دانلود رایگان مقاله انگلیسی رویکرد فازی نوری تطبیقی برای مدل سازی تعادل رابطه سرعت با چگالی - تیلور و فرانسیس 2018

ABSTRACT

This paper endeavors to model the equilibrium speed–density relationship using a new fuzzy logic-based approach. To capture the randomness in traffic flow dynamics, it develops a single-input Adaptive Neuro-Fuzzy Inference System (ANFIS) trained with a hybrid algorithm. Furthermore, it proposes a new Premise-Consequent Conjugate Effect (PCCE) relationship to estimate fundamental diagram (FD) parameters from the ANFIS model. Several options (i.e. optimal split of data into training and testing data, selection of suitable membership function) offered by ANFIS are then illustrated. An experiment is performed to determine the maximum achievable goodness of fit without the occurrence of overfitting phenomenon by changing the number of clusters. The calibrated ANFIS model is compared against traditional and advanced speed–density models for five different freeway locations. Results show that the proposed model outperforms other preceding models by attaining goodness-of-fit values within a range of 0.82–0.92. Finally, the proposed PCCE relationship shows the ANFIS model’s robustness in accurate estimation of FD parameters for all freeway locations.

5. Conclusion and future directions

FDs have been the subject of comprehensive study due to its importance in both the design of traffic facilities and for the control of traffic operations. Traditional speed–density models try to fit the traffic dynamics to a definite shape (i.e. logarithmic, exponential, and exponential to the quadratic and various forms of polynomials) rather than capturing the variations in drivers’ behavior caused by the shockwave in the transition zone. In addition, they fail to acknowledge the effect of different geometric patterns of the roadway (i.e. on-ramp/off-ramp on a freeway) on the shape of the speed–density FD.

We have applied the ANFIS in modeling equilibrium speed–density relationship because of its efficacy in being shape-flexible. ANFIS provides shape flexibility incorporating three factors: (a) premise parameters; (b) number of MF; and (c) consequent parameters. Among these, premise parameters provide the required curvature to the speed–density FD, whereas the number of MF controls the extent of the curvature. Individual MF covers a particular region of the speed–density curve. It opens a scope for agglomeration of the empirical data according to their characteristics into a particular MF. The overlapping among the MFs causes superimposition of the curves, which ultimately adds further flexibility to the ANFIS model. In contrast, the consequent parameters control the direction of the baseline of this curvature. Combination of these three factors enables ANFIS model to capture the actual trend in empirical speed–density data. Moreover, in this research, the Sugeno model has been correlated with the equivalent Greenshields model, which proves the eligibility of ANFIS model to represent speed–density relation. It helped to reveal the contribution of premise and consequent in the speed–density relation. Incorporating this knowledge, the PCCE relationship with the speed–density equilibrium is established. Accordingly, the MFs for estimating free flow speed, jam density and capacity have been revealed.