如何助力中小型制造商打造智能工厂
在当今制造领域的一众流行词汇中，“智能工厂”或“未来工厂”尤为引人注目。在这份由 Siemens Digital Industries Software 专家撰写的白皮书中，我们将解读该术语的含义，审视理解其价值的关键考虑因素，并探讨几个关键要点以说明中小型企业 (SMB) 如何利用这些技术。
运用数字孪生打造未来工厂
数字孪生是物理对象或系统的虚拟表示。创建数字孪生的方式是使用来自传感器、计算机辅助设计 (CAD) 模型以及其他来源的数据创建对象或系统的详细、实时仿真。在制造业中，数字孪生有助于优化工艺，还可以提前发现潜在问题，防患于未然。
例如，正如加格所提到的，工厂车间的数字孪生可用于对不同生产场景进行仿真和测试，让制造商能够提前发现瓶颈和效率低下的情况，避免此类情况在实际生产环境中出现。数字孪生也可以用于监测和控制物理对象或系统的性能。
仿真软件已在制造业中应用多年，如机器人编程、产品设计和数控机床刀轨编程等。但是，计算能力和数据访问方面的进步显著提高了仿真的价值和质量，加格表示，就连对车间机器的调试过程进行仿真也不在话下。工艺的每一个步骤都可以进行仿真，这就避免了生产线停工和错误等成本。
柔性制造方法的优点
智能工厂是运用人工智能、数字孪生等先进技术和物联网 (IoT) 提高效率和生产率的制造工厂。在智能工厂中，机器与其他设备相互连通并连接到中央网络，使其能够实时传递和共享数据。这让工厂能够迅速响应不断变化的情况和客户需求。智能工厂还纳入了自动化和机器人，这样便能够比人更加准确、一致和高效地执行任务。“工具以数字化形式遭到损坏的成本为零。但在机器上实际损坏工具的成本却相当高。”拉胡尔·加格 (Rahul Garg) 说道。
充分利用工业物联网和预测性维护
在开始着手收集设备监测数据后，制造商所面临的一大挑战是他们具体要如何处理这些数据。振动或温度读数等高频数据会迅速累积成海量数字化数据。如果没有能够对其进行解析的工具和策略，这些数据便毫无用处，甚至还会成为障碍。
智能工厂让数据收集变得智能。传感器只能显示电机外壳振动加剧，但智能分析却能指出需要替换哪个轴承。这就是数据收集和可操作数据之间的差距。
相关资源
LG Electronics: Video Encoder IP Design Optimization and Verification Using Catapult
In this session, LGE describes a new design approach which concluded that adopting Catapult in IP development increases efficiency in time and cost, and they plan to increase usage in future IP projects.
NVIDIA: High-Level Synthesis in Agile System-on-Chip Flows: Overview and Techniques
This talk provides a brief overview of NVIDIA Research’s use of Catapult HLS and highlights some useful features and flows of the Connections library, such as the ability to back-annotate SystemC simulations.
Catapult AI NN – From AI/ML Framework to Optimized RTL
Video describing how Catapult AI NN now delivers a methodology and flow from “AI/ML Framework to RTL” enabling rapid exploration of network, quantization, design reuse factors, and more!
High-Level Synthesis Verification Technologies and Techniques
This session will describe applying known and trusted static, formal and dynamic approaches to verification performed at the C++ or SystemC HLS level of abstraction.
Hardware Accelerators – Exploring Power and Performance in Today’s AI
This session explores the design process from algorithm to hardware accelerator on a RISC-V processor as we quantify power consumption and performance.
Nokia: Experience in Adopting HLS and HLV Methodology
For increasing requirements for shorter time to market, Nokia has explored is raising abstraction level in both RTL design and verification with the help of High-Level Synthesis and Verification tools.
STMicroelectronics: In sensor Bricks Multi-objective Optimization of an Algorithm Chain for In-Sensor Processing
Through HLS and their innovative modular system, STMicroelectronics leads in the seamless integration of digital intelligence into analog native products, setting new standards for efficiency and market.
INOVA Semiconductors and Coseda: Paradigm Shift in Mixed Signal ASIC Design, Adopting SystemC and High-Level-Synthesis vs. Traditional RTL Design Flow
The authors will present the ease of use and the value-add of the HLS methodology in an automotive context.
HW Acceleration with High-Level Synthesis
Session introduces High-Level Synthesis, a technology that allows a developer to take a C++ function and automatically compile it into an RTL hardware description, suitable to be deployed into an ASIC or FPGA.
Fermilab: Bridging Machine Learning and Hardware Design with hls4ml and Catapult HLS
Fermilab introduces their partnership with Siemens to provide full integration with Catapult HLS design & verification flow, describe projects that have benefitted from hls4ml, and outline future directions.
Oak Ridge National Lab (ORNL): A Spiking Neural Network Architecture for Ultra-low Power and Ultra-low Latency Computing
ORNL with the help of the Siemens EDA tools, including Catapult HLS, the neuromorphic accelerator is being adapted from an FPGA prototype to a more capable and lower-power ASIC implementation.
How NVIDIA Uses High-Level Synthesis Tools for AI Hardware Accelerator Research
With constant change in AI/ML workloads, NVIDIA leverages a High-Level Synthesis design methodology based off SystemC and libraries like MatchLib to maximizing code reuse & minimizing design verification effort
.png?auto=format,compress?w=500&fit=max&q=60&dpr=1&auto=format)
Telechips: RTL Hardware Design Acceleration for On-The-Fly Image (De-)Warper in Automotive SoC Using C++ HLS
Telechips designed a new dewarping engine processing video stream data on-the-fly, different from traditional GPU-based memory-to-memory approach, by utilizing hierarchical design methodology in Catapult HLS.
STMicroelectronics: A Common C++ and UVM Verification Flow of High-Level IP
STMicro presents a unified way to integrate the definition of RTL and C functional coverage and assertion (reducing the coding effort) and a method to add constraints to the random values generated in UVMF.
Infineon: HLS Formal Verification Flow Using Siemens Formal Verification
High-Level Synthesis (HLS) is design flow in which design intent is described at a higher level of abstraction such as SystemC/C++/Matlab/etc.
CEA: Bridging the Gap Between Neural Network Exploration and Hardware Implementation
CEA presents a methodology that bridges the open-source DL framework N2D2 and Catapult HLS to help reducing the design process of hardware accelerators, making it possible to keep pace with new AI algorithms.
High-Level Synthesis & Advanced RTL Power Optimization – Are you still missing out?
Discover how C++ & SystemC/MatchLib HLS is more than just converting SystemC to RTL. In the RTL Design space, we will cover our technology for Power Optimization with PowerPro Designer & Optimizer.
Infineon & Coseda: Facelifting a SystemC System Level Model Towards Physical Prototype – Adoption of High-Level-Synthesis
Infineon & Coseda present on the adoption of High-Level-Synthesis at an existing SystemC system level model.
Ultra Video Group (Tampere University): Managing the Complexity of an HEVC Encoder (Kvazaar) Implementation on FPGA with Catapult HLS
Dr. Panu Sjövall from Ultra Video Group (Tampere University), sheds light on how they were able to implement their embedded real-time HEVC intra encoder (Kvazaar) on HW with Catapult HLS.
Quantization of HLS Designs Using Value Range Analysis
Introduces simple & robust quantization methodology based on value range analysis. Learn what’s fixed-point conversion a.k.a quantization; dynamic & static quantization methods; and how to use Catapult VRA.
DUTh: Architectural Improvements for Low-Power and Functional Safety of Dataflow CNN Accelerators Using HLS
DUTh demos using HLS to design CNN accelerators with on-line checking capabilities, improve power efficiency due to optimized data handling on spatial variants of convolution, and effectively use HLS.
Alibaba: Innovating Agile Hardware Development with Catapult HLS
At the IP level, an ISP was created within a year using Catapult, a task impossible using traditional RTL. To reduce dependency on designer experience, Alibaba introduced an AI-assisted DSE tool.
Cornell University: Building Sparse Linear Algebra Accelerators with HLS
Cornell intros HiSparse: accelerator on sparse-matrix dense-vector multiplication. Using both HLS implementation and simulation, their sparse accelerators deliver promising speedup.
FNAL: Ultrafast Neural Networks for On-Detector Edge Processing in Resource-Constrained Extreme Radiation Environment
FNAL demos that a NN autoencoder model can be implemented in a radiation-tolerant ASIC to perform lossy data compression. This alleviates the data transmission problem.
Harvard University: Effective SW/HW Co-Design of Specialized ML Accelerators Using Catapult HLS
Harvard sheds light on their agile algo-hw co-design & co-verification methodology powered by HLS. It led to an order of magnitude improvement in the design effort across 3 generations edge AI accelerator SoCs.
Stanford University: Edge ML Accelerator SoC Design Using Catapult HLS
Describes the design and verification of the systolic array-based DNN accelerator taped out by Stanford, the performance optimizations of the accelerator, and the integration of the accelerator into an SoC.
From Simulink to High-Quality RTL using High-Level Synthesis - The Design Methodology
Webinar introducing a design methodology starting from a flat floating-point Simulink model and step through to HLS generated RTL. All design steps including fixed-point conversion are described in detail.
From MATLAB® to High-Quality RTL Using High-Level Synthesis - The Design Methodology
Webinar introducing a design methodology that starts from a self-contained MATLAB script and goes through the different workflow steps to HLS generated, high-quality RTL. All design steps are detailed.
High-Level Verification of an AI/ML Accelerator Design
This webinar demonstrates how one can achieve comprehensive verification faster at a higher level of abstraction but still apply known and trusted RTL verification techniques.
HLS 101 - What Every RTL HW Design Team Needs to Know
High-Level Synthesis (HLS) extends the traditional design flow, providing a new and powerful approach to hardware design. It is important to understan
Microsoft - HLS Hardware Design Patterns
High-Level Synthesis (HLS) using untimed C++ presents an elegant hardware abstraction framework for simplifying hardware design at the unit level. To
Doing Research with Catapult HLS at Harvard
One of them is about proposing adaptive floating-point (FP) quantization to replace integer (INT) quantization for NNs.
NVIDIA: Design and Verification of a Machine Learning Accelerator SoC Using an Object-Oriented HLS-Based Design Flow
A high-productivity digital VLSI flow for designing complex SoCs is presented in this webinar. It includes High-Level Synthesis tools, an efficient im
Porting Vivado HLS Designs to Catapult HLS Platform
This webinar will cover how to port an existing HLS design developed within the Xilinx® Vivado® HLS environment into Siemens' Catapult® HLS Platform.
Early AXI4 SOC Performance Verification Using NVIDIA MatchLib and Catapult HLS
This webinar will introduce NVIDIA Matchlib and its usage with Catapult HLS using some AXI4 SOC demonstration examples.
From HLS Component to a Working Design
Complex algorithms do not exist in a vacuum. After High-Level Synthesis (HLS) is used to create an RTL component, to be useful, it needs to be integra
Part 1: Why Are High-Performance Low-Energy Applications Moving from GPUs and DSPs to FPGAs and ASICs?
Transistor counts and performance of integrated circuits are reaching their peak. Artificial intelligence is emerging as the next "big thing" in areas
Part 2: Adapting software algorithms to hardware architectures for high performance and low-power
GPUs and DSPs offer very high-parallelism and impressive memory bandwidths, within the scope of a fully programmable platform. However, they need to f
High-Level Verification: Verification Methodology and Flows When Using C++ and HLS
Highlights proven tools and methodology that help an HLS designer check and verify his design, measure, and close coverage, and compare the C to RTL implementation.
Building an iDCT for H.265 Using High-Level Synthesis
High-Level Synthesis (HLS), has been adopted by leading companies to speed design time and reduce verification costs in applications such as video and
Catapult HLS for RTL Teams - What You Need to Know
Catapult® HLS is a key competitive technology in several emerging markets like machine learning and vision. In this webinar, we cover both an introduc
Implementing Machine Learning Hardware Using High-Level Synthesis
Neural networks are typically developed and trained in a high-performance 32-bit floating-point compute environment. But, in many cases a custom hardw
Using high-level synthesis to accelerate computer/machine Vision applications
High-Level Synthesis (HLS) has been used in multiple companies, projects, and designs targeting vision processing for the past several years. HLS adop
Using HLS to Accelerate Computer Vision for Autonomous Drive
The algorithms to teach a computer to see, understand and make decisions for ADAS and Autonomous Drive systems require a significant amount of paralle
Stanford/AMD: Automated Methodology for Efficient Hardware Accelerator
Mobile devices today are composed of many specialized accelerators to achieve high-performance and low-power specifications. However, accelerator desi
Machine Learning: How HLS Can Be Used to Quickly Create FPGA/ASIC HW for a Neural Network Inference Solution
This session reviews the consideration around fast HW prototyping for validating acceleration in Neural Networks for Inferencing vs highest performance implementation and the tradeoffs.
Neural Network Quantization for Low-Power
This webinar will describe how to use Qkeras and High-Level Synthesis to produce a bespoke quantized CNN accelerator, and compares the accuracy, power, performance, and area of different quantizations.
Moving Between FPGA and ASIC with High-Level Synthesis
Writing RTL that works smoothly on both FPGA and ASIC implementations is nearly impossible. But, High-Level Synthesis (HLS) can make technology-indepe
Solutions for the Design and Verification of 5G SoCs
Catapult, Veloce 5G Fronthaul, Veloce X-STEP, Questa