Fault detection and diagnostics of building automation systems
AssigneeSiemens Aktiengesellschaft
InventorsJake Petersen, Florian Koehler, Jan Monica
Life of this patent
Estimating the term…
Abstract
Systems and methods detect and diagnose faults of a building automation system. Timeseries data are received from the building automation system. A label plausibility is determined for each set of timeseries data and the corresponding label associated with the set of timeseries data based on a tree-based classifier and an image transformation classifier. The tree-based classifier and the image transformation classifier receive the same data input and operating distinctly from each other.
Claims18
A method for fault detection and diagnostics of a building automation system comprising:
- receiving, by a processor of a management station of the building automation system communicating with one or more field devices via one or more communication protocols, timeseries data from the building automation system;
- determining a label plausibility for each set of timeseries data and the corresponding label associated with the set of timeseries data based on a tree-based classifier and an image transformation classifier, the tree-based classifier and the image transformation classifier receiving the same data input and operating distinctly from each other, wherein the image transformation classifier determines the label plausibility in part by transforming each set of timeseries data to an RGB image comprising at least one of a Gramian angular field image or a Markov transition field image, and wherein determining the label plausibility comprises determining the label plausibility based on a first probability of the tree-based classifier and a second probability of the image transformation classifier, the label plausibility including a percentage or ratio representing how well each label associates with the timeseries data corresponding to the label;
- and
- modifying a control parameter of a building equipment based on the determined label plausibility, wherein modifying the control parameter comprises modifying one or more labels associated with data points of the one or more field devices based on the label plausibility.
A system for fault detection and diagnostics of a building automation system comprising:
- a management station communicating with one or more field devices of the building automation system via one or more communication protocols;
- an input component of the management station configured to receive timeseries data from the one or more field devices of the building automation system;
- and
- a processor of the management station configured to determine a label plausibility for each set of timeseries data and the corresponding label associated with the set of timeseries data based on a tree-based classifier and an image transformation classifier, the tree-based classifier and the image transformation classifier receiving the same data input and operating distinctly from each other,
- wherein the processor determines the label plausibility based on a first probability of the tree-based classifier and a second probability of the image transformation classifier, the label plausibility including a percentage or ratio representing how well each label associates with the timeseries data corresponding to the label, and wherein the processor modifies a control parameter of a building equipment based on the determined label plausibility, wherein modifying the control parameter comprises modifying one or more labels associated with data points of the one or more field devices based on the label plausibility.
Dependencies are inferred from the claim text.