scholarly journals Reliability analysis using experimental statistical methods and AIS: application in continuous flow tubes of gaseous medium

2021 ◽  
Vol 43 ◽  
pp. e55825
Author(s):  
Roberto Outa ◽  
Fábio Roberto Chavarette ◽  
Aparecido Carlos Gonçalves ◽  
Sidney Leal da Silva ◽  
Vishnu Narayan Mishra ◽  
...  
Keyword(s):  
Standardized Tests ◽  
Negative Selection ◽  
Production Systems ◽  
Wiener Filter ◽  
Pressure Vessels ◽  
Signal Recognition ◽  
Security Risk ◽  
Artificial Immune ◽  
Degree Of Severity

The motivation for the development of this work arose from the observation of maintenance in pressure vessels, which are categorized as highly hazardous security risk products. The costs of detecting failures in the production systems allow the result of the process to be safe and of good quality, using standardized tests internally within the company. The main objective of this work demonstrates the efficiency and robustness of the artificial immune system (AIS) of negative selection in the detection of failures by recognizing the vibration signals and categorizing them in the degree of probability and level of severity of failures. The intrinsic objectives are the application of the elimination of signal noise by the Wiener filter, and the processing of data-Wiener data using experimental statistics. The result of this work successfully demonstrates the precision between the experimental statistical and AIS techniques of negative selection; the robustness of the algorithm in precision and signal recognition; and the classification of the degree of severity and probability of failure

scholarly journals Analysis and Prognosis of Failures in Intelligent Hybrid Systems Using Bioengineering: Gear Coupling

2022 ◽  
Vol 8 (1) ◽  
Author(s):  
Roberto Outa ◽  
Fabio Roberto Chavarette ◽  
Vishnu Narayan Mishra ◽  
Aparecido Carlos Gonçalves ◽  
Adriana Garcia ◽  
...  
Keyword(s):  
Immune System ◽  
Hybrid Systems ◽  
Acoustic Signal ◽  
Signal Analysis ◽  
Negative Selection ◽  
Artificial Immune System ◽  
Development Process ◽  
Wiener Filter ◽  
Artificial Immune ◽  
Acoustic Signal Analysis

This work is of multidisciplinary concept, whose development is difficult to perform. Considering also that, in one of the steps, the similarity between the FRF of the vibration and acoustic signal is demonstrated. The objective of this work is the analysis and prognosis of the progression of failures of a pair of gears using the artificial immune system (AIS) of negative selection. In order to have this condition met, during the development of this work, the Wiener filter technique, the vibration and acoustic signal analysis (FRF), the application of negative selection AIS techniques for classification and grouping of signals were applied. The final result successfully demonstrates the effectiveness of the development process of this work and the robustness of the negative selection AIS algorithm.

Identification of cavitation in centrifugal pump by artificial immune network

2021 ◽  
pp. 095440892110284
Author(s):  
Seyed M Matloobi ◽  
Mohammad Riahi
Keyword(s):  
Immune System ◽  
Production Systems ◽  
Principal Component ◽  
Immune Network ◽  
Centrifugal Pumps ◽  
Artificial Immune ◽  
Human Immune System ◽  
Time Frequency ◽  
Artificial Immune Network ◽  
Damage Condition

Reducing the cost of unscheduled shutdowns and enhancing the reliability of production systems is an important goal for various industries; this could be achieved by condition monitoring and artificial intelligence. Cavitation is a common undesired phenomenon in centrifugal pumps, which causes damage and its detection in the preliminary stage is very important. In this paper, cavitation is identified by use of vibration and current signal and artificial immune network that is modeled on the base of the human immune system. For this purpose, first data collection were done by a laboratory setup in health and five stages damage condition; then various features in time, frequency, and time–frequency were extracted from vibration and current signals in addition to pressure and flow rate; next feature selection and dimensions reduction were done by artificial immune method to use for classification; finally, they were used by artificial immune network and some other methods to identify the system condition and classification. The results of this study showed that this method is more accurate in the detection of cavitation in the initial stage compared to methods such as non-linear supportive vector machine, multi-layer artificial neural network, K-means and fuzzy C-means with the same data. Also, selected features with artificial immune system were better than principal component analysis results.

Structural failures diagnosis using a hybrid artificial intelligence method / Diagnóstico de falhas estruturais utilizando um método híbrido de inteligência artificial

2021 ◽  
Vol 7 (7) ◽  
pp. 66873-66893
Author(s):  
Simone Silva Frutuoso de Souza ◽  
Mailon Bruno Pedri de Campos ◽  
Fábio Roberto Chavarette ◽  
Fernando Parra dos Anjos Lima
Keyword(s):  
Immune System ◽  
Negative Selection ◽  
Artificial Immune System ◽  
Artificial Immune ◽  
Aircraft Structure ◽  
Inspection Process ◽  
Artificial Immune System Algorithm ◽  
Structural Failures ◽  
Aluminum Beam ◽  
Hybrid Artificial Intelligence

This paper presents a Wavelet-artificial immune system algorithm to diagnose failures in aeronautical structures. Basically, after obtaining the vibration signals in the structure, is used the wavelet module for transformed the signals into the wavelet domain. Afterward, a negative selection artificial immune system realizes the diagnosis, identifying and classifying the failures. The main application of this methodology is the auxiliary structures inspection process in order to identify and characterize the flaws, as well as perform the decisions aiming at avoiding accidents or disasters. In order to evaluate this methodology, we carried out the modeling and simulation of signals from a numerical model of an aluminum beam, representing an aircraft structure such as a wing. The results demonstrate the robustness and accuracy methodology.

Limit Loads of Bolted Flange Connections

2021 ◽  
Author(s):  
Finn Kirkemo ◽  
Przemyslaw Lutkiewicz
Keyword(s):  
Calculation Method ◽  
Production Systems ◽  
Pressure Vessels ◽  
Finite Element Analyses ◽  
Limit Loads ◽  
Face To Face ◽  
Structural Capacity ◽  
Process Piping ◽  
Asme Code ◽  
Bolted Flange

Abstract High-pressure applications such as process piping, pressure vessels, risers, pipelines, and subsea production systems use bolted flange connections. Design of flanged joints may be done by design by rules and design by analysis. This paper presents a design by rules method applicable for flanges designed for face-to-face make-up. Limit loads are used to calculate the structural capacity (resistance) of the flanges, bolts, and metallic seal rings. Designers can use the calculation method to size bolted flange connections and calculate the structural capacity of existing bolted flange connections. Finite element analyses have been performed to verify the analytically based calculation method. The intention is to prepare for an ASME code case based on the calculation method presented in this paper.

Performance of Negative Selection Algorithms in Patient Detection and Classification

2018 ◽  
pp. 78-102
Author(s):  
Orhan Bölükbaş ◽  
Harun Uğuz
Keyword(s):  
Immune System ◽  
Error Detection ◽  
Classification Accuracy ◽  
Negative Selection ◽  
Clonal Selection ◽  
Artificial Immune Systems ◽  
Detection Accuracy ◽  
Data Sets ◽  
Selection Algorithm ◽  
Artificial Immune

Artificial immune systems inspired by the natural immune system are used in problems such as classification, optimization, anomaly detection, and error detection. In these problems, clonal selection algorithm, artificial immune network algorithm, and negative selection algorithm are generally used. This chapter aims to solve the problem of correct identification and classification of patients using negative selection (NS) and variable detector negative selection (V-DET NS) algorithms. The authors examine the performance of NSA and V-DET NSA algorithms using three sets of medical data sets from Parkinson, carotid artery doppler, and epilepsy patients. According to the obtained results, NSA achieved 92.45%, 91.46%, and 92.21% detection accuracy and 92.46%, 93.40%, and 90.57% classification accuracy. V-DET NSA achieved 94.34%, 94.52%, and 91.51% classification accuracy and 94.23%, 94.40%, and 89.29% detection accuracy. As can be seen from these values, V-Det NSA yielded a better result. Artificial immune system emerges as an effective and promising system in terms of problem-solving performance.

Automatic Selector Between Cardiogenic Oscillation and Airway Secretion in Mechanical Ventilation Flow Signals Using Artificial Immune System

2018 ◽  
Vol 9 (4) ◽  
pp. 65-78
Author(s):  
Samuel Sobral dos Santos ◽  
Hatus Vianna Wanderley ◽  
Fernando Buarque de Lima Neto
Keyword(s):  
Immune System ◽  
Artificial Immune System ◽  
Artificial Immune ◽  
Flow Signal ◽  
Specificity And Sensitivity ◽  
Airway Secretion ◽  
Artificial Immune System Algorithm ◽  
Ventilation Modes ◽  
Cardiogenic Oscillation

The accumulation of secretions in the airways of ventilator-dependent patients is a common problem, and if not detected and treated in due time, it greatly increases the risk of infections and asynchrony. Unfortunately, cardiogenic oscillation modifies the flow signal shape that can confuse clinical staff and modern lung ventilators. In this article, the authors use an artificial immune system algorithm in a pre-processed flow signal. The authors' approach was able to automatically detect the presence or absence of airway secretions, even if the sample contains the influence of cardiogenic oscillation. The training and validation of the algorithm was carried out using a database containing flow signals of 457 respiratory cycles, obtained from three patients in different ventilation modes. The algorithm trained with 60% of the base cycles, was able to achieve specificity and sensitivity above 0.96 in the classification of the remaining cycles of the base.

Comparing the capabilities of transfer learning models to detect skin lesion in humans

2020 ◽  
Vol 234 (10) ◽  
pp. 1083-1093 ◽  
Author(s):  
Aditi Singhal ◽  
Ramesht Shukla ◽  
Pavan Kumar Kankar ◽  
Saurabh Dubey ◽  
Sukhjeet Singh ◽  
...  
Keyword(s):  
Skin Lesion ◽  
Transfer Learning ◽  
Wiener Filter ◽  
Skin Lesions ◽  
Automated Classification ◽  
Convolutional Networks ◽  
Image Quantization ◽  
Malignant Skin ◽  
Effective Diagnosis

Effective diagnosis of skin tumours mainly relies on the analysis of the characteristics of the lesion. Automatic detection of malignant skin lesion has become a mandatory task to reduce the risk of human deaths and increase their survival. This article proposes a study of skin lesion classification using transfer learning approach. The transfer learning model uses four different state-of-the-art architectures, namely Inception v3, Residual Networks (ResNet 50), Dense Convolutional Networks (DenseNet 201) and Inception Residual Networks (Inception ResNet v2). These models are trained under the dataset comprising seven different classes of skin lesions. The skin lesion images are pre-processed using image quantization, grayscaling and the Wiener filter before final training step. These models are compared for performance evaluation on different metrics. The present study shows the efficacy of the methodology for automated classification of lesion images.

Sign in / Sign up

Export Citation Format

Share Document