Development of Prediction Model for Axle Torque of Agricultural Tractors

2020 ◽  
Vol 63 (6) ◽  
pp. 1773-1786 ◽  
Author(s):  
Wan-Soo Kim ◽  
Yeon-Soo Kim ◽  
Yong-Joo Kim
Keyword(s):  
Prediction Model ◽  
Prediction Models ◽  
Traction Force ◽  
Field Tests ◽  
Travel Speed ◽  
List Type ◽  
Slip Ratio ◽  
Agricultural Tractors ◽  
Torque Values ◽  
Agricultural Tractor

HighlightsA prediction model was developed for estimating the axle torque of an agricultural tractor.The model was developed by complementing and modifying a previously proposed traction equation.Compared to the actual axle torque, the proposed model attained MAPE of 2.1%, RMSE of 29 Nm, and RD of 2.7%.The model predicted axle torque more accurately than the traction force-based prediction model.Abstract. The tractor driving axle torque is an important factor in optimal transmission design and service life evaluation. Axle torque measurement sensor systems are very expensive, and traction force-based axle torque prediction models cannot accurately estimate the axle torque because they do not consider both the conditions of the tractor and the attached implement. Therefore, in this study, a prediction model was developed to estimate the axle torque of an agricultural tractor based on the traction force equation and motion resistance. A load measurement system was established to verify the developed prediction model, and actual field torque data were collected through field tests. The developed prediction model was verified by comparing the results of five reference prediction methods, including weight, engine-rated torque, and three traction equations (Wismer-Luth, ASABE Standard D497.4, and Brixius), using the measured axle torque. Performance evaluation was conducted based on the main variables, including travel speed, tillage depth, and slip ratio. The proposed prediction model was found to be closest to the 1:1 line at all travel speeds, tillage depths, and slip ratios, implying that it can best explain the measured torque values among all prediction models. Compared to the other prediction models, the proposed prediction model’s results under all variable conditions had an R2 of 0.65, MAPE of 2.1%, RMSE of 29 Nm, and RD of 2.7%, indicating excellent prediction of the measured torque. The results show that the developed prediction model can be applied to axle torque prediction by explaining the actual measured axle torque. Keywords: Agricultural tractor, Axle torque, Prediction model, Torque estimation, Traction force.

scholarly journals Estimation of the traction power of agricultural tractors from dynamometric tests

2018 ◽  
Vol 48 (4) ◽  
Author(s):  
Alexandre Russini ◽  
José Fernando Schlosser ◽  
Marcelo Silveira de Farias
Keyword(s):  
Correlation Analysis ◽  
Eddy Currents ◽  
Field Tests ◽  
Prediction Equations ◽  
Static Tests ◽  
Dynamic Field ◽  
Agricultural Tractors ◽  
Santa Maria ◽  
Agricultural Tractor ◽  
Traction Power

ABSTRACT: The objective of this research was to predict, from dynamometric tests, the traction performance of agricultural tractors, without the need to employ the standard official tests carried out on concrete tracks. The evaluations were conducted at the experimental area of the Universidade Federal de Santa Maria, where an instrumented agricultural tractor was subjected to dynamic field traction tests and static tests in the laboratory, using an eddy currents dynamometer. It can be verified through the correlation analysis between the values obtained and the estimated values that, based on the prediction equations, a high correlation (r² = 0.99) was obtained between the power observed in the field and the estimated power obtained using dynamometric tests. Based on the analysis of the results obtained in this study, it can be stated that the traction performance of an agricultural tractor can be estimated from dynamometric tests. We concluded that the dynamic field tests can be replaced by static tests carried out in laboratories, which are generally less expensive.

scholarly journals Development of a Prediction Model for Tractor Axle Torque during Tillage Operation

2020 ◽  
Vol 10 (12) ◽  
pp. 4195 ◽  
Author(s):  
Wan-Soo Kim ◽  
Yong-Joo Kim ◽  
Seung-Yun Baek ◽  
Seung-Min Baek ◽  
Yeon-Soo Kim ◽  
...  
Keyword(s):  
Prediction Model ◽  
Measurement System ◽  
Engine Speed ◽  
Prediction Models ◽  
Travel Speed ◽  
Percentage Error ◽  
Engine Torque ◽  
Load Measurement ◽  
Tillage Operation ◽  
Tillage Depth

In general, the tractor axle torque is used as an indicator for making various decisions when engineers perform transmission fatigue life analysis, optimal design, and accelerated life testing. Since the existing axle torque measurement method requires an expensive torque sensor, an alternative method is required. Therefore, the aim of this study is to develop a prediction model for the tractor axle torque during tillage operation that can replace expensive axle torque sensors. A prediction model was proposed through regression analysis using key variables affecting the tractor axle torque. The engine torque, engine speed, tillage depth, slip ratio, and travel speed were selected as explanatory variables. In order to collect explanatory and dependent variable data, a load measurement system was developed, and a field experiment was performed on moldboard plow tillage using a tractor with a load measurement system. A total of eight axle torque prediction regression models were proposed using the measured calibration dataset. The adjusted coefficient of determination (R2) of the proposed regression model showed a range of 0.271 to 0.925. Among them, the prediction model E showed an adjusted R2 of 0.925. All of the prediction models were verified using a validation set. All of the axle torque prediction models showed an mean absolute percentage error (MAPE) of less than 2.8%. In particular, Model E, adopting engine torque, engine speed, and travel speed as variables, and Model H, adopting engine torque, tillage depth and travel speed as variables, showed MAPEs of 1.19 and 1.30%, respectively. Therefore, it was found that the proposed prediction models are applicable to actual axle torque prediction.

scholarly journals Reducing the soil structure destruction along the rut and increasing the traction properties of the tractor by using the rear grouser of the track link

2021 ◽  
Vol 282 ◽  
pp. 07009
Author(s):  
V.N. Kozhanov ◽  
M.A. Rusanov ◽  
M.G. Shtyka ◽  
V.S. Kukhar
Keyword(s):  
Traction Force ◽  
Rolling Resistance ◽  
Resistance Coefficient ◽  
Support Surface ◽  
Horizontal Deformation ◽  
Tangential Traction ◽  
Soil Destruction ◽  
Agricultural Tractors ◽  
Agricultural Tractor ◽  
Traction Power

The traditionally used mixed grouser of the metal track link causes a decrease in the traction qualities of the agricultural tractor. The use of a rear grouser on the track link, in our opinion, will significantly improve the traction properties of an agricultural tractor with a metal track and reduce the soil destruction. When the rear grouser is immersed in the soil, an additional horizontal deformation of the soil occurs, which changes the law of horizontal deformation distribution along the support surface of the trackdrive, which ensures the alignment of the link shares in the implementation of the tangential traction force. This leads not only to a reduction in the trackdrive skidding, but also to a reduction in tractor rolling losses. Comparative tests of the T-4A tractor with a serial track, and a track on which links the front grousers were removed showed that the maximum traction power increases from 59 to 65 kW, the skidding with a hook load of 40 kN decreases from 14.6 to 9.4%, the rolling resistance coefficient decreases from 0.093 to 0.072, eliminates the “scissors” effect, which will reduce the number of erosive-dangerous particles in the track trace to 30...40%, which is 5.6...4.25 times less than in agricultural tractors with a mixed grouser, which confirms the effectiveness of their use.

scholarly journals Fuel consumption efficiency of an agricultural tractor equipped with continuously variable transmission

2017 ◽  
Vol 47 (6) ◽  
Author(s):  
Marcelo Silveira de Farias ◽  
José Fernando Schlosser ◽  
Pilar Linares ◽  
Juan Paulo Barbieri ◽  
Giácomo Müller Negri ◽  
...  
Keyword(s):  
Fuel Consumption ◽  
Standard Procedure ◽  
Traction Force ◽  
Travel Speed ◽  
Continuously Variable Transmission ◽  
Load Level ◽  
Production Costs ◽  
Variable Transmission ◽  
Agricultural Tractor ◽  
Consumption Efficiency

ABSTRACT: The correct choice of modern power transmissions can help farmers decrease production costs. The following research aimed to assess fuel consumption efficiency of an agricultural tractor equipped with continuously variable transmission, at different travel speed and load levels applied on the tractor drawbar. Standard procedure has been applied considering six load levels (30; 40; 50; 60; 70 and 80% of Q0) by means of breaking with a dynamometer car instrumented in a concrete test track, at three travel speeds (5.16; 7.29 and 10.48km h-1). Throughout the experiment, engine speed, traction force and hourly fuel consumption were monitored. The results indicated that there was an average increase of 2.67; 2.82; and 2.61L h-1 in the hourly fuel consumption for each 10% increase in the load level on the tractor, for travel speed of 5.16; 7.29 and 10.48km h-1, respectively. In general, the specific fuel consumption of the tractor decreased as the load levels and the travel speeds were increased.

scholarly journals Evaluation of new agricultural tractors engines by using a portable dynamometer

2016 ◽  
Vol 46 (5) ◽  
pp. 820-824 ◽  
Author(s):  
Marcelo Silveira de Farias ◽  
José Fernando Schlosser ◽  
Javier Solis Estrada ◽  
Ulisses Giacomini Frantz ◽  
Fabrício Azevedo Rodrigues
Keyword(s):  
Decision Making ◽  
Class Iii ◽  
Class V ◽  
Agricultural Engineering ◽  
Student Test ◽  
Agricultural Tractors ◽  
Torque Values ◽  
Agricultural Tractor ◽  
Class Iv ◽  
Engine Power

ABSTRACT: Official agricultural engineering testing aims to determine torque and power, which are important information for decision making when buying an agricultural tractor. In this research the torque and maximum power values provided by manufacturers with the dynamometer tests values, were compared. Forty new agricultural tractors commercialized in the brazilian market were used. Tractors were classified according to the power range in: Class I (less than or equal 22.1kW); Class II (between 22.1 and 51.5kW); Class III (51.5 and 73.5kW); Class IV (73.5 and 117.7kW); and Class V (117.7 and 183.9kW). Variables were analyzed with the statistic t-Student test (P≥0.05). Class IV tractors engines power is bigger in comparison to the values specified by manufacturers. As for Class III tractors engines, torque values observed were bigger when compared to the specified, while for Class V was presented smaller values. As conclusion, with respect to the maximum engine power, it was verified that 67.5% of the evaluated tractors meet the information provided by manufactures.

Investigation of the Performance of Different Cleaning Devices in Maize Grain Harvesters Based on Field Tests

2020 ◽  
Vol 63 (4) ◽  
pp. 809-821
Author(s):  
Lijun Wang ◽  
Yongtao Yu ◽  
Yang Ma ◽  
Xin Feng ◽  
Tianhua Liu
Keyword(s):  
Field Tests ◽  
Travel Speed ◽  
List Type ◽  
Plant Spacing ◽  
Harvest Time ◽  
Maize Varieties ◽  
Common Scale ◽  
Reclamation Area ◽  
The Common ◽  
Maize Grain

HighlightsThe effects of different factors on the performance of cleaning devices are investigated.The loss percentage is negatively correlated to the moisture content of maize grain.The cleaning performance is affected by the plant spacing and the ear mass of maize.The long-toothed scale screen has the best performance in throwing impurities.Abstract. The direct harvest of maize grain achieves high working efficiencies and low harvest costs; thus, direct harvest will become increasingly common for harvesting maize in the future. To investigate the loss percentage of maize grain (LPOMG) and the impurity percentage of maize grain (IPOMG) for harvesting in the northeast reclamation area in China, field tests were completed with various moisture contents of maize grain (MCOMGs), maize varieties, types of cleaning screens, and travel speeds of the harvesters. The results showed that the LPOMG of Xianda 205 maize with an MCOMG of 30.49% was the lowest at 0.37% and the IPOMG of Xianda 205 maize with an MCOMG of 22.62% was the lowest at 0.14% when the maize mixture was cleaned with the common scale screen in the S660 harvester. The LPOMG of Hayu 189 maize was the lowest at 0.19% when using the S660 harvester at a travel speed of 1.0 m s-1, and the IPOMG of Xianda 205 maize was the lowest at 0.28% when using the S660 harvester at a travel speed of 2.0 m s-1; the different varieties of maize mixtures were cleaned with the common scale screen. The LPOMG of Xianda 205 maize cleaned with the stepped woven screen was the lowest at 0.25% when using the GK100 harvester at a travel speed of 1.0 m s-1, and the IPOMG of Xianda 205 maize cleaned with the long-toothed scale screen was the lowest at 0.10% when using the 7088 harvester at a travel speed of 2.0 m s-1. This study provides a reference for selecting a suitable maize variety, type of screen, and the earliest harvest time for direct harvesting of maize grain. Keywords: Cleaning, Field test, Harvesting maize, Impurity, Loss.

scholarly journals Early prediction of high risk gestational diabetes mellitus via machine learning models

2020 ◽  
Author(s):  
Yan-Ting Wu ◽  
Chen-Jie Zhang ◽  
Ben Willem Mol ◽  
Cheng Li ◽  
Lei Chen ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Gestational Diabetes ◽  
Prediction Model ◽  
Early Pregnancy ◽  
Prediction Models ◽  
List Type ◽  
Discriminative Power ◽  
Learning Models ◽  
Machine Learning Models

AbstractAimsGestational diabetes mellitus (GDM) is a pregnancy-specific disorder that can usually be diagnosed after 24 gestational weeks. So far, there is no accurate method to predict GDM in early pregnancy.MethodsWe collected data extracted from the hospital’s electronic medical record system included 73 features in the first trimester. We also recorded the occurrence of GDM, diagnosed at 24-28 weeks of pregnancy. We conducted a feature selection method to select a panel of most discriminative features. We then developed advanced machine learning models, using Deep Neural Network (DNN), Support Vector Machine (SVM), K-Nearest Neighboring (KNN), and Logistic Regression (LR), based on these features.ResultsWe studied 16,819 women (2,696 GDM) and 14,992 women (1,837 GDM) for the training and validation group. DNN, SVM, KNN, and LR models based on the 73-feature set demonstrated the best discriminative power with corresponding area under the curve (AUC) values of 0.92 (95%CI 0.91, 0.93), 0.82 (95%CI 0.81, 0.83), 0.63 (95%CI 0.62, 0.64), and 0.85 (95%CI 0.84, 0.85), respectively. The 7-feature (selected from the 73-feature set) DNN, SVM, KNN, and LR models had the best discriminative power with corresponding AUCs of 0.84 (95%CI 0.83, 0.84), 0.69 (95%CI 0.68, 0.70), 0.68 (95%CI 0.67, 0.69), and 0.84 (95% CI 0.83, 0.85), respectively. The 7-feature LR model had the best Hosmer-Lemeshow test outcome. Notably, the AUCs of the existing prediction models did not exceed 0.75.ConclusionsOur feature selection and machine learning models showed superior predictive power in early GDM detection than previous methods; these improved models will better serve clinical practices in preventing GDM.Research in Context sectionEvidence before this studyA hysteretic diagnosis of GDM in the 3rd trimester is too late to prevent exposure of the embryos or fetuses to an intrauterine hyperglycemia environment during early pregnancy.Prediction models for gestational diabetes are not uncommon in previous literature reports, but laboratory indicators are rarely involved in predictive indicators.The penetration of AI into the medical field makes us want to introduce it into GDM predictive models.What is the key question?Whether the GDM prediction model established by machine learning has the ability to surpass the traditional LR model?Added value of this studyUsing machine learning to select features is an effective method.DNN prediction model have effective discrimination power for predicting GDM in early pregnancy, but it cannot completely replace LR. KNN and SVM are even worse than LR in this study.Implications of all the available evidenceThe biggest significance of our research is not only to build a prediction model that surpasses previous ones, but also to demonstrate the advantages and disadvantages of different machine learning methods through a practical case.

Bioactivity Prediction Based on Matched Molecular Pair and Matched Molecular Series Methods

2020 ◽  
Vol 26 (33) ◽  
pp. 4195-4205
Author(s):  
Xiaoyu Ding ◽  
Chen Cui ◽  
Dingyan Wang ◽  
Jihui Zhao ◽  
Mingyue Zheng ◽  
...  
Keyword(s):  
Prediction Model ◽  
Large Scale ◽  
Prediction Models ◽  
Predictive Accuracy ◽  
Lead Optimization ◽  
Consensus Method ◽  
Molecular Pair ◽  
Bioactivity Prediction ◽  
Compound Synthesis ◽  
Consensus Modeling

Background: Enhancing a compound’s biological activity is the central task for lead optimization in small molecules drug discovery. However, it is laborious to perform many iterative rounds of compound synthesis and bioactivity tests. To address the issue, it is highly demanding to develop high quality in silico bioactivity prediction approaches, to prioritize such more active compound derivatives and reduce the trial-and-error process. Methods: Two kinds of bioactivity prediction models based on a large-scale structure-activity relationship (SAR) database were constructed. The first one is based on the similarity of substituents and realized by matched molecular pair analysis, including SA, SA_BR, SR, and SR_BR. The second one is based on SAR transferability and realized by matched molecular series analysis, including Single MMS pair, Full MMS series, and Multi single MMS pairs. Moreover, we also defined the application domain of models by using the distance-based threshold. Results: Among seven individual models, Multi single MMS pairs bioactivity prediction model showed the best performance (R2 = 0.828, MAE = 0.406, RMSE = 0.591), and the baseline model (SA) produced the most lower prediction accuracy (R2 = 0.798, MAE = 0.446, RMSE = 0.637). The predictive accuracy could further be improved by consensus modeling (R2 = 0.842, MAE = 0.397 and RMSE = 0.563). Conclusion: An accurate prediction model for bioactivity was built with a consensus method, which was superior to all individual models. Our model should be a valuable tool for lead optimization.

Fire modelling in Tasmanian buttongrass moorlands. III. Dead fuel moisture

2001 ◽  
Vol 10 (2) ◽  
pp. 241 ◽  
Author(s):  
Jon B. Marsden-Smedley ◽  
Wendy R. Catchpole
Keyword(s):  
Prediction Model ◽  
Regression Model ◽  
Fire Management ◽  
Prediction Models ◽  
Dew Point ◽  
Seasonal Effects ◽  
Experimental Program ◽  
Fuel Moisture ◽  
Fire Behaviour ◽  
Fire Modelling

An experimental program was carried out in Tasmanian buttongrass moorlands to develop fire behaviour prediction models for improving fire management. This paper describes the results of the fuel moisture modelling section of this project. A range of previously developed fuel moisture prediction models are examined and three empirical dead fuel moisture prediction models are developed. McArthur’s grassland fuel moisture model gave equally good predictions as a linear regression model using humidity and dew-point temperature. The regression model was preferred as a prediction model as it is inherently more robust. A prediction model based on hazard sticks was found to have strong seasonal effects which need further investigation before hazard sticks can be used operationally.

scholarly journals A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 285
Author(s):  
Kwok Tai Chui ◽  
Brij B. Gupta ◽  
Pandian Vasant
Keyword(s):  
Genetic Algorithm ◽  
Feature Extraction ◽  
Prediction Model ◽  
Prediction Models ◽  
Remaining Useful Life ◽  
Prediction Algorithm ◽  
Short Term ◽  
Turbofan Engine ◽  
Term Prediction ◽  
Useful Life

Understanding the remaining useful life (RUL) of equipment is crucial for optimal predictive maintenance (PdM). This addresses the issues of equipment downtime and unnecessary maintenance checks in run-to-failure maintenance and preventive maintenance. Both feature extraction and prediction algorithm have played crucial roles on the performance of RUL prediction models. A benchmark dataset, namely Turbofan Engine Degradation Simulation Dataset, was selected for performance analysis and evaluation. The proposal of the combination of complete ensemble empirical mode decomposition and wavelet packet transform for feature extraction could reduce the average root-mean-square error (RMSE) by 5.14–27.15% compared with six approaches. When it comes to the prediction algorithm, the results of the RUL prediction model could be that the equipment needs to be repaired or replaced within a shorter or a longer period of time. Incorporating this characteristic could enhance the performance of the RUL prediction model. In this paper, we have proposed the RUL prediction algorithm in combination with recurrent neural network (RNN) and long short-term memory (LSTM). The former takes the advantages of short-term prediction whereas the latter manages better in long-term prediction. The weights to combine RNN and LSTM were designed by non-dominated sorting genetic algorithm II (NSGA-II). It achieved average RMSE of 17.2. It improved the RMSE by 6.07–14.72% compared with baseline models, stand-alone RNN, and stand-alone LSTM. Compared with existing works, the RMSE improvement by proposed work is 12.95–39.32%.

Sign in / Sign up

Export Citation Format

Share Document