iPredicta RIOT

该项目涉及两个政府优先事项...提高制造业中小企业的生产率和减少碳足迹，以在2050年前实现净零。制造业中小企业的一项主要资本支出成本是新厂房和设备，如数控或AM机床。然而，由于缺乏实时机器数据、商业智能应用程序和计划系统，许多中小企业在已使用的工厂下运营，这不仅影响了生产率，还浪费了能源。然而，机器监控解决方案上市已有20多年，尽管对生产率有潜在影响，我们调查了400多家英国制造业客户中具有代表性的样本，以了解他们为什么以前没有采用机器监控技术，他们的保留意见如下：*硬件和软件成本*工厂集成和实施服务的复杂性和成本*缺乏系统灵活性FitFactory已经开始开发一种超低成本的振动检测传感器，可以使用磁铁连接到任何机器的外部。我们的FitFactory Business Intelligence应用程序--Insights--与不同的ERP系统和我们的快速物联网振动传感器无缝连接，不仅提供利用率数据和自动化警报，而且还能自动发出警报还为生产团队提供了可操作的见解和风险，以监控和添加他们学到的经验。然而，要创建一个改变游戏规则的平台，我们必须部署可轻松应用于多个用例的机器学习人工智能，通过获取传感器振动数据，并分析吸取的经验教训，创建一种智能预测工具，使操作员能够做出更明智的车间规划决策，将停机时间和能源使用降至最低。通过与领先的英国RTO合作，我们相信，我们能够克服复杂的分析挑战，创建一个可以快速配置和规模化部署的直观平台，以加快中小企业制造工厂利用率的优化至少10%，并减少5%的能源消耗。STFC将提供专家支持，以创建灵活的机器学习解决方案，该解决方案可以应用于所有制造工厂和设备，可以以最低的成本快速配置，使用生产操作员的简单用户界面来捕获停机的各种定性根本原因分析，结合定量工厂利用率分析来预测机床磨损，并通过改进的计划决策支持来减少停机时间。

This project addresses 2 Government priorities...improving productivity of manufacturing SMEs and reducing carbon footprint to achieve net zero by 2050\.A major capex cost for manufacturing SMEs is new plant & equipment such as CNC or AM machines. However due to a lack of real-time machine data, business intelligence applications and planning systems, many SMEs operate under utilised plant which not only impacts productivity but also wastes energy.Machine monitoring solutions have been on the market for more than 20 years however, despite the potential impact on productivity, their adoption has been limited especially within the SME sector.We surveyed a representative sample of our 400+ UK manufacturing clients to understand why they had not adopted machine monitoring technologies previously and their reservations were as follows:* cost of hardware and software* complexity and cost of plant integration and implementation services* lack of systems flexibilityFitfactory have started to address these challenges by developing a super low cost vibration detection sensor that can be attached to the outside of any machine using magnets.Our Fitfactory Business Intelligence application -- Insights - connects seamlessly with disparate ERP systems and our Rapid IOT vibration sensor to not only present utilisation data and automate alerts but also generates actionable insights and risks for production teams to monitor and add their lessons learned.However, to create a game-changing platform, we must deploy machine learning AI that can be easily applied for multiple use cases, by taking the sensor vibration data, and analysing the lessons learned, to create an intelligent prediction tool that empowers operators so that they can make more informed shop floor planning decisions to minimise downtime and energy usage.By collaborating with a leading UK RTO, we are confident that we can overcome the complex analytical challenges to create an intuitive platform that can be rapidly configured and deployed at scale to accelerate the optimisation of SME manufacturing plant utilisation by at least 10% and reduce energy usage by 5%.STFC will provide specialist support to create a flexible machine learning solution that be applied to all manufacturing plant and equipment that can be quickly configured, at minimum cost, using a simple user interface for production operators to capture various qualitative root cause analysis reasons for downtime, combined with quantitative plant utilisation analysis to predict machine tool wear and to mitigate downtime through improved planning decision support.