All Member Open Forum

Hi Juned

There are some great solutions out there and although I am biased, I currently work for VIETECHNOLOGIES and we have a fantastic predictive maintenance solution.  If possible I would love to help.

Prior to my new role, I worked for Johnson controls and spend a lot of time with the predictive analytics team reviewing new technologies and solutions in the PdM space. I am be happy to share information with you on solutions that exist beyond what VIE offers.

Good luck and hope to support you in anyway I can!

Christine
cwitte@vietechnologies.com
702-221-0055

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

(I went on amazon, searched for "electronic gadget" and took the "decision map" for the first search hit. Replace each gadget with a predictive analytics software offering, and each row as a different evaluation criteria).   In other words, the results of this would be a consumer reports type thing, but part of the results would be a set of criteria for identifying vendors.

What you are talking about is developing a framework for selection of where and when applying predictive analytics technology in your business is appropriate.  This is related to but not the same as vendor determination.  For determining vendors, I'm assuming you've already identified your use cases where it is both physically feasible and makes business sense and possibly just need some cost information to weight the benefits.  

If there's a greater interest in discussing determining where to use predictive analytics technologies in this thread, let's just be clear about where in the pipeline we're talking so we're not all over the place. It makes sense to keep this themed conversation in one place.
Classical RCM is a great philosophical approach for these things, but often in practice is exhaustive and too much.  Some practical modifications help depending on the application.  For example, for predictive technologies it's going to be expensive, so you only really need to look at high critical assets. 

There is a master's thesis on exactly this topic that I think is fabulous - we don't need to rethink a lot of this stuff, Ruben Milje has done a fantastic job already:  https://uis.brage.unit.no/uis-xmlui/handle/11250/182746
Milje, Ruben. Engineering methodology for selecting condition based maintenance. MS thesis. University of Stavanger, Norway, 2011.

It's written specifically for CBM, but most of everything described applies to predictive technologies.
As a sample, here's a summary flowchart from the thesis to help select if CBM is appropriate:

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

(I went on amazon, searched for "electronic gadget" and took the "decision map" for the first search hit. Replace each gadget with a predictive analytics software offering, and each row as a different evaluation criteria).   In other words, the results of this would be a consumer reports type thing, but part of the results would be a set of criteria for identifying vendors.

What you are talking about is developing a framework for selection of where and when applying predictive analytics technology in your business is appropriate.  This is related to but not the same as vendor determination.  For determining vendors, I'm assuming you've already identified your use cases where it is both physically feasible and makes business sense and possibly just need some cost information to weight the benefits.

If there's a greater interest in discussing determining where to use predictive analytics technologies in this thread, let's just be clear about where in the pipeline we're talking so we're not all over the place. It makes sense to keep this themed conversation in one place.
Classical RCM is a great philosophical approach for these things, but often in practice is exhaustive and too much.  Some practical modifications help depending on the application.  For example, for predictive technologies it's going to be expensive, so you only really need to look at high critical assets.

There is a master's thesis on exactly this topic that I think is fabulous - we don't need to rethink a lot of this stuff, Ruben Milje has done a fantastic job already:  https://uis.brage.unit.no/uis-xmlui/handle/11250/182746
Milje, Ruben. Engineering methodology for selecting condition based maintenance. MS thesis. University of Stavanger, Norway, 2011.

It's written specifically for CBM, but most of everything described applies to predictive technologies.
As a sample, here's a summary flowchart from the thesis to help select if CBM is appropriate:

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

HI Sarah,

I love simple, you know me I am simple.
Having worked with implementing predictive technologies RCM decision logic is at the core of any implementation.  Is installing a sensor or capturing an already installed sensors data worth doing.  Is IR/VIB/Ultrasound/MCA/Motion Amplification or the next tech to hit the field an applicable and effective task if implemented to mitigate the failure. Does it provide value to implement, monitor and analyze?
I've seen various offerings for analyzing and displaying the data, the decision is what makes sense, is it cost effective and meet your needs/wants.  Face it we and our companies don't always purchase just what meets our needs, sometimes we want the "Bells and Whistles". That's why I don't drive a basic work truck with crank windows and vinyl seats.

I started analyzing data as Watchstander on equipment many years ago recording and analyzing readings on a log sheet.  I finished my watchstanding career monitoring a computerized control board and reviewing/analyzing the hourly data capture sheet.  It was frustrating that 20 years ago the organization did not have the capability to capture that data and trend it for me, because the capability was there but not affordable.  Back then it was a manual effort to put the data in Excel and look for and set up scripts to identify trends.
Data capture and analytics is now affordable, machine learning is improving as more data is captured.   The platform utilized to capture, analyze and display your data dependent on what you can afford and works for you.

I started out with log sheets and graph paper and finished up with data transfers to Excel.  I envy the tools that are available now and think a decision assistant to outline the capabilities of the various offerings is needed and would be well received. Maybe something for Plant Services or another independent magazine or organization like SMRP to support.

This article basically sums up my comments, I wasn't a submariner but my experiences were similar.
Plant Services Article A-Navy-Perspective-On-Predictive-Maintenance

(I went on amazon, searched for "electronic gadget" and took the "decision map" for the first search hit. Replace each gadget with a predictive analytics software offering, and each row as a different evaluation criteria).   In other words, the results of this would be a consumer reports type thing, but part of the results would be a set of criteria for identifying vendors.

What you are talking about is developing a framework for selection of where and when applying predictive analytics technology in your business is appropriate.  This is related to but not the same as vendor determination.  For determining vendors, I'm assuming you've already identified your use cases where it is both physically feasible and makes business sense and possibly just need some cost information to weight the benefits.

If there's a greater interest in discussing determining where to use predictive analytics technologies in this thread, let's just be clear about where in the pipeline we're talking so we're not all over the place. It makes sense to keep this themed conversation in one place.
Classical RCM is a great philosophical approach for these things, but often in practice is exhaustive and too much.  Some practical modifications help depending on the application.  For example, for predictive technologies it's going to be expensive, so you only really need to look at high critical assets.

There is a master's thesis on exactly this topic that I think is fabulous - we don't need to rethink a lot of this stuff, Ruben Milje has done a fantastic job already:  https://uis.brage.unit.no/uis-xmlui/handle/11250/182746
Milje, Ruben. Engineering methodology for selecting condition based maintenance. MS thesis. University of Stavanger, Norway, 2011.

It's written specifically for CBM, but most of everything described applies to predictive technologies.
As a sample, here's a summary flowchart from the thesis to help select if CBM is appropriate:

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

(I went on amazon, searched for "electronic gadget" and took the "decision map" for the first search hit. Replace each gadget with a predictive analytics software offering, and each row as a different evaluation criteria).   In other words, the results of this would be a consumer reports type thing, but part of the results would be a set of criteria for identifying vendors.

What you are talking about is developing a framework for selection of where and when applying predictive analytics technology in your business is appropriate.  This is related to but not the same as vendor determination.  For determining vendors, I'm assuming you've already identified your use cases where it is both physically feasible and makes business sense and possibly just need some cost information to weight the benefits.

If there's a greater interest in discussing determining where to use predictive analytics technologies in this thread, let's just be clear about where in the pipeline we're talking so we're not all over the place. It makes sense to keep this themed conversation in one place.
Classical RCM is a great philosophical approach for these things, but often in practice is exhaustive and too much.  Some practical modifications help depending on the application.  For example, for predictive technologies it's going to be expensive, so you only really need to look at high critical assets.

There is a master's thesis on exactly this topic that I think is fabulous - we don't need to rethink a lot of this stuff, Ruben Milje has done a fantastic job already:  https://uis.brage.unit.no/uis-xmlui/handle/11250/182746
Milje, Ruben. Engineering methodology for selecting condition based maintenance. MS thesis. University of Stavanger, Norway, 2011.

It's written specifically for CBM, but most of everything described applies to predictive technologies.
As a sample, here's a summary flowchart from the thesis to help select if CBM is appropriate:

• Relevant use cases - there is no one magic predictive analytic modeling solution.  Some software will be stronger for different use cases than others, and this could span failure mode characterizations, equipment catalogues, industrial application, etc.
• Verticals proven effective - such as oil and gas, aviation, manufacturing, mining, etc. What industries is this software been proven to be used in effectively?  
• Integration with various "stuff" (need to work out what the different "stuff" are) - but I mean, a model working in isolation is not practical - a solution needs to integrate with work processes, asset strategies that are in place, different other software platforms in use, etc. so that alerts can be timely and the right actions can be taken in the right way at the right time
• Deployment options - such as on-prem or in the cloud (or both), is there a managed services options, etc.
• ...

Hi Juned

There are some great solutions out there and although I am biased, I currently work for VIETECHNOLOGIES and we have a fantastic predictive maintenance solution.  If possible I would love to help.

Prior to my new role, I worked for Johnson controls and spend a lot of time with the predictive analytics team reviewing new technologies and solutions in the PdM space. I am be happy to share information with you on solutions that exist beyond what VIE offers.

Good luck and hope to support you in anyway I can!

Christine
cwitte@vietechnologies.com
702-221-0055

Hi Juned

There are some great solutions out there and although I am biased, I currently work for VIETECHNOLOGIES and we have a fantastic predictive maintenance solution.  If possible I would love to help.

Prior to my new role, I worked for Johnson controls and spend a lot of time with the predictive analytics team reviewing new technologies and solutions in the PdM space. I am be happy to share information with you on solutions that exist beyond what VIE offers.

Good luck and hope to support you in anyway I can!

Christine
cwitte@vietechnologies.com
702-221-0055