Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Parallel Analog Circuit Optimization Method Based on Genetic Algorithm and Machine Learning

A machine learning and genetic algorithm technology, applied in the field of parallel analog circuit optimization, can solve the problems of SPICE simulation time-consuming, large time cost, etc., to save time, ensure optimization accuracy, and improve optimization efficiency.

Active Publication Date: 2021-03-30
SHANDONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The SPICE simulator is an industry-standard integrated circuit simulation tool that can accurately evaluate circuit performance. The crux of the problem is that SPICE simulation takes a long time
When there are many design variables and a large search space, the number of simulations required reaches tens of thousands or more, which brings huge time costs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Parallel Analog Circuit Optimization Method Based on Genetic Algorithm and Machine Learning
  • A Parallel Analog Circuit Optimization Method Based on Genetic Algorithm and Machine Learning
  • A Parallel Analog Circuit Optimization Method Based on Genetic Algorithm and Machine Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A parallel analog circuit optimization method based on genetic algorithm and machine learning, the circuit is figure 2 The fifth-order complex filter circuit shown is composed of a first low-pass filter, a second low-pass filter, and a coupling unit. Both the first low-pass filter and the second low-pass filter are 5th-order effective Source RC low-pass filter, the coupling connection unit includes 5 sets of coupling resistors. Table 1 lists the design goals of this fifth-order complex filter.

[0048] Table 1

[0049]

[0050] That is to say, the optimization goal of this embodiment is to make the passband ripple as small as possible under the premise of ensuring a center frequency of 12.24 MHz and a bandwidth of 9 MHz (deviation not exceeding 5%). For this optimization goal, five sets of coupling resistors R 1 , R 2 , R 3 , R 4 , R 5 The resistance value of is used as the circuit design variable to be optimized. The specific implementation steps are as fol...

Embodiment 2

[0083] A parallel analog circuit optimization method based on genetic algorithm and machine learning, the circuit is Figure 4 The second-order differential operational amplifier circuit shown is a fully differential second-order operational amplifier circuit for high gain and high linearity. Among them, the compensation network includes a Miller compensation capacitor and a zeroing resistor for improving phase margin.

[0084] Table 4 lists the optimization indicators of the op amp.

[0085] Table 4

[0086]

[0087] That is to say, the optimization goal of this embodiment is to increase the open-loop gain and bandwidth as much as possible on the premise of satisfying the unity gain bandwidth and phase margin. According to the symmetry requirement, the transistor M 2 , M 4 , M 6 , M 8 respectively with M 1 , M 3 , M 5 , M 7 same, that is, their widths have the following relationship: W 1 =W 2 ,W 3 =W 4 ,W 5 =W 6 ,W 7 =W 8 . In addition, the compensation ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a parallel analog circuit optimization method based on genetic algorithm and machine learning. The present invention includes global optimization based on genetic algorithm and local optimization based on machine learning. Global optimization and local optimization are performed alternately. In the part of global optimization based on genetic algorithm, the SPICE simulation and parallel computing are combined, and the parallel SPICE simulation is adopted, which greatly improves the optimization efficiency while ensuring the accuracy. In the local optimization stage based on machine learning, a machine learning model is established near the global optimal point obtained by global optimization, and the machine learning model is used to replace the SPICE simulator, thereby reducing the time cost caused by a large number of SPICE simulations. Among them, the training data for training the machine learning model is also generated through parallel SPICE simulation, which significantly improves the efficiency compared with serial simulation. The optimization of the analog circuit by the method can greatly improve the optimization efficiency while achieving the optimization accuracy of SPICE level.

Description

technical field [0001] The invention relates to a parallel analog circuit optimization method based on genetic algorithm and machine learning, which belongs to the technical field of artificial intelligence and integrated circuit design or computer aided design. Background technique [0002] Nowadays, integrated circuit design has entered the era of System-on-Chip (SoC). SoC generally includes two parts of analog circuit and digital circuit. Among them, the design of the digital circuit part can be quickly realized with the help of mature EDA auxiliary tools. The design of the simulation part mainly depends on the manual design and debugging by the designer with the help of simulation software such as SPICE. Because there are many non-ideal factors in the design of analog circuits, manual debugging is difficult and time-consuming when there are many design variables and a large design space. In order to solve the problems faced by manual debugging of analog circuits, it i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/373G06N3/12
CPCG06N3/126G06F30/36G06F30/373G06F30/367G06F30/27G06N3/0985G06F2119/02
Inventor 周冉冉李亚萍王永李俞松黄学政孙娟娟
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com