Programmable Logic System Research Articles

Технології реалізації штучного інтелекту як сервісу на основі апаратних прискорювачів

The subject of study in this article is modern technologies, tools and methods of building AI systems as a service using FPGA as a platform. The goal is to analyze modern technologies and tools used to develop FPGA-based projects for systems that implement artificial intelligence as a service and to prepare a practical AI service prototype. Task: to analyze the evolution of changes in the products of leading manufacturers of programmable logic devices and experimental and practical examples of the implementation of the paradigm of continuous reprogramming of programmable logic; analyze the dynamics of changes in the development environment of programmable logic systems for AI; analyze the essential elements of building projects for AI systems using programmable logic. According to the tasks, the following results were obtained. The area of application of hardware implementation of artificial intelligence for on-board and embedded systems including airspace industry, smart cars and medical systems is analyzed. The process of programming FPGA accelerators for AI projects is analyzed. The analysis of the capabilities of FPGA with HBM for building projects that require enough of high speed memory is performed. Description languages, frameworks, the hierarchy of tools for building of hardware accelerators for AI projects are analyzed in detail. The stages of prototyping of AI projects using new FPGA development tools and basic DPU blocks are analyzed. The parameters of the DPU blocks were analyzed. Practical steps for building such systems are offered. The practical recommendations for optimizing the neural network for FPGA implementation are given. The stages of neural network optimization are provided. The proposed steps include pruning of branches with low priority and the use of fixed point computations with custom range based on the requirements of an exact neural network. Based on these solutions, a practical case of AI service was prepared, trained and tested. Conclusions. The main contribution of this study is that, based on the proposed ideas and solutions, the next steps to create heterogeneous systems based on the combination of three elements are clear: AI as a service, FPGA accelerators as a technology for improving performance, reliability and security, and cloud or Edge resources to create FPGA infrastructure and AI as service. The development of this methodological and technological basis is the direction of further R&D.

Lavagem automatizada de veículos empregando máquina de estados implementada em FPGA

By using FPGA (Field-Programmable Gate Array) technology it is possible to rule out the use of printed circuits for a specific process. In addition, process automation has been growing in the industry for financial returns and improved procedures. So, for the purpose of academic learning, it was proposed in the discipline of analysis and design of programmable logic systems of Electrical Engineering course at UFSM-CS the development of an automatic car wash system, usually found in gas stations, with autonomous execution. The project has two operation modules, where one module operates in a simplified way in the washing and the other mode is complete to obtain the effective cleaning of the vehicle. For system implementation, a code describing a state machine was developed in VHDL hardware description language., in which each state performs a system operation. A small scale prototype consisting of CD drives, stepper motors, DC motors and drivers has been developed.

Proton-beam writing channel based on an electrostatic accelerator

We have described the structure of the proton-beam writing channel as a continuation of a nuclear scanning microprobe channel. The problem of the accuracy of positioning a probe by constructing a new high-frequency electrostatic scanning system has been solved. Special attention has been paid to designing the probe-forming system and its various configurations have been considered. The probe-forming system that best corresponds to the conditions of the lithographic process has been found based on solving the problem of optimizing proton beam formation. A system for controlling beam scanning using multifunctional module of integrated programmable logic systems has been developed.

The effectiveness of statistical testing when applied to logic systems

In this paper we demonstrate the effectiveness of statistical testing for error detection on the example of a Programmable Logic System (PLS). Statistical testing was introduced into this project as a complementary testing technique with the potential to quantify system reliability, after a variety of acceptance tests had been performed. An appropriate statistical testing algorithm was devised and implemented, which is described in detail in this paper. We compare the results of statistical testing with those of a variety of other testing methods employed on the PLS. In terms of differences detected per number of tests, statistical testing showed an outstanding effectiveness. Furthermore, it detected a problem, which was missed by all other testing techniques. This together with its potential for reliability quantification illustrates its importance for system validation as part of a risk-based safety-case.

The clause counter map: an event chaining algorithm for online programmable logic

The clause counter map method (CCM) is a software inference engine for programmable logic systems, including logic controllers and knowledge-based information systems. It provides efficient realizations of synchronous sequential machines using two-valued or three-valued logic. CCM permits the use of general purpose processors for large on-line control models. The CCM interpreter is designed to trade space for time. A redundant state is maintained in a compact map form. Logical events percolate through an otherwise static model. This mode of operation distinguishes the class of event chaining algorithms. Prior on-line methods repeatedly reconstruct or test unchanging portions of the model. In large models, CCM can exceed binary decision machines in speed and require less space. Contemporary modeling languages can be translated into CCM models. Thus event chaining implementation is available for control models defined by relay ladder logic, state machines, function charts, and Petri nets. >

Application of a Microprocessor Based Solid State Programmable Logic System for Control of Class 1E Components and Devices

Application of a Microprocessor Based Solid State Programmable Logic System for Control of Class 1E Components and Devices

Application of a Microprocessor Based Solid State Programmable Logic System for Control of Class 1E Components and Devices

The paper discusses the microprocessor based Solid State Programmable Logic System (SSPLS) designed for the Clinch River Breeder Reactor Plant (CRBRP) which was terminated in December 1983 by U.S. Congress. Even though procurement of equipment did not take place, the topics discussed here reflect the advanced engineering and design completion (85 percent) on the project and the authors feel that the information presented reflects worthwhile experience associated with the implementation of the state-of-the-art technology and may benefit future designs as well as the industry in general. Topics presented include discussion on design description and hardware, programming, verification and validation, licensing concerns and requirements on reliability and maintainability. The paper describes licensing interaction with the Nuclear Regulatory Commission (NRC) Staff at the construction permit stage and outlines additional details that would be needed at an operating license permit stage.