Tag

pattern recognition software

Intuitive IoT Machine Learning

By | IT/OT Management

Since the Falkonry Service was released, numerous users across several industries have used it to understand their #IoT data and recognize conditions. Their objectives are to prevent undesirable outcomes such as failures and low performance/yields. These industries range from power generation and transportation to agriculture, and building management to automotive and steel production. Our users are mostly non-data scientists and seek a solution that they can create and manage. At times, data scientists prefer Falkonry since it can do one thing really well – provide visibility of conditions without much effort.

Falkonry Service

 

Falkonry Service–now it’s easier

Taking into account all of the feedback we received from our users, we have redesigned the Falkonry Service to be simpler and yet more powerful. You can more easily work with many things, assessments, and conditions. This new User Interface has been rolled out to all users. Here’s an overview of this new design.

By distilling the raw information down to a one-dimensional timeline, Falkonry simplifies understanding of high speed, multivariate IoT data. The main design improvement in the updated UI is that you can understand Falkonry’s findings, at a macro level, instantly and drill down in terms of time and things easily. As you can see in the design, there’s the ability to compare the performance of two or more things side by side. Simultaneous visualization of conditions across things means that conditions can be interpreted comparatively.

image

Secondly, both live monitoring and learning views are designed to be analogous, which makes it easier to understand both. The seamless transition from learning to monitoring also means that users can drill-in from high level summary of conditions across an entire fleet, to a single individual thing for a particular period in time where a certain condition arises.

image

One thing that did not change is that it is just as easy to learn new predictive models without knowing data science or programming. Users can still easily annotate Falkonry’s findings and confirm the conditions visually, as well as in bulk through files.

image

Next, menus have been simplified so that our users can easily find the pipelines they work with to manage their account. The menu is always to the left and can easily be expanded or collapsed.

Finally, Falkonry’s machine learning continues to improve and find more interesting behavior on its own. As many of our users have told us, Falkonry’s unsupervised machine learning is the best thing to happen to IoT, and we have been working to make it even better. For example, Falkonry figures out from the data what patterns repeat and at what interval so that any periodicity is automatically spotted without the need to give hints or tweak anything.

We continue to make this intuitive experience of IoT data analytics and visualization even more powerful and usable. Even as our technology improves and the Falkonry Service is upgraded, you can be assured that your data and prediction models will be just a click away.

Falkonry’s advanced analytics and simple visualization means that computers are left to do what they are good at – computation – and people can control what the computations do without having to perform detailed debugging or adjustments. There should be no reason for people to pore over hundreds of plots constantly looking for patterns when such work can be efficiently and effectively performed by computers using Falkonry Condition Prediction Service.

 

This post was originally written February 6, 2016.

Falkonry Service Improves the AI Experience: More Connections, Better Deployment Options

By | IT/OT Management

Falkonry Service was introduced a few months ago to improve the Falkonry solution fit and flexibility. As we’ve interacted with customers over the last several months, we’ve gained a greater understanding of the many different types of solutions people are trying to build with embedded pattern recognition capabilities provided by Falkonry. This release is a reaction to those needs and includes:

  • Improved data consumption capabilities
  • Expanded connection options
  • Simpler private deployment options

Falkonry Service Architecture

 

You can watch videos about Falkonry on our Website to learn more.

Improved data consumption capabilities

To better address current needs and in anticipation of future needs, we added a new core architectural element to Falkonry called Event Buffer.  Event Buffers separate the responsibility for managing data inbound to Falkonry from Pipelines that process that data.  One obvious benefit from the addition of Event Buffers is that one data source can supply data to multiple pipelines. This capability can be used to simply allow reuse of previously loaded data or to support more complex real-time simultaneous pattern recognition scenarios. Each pipeline, for example can make independent choices on how to interpret and process the same data stream.  An additional capability associated with Event Buffers is the ability to chain Pipeline executions to each other – i.e. to route output from one Pipeline to an Event Buffer that feeds other Pipelines.

Event Buffers also support and provide a focus for a growing set of capabilities related to data consumption.  The new release, for example, allows users to supply data to Falkonry in ‘Data Historian style’ format – sets of points in the form of a <timestamp, tag, value> triple format.  This augments the tabular structure supported previously.  Likewise, JSON (line delimited) support was added to complement CSV.

Expanded Connection Options

The new release also makes it easier to connect to Falkonry and to embed it in your solutions.  New capabilities include:

  • MQTT connectivity
  • Webhooks connectivity
  • Updated REST API
  • Expanded set of client libraries
  • Updated Splunk plugin

The Falkonry UI makes it easy for an Event Buffer to subscribe to a MQTT topic or for a Pipeline’s outflow  to be published to a MQTT topic or a Webhook URL. Additional subscription and publication options will be added in the future.

Client libraries are now available for Javascript and Python and others (e.g. C# and Java) are under development.

The Falkonry Splunk App that makes it easy to bi-directionally connect Splunk to a Falkonry Service instance was updated and streamlined, and plug-ins for other data platforms are under development.

Simpler Private Deployment Options

While the Falkonry Sandbox provides a useful and effective path for experimentation and early solution development, private deployments are the primary way Falkonry gets delivered.  Private deployments can be either:

  • Virtual Private Cloud (VPC) Deployments: Falkonry deployed in customer specific VPCs on public provider infrastructure like Oracle, Microsoft Azure, Google Compute Engine (GCE), Amazon Web Services (AWS)
  • Private Deployments: Falkonry deployed on customer controlled compute and storage infrastructure.

To make installation much simpler, Falkonry now offers a downloadable option for Private Deployments.

Falkonry AI Augments Operational Decision-making

As extreme growth in the generation of live operational data continues, the need to build solutions that recognize patterns in this data grows in parallel. Falkonry is committed to making AI-based pattern recognition an easy to incorporate component of any operations-oriented solution, and this release furthers us down that path.

For more information, please visit www.falkonry.com

What Does Falkonry’s $5.3M in Equity Funding Mean for Industry? What do Zetta Venture Partners and Polaris Partners see in Falkonry??

By | Uncategorized

Falkonry discovers, recognizes, and predicts operating and performance conditions from time series data, using machine learning/pattern recognition. From its inception, Falkonry has had a single purpose: to make industrial operations  more productive. Falkonry achieves this by applying  advanced signal processing techniques to:

  • Gain yield/OEE improvements not possible without advanced pattern recognition
  • Create a whole new ‘view’ of process and asset operations through patterns in operational data
  • Put advanced pattern recognition technology into the hands of process and industrial engineers — those who know and understand the operation of their assets and processes.

Investors Zetta and Polaris recognize the ground-breaking shift in yield outcomes enabled by Falkonry’s advanced pattern recognition technology. Their backing, and the backing of Falkonry’s partners and customers, signal the transition of Falkonry’s innovations from a nascent technology to a truly industry-impacting software offering.

 

pattern recognition

Falkonry Pattern Recognition

 

Falkonry advanced pattern recognition technology delivers an intuitive UI designed for process and industrial engineers — the company domain experts; no data engineering or scientists are needed. It allows companies that generate massive amounts of data, such as those in the process industries (oil and gas; metals, mining and minerals; pulp and paper) to detect, recognize, and monitor patterns of operation that are only “visible” across complex, multi-variable, time-series data. Recognizing patterns of asset and process operation illuminates areas across  assets and processes that for OEE and yield improvement; where bottlenecks and choke points reside; and where in the process flow tuning can be applied.  Falkonry’s customers report gains in process visibility; uptime; and process throughput.

For more information on Falkonry, please visit www.falkonry.com.