Skip navigation
All Places > All Things PI - Ask, Discuss, Connect > Blog > Author: gopal
This Lab was part of the TechCon Hands-on Labs during PI Users Conference in 2017 in San Francisco.  The Lab was also offered in Sao Paulo, Brazil during LATAM Regional 2017 and at UC EMEA London. The Lab manual is attached; the manual is intended for an instructor led interactive workshop – so you may find the written content short on some of the explanations.

 


You can access the VM used for the lab via Home Page - OSIsoft Learning and, look under the Virtual Learning Environment.

Below is an extract from the Intro section of the Lab manual:

 

At TechCon 2016, we reviewed an end-to-end use case for developing a machine learning (multivariate PCA - principal component analysis) model to predict equipment failure. This lab builds on those concepts but we now use data from a process unit operation and apply data science and machine learning methods for diagnostics.

 

Troubleshooting faulty processes and equipments – also known as FDD (fault detection and diagnostics) or anomaly detection is a challenge.  This hands-on-lab provides an end-to-end walk-through for applying data driven techniques - specifically machine learning - for such tasks.

 

The learning objectives of this lab include:

  • Extracting data from the PI System using PI Integrator
  • Using the PI System data with R, data cleansing, feature selection, model development for a multivariate process using PCA (principal component), etc.
  • Using the PCA model with Shiny  https://shiny.rstudio.com/ to create an interactive display for visualizing and exploring faults vs. normal operation; also using SVM (support vector machine) for classification and prediction of Air Handler (AHU) fault/no-fault state
  • Using Azure ML with PI System data for machine learning
  • Deploying the machine learning model for continuous execution with real-time data
  • Understanding the end-to-end data science process – data retrieval, data cleansing, shaping and preparation with meta-data context, feature selection via domain specific guidelines, applying machine learning methods, visualizing the results and operationalizing the findings

 

The application of data science and machine learning methods are well known in several fields – image and speech recognition, fraud detection, search, shopping recommendations, and others.  In manufacturing, including manufacturing operations management, and particularly in plant-floor operations with time-series sensor data, select data science/machine learning methods are highly effective.

 

Principal Component Analysis (PCA) is one such well-known and established machine learning technique for gaining insights from multivariate process operations data. PCA has several use cases – exploratory analysis, feature reconstruction, outlier detection, and others. And, other derived algorithms such as PLS (projection to latent structures), O-PLS (orthogonal …), PLS-DA (… discriminant analysis) etc. are widely used in the industry.

In a multivariate process, several parameters - sometimes just a handful but often dozens of parameters - vary simultaneously, resulting in multi-dimensional datasets that are difficult to visualize and analyze. Examples of multivariate processes are:

  • Brewery - Beer fermentation
  • Oil Refinery – Distillation column
  • Facilities – Heating, Ventilation and Air-Conditioning (HVAC) - Air Handler Unit

 

...In this lab, we use the Air Handler Unit (AHU) to illustrate an approach for analyzing such multivariate processes.  A typical HVAC system with AHU is shown below.

 

AirHandler.png

Figure HVAC system with Air Handling Unit (AHU)

 

Sensor data available from the AHU, as part of the BMS (building management system) are:

  • Outside air temperature
  • Relative Humidity
  • Mixed air temperature
  • Supply air temperature
  • Damper position
  • Chilled water flow
  • Supply air flow
  • Supply air fan VFD (variable frequency drive) power

During the course of a day, the AHU operating conditions change continuously as the outside air temperature rises and falls, along with changing humidity and wind conditions, changing thermostat set-points, building occupancy level, and others. The BMS control system adjusts the supply air flow rate, chilled water flow rate, damper position etc. to provide the necessary heating or cooling to the rooms to ensure tenant comfort.

 

However, fault conditions such as incorrect/drifting sensor measurements (temperature, flow, pressure …), dampers stuck at open/closed/partial-open position, stuck chilled water valve, and others, can waste energy, or lead to tenant complaints from other malfunctions causing rooms to get too hot or too cold.

For troubleshooting and diagnostics, HVAC engineers need tools to answer questions such as:

  • How can I use data to detect faulty AHU operations i.e. air damper stuck open at 100% open on a hot day in mid-July?
  • What’s the AHU “state” during 100 ºF + days? In 2016? In 2015? And, in 2014 before we installed the Economizer?
  • What are the AHU outlier/extreme operating states?
  • How did it get to the extreme state; what were the immediate prior operating states for that day?
  • What’s the AHU state at supply fan flow limit constraint? When did it happen?

For Part 1, see  PI-System-and-ISO-50001

For Part 2, see  The-7-steps-in-US-DoE-eGuide-for-ISO-50001-to-implement-an-energy-management-system-how-can-pi-system-products-meet-some-of-these-requirements

 

 

The PI System meets several of the EnMS requirements via a suite of integrated modules that are categorized under: Collect, Historize, Find, Analyze, Deliver, and Visualize.

  • Collect includes PI Interfaces that collect data from a multitude of data sources.
  • Historize includes PI Server that works with the PI Interfaces to provide the real-time data collection, archiving, and distribution services. The PI Server brings all the relevant data from disparate sources, such as enterprise systems, databases, and operational data sources into a single system, secures it so appropriate access is given to individuals based on their roles, and delivers it to users and applications at all levels of the enterprise.
  • Find includes PI Asset Framework (PI AF) and PI Event Frames (PI EF). PI AF provides for a configurable meta-data layer that can host multiple data models - a process flow, i.e. connectivity model, an equipment component model, a transaction object model, and others.  PI EF provides the infrastructure and a configurable model for storing data by manufacturing events.
  • PI AF and PI EF work together to quickly find the appropriate data in the correct context and inter-relate data and events to profile your energy situation.
  • Analyze PI Analytics provide real-time analytics and enables you to analyze and aggregate real-time and historical data and events into user-defined actionable information or key performance indicators (KPIs).
  • Deliver PI Data Access and PI Notifications provide the functionality to deliver data when, where and how it is needed. PI Data Access supports a number of industry standards such as Web Services (SOAP), OLEDB, ODBC, JDBC, OPC, and others. XML based i/o is supported and with appropriate XSL transform files, it can be used for XML messaging based data exchange
  • Visualize includes PI Coresight, PI WebParts, PI DataLink, PI ProcessBook and others to meet the functional requirements with regard to energy analysis, and energy tracking/reporting.


As a follow up to the previous post, the items in red below indicate the steps from the US DoE eGuide where the PI System capabilities can be used.  For several items, one or more PI System products can completely meet a Step’s requirements. However, in other Steps, the requirements are outside the scope of the PI System and you have to use other tools.


Step 1 Getting Started


Step 2 Profile Your Energy Situation


Step 3 Develop Objectives, Targets and Action Plans


Step 4 Reality Check: Stop! Look! Can I Go?


Step 5 Manage Current State and Improvements


Step 6 Check the System


Step 7 Sustain And Improve The System


Do you have an active ISO 50001 or Energy Management project where you are using the PI System stack?  Please share your findings.

For Part 1 in this series, please see  PI-System-and-ISO-50001

 

For Part 3 in this series, please see  Using-the-OSIsoft-PI-System-in-ISO-50001-energy-management-system-enms-implementations

 

 

The US DoE eGuide for ISO 50001 helps you to implement an EnMS through a step-by-step process. It includes forms, checklists, templates, examples and guidance to assist you throughout the implementation. This eGuide outlines the following steps:

  • Step 1 Getting Started
  • Step 2 Profile Your Energy Situation
  • Step 3 Develop Objectives, Targets and Action Plans
  • Step 4 Reality Check: Stop! Look! Can I Go?
  • Step 5 Manage Current State and Improvements
  • Step 6 Check the System
  • Step 7 Sustain And Improve The System


For details, please see: https://save-energy-...Pages/home.aspx

As illustration, for Step 2.2.3 Formulate a process for acquiring and recording data the eGuide gives the following example:
ISO_50001_DataCollectionMatrix.png


It is easy to recognize how PI System products such as PI Interfaces and PI Manual Logger that are part of the PI System data collection stack can be used in this step.

Another illustration is for Step 2.3.5 Analyze and track significant energy uses and the eGuide gives the following example:

 

ISO_50001_ExcelTracking.png

 

ISO_50001_Trend.png




Here again, you see PI System products such as PI DataLink, PI ProcessBook, PI WebParts and others that are part of the PI System visualization can be used to the meet the requirements in this Step.

Overall, various PI System products can help you with ISO 50001 EnMS implementation. For several items, one or more PI System products can completely meet a Step’s requirements. And, in some cases it may be beyond the scope of PI System and you will have to either extend the PI System or supplement it with other outside tools and methods.


Using the OSIsoft PI System in ISO 50001 Energy Management System (EnMS) Implementations to see the next post in this series.

gopal

PI System and ISO 50001

Posted by gopal Oct 15, 2012

Briefly, the purpose of ISO 50001 is to enable organizations to establish the systems and processes necessary to improve energy performance, including energy efficiency and intensity. It specifies requirements for an energy management system (EnMS) to develop and implement an energy policy, establish objectives, targets, and action plans.
An energy management system addresses:

  • energy supply
  • measurement, documentation, and reporting of energy use
  • procurement and design practices for energy-using equipment, systems, and processes


ISO 50001 does not itself state specific performance criteria with respect to energy. The standard applies to all factors affecting energy use that can be monitored and influenced by the organization. It has been designed to be used independently but can be aligned or integrated with other management systems such as ISO 9000 (Quality Management) and ISO 14000 (Environmental Management).

 

It is based on the Plan-Do-Check-Act continual improvement framework and incorporates energy management into everyday organization practices. The basis of this approach is shown in Figure 1.

 

ISO_50001_PlanDoCheckAct.png
Figure 1 Energy Management System Model

 


The PI System provides the software to implement the data infrastructure for the EnMS data collection, performance analysis and tracking/reporting.

 

Please respond with your field experiences as you use the PI System stack for meeting ISO 50001 requirements.

 


If you are new to ISO 50001, please see this: ISO 50001 Energy Management Standard

 

For Part 2 in this series, please see The 7 steps in US DoE eGuide for ISO 50001 to implement an Energy Management System - How can PI System products meet some of these requirements?

For Part 3 in this series, please see  Using-the-OSIsoft-PI-System-in-ISO-50001-energy-management-system-enms-implementations

 

 

Filter Blog

By date: By tag: