. Sampled points on the line pairs are used to align the line pairs, and occupied voxels and downsampled point clouds are used for efficient consensus calculation. The method is tested using three data sets of different types of bridges: a small steel bridge, a middle-size concrete bridge, and a high-pier concrete bridge. In our experiments, successful rates of our rough registration were 100%, and the processing time of rough registration for 19 point clouds was about 1 min.
A thick steel plate with a unique curvature was employed to make the outer shell of a ship. This curved shell plate is shaped one at a time by craftsmen carrying out plastic deformation using gas heating. The process includes evaluation of forming accuracy and selection of thermal forming instructions. Both are done using fitting molds called “wooden templates” in a manner that is qualitative but dependent on individual skills. Thus, there is a problem of variation in quality. To solve the problem, research and development have been promoted on a manufacturing process assisted by a laser scanner that is a highly accurate three-dimensional measuring device. An evaluation method for forming accuracy has been established and has reached a satisfactory level for operation on site. However, the method of automatic selection of thermal forming instructions is still immature. Focusing on the curvature of frame lines on the outer plate that acts as an index when instructions for thermal forming are decided upon, a curvature gap estimation system was developed for outer plate frame lines using a laser scanner. Here, a frame line refers to the standard to be compared with a design shape to evaluate the forming accuracy of the members. The system extracts from measured data a point cloud that makes up each frame line, calculates curvature at a given point on the frame line, and visualizes it with a graph and a color map. This system uses an evaluation method whose curvature calculation has sufficiently appropriate accuracy and that is feasible and useful on site. First, the sufficiently appropriate accuracy of the curvature calculation was confirmed using a measurement form of a cylindrical model that simulated a gap between the distance direction generated by measurement with the laser scanner and the direction of laser irradiation. Next, the feasibility and usefulness on site were confirmed by applying the measurement method to the processing data of the ship shell outer plate shape that was obtained through the curving process in the shipyard, and then by comparing the record of regions thermally formed by the worker with index calculation results made by the system.
Recently, we proposed stochastic point-based rendering, which enables precise and interactive-speed transparent rendering of large-scale laser-scanned point clouds. This transparent visualization method does not suffer from rendering artifact and realizes correct depth feel in the created 3D image.
In this paper, we apply the method to several kinds of large-scale laser-scanned point clouds of cultural heritage objects and prove its wide applicability.
In addition, we prove better image quality is realized by properly eliminating points to realize better distributional uniformity of points. Here, the distributional uniformity means uniformity of inter-point distances between nearest-neighbor points.
We also demonstrate that highlighting feature regions, especially edges, in the transparent visualization helps us understand 3D internal structures of complex laser-scanned objects. The feature regions are highlighted by properly increasing local opacity of the regions.
This paper proposes a novel method for polygonizing scanned point cloud data of tunnels to feature-preserved polygons to be used for maintenance purposes. The proposed method uses 2D cross-sections of structures and polygonizes them by a lofting operation. In order to extract valid cross-sections from the input point cloud, center lines and orthogonal planes are used. Center lines of the point cloud are extracted using local symmetry analysis. In addition, this research segments a point cloud of a tunnel into lining concrete, road, and other facilities. The results of applying the proposed method to the point clouds of three types of tunnels are demonstrated, and the advantages and limitations of the proposed method are discussed.
Mobile mapping systems (MMS) can capture point cloud and continuous panoramic images of roads and their surrounding environment. These data are widely used for the maintenance of road-side objects and the creation or update of road ledgers. For these purposes, there is a need to detect and classify each object from captured data, and localize them on 3D maps. Many studies have been reported on the detection and classification of pole-like objects using point clouds captured by a mounted laser scanner. Although MMS images contain valuable information related to color and shape about objects, they have not been well utilized to date for this purpose. It is reasonable to extract shape and color features from images and use them for classification. In this paper, we focus on MMS images rather than point clouds, and evaluate the classification performance for pole-like objects, such as power poles, street lamps, street-side tree, signal lights, and road signs. For classification, Convolutional Neural Network (CNN) is used, because it is known to provide better classification results than conventional methods where hand crafted features and machine learning techniques are commonly used. We also use image super resolution (ISR) techniques based on deep learning for MMS low-resolution images. In contrast to conventional methods in which entire points of pole-like objects are evaluated, our approach selects functional parts attached to the top of the pole (e.g., three-color traffic lights) for classification, because these parts represent unique characteristics of each class of object. We demonstrate the classification performance of our proposed approach through various experiments using MMS images. We also compare the difference in classification results depending on the imaging angles.
Our goal is to automatically classify objects from Mobile Mapping System data to enable the automatic construction of dynamic maps. We aimed at the extraction of curbstones and classification of curb types. Although there is much research about curbstones being recognized from laser-scanned point clouds, there are few methods to classify curb types. In this paper, we propose a method to extract curbstones from low-density-type laser scan data. We also propose a method to distinguish whether curbstones allow access to off-road facilities. Evaluation tests give an F-measure of ≥94.4% and an accessibility classification accuracy of ≥99.6%. Moreover, the results of applying multiple filters to noise removal are compared.
When we drive a car, the white lines on the road show us where the lanes are. The lane marks act as a reference for where to steer the vehicle. Naturally, in the field of advanced driver-assistance systems and autonomous driving, lane-line detection has become a critical issue. In this research, we propose a fast and precise method that can create a three-dimensional point cloud model of lane marks. Our datasets are obtained by a vehicle-mounted mobile mapping system (MMS). The input datasets include point cloud data and color images generated by laser scanner and CCD camera. A line-based point cloud region growing method and image-based scan-line method are used to extract lane marks from the input. Given a set of mobile mapping data outputs, our approach takes advantage of all important clues from both the color image and point cloud data. The line-based point cloud region growing is used to identify boundary points, which guarantees a precise road surface region segmentation and boundary points extraction. The boundary points are converted into 2D geometry. The image-based scan line algorithm is designed specifically for environments where it is difficult to clearly identify lane marks. Therefore, we use the boundary points acquired previously to find the road surface region from the color image. The experiments show that the proposed approach is capable of precisely modeling lane marks using information from both images and point cloud data.
Plant shape measurements have conventionally been conducted in plant science by classifying their shape features, by measuring their widths and lengths with a Vernier caliper, or by similar methods. Those measurements rely heavily on human senses and manual labor, making it difficult to acquire massive data. Additionally, they are prone to large measurement differences. To cope with those problems of conventional measuring methods, we are developing a three-dimensional (3D) shape-measuring system using images and a reliable assessment technique. 3D objects enable us to assess and measure shape features with high accuracy and to automatically measure volume, which conventional methods cannot. Thus, our new system is capable of automatically and efficiently measuring objects. Our goal is to obtain wide acceptance of our method at actual research sites. Unlike industrial products, it is difficult to properly assess the measurements of plants because of their object fluctuations and shape complexities. This paper describes our automatic 3D shape-measuring system, the method for assessing measurement accuracy, and the assessment results. The measurement accuracy of the developed system for strawberry fruits is 0.6 mm or less for 90% or more of the fruit and 0.3 mm or less for 80%. This evidence supports the system’s capability of shape assessment. The developed system can fully automate photographing, measuring, and modeling objects and can semi-automatically analyze them, reducing the time required for the entire process from the conventional time of 6–7 h to 1.5 h. The developed system is designed for users with no technical knowledge so that they can easily use it to acquire 3D measurement data on plants. Thus, we intend to expand measurable objects from strawberry fruits to other plants and their parts, including leaves, stalks, and flowers
A new type of surgical instrument developed as substitutes for an abdominal retractor for use during surgery is described. The new instrument can increase the efficiency of retraction during surgery. We develop an assistant mechanism which has a six-D.o.F, as high controllability at the tip of the mechanism. The mechanism consists of a serial three-link manipulator whose each joint is composed of a ball joint. The instrument needs to maintain the shape of the relevant body part while maintaining own posture during surgery.
This paper presents the development and implementation of a pneumatic muscle actuator based on an idea proposed by a research group at the University of Warsaw. The muscle comprises a silicone rubber tube with plugs at the ends. The tube wall contains high-rigidity wires arranged parallel to the tube axis. Circular rings are present on the exterior of the tube. When air is introduced into the tube, the actuator becomes bulky and contracts. In order to establish a prediction model of muscle behavior, a finite element model was developed, and in this model, the Mooney-Rivlin formulation was implemented with two coefficients for rubber simulation and truss elements for the wires. Several prototypes were developed, and a test bench for the experimental characterization of muscle performance was set up. The results of comparison between prototype behavior and model prediction are presented. The finite element model can be used to design the actuator with different dimensions; hence, it was used to conduct a simulated test campaign to develop a quick actuator sizing procedure. Using dimensional analysis, few project parameters were identified on which the performance of the actuator depends. Through a complete simulation campaign using the finite element model, an abacus was constructed. It allows sizing the actuator as required based on the desired performances according to an established procedure.
Although the applicability of additive manufacturing (AM) to the production of complex shapes has attracted attention from the automobile and aerospace industries, companies hesitate to introduce AM processes because of their low reliability, which is due to pores inside the produced parts. Consequently, many researchers have experimentally evaluated the relation between the pore evolution and production conditions in AM processes. On the other hand, several studies have focused on finishing processes in order to enhance the quality of AM production, considering that production quality cannot be improved enough only by modifying the production conditions in AM processes. To reduce pores in a metal product, hot isostatic pressing (HIP), which applies high pressure and heat energy to metal AM products and enhances production density, has proven to be an efficient approach. However, special equipment is required to produce a high-temperature and high-pressure environment, leading to high cost and low productivity. From the view point of practicability, a simple finishing process would be a fundamental solution to make metal AM processes highly reliable. This paper therefore proposes a method of reducing pores through a remelting process in the direct energy deposition of Inconel 625. Furthermore, a method of doing a graphical analysis to evaluate the bias of pore distribution in the deposited object is proposed. The pore reduction effect in remelting is experimentally evaluated by irradiating the low density area with a laser beam, and a graphical evaluation clarifies that the concentration of residual pores occurs in the top layer of a deposited object. As a result, residual pores are eliminated with certainty through the remelting process. The density of the deposit can be enhanced easily and without any complicated finishing systems with just the laser system originally introduced in a DED machine.