A learning algorithm based estimation method for maintenance cost of product concepts

2006 ◽  
Vol 50 (1-2) ◽  
pp. 66-75 ◽  
Author(s):  
Kwang-Kyu Seo ◽  
Beum Jun Ahn
Keyword(s):  
Learning Algorithm ◽  
Estimation Method ◽  
Maintenance Cost ◽  
Product Concepts

A Time-Dependent Reliability Estimation Method Based on Gaussian Process Regression

2018 ◽  
Author(s):  
Wang Han ◽  
Xiaoling Zhang ◽  
Xiesi Huang ◽  
Haiqing Li
Keyword(s):  
Machine Learning ◽  
Mechanical System ◽  
Physical Modeling ◽  
Learning Algorithm ◽  
Estimation Method ◽  
Gaussian Process Regression ◽  
Reliability Estimation ◽  
Time Dependent ◽  
Physics Of Failure ◽  
Gear Transmission System

This paper presents a time-dependent reliability estimation method for engineering system based on machine learning and simulation method. Due to the stochastic nature of the environmental loads and internal incentive, the physics of failure for mechanical system is complex, and it is challenging to include uncertainties for the physical modeling of failure in the engineered system’s life cycle. In this paper, an efficient time-dependent reliability assessment framework for mechanical system is proposed using a machine learning algorithm considering stochastic dynamic loads in the mechanical system. Firstly, stochastic external loads of mechanical system are analyzed, and the finite element model is established. Secondly, the physics of failure mode of mechanical system at a time location is analyzed, and the distribution of time realization under each load condition is calculated. Then, the distribution of fatigue life can be obtained based on high-cycle fatigue theory. To reduce the calculation cost, a machine learning algorithm is utilized for physical modeling of failure by integrating uniform design and Gaussian process regression. The probabilistic fatigue life of gear transmission system under different load conditions can be calculated, and the time-varying reliability of mechanical system is further evaluated. Finally, numerical examples and the fatigue reliability estimation of gear transmission system is presented to demonstrate the effectiveness of the proposed method.

Intraocular Pressure Estimation Method Based on Vibration Propagation Characteristics According to Structure Contact

2021 ◽  
Vol 263 (1) ◽  
pp. 5552-5554
Author(s):  
Kim Deukha ◽  
Seongwook Jeon ◽  
Won June Lee ◽  
Junhong Park
Keyword(s):  
Intraocular Pressure ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Ex Vivo ◽  
Estimation Method ◽  
Biological Tissues ◽  
Response To Treatment ◽  
Deep Learning Algorithm ◽  
Cross Correlation Analysis ◽  
Porcine Eyes

Intraocular pressure (IOP) measurement is one of the basic tests performed in ophthalmology and is known to be an important risk factor for the development and progression of glaucoma. Measurement of IOP is important for assessing response to treatment and monitoring the progression of the disease in glaucoma. In this study, we investigate a method for measuring IOP using the characteristics of vibration propagation generated when the structure is in contact with the eyeball. The response was measured using an accelerometer and a force sensitive resistor to determine the correlation between the IOP. Experiment was performed using ex-vivo porcine eyes. To control the IOP, a needle of the infusion line connected with the water bottle was inserted into the porcine eyes through the limbus. A cross correlation analysis between the accelerometer and the force sensitive resistor was performed to derive a vibration factor that indicate the change in IOP. In order to analyze the degree of influence of biological tissues such as the eyelid, silicon was placed between the structure and the eyeball. The Long Short-Term Memory (LSTM) deep learning algorithm was used to predict IOP based on the vibration factor.

Quantitative Wear Estimation for Floating Structures by Using 3-D Geometry of Mooring Chain

2020 ◽  
Author(s):  
Takaaki Takeuchi ◽  
Tomoaki Utsunomiya ◽  
Koji Gotoh ◽  
Iku Sato
Keyword(s):  
Estimation Method ◽  
Maintenance Cost ◽  
Offshore Wind Turbine ◽  
Response Analysis ◽  
Chain Model ◽  
Contact Method ◽  
Spring Model ◽  
Mass Spring Model ◽  
Mass Spring ◽  
Mooring Chain

Abstract For reducing the maintenance cost of floating offshore wind turbine structures, it is necessary to establish a quantitative wear estimation method for the mooring chains. In this paper, attempts have been made to improve the accuracy of the estimation method in terms of the mooring chain model. These investigations were performed about a spar-type floater moored with three catenary mooring lines at Goto, Nagasaki prefecture, Japan. Up to now, the mass-spring model had been used for the mooring chain in response analysis and the relative angle between two spring lines was considered as only a sliding angle without friction. However, there is also rolling in the motion between mooring links, which should cause less wear than by sliding. In this study, the detailed motion of the link in response analysis is calculated and applied to the wear estimation by using a 3-D model in MSC. Adams. This enables the wear estimation considering link motion closer to a real phenomenon. A Contact analysis between the 3-D chain model requires some contact properties (e.g. contact stiffness and friction). In this paper, these properties are calculated based on the Hertzian contact method and FEM analysis. As a result, the wear amounts overestimated by using the mass-spring model in the previous investigation, especially at the point located clump weight and touchdown point, decrease getting closer to the measurements. In addition, by tracking the contact points it is found that the major motion caused between links is the rolling. For future works, there remains a need for further validation and the consideration of elasticity between mooring links, impressions caused by proof load test and the effect of corrosion.

CONDITION MONITORING OF OFF-HIGHWAY TRUCK TIRES AT SUNGUN COPPER MINE USING NEURAL NETWORKS / MONITOROWANIE STANU TECHNICZNEGO OPON W CIĘŻKICH POJAZDACH TERENOWYCH EKSPLOATOWANYCH W KOPALNI MIEDZI SUNGUN, PRZY UŻYCIU SIECI NEURONOWYCH

2013 ◽  
Vol 58 (4) ◽  
pp. 1133-1144 ◽  
Author(s):  
Amin Moniri Morad ◽  
Javad Sattarvand
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Unit Cost ◽  
Back Propagation ◽  
Maintenance Cost ◽  
Copper Mine ◽  
Sungun Copper Mine ◽  
Feed Forward Back Propagation ◽  
Truck Tires ◽  
Traditional Approaches

Abstract Maintenance cost of the equipment is one of the most important portions of the operating expenditures in mines; therefore, any change in the equipment productivity can lead to major changes in the unit cost of the production. This clearly shows the importance and necessity of using novel maintenance methods instead of traditional approaches, in order to reach the minimum sudden occurrence of the equipment failure. For instance, the tires are costly components in maintenance which should be regularly inspected and replaced among different axles. The paper investigates the current condition of equipment tires at Sungun Copper Mine and uses neural networks to estimate the wear of the tires. The Input parameters of the network composed of initial tread depth, time of inspection and consumed tread depth by the time of inspection. The output of the network is considered as the residual service time ratio of the tires. The network trained by the feed-forward back propagation learning algorithm. Results revealed a good coincidence between the real and estimated values as 96.6% of correlation coefficient. Hence, better decisions could be made about the tires to reduce the sudden failures and equipment breakdowns.

scholarly journals A Recursive Least Squares Method with Double-Parameter for Online Estimation of Electric Meter Errors

Energies ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 805 ◽  
Author(s):  
Xiangyu Kong ◽  
Yuying Ma ◽  
Xin Zhao ◽  
Ye Li ◽  
Yongxing Teng
Keyword(s):  
Least Squares ◽  
Estimation Method ◽  
Measured Data ◽  
Recursive Least Squares ◽  
Maintenance Cost ◽  
Parameter Method ◽  
Online Estimation ◽  
Light Load ◽  
Verification Methods ◽  
Line Loss

In view of the existing verification methods of electric meters, there are problems such as high maintenance cost, poor accuracy, and difficulty in full coverage, etc. Starting from the perspective of analyzing the large-scale measured data collected by user-side electric meters, an online estimation method for the operating error of electric meters was proposed, which uses the recursive least squares (RLS) and introduces a double-parameter method with dynamic forgetting factors λa and λb to track the meter parameters changes in real time. Firstly, the obtained measured data are preprocessed, and the abnormal data such as null data and light load data are eliminated by an appropriate clustering method, so as to screen out the measured data of the similar operational states of each user. Then equations relating the head electric meter in the substation and each users’ electric meter and line loss based on the law of conservation of electric energy are established. Afterwards, the recursive least squares algorithm with double-parameter is used to estimate the parameters of line loss and the electric meter error. Finally, the effects of double dynamic forgetting factors, double constant forgetting factors and single forgetting factor on the accuracy of estimated error of electric meter are discussed. Through the program-controlled load simulation system, the proposed method is verified with higher accuracy and practicality.

Dictionary learning and shift-invariant sparse coding denoising for CSEM data combined with CEEMD

Geophysics ◽  
2021 ◽  
pp. 1-52
Author(s):  
Guang Li ◽  
Zhushi He ◽  
Jing Tian Tang ◽  
Juzhi Deng ◽  
Xiaoqiong Liu ◽  
...  
Keyword(s):  
Dictionary Learning ◽  
Sparse Coding ◽  
Learning Algorithm ◽  
Signal To Noise Ratio ◽  
Estimation Method ◽  
Real Data ◽  
Ensemble Empirical Mode Decomposition ◽  
Baseline Drift ◽  
Mode Decomposition ◽  
Useful Signal

Controlled-source electromagnetic (CSEM) data recorded in industrialized areas are inevitably contaminated by strong cultural noise. Traditional noise attenuation methods are often ineffective for intricate aperiodic noise. To address the problem mentioned above, we propose a novel noise isolation method based on fast Fourier transform (FFT), complementary ensemble empirical mode decomposition (CEEMD) and shift-invariant sparse coding (SISC, an unsupervised machine learning algorithm under a data-driven framework). First, large powerline noise is accurately subtracted in the frequency domain. Then, the CEEMD based algorithm is used to correct the large baseline drift. Finally, taking advantage of the sparsity of periodic signals, SISC is applied to autonomously learn a feature atom (the useful signal with a length of one period) from the detrended signal and recover CSEM signal with high accuracy. We demonstrate the performance of the SISC by comparing with other three promising signal processing methods, including the mathematic morphology filtering (MMF), soft-threshold wavelet filtering, and K-SVD (another dictionary learning method) sparse decomposition. Experimental results illustrate that SISC provides the best performance. Robustness test results show that SISC can increase the signal-to-noise ratio (SNR) of noisy signal from 0 dB to more than 15 dB. Case studies of synthetic and real data collected in the Chinese Provinces Sichuan and Yunnan show that the proposed method is capable of effectively recovering the useful signal from the observed data contaminated with different kinds of strong ambient noise. The curves of U/I and apparent resistivity after applying the proposed method improved greatly. Moreover, the proposed method performs better than the robust estimation method based on correlation analysis.

Quantitative Wear Estimation for Mooring Chain of Floating Structures and its Validation

2019 ◽  
Author(s):  
Takaaki Takeuchi ◽  
Tomoaki Utsunomiya ◽  
Koji Gotoh ◽  
Iku Sato
Keyword(s):  
Estimation Method ◽  
Offshore Wind ◽  
Floating Body ◽  
Maintenance Cost ◽  
Offshore Wind Turbine ◽  
Lumped Mass ◽  
Sliding Angle ◽  
Mass Model ◽  
Element Analysis ◽  
Mooring Chain

Abstract For reducing maintenance cost of floating offshore wind turbine structures, it is necessary to establish quantitative wear estimation method for the mooring chains. In this paper, attempts have been made to improve the accuracy and applicability of the estimation method in the following steps. By using the wear analysis method between the links of mooring chain that Gotoh et al. investigated with the finite element analysis software (MSC. Marc), the expression of the wear amount was obtained, which was a proportional functional form associated with sliding angle and tension. The relative sliding angle and tension between links were analyzed by using a multibody dynamics software (MSC. Adams). A spar-type floater moored with three catenary mooring lines at Goto, Nagasaki prefecture, Japan was analyzed. Here, the floating body was modelled as a rigid body and mooring chains were modelled by mass-spring (lumped mass) model. From these results, the wear amounts calculated by using the estimation formula and relative sliding angle and tension between links were compared with the measured wear amounts for mooring chain of the floater which was deployed for about one-year at Goto. The cases with only waves and those with wind and waves were analyzed. From the comparison between the simulation results and the measured ones, it was found that the proposed method can fairly predict the wear amount of mooring chains. However, it was also found that the proposed method has a tendency to overestimate the measured results. These reasons were discussed in the paper.

scholarly journals Developing a Travel Time Estimation Method of Freeway Based on Floating Car Using Random Forests

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Juan Cheng ◽  
Gen Li ◽  
Xianhua Chen
Keyword(s):  
Travel Time ◽  
Traffic Flow ◽  
Random Forests ◽  
Polynomial Regression ◽  
Learning Algorithm ◽  
Estimation Method ◽  
Time Estimation ◽  
Variable Importance ◽  
Estimation Accuracy ◽  
Travel Time Estimation

Travel time of traffic flow is the basis of traffic guidance. To improve the estimation accuracy, a travel time estimation model based on Random Forests is proposed. 7 influence variables are viewed as candidates in this paper. Data obtained from VISSIM simulation are used to verify the model. Different from other machine learning algorithm as black boxes, Random Forests can provide interpretable results through variable importance. The result of variable importance shows that mean travel time of floating car t-f, traffic state parameter X, density of vehicle Kall, and median travel time of floating car tmenf are important variables affecting travel time of traffic flow; meanwhile other variables also have a certain influence on travel time. Compared with the BP (Back Propagation) neural network model and the quadratic polynomial regression model, the proposed Random Forests model is more accurate, and the variables contained in the model are more abundant.

Sign in / Sign up

Export Citation Format

Share Document