In order to achieve the greatest success with our clients, it is essential that those seeking digital transformation have an understanding of what they need and the services Predictronics provides, our team background and how those skills translate into customer ROI, as well as tips and best practices for adopting and deploying predictive analytics for their industrial assets. This blog series aims to address these many quandaries, with knowledge the Predictronics team has acquire from our years of experience, in order to help others to make the right decisions regarding their data and asset management.

When planning for predictive, and later developing and managing a solution, Predictronics customers frequently have the same common questions for our team concerning their data availability and quality, the role of their own team members, the functionality of our software, the proof of value process, and more. In this second installment of our series, we have gathered a select handful of the most popular pre-deployment questions asked by customers and our responses, regarding the solution building process, our approach, and their involvement. Our expertise will help guide you through your own preparations.

How much data is needed before the predictive solution comes online?

The period of data required hinges on two main factors: how often the machine runs and whether it is currently healthy. For a healthy machine that runs daily, Predictronics has found that two weeks of data collection is usually adequate enough to form a baseline.

Do I have to be collecting data all the time?

Data does not need to be collected constantly. Specifically, Predictronics’ predictive software platform, PDX, offers the ability to trigger data collection based on certain conditions, such as a specific program ID run on the machine. By only collecting data relevant to the predictive application, you achieve a more accurate predictive model while also saving on data storage.

How much routine, manual effort is required to provide the solution with the data it needs?

Very little manual effort is required. Our PDX platform has access to the sensors and hardware it needs. The requisite data from the machine is automatically collected by our data acquisition application in PDX. The Predictronics team then develops the predictive model/s and sets failure threshold parameters. Finally, the end-user sees data insights and receives failure pattern alerts through the data visualization dashboard in PDX.

The only efforts required of your team would be routine backup and cleaning of old data to make space for new data, as well as troubleshooting, if necessary.

My data is sensitive and it can't reside on the public cloud. Is there an alternative, more secure deployment strategy?

Yes, Predictronics has several customers with similar data security concerns. Our team supports on-premise deployments for proof of value engagements and then recommends virtual, private clouds when scaling the solution.

Do we create the predictive models? How are the models updated?

The models are created by Predictronics and reviewed with the customer before deployment. In addition, our team can update the models, if the need arises. Although, that may carry service charges depending on the extent of modification.

Who sets the model threshold? Can we change it?

The model comes with Predictronics’ recommended failure thresholds. Although, our team can always modify the model to be more or less sensitive to increase accuracy of alerts or prevent false alarms.

How will my maintenance team know when to look at the asset?

For your team members that need immediate notification when a failure event occurs, our PDX solution offers the ability to configure alerts in the data visualization dashboard. We also offer regular email reports, for a quick overview of machine health.

When pursuing predictive, you want to make sure you have personnel with the right level of knowledge and experience to help guide your internal team through the process of setting up, deploying, and maintaining your solution.

In part three of our series, we will highlight our approach and our own solution development team, along with their background and skill sets, which will give you an understanding of what areas of expertise are needed.

Read the first installment of our blog series to learn the most popular pre-engagement questions asked by customers and our responses.