Filter Plugin For Breakover Prediction

flir-filter-breakover forecast the possibility of breakover. The output of this plugin can appear as follows

asset_reading

1. Setting up your artifacts

The trained model from keras needs to be in .h5 format for its usage in this filter.

models/
├── breakover_forecasting_model.tflite
└── breakover_forecasting_model.h5

2. Setting up bucket

ML Model Upload Screen

  1. Make sure flir-gui-ml-models and flir-service-bucket is installed. If not, install these.

  2. Click on “ML Models” in FLIR Bridge GUI

  3. Click on import, and set the appropriate values. Then upload the prepared model above. e.g.

Name: "breakover_model.h5"
Architecture: All
Hardware: CPU
Version: "1.0"
Description: ""
File: "models/breakover_forecasting_model.h5"

3. Setting up plugin configuration

Configuring the filter, starts with selecting the filter and giving an application name for it. The screen will look like the following.

Plugin Screen 1

Following this the next screen will have the plugin configuration as shown below:

cfg2_enable

  • ‘Add performance counters’: type: `boolean` default: ‘false’:

    Add performance counters metadata containing resource utilization statistics.

  • ‘Log level’: type: `enumeration` default: ‘INFO’:

    Log level for diagnostic or error output.

    Options are:

    • ERROR

    • WARN

    • INFO

    • DEBUG

  • ‘Enabled’: type: `boolean` default: ‘false’:

    Enable breakover forecast filter plugin.

cfg2_inference

  • ‘Sequence size’: type: `integer` default: ‘10.0’:

    Sequence size that is to be used for breakover forecasting.

  • ‘Inference interval’: type: `float` default: ‘1.0’:

    Time interval after which the data will be passed through the model.

  • ‘Inference interval unit’: type: `enumeration` default: ‘seconds’:

    Time interval unit.

    Options are:

    • seconds

    • minutes

    • hours

cfg2_ml_model

  • ‘Model name’: type: `string` default: ‘breakover_forecasting_model.h5’:

    Model to be loaded from bucket service.

  • ‘Model version’: type: `string` default: ‘1.0’:

    Model version as stored in bucket.

cfg2_inputs

List of objects are to be added in this group. Object properties are as below:

  • ‘Asset name’: type: `string` default: ‘asset_1’:

    Enter input asset name.

  • ‘Datapoint name’: type: `string` default: ‘datapoint_1’:

    Enter input datapoint name.

  • ‘Feature type’: type: `enumeration` default: ‘Boolean’:

    Datatype of the feature.

    Options are:

    • Boolean

    • Numeric

  • ‘Scaling strategy’: type: `enumeration` default: ‘None’:

    The strategy that is to be used for data scaling.

    Options are:

    • None

    • Normalization

    • Standardization

  • ‘Minimum’: type: `float` default: ‘-1.0’:

    Enter minimum value for data normalization.

  • ‘Mean’: type: `float` default: ‘-1.0’:

    Enter mean value for data standardization.

  • ‘Maximum’: type: `float` default: ‘-1.0’:

    Enter maximum value for data normalization.

  • ‘Standard deviation’: type: `float` default: ‘-1.0’:

    Enter standard deviation value for data standardization.

cfg2_output

  • ‘Forward data’: type: `boolean` default: ‘true’:

    Whether to forward received PLC data down the filter chain.

  • ‘Asset name’: type: `string` default: ‘breakover’:

    Name of asset that indicates breakover forecast.

  • ‘Score datapoint name’: type: `string` default: ‘forecast_score’:

    Name of datapoint that indicates breakover forecast score.

  • ‘Forecast datapoint name’: type: `string` default: ‘forecast_imminent’:

    Name of datapoint that indicates breakover forecast.

cfg2_post_process

  • ‘Score Window Length’: type: `integer` default: ‘10’:

    Number of score values that is to be used for breakover forecasting.

  • ‘Measure name’: type: `enumeration` default: ‘Average’:

    Measure to calculate on the scores value present in the window.

    Options are:

    • Summation

    • Minimum

    • Average

    • Median

    • Maximum

    • Standard Deviation

    • Variance

  • ‘Threshold’: type: `float` default: ‘0.5’:

    Threshold to apply on the calculated measure value.

Click on Done when ready.

See Also

flir-filter-ADM_LD_prediction - Filter to detect whether a large discharge is required for a centrifuge

flir-filter-edgeml - Filter which takes image data, calls out to ML process, and forwards the inference from ML as asset contents.

flir-filter-expression - A FLIR Bridge processing filter plugin that applies a user define formula to the data as it passes through the filter

flir-filter-fft - A FLIR Bridge processing filter plugin that calculates a Fast Fourier Transform across sensor data

flir-filter-log - A FLIR Bridge filter that converts the readings data to a logarithmic scale. This is the example filter used in the plugin developers guide.

flir-filter-normalise - Normalise the timestamps of all readings that pass through the filter. This allows data collected at different rate or with skewed timestamps to be directly compared.

flir-filter-python35 - A FLIR Bridge processing filter that allows Python 3 code to be run on each sensor value.

flir-filter-rms - A FLIR Bridge processing filter plugin that calculates RMS value for sensor data

flir-filter-scale-set - A FLIR Bridge processing filter plugin that applies a set of sale factors to the data

flir-filter-specgram - FLIR Bridge filter to generate spectrogram images for vibration data

flir-filter-statistics - Generic statistics filter for FLIR Bridge data that supports the generation of mean, mode, median, minimum, maximum, standard deviation and variance.

flir-filter-vibration_features - A filter plugin that takes a stream of vibration data and generates a set of features that characterise that data

flir-south-ABB - A south plugin to pull data from the ABB cloud

flir-south-Beckhoff - A Beckhoff ADS data ingress plugin for FLIR Bridge, this monitors Beckhoff PLCs and returns the state of internal variables within the PLC

flir-south-Expression - A FLIR Bridge south plugin that uses a user define expression to generate data

flir-south-ModbusC - A FLIR Bridge south plugin that implements modbus-tcp and modbus-rtu

flir-south-S7 - A south plugin that uses the S7 Communications protocol to read data from a Siemens S7 series PLC.

flir-south-dnp3 - A south plugin for FLIR Bridge that implements the DNP3 protocol

flir-south-etherip - A south plugin to read tags data from a number of different Allen-Bradley and Rockwell PLCs.

flir-south-opcua - A FLIR Bridge south service that pulls data from an OPC-UA server

flir-south-s2opcua - An OPC UA south plugin based on the Systerel S2OPC OPC UA Toolkit. This plugin offers similar functionality to the flir-south-opcua plugin but also offers data encryption and authentication.