Analog mixed-signal (AMS) verification is one of the essential tasks in the development process of modern systems-on-chip (SoC). Most parts of the AMS verification flow are already automated, except for stimuli generation, which has been performed manually. It is thus challenging and time-consuming. Hence, automation is a necessity. To generate stimuli, subcircuits or subblocks of a given analog circuit module should be identified/classified. However, there currently needs to be a reliable industrial tool that can automatically identify/classify analog sub-circuits (eventually in the frame of a circuit design process) or automatically classify a given analog circuit at hand. Besides verification, several other processes would profit enormously from the availability of a robust and reliable automated classification model for analog circuit modules (which may belong to different levels). This paper presents how to use a Graph Convolutional Network (GCN) model and proposes a novel data augmentation strategy to automatically classify analog circuits of a given level. Eventually, it can be upscaled or integrated within a more complex functional module (for a structure recognition of complex analog circuits), targeting the identification of subcircuits within a more complex analog circuit module. An integrated novel data augmentation technique is particularly crucial due to the harsh reality of the availability of generally only a relatively limited dataset of analog circuits’ schematics (i.e., sample architectures) in practical settings. Through a comprehensive ontology, we first introduce a graph representation framework of the circuits’ schematics, which consists of converting the circuit’s related netlists into graphs. Then, we use a robust classifier consisting of a GCN processor to determine the label corresponding to the given input analog circuit’s schematics. Furthermore, the classification performance is improved and robust by involving a novel data augmentation technique. The classification accuracy was enhanced from 48.2% to 76.6% using feature matrix augmentation, and from 72% to 92% using Dataset Augmentation by Flipping. A 100% accuracy was achieved after applying either multi-Stage augmentation or Hyperphysical Augmentation. Overall, extensive tests of the concept were developed to demonstrate high accuracy for the analog circuit’s classification endeavor. This is solid support for a future up-scaling towards an automated analog circuits’ structure detection, which is one of the prerequisites not only for the stimuli generation in the frame of analog mixed-signal verification but also for other critical endeavors related to the engineering of AMS circuits.
This paper addresses the issue of reliable and automated analog circuit’s structure recognition (ACSR). First, it presents a comprehensive critical review of the related state-of-the-art. Then, essentially, this study proposes and validates a novel approach for realizing a dependable structure recognition system for analog circuits through a comprehensive ontology definition, some transformation tools, scene modeling through graph models, and then, by involving a graph attention neural network (GAT) model. Knowingly, identifying sub-circuits requires, in the brute-force mode, extensive screening of the numerous alternative substructures that can be constructed from the basic elements (i.e. the transistors) in presence, especially w.r.t. the actual connectivity topology amongst them; this is evidently a very complex and challenging endeavor. The relevant state-of-the-art has involved mostly unsupervised learning approaches to tackle this analog circuit’s structure recognition-related challenging task, whereby they have reached a clear limitation of not (or only very hardly) reaching beyond 90% to 93% accuracy/precision. But in this work, we develop, for the first time, a comprehensive supervised-learning approach that demonstrates its clear superiority by enabling the reaching of a recognition accuracy or precision that is reliably in the range beyond 99% (or even 100%) for each subblock of the analog circuit. The supervised clustering approach developed and validated in this study consists of a comprehensive modeling and conceptual pipeline that is implemented around and through a Graph Attention Neural Network model, which ensures a reliable recognition of sub-blocks of analog circuits and their related internal adjacency connectivity topology. Besides the modeling pipeline, this study also develops a set of tools for mapping an analog circuit’s schematics into a graph model. To overcome the limited and unbalanced samples for training the graph neural model, this study proposes a special novel augmentation strategy based on a graph sub-cropping technique. This augmentation technique is embedded in a smart stepwise augmentation protocol that leads at the end, through iterative additional dedicated training steps to a significant progressive increase of the recognition accuracy by the graph neural model until reaching more than 99%, better 100%, for each of the subblocks of the analog circuits as demonstrated in the demonstration case-study presented. Indeed, this paper’s quintessence represents a significant breakthrough in view of the clear outperforming of the currently relevant related state-of-the-art.
The introduction of Shared, Electric, Automated, and Connected Mobility (SEACM) systems will completely transform the transportation sector in the near future. However, these systems present additional challenges that require comprehensive performance analysis and effective deployment techniques. This paper will investigate the importance of creating artificial datasets for training Machine Learning models (ML), with a focus on generating datasets specific to SEACM systems. In contrast, to generate artificial datasets for the SEACM system, many characteristics should be considered such as user behavior, vehicle dynamics, charging infrastructure, and environmental conditions. As a result, using these synthetic datasets, decision-makers can correctly simulate several scenarios and evaluate the performance of these complex systems. This review paper also shows how artificial datasets may be used to train ML models to simulate SEACM with autonomous repositioning. This allows researchers to assess how well ML-based algorithms can be used to optimize vehicle routing, charging infrastructure usage, demand forecasting, and other important operational elements. In addition, we highlight the significant impact that the generation of artificial datasets has on performance evaluation and deployment approaches. Academics can develop efficient deployment strategies that maximize the effectiveness and sustainability of shared automated and connected electric mobility systems by training ML models on these datasets to better understand the strengths and limitations of various algorithms, identify potential areas for improvement, and more. Taken as a whole, this research highlights the importance of generating artificial datasets in the context of shared automated and connected electric mobility systems. It illustrates the methods used to generate these datasets, their importance for modeling and simulation, and their implications for performance evaluations and deployment strategies. To more rapidly build and optimize machine learning (ML) models for shared mobility systems, researchers and practitioners can exploit the potential of artificial datasets. This will ultimately lead to better transportation experiences and sustainable urban mobility.
AMS circuits are crucial components in modern electronic systems. However, AMS circuits are variable and complex, making their design and verification difficult. Design and verification of AMS circuits demand accurate analog circuit structure recognition for layout generation, performance optimization, and hierarchical breakdown. In context with this, the current work introduces a robust, systematic, and exhaustive approach to AMS schematic recognition to enhance the capabilities of existing approaches within the AMS circuits hierarchy. Our solution applies graph attention networks (GATs) and machine learning (ML) techniques to analyze the structure and connectivity of circuits. To cope with the complexity of AMS circuits, we use graph-based learning methods. Graph attention techniques enable the model to focus on the circuit's most intriguing sections, thereby enhancing the accuracy of structure recognition. We evaluated the proposed approach on a large dataset of AMS circuits with various levels of complexity. Our method is superior for AMS schematic structure recognition, particularly for large-scale and highly dynamic circuits. Our strategy of vertical generalization enhances performance. This essential characteristic enables our method to scale successfully, precisely, and efficiently despite circuit complexity. Our data augmentation approach showed outstanding outcomes compared to others. This enhances learning by providing diverse circuit examples and makes the model more robust against the diversity and complexity of AMS circuits. These enhancements increase the efficiency and dependability of analog circuit design and verification, thereby resolving current electronic system issues.