scholarly journals Developing automatic recognition system of drill wear in standard laminated chipboard drilling process

2016 ◽  
Vol 64 (3) ◽  
pp. 633-640 ◽  
Author(s):  
J. Kurek ◽  
M. Kruk ◽  
S. Osowski ◽  
P. Hoser ◽  
G. Wieczorek ◽  
...  
Keyword(s):  
Diagnostic System ◽  
Recognition System ◽  
Point Of View ◽  
Support Vector ◽  
Drilling Process ◽  
Processing Quality ◽  
Statistical Parameters ◽  
Diagnostic Features ◽  
Feed Force ◽  
Wavelet Representations

Abstract The paper presents an automatic approach to recognition of the drill condition in a standard laminated chipboard drilling process. The state of the drill is classified into two classes: “useful” (sharp enough) and “useless” (worn out). The case “useless” indicates symptoms of excessive drill wear, unsatisfactory from the point of view of furniture processing quality. On the other hand the “useful” state identifies tools which are still able to drill holes acceptable due to the required processing quality. The main problem in this task is to choose an appropriate set of diagnostic features (variables), based on which the recognition of drill state (“useful” versus “useless”) can be made. The features have been generated based on 5 registered signals: feed force, cutting torque, noise, vibration and acoustic emission. Different statistical parameters describing these signals and also their Fourier and wavelet representations have been used for defining the features. Sequential feature selection is applied to detect the most class discriminative set of features. The final step of recognition is done by using three types of classifiers, including support vector machine, ensemble of decision trees and random forest. Six standard drills of 12 mm diameter with tungsten carbide tips were used in experiments. The results have confirmed good quality of the proposed diagnostic system.

Control of Drilling and Coring Device Based on Online Identification

2013 ◽  
Author(s):  
Qiquan Quan ◽  
S. Li ◽  
S. Jiang ◽  
X. Hou ◽  
Z. Deng
Keyword(s):  
Object Recognition ◽  
Lunar Regolith ◽  
Lunar Soil ◽  
Recognition System ◽  
Current Level ◽  
Support Vector ◽  
Drilling Process ◽  
Operating Modes ◽  
Online Identification ◽  
Lunar Environment

This paper presents a drilling and coring device for the lunar exploration, which is possibly utilized to acquire the lunar regolith with a certain depth. The drilling device is composed of three components: rotary unit, percussive unit and penetrating unit. The rotary-percussion drill can work in two different operating modes: rotary mode and rotary-percussive mode, depending on the properties of cut object. In the relatively loose regolith, rotation and penetration can make the drill work in a well state. However, once rock is encountered in the drilling process, besides rotation and penetration, percussion must be launched to reduce the drilling power and the required penetrating force. Due to the indetermination of the lunar environment, it is not easy to control the coring drill to adapt to the encountered conditions. To obtain a high coring ratio with relatively low power, an intelligent drilling strategy is inevitably proposed to accomplish the drilling process control. Considering the lunar soil simulant should cover the possible composition of real lunar soil, simulant are classified into several levels based on the generalized drillability. For each level of drillability of lunar soil simulant, experiments are conducted to get the characteristics in frequency-domain of rotary torque output. The sampled characteristics of rotary torque output are utilized to train the object-recognition system based on Support Vector Machine (SVM). Information in all the levels of drillability of lunar soil simulant is stored in the object-recognition system as an expert system. To understand the properties of the drilling object, rotary torque is selected to identify the level of drillability of simulant in drilling process. Subsequently, once the level is obtained, drilling strategy is adjusted to adapt to the current level correspondingly in real time. Experiments are conducted to verify the intelligent drilling strategy successfully.

scholarly journals Design of Fractal Features-Based Partial Discharge Pattern Recognition using Multi Support Vector Machine Method

2018 ◽  
Vol 159 ◽  
pp. 02048
Author(s):  
Rahayu ◽  
G.T. Anuraga ◽  
H. Prasetia ◽  
Umar Khayam
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machine ◽  
High Voltage ◽  
Partial Discharge ◽  
Diagnostic System ◽  
Diagnostic Technique ◽  
Recognition System ◽  
Support Vector ◽  
Machine Method ◽  
Pattern Recognition System

Partial Discharge (PD) is one of the causes of insulation deteriorisation mode and impacts on the reliability of high voltage equipment. Therefore, PD measurement is used for diagnostic technique of high voltage equipment. Diagnostic output of high voltage equipment contain information about PD type, PD cause, PD location and PD severity. after identification, a proper preventive maintenance pattern can be performed. Therefore PD pattern recognition system is very important on PD diagnostic system to recognize the PD pattern and determine the level of hazard that occurs in specimen object or high voltage equipment‥ In this paper, PD pattern recognition system is designed with fractal geometry approach and support vector machine (SVM) algorithm. The coding and programming of graphical user interface of the application is done. Each PD type and hazard level on various insulating materials (solid, liquid and gas) have the dimensions of the fractal and the lacunarity. The type of PD (void, corona) and its danger level (bad, fair and good) can be identified with the support vector machine (SVM)

Selective statistical estimates of multi-year monthly concentrations of biogenous pollution of small rivers of the Northwest zone of the Russian Federation

2020 ◽  
pp. 9-13
Author(s):  
Sergey Kovalenko
Keyword(s):  
Statistical Processing ◽  
Point Of View ◽  
Small Rivers ◽  
Statistical Parameters ◽  
Monthly Data ◽  
Statistical Estimates ◽  
Scientific Task ◽  
The Russian Federation ◽  
Agricultural Areas

The management of surface watercourses is an urgent scientific task. The article presents the results of statistical processing of long-term monthly data of field observations of hydrological and hydrochemical parameters along the Upper Yerga small river in the Vologda region. Sampling estimates of statistical parameters are obtained, autocorrelation and correlation analyzes are performed. The limiting periods from the point of view of pollution for water receivers receiving wastewater from drained agricultural areas are identified.

OFFLINE YORÙBÁ HANDWRITTEN WORD RECOGNITION USING GEOMETRIC FEATURE EXTRACTION AND SUPPORT VECTOR MACHINE CLASSIFIER

2020 ◽  
Vol 5 (2) ◽  
pp. 504
Author(s):  
Matthias Omotayo Oladele ◽  
Temilola Morufat Adepoju ◽  
Olaide ` Abiodun Olatoke ◽  
Oluwaseun Adewale Ojo
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Word Recognition ◽  
Support Vector Machine Classifier ◽  
Recognition Accuracy ◽  
Recognition System ◽  
Support Vector ◽  
Geometric Features ◽  
Total Length ◽  
Yoruba Language

Yorùbá language is one of the three main languages that is been spoken in Nigeria. It is a tonal language that carries an accent on the vowel alphabets. There are twenty-five (25) alphabets in Yorùbá language with one of the alphabets a digraph (GB). Due to the difficulty in typing handwritten Yorùbá documents, there is a need to develop a handwritten recognition system that can convert the handwritten texts to digital format. This study discusses the offline Yorùbá handwritten word recognition system (OYHWR) that recognizes Yorùbá uppercase alphabets. Handwritten characters and words were obtained from different writers using the paint application and M708 graphics tablets. The characters were used for training and the words were used for testing. Pre-processing was done on the images and the geometric features of the images were extracted using zoning and gradient-based feature extraction. Geometric features are the different line types that form a particular character such as the vertical, horizontal, and diagonal lines. The geometric features used are the number of horizontal lines, number of vertical lines, number of right diagonal lines, number of left diagonal lines, total length of all horizontal lines, total length of all vertical lines, total length of all right slanting lines, total length of all left-slanting lines and the area of the skeleton. The characters are divided into 9 zones and gradient feature extraction was used to extract the horizontal and vertical components and geometric features in each zone. The words were fed into the support vector machine classifier and the performance was evaluated based on recognition accuracy. Support vector machine is a two-class classifier, hence a multiclass SVM classifier least square support vector machine (LSSVM) was used for word recognition. The one vs one strategy and RBF kernel were used and the recognition accuracy obtained from the tested words ranges between 66.7%, 83.3%, 85.7%, 87.5%, and 100%. The low recognition rate for some of the words could be as a result of the similarity in the extracted features.

GESTURE RECOGNITION SYSTEM FOR NIGERIAN TRIBAL GREETING POSTURES USING SUPPORT VECTOR MACHINE

2020 ◽  
Vol 5 (2) ◽  
pp. 609
Author(s):  
Segun Aina ◽  
Kofoworola V. Sholesi ◽  
Aderonke R. Lawal ◽  
Samuel D. Okegbile ◽  
Adeniran I. Oluwaranti
Keyword(s):  
Support Vector Machine ◽  
Gesture Recognition ◽  
Recognition Rate ◽  
Recognition Task ◽  
Recognition System ◽  
Human Interaction ◽  
Support Vector ◽  
System A ◽  
Extraction Algorithm ◽  
Gaussian Blur

This paper presents the application of Gaussian blur filters and Support Vector Machine (SVM) techniques for greeting recognition among the Yoruba tribe of Nigeria. Existing efforts have considered different recognition gestures. However, tribal greeting postures or gestures recognition for the Nigerian geographical space has not been studied before. Some cultural gestures are not correctly identified by people of the same tribe, not to mention other people from different tribes, thereby posing a challenge of misinterpretation of meaning. Also, some cultural gestures are unknown to most people outside a tribe, which could also hinder human interaction; hence there is a need to automate the recognition of Nigerian tribal greeting gestures. This work hence develops a Gaussian Blur – SVM based system capable of recognizing the Yoruba tribe greeting postures for men and women. Videos of individuals performing various greeting gestures were collected and processed into image frames. The images were resized and a Gaussian blur filter was used to remove noise from them. This research used a moment-based feature extraction algorithm to extract shape features that were passed as input to SVM. SVM is exploited and trained to perform the greeting gesture recognition task to recognize two Nigerian tribe greeting postures. To confirm the robustness of the system, 20%, 25% and 30% of the dataset acquired from the preprocessed images were used to test the system. A recognition rate of 94% could be achieved when SVM is used, as shown by the result which invariably proves that the proposed method is efficient.

QSAR Study of PARP Inhibitors by GA-MLR, GA-SVM and GA-ANN Approaches

2020 ◽  
Vol 16 (8) ◽  
pp. 1088-1105
Author(s):  
Nafiseh Vahedi ◽  
Majid Mohammadhosseini ◽  
Mehdi Nekoei
Keyword(s):  
Present Report ◽  
Principal Component ◽  
Parp Inhibitors ◽  
Support Vector ◽  
Ann Model ◽  
Statistical Parameters ◽  
Qsar Study ◽  
Data Set ◽  
Test Set ◽  
Non Linear

Background: The poly(ADP-ribose) polymerases (PARP) is a nuclear enzyme superfamily present in eukaryotes. Methods: In the present report, some efficient linear and non-linear methods including multiple linear regression (MLR), support vector machine (SVM) and artificial neural networks (ANN) were successfully used to develop and establish quantitative structure-activity relationship (QSAR) models capable of predicting pEC50 values of tetrahydropyridopyridazinone derivatives as effective PARP inhibitors. Principal component analysis (PCA) was used to a rational division of the whole data set and selection of the training and test sets. A genetic algorithm (GA) variable selection method was employed to select the optimal subset of descriptors that have the most significant contributions to the overall inhibitory activity from the large pool of calculated descriptors. Results: The accuracy and predictability of the proposed models were further confirmed using crossvalidation, validation through an external test set and Y-randomization (chance correlations) approaches. Moreover, an exhaustive statistical comparison was performed on the outputs of the proposed models. The results revealed that non-linear modeling approaches, including SVM and ANN could provide much more prediction capabilities. Conclusion: Among the constructed models and in terms of root mean square error of predictions (RMSEP), cross-validation coefficients (Q2 LOO and Q2 LGO), as well as R2 and F-statistical value for the training set, the predictive power of the GA-SVM approach was better. However, compared with MLR and SVM, the statistical parameters for the test set were more proper using the GA-ANN model.

scholarly journals Temperature monitoring in the subsurface during single lip deep hole drilling

2020 ◽  
Vol 87 (12) ◽  
pp. 757-767
Author(s):  
Robert Wegert ◽  
Vinzenz Guski ◽  
Hans-Christian Möhring ◽  
Siegfried Schmauder
Keyword(s):  
Cutting Parameters ◽  
Drill Hole ◽  
Machining Process ◽  
Hole Drilling ◽  
Drilling Process ◽  
Deep Hole ◽  
Machining Processes ◽  
Deep Hole Drilling ◽  
Feed Force ◽  
Cutting Zone

AbstractThe surface quality and the subsurface properties such as hardness, residual stresses and grain size of a drill hole are dependent on the cutting parameters of the single lip deep hole drilling process and therefore on the thermomechanical as-is state in the cutting zone and in the contact zone between the guide pads and the drill hole surface. In this contribution, the main objectives are the in-process measurement of the thermal as-is state in the subsurface of a drilling hole by means of thermocouples as well as the feed force and drilling torque evaluation. FE simulation results to verify the investigations and to predict the thermomechanical conditions in the cutting zone are presented as well. The work is part of an interdisciplinary research project in the framework of the priority program “Surface Conditioning in Machining Processes” (SPP 2086) of the German Research Foundation (DFG).This contribution provides an overview of the effects of cutting parameters, cooling lubrication and including wear on the thermal conditions in the subsurface and mechanical loads during this machining process. At first, a test set up for the in-process temperature measurement will be presented with the execution as well as the analysis of the resulting temperature, feed force and drilling torque during drilling a 42CrMo4 steel. Furthermore, the results of process simulations and the validation of this applied FE approach with measured quantities are presented.

scholarly journals CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 617
Author(s):  
Umer Saeed ◽  
Young-Doo Lee ◽  
Sana Ullah Jan ◽  
Insoo Koo
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Diagnostic System ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Context Aware ◽  
Sensor Faults ◽  
Training Time ◽  
Low Intensity ◽  
Fault Diagnostic

Sensors’ existence as a key component of Cyber-Physical Systems makes it susceptible to failures due to complex environments, low-quality production, and aging. When defective, sensors either stop communicating or convey incorrect information. These unsteady situations threaten the safety, economy, and reliability of a system. The objective of this study is to construct a lightweight machine learning-based fault detection and diagnostic system within the limited energy resources, memory, and computation of a Wireless Sensor Network (WSN). In this paper, a Context-Aware Fault Diagnostic (CAFD) scheme is proposed based on an ensemble learning algorithm called Extra-Trees. To evaluate the performance of the proposed scheme, a realistic WSN scenario composed of humidity and temperature sensor observations is replicated with extreme low-intensity faults. Six commonly occurring types of sensor fault are considered: drift, hard-over/bias, spike, erratic/precision degradation, stuck, and data-loss. The proposed CAFD scheme reveals the ability to accurately detect and diagnose low-intensity sensor faults in a timely manner. Moreover, the efficiency of the Extra-Trees algorithm in terms of diagnostic accuracy, F1-score, ROC-AUC, and training time is demonstrated by comparison with cutting-edge machine learning algorithms: a Support Vector Machine and a Neural Network.

A Test Sheet Optimization Approach to Supporting Web-based Learning Diagnosis Using Group Testing Methods

2017 ◽  
Vol 7 (4) ◽  
pp. 1-23
Author(s):  
Chu-Fu Wang ◽  
Chih-Lung Lin ◽  
Gwo-Jen Hwang ◽  
Sheng-Pin Kung ◽  
Shin-Feng Chen
Keyword(s):  
Test Item ◽  
Group Testing ◽  
Diagnostic System ◽  
Point Of View ◽  
Optimization Approach ◽  
Exposure Rate ◽  
Web Based ◽  
Item Exposure ◽  
Test Items ◽  
Doubling Method

Assessment can help teachers to examine the effectiveness of teaching and to diagnose the unfamiliar basic concepts (or attributes) of students within the testing scope. A web-based adaptive testing and diagnostic system can achieve the above objective efficiently and correctly. From a diagnostic point of view, the major concerns are to diagnose whether or not an examinee has learned each basic concept well in the testing scope, while also limiting the number of test items used (the testing length) to as few as possible, which will be directly related to the patience of the examinee. In this paper, we consider a test item selecting optimization diagnostic problem to reveal the mastery profile of an examinee (that is, to diagnose each basic concept's learning status (well learned/unfamiliar) in the testing scope) with a short testing length and a limited test item exposure rate. This paper uses the techniques of Group Testing theory for the design of our test item selecting algorithm. Two test item selecting strategies, the bisecting method and the doubling method, are proposed. The effectiveness of the proposed methods was evaluated by experimental simulations. The results show that both of the proposed algorithms use fewer test items and a limited test item exposure rate compared to the conventional methods.

Sign in / Sign up

Export Citation Format

Share Document