小程序
传感搜
传感圈

Artificial Intelligence: The Driving Force of Industry 4.0

2023-03-25
关注

Illustration: © IoT For All

A lot of the hype surrounding artificial intelligence in manufacturing is focused on industrial automation, but this is just one aspect of the smart factory revolution — a natural next step in the pursuit of efficiency. Artificial intelligence also brings its capability to reveal new avenues for business to the manufacturing table. We will outline the ability of artificial intelligence to drive industrial automation and open up new business opportunities as part of the emerging Industry 4.0 paradigm. Also, we will introduce how this powerful technology is already being used by manufacturers to drive efficiency, improve quality, and better manage supply chains.

AI Manufacturing Use Cases

#1: Predictive Quality & Yield

Reducing production losses and preventing production process inefficiencies has always been a challenge for manufacturers across all industries. Today, this is as true as ever, as growing demand meets increased competition.

On the one hand, consumers’ expectations are very high; global consumer habits are gradually “westernizing,” even as the population boom continues. According to numerous surveys in recent years, the global population will grow by 25 percent by 2050, equating to 200,000 additional mouths to feed every day.

On the other hand, consumers have never had so many product alternatives at their disposal. Recent surveys indicate that this wealth of options means consumers are increasingly likely to permanently ditch even their favorite brands if, for example, a product isn’t available on the shelf.

With these trends in mind, manufacturers can no longer afford to accept process inefficiencies and their associated losses. Every loss in terms of waste, yield, quality, or throughput chips away at their bottom line and hands another inch to the competition — assuming their production processes are more efficient.

The challenge for many manufacturers — particularly those with complex processes — is that they eventually hit a ceiling in terms of process optimization. Some inefficiencies do not have an obvious root cause, which puts process experts at a loss to explain them.

Predictive quality and yield use AI-driven processes and machine health solutions to reveal the hidden causes of many of the perennial production losses manufacturers face. This is done via continuous, multivariate analysis, using machine learning algorithms that are uniquely trained to intimately understand individual production processes.

The specific AI/machine learning technique used here is called supervised learning which means the algorithm is trained to identify trends and patterns within the data. Automated recommendations and alerts can then be generated to inform production teams and process engineers of an imminent problem, and seamlessly share important knowledge on how to prevent losses before they happen.

#2: Predictive Maintenance

Predictive maintenance is one of the most well-known applications of industrial AI. Instead of performing maintenance according to a predetermined schedule, predictive maintenance uses algorithms to anticipate the next failure of a component, machine, or system and then alerts personnel to perform focused maintenance procedures to prevent the failure. These alerts happen at the right time so as not to waste unnecessary downtime.

These maintenance systems rely on unsupervised machine-learning techniques to formulate predictions. Predictive maintenance solutions can help reduce costs while also eliminating the need for planned downtime in many cases, which strengthens the bottom line and improves the employee experience.

By preempting a failure with machine learning, systems can continue to function without unnecessary interruptions or delays. The maintenance that is needed is very focused – technicians are informed of the components that need inspection, repair, and replacement; which tools to use, and which methods to follow.

Predictive maintenance also leads to a longer Remaining Useful Life (RUL) of machinery and equipment since secondary damage is prevented while smaller labor forces are needed to perform maintenance procedures. Improving RUL can increase sustainability efforts and reduce waste.

#3: Human-Robot Collaboration

According to the International Federation of Robotics (IFR), roughly 1.64 million industrial robots are in operation worldwide as of 2020. There are fears of robots taking jobs, but the industry is seeing workers embrace training for higher-level positions in programming, design, and maintenance.

Humans are also working alongside robots to improve efficiency and productivity on the factory floor and beyond. AI will play a significant role as robots become more ingrained in manufacturing. It will ensure the safety of human workers as well as give robots more autonomy to make decisions that can further optimize processes based on real-time data collected from the production floor.

#4: Generative Design

Manufacturers can also make use of artificial intelligence in the design phase. With a clearly defined design brief as input, designers, and engineers can make use of an AI algorithm, generally referred to as generative design software, to explore all the possible configurations of a solution.

The brief can include restrictions and definitions for material types, production methods, time constraints, and budget limitations. The set of solutions generated by the algorithm can then be tested using machine learning. The testing phase provides additional information about which ideas or design decisions worked, and which did not. From there, additional improvements can be made until an optimal solution is reached.

#5: Market Adaptation & Supply Chain

Artificial intelligence permeates the entire Industry 4.0 ecosystem and it is not limited to the production floor. AI algorithms can optimize the supply chain of manufacturing operations and help manufacturers better respond to, and anticipate, the changing market. 

An algorithm can construct estimations of market demand by taking into account demand patterns categorized by a multitude of factors like date, location, socioeconomic attributes, macroeconomic behavior, political status, weather patterns, and more. Manufacturers can use this information to plan for the road ahead. A few processes that can be optimized with these insights include inventory control, staffing, energy consumption, raw materials, and financial decisions.

Industry 4.0 & Collaboration

AI is trendy but it requires collaboration to get it right. To get started, manufacturers should weigh the pros and cons of buying vs. building the required technology and expertise. An Industry 4.0 system consists of a number of elements and phases that are unique to the manufacturer:

  • Historical data collection.
  • Live data capturing via sensors.
  • Data aggregation.
  • Connectivity via communication protocols, routing, and gateway devices.
  • Integration with PLCs.
  • Dashboards for monitoring and analysis.
  • AI Applications: machine learning and other techniques.

Industrial AI is no longer a far-off aspiration. Manufacturers can use these technologies today to meet their specific business challenges and needs. As Industry 4.0 evolves with more complexity, manufacturers will require the agility and visibility made possible by artificial intelligence.

Tweet

Share

Share

Email

  • Artificial Intelligence
  • Industrial Automation
  • Industry 4.0
  • Manufacturing
  • Predictive Analytics

  • Artificial Intelligence
  • Industrial Automation
  • Industry 4.0
  • Manufacturing
  • Predictive Analytics

参考译文
人工智能:工业4.0的驱动力
很多围绕制造业人工智能的炒作都集中在工业自动化上,但这只是智能工厂革命的一个方面——追求效率的自然下一步。人工智能还为制造业带来了揭示商业新途径的能力。我们将概述人工智能在推动工业自动化方面的能力,并作为新兴工业4.0范式的一部分开辟新的商业机会。此外,我们还将介绍这种强大的技术是如何被制造商用于提高效率、提高质量和更好地管理供应链的。减少生产损失和防止生产过程效率低下一直是所有行业制造商面临的挑战。今天,随着需求的增长和竞争的加剧,这一点一如既往。一方面,消费者的期望很高;全球的消费习惯正在逐渐“西方化”,即使人口激增仍在继续。根据近年来的众多调查,到2050年,全球人口将增长25%,相当于每天增加20万张嘴。另一方面,消费者从未有过如此多的产品可供选择。最近的调查显示,如此丰富的选择意味着消费者越来越有可能永远放弃他们最喜欢的品牌,比如,如果货架上没有产品的话。考虑到这些趋势,制造商再也不能接受工艺效率低下及其相关的损失。在浪费、产量、质量或产量方面的每一次损失都在侵蚀他们的底线,并将另一英寸拱手让给竞争对手——假设他们的生产过程更高效。许多制造商面临的挑战——尤其是那些工艺复杂的制造商——是他们最终在工艺优化方面遇到了瓶颈。一些低效率没有明显的根本原因,这使得流程专家无法解释它们。使用人工智能驱动的流程和机器健康解决方案来预测质量和产量,以揭示制造商面临的许多长期生产损失的隐藏原因。这是通过持续的多元分析来完成的,使用机器学习算法,这些算法经过独特的训练,可以深入了解各个生产过程。这里使用的特定AI/机器学习技术被称为监督学习,这意味着算法经过训练,可以识别数据中的趋势和模式。然后可以自动生成建议和警报,将即将发生的问题通知生产团队和工艺工程师,并无缝共享关于如何在损失发生之前预防损失的重要知识。预测性维护是工业人工智能最著名的应用之一。预测性维护不是根据预定的时间表执行维护,而是使用算法来预测组件、机器或系统的下一次故障,然后提醒人员执行集中维护程序以防止故障。这些警报在正确的时间发生,以免浪费不必要的停机时间。这些维护系统依靠无监督的机器学习技术来制定预测。预测性维护解决方案可以帮助降低成本,同时在许多情况下还可以消除计划停机的需要,从而加强底线并改善员工体验。通过机器学习先发制人,系统可以在没有不必要的中断或延迟的情况下继续运行。所需要的维护是非常集中的——技术人员被告知需要检查、修理和更换的部件;使用哪些工具,遵循哪些方法。 预测性维护还可以延长机器和设备的剩余使用寿命(RUL),因为防止了二次损坏,而执行维护程序所需的劳动力更少。改善RUL可以增加可持续性努力并减少浪费。根据国际机器人联合会(IFR)的数据,截至2020年,全球约有164万台工业机器人投入使用。人们担心机器人会抢走工作,但该行业看到工人们接受了编程、设计和维护等更高层次职位的培训。人类还与机器人一起工作,以提高工厂车间和其他地方的效率和生产力。随着机器人在制造业中越来越根深蒂固,人工智能将发挥重要作用。它将确保人类工人的安全,并赋予机器人更大的自主权,从而根据从生产车间收集的实时数据进一步优化流程。制造商也可以在设计阶段利用人工智能。通过明确定义的设计概要作为输入,设计师和工程师可以使用AI算法(通常称为生成设计软件)来探索解决方案的所有可能配置。概要可以包括对材料类型、生产方法、时间限制和预算限制的限制和定义。然后,算法生成的解决方案集可以使用机器学习进行测试。测试阶段提供了关于哪些想法或设计决策有效,哪些无效的额外信息。在此基础上,可以进行额外的改进,直到达到最佳解决方案。人工智能渗透在整个工业4.0生态系统中,并不局限于生产车间。人工智能算法可以优化制造运营的供应链,帮助制造商更好地应对和预测不断变化的市场。一种算法可以通过考虑按日期、地点、社会经济属性、宏观经济行为、政治地位、天气模式等多种因素分类的需求模式来构建市场需求的估计。制造商可以利用这些信息来规划未来的道路。可以通过这些见解优化的一些流程包括库存控制、人员配备、能源消耗、原材料和财务决策。人工智能是一种潮流,但它需要合作才能做好。首先,制造商应该权衡购买和建造所需的技术和专业知识的利弊。工业4.0系统由制造商独有的许多元素和阶段组成:工业人工智能不再是一个遥远的愿望。如今,制造商可以使用这些技术来满足他们特定的业务挑战和需求。随着工业4.0的发展变得越来越复杂,制造商将需要人工智能带来的灵活性和可见性。
您觉得本篇内容如何
评分

评论

您需要登录才可以回复|注册

提交评论

提取码
复制提取码
点击跳转至百度网盘