Advances in Manufacturing

Guest editorial

Ke-Sheng Wang Da-Wei Tu

2014, 2(1): 1-2. doi:10.1007/s40436-014-0063-4

摘要 ( 900 )

PDF (101KB) ( 394 )

参考文献 | 相关文章 | 多维度评价

Toward intelligent manufacturing: label characters marking and recognition method for steel products with machine vision

Qi-Jie Zhao Peng Cao Da-Wei Tu

2014, 2(1): 3-12. doi:10.1007/s40436-014-0057-2

摘要 ( 1105 )

PDF (1769KB) ( 676 )

参考文献 | 相关文章 | 多维度评价

Correctly coding materials and identifying characters marked on materials are very important for steel manufacturing industry to realize informatization management and intelligent manufacturing. However, the steel products manufacturing is often in a high temperature environment, and there are a lot of material storage and retrieval processes, workers are not easily close to the environment and complete tasks, so it is a great challenge to automatically mark and identify characters on the steel products. This paper presents a framework of label characters marking and management for steel materials, furthermore, a kind of marked characters online detection and tracking method has been provided based on machine vision. In addition, some experiments have been done in BaoSteel to mark characters on hot billets and recognize them in multi situations, and the results show that the proposed method is practical, and has provided a helpful exploration in obtaining accurate fundamental data for the intelligent manufacturing system in steelworks.

Current status and challenges of using geometric tolerance information in intelligent manufacturing systems

Hirpa G. Lemu

2014, 2(1): 13-21. doi:10.1007/s40436-014-0056-3

摘要 ( 1061 )

PDF (546KB) ( 859 )

参考文献 | 相关文章 | 多维度评价

Recent development in computer-based manufacturing and inspection has necessitated extended knowledge and usage of geometric tolerances as carriers of design intent. The aim of applying geometrical tolerances in design is to provide function-oriented precise description of part geometry where the conventional size tolerance system fails to address. In view of the current development of computer-aided systems, applying geometric tolerances opens a new research front. This article examines the challenges in applying geometric tolerance information to carry the design intent to other downstream manufacturing processes and intelligently integrate the whole system. Based on the observed practical capabilities and literature studies, it is concluded that the current computer-aided design (CAD) systems cannot effectively provide the appropriate use of geometric tolerances. This article highlights the existing challenges and proposes a scheme of algorithm development for appropriate use of tolerance symbols and conditions at the design specification stage. This, in the long run, enables the CAD model to carry the design intent and opens a window of opportunity for intelligently integrating manufacturing systems.

Computer vision supported by 3D geometric modelling

Sven Fjeldaas

2014, 2(1): 22-31. doi:10.1007/s40436-014-0068-z

摘要 ( 1051 )

PDF (413KB) ( 579 )

参考文献 | 相关文章 | 多维度评价

This paper suggests four data structures, one based on the other, for a geometric modeller suitable for computer vision. The structures are the key to advance from two-dimensional to three-dimensional automatic picture processing. Three application areas are indicated: one in semisynthetic design of materials, another in measurements of large three-dimensional industrial constructions, and the third one in robotics. There are comments on the software development needed.

A hybrid point cloud alignment method combining particle swarm optimization and iterative closest point method

Quan Yu Kesheng Wang

2014, 2(1): 32-38. doi:10.1007/s40436-014-0059-0

摘要 ( 1315 )

PDF (904KB) ( 824 )

参考文献 | 相关文章 | 多维度评价

3D quality inspection is widely applied in many industrial fields including mould design, automotive and blade manufacturing, etc. A commonly used method is to obtain the point cloud of the inspected object and make a comparison between the point cloud and the corresponding CAD model or template. Thus, it is important to align the point cloud with the template first and foremost. Moreover, for the purpose of automatization of quality inspection, this alignment process is expected to be completed without manual interference. In this paper, we propose to combine the particle swarm optimization (PSO) with iterative closest point (ICP) algorithm to achieve the automated point cloud alignment. The combination of the two algorithms can achieve a balance between the alignment speed and accuracy, and avoid the local optimal caused by bad initial position of the point cloud.

Phase error correction for fringe projection profilometry by using
constrained cubic spline

Jun-Zheng Peng Hang-Kong Ouyang Quan Yu Ying-Jie Yu Ke-Sheng Wang

2014, 2(1): 39-47. doi:10.1007/s40436-014-0058-1

摘要 ( 1289 )

PDF (5122KB) ( 629 )

参考文献 | 相关文章 | 多维度评价

In fringe projection profilometry, the nonlinear intensity response caused by the c effect of a digital projector results in periodic phase error and therefore measurement error. Previous error correction methods are largely based on the calibration of single c value. However, in practice, it is difficult to accurately model the full range of the intensity response with a one-parameter c function. In this paper, a compensated intensity response curve is generated and fitted with the constrained cubic spline. With the compensated curve, the full range of the nonlinear intensity response can be corrected and the periodic phase errors can be removed significantly. Experimental results on a flat board confirm the average root mean square (RMS) of the phase error which can be reduced to at least 0.0049 rad.

Virtual simulation of production line for ergonomics evaluation

Ming Chen Jin-Fei Liu

2014, 2(1): 48-53. doi:10.1007/s40436-014-0060-7

摘要 ( 1397 )

PDF (1220KB) ( 754 )

参考文献 | 相关文章 | 多维度评价

To avoid ergonomic problems in the early planning stages of a production line and achieve more satisfactory planning and design, ergonomic simulation is
particularly important in digital production line planning. An ergonomics analysis method is presented by using two theories: Ovako working posture analysis system (OWAS) and Burandt-Schultetus hand-arm force analysis (BSHA). The processes of ergonomics analysis and simulation are discussed based on a platform of process simulation and process designer. As an example, the paper shows how ergonomics problems are considered in production line planning to make a better choice between different production line planning schemes.

Graph representation of n-dimensional space

Tomasz Kosicki

2014, 2(1): 54-60. doi:10.1007/s40436-014-0065-2

摘要 ( 1037 )

PDF (601KB) ( 507 )

参考文献 | 相关文章 | 多维度评价

This paper investigates how graph representation can be created for the mesh which is a discrete approximation of n-dimensional continuous space. The paper discusses the relationship between mesh dimensionality and the type and quantity of edges connecting each vertex with its neighbors. Basing on the analysis, a simple algorithm is also proposed to create such graph representation. The purpose of the graph is to search optimal paths and trajectories in the represented space.

SCADA data based condition monitoring of wind turbines

Ke-Sheng Wang Vishal S. Sharma Zhen-You Zhang

2014, 2(1): 61-69. doi:DOI10.1007/s40436-014-0067-0

摘要 ( 1247 )

PDF (2035KB) ( 1284 )

参考文献 | 相关文章 | 多维度评价

Wind turbines (WTs) are quite expensive pieces of equipment in power industry. Maintenance and repair is a critical activity which also consumes lots of time
and effort, hence making it a costly affair. Carefully planning the maintenance based upon condition of the equipment would make the process reasonable. Mostly the WTs are equipped with some kind of condition monitoring device/system, which provides the information about the device to the central data base i.e., supervisory control and data acquisition (SCADA) data base. These devices/systems make use of data processing techniques/methods in order to detect and predict faults. The information provided by condition monitoring equipments keeps on recoding in the SCADA data base. This paper dwells upon the techniques methods/algorithms developed, to carry out diagnosis and prognosis of the faults, based upon SCADA data. Subsequently data driven approaching for SCADA data interpretation has been reviewed and an artificial intelligence (AI) based framework for fault diagnosis and prognosis of WTs using SCADA data is proposed.

Wind turbine fault detection based on SCADA data analysis using ANN

Zhen-You Zhang Ke-Sheng Wang

2014, 2(1): 70-78. doi:10.1007/s40436-014-0061-6

摘要 ( 1337 )

PDF (3286KB) ( 1207 )

参考文献 | 相关文章 | 多维度评价

Wind energy is one of the fast growing sources of power production currently, and there is a great demand to reduce the cost of operation and maintenance. Most wind farms have installed supervisory control and data acquisition (SCADA) systems for system control and logging data. However, the collected data are not used effectively. This paper proposes a fault detection method for main bearing wind turbine based on existing SCADA data using an artificial neural network (ANN). The ANN model for the normal behavior is established, and the difference between theoretical and actual values of the parameters is then calculated. Thus the early stage of main bearing fault can be identified to let the operator have sufficient time to make more informed decisions for maintenance.

Models for lifetime estimation: an overview with focus on applications to wind turbines

Thomas M. Welte Kesheng Wang

2014, 2(1): 79-87. doi:10.1007/s40436-014-0064-3

摘要 ( 1208 )

PDF (212KB) ( 618 )

参考文献 | 相关文章 | 多维度评价

This paper provides an overview of models and methods for estimation of lifetime of technical components. Although the focus in this paper is on wind turbine applications, the major content of the paper is of general nature. Thus, most of the paper content is also valid for lifetime models applied to other technical systems. The models presented and discussed in this paper are classified in different types of model classes. The main classification used in this paper divides the models in the following classes: physical models, stochastic models, data-driven models and artificial intelligence, and combined models. The paper provides an overview of different models for the different classes. Furthermore, advantages and disadvantages of the models are discussed, and the estimation of model parameters is briefly described. Finally, a number of literature examples are given in this paper, providing an overview of applications of different models on wind turbines.

Evaluation of thermal imaging system and thermal radiation
detector for real-time condition monitoring of high power
frequency converters

Anders Eriksen Dominik Osinski Dag Roar Hjelme

2014, 2(1): 88-94. doi:10.1007/s40436-014-0066-1

摘要 ( 1224 )

PDF (2477KB) ( 890 )

参考文献 | 相关文章 | 多维度评价

We have carried out at laboratory test to study the feasibility of using thermal radiation detectors for online thermal monitoring of electrical systems in wind
turbines. A 25 kW frequency converter is instrumented with a thermal camera, operating in the 8–14 lm wavelength range, and a single-pixel thermopile sensor, operating in the 4–8 lm wavelength range, to monitor the temperature development of the power electronics under various load sequences. Both systems performed satisfactorily with insignificant temperature deviations when compared to data from calibrated point contact sensor. With spatial averaging over a 7 mm 9 7 mm for the camera and temporal averaging over 60 s for the thermopile sensor, we reduce the root mean square noise to 45 mK
and 68 mK respectively. The low cost and simple operation of the thermopile sensor make it very attractive for condition monitoring applications, whereas the attractive feature of the camera is the possibility of multi-point or distributed temperature measurements.

当期目录