Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
ABSTRAK
Kendaraan roda empat dapat mengalami perilaku understeer atau oversteer ketika berbelok. Perilaku tersebut menunjukkan ketidakstabilan pada kendaraan yang dapat terjadi ketika kendaraan di laju dengan kecepatan tinggi diatas permukaan jalan dengan koefisien gesek yang rendah. Ketidakstabilan ini dapat menjadi potensi bahaya ketika berkendara.Desain pengendali prediktif bertingkat dengan model gerak kendaraan double track, diajukan dalam skripsi ini untuk mengatasi perilaku understeer dan oversteer. Perancangan pengendali dimulai dari mendapatkan data masukkan dan keluaran pergerakkan kendaraan. Kemudian dengan metode least square bertingkat, didapatkan matrik matrik model identifikasi bertingkat. Model identifikasi tingkat pertama digunakan untuk mendapatkan nilai eror estimasi keluaran, sedangkan model identifikasi tingkat kedua digunakan sebagai model pengendali prediktif bertingkat.Pada akhir penelitian, desain pengendali prediktif bertingkat diuji melalui simulasi untuk melihat kemampuan pengendali yang telah dirancang.

---

ABSTRACT
Oversteer and understeer could be experienced by each of four wheel vehicle. The behaviours show the instability of the vehicle, and might be happened because of high velocity of the vehicle and low friction coefficient of the road. The instability could be one of the potential risks in driving the vehicle.The design of multistage predictive control with double track vehicle model is proposed in this research to handle understeer and oversteer behaviours. The design started from collecting the related input and output. Then the multistage least square method is used to find the matrix used in multistage identification model. The first stage of identification model is used to get prediction error that happened while estimating the output. The second level of identification model is used as multistage predictive control model.In the end of research, the multistage predictive control is tested through simulation to check the performance of the controller.

Abstrak :
Fixation points, as the stopping location of eye movements, can be extracted to generate valuable information about a picture or an object. This information is valuable as it enables the identification of the area/part of the picture that attracts people’s attention, which can be used as a consideration when making decisions in the future, for example in marketing. For this reason, in this study, a Neural Network (NN) model was developed to predict the fixation points of a picture. Specifically, the authors experimented with various transfer and training functions in the NN in order to determine which causes the fewest errors. The results show that the method used is applicable in practice since it produces MAPE (Mean Absolute Percent Error) of around 13–15% and MSE (Mean Squared Error) of 0.9–1.1%.