# US 12,111,634 B2 · Systems and methods for using intermediate data to improve system control and diagnostics > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,111,634 B2 - Document ID: US12111634B2 - Status: Granted - Kind: B2 - Application number: 17/443,595 - Filed: 2021-07-27 - Published: 2022-01-27 - Granted: 2024-10-08 - Earliest claimed: 2020-07-27 - Assignees: Watlow Electric Manufacturing Company - Applicants: Watlow Electric Manufacturing Company - Inventors: Jacob Lindley; Miranda Pizzella; Jeremy Quandt; Philip Schmidt; John Bergen; Hanwen Yuan; Daniel Gander - Web page: https://patentgrep.com/patent/US12111634B2 ## CPC - G05B 17/02: electric - G05B 19/4155: characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program - G05B 13/04: involving the use of models or simulators - G05B 13/048: {using a predictor} - G05B 17/00: Systems involving the use of models or simulators of said systems (G05B13/00, G05B15/00, G05B19/00 take precedence) - G05B 11/42: for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D. - G05B 2219/50333: Temperature - G05D 23/1917: {using digital means} - 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) - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES ## Abstract A method of controlling a thermal system of an industrial process includes monitoring intermediate data, associating the intermediate data with correlation data, wherein the correlation data includes an internal process control input, an external heater control input, the output control, or a combination thereof. The method further includes generating a model that defines a relationship between the intermediate data and the correlation data, identifying a state of the heater system based on the model, and selectively performing a corrective action based on the identified state of the heater system. ## Claims ### Claim 1 A method of controlling a thermal system of an industrial process, the thermal system including a heater system and a process control system configured to generate an output control for the heater system based on intermediate data generated by the process control system, the method comprising: monitoring the intermediate data; associating the intermediate data with correlation data, wherein the correlation data is associated with the output control, and wherein the intermediate data comprises one or more of: proportional gain data, integral gain data, or derivative gain data; generating a supervised learning model that defines a relationship between the intermediate data and the correlation data; predicting a state of the heater system based on the supervised learning model; and selectively performing a corrective action based on the predicted state of the heater system, wherein the corrective action includes controlling power to the heater system based on the predicted state of the heater system. ### Claim 2 (depends on 1) The method of claim 1, wherein the correlation data includes an internal process control input or an external heater control input. ### Claim 3 (depends on 1) The method of claim 1, wherein the output control is based on a sum of the proportional gain data, the integral gain data, and the derivative gain data. ### Claim 4 (depends on 1) The method of claim 1, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and wherein the intermediate data includes loop data of the cascade control system. ### Claim 5 (depends on 4) The method of claim 4, wherein the output control is based on a sum of proportional gain data of the secondary controller, integral gain data of the secondary controller, and derivative gain data of the secondary controller. ### Claim 6 (depends on 1) The method of claim 1, wherein the intermediate data includes a controller gain of the process control system. ### Claim 7 (depends on 1) The method of claim 1, wherein the model is one or more of a mathematical model or a machine learning model. ### Claim 8 (depends on 1) The method of claim 1 further comprising: comparing the model with a nominal model defining a nominal relationship between the intermediate data and the correlation data; and determining a deviation between the nominal model and the model, wherein the predicted state of the heater system is further based on the deviation. ### Claim 9 (depends on 8) The method of claim 8, wherein the deviation includes a proportional gain deviation, an integral gain deviation, or a derivative gain deviation. ### Claim 10 (depends on 1) The method of claim 1, wherein the correlation data comprises an internal process control input that comprises a desired setpoint of a performance characteristic of the heater system, a setpoint for controlling the heater system, a process variable, a measured value of the process variable, or an alert associated with the thermal system. ### Claim 11 (depends on 10) The method of claim 10, wherein the internal process control input comprises pressure data, mass flow rate data, vibration data, strain data, or temperature data. ### Claim 12 (depends on 1) The method of claim 1, wherein the corrective action includes controlling power to the heater system based on the predicted of the heater system. ### Claim 13 (depends on 1) The method of claim 1, wherein the corrective action includes broadcasting an alert based on the predicted state of the heater system, wherein the alert indicates a material accumulation within a conduit communicatively coupled to the process control system, or a nominal thermal deviation of a resistive heating element communicatively coupled to the process control system. ### Claim 14 (depends on 1) The method of claim 1, wherein the correlation data comprises an external heater control input that is an output generated by an external device of the process control system. ### Claim 15 A process control system for controlling a heater system, the process control system configured to generate an output control for the heater system based on intermediate data generated by the process control system, the process control system comprising: a processor; and a nontransitory computer-readable medium comprising instructions that are executable by the processor, wherein the instructions comprise: monitoring the intermediate data; associating the intermediate data with correlation data, wherein the correlation data is associated with the output control, and wherein the intermediate data comprises one or more of: proportional gain data, integral gain data, or derivative gain data; generating a supervised learning model that defines a relationship between the intermediate data and the correlation data; predicting identifying a state of the heater system based on the supervised learning model; and selectively performing a corrective action based on the predicted state of the heater system, wherein the corrective action includes controlling power to the heater system based on the predicted state of the heater system. ### Claim 16 (depends on 15) The process control system of claim 15, wherein the correlation data includes an internal process control input or an external heater control input. ### Claim 17 (depends on 15) The process control system of claim 15, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and wherein the intermediate data includes loop data of the cascade control system. ### Claim 18 (depends on 15) The process control system of claim 15, wherein: the model is configured to predict the state of the heater system based on the intermediate data and the correlation data; and the instructions further comprise: comparing the model with a nominal model defining a nominal relationship between the intermediate data and the correlation data; and determining a deviation between the nominal model and the model, wherein the predicted state of the heater system is further based on the deviation. ### Claim 19 (depends on 15) The process control system of claim 15, wherein the correlation data includes the output control, wherein the output control comprises an internal process control input that comprises a desired setpoint of a performance characteristic of the heater system, a setpoint for controlling the heater system, a process variable, a measured value of the process variable, or an alert associated with a thermal system. ### Claim 20 (depends on 15) The process control system of claim 15, wherein the output control is based on a sum of the proportional gain data, the integral gain data, and the derivative gain data. ### Claim 21 A method of controlling a thermal system of an industrial process, the thermal system including a heater system and a process control system configured to generate an output control for the heater system based on intermediate data generated by the process control system, the method comprising: associating the intermediate data with correlation data, wherein the correlation data is associated with the output control, and wherein the intermediate data comprises one or more of: proportional gain data, integral gain data, or derivative gain data; generating a supervised learning model that defines a relationship between the intermediate data and the correlation data; comparing the model with a nominal model defining a nominal relationship between the intermediate data and the correlation data; predicting a state of the heater system based on the comparison between the nominal model and the model; and selectively performing a corrective action based on the predicted state of the heater system, wherein the corrective action includes controlling power to the heater system based on the predicted state of the heater system. ### Claim 22 (depends on 21) The method of claim 21, wherein the correlation data includes an internal process control input or an external heater control input. ### Claim 23 (depends on 21) The method of claim 21, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and wherein the intermediate data includes loop data of the cascade control system. ### Claim 24 (depends on 21) The method of claim 21, wherein the predicted state of the heater system is further based on a deviation between the nominal model and the model, and wherein the deviation includes a proportional gain deviation, an integral gain deviation, or a derivative gain deviation. ### Claim 25 (depends on 21) The method of claim 21, wherein the correlation data comprises an internal process control input that comprises a desired setpoint of a performance characteristic of the heater system, a setpoint for controlling the heater system, a process variable, a measured value of the process variable, or an alert associated with the thermal system. ### Claim 26 (depends on 25) The method of claim 25, wherein the internal process control input comprises pressure data, mass flow rate data, vibration data, strain data, or temperature data. ### Claim 27 (depends on 21) The method of claim 21, wherein the correlation data comprises an external heater control input that is an output generated by an external input controller of the process control system.