• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.727-732
• /
• 2007

Most of previous work on indexing and searching time series focused on the similarity matching and retrieval of one-attribute time series. However, multimedia databases such as music, video need to handle the similarity search in multi-attribute time series. The limitation of the current similarity models for multi-attribute sequences is that there is no consideration for attributes' sequences. The multi-attribute sequences are composed of several attributes' sequences. Since the users may want to find the similar patterns considering attributes's sequences, it is more appropriate to consider the similarity between two multi-attribute sequences in the viewpoint of attributes' sequences. In this paper, we propose the similarity search method based on attributes's sequences in multi-attribute time series databases. The proposed method can efficiently reduce the search space and guarantees no false dismissals. In addition, we give preliminary experimental results to show the effectiveness of the proposed method.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.2
• /
• pp.224-234
• /
• 2008

Multi-phase machines can be used in variable speed drives. Their applications include electric ship propulsion, 'more-electric aircraft' and traction applications, electric vehicles, and hybrid electric vehicles. Multi-phase machines enable independent control of a few numbers of machines that are connected in series in a particular manner with their supply being fed from a single voltage source inverter(VSI). The idea was first implemented for a five-phase series-connected two-motor drive system, but is now applicable to any number of phases more than or equal to five-phase. The number of series-connected machines is a function of the phase number of VSI. Theoretical and simulation studies have already been reported for number of multi-phase multi-motor drive configurations of series-connection type. Variable speed induction motor drives without mechanical speed sensors at the motor shaft have the attractions of low cost and high reliability. To replace the sensor, information concerning the rotor speed is extracted from measured stator currents and voltages at motor terminals. Open-loop estimators or closed-loop observers are used for this purpose. They differ with respect to accuracy, robustness, and sensitivity against model parameter variations. This paper analyses operation of an MRAS estimator based sensorless control of a vector controlled series-connected two-motor five-phase drive system with current control in the stationary reference frame. Results, obtained with fixed-voltage, fixed-frequency supply, and hysteresis current control are presented for various operating conditions on the basis of simulation results. The purpose of this paper is to report the first ever simulation results on a sensorless control of a five-phase two-motor series-connected drive system. The operating principle is given followed by a description of the sensorless technique.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.3
• /
• pp.493-499
• /
• 2017

This paper proposes a combined very-short-term and short-term multi-variate time-series model for 24 hour load forecasting. First, the best model for very-short-term and short-term load forecasting is selected by considering the least error value, and then they are combined by the optimal forecasting time. The actual load data of industry complex is used to show the effectiveness of the proposed model. As a result the load forecasting accuracy of the combined model has increased more than a single model for 24 hour load forecasting.

• Smart Structures and Systems
• /
• v.25 no.4
• /
• pp.423-432
• /
• 2020

In this paper, a novel but practical approach named series/parallel multi-sensing technique was proposed to evaluate the bolt looseness in a bolt group. The smart washers (SWs), which were fabricated by embedding a Lead Zirconate Titanate (PZT) transducer into two flat metal rings, were installed to the bolts group. By series connection of SWs, the impedance signals of different bolts can be obtained through only one sweep. Therefore, once the loosening occurred, the shift of different peak frequencies can be used to locate which bolt has loosened. The proposed multi input single output (MISO) damage detection scheme is very suitable for the structural health monitoring (SHM) of joint with a large number of bolts connection. Another notable contribution of this paper is the proposal of 3-dB bandwidth root mean square deviation (3 dB-RMSD) which can quantitatively evaluate the severity of bolt looseness. Compared with the traditional naked-eye observation method, the equivalent circuit based 3-dB bandwidth can accurately define the calculation range of RMSD. An experiment with three bolted connection specimens that installed the SWs was carried out to validate our proposed approach. Experimental result shows that the proposed 3 dB-RMSD based multi-sensing technique can not only identify the loosened bolt but also monitor the severity of bolt looseness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.201-207
• /
• 2023

In this paper, we propose an optimal model for mid to long-term price prediction of agricultural products using LGBM, MLP, LSTM, and GRU to compare and analyze the three strategies of the Multi-Step Time Series. The proposed model is designed to find the optimal combination between the models by selecting methods from various angles. Prior agricultural product price prediction studies have mainly adopted traditional econometric models such as ARIMA and LSTM-type models. In contrast, agricultural product price prediction studies related to Multi-Step Time Series were minimal. In this study, the experiment was conducted by dividing it into two periods according to the degree of volatility of agricultural product prices. As a result of the mid-to-long-term price prediction of three strategies, namely direct, hybrid, and multiple outputs, the hybrid approach showed relatively superior performance. This study academically and practically contributes to mid-to-long term daily price prediction by proposing an effective alternative.

• Journal of Mechanical Science and Technology
• /
• v.18 no.7
• /
• pp.1107-1120
• /
• 2004

This study proposes a new scheme for the sampled-data representation of nonlinear systems with time-delayed multi-input. The proposed scheme is based on the Taylor-series expansion and zero-order hold assumption. The mathematical structure of a new discretization scheme is explored. On the basis of this structure, the sampled-data representation of nonlinear systems including time-delay is derived. The new scheme is applied to nonlinear systems with two inputs and then the delayed multi-input general equation is derived. The resulting time-discretization provides a finite-dimensional representation of nonlinear control systems with time-delay enabling existing controller design techniques to be applied to them. In order to evaluate the tracking performance of the proposed scheme, an algorithm is tested for some of the examples including maneuvering of an automobile and a 2-DOF mechanical system.

• Proceedings of the KIEE Conference
• /
• 1996.07a
• /
• pp.585-587
• /
• 1996

A simple regenerative snubber structure is proposed, which is applicable to multi-level inverter with series-connected GTOs for high power applications. The novel snubber structure can solve large energy loss problems and guarantee safe operation of power converter can be achieved. The proposed new snubber has the potential of high performance and high reliability and is particularly suitable to high power and multi-level application with series connected power devices. The snubber voltage and current waveforms are analized and shown the simulation and experimental results for a GTO 3-level inverter circuit with inductive load.

• Journal of Mechanical Science and Technology
• /
• v.19 no.11
• /
• pp.1975-1987
• /
• 2005

An input time delay always exists in practical systems. Analysis of the delay phenomenon in a continuous-time domain is sophisticated. It is appropriate to obtain its corresponding discrete-time model for implementation via digital computers. In this paper a new scheme for the discretization of nonlinear systems using Taylor series expansion and the zero-order hold assumption is proposed. The mathematical structure of the new discretization method is analyzed. On the basis of this structure the sampled-data representation of nonlinear systems with time-delayed multi-input is presented. The delayed multi-input general equation has been derived. In particular, the effect of the time-discretization method on key properties of nonlinear control systems, such as equilibrium properties and asymptotic stability, is examined. Additionally, hybrid discretization schemes that result from a combination of the scaling and squaring technique (SST) with the Taylor series expansion are also proposed, especially under conditions of very low sampling rates. Practical issues associated with the selection of the method's parameters to meet CPU time and accuracy requirements, are examined as well. A performance of the proposed method is evaluated using a nonlinear system with time delay maneuvering an automobile.