Search results

This paper proposes a framework to assist in managing predictive maintenance by detecting progressive surface wear on spur gears through the analysis of digital images of gear teeth using computer vision (CV) techniques.

An experimental setup was constructed to capture images of gear teeth using endoscopic cameras. The images were selected, pre-processed, stored in a database and used in the experimental study of the proposed framework. Three CV techniques were explored within the framework for detecting wear in spur gears: (1) edge detection; (2) gray level co-occurrence matrix (GLCM) combined with machine learning (ML) algorithms and (3) deep learning with convolutional neural networks (CNN).

The results showed 85% accuracy using the edge detection algorithm. Among the ML algorithms, accuracy was above 60% for the support vector machine (SVM) and above 70% for K-nearest neighbors (KNN). Principal component analysis (PCA) indicated that as the distance between the principal components increased, it characterized the formation and progression of surface wear on the gear teeth. With the CNN, an accuracy of 99.999981% was achieved in the training loss rate, with a classification accuracy rate (CAR) of 91.6666%, an F1 score of 90.9090% and a recall of 83.3334% during the testing phase.

This framework is applicable to a variety of gear systems and industrial contexts requiring predictive maintenance, making it a highly scalable solution for industry professionals.

This paper proposes a novel framework that considers various CV techniques to detect and assess the level of wear on spur gear surfaces. Moreover, the results provide guidelines for selecting the most appropriate method for detecting wear in gear systems.

The purpose of this paper is to explore a new design for the journal of revolute joints that can improve the dynamic performance of 3D printed non-assembly mechanisms.

The design improves upon previous proposed designs that use drum-shaped journals in place of cylindrical ones. The authors introduce an innovative new worm-shaped journal. The authors also propose a systematic and efficient procedure to identify the best parameter values for defining the exact shape of the journal. Using three different mechanisms for the experiments, the paper constructs 3D computer-aided design (CAD) models using the design as well as cylindrical and drum-shaped designs. The parameters for the optimum geometry for each type of design are determined by dynamic simulation using the CAD system. Actual prototypes of the ideal designs are constructed using a commercial fused deposition modeling (FDM) machine for physical comparisons.

This paper shows that in simulations as well in physical models, the proposed design outperforms the previous designs significantly.

This study was mainly focused on the FDM process, and the authors have not yet explored other processes. One limitation of this approach is that it requires the mechanism to be printed along the axial direction of the revolute joint.

This paper proposes a new design for the journal in 3D printed revolute joints. A clear advantage of the design is that it can easily be used to replace normal revolute joins in non-assembly models without affecting any other parts of the geometry. Therefore, with relatively little effort, the authors can print non-assembly mechanisms with improved dynamic performance.

The purpose of this paper is to discuss the performance of a proposed machine design for an in‐wheel motor with the required torque‐speed characteristic.

Calculation of the winding factor of the machine with the star of slots theory is performed first. The field weakening capability of the machine is investigated and the operating speed range is determined. The tooth contour modeling method for calculating the performance of the machine with a limited number of elements is introduced. The method is used to construct two models of different complexity and the results obtained with the models are compared with the results obtained by finite element models.

The 14 pole 12 slot in‐wheel PMSM discussed in this paper is able to meet the stringent performance requirements. The results obtained with the tooth contour models show good agreement with the results obtained with finite element models despite the limited number of elements. Increasing the number of elements in the model allows for modeling of armature reaction and increases the accuracy of the model.

This work can be continued with investigating the possibilities to model the armature reaction more accurately.

This paper proposes a modeling method which accurately describes the performance of a PMSM with limited number of elements. With this method, the calculation procedure can be easily used for optimization of the machine design.

THE curtain has now been rung down on the Jubilee of the Library Association and all who witnessed or took part in the performance will agree that the show was good. The setting of the scene in so beautiful a city, the lavish and dignified hospitality, the fine and sympathetic chairmanship of the new President, the general good‐humoured seriousness of the discussions—all these things will remain to make the Edinburgh Conference the most memorable in our annals. The Conference was not only nation‐wide and empire‐wide—it was world‐wide; and several languages and many accents were heard. Librarians of great fame, who hitherto have been names only, became known friends within the week.

The rather drastic changes in the Cataloguing Rules of University College London, which were described in Vol. 12, no. 2 of this journal, published in June 1956, soon became accepted routine to the inconvenience of no one, so far as is known, except of the cataloguers whose task it was to make the necessary adjustments and to recatalogue small batches of cards from time to time. This inconvenience was more than compensated by the comparative simplicity of headings for both main and subsidiary entries, and by a reduction in the number of added entries needed.

The changes in cataloguing rules and practice that were put into operation in the Library of University College, London, in the summer of 1955 cannot in the nature of things compare in scope or elaboration with the new scheme of classification, the main features of which were described by Mr. Garside in Vol. 10, No. 4 of this journal. Nevertheless they represent the beginnings of a desirable complement on the cataloguing side to the massive improvements in the arrangement of books inaugurated by the adoption of the new scheme. They are designed to facilitate the finding of books in the catalogue as the classification does on the shelves. Incidentally, they will considerably reduce the need for adding the fourth, alphabetical element of the classmark to the cards. Like the classification, they represent an economy in administration in the long, if not always immediately in the short run.

THE Fifty‐First Conference of the Library Association takes place in the most modern type of British town. Blackpool is a typical growth of the past fifty years or so, rising from the greater value placed upon the recreations of the people in recent decades. It has the name of the pleasure city of the north, a huge caravansary into which the large industrial cities empty themselves at the holiday seasons. But Blackpool is more than that; it is a town with a vibrating local life of its own; it has its intellectual side even if the casual visitor does not always see it as readily as he does the attractions of the front. A week can be spent profitably there even by the mere intellectualist.

WE write on the eve of an Annual Meeting of the Library Association. We expect many interesting things from it, for although it is not the first meeting under the new constitution, it is the first in which all the sections will be actively engaged. From a membership of eight hundred in 1927 we are, in 1930, within measurable distance of a membership of three thousand; and, although we have not reached that figure by a few hundreds—and those few will be the most difficult to obtain quickly—this is a really memorable achievement. There are certain necessary results of the Association's expansion. In the former days it was possible for every member, if he desired, to attend all the meetings; today parallel meetings are necessary in order to represent all interests, and members must make a selection amongst the good things offered. Large meetings are not entirely desirable; discussion of any effective sort is impossible in them; and the speakers are usually those who always speak, and who possess more nerve than the rest of us. This does not mean that they are not worth a hearing. Nevertheless, seeing that at least 1,000 will be at Cambridge, small sectional meetings in which no one who has anything to say need be afraid of saying it, are an ideal to which we are forced by the growth of our numbers.

It has often been said that a great part of the strength of Aslib lies in the fact that it brings together those whose experience has been gained in many widely differing fields but who have a common interest in the means by which information may be collected and disseminated to the greatest advantage. Lists of its members have, therefore, a more than ordinary value since they present, in miniature, a cross‐section of institutions and individuals who share this special interest.

This series of annual reviews of the literature of special librarianship, which now reaches its fifth year, has been designed to help those most in need of the body of professional experience contained in the literature. Those special librarians or information officers with little or no professional training, who work in small departments far away from more experienced colleagues, have only the recorded knowledge in the literature to help them, but, because of lack of experience, they are often unable to sift from the mass of articles of varying value and character which crowd the pages of the professional journals the comparatively few items likely to be of practical use to them. For their benefit we present a selection of those papers really likely to give them solid help, leaving aside all purely theoretical and polemical articles, however important, and all literature on large libraries, unless they are likely to have applications in smaller ones. To these we add a selection of reference books likely to be of professional use to anyone in information work, including a number which he may wish to know about, even though he does not have them in his own library. The list is not restricted to work published in 1956, but is intended rather to be representative of items received in British libraries during that year. With the growing volume of library literature, the choice of a hundred or so items is bound to be in some respects a personal one, with which many may disagree, especially over the omissions, but it is hoped that all the items included will be of positive value.