Changing the Corrugated Manufacturing Industry With Anomaly Detection Software

SUN 与 Very 合作开发了 Helios，一种硬件和软件边缘计算解决方案，用于促进机器数据的收集和分析。通过丰富的数据展示、异常检测和问题报告，该解决方案提供了对机器健康状况的更深入理解，使用户能够在故障发生前预测（并预防）机器故障。

项目挑战

瓦楞纸制造业与许多其他工业领域一样，正在经历快速变革。 随着资深操作人员和维护工人退休或转行，他们带走了对工厂机器根深蒂固的知识。企业需要一种可扩展、可持续的方式来理解和可靠地预测机器健康——无论是现在还是未来。

作为向全球工厂供应瓦楞纸机械的顶级供应商，SUN 设想构建一个前沿的解决方案来为客户解决这个问题。时间紧迫：SUN 必须快速上市，在新兴第三方产品面前占据竞争优势。

牵头这一计划的是 Matthew Miller，SUN 的技术总监，也是 GE 的前技术领导者。Matt 正在寻找一个值得信赖的、拥有机器学习专长的技术合作伙伴。 他找到了许多能够构建 IIoT 平台的供应商，但没有一个能包含一个关键要素：异常检测软件。 此外，作为一名认证 Scrum Master，Matt 希望与敏捷团队合作。

在了解了我们过去的客户以及我们在敏捷和机器学习专长后，Matt 与我们的解决方案架构团队安排了一次会议。

"从第一次会议起，Very 的流程和技能就给我留下了深刻印象，"Matt 说。"他们能够迅速深入到项目的核心细节中。"

实施过程

SUN 已经进行了财务分析来预测产品的市场表现。还需要额外的产品研究，以确保产品能够满足潜在客户的需求。

项目以技术设计冲刺拉开序幕。 在这一初始发现阶段，我们深入挖掘了 Helios 背后的驱动力：产品用户是谁？什么对他们最重要？

Our research indicated that SUN customers wanted a solution that would give them real-time insights into machine health, as well as the ability to understand how the machines are performing over time through aggregate metrics. Helios would also need to cater to SUN admin users and provide them with full control of the system, including the ability to add users, customers, and machines, manage firmware, customize alerts, and use the API. 

After our initial discovery phase, SUN applied some of Very’s research techniques, such as a customer questionnaire, to their other R&D and product development efforts. 

“What Very brings to the table are those soft skills and the ability to help you through the strategic pieces of your project,” Matt says. “That’s something I’ve never found with any firm that I’ve dealt with before, and I’ve definitely dealt with a lot of firms.”

Following the Technical Design Sprint, we completed the build using our Agile IoT development process. Helios includes an edge computer that queries existing machine programmable logic controllers (PLCs) for relevant data through common industrial protocol (CIP) over EtherNet/IP. That data is sent to a cloud backend, which includes services for machine learning, databases for application data and long-term storage, and a web application with a responsive user interface. Product users now have critical information regarding their corrugated converting equipment at their fingertips.

We placed particular emphasis on anomaly detection and aggregate measures to lock in the machine learning processes. Once we collected enough data from the PLC, we could design machine learning models that can detect anomalous behavior in converting machines. 

Below, you’ll find the tech stack for each project component:

• Firmware: Nerves and NervesHub for the gateway device
• Hosting: AWS
• Data pipeline: AWS IoT, AWS Lambda, and AWS Kinesis Firehose – all coordinated through Serverless Framework
• Data storage: Application data stored in AWS RDS, with long-term storage in AWS S3 
• Web application: Phoenix framework and React for front end

“The Very team is knowledgeable, and they deliver. They’ve delivered everything they’ve promised in the timeframe that they’ve promised it.”

Chris Kyger
President, SUN Automation

项目成果

项目启动仅五个多月后，Very 就为 SUN 提供了一套稳健的异常检测预测性维护解决方案。 如今，SUN 享有竞争优势——为先进异常检测模型的未来设定标准——而他们的客户也在享受 Helios 的好处，预测故障、减少计划外停机时间并优化纸箱工厂的生产力。

准备好打造 IoT 领域的下一个重大创新了吗？Very 可以帮助您

Very 不仅仅是另一家 IoT 技术提供商。虽然我们确实帮助客户构建和部署创新的 IoT 解决方案，但我们首先是值得信赖的技术合作伙伴。这意味着我们从第一天起就全心投入客户的成功，并采取战略性、有意识的步骤帮助他们超越目标。他们的使命就是我们的使命。如果您希望我们帮助您将改变行业的 IoT 解决方案推向市场，请联系我们。

想要带走 SUN Automation 的成功案例？Download the full PDF case study →