# Tensorflow Integration **URL:** \ **Category:** Ignition\ **Created:** [March 25, 2019, 9:40pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584 "2019-03-25T21:40:45Z")\ **Posts on this page:** 18\ **Page:** 1
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 25, 2019, 9:40pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/1 "2019-03-25T21:40:45Z")
Does Ignition support Machine Learning frameworks such as Tensorflow? ---
**Author:** ![Kevin.Herron](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kevin.herron/32/7259_2.png) [@Kevin.Herron](https://forum.inductiveautomation.com/u/Kevin.Herron)\ **Post date:** [March 26, 2019, 1:07am UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/2 "2019-03-26T01:07:36Z")
What would support for Tensorflow look like to you? ---
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 26, 2019, 10:24pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/3 "2019-03-26T22:24:12Z")
So, for the moment it’s very basic: My primary question is how does Tensorflow, or any ML/AI framework, interact with the core logic of the Ignition platform supervisory capabilities? Other questions: Are there any limitations, that you (inductive automation) are aware of (Ignition \<–\> Tensorflow)? If so, can you (briefly) reply to the most important? Basically, we are trying to implement a AI/ML platform for renewable energy applications, that means stand-alone power plants with minimal human interaction. We like what we see with the Ignition platform, but we would like to ensure compatibility before we move forward, or at least be reasonably sure that there are no major incompatibility issues. ---
**Author:** ![Kevin.Herron](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kevin.herron/32/7259_2.png) [@Kevin.Herron](https://forum.inductiveautomation.com/u/Kevin.Herron)\ **Post date:** [March 26, 2019, 10:36pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/4 "2019-03-26T22:36:56Z")
I’ve read this 3 times and I still can’t really figure out what you’re asking. Maybe you can define your question in terms of what kinds of data is an input to tensorflow and an output from Ignition, and/or the other way around. ---
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 26, 2019, 10:51pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/5 "2019-03-26T22:51:28Z")
To go into that level of detail would get too involved (for the time being). Perhaps a better way of asking the question is do you see any major issues or incompatibilities with integration between Ignition and AI/ML frameworks such as Tensorflow? There is no information (that I could find, anyway) that covers Ignition integration or control under AI/ML. This was a round-about inquiry if it’s at all possible. ---
**Author:** ![Kevin.Herron](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kevin.herron/32/7259_2.png) [@Kevin.Herron](https://forum.inductiveautomation.com/u/Kevin.Herron)\ **Post date:** [March 26, 2019, 10:58pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/6 "2019-03-26T22:58:57Z")
We have no Tensorflow or other ML-specific integrations, but the realtime and historical data in Ignition is easily accessible. I can’t really tell you anymore than that if you can’t provide actual details. There certainly aren’t just `doMachineLearning()` hooks everywhere in the platform if that’s what you’re asking, but again, I really can’t tell. ---
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 26, 2019, 11:02pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/7 "2019-03-26T23:02:24Z")
Funny! I’ll circle back when I have more time to devote to this question. Thank you! ---
**Author:** ![Kevin.Herron](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kevin.herron/32/7259_2.png) [@Kevin.Herron](https://forum.inductiveautomation.com/u/Kevin.Herron)\ **Post date:** [March 26, 2019, 11:03pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/8 "2019-03-26T23:03:56Z")
There’s also a module SDK that lets you hook into the platform and get access to a bunch of stuff you might not otherwise have access to, which could be another avenue for integration. ---
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 26, 2019, 11:06pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/9 "2019-03-26T23:06:09Z")
Thank you!! Could you point to that SDK? That may be the solution. ---
**Author:** ![Kevin.Herron](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kevin.herron/32/7259_2.png) [@Kevin.Herron](https://forum.inductiveautomation.com/u/Kevin.Herron)\ **Post date:** [March 26, 2019, 11:11pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/10 "2019-03-26T23:11:07Z")
It’s not so much a thing you download as it is a set of outdated documentation and examples… [https://docs.inductiveautomation.com/display/SE/Ignition+SDK+Programmers+Guide](https://docs.inductiveautomation.com/display/SE/Ignition+SDK+Programmers+Guide) [https://files.inductiveautomation.com/sdk/javadoc/ignition80/8.0.0-beta/index.html](https://files.inductiveautomation.com/sdk/javadoc/ignition80/8.0.0-beta/index.html) [https://github.com/inductiveautomation/ignition-sdk-examples](https://github.com/inductiveautomation/ignition-sdk-examples) The actual API artifacts are hosted in a Nexus server that your project will automatically download when it resolves dependencies, assuming you use a sane build tool. ---
**Author:** ![blainob](https://avatars.discourse-cdn.com/v4/letter/b/4bbf92/32.png) [@blainob](https://forum.inductiveautomation.com/u/blainob)\ **Post date:** [March 26, 2019, 11:26pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/11 "2019-03-26T23:26:53Z")
Thank you very much! ---
**Author:** ![pturmel](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/pturmel/32/3295_2.png) [@pturmel](https://forum.inductiveautomation.com/u/pturmel)\ **Post date:** [March 27, 2019, 3:25am UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/12 "2019-03-27T03:25:32Z")
> [@Kevin.Herron](#): > > use a sane build tool. Hah! And where would one find this sane build tool? 😛 ---
**Author:** ![grietveld](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/grietveld/32/6984_2.png) [@grietveld](https://forum.inductiveautomation.com/u/grietveld)\ **Post date:** [March 27, 2019, 11:47am UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/13 "2019-03-27T11:47:25Z")
I would maybe check out the couple of Webinars that have been done on this topic by IA. They dont dive into the details too much but have some good examples. There are a couple of Apache Common Math libraries that have the ability to do some basic machine learning tasks. There is an example of a K-Means algorithm, and the library seems to have the ability to do some neural net type applications, but I haven’t had time to sort through how just yet. I think the main issue that you’d run into trying to use a Tensorflow API is that the Java version is still experimental, so it may not be as supported as the other libraries they have. ---
**Author:** ![dkhayes117](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/dkhayes117/32/68344_2.png) [@dkhayes117](https://forum.inductiveautomation.com/u/dkhayes117)\ **Post date:** [March 27, 2019, 12:24pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/14 "2019-03-27T12:24:31Z")
> [@](#): > > Django is like MQTT OPC UA server for Ignition. It’s rock solid, highly secured and the world’s most powerful Python server. You can run state of the art ML algorithms like Tensor flow on Django. This makes Ignition as “ML powered SCADA”. @R.Alamsha posted this in another thread a while back. I'm not sure on it's validity, but it may be worth looking into. ---
**Author:** ![KathyApplebaum](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/kathyapplebaum/32/7261_2.png) [@KathyApplebaum](https://forum.inductiveautomation.com/u/KathyApplebaum)\ **Post date:** [March 27, 2019, 1:56pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/15 "2019-03-27T13:56:43Z")
You may want to check out one of our strategic partners, Cirrus Link. They have modules to link your Ignition data to a few of the major cloud ML platforms (AWS, Azure, etc.) We do have plans to add more ML integration in the future, but those plans aren’t yet to the stage where I can say anything meaningful about them. 🙂 ---
**Author:** ![louagejasper](https://sea1.discourse-cdn.com/inductiveautomation/user_avatar/forum.inductiveautomation.com/louagejasper/32/86311_2.png) [@louagejasper](https://forum.inductiveautomation.com/u/louagejasper)\ **Post date:** [March 16, 2021, 10:28am UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/16 "2021-03-16T10:28:06Z")
I wonder. Are these plans more concrete now? It surely would be interesting to be able to simply add the Python TensorFlow library and do the machine learning in Ignition. I think with the easy visualisations in Ignition, you could really get some good value out of it. ---
**Author:** ![sanjanakrishnamurthy](https://avatars.discourse-cdn.com/v4/letter/s/bcef8e/32.png) [@sanjanakrishnamurthy](https://forum.inductiveautomation.com/u/sanjanakrishnamurthy)\ **Post date:** [February 24, 2026, 8:30am UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/17 "2026-02-24T08:30:50Z")
Hi, Any updates on this with the current development of AI/ML? ---
**Author:** ![Chris\_Bingham](https://avatars.discourse-cdn.com/v4/letter/c/e5b9ba/32.png) [@Chris\_Bingham](https://forum.inductiveautomation.com/u/Chris_Bingham)\ **Post date:** [February 24, 2026, 1:25pm UTC](https://forum.inductiveautomation.com/t/tensorflow-integration/23584/18 "2026-02-24T13:25:26Z")
There has been lots of developments over the years. Perhaps no magic / easy button, but lots to get a data engineer started: > **[Using Ignition with Machine Learning Libraries](https://inductiveautomation.com/resources/icc/2022/using-ignition-with-machine-learning-libraries)** > > Using Ignition and machine learning libraries can be a powerful combination. Inductive Automation's machine learning experts will lead conference attendees through practical applications for ML, along with typical ML setups that Ignition users could... > **[Ignition Exchange](https://inductiveautomation.com/exchange/2365/overview)** > > Discover, share, and download community made Ignition resources in collaboration with your organization or the Ignition community. > [@MCP Module Early Access](https://forum.inductiveautomation.com/t/mcp-module-early-access/113966): > > MCP Module Early Access We are excited to announce the Early Access (EA) release of the new MCP Module for Ignition. This initial, limited-scope release is designed to demonstrate IA's commitment to the emerging AI landscape, providing a streamlined way to use Ignition to connect OT data with external Large Language Model (LLM) clients and tools. This module requires a nightly build of the Ignition platform to run until the full release of Ignition 8.3.5. What is the Early Access MCP Module? T… I’m certain there are others…