• Title/Summary/Keyword: Robust Term

Search Result 277, Processing Time 0.028 seconds

Continuation-Based Quasi-Steady-State Analysis Incorporating Multiplicative Load Restoration Model (증배형 부하회복 모델을 포함하는 연속법 기반 준정적 해석)

  • Song, Hwa-Chang;Ajjarapu, Venkatanamana
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.14 no.2
    • /
    • pp.111-117
    • /
    • 2008
  • This paper presents a new continuation-based quasi-steady-state(CQSS) time-domain simulation algorithm incorporating a multiplicative aggregated load model for power systems. The authors' previous paper introduced a CQSS algorithm, which has the robust convergent characteristic near the singularity point due to the application of a continuation method. The previous CQSS algorithm implemented the load restoration in power systems using the exponent-based load recovery model that is derived from the additive dynamic load model. However, the reformulated exponent-based model causes the inappropriate variation of short-term load characteristics when switching actions occur, during time-domain simulation. This paper depicts how to incorporate a multiplicative load restoration model, which does not have the problem of deforming short-term load characteristics, into the time simulation algorithm, and shows an illustrative example with a 39-bus test system.

A robust collision prediction and detection method based on neural network for autonomous delivery robots

  • Seonghun Seo;Hoon Jung
    • ETRI Journal
    • /
    • v.45 no.2
    • /
    • pp.329-337
    • /
    • 2023
  • For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

MARGIN-BASED GENERALIZATION FOR CLASSIFICATIONS WITH INPUT NOISE

  • Choe, Hi Jun;Koh, Hayeong;Lee, Jimin
    • Journal of the Korean Mathematical Society
    • /
    • v.59 no.2
    • /
    • pp.217-233
    • /
    • 2022
  • Although machine learning shows state-of-the-art performance in a variety of fields, it is short a theoretical understanding of how machine learning works. Recently, theoretical approaches are actively being studied, and there are results for one of them, margin and its distribution. In this paper, especially we focused on the role of margin in the perturbations of inputs and parameters. We show a generalization bound for two cases, a linear model for binary classification and neural networks for multi-classification, when the inputs have normal distributed random noises. The additional generalization term caused by random noises is related to margin and exponentially inversely proportional to the noise level for binary classification. And in neural networks, the additional generalization term depends on (input dimension) × (norms of input and weights). For these results, we used the PAC-Bayesian framework. This paper is considering random noises and margin together, and it will be helpful to a better understanding of model sensitivity and the construction of robust generalization.

Ultralow Intensity Noise Pulse Train from an All-fiber Nonlinear Amplifying Loop Mirror-based Femtosecond Laser

  • Dohyeon Kwon;Dohyun Kim
    • Current Optics and Photonics
    • /
    • v.7 no.6
    • /
    • pp.708-713
    • /
    • 2023
  • A robust all-fiber nonlinear amplifying loop-mirror-based mode-locked femtosecond laser is demonstrated. Power-dependent nonlinear phase shift in a Sagnac loop enables stable and power-efficient mode-locking working as an artificial saturable absorber. The pump power is adjusted to achieve the lowest intensity noise for stable long-term operation. The minimum pump power for mode-locking is 180 mW, and the optimal pump power is 300 mW. The lowest integrated root-mean-square relative intensity noise of a free-running mode-locked laser is 0.009% [integration bandwidth: 1 Hz-10 MHz]. The long-term repetition-rate instability of a free-running mode-locked laser is 10-7 over 1,000 s averaging time. The repetition-rate phase noise scaled at 10-GHz carrier is -122 dBc/Hz at 10 kHz Fourier frequency. The demonstrated method can be applied as a seed source in high-precision real-time mid-infrared molecular spectroscopy.

Robust Tree Coding Combined with Harmonic Scaling of Speech at 4.8 Kbps (견실한 배음 축척과 결합된 4.8KBPS 트리 음성부호기)

  • 강상원;이인성;한경호
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.18 no.12
    • /
    • pp.1806-1814
    • /
    • 1993
  • Efficient speech coders using tree coding combined with harmonic scaling are designed at the rate of 4.8 kilobitts/sec (kbps). A time domain harmonic scaling algorithm (TDHS) is used to compress input speech by a factor of two. This process allows the tree coder have 1.5 bits/sample for 4.8 kbps in the case of a 6.4 kHz sampling rate. In the backward adaptive tree coder, there are three components of the code generator, including a hybrid adaptive quantizer, a short-term predictor and a pitch predictor. The robustness of the tree coder is achieved by carefully choosing the input of the short term predictor adaptation. Also, inclusion of a smoother in the pitch predictor improves the error performance of tree coder in the noisy channel. Subjectively, tree coding combined with TDHS provides good quality speech at 4.8 kbps.

  • PDF

Deep learning-based sensor fault detection using S-Long Short Term Memory Networks

  • Li, Lili;Liu, Gang;Zhang, Liangliang;Li, Qing
    • Structural Monitoring and Maintenance
    • /
    • v.5 no.1
    • /
    • pp.51-65
    • /
    • 2018
  • A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.

Nominal Price Anomaly in Emerging Markets: Risk or Mispricing?

  • HOANG, Lai Trung;PHAN, Trang Thu;TA, Linh Nhat
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.7 no.9
    • /
    • pp.125-134
    • /
    • 2020
  • This study examines the nominal price anomaly in the Vietnamese stock market, that is, whether stocks with low nominal price outperform stocks with high nominal price. Using a sample of all 351 companies listed on the Ho Chi Minh Stock Exchange (HOSE) from June 2009 to March 2018, we confirm our hypothesis and document that cheaper stocks yield higher subsequent abnormal returns. The results are robust after controlling for various stock characteristics that have been documented to be value-relevant in prior literature, including firm size, book-to-market ratio, intermediate-term momentum, short-term reversal, skewness, market risk, idiosyncratic risk, illiquidity and extreme daily returns, using both the portfolio analysis and the Fama-MacBeth cross-sectional regression. The negative effect persists in the long term (i.e., after up to 12 months), implying a slow adjustment of stock prices to their intrinsic value. Further analysis show that the observed nominal price anomaly is mainly driven by mispricing but not a latent risk factor proxied by stock price, thus the observed anomaly reflects a mispricing but not a fundamental risk. The study highlights the irrational behaviour of investors and market inefficiency in the Vietnamese stock market and provides important implication for investors in the market.

Short-term Electric Load Forecasting for Summer Season using Temperature Data (기온 데이터를 이용한 하계 단기전력수요예측)

  • Koo, Bon-gil;Kim, Hyoung-su;Lee, Heung-seok;Park, Juneho
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.64 no.8
    • /
    • pp.1137-1144
    • /
    • 2015
  • Accurate and robust load forecasting model is very important in power system operation. In case of short-term electric load forecasting, its result is offered as an standard to decide a price of electricity and also can be used shaving peak. For this reason, various models have been developed to improve forecasting accuracy. In order to achieve accurate forecasting result for summer season, this paper proposes a forecasting model using corrected effective temperature based on Heat Index and CDH data as inputs. To do so, we establish polynomial that expressing relationship among CDH, load, temperature. After that, we estimate parameters that is multiplied to each of the terms using PSO algorithm. The forecasting results are compared to Holt-Winters and Artificial Neural Network. Proposing method shows more accurate by 1.018%, 0.269%, 0.132% than comparison groups, respectively.

A SE Approach for Machine Learning Prediction of the Response of an NPP Undergoing CEA Ejection Accident

  • Ditsietsi Malale;Aya Diab
    • Journal of the Korean Society of Systems Engineering
    • /
    • v.19 no.2
    • /
    • pp.18-31
    • /
    • 2023
  • Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

Extrapolation of extreme traffic load effects on bridges based on long-term SHM data

  • Xia, Y.X.;Ni, Y.Q.
    • Smart Structures and Systems
    • /
    • v.17 no.6
    • /
    • pp.995-1015
    • /
    • 2016
  • In the design and condition assessment of bridges, it is usually necessary to take into consideration the extreme conditions which are not expected to occur within a short time period and thus require an extrapolation from observations of limited duration. Long-term structural health monitoring (SHM) provides a rich database to evaluate the extreme conditions. This paper focuses on the extrapolation of extreme traffic load effects on bridges using long-term monitoring data of structural strain. The suspension Tsing Ma Bridge (TMB), which carries both highway and railway traffic and is instrumented with a long-term SHM system, is taken as a testbed for the present study. Two popular extreme value extrapolation methods: the block maxima approach and the peaks-over-threshold approach, are employed to extrapolate the extreme stresses induced by highway traffic and railway traffic, respectively. Characteristic values of the extreme stresses with a return period of 120 years (the design life of the bridge) obtained by the two methods are compared. It is found that the extrapolated extreme stresses are robust to the extrapolation technique. It may owe to the richness and good quality of the long-term strain data acquired. These characteristic extremes are also compared with the design values and found to be much smaller than the design values, indicating conservative design values of traffic loading and a safe traffic-loading condition of the bridge. The results of this study can be used as a reference for the design and condition assessment of similar bridges carrying heavy traffic, analogous to the TMB.