METHODS AND SYSTEMS FOR SELF-ORGANIZATION OF COLLECTED DATA USING 3RD PARTY DATA FROM A DATA MARKETPLACE IN AN INDUSTRIAL INTERNET OF THINGS ENVIRONMENT
A system, method and apparatus for data collection in an industrial production environment is described. The system may include a data acquisition circuit structured to interpret a plurality of detection values corresponding to input received from a plurality of input sensors, each of the plurality of input sensors operatively coupled to at least one of a plurality of components of an industrial production process, a data storage circuit structured to store a subset of the plurality of detection values and a plurality of data collection routes, wherein the plurality of data collection routes each include a different data collection routine, an expert system circuit structured to self-organize the plurality of detection values into at least one data collection band, and a data analysis circuit structured to analyze the subset of the plurality of detection values and determine a status parameter value.
1 . A system for data collection in an industrial production environment, the system comprising:
a data acquisition circuit structured to interpret a plurality of detection values, each of the plurality of detection values corresponding to input received from at least one of a plurality of input sensors, the at least one of the plurality of input sensors comprising a detection package, each of the plurality of input sensors operatively coupled to at least one of a plurality of components of an industrial production process;
a data storage circuit structured to store a subset of the plurality of detection values and a plurality of data collection routes, wherein the plurality of data collection routes each comprise a different data collection routine;
an expert system circuit structured to self-organize the plurality of detection values into at least one data collection band; and
a data analysis circuit structured to analyze the subset of the plurality of detection values and determine a status parameter value.
2 . The system of claim 1 , wherein the at least one data collection band comprises at least one of the characteristics selected from the characteristics consisting of: a specific frequency band, a group of spectral peaks, a true-peak level, a crest factor derived from a time waveform, a utilization level, a process yield, and an overall waveform derived from a vibration envelope.
3 . The system of claim 1 , wherein the expert system circuit is further structured to self-organize the plurality of detection values into the at least one data collection band utilizing at least one neural network selected from the networks consisting of: learning vector quantization, an echo state network, a bi-directional recurrent network, a stochastic network, a genetic scale recurrent network, a committee of machines, an associative network, a neuro-fuzzy network, a compositional pattern-producing network, a hierarchical temporal memory network, and a holographic associate memory network.
4 . The system of claim 1 , wherein the expert system circuit is further structured to self-organize the plurality of detection values into the at least one data collection band utilizing a learning vector quantization.
5 . The system of claim 1 , further comprising an analysis response circuit structured to adjust the detection package in response to the status value.
6 . The system of claim 5 , wherein the analysis response circuit structured to adjust the detection package in response to the status parameter value by performing at least one operation selected from the operations consisting of: adjusting a sensor range value; adjusting a sensor scaling value; adjusting a sampling frequency value; activating a sensor; deactivating a sensor; supporting multiple uses of a sensors input; and switching between sensors having different values for a characteristic selected from the characteristics consisting of: input range, sensitivity, type of sensor, location, reliability, duty cycle, and maintenance requirements.
7 . The system of claim 1 , further comprising a data marketplace circuit structured to communicate at least a portion of the detection values to a data marketplace, wherein the data marketplace circuit performs at least one of self-organizing the data marketplace and automating the data marketplace.
8 . The system of claim 7 , wherein the data storage circuit is further structured to store a distributed ledger, wherein the distributed ledger for stores at least one of: at least a portion of transaction associated with the data marketplace, and at least a portion of the data values.
9 . The system of claim 1 , further comprising a signal conditioning circuit structured to condition at least one of the plurality of detection values.
10 . The system of claim 9 , wherein the signal conditioning circuit is further structured to condition the at least one of the plurality of detection values by performing at least one operation selected from the operations consisting of: increasing an over-sampling rate, reducing a sampling rate, using a clock divider, reducing anti-aliasing operations, improving a signal to noise ratio, band pass filtering, and band pass tracking.
11 . A method for data collection in an industrial production environment, the method comprising:
interpreting a plurality of detection values, each of the plurality of detection values corresponding to input received from a detection package, the detection package comprising at least one of a plurality of input sensors, each of the plurality of input sensors operatively coupled to at least one of a plurality of process components;
storing the plurality of detection values and a plurality of data collection routes, wherein the plurality of data collection routes each comprise a different data collection routine;
self-organizing the plurality of detection values into at least one data collection band; and
analyzing the plurality of detection values and determine a status parameter value.
12 . The method of claim 11 , wherein at least one data collection band comprises at least one of the characteristics selected from the characteristics consisting of: a specific frequency band, a group of spectral peaks, a true-peak level, a crest factor derived from a time waveform, a utilization level, a process yield, and an overall waveform derived from a vibration envelope.
13 . The method of claim 11 , wherein self-organizing the plurality of detection values comprises performing at least one technique selected from the techniques consisting of: learning vector quantization, utilizing an echo state network, utilizing a bi-directional recurrent network, utilizing a stochastic network, utilizing a genetic scale recurrent network, utilizing a committee of machines, utilizing an associative network, utilizing a neuro-fuzzy network, utilizing a compositional pattern-producing network, utilizing a hierarchical temporal memory network, and a utilizing a holographic associate memory network.
14 . The method of claim 11 , further adjusting the detection package in response to the status parameter value,
15 . The method of claim 14 , wherein adjusting the detection package comprises performing at least one of the operations selected from the operations consisting of: adjusting a sensor range; adjusting a sensor's scaling; adjusting a sampling frequency; activating a sensor; deactivating a sensor; supporting multiple uses of a sensors input; and switching between sensors having distinct values for at least one characteristic selected from the characteristics consisting of: input ranges, sensitivities, locations, reliabilities, duty cycles, sensor types, and maintenance requirements.
16 . The method of claim 11 , further comprising:
communicating at least a portion of the detection values to a data marketplace, wherein the data marketplace comprises one of self-organizing and automated; and
storing a distributed ledger for tracking at least one transaction of the data marketplace circuit.
17 . An apparatus for data collection in an industrial production environment, the apparatus comprising:
a data acquisition component configured to interpret a plurality of detection values, each of the plurality of detection values corresponding to input received from at least one of a plurality of input sensors, wherein the at least one of the plurality of input sensors comprises a detection package, each of the plurality of input sensors operatively coupled to at least one of a plurality of components of an industrial production process;
a data storage component configured to store at least one of: a subset of the plurality of detection values, and a plurality of data collection routes; wherein the plurality of data collection routes each comprise a different data collection routine;
an expert system component configured to self-organize the plurality of detection values into at least one data collection band; and
a data analysis component configured to analyze the subset of the plurality of detection values and determine a status parameter value.
18 . The apparatus of claim 17 , further comprising a data marketplace component configured to make available at least a portion of the detection values in a data marketplace.
19 . The apparatus of claim 18 , wherein the data storage component is further configured to store a distributed ledger for tracking at least one transaction associated with the data marketplace.
20 . The apparatus of claim 14 , further comprising a signal conditioning component configured to condition at least one of the plurality of detection values by increasing an over-sampling rate and reducing anti-aliasing operations.