一种新的ANN-PSO方法,用于优化一个双场板 GaN HEMT 的小信号等效模型.
Haowen Shen1, Wenyong Zhou2, Jinye Wang1
1Innovation Center for Electronic Design Automation Technology, Hangzhou Dianzi University, Hangzhou 310018, China.
Micromachines
|January 8, 2025
概括
本研究介绍了一种结合人工神经网络 (ANN) 和粒子集群优化 (PSO) 的新方法,以高效优化化高电子移动性晶体管 (GaN HEMT) 设备的参数. ANN-PSO方法可以提高设备建模的自动化和准确性.
科学领域:
- 半导体设备物理 半导体设备物理
- 电子领域的人工智能
- 计算电磁学 计算机电磁学
背景情况:
- 准确的小信号等效模型对于设计化高电子移动性晶体管 (GaN HEMT) 设备至关重要.
- 传统的参数优化方法可能耗时且缺乏精度.
- 由于其复杂的结构,双场板 GaN HEMT 存在独特的建模挑战.
研究的目的:
- 开发和验证一种新,高效和精确的方法来优化双场板GaN HEMT设备的小信号等效模型参数.
- 将人工神经网络 (ANN) 与粒子集群优化 (PSO) 算法集成,以实现增强的参数提取.
- 将拟议的ANN-PSO方法的性能与其他优化算法 (如NSGA2和DE) 进行比较.
主要方法:
- 一个人工神经网络 (ANN) 模型被开发来预测GaN HEMT设备的S参数.
- 使用粒子集群优化 (PSO) 算法来优化小信号等效电路模型的参数.
- 在1-18 GHz频率范围内,ANN-PSO方法应用于4 × 250μm双场板GaN HEMT模型.
- 在各种偏差条件下,对传统物理公式分析进行了性能验证.
主要成果:
- 与NSGA2和DE算法相比,PSO算法显示出更高的融合速度和准确性.
- 通过ANN-PSO方法实现了GaN HEMT等效电路模型参数的自动化和高效优化.
- 优化的模型显示了高准确性,在不同的偏差条件下得到验证.
- 该方法在提高自动化和效率,同时保持模型精度方面被证明是有效的.
结论:
- 集成的ANN-PSO方法为GaN HEMT设备模型的自动参数优化提供了显著的进步.
- 这种方法为优化其他复杂的半导体设备模型提供了可靠和高效的参考.
- 该研究强调了将机器学习与元启发式优化相结合用于设备建模和设计的潜力.
相关概念视频
Small-Signal Analysis of MOSFET Amplifiers
503
In small-signal analysis, a MOSFET transistor amplifier acts as a linear amplifier when operating in its saturation region. The gate-to-source voltage (VGS) of the MOSFET is the sum of the DC biasing voltage and the small time-varying input signal. This combination sets up the operating point and modulates the drain current (ID) that flows from the drain to the source. When a small AC signal is superimposed on the DC bias voltage at the gate, the instantaneous drain current comprises three...
503
Small-Signal Analysis of BJT Amplifiers
951
Small signal analysis is a fundamental approach used in electronics to understand how a Bipolar Junction Transistor (BJT) amplifier processes signals. In the active region, the BJT is designed for linear amplification. The transistor's behavior under these conditions is governed by its instantaneous base-emitter voltage VBE, a sum of the DC bias VBE, and a small AC signal VBE, resulting in the collector current iC. Here, the collector current has a DC component and an AC component.
951
Small-signal Diode Model
741
In analyzing the behavior of diodes in circuits, the relationship between the current through a diode and the voltage across it is of particular interest, especially when considering the effect of a direct current (DC) bias voltage. When applied, this DC bias influences the diode's operating point, known as the Q point, around which the current-voltage (I-V) characteristic of the diode exhibits exponential behavior. Introducing a small, time-varying signal on top of this bias aids in...
741
MOSFET: Enhancement Mode
284
Enhancement-mode MOSFETs are pivotal components in electronics, distinguished by their capacity to act as highly efficient switches. They are part of the larger family of metal-oxide Semiconductor Field-Effect Transistors (MOSFETs). They are available in two types: p-channel and n-channel, each tailored to specific polarity operations.
In their basic form, enhancement-mode MOSFETs are typically non-conductive when the gate-source voltage (Vgs) is zero. This default 'off' state means no...
In their basic form, enhancement-mode MOSFETs are typically non-conductive when the gate-source voltage (Vgs) is zero. This default 'off' state means no...
284
Transformers with Off-Nominal Turns Ratios
138
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
138
SFG Algebra
107
In Signal Flow Graph (SFG) algebra, the value a node represents is determined by the sum of all signals entering that node. This summed value is then transmitted through every branch leaving the node, making the SFG a powerful tool for visualizing and analyzing control systems.
Each node in an SFG corresponds to a variable, and the interactions between nodes are represented by branches with associated gains. When multiple branches lead into a node, the value at that node is the sum of the...
Each node in an SFG corresponds to a variable, and the interactions between nodes are represented by branches with associated gains. When multiple branches lead into a node, the value at that node is the sum of the...
107


