Graduation design of intelligent traffic light monitoring system based on fuzzy control

Urban roads are complex and interconnected, with traffic lights serving as a crucial command system for managing urban traffic. As an effective tool for regulating traffic flow and increasing road capacity, traffic lights have proven to be highly effective in reducing traffic accidents. However, traffic volume is constantly changing, while traditional traffic light systems rely on fixed-time control, which can lead to congestion. To address this issue, it's necessary to adjust the timing of traffic lights based on real-time traffic conditions. This paper proposes an intelligent traffic light monitoring system that utilizes a fuzzy control algorithm to optimize traffic light operations. **1. Overall System Design** The traffic light monitoring system is designed as a distributed and networked platform, consisting of a central monitoring center and multiple intelligent terminals. These terminals are responsible for centralized monitoring and maintenance of independently operating traffic signals. Each intersection functions as a monitoring terminal, equipped with a data collector, a GPRS module, and a controller. The controller manages the status of the traffic lights, displays time information, and collects vehicle data from each lane. The data collector gathers information from all subordinate controllers and sends control commands accordingly. Using the GPRS network, the collected data is transmitted to the monitoring center, where it is analyzed to monitor road conditions. Fuzzy logic is applied to process vehicle data and adjust traffic signal timings dynamically. **2. Fuzzy Control Algorithm Design** Fuzzy control leverages human experience as a control strategy, translating it into natural language that machines can interpret for automated decision-making. In this study, the human-based traffic command strategies are converted into machine-readable algorithms, enabling the system to simulate human judgment in analyzing the optimal time allocation for each lane. For a four-way intersection, the cycle is divided into four phases, as illustrated in Figure 1 (Phase 1: East-West, West-East, West-South, East-North; Phase 2: West-North, East-South; Phase 3: South-North, North-South, South-East, North-West; Phase 4: North-East, South-West).

Graduation design of intelligent traffic light monitoring system based on fuzzy control

Figure 1: Four-phase Intersection

**2.1 Input and Output Variable Definition** In fuzzy control, linguistic variables represent input and output values in natural language form rather than numerical values. For this system, the average number of waiting vehicles in the current phase and the next phase are selected as inputs. The green light duration for the current phase is the output variable, resulting in a two-input one-output fuzzy controller. This model is illustrated in Figure 2.

Graduation design of intelligent traffic light monitoring system based on fuzzy control

Figure 2: Two-Input One-Output Model

In this model: - X1: Total number of vehicles / Number of lanes (rounded) - X2: Total number of vehicles in the next phase / Number of lanes (rounded) - Y: Green light duration for the current phase **2.2 Variable Settings** **(1) Input Variables: X1 and X2** The basic domain for the average number of waiting vehicles is defined as [0, Qmax], where Qmax represents the maximum number of vehicles that can be accommodated. Based on practical conditions, Qmax is set to 40. The discrete domain for linguistic variables is determined as {-5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5}. A conversion table between the basic domain and the discrete domain is provided in Table 1. **Table 1: Conversion Table for Average Vehicle Input**

Graduation design of intelligent traffic light monitoring system based on fuzzy control

**(2) Output Variable: Y** The basic domain for the green light delay time is defined as [Gmin, Gmax], where Gmin is the minimum acceptable green light duration, and Gmax is the maximum. Here, Gmin is set to 0 seconds, and Gmax is 60 seconds. The discrete domain for the output is {0, 1, 2, ..., 12}. A scaling factor K = 60/12 = 5 is used to convert the fuzzy output into an exact delay time: **Delay Time = K × Fuzzy Set Data** **2.3 Membership Functions** The linguistic variables for X and Y are defined using seven levels: "Rare" (NB), "Less" (NM), "Few" (NS), "Normal" (ZE), "More" (PS), "More" (PM), and "Many" (PB). Based on these, assignment tables for both input and output variables are established. Tables 2 and 3 provide the corresponding assignments for the input and output linguistic variables, respectively. **Table 2: Assignment Table for Input Variable X**

Graduation design of intelligent traffic light monitoring system based on fuzzy control

**Table 3: Assignment Table for Output Variable Y**

Graduation design of intelligent traffic light monitoring system based on fuzzy control

New Energy Structure

Our Wind Power Lighting Pole, Solar Street Lights Pole are made from quality sheet through bending, forming, automatic welding and hot galvanization. We can reach one-run machining length of 14m and can bend sheet of thickness up to 45mm. We adopt advanced welding procedures, automatically weld main joints and reach rank-II welding quality.

We have supplied our Wind Power Lighting Pole,Solar Street Lights Pole to Australia, Columbia, England, Kuwait, Iraq, Philippines, Pakistan and etc.

Wind Power Pole, Solar Lighting Pole, Solar Street Lights Pole, Wind and Solar Lighting Poles

JIANGSU XINJINLEI STEEL INDUSTRY CO.,LTD , https://www.steel-pole.com