Machine condition monitoring using a flexible monitoring framework
A flexible framework and a corresponding user interface allow a user to configure a machine condition monitoring system. A user-configurable computation framework offers flexibility in designing the machine condition monitoring system. In this framework, every computation based on machine attributes is represented as an input-output system. A simple computation can be easily defined by specifying the computation type, number of inputs, structure, and parameters. The user can use the determined output attributes of computations as input attributes in other computations. Ultimately, the computations are aggregated by the framework configured by the user to produce an output computation attribute that indicates a machine condition or predicts a machine condition.
1 . A method of machine condition monitoring comprising:
determining a plurality of computations;
inputting at least one input attribute into each of the plurality of computations;
determining at least one output attribute for each of the plurality of computations;
inputting at least one of the at least one output attributes as a computed input attribute into at least one of the plurality of computations; and
determining a computation output attribute based at least in part on the computed input attribute.
2 . The method of claim 1 wherein the computation output attribute is an indication of a machine condition.
3 . The method of claim 2 further comprising:
displaying the indication of the machine condition to a user.
4 . The method of claim 1 wherein at least one of the plurality of computations are determined by a user utilizing a user interface.
5 . The method of claim 1 wherein determining at least one output attribute for each of the plurality of computations comprises determining a plurality of output attributes for one of the plurality of computations and further comprising:
providing at least one output attribute of the plurality of output attributes to a user; and
storing the remaining output attributes.
6 . The method of claim 5 wherein the one of the plurality of computations is a neural network.
7 . A method of machine condition monitoring comprising:
determining a first computation task;
inputting at least one input attribute for the first computation task;
determining a plurality of output attributes of the first computation task based at least in part on the input at least one input attribute;
outputting to a user at least one output attribute of the plurality of output attributes; and
storing the remaining output attributes.
8 . The method of claim 7 further comprising:
inputting at least one of the stored remaining output attributes as a computed input attribute for a second computation task; and
determining a computation output attribute based at least in part on the computed input attribute.
9 . The method of claim 7 wherein outputting to a user at least one output attribute of the plurality of output attributes comprises:
displaying the at least one output attribute.
10 . The method of claim 9 wherein displaying the at least one output attribute comprises:
displaying a machine condition to the user.
11 . A system for machine condition monitoring comprising:
means for determining a plurality of computation components;
means for inputting at least one input attribute into each of the plurality of computation components;
means for determining at least one output attribute for each of the plurality of computation components;
means for inputting at least one of the at least one output attributes as a computed input attribute into at least one of the plurality of computation components; and
means for determining a computation output attribute based at least in part on the computed input attribute.
12 . The system of claim 11 wherein the computation output attribute is an indication of a machine condition.
13 . The system of claim 12 further comprising:
means for displaying the indication of the machine condition to a user.
14 . The system of claim 11 further comprising a user interface configured to allow a user to determine at least one of the plurality of computation components.
15 . The system of claim 11 wherein the means for determining at least one output attribute for each of the plurality of computation components comprises means for determining a plurality of output attributes for one of the plurality of computation components and further comprising:
means for providing at least one output attribute of the plurality of output attributes to a user; and
means for storing the remaining output attributes.
16 . The method of claim 15 wherein the one of the plurality of computation components employs a neural network.
17 . A machine readable medium having program instructions stored thereon, the instructions capable of execution by a processor and defining the steps of:
determining a plurality of computations;
inputting at least one input attribute into each of the plurality of computations;
determining at least one output attribute for each of the plurality of computations;
inputting at least one of the at least one output attributes as a computed input attribute into at least one of the plurality of computations; and
determining a computation output attribute based at least in part on the computed input attribute.
18 . The machine readable medium of claim 17 wherein the computation output attribute is an indication of a machine condition.
19 . The machine readable medium of claim 18 wherein the instructions further define the step of:
displaying the indication of the machine condition to a user.
20 . The machine readable medium of claim 17 wherein the instructions further define the step of:
receiving at least one of the plurality of computations from a user interface.
21 . The machine readable medium of claim 17 wherein the instructions for determining at least one output attribute for each of the plurality of computations comprises instructions for determining a plurality of output attributes for one of the plurality of computations and further defines the steps of:
providing at least one output attribute of the plurality of output attributes to a user; and
storing the remaining output attributes.
22 . The machine readable medium of claim 21 wherein the one of the plurality of computations is a neural network.