# US 2025/0155855 A1 · Automated monitoring diagnostic using augmented streaming decision tree

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0155855 A1
- Document ID: US20250155855A1
- Status: Published application
- Kind: A1
- Application number: 19/022,600
- Filed: 2025-01-15
- Published: 2025-05-15
- Earliest claimed: 2021-07-13
- Assignees: Rockwell Automation Technologies, Inc.
- Applicants: Rockwell Automation Technologies, Inc.
- Inventors: Bijan SayyarRodsari; Jakob Methfessel; Kadir Liano
- Web page: https://patentgrep.com/patent/US20250155855A1

## CPC

- G05B 13/042: {in which a parameter or coefficient is automatically adjusted to optimise the performance}
- G05B 13/028: {using expert systems only}
- G05B 13/048: {using a predictor}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processor to perform operations that include receiving operational parameters for one or more automation devices, wherein the one or more automation devices are configured to implement control logic generated based on a decision tree. The operations also include receiving an output by the decision tree based on the operational parameters. Further, the operations include determining the output is an anomalous output based on a constraint associated with the decision tree. Further still, the operations include generating an updated decision tree based on the anomalous output. Even further, the operations include generating updated control logic for the one or more automation devices based on the updated decision tree. Even further, the operations include sending the updated control logic to the one or more automation devices.

## Claims

### Claim 1

A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processing system to perform operations comprising:
receiving process input data associated with one or more automation devices, wherein the one or more automation devices are configured to implement control logic generated based on a decision tree;
receiving a classification output from a plurality of classification outputs by the decision tree corresponding to an expected operating condition of the one or more automation devices based on one or more operational parameters;
determining that the classification output is an anomalous classification output based on one or more operating range thresholds of the one or more operational parameters;
identifying a plurality of nodes of the decision tree that link the process input data to the classification output based on a first plurality of branches of the decision tree;
identifying one or more validated nodes of the plurality of nodes based on the first plurality of branches;
generating an updated decision tree based on the one or more validated nodes, wherein the updated decision tree comprises a second plurality of branches and the one or more validated nodes;
generating updated control logic for the one or more automation devices based on the updated decision tree; and
sending the updated control logic to the one or more automation devices, wherein the updated control logic, when executed, causes the one or more automation devices to adjust one or more operations of the one or more automation devices based on the updated control logic such that the one or more operational parameters are within the one or more operating range thresholds.

### Claim 2 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein determining that the classification output is the anomalous classification output is based on a constraint indicating the one or more operating range thresholds of the one or more automation devices.

### Claim 3 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein generating the updated decision tree comprises generating a new path within the updated decision tree that links a subset of the process input data to an additional classification output of the plurality of classification outputs.

### Claim 4 (depends on 3)

The non-transitory computer-readable medium of claim 3, wherein the new path comprises an additional plurality of nodes, and wherein the additional plurality of nodes is different from the plurality of nodes.

### Claim 5 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the expected operating condition indicates a future fault that may occur for the one or more automation devices.

### Claim 6 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the control logic comprises ladder logic.

### Claim 7 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the computer-executable instructions, when executed, are configured to cause the processing system to cluster the process input data, wherein clustering the process input data comprises utilizing a stream clustering engine to create labels for the process input data.

### Claim 8 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the updated control logic, when executed, is received via a control system associated with the one or more automation devices.

### Claim 9 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein determining that the classification output is the anomalous classification output comprises outputting a notification indicative of the classification output.

### Claim 10

A method, comprising:
receiving, via a processing system, process input data associated with one or more automation devices, wherein the one or more automation devices are configured to implement control logic generated based on a decision tree;
receiving, via the processing system, a classification output from a plurality of classification outputs by the decision tree corresponding to an expected operating condition of the one or more automation devices based on one or more operational parameters;
determining, via the processing system, that the classification output is an anomalous classification output based on one or more operating range thresholds of the one or more operational parameters;
identifying, via the processing system, a plurality of nodes of the decision tree that link the process input data to the classification output based on a first plurality of branches of the decision tree;
identifying, via the processing system, one or more validated nodes of the plurality of nodes based on the first plurality of branches;
generating, via the processing system, an updated decision tree based on the one or more validated nodes, wherein the updated decision tree comprises a second plurality of branches and the one or more validated nodes;
generating, via the processing system, updated control logic for the one or more automation devices based on the updated decision tree; and
sending, via the processing system, the updated control logic to the one or more automation devices, wherein the updated control logic, when executed, causes the one or more automation devices to adjust one or more operations of the one or more automation devices based on the updated control logic such that the one or more operational parameters are within the one or more operating range thresholds.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining that the classification output is the anomalous classification output is based on a constraint indicating the one or more operating range thresholds of the one or more automation devices.

### Claim 12 (depends on 10)

The method of claim 10, wherein generating the updated decision tree comprises generating a new path within the updated decision tree that links a subset of the process input data to an additional classification output of the plurality of classification outputs.

### Claim 13 (depends on 12)

The method of claim 12, wherein the new path comprises an additional plurality of nodes, and wherein the additional plurality of nodes is different from the plurality of nodes.

### Claim 14 (depends on 10)

The method of claim 10, wherein the expected operating condition indicates a future fault that may occur for the one or more automation devices.

### Claim 15 (depends on 10)

The method of claim 10, wherein the control logic comprises ladder logic.

### Claim 16 (depends on 10)

The method of claim 10, further comprising:
clustering, via the processing system, the process input data, wherein clustering the process input data comprises utilizing a stream clustering engine to create labels for the process input data.

### Claim 17 (depends on 10)

The method of claim 10, wherein the updated control logic, when executed, is received via a control system associated with the one or more automation devices.

### Claim 18 (depends on 10)

The method of claim 10, wherein determining that the classification output is the anomalous classification output comprises outputting a notification indicative of the classification output.

### Claim 19

A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processing system to perform operations comprising:
receiving process input data associated with one or more automation devices, wherein the one or more automation devices are configured to implement control logic generated based on a decision tree;
clustering the process input data, wherein clustering the process input data comprises utilizing a steam clustering engine;
receiving a classification output from a plurality of classification outputs by the decision tree corresponding to an expected operating condition of the one or more automation devices based on one or more operational parameters;
determining that the classification output is an anomalous classification output based on one or more operating range thresholds of the one or more operational parameters;
identifying a plurality of nodes of the decision tree that link the clustered process input data to the classification output based on a first plurality of branches of the decision tree;
identifying one or more validated nodes of the plurality of nodes based on the first plurality of branches;
generating an updated decision tree based on the one or more validated nodes, wherein the updated decision tree comprises a second plurality of branches and the one or more validated nodes;
generating updated control logic for the one or more automation devices based on the updated decision tree; and
sending the updated control logic to the one or more automation devices, wherein the updated control logic, when executed, causes the one or more automation devices to adjust one or more operations of the one or more automation devices based on the updated control logic such that the one or more operational parameters are within the one or more operating range thresholds.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein generating the updated decision tree comprises generating a new path within the updated decision tree that links a subset of the clustered process input data to an additional classification output of the plurality of classification outputs, and wherein the new path comprises an additional plurality of nodes such that the additional plurality of nodes is different from the plurality of nodes.
