Jump to content

All Activity

This stream auto-updates

  1. Yesterday
  2. Lindsey, The 7 days forecast is looking like that today. The Connector has low reliability which Seeq has said is due to the NOAA's servers. It is possible the NOAA's servers were not providing forecast data when I investigated. For portions of last month, the NOAA's servers did not even provide current data.
  3. Last week
  4. I was wondering if we can have a feature to create a new/duplicated worksheet next to the current selected one instead of creating it at the end of the workbench? Some cases when we have multiple number of worksheets within a workbench analysis, it's hard to move worksheet from the end position to the required position. I was looking for a feature like a traditional power points/google slides where the newly created slide will be next to the current selected slide.
  5. Here’s an example on how to add color threshold so that it alerts when the current value to day deviates by +-5 degF Step 1: Calculate daily average temperature using signal from condition. Step 2: Create the high and low limits in the formula as below:- High Limit: ($averagetemperature.move(1d))+5 Low Limit: ($averagetemperature.move(1d))-5 Step 3: Add the high and low limits in the metric's threshold as below screenshot:-
  6. Earlier
  7. Here's another method to pick a specific capsule within a condition. In this example, the user want to pick the first capsule from condition 2 within condition 1. Use formula tool: $condition1 .removeLongerThan(1d) .transform($c -> $condition2.removeLongerThan(1d).toGroup($c).pick(1)) The output:
  8. Thanks Joe, yeah forecastLinear works for linear forecasting. I'm looking for an option in "Model & Predict", for a "Time Series Forecast" which can be similar to the "Prediction" feature, however the only change I'm looking for is there shouldn't any option for "Input Signals", this feature should take the time series as the input signal by default (considering the training window). I am aware that we can create a signal using timesince() function and use this as my "Input Signals" and use the traditional "Prediction" feature. However SEEQ mostly deals with the time-series data, I think h
  9. I'll also add that as of R22.0.49, there's new forecast functions like forecastLinear that allows you to create a linear regression out into the future based on the last X number of minutes. You can see a little bit about that at the What's New Knowledge Base here if you are not on that version yet or can check out the formula documentation for more information on those functions.
  10. Sivaji, I am not 100% sure if this is what you are looking for, but you can create a time signal from a condition. This allows you to build a condition with the manual condition tool and apply the following formula to create the time counter. timesince($condition,1h) You can then just limit the training window to that condition. If you need to extend the time counter into the future you may want to apply growend() to the condition in the time since formula above. Teddy
  11. While Seeq is working towards enhancing our features in the Histogram tool, here are a simple workaround commonly used to create a histogram for multiple signals with display times in chronological order. Step 1: Start by loading all of the signals we want to include in the matrix into the display. Step 2: Create a monthly condition with a property that split the years and months (YYYY-MM) from the initial date format (YYYY-MM-DDT00:00:00Z) using the formula tool. Formula 1 - month_withProperty $monthly = months("Asia/Kuala_Lumpur") //split the years and month
  12. I understand in the current version we need to create a time signal using timesince() function, and use the predict function to train the signal that we need over the time signal created. However I was wondering if we can time-series forecast function which internally creates the time signal based on the start datetime of the training window and trains the model.
  13. When I tried pulling it the result showed "Not a Signal, Condition or Scalar - skipping". Alternatively I can create a signal from condition and can pull the data. However I have already calculated many scorecard metrics formulae, I was wondering if there is any workaround to pull them using DataLab?
  14. Hi Prachi, A couple different options for you: Option 1 You're probably familiar that you can use Formula (or Value Search) with the following to create a capsule for when one signal is equal to 1: $signal==1 Therefore, one option is to combine this search together for each signal using the combinewith function: combinewith($signal1==1, $signal2==1, ... , $signal50==1) This will create a capsule for each signal equal to 1, which would result in multiple overlapped capsules if more than one signal was equal to 1. If you'd like to reduce that to create a capsule if "
  15. Hi, I have 50 signals. I want to check if any of the signal has value 1. How can create new signal (or capsule) based on this check condition?
  16. To follow up if you want to put the folder and workbook names into variables the code looks like this FolderPath = 'Folder level 1 >> Folder level 2' WorkbookName = 'My Workbook' spy.push(data = statusExpanded,workbook=f'{spy.workbooks.CORPORATE} >> ' + FolderPath + ' >> ' + WorkbookName)
  17. If you have a signal in Seeq that is an integer representing an 8-bit 16-bit or 32-bit set of states here is some example code you can use to convert the integer signal into 8-16-32 separate 0/1 signals that can be used to define machine states elsewhere in the Seeq platform Import Python packages from seeq import spy import pandas as pd import numpy as np Use Spy.search to find your integer signal of interest - see spy.search() docs for more information IntegerSignal = spy.search( <your method here> ) Pull the signal for your time period of interest. This is a good p
  18. Starting in Version 50 Seeq now includes a Corporate Drive which is a great place to store shared documents. In order to push content to the Corporate drive using the folder path structure you need to include a bit of special code for the base "Corporate" folder spy.push(data=csv_file,workbook=f'{spy.workbooks.CORPORATE} >> My Folder Name >> WorkbookName')
  19. Here is a nice a simple example from a question emailed in this morning. This can be accomplished in a couple of minutes using a combination of Value Search to create a condition that captures our "Pump Running" state and Chain view to filter our trends to only those "Pump Running" time periods Step 1 - Create a condition that captures your event of interest. In our simple example that will be whenever the Stage tag is != to "OFF". This step can be much more complex and use the full range of tools in the "Identify" category to refine your search to exactly the periods relevant to
  20. Thanks for sharing, I'd not figured out a vertical line method. For horizontal I'd used: 55*$x/$x
  21. Using some of the new Asset Group features in R52 we can easily create unique prediction training ranges for each asset. In this example we are going to create three separate training ranges for three assets. Step 1 - Find the assets you want to model with your prediction and add them to a new asset group Step 2 - Create a Manual Condition for each asset with your desired training range for each particular asset. These training ranges can be as simple as single capsules or as complex as a Manual Condition combined with a mode of operation condition. Step 3 - Add t
  22. Currently in Seeq (June 2021) there is not a method to export ungridded signal data. There are a couple of development items in the works which will help in the future but for the moment this is the best work around for oData connections. As a reminder if you just need the data in excel, there is an ungridded raw timestamp option available for the excel export. Lets use the following setup as our example. We have a condition which represents my batches and we have a simple temperature signal that I want to get the average value of for each batch. Step 1 - Create my Average temperat
  23. In later Seeq versions, an alternative to the method above may be to use the countOverlaps() function, which will also generate a signal showing the number of capsules simultaneously occurring based on the input conditions. countOverlaps( $a > 80, $b > 80, $c > 80, $g > 80, $h > 80, $i > 80) Take note that countOverlaps has a default sample period of 1 second, but this can be amended by adding a sample period before the conditions to be counted. Further details can be found in the formula documentation.
  24. It is common in manufacturing processing plants such as oil and gas refineries, to monitor the temperature trend in furnaces. Example in the refineries, the furnaces tube metal temperature (TMT) monitoring severity increases for dirty services such as crude distillation and coker units. Operation team uses this information to decide either to go for rate cut or feed rate skewing before the TMT reaching mechanical limits to prolong the run length. Upon reaching the limit, the furnace will be taken out-of-service by means of spalling or pigging, and consequently impacts the production rate.
  25. Run Length Optimization brittanyebaugh Thu, 05/27/2021 - 13:41 Industry Chemicals & Petrochemicals Food & Beverage Mining, Metals & Materials Oil & Gas Challenge: Many continuous manufacturing units run into process throughput constraints over the course of a run. These constraints are often reversible but come with the high cost of shutting down to clean or maintain equipment. The manufacturing p
  26. In the process manufacturing world, there’s been a significant increase in the accessibility into operational and equipment data. Teams now have visibility into both historical and near real-time data from their operation, and can even monitor this as it’s happening at remote locations. But the problem with this is that teams are drowning in data—”DRIP”—data rich, information poor. View the full article
  27. This is a question that came into our Support system today that I thought a number of our users might find interesting. Question - I have a signal that is calculating a number of equipment events and I want to create a scorecard with our total compliance to our procedures showing % Compliance per week / month / year For this example we are going to use the Area A -> Compressor Power example data and create a scorecard judging our compliance with our policy that the compressor has to turn on ever day. Step I - Create a metric that measures if you met your compliance requirem
  1. Load more activity
×
×
  • Create New...