ali ghorbanian

Increasing the accuracy of time-series clustering while reducing execution time is a primary challenge in the field of time-series clustering. Researchers have recently applied approaches, such as the development of distance metrics and dimensionality reduction, to address this challenge. However, using segmentation and ensemble clustering to solve this issue is a key aspect that has received less attention in previous research. In this study, an algorithm based on the selection and combination of the best segments created from a time-series dataset was developed. In the first step, the dataset was divided into segments of equal lengths. In the second step, each segment is clustered using a hierarchical clustering algorithm. In the third step, a genetic algorithm selects different segments and combines them using combinatorial clustering. The resulting clustering of the selected segments was selected as the final dataset clustering. At this stage, an internal clustering criterion evaluates and sorts the produced solutions. The proposed algorithm was executed on 82 different datasets in 10 repetitions. The results of the algorithm indicated an increase in the clustering efficiency of 3.07%, reaching a value of 67.40. The obtained results were evaluated based on the length of the time series and the type of dataset. In addition, the results were assessed using statistical tests with the six algorithms existing in the literature.

In time series clustering, features are typically extracted from the time series data and used for clustering instead of directly clustering the data. However, using the same set of features for all data sets may not be effective. To overcome this limitation, this study proposes a five-step algorithm that extracts a complete set of features for each data set, including both direct and indirect features. The algorithm then selects essential features for clustering using a genetic algorithm and internal clustering criteria. The final clustering is performed using a hierarchical clustering algorithm and the selected features. Results from applying the algorithm to 81 data sets indicate an average Rand index of 72.16%, with 38 of the 78 extracted features, on average, being selected for clustering. Statistical tests comparing this algorithm to four others in the literature confirm its effectiveness.

Parametric models are considered the widespread methods for time series forecasting. Non-parametric or machine learning methods have significantly replaced statistical methods in recent years. In this study, we develop a novel two-level clustering algorithm to forecast short-length time series datasets using a multi-step approach, including clustering, sliding window, and MLP neural network. In first-level clustering, the time series dataset in the training part is clustered. Then, we made a long time series by concatenating the existing time series in each cluster in the first level. After that, using a sliding window, every long-time series created in the previous step is restructured to equal-size sub-series and clustered in the second level. Applying an MLP network, a model has been fitted to final clusters. Finally, the test data distance is calculated with the center of the final cluster, selecting the nearest distance, and using the fitted model in that cluster, the final forecasting is done. Using the WAPE index, we compare the one-level clustering algorithm in the literature regarding the mean of answers and the best answer in a ten-time run. The results reveal that the algorithm could increase the WAPE index value in terms of the mean and the best solution by 8.78% and 5.24%, respectively. Also, comparing the standard deviation of different runs shows that the proposed algorithm could be further stabilized with a 3.24 decline in this index. This novel study proposed a two-level clustering for forecasting short-length time series datasets, improving the accuracy and stability of time series forecasting.

In this research, the effect of different parameters in Friction Stir Processing (FSP) on hardness and wear resistance of Al2024 is investigated. For this reason, five levels are considered for the three main parameters including pin rotating speed, pin traveling speedand pin angle using response surface methodology. The maximum hardeness and minimum wear rates are considered as the responses for optimization. For evaluating the hardness (under the 300 gr loading) and wear behaviour of processed samples (under the 500 gr loading and 1000m sliding distance), ASTM -E384 standard micro-vikers hardness tests and ASTM-G99 standard pin on disk tests are used, respectively. For investigating the FSP effect on micro-structure, grain size and morphology, optical microscopy is used. The results show that pin rotating speed and traveling speed have directly effect on the average hardness and also have a second power index relation on it. Furthermore it is obvious that these two parameters have interaction on each other and able to study them separately. Pin angle parameter had not any effect on the average hardness approximately and also no interaction by other two parameters. After optimizing process, the optimized values for pin rotating speed, pin traveling speed and pin angle for the Al-2024 were 28mm/min, 1274 rpm and 2.5 degree, respectively. Hardness value and weight reduction in wear test for processed case in optimized case were 154 vikers and 9.3mg.

In this study, a multi-state degraded system is studied, where status of system is degrading over time continuously. As time progresses, system may either deteriorate gradually and go to lower performance state or it may fail suddenly. If the system fails, some repairs are carried out to restore the system to the previous state. When the inspections revealed that the system has reached its last acceptable state, a PM is carried out to restore the system to the higher performance states. The goal is to find the optimal PM level so that the mean availability of the system is maximized and the total cost of the system is minimized. In this regard, Markov process is employed to represent different states of system. An integrated optimization approach is also suggested based on the desirability function statistical approach. The suggested aggregation method is robust to the potential dependency between the total cost and the mean availability. It also ensures that both objective functions fall in decision maker’s acceptable region. In order to show the efficiency of the proposed approach, a numerical example is presented and analyzed.