Data processing device, processor core array and method for characterizing behavior of equipment under observation

• US 10,481,923 B2
• Filed: 12/21/2018
• Issued: 11/19/2019
• Est. Priority Date: 12/05/2013
• Status: Active Grant

• Current Assignee: Blue Yonder Group, Inc. (Panasonic Holdings Corporation)
• Original Assignee: JDA Software Group Incorporated (RedPrairie Holding Incorporated)
• Inventors: Kienle, Frank
• Primary Examiner(s): Nguyen, Tan T.
• Application Number:
  US16/229,283
• Publication Number:
  US 20190114184A1
• Time in Patent Office: 333 Days
• Field of Search: None
• CPC Class Codes: G05B 19/042 using digital processors G05B19/05 takes precedence
• CPC Class Codes: G06F 11/3024 where the computing system component is a central processing unit [CPU]
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 9/44505 Configuring for program initiating, e.g. using registry, configuration files

Abstract

A data processing device (100) characterizes behavior properties of equipment under observation (105). The device (100) has a plurality of processing units that are adapted to process input values (a) to output values (e) according to numerical transfer functions. The functions implement an input-to-output mapping specified by a configuration (C) that is obtained by pre-processing historic data (114) from a plurality of master equipment (104). The configuration is related to the behavior properties of the equipment (105) so that some of the output values (e) represent the behavior properties of the equipment (105) under observation.

Claims

1. A data processing device for characterizing behavior properties of equipment under observation, the data processing device comprising:

a processor core array comprising two or more processor cores configured to select processor cores of the two or more processor cores as a first processing stage and processor cores of the two or more processor cores as a second processing stage according to an availability of the processor cores and according to a presence of equipment data values from an equipment under observation, wherein the processor cores of the first processing stage receive two or more equipment data values from the equipment under observation as input and provide two or more intermediate data values as output, according to two or more first numerical transfer functions, and wherein the processor cores of the second processing stage receive the two or more intermediate data values as input and provide behavior data as output values according to a second numerical transfer function; and

the selected processor cores process input values based on numerical transfer functions to output values by implementing an input-to-output mapping based on a configuration obtained by a pre-processing of historic data from two or more master equipment and related to the behavior properties of the equipment under observation.

2. The data processing device according to claim 1, further comprising causing the selected processor cores to serialize operation when a number of selected processor cores is smaller than a number of equipment data values that are simultaneously present in parallel from the equipment under observation.

3. The data processing device of claim 2, wherein the selected processor cores operate sequentially as a first processing stage and a second processing stage.

4. The data processing device of claim 3, wherein the configuration comprises a first processing stage configuration and a second processing stage configuration.

5. The data processing device of claim 4, further comprising assigning data structures in a memory to operate as configuration buffers and associates the data structures with the selected processor cores to receive the configuration.

6. The data processing device of claim 5, further comprising assigning a data structure to receive a configuration of a first processing context and to receive a configuration of a second processing context, and wherein the processor core array selects two or more processor cores to process data values accordingly.

7. A computer-implemented method for operating a data processing device to characterize behavior properties of equipment under observation, the computer-implemented method comprising:

selecting processor cores of a processor core array comprising two or more processor cores as a first processing stage and processor cores of the two or more processor cores as a second processing stage, according to an availability of the selected processor cores and according to a presence of equipment data values from an equipment under observation, wherein the processor cores of the first processing stage receive two or more equipment data values from the equipment under observation as input and provide two or more intermediate data values as output, according to two or more first numerical transfer functions, and wherein the processor cores of the second processing stage receive the two or more intermediate data values as input and provide behavior data as output values according to a second numerical transfer function; and

processing input values, by the selected processor cores, based on numerical transfer functions to output values by an input-to-output mapping based on a configuration obtained by a pre-processing of historic data from two or more master equipment and related to the behavior properties of the equipment under observation.

8. The computer-implemented method of claim 7, wherein the computer-implemented method further comprises:

serializing operation, by the selected processor cores, when a number of selected processor cores is smaller than a number of equipment data values that are simultaneously present in parallel from the equipment under observation.

9. The computer-implemented method of claim 8, wherein the computer-implemented method further comprises:

operating sequentially the selected processor cores as a first processing stage and a second processing stage.

10. The computer-implemented method of claim 9, wherein the configuration comprises a first processing stage configuration and a second processing stage configuration.

11. The computer-implemented method of claim 10, wherein the computer-implemented method further comprises:

assigning data structures in a memory to operate as configuration buffers; and

associating the data structures with the selected processor cores to receive the configuration.

12. The computer-implemented method of claim 11, wherein the computer-implemented method further comprises:

assigning a data structure to receive a configuration of a first processing context and to receive a configuration of a second processing context; and

selecting, by the processor core array, two or more processor cores to process data values according to the configuration of the first processing context and the configuration of the second processing context.

13. A non-transitory computer-readable medium having stored thereon a sequence of computer-executable instructions which when executed by at least one processor of a computer performs a method for controlling a data processing device, the method comprising:

selecting processor cores of a processor core array comprising two or more processor cores, as a first processing stage and processor cores of the two or more processor cores as a second processing stage according to an availability of the selected processor cores and according to a presence of equipment data values from an equipment under observation, wherein the operation module selects the processor cores from the two or more processor cores according to an availability of the processor cores and according to a presence of equipment data values from an equipment under observation, wherein the processor cores of the first processing stage receive two or more equipment data values from the equipment under observation as input and provide two or more intermediate data values as output, according to two or more first numerical transfer functions, and wherein the processor cores of the second processing stage receive the two or more intermediate data values as input and provide behavior data as output values according to a second numerical transfer function; and

processing input values based on numerical transfer functions to output values by an input-to-output mapping based on a configuration obtained by a pre-processing of historic data from two or more master equipment and related to the behavior properties of the equipment under observation.

14. The non-transitory computer-readable medium of claim 13, wherein the method further comprises:

serializing operation of the selected processor cores when a number of selected processor cores is smaller than a number of equipment data values that are simultaneously present in parallel from the equipment under observation.

15. The non-transitory computer-readable medium of claim 14, wherein the method further comprises:

operating sequentially the selected processor cores as a first processing stage and a second processing stage.

16. The non-transitory computer-readable medium of claim 15, wherein the configuration comprises a first processing stage configuration and a second processing stage configuration.

17. The non-transitory computer-readable medium of claim 16, wherein the method further comprises:

assigning data structures in a memory to operate as configuration buffers; and

associating the data structures with the selected processor cores to receive the configuration.