scholarly journals Evaluation of Machine Learning Methods for Monitoring the Health of Guyed Towers

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 213
Author(s):  
Diana Marcela Martinez Ricardo ◽  
German Efrain Castañeda Jimenez ◽  
Janito Vaqueiro Ferreira ◽  
Euripedes Guilherme de Oliveira Nobrega ◽  
Eduardo Rodrigues de Lima ◽  
...  
Keyword(s):  
Machine Learning ◽  
Service Failure ◽  
Failure Detection ◽  
Weather Conditions ◽  
Element Model ◽  
Machine Learning Approach ◽  
Different Types ◽  
Sensor Signals ◽  
Tower Vibration ◽  
The Finite Element Model

This paper presents the development of a methodology to detect and evaluate faults in cable-stayed towers, which are part of the infrastructure of Brazil’s interconnected electrical system. The proposed method increases system reliability and minimizes the risk of service failure and tower collapse through the introduction of predictive maintenance methods based on artificial intelligence, which will ultimately benefit the end consumer. The proposed signal processing and interpretation methods are based on a machine learning approach, where the tower vibration is acquired from accelerometers that measure the dynamic response caused by the effects of the environment on the towers through wind and weather conditions. Data-based models were developed to obtain a representation of health degradation, which is primarily based on the finite element model of the tower, subjected to wind excitation. This representation is also based on measurements using a mockup tower with different types of provoked degradation that was subjected to ambient changes in the laboratory. The sensor signals are preprocessed and submitted to an autoencoder neural network to minimize the dimensionality of the resources involved, being analyzed by a classifier, based on a Softmax configuration. The results of the proposed configuration indicate the possibility of early failure detection and evolution evaluation, providing an effective failure detection and monitoring system.

scholarly journals Redewiedergabe – Schritte zur automatischen Erkennung

2019 ◽  
Vol 47 (1) ◽  
pp. 216-248
Author(s):  
Annelen Brunner
Keyword(s):  
Machine Learning ◽  
Automatic Detection ◽  
Learning Approach ◽  
Manual Annotation ◽  
Narrative Texts ◽  
Rule Based ◽  
Machine Learning Approach ◽  
Different Types ◽  
Short Narrative ◽  
Over Time

Abstract This contribution presents a quantitative approach to speech, thought and writing representation (ST&WR) and steps towards its automatic detection. Automatic detection is necessary for studying ST&WR in a large number of texts and thus identifying developments in form and usage over time and in different types of texts. The contribution summarizes results of a pilot study: First, it describes the manual annotation of a corpus of short narrative texts in relation to linguistic descriptions of ST&WR. Then, two different techniques of automatic detection – a rule-based and a machine learning approach – are described and compared. Evaluation of the results shows success with automatic detection, especially for direct and indirect ST&WR.

scholarly journals Machine Learning Approach to Classify Rain Type Based on Thies Disdrometers and Cloud Observations

Atmosphere ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 251 ◽  
Author(s):  
Wael Ghada ◽  
Nicole Estrella ◽  
Annette Menzel
Keyword(s):  
Machine Learning ◽  
Geographical Location ◽  
Classification Performance ◽  
Classification Methods ◽  
Reference Dataset ◽  
Machine Learning Classification ◽  
Machine Learning Approach ◽  
Different Types ◽  
Microstructure Parameters

Rain microstructure parameters assessed by disdrometers are commonly used to classify rain into convective and stratiform. However, different types of disdrometer result in different values for these parameters. This in turn potentially deteriorates the quality of rain type classifications. Thies disdrometer measurements at two sites in Bavaria in southern Germany were combined with cloud observations to construct a set of clear convective and stratiform intervals. This reference dataset was used to study the performance of classification methods from the literature based on the rain microstructure. We also explored the possibility of improving the performance of these methods by tuning the decision boundary. We further identified highly discriminant rain microstructure parameters and used these parameters in five machine-learning classification models. Our results confirm the potential of achieving high classification performance by applying the concepts of machine learning compared to already available methods. Machine-learning classification methods provide a concrete and flexible procedure that is applicable regardless of the geographical location or the device. The suggested procedure for classifying rain types is recommended prior to studying rain microstructure variability or any attempts at improving radar estimations of rain intensity.

The Stress Analysis for the Trenchless Pipeline Rehabilitation

2005 ◽  
Author(s):  
Kuang-Chyi Lee ◽  
Rong-Yuan Jou ◽  
Hsin Her Yu ◽  
Yuan-Cheng Liang ◽  
Chien-Chang Lin
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Stress Analysis ◽  
Heavy Traffic ◽  
Element Model ◽  
Hydraulic Pressure ◽  
Optimal Thickness ◽  
Plastic Sheet ◽  
Different Types ◽  
The Finite Element Model

Most of the pipelines will get aging year after year and then they will need to be rehabilitated. Because of the heavy traffic on the ground or the congested pipelines under the ground, the replacement of old pipes will be very difficult in the cities. The dig-free (trenchless) method is a revolutionary pipelining method which uses air pressure, hydraulic pressure or mechanical drag force to pull the flexible piping plastic sheet into the old pipe. This research proposes a stress analysis for trenchless pipeline method by the finite element model with CATIA. The material of piping sheet is combined of two different types of epoxy with the anionic harder. We do the stress analysis of the trenchless rehabilitated pipelines to decide the optimal thickness of flexible piping plastic sheet and whether the material is available or not by finite element method.

scholarly journals Geometry Optimisation of a Hall-Effect-Based Soft Fingertip for Estimating Orientation of Thin Rectangular Objects

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 4056 ◽  
Author(s):  
Rosle ◽  
Wang ◽  
Hirai
Keyword(s):  
Hall Effect ◽  
Element Model ◽  
Object Orientation ◽  
Parameter Design ◽  
Average Error ◽  
Trial And Error ◽  
Tactile Sensors ◽  
Design Variables ◽  
Machine Learning Approach ◽  
The Finite Element Model

Soft tactile sensors have been applied to robotic grippers for assembly. It is a challenging task to obtain contact information and object orientation using tactile sensors during grasping. Currently, the design of Hall-effect-based tactile sensors to perform such tasks is based on trial and error. We present a method of investigating the optimal geometrical design of a cylindrical soft sensor to increase its sensitivity. The finite element model of a soft fingertip was constructed in Abaqus with two design variables, i.e., hollow radius and magnet position. Then, the model was imported into Isight, with the maximisation of magnet displacement as the objective function. We found that the optimal design was at the boundary of the parameter design space. Four fingertips were fabricated with one intuitive, one optimal, and two optional sets of parameters. Experiments were performed, and object orientation was estimated by utilising linear approximation and a machine learning approach. Good agreements were achieved between optimisation and experiments. The results revealed that the estimated average error in object orientation was decreased by the optimised fingertip design. Furthermore, the 3-axis forces could successfully be estimated based on sensor outputs.

A frequency response function-based updating technique for the finite element model of automotive structures

2008 ◽  
Vol 222 (10) ◽  
pp. 1781-1791 ◽  
Author(s):  
D-C Lee ◽  
C-S Han
Keyword(s):  
Finite Element ◽  
Element Model ◽  
Design Parameters ◽  
External Loading ◽  
Element Analysis ◽  
Automotive Structures ◽  
Different Types ◽  
External Loads ◽  
The Finite Element Model ◽  
Huge Variety

Today's automotive industry uses finite element analysis (FEA) in a huge variety of applications in order to optimize structures and processes before hardware is produced. Efficiencies can be enhanced and margins are reduced because the external loads and structural properties are identified with higher confidence. The accuracy of FEA predictions has become increasingly important and directly influences the competitiveness of a product on the market. Because automotive structures are under dynamic environments, the correlation on the basis of static deformations independent of the mass and damping parameters do not provide a valuable reference from the view of the dynamic characteristics. In this paper, by systematically comparing the results from analytical and experimental analysis techniques, finite element (FE) models can be validated by the deterministic and robust design on the basis of each tolerance of design parameters, and improved so that they can be used with more confidence in further analysis. Making use of different types of test datum, a recommended procedure is to use a sequence of analysis in which mass, stiffness, damping, and external loading are validated and, if necessary, updated.

scholarly journals HAMLET

Terminology ◽  
2021 ◽  
Author(s):  
Ayla Rigouts Terryn ◽  
Véronique Hoste ◽  
Els Lefever
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Hybrid Approach ◽  
Substantial Effect ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Term Extraction ◽  
Machine Learning Approach ◽  
Different Types

Abstract Automatic term extraction (ATE) is an important task within natural language processing, both separately, and as a preprocessing step for other tasks. In recent years, research has moved far beyond the traditional hybrid approach where candidate terms are extracted based on part-of-speech patterns and filtered and sorted with statistical termhood and unithood measures. While there has been an explosion of different types of features and algorithms, including machine learning methodologies, some of the fundamental problems remain unsolved, such as the ambiguous nature of the concept “term”. This has been a hurdle in the creation of data for ATE, meaning that datasets for both training and testing are scarce, and system evaluations are often limited and rarely cover multiple languages and domains. The ACTER Annotated Corpora for Term Extraction Research contain manual term annotations in four domains and three languages and have been used to investigate a supervised machine learning approach for ATE, using a binary random forest classifier with multiple types of features. The resulting system (HAMLET Hybrid Adaptable Machine Learning approach to Extract Terminology) provides detailed insights into its strengths and weaknesses. It highlights a certain unpredictability as an important drawback of machine learning methodologies, but also shows how the system appears to have learnt a robust definition of terms, producing results that are state-of-the-art, and contain few errors that are not (part of) terms in any way. Both the amount and the relevance of the training data have a substantial effect on results, and by varying the training data, it appears to be possible to adapt the system to various desired outputs, e.g., different types of terms. While certain issues remain difficult – such as the extraction of rare terms and multiword terms – this study shows how supervised machine learning is a promising methodology for ATE.

scholarly journals Advanced Machine Learning Models to Handle Unifying Attacks in Images

2019 ◽  
Vol 8 (10) ◽  
pp. 4336-4339
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Digital Systems ◽  
Neural Systems ◽  
Learning Approach ◽  
Digital Environment ◽  
Machine Learning Approach ◽  
Different Types ◽  
Innovative Work ◽  
Machine Learning Models

Critical advancement has been made with profound neural systems as of late. Sharing prepared models of profound neural systems has been a significant in the fast advancement of innovative work of these frameworks. In digital environment, there are different types of applications face security related attack sequences from third parties. Most of the machine learning related approaches was introduced to describe security in wind and vulnerable attack sequences. Digital Watermarking is one of the approach to handle adversary related security approach to handle attacks appeared in digital environment. But it has some limitations to describe efficient security behind the web related applications appeared in real time environment. So that in this paper, we propose and implement advanced machine learning approach i.e Neural Network based Click Prediction (NNBCP) to handle web related attack sequences in real time environment. It uses Integrated CAPTCHA procedure to provide machine learning based captcha generation for user login and registration to handle different types of attacks in digital systems.

scholarly journals Forecasting Appliances Failures: A Machine-Learning Approach to Predictive Maintenance

Information ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 208
Author(s):  
Sofia Fernandes ◽  
Mário Antunes ◽  
Ana Rita Santiago ◽  
João Paulo Barraca ◽  
Diogo Gomes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Acquisition ◽  
Failure Detection ◽  
Predictive Maintenance ◽  
Learning Approach ◽  
Household Appliances ◽  
Machine Learning Approach ◽  
The Cost

Heating appliances consume approximately 48 % of the energy spent on household appliances every year. Furthermore, a malfunctioning device can increase the cost even further. Thus, there is a need to create methods that can identify the equipment’s malfunctions and eventual failures before they occur. This is only possible with a combination of data acquisition, analysis and prediction/forecast. This paper presents an infrastructure that supports the previously mentioned capabilities and was deployed for failure detection in boilers, making possible to forecast faults and errors. We also present our initial predictive maintenance models based on the collected data.

Sign in / Sign up

Export Citation Format

Share Document