• Journal of Digital Convergence
• /
• v.17 no.5
• /
• pp.217-223
• /
• 2019

A study in predicting defects of spot welding in real time in automotive field is essential for cost reduction and high quality production. Welding quality is determined by shear strength and the size of the nugget, and results depend on different independent variables. In order to develop the real-time prediction system, multiple regression analyses were conducted and the two dependent variables were obtained with sufficient statistical results with three independent variables, however, the quality prediction by the regression formula could not ensure accuracy. In this study, a multi-layer neural network circuit was constructed. The neural network by 10 dynamic resistance variables was constructed with three hidden layers to obtain execution functions and weighting matrix. In this case, the neural network was established with three independent variables based on regression analysis, as there could be difficulties in real-time control due to too many input variables. As a result, all test data were divided into poor, partial, and modalities. Therefore, a real-time welding quality determination system by three independent variables obtained by multiple regression analysis was completed.

• New & Renewable Energy
• /
• v.10 no.2
• /
• pp.19-28
• /
• 2014

Wind power generation of 5 MW wind turbine was predicted by using wind measurement data from HeMOSU-1 which is at south west coast of Korea. Time histories of turbulent wind was generated from 10-min mean wind speed and then they were used as input to Bladed to estimated electric power. Those estimated powers are used in both polynominal regression and neural network training. They were compared with each other for daily production and yearly production. Effect of mean wind speed and turbulence intensity were quantitatively analyzed and discussed. This technique further can be used to assess lifetime power of wind turbine.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1193-1215
• /
• 2021

The measurement of the key product quality index plays an important role in improving the production efficiency and ensuring the safety of the enterprise. Since the actual working conditions and parameters will inevitably change to some extent with time, such as drift of working point, wear of equipment and temperature change, etc., these will lead to the degradation of the quality variable prediction model. To deal with this problem, the selective integrated moving windows based principal component regression (SIMV-PCR) is proposed in this study. In the algorithm of traditional moving window, only the latest local process information is used, and the global process information will not be enough. In order to make full use of the process information contained in the past windows, a set of local models with differences are selected through hypothesis testing theory. The significance levels of both T - test and χ² - test are used to judge whether there is identity between two local models. Then the models are integrated by Bayesian quality estimation to improve the accuracy of quality variable prediction. The effectiveness of the proposed adaptive soft measurement method is verified by a numerical example and a practical industrial process.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.330-334
• /
• 2022

In light of the decreasing crop production and shortage of food across the world, one of the crucial criteria of agriculture nowadays is selecting the right crop for the right piece of land at the right time. First problem is that How Farmers can predict the right crop for cultivation because famers have no knowledge about prediction of crop. Second problem is that which algorithm is best that provide the maximum accuracy for crop prediction. Therefore, in this research Author proposed a method that would help to select the most suitable crop(s) for a specific land based on the analysis of the affecting parameters (Temperature, Humidity, Soil Moisture) using machine learning. In this work, the author implemented Random Forest Classifier, Support Vector Machine, k-Nearest Neighbor, and Decision Tree for crop selection. The author trained these algorithms with the training dataset and later these algorithms were tested with the test dataset. The author compared the performances of all the tested methods to arrive at the best outcome. In this way best algorithm from the mention above is selected for crop prediction.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.3
• /
• pp.125-132
• /
• 2023

In this study, we compared the performance of machine learning models for predicting Vapor Pressure Deficits (VPD) in greenhouses that affect pore function and photosynthesis as well as plant growth due to nutrient absorption of plants. For VPD prediction, the correlation between the environmental elements in and outside the greenhouse and the temporal elements of the time series data was confirmed, and how the highly correlated elements affect VPD was confirmed. Before analyzing the performance of the prediction model, the amount and interval of analysis time series data (1 day, 3 days, 7 days) and interval (20 minutes, 1 hour) were checked to adjust the amount and interval of data. Finally, four machine learning prediction models (XGB Regressor, LGBM Regressor, Random Forest Regressor, etc.) were applied to compare the prediction performance by model. As a result of the prediction of the model, when data of 1 day at 20 minute intervals were used, the highest prediction performance was 0.008 for MAE and 0.011 for RMSE in LGBM. In addition, it was confirmed that the factor that most influences VPD prediction after 20 minutes was VPD (VPD_y__71) from the past 20 minutes rather than environmental factors. Using the results of this study, it is possible to increase crop productivity through VPD prediction, condensation of greenhouses, and prevention of disease occurrence. In the future, it can be used not only in predicting environmental data of greenhouses, but also in various fields such as production prediction and smart farm control models.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.177-190
• /
• 2021

Due to the development of the fourth industrial revolution technology, efforts are being made to improve areas that humans cannot handle by utilizing artificial intelligence techniques such as machine learning. Although on-demand production companies also want to reduce corporate risks such as delays in delivery by predicting total production time for orders, they are having difficulty predicting this because the total production time is all different for each order. The Theory of Constraints (TOC) theory was developed to find the least efficient areas to increase order throughput and reduce order total cost, but failed to provide a forecast of total production time. Order production varies from order to order due to various customer needs, so the total production time of individual orders can be measured postmortem, but it is difficult to predict in advance. The total measured production time of existing orders is also different, which has limitations that cannot be used as standard time. As a result, experienced managers rely on persimmons rather than on the use of the system, while inexperienced managers use simple management indicators (e.g., 60 days total production time for raw materials, 90 days total production time for steel plates, etc.). Too fast work instructions based on imperfections or indicators cause congestion, which leads to productivity degradation, and too late leads to increased production costs or failure to meet delivery dates due to emergency processing. Failure to meet the deadline will result in compensation for delayed compensation or adversely affect business and collection sectors. In this study, to address these problems, an entity that operates an order production system seeks to find a machine learning model that estimates the total production time of new orders. It uses orders, production, and process performance for materials used for machine learning. We compared and analyzed OLS, GLM Gamma, Extra Trees, and Random Forest algorithms as the best algorithms for estimating total production time and present the results.

• Agribusiness and Information Management
• /
• v.6 no.2
• /
• pp.32-39
• /
• 2014

The goal of this research was to develop a portable system that could be used to evaluate the quality of milk in real time at a raw milk production site. A real-time portable quality evaluation system for raw milk was developed to enable non-destructive quality evaluation of somatic cell count (SCC), fat, protein, lactose, and total solid (TS) in milk samples. A prediction model of SCC, fat, protein, lactose, and TS was constructed using partial least squares (PLS) and 200 milk samples were used to evaluate the prediction performance of the portable quality evaluation system and high performance spectroscopy. Through prediction model development and verification, it was found that the accuracy of high performance spectroscopy was 90% for SSC, 96% for fat, 96% for protein, 91% for lactose, and 97% for TS. In comparison, the accuracy of the portable quality evaluation system was relatively low, at 90% for SSC, 95% for fat, 92% for protein, 89% for lactose, 92% for TS. However, the measurement time for high performance spectroscopy was 10 minutes for 1 sample, while for the portable quality evaluation system it was 6 minutes. This means that the high performance spectroscopy system can measure 48 samples per day (8 hours), while the portable quality evaluation system can measure 80 (8 hours). Therefore, it was found that the portable quality evaluation system enables quick on-site quality evaluation of milk samples.

• Animal Bioscience
• /
• v.37 no.5
• /
• pp.944-951
• /
• 2024

Objective: Parturition is crucial for dams, their calves, and cow managers. The prediction of calving time, which assists cow managers to decide on the relocation of cows to maternity pens and necessity of human supervision, is a pivotal aspect of livestock farming. However, existing methods of predicting calving time in dairy cows based on hormonal changes and clinical symptoms are time-consuming and yield unreliable predictions. Accordingly, we investigated whether heart rate variability (HRV) which is a non-invasive assessment of autonomic nervous system (ANS) activity and behavior during the prepartum period would be useful for predicting calving time in dairy cows. Methods: Eight pregnant cows were surveilled under electrocardiogram and video recordings for HRV and behavioral analyses, respectively. HRV parameters in time and frequency domains were evaluated. A 24-h time budget was calculated for each of six types of behavior (standing and lying with or without rumination, sleeping, and eating). Results: Heart rate on calving day is considerably higher than those recorded on the days preceding calving. Low frequency power declined, whereas high frequency power escalated on the calving day compared to the period between 24 and 48 h before calving. The time budget for ruminating while lying decreased and that while standing increased markedly on the calving day compared to those allocated on the preceding days; nonetheless, the total time budget for ruminating did not differ during the prepartum period. Conclusion: We elucidated the ANS activity and behavioral profiles during prepartum period. Our results confirm that HRV parameters and behavior are useful for predicting calving time, and interestingly indicate that the time budget for ruminating while standing (or lying) may serve as a valuable predictor of calving. Collectively, our findings lay the foundation for future investigations to determine other potential predictors and formulate an algorithm for predicting calving time.

• Applied Chemistry for Engineering
• /
• v.31 no.5
• /
• pp.520-525
• /
• 2020

In this study, we developed a machine learning-based model for predicting the production stage temperature of distillation process. It is necessary to predict an accurate temperature for control because the control of the distillation process is done through the production stage temperature. The temperature in distillation process has a nonlinear complex relationship with other variables and time series data, so we used the recurrent neural network algorithms to predict temperature. In the model development process, by adjusting three recurrent neural network based algorithms, and batch size, we selected the most appropriate model for predicting the production stage temperature. LSTM₁₂₈ was selected as the most appropriate model for predicting the production stage temperature. The prediction performance of selected model for the actual temperature is RMSE of 0.0791 and R² of 0.924.

• Asian-Australasian Journal of Animal Sciences
• /
• v.12 no.4
• /
• pp.511-514
• /
• 1999

Data pertaining to 1111 first lactation performance record of Karan Fries (Holstein-Friesian $\times$ Zebu) cows spread over a period of 21 years and sired by 72 bulls were used to examine the efficiency of sire indices for lactation milk production using auxiliary traits. First lactation length, first service period, first calving interval, first dry period and age at first calving were considered as auxiliary traits. The efficiency of this method was compared with simple daughter average index (D), contemporary comparison method (CC), least-square method (LSQ), simplified regressed least-squares method (SRLS) and best linear unbiased prediction (BLUP) for lactation milk production. The relative efficiency of sire evaluation methods using one auxiliary trait was lower (24.2-32.8%) in comparison to CC method, the most efficient method observed in this study. Use of two auxiliary traits at a time did not further improve the efficiency. The auxiliary sire indices discriminate better among bulls as the range of breeding values were higher in these methods in comparison to conventional sire evaluation methods. The rank correlation between breeding values estimated using auxiliary traits were high (0.77-0.78) with CC method. The rank correlation among auxiliary sire indices ranged from 0.98 to 0.99, indicating similar ranking of sire for breeding values of milk production in all the auxiliary sire indices.