Systems and methods for using intermediate data to improve system control and diagnostics.

Abstract

A method for controlling a thermal system of an industrial process includes monitoring intermediate data and associating the intermediate data with correlated data, the correlated data including internal process control inputs, external heater control inputs, output controls, or a combination thereof. The method further includes generating a model defining a relationship between the intermediate data and the correlated data, identifying a state of the heater system based on the model, and selectively taking corrective action based on the identified state of the heater system.

Description

Technical Field

[0001] The present disclosure relates to a method for operating a thermal system having a process control system and a heater system.

[0002] Cross - Reference to Related Applications This application claims the priority and benefit of U.S. Provisional Patent Application No. 63 / 056,810, filed on Jul. 27, 2020. The content of the above application is hereby incorporated herein by reference in its entirety.

Background Art

[0003] The description in this section merely provides background information related to the present disclosure and may not constitute prior art.

[0004] [[ID=二十一]] [[ID=二十二]]

Summary of the Invention

[0005] This section provides a general overview of the present disclosure and does not disclose comprehensively all the scope or all the features of the present disclosure. [[ID=三十]] ​

[0006] This disclosure provides a method for controlling a thermal system in an industrial process. The thermal system includes a heater system and a process control system configured to generate output controls for the heater system based on intermediate data generated by a process control system. The method includes monitoring the intermediate data and relating the intermediate data to correlated data, the correlated data including internal process control inputs, external heater control inputs, output controls, or a combination thereof. The method includes generating a model that defines the relationship between the intermediate data and the correlated data, identifying the state of the heater system based on the model, and taking selective corrective actions based on the identified state of the heater system.

[0007] In some forms, the intermediate data includes proportional gain data, integral gain data, differential gain data, or a combination thereof. In some forms, output control is based on the sum of proportional gain data, integral gain data, and differential gain data. In some forms, the process control system includes a cascaded control system having primary and secondary controllers, and the intermediate data includes loop data of the cascaded control system. In some forms, output control is based on the sum of proportional gain data of the secondary controller, integral gain data of the secondary controller, and differential gain data of the secondary controller. In some forms, the intermediate data includes controller gains of the process control system. In some forms, the model is a mathematical model, a machine learning model, or a combination thereof. In some forms, the machine learning model is a supervised learning model configured to predict the state of the heater system based on intermediate data and correlation data. In some forms, the method includes comparing the model with a nominal model that defines a nominal relationship between the intermediate data and correlation data, and determining the deviation between the nominal model and the model, and the identified state of the heater system is further based on the deviation. In some forms, the deviation includes proportional gain deviation, integral gain deviation, differential gain deviation, or a combination thereof. In some forms, the internal process control input includes a desired setpoint for the performance characteristics of the heater system, a setpoint for controlling the heater system, process variables, measured values ​​of process variables, alerts related to the thermal system, or a combination thereof. In some forms, the corrective action includes controlling the power of the heater system based on an identified state of the heater system. In some forms, the corrective action includes broadcasting an alert based on an identified state of the heater system, the alert indicating material accumulation in a conduit communicably coupled to the process control system, the nominal thermal deviation of a resistive heating element communicably coupled to the process control system, or a combination thereof. In some forms, the external heater control input is external to the process control system. deviceThis is the output generated by the process. In some forms, the internal process control input includes pressure data, mass flow data, vibration data, strain data, temperature data, or a combination thereof.

[0008] This disclosure provides a process control system for controlling a heater system, the process control system configured to generate output controls for the heater system based on intermediate data generated by the process control system. The process control system includes a processor and a non-temporary computer-readable medium having instructions executable by the processor. The instructions include monitoring intermediate data and associating the intermediate data with correlated data, the correlated data including internal process control inputs, external heater control inputs, output controls, or a combination thereof. The instructions include generating a model that defines the relationship between the intermediate data and the correlated data, identifying the state of the heater system based on the model, and taking selective corrective actions based on the identified state of the heater system.

[0009] In some forms, the model is configured to predict the state of the heater system based on intermediate data and correlated data. In some forms, the instructions further include comparing the model with a nominal model that defines a nominal relationship between the intermediate data and correlated data, determining the deviation between the nominal model and the model, and the identified state of the heater system is further based on the deviation.

[0010] This disclosure provides a method for controlling a thermal system in an industrial process. The thermal system includes a heater system and a process control system configured to generate output controls for the heater system based on intermediate data generated by a process control system. The method includes associating the intermediate data with correlation data, the correlation data including internal process control inputs, external heater control inputs, output controls, or a combination thereof. The method includes generating a model that defines the relationship between the intermediate data and the correlation data; comparing the model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data; identifying the state of the heater system based on the comparison between the nominal model and the model; and selectively taking corrective actions based on the identified state of the heater system.

[0011] Further areas of application will become apparent from the descriptions provided herein. It should be understood that these descriptions and examples are for illustrative purposes only and are not intended to limit the scope of this disclosure. [Brief explanation of the drawing]

[0012] To ensure that this disclosure is properly understood, various forms of this disclosure, given as examples, will be described below with reference to the attached drawings.

[0013] [Figure 1] This is a block diagram of a thermal system having a process control system, a heater system, and an intermediate control system related to this disclosure. [Figure 2] This is an example of a process control system related to this disclosure. [Figure 3] This is another example of a process control system related to this disclosure. [Figure 4] This is another example of a process control system related to this disclosure. [Figure 5] This is a flowchart for operating a thermal system having an intermediate control system as described in this disclosure.

[0014] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of this disclosure in any way. [Modes for carrying out the invention]

[0015] The following description is essentially a typical example and is not intended to limit the scope of this disclosure, application, or use. It should be understood that throughout the drawings, corresponding reference numbers indicate similar or corresponding parts and features.

[0016] Referring to Figure 1, a thermal system 10 is shown, which includes a process control system 100, an intermediate control system 200, and a heater system 300 having a heater 302. In one embodiment, the process control system 100 is configured to control the operation of the heater system 300, specifically the heater 302. As further described herein, the intermediate control system 200 of this disclosure is configured to define a model (e.g., a mathematical model, a machine learning model, or a combination thereof) based on intermediate data in order to predict the state of the heater system 300 using real-time intermediate data input.

[0017] The thermal system 10 may be part of various types of industrial processes for controlling the thermal properties of a heated load. For example, the thermal system 10 may be part of a semiconductor process in which a heater system 300 includes a pedestal heater for heating a wafer (e.g., a load). In this example, the process control system 100 may be configured to control the thermal profile of the pedestal heater, which may vary based on external and internal thermal control. For example, internal thermal control may include, but is not limited to, the power supplied to the pedestal heater, the operating mode of the thermal system 10 (e.g., among various operating modes defined to control the heater system 300, a manual mode that controls power to the heater 302 based on user input, a cold start mode that gradually increases the temperature of the pedestal heater, a steady-state mode that maintains the pedestal heater at a temperature setpoint), and / or, if the pedestal heater is a multi-zone heater, the operating states of different zones of the pedestal heater. Examples of external thermal control include, but are not limited to, the type of wafer being heated, the gas injected into the process chamber having the pedestal heater, and / or the pressure difference within the chamber for fixing the wafer to the pedestal heater, among various factors that are not controllable by the thermal system 10.

[0018] In other examples, the thermal system 10 may be used in a semiconductor process abatement system to heat a fluid flowing through a network of conduits. In one embodiment, the heater system 300 may include a plurality of flexible heaters wrapped around conduits for heating the fluid inside. In yet another example, the thermal system 10 may utilize a cartridge heater as part of the heating system 300 to directly heat a fluid (e.g., gas and / or liquid) flowing through conduits or supplied into a container.

[0019] Various process control systems 100 may be used to control the heating system 300. An example of a process control system 100 is disclosed in U.S. Patent No. 10,908,195, filed August 10, 2018, entitled “SYSTEM AND METHOD FOR CONTROLLING POWER TO A HEATER,” which is co-owned with this application and whose entire contents are incorporated herein by reference. In this example of a process control system, the controller is configured to select state model controls that define one or more operating settings for the heater (e.g., power-up control, soft-start control, set-rate control, and steady-state control), and to control the power supplied to the heater based on the state model controls and the electrical characteristics of the heater (e.g., current, voltage, or a combination thereof).

[0020] Another example of the process control system 100 is disclosed in U.S. Application No. 16 / 294,201, a concurrently pending application filed on March 6, 2019, entitled “CONTROL SYSTEM FOR CONTROLLING A HEATER,” which is co-owned with this application and whose entire contents are incorporated herein by reference. In this example of a process control system, two or more auxiliary controllers control the power to multiple zones of the heating system 300 based on the performance characteristics of the heating system 300, and a primary controller provides operating setpoints for each heater zone based on the performance characteristics.

[0021] An example of an additional process control system 100 is disclosed in U.S. Application No. 16 / 568,757, a co-pending application entitled "SYSTEM AND METHOD FOR A CLOSED-LOOP BAKE-OUT CONTROL," filed on September 12, 2019, which is co-owned with this application and the entire content of which is incorporated herein by reference. In this example of a process control system, the controller is configured to determine an operating power level based on measured performance characteristics of the heater, a power setpoint, and a power control algorithm, and is configured to determine a bake-out power level. The controller selects a power level applied to the heating system 300 based on the lower of the operating power level and the bake-out power level.

[0022] Another example of a process control system 100 is disclosed in U.S. Application No. 17 / 089,447, a co-pending application entitled "CONTROL AND MONITORING SYSTEM FOR GAS DELIVERY SYSTEM," filed on November 4, 2020, which is co-owned with this application and the entire content of which is incorporated herein by reference. In this example, the process control system generates a virtual image that visualizes the gases flowing through the fluid flow line and their impact on the thermal system 10 based on virtual mapping routines, measured system data, and / or statistical analysis.

[0023] Specific applications of the thermal system 10 are provided herein, but the present disclosure may be applicable to other industrial processes having a thermal system for heating a load. These applications may include, by way of example, injection molding processes, heat exchangers, exhaust gas aftertreatment systems, and energy processes. Also, the heater 302 of the heating system 300 should not be limited to the examples provided herein and may include, by way of example, a sheet heater, a cartridge heater, a tubular heater, a polymer heater, a flexible heater, and the like. In each application, as described herein, external and internal controls can be identified and utilized by the intermediate control system 200.

[0024] As used herein, the term "intermediate data" refers to data generated by the process control system 100 to determine output control. For example, the intermediate data may include proportional gain data, integral gain data, and / or derivative gain data, loop data of a cascade control system (as the process control system 100), and / or controller gain of the process control system 100.

[0025] As used herein, the term "process variable" refers to a measurable performance characteristic of the heater system 300. For example, if the heater system 300 is a two-wire heater system as described below, the performance characteristics may include the temperature, resistance, voltage, and / or current of the heater 302. In other forms, the performance characteristics may be measured using individual sensors arranged with the heater system 300. As another example, the process variable may include the power applied to the heater 302.

[0026] As used herein, the term "output control" refers to an output for controlling the process variable of the heater system 300 and is based on intermediate data. For example, the output control may include, but is not limited to, the output of PID control, the amount of power supplied to the heater system 300, and / or other suitable parameters for controlling the power to the heater system 300, and is based on intermediate data. As another example, the output control may include the sum of the proportional data, integral gain data, and derivative gain data of the secondary controller of a cascade control system (as the process control system 100).

[0027] As used herein, the term “internal process control input” refers to measured data from systems / sensors within the thermal system 10 (e.g., pressure data, mass flow data, vibration data, strain data, temperature data, etc.) and may include process variables, measured values ​​of process variables, setpoints for controlling the heater system 300, and / or performance characteristics of the heater system 300. The internal process control input may also include, in particular, setpoints such as target values ​​for process variables, temperature setpoints, and power setpoints, among a variety of measurable setpoints that may be provided by the user or defined by the process control system 100. The internal process control input may also include data indicating alerts issued by the thermal system 10 in response to abnormal operation of the heater system 300.

[0028] As used herein, the term “external heater control input” refers to an input from an external input device 320 which may include an external controller and / or system located outside the thermal system 10. device Examples 320 include, but are not limited to, various external devices / systems, particularly feedforward controllers, sensors located outside the thermal system 10, control systems(s) that operate different subsystems in an industrial process, and human-machine interfaces that can be operated by a technician to provide information about the operating state of the industrial process. In one embodiment, external heater control inputs may include, but are not limited to, various external heater control inputs not controlled and / or generated by the thermal system 10, particularly inputs / information from a technician, disturbances in the industrial process that may affect the performance of the thermal system 10 (e.g., diagnostic codes or alerts indicating identified abnormal operation, such as over-temperature alarms, over-current alarms, over-voltage alarms, leakage limit alarms, shutdown alarms, corrective action alarms, etc.), data from sensors located outside the thermal system 10, and the operating state of external subsystems.

[0029] In one embodiment, the heater system 300 may be a two-wire heater system in which the heater 302 is operable to generate heat and act as a sensor for measuring the performance characteristics of the heater 302. For example, the heater 302 includes one or more resistive heating elements that act as sensors for measuring the average temperature of the resistive heating elements based on the resistance of the resistive heating elements. Specifically, an example of such a two-wire heater system is disclosed in U.S. Patent No. 7,196,295, which is co-owned with this application and whose entire contents are incorporated herein by reference. In a two-wire system, the thermal system is a thermal system that integrates the heater design into a control that incorporates power, resistance, voltage, and current into a customizable feedback control system, which controls one or more of these parameters (i.e., power, resistance, voltage, and current) while limiting the others. In one embodiment, the process control system 100 is configured to monitor at least one of the current, voltage, and power supplied to the resistive heating elements in order to determine the temperature of the resistive heating elements by determining the resistance.

[0030] In other applications, as a two-wire heater, heater 302 is configured to include temperature-sensing power pins for measuring the temperature of heater 302. The use of power pins as thermocouples for measuring the temperature of a resistive heating element is disclosed in the applicant's concurrently pending application, U.S. Application No. 14 / 725,537, filed May 29, 2015, entitled “RESISTIVE HEATER WITH TEMPERATURE SENSING POWER PINS,” which is co-owned with this application and whose entire contents are incorporated herein by reference. Generally, the resistive heating element of heater 302 and the process control system 100 are connected via first and second power pins defining a first and second junction, respectively. The first and second power pins function as thermocouple-sensing pins for measuring the temperature of the resistive heating element of heater 302. The process control system communicating with the first and second power pins is configured to measure changes in voltage at the first and second junctions. Specifically, the process control system measures millivolt (mV) changes at the junction and then uses these voltage changes to calculate the average temperature of the resistive heating element.

[0031] As an alternative to or addition to a two-heater system, the heater system 300 may include one or more discrete sensors for measuring the performance characteristics of the heater 302. For example, a temperature sensor may be provided on the heater 302 and communicatively coupled to the process control system 100 to provide temperature measurements as process variables. In one embodiment, at least one of the following, such as a pressure sensor, a flow sensor, a voltage sensor, and / or a current sensor, is provided on the heater 302 to obtain the corresponding performance characteristics.

[0032] The process control system 100 is configured to control the heater system 300 based on one or more control processes that generate intermediate data to determine output control for controlling the heater system 300. In one embodiment, the process control system 100 includes a control loop module 102 and a power control module 104. The control loop module 102 is configured to perform one or more control processes to determine output control based on at least one setpoint (a variety of measurable parameters for controlling the heater system, such as temperature, power, and resistance) and process variables that represent measurable performance characteristics of the heater system 300.

[0033] In one embodiment, referring to Figure 2, the control loop module 102 may be provided as a control loop module 102-1 which is a PID controller including a summation module 103, a proportional control module 105, an integral control module 106, a differential control module 108, and a summation module 110. Although the control loop module 102-1 is shown having a proportional control module 105, an integral control module 106, and a differential control module 108, it should be understood that the control loop module 102-1 may not include all of these modules in other modifications. For example, the control loop module may be a PI module having a proportional control module and an integral control module.

[0034] During operation, based on the setpoint and process variables, the summation module 103 determines an error value based on the difference between the setpoint and the process variables and provides the error value to modules 105, 106, and 108. The proportional control module 105 determines proportional gain data based on the product of the error value and the proportional gain value. The integral control module 106 determines integral gain data based on the product of the integral of the error value and the integral gain value. The differential control module 108 determines differential gain data based on the product of the derivative of the error value and the differential gain value. In some forms, the proportional gain value, integral gain value, and differential gain value may be selectively selected to achieve specific response characteristics of the heater system 300, such as a particular rise time, overshoot magnitude, settling time, and steady-state error. The summation module 110 then provides the sum of the proportional gain data, integral gain data, and differential gain data to the power control module 104 as output control.

[0035] As a specific example, the control loop module 102-1 is configured to calculate the operating power level applied to the heater 302 of the heater system 300 such that the power applied to the heater 302 is approximately equal to the power setpoint. For example, in one embodiment, the control loop module 102-1 calculates the power supplied to the heater 302 based on the measured operating current and the input voltage (i.e., process variable) applied to the heater 302. The summation module 103 determines the difference between the measured power applied and the setpoint, and the proportional control module 105, integral control module 106, and differential control module 108 determine the power level (i.e., operating power level) required to reduce the difference between the measured power of the heater 302 and the power setpoint as output control.

[0036] As another example, as shown in Figure 3, the control loop module 102-2 may include multiple PID control modules, such as a power PID control module 112 and a temperature PID control module 114, which selectively monitor and control the heater system 300 via a PID selection module 116. The power PID control module 112 may be configured to perform the functions of the control loop module 102-1 described above with reference to Figure 2. The temperature PID control module 114 is configured to calculate the operating temperature of the heater 302 such that the temperature of the heater 302 is approximately equal to the temperature setpoint. For example, in one embodiment, the temperature PID control module 114 calculates the temperature of the heater 302 based on the resistance / impedance of the heater 302 and / or data from one or more temperature sensors placed within the heater system (i.e., process variables). The temperature PID control module 114 determines the difference between the measured temperature and the temperature setpoint and, as output control, determines the power level required to reduce the difference between the measured temperature and the temperature setpoint of the heater 302.

[0037] As an additional example, as shown in Figure 4, the control loop module 102-3 includes a primary controller 118 and a secondary controller 120 as the control loop module 102, collectively forming a cascaded control system. The primary controller 118 (e.g., power PID control module 112) and the secondary controller 120 (e.g., temperature PID control module 114) may be configured to perform the functions of the control loop module 102-1 described above with reference to Figure 2. However, in this configuration, the output control of the primary controller 118 is provided to the secondary controller 120 as a setpoint variable, and the secondary controller 120 generates the output control by determining the difference between the setpoint variable obtained from the primary controller 118 and a process variable. That is, the secondary controller 120 may generate the output control based on the sum of the secondary controller 120's proportional gain data, the secondary controller 120's integral gain data, and the secondary controller 120's differential gain data.

[0038] Referring to Figure 1, in one embodiment, the control loop module 102 determines output control based on a state control signal from an intermediate control system, specifically controlling power to the heater system 300. As further described herein, the state control signal may identify the state of the heater system 300 and include instructions for controlling power to the heater system 300 based on the state. For example, the state of the heater system 300 may indicate abnormal operation of the thermal system 10 and / or industrial process, such as, for example, a failure of heater 302, undesirable thermal coupling between adjacent zones of heater 302, undesirable thermal resistance of heater 302, or blockage of fluid lines of the thermal system 10. If the state of the heater system 300 is provided as abnormal operation, the state control signal provides information indicating the abnormal operation and, in some cases, further provides instructions to address the abnormal operation, such as, for example, turning off the heater system or recalibrating the gain parameters of the process control system 100 to mitigate damage to the heater system 300. Therefore, the control loop module 102 may modify its output control to the power control module 104 to turn off power to the heater 302 and may issue an alert (e.g., a message and / or audio sound) indicating abnormal operation.

[0039] Based on the output control from the control loop module 102, the power control module 104 controls the power to the heater system 300. In one embodiment, the power control module 104 may include a power regulator circuit (not shown) that is electrically coupled to a power supply (not shown) and adjusts the power from the power supply to a selected power level and applies the adjusted power to the heater 302. Using a predefined algorithm and / or table, the power control module 104 is configured to select the power level of the heater system 300 based on the output control.

[0040] The process control system 100 is shown and described as a PID control module in Figures 1-4, but it should be understood that the process control system 100 may be various other control loop systems. Furthermore, the process control system 100 may be configured to include a separate module for analyzing state control signals from the intermediate control system 200 to determine whether corrective action (e.g., adjusting power output to the heater system 300, issuing alerts) should be taken. While specific modules are provided to form the process control system 100, the process control system 100 may also include other modules for controlling the operation of the heater system 300, such as a diagnostic module for detecting abnormal operation of the heater system 300.

[0041] In one configuration, the intermediate control system 200 is configured to analyze intermediate and correlated data from the process control system 100 to generate one or more models (e.g., machine learning models, mathematical models, etc.) that define the relationships between the intermediate and correlated data. More specifically, historical datasets of intermediate and correlated data are stored and analyzed over time to generate a model(s) and ultimately a system state model (i.e., a system state module) that associates the output of the models with the state of the heater system 300. Once defined, real-time data inputs (i.e., real-time intermediate and correlated data) are analyzed by the model(s) and system state module to determine the state of the heater system 300, and the intermediate control system provides and outputs state control signals to the process control system 100 to control the output control signals to the heater 302. Hereinafter, intermediate and correlated data may be collectively referred to as “intermediate correlated data”. To perform the functions described herein, the intermediate control system 200 of this disclosure may include one or more databases for storing historical intermediate correlation data and / or real-time intermediate correlation data, a communication infrastructure for exchanging data with external systems such as a process control system 100, and a computing system for processing the intermediate correlation data.

[0042] In one embodiment, the intermediate control system 200 includes an intermediate data model generator 201, which includes a correlation module 202 and an relation module 204, and a system state module 206. In one embodiment, the correlation module 202 is configured to acquire intermediate data (e.g., proportional gain values, integral gain values, differential gain values) and correlation data (e.g., internal process control inputs, output control and / or external heater control inputs) and store the intermediate data and correlation data in a database (not shown) using an association scheme based on, for example, a timestamp of the intermediate correlation data. For example, proportional gain values, integral gain values, and / or differential gain values ​​(collectively, PID values) from the control loop module 102 are stored in association with data from sensors (not shown) located in the thermal system 10 and / or industrial process, and alerts issued in the industrial process and / or thermal system.

[0043] In one configuration, the relation module 204 is configured to determine the relationships between intermediate correlation data, specifically, the model(s) 208. That is, using appropriate data modeling techniques, the relation module 204 identifies trends / relationships between intermediate correlation data. For example, the relation module 204 is configured to perform various supervised machine learning routines, such as linear, nonlinear, or logistic regression routines, random forest routines, or support vector routines, to generate a nominal model (as model(s) 208) that defines a nominal relationship between intermediate data and correlation data (e.g., a nonlinear regression showing a proportional gain value predicted over time) during the training routine. Alternatively, the relation module 204 may be configured to perform supervised machine learning routines to generate a supervised learning model (as model(s) 208) that shows the relationships between real-time intermediate correlation data. It should be understood that the relation module 204 may perform unsupervised or semi-supervised learning routines (e.g., clustering routines) to generate model(s) 208.

[0044] Based on model(s) 208, the intermediate data model generator 201 defines a system state module 206 used to analyze real-time intermediate correlation data. In one embodiment, the intermediate data model generator 201 continuously analyzes the intermediate correlation data to improve the model and further improve the system state module 206. The system state module 206 is provided as part of the intermediate control system 200, but once defined, it can be used with the process control system 100 to improve the response time of real-time analysis.

[0045] In one embodiment, the system state module 206 associates the possible outputs of the model(s) 208 with one or more defined states of the heater system 300. The system state module 206 processes real-time intermediate correlation data using the models stored therein to identify the state of the heater system 300 from among the defined states and transmits the identified state as a state control signal. In an application example, the system state module 206 may identify the state of the heater 302 based on its change as a function of time and adjust one of the proportional, integral, and differential gain values ​​accordingly. To perform the functions described herein, it should be understood that the system state module 206 may iteratively perform machine learning training routines to associate the outputs of the model(s) 208 with the defined states of the heater system 300. For example, the machine learning training routine may be a supervised learning routine that includes tagging training data with various states of the heater system 300, particularly the fluid storage amount in the fluid flow system, the thermal deviation of the resistive heating elements of the heater system 300, and the mismatched tool state of the heater system 300.

[0046] For example, Model 208 may define the change in intermediate data between multiple iterations as a function of timer data, and the system state module 206 may identify the state of the heater system 300 based on the change as a function of time and adjust one of the proportional gain value, integral gain value, and derivative gain value accordingly. For example, the system state module 206 may determine that a significant change in the proportional gain value of the mathematical model (as Model 208) between two or more iterations indicates that the heater system 300 is consuming excessive power, as a state of the heater system 300. Thus, the system state module 206 may transmit a state control signal indicating the state associated with the change in the proportional gain value (e.g., undesirable thermal coupling of the heater system 300). The state control signal may also instruct the process control system 100 to adjust (e.g., increase / decrease) the proportional gain value.

[0047] As another example, when the process control system 100 performs a temperature control routine, the control loop module 102 may perform an auto-tune routine that utilizes the response of the heater system 300 to select proportional, integral, and / or differential gain values ​​(collectively referred to as PID gain values). The auto-tune routine may be performed periodically, and the PID gain values ​​may be recorded each time the auto-tune routine is performed. The system state module 206 may be configured to determine that a deviation in at least one of the PID gain values ​​over time compared to a nominal model of the PID gain values ​​indicates a change in the thermal response of the heater system 300, in particular among various thermal responses identified for a specific application of the thermal system 10, such as heater dielectric breakdown or fluid accumulation in the conduits of a fluid flow system coupled to the heater system 300, as a state of the heater system 300.

[0048] As another example, using correlation data including output controls and alerts issued by the thermal system 10 and / or industrial process, the relation module 204 may associate intermediate data with output control and / or alert data and determine a response model to predict future alerts. The system state module 206 may then identify the state of the heater 302 as a possible alert and provide corrective actions based on the alert. For example, the system state module 206 may determine, based on a supervised machine learning model, that when the system generates output controls to heat a target of the fluid flow system to a specific setpoint temperature, the heater system 300 frequently initiates an emergency shutdown protocol and generates a shutdown alert. Therefore, the system state module 206 may send a state control signal that identifies a possible shutdown as the state of the heater system 300, and an instruction to adjust at least one of the PID gain values ​​to suppress the possibility of a shutdown.

[0049] Although the process control system 100, the intermediate control system 200, and the heater system 300 are shown as separate systems, it should be understood that at least one of the process control system 100, the intermediate control system 200, and the heater system 300 may be implemented as a single system. For example, the intermediate control system 200 may be provided as part of the process control system 100. In one embodiment, the intermediate control system may be located at a different location from the process control system 100 and may communicate with the process control system 100 via a wireless communication network, one or more edge computing devices located within the thermal system 10, or a combination thereof.

[0050] Referring to Figure 5, a flowchart is shown illustrating an example of routine 500 for controlling a heater system using the intermediate control system of this disclosure. In 504, the intermediate control system monitors intermediate data generated by the process control system 100. In 508, the intermediate control system 200 associates the intermediate data with correlated data. For example, in 508, the intermediate control system associates PID gain data with an output control indicating a request to set heater 303 to a specific temperature or an output control indicating a request to supply a specific voltage and / or current value to heater 302. In another example, in 508, the intermediate control system 200 associates PID gain data with an external heater control input from an external input device 320 indicating semiconductor tool matching of heater system 300. In yet another example, in 508, the intermediate control system 200 associates PID gain data with an external heater control input from an external input device 320 provided to another heater system included in the heater system network.

[0051] In 512, the intermediate control system 200 determines a model that defines the relationship between intermediate data and correlated data. In 516, the intermediate control system 200 identifies the state of the heater system based on the model. For example, in 516, the intermediate control system 200 may detect the amount of fluid stored in the fluid flow system, the thermal deviation of the resistance heating elements of the heater system, the mismatched tool state, etc. In 520, the intermediate control system 200 selectively takes corrective action based on the identified state of the heater system 300, such as controlling the power supplied to the heater system 300 based on the identified state.

[0052] Unless otherwise explicitly stated herein, all numerical values ​​indicating mechanical / thermal properties, compositional ratios, dimensions and / or tolerances, or other properties should be understood to be modified with the word "about" or "approximately" in order to describe the scope of this disclosure. This modification is desired for a variety of reasons, including industrial practice, material, manufacturing, and assembly tolerances, as well as test capability.

[0053] The spatial and functional relationships between elements are described using a variety of terms, including “connection,” “engagement,” “joining,” “adjacent,” “next to,” “above,” “below,” and “positioning.” Unless otherwise expressly described as “direct,” where a relationship between first and second elements is described in this disclosure, that relationship may be a direct relationship in which there are no other intervening elements between the first and second elements, or an indirect relationship in which there are one or more intervening elements (spatially or functionally) between the first and second elements. Where used herein, the expression “at least one of A, B, and C” should be interpreted as meaning a non-exclusive OR (A OR B OR C) and not as “at least one of A, at least one of B, and at least one of C.”

[0054] In this application, the term “module” may be replaced with the term “circuit.” The term “module” means, or may include, a part of, or all of the above, a combination of an application-specific integrated circuit (ASIC), a digital, analog, or analog / digital mixed discrete circuit, a digital, analog, or analog / digital mixed integrated circuit, a combinational logic circuit, a field-programmable gate array (FPGA), a processor circuit (shared, dedicated, or group) that executes code, a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit, other suitable hardware components that provide the function described, or some or all of the above, such as a system on a chip.

[0055] The term "code" may include software, firmware, and / or microcode, and may refer to programs, routines, functions, classes, data structures, and / or objects. The term "memory circuit" is a subset of the term "computer-readable medium." As used herein, the term "computer-readable medium" does not include transient electrical or electromagnetic signals that propagate through a medium (e.g., on a carrier wave), and may therefore be considered tangible and non-transient.

[0056] The descriptions in this disclosure are essentially typical examples, and any modifications that do not deviate from the gist of this disclosure are intended to be within the scope of this disclosure. Such modifications should not be considered to deviate from the intent and scope of this disclosure. The invention described in the original claims of this application is listed below. [1] A method for controlling a thermal system in an industrial process, wherein the thermal system includes a heater system and a process control system configured to generate output control of the heater system based on intermediate data generated by a process control system, Monitoring the aforementioned intermediate data, The intermediate data is associated with correlation data, wherein the correlation data includes internal process control inputs, external heater control inputs, output control, or a combination thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, Identifying the state of the heater system based on the aforementioned model, Selective corrective action is taken based on the identified state of the heater system. A method for providing this. [2] The method according to [1], wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, or a combination thereof. [3] The output control is the method according to [2], which is based on the sum of the proportional gain data, the integral gain data, and the differential gain data. [4] The process control system includes a cascade control system having a primary controller and a secondary controller, and the intermediate data includes loop data of the cascade control system, according to the method in [1]. [5] The output control is based on the sum of the proportional gain data of the secondary controller, the integral gain data of the secondary controller, and the differential gain data of the secondary controller, according to the method in [4]. [6] The method according to [1], which includes the controller gain of the process control system. [7] The model described above is a mathematical model, a machine learning model, or a combination thereof, as described in [1]. [8] The method according to [7], wherein the machine learning model is a supervised learning model configured to predict the state of the heater system based on the intermediate data and the correlation data. [9] The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, The determination of the deviation between the nominal model and the model, wherein the identified state of the heater system is further based on the deviation. The method according to [1], further comprising:

[10] The method described in [9], wherein the deviation includes a proportional gain deviation, an integral gain deviation, a differential gain deviation, or a combination thereof.

[11] The method according to [1], wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, a measured value of the process variables, an alert related to the thermal system, or a combination thereof.

[12] The method according to [1], wherein the corrective action includes controlling the power to the heater system based on the identified state of the heater system.

[13] The corrective action includes broadcasting an alert based on the identified state of the heater system, the alert indicating a material accumulation in a conduit communicably coupled to the process control system, a nominal thermal deviation of a resistive heating element communicably coupled to the process control system, or a combination thereof, according to the method in [1].

[14] The method according to [1], wherein the external heater control input is an output generated by an external device of the process control system.

[15] The method according to [1], wherein the internal process control input comprises pressure data, mass flow data, vibration data, strain data, temperature data, or a combination thereof.

[16] A process control system for controlling a heater system, configured to generate output control of the heater system based on intermediate data generated by the process control system, Processor and A non-temporary computer-readable medium having instructions executable by the aforementioned processor and The instruction is provided, Monitoring the aforementioned intermediate data, The intermediate data is associated with correlation data including internal process control inputs, external heater control inputs, output control, or combinations thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, Identifying the state of the heater system based on the aforementioned model, Selective corrective action is taken based on the identified state of the heater system. A process control system equipped with the following features.

[17] The process control system according to

[16] , wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, controller gain of the process control system, or a combination thereof.

[18] The process control system described in

[16] includes a cascade control system having a primary controller and a secondary controller, wherein the intermediate data includes loop data of the cascade control system.

[19] The model is configured to predict the state of the heater system based on the intermediate data and the correlation data. The aforementioned instruction further states: The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, The determination of the deviation between the nominal model and the model, wherein the identified state of the heater system is further based on the deviation. The process control system according to

[16] , comprising:

[20] The process control system according to

[16] , wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, a measured value of the process variables, an alert related to the thermal system, or a combination thereof.

[21] A method for controlling a thermal system in an industrial process, wherein the thermal system includes a heater system and a process control system configured to generate output control of the heater system based on intermediate data generated by a process control system, The intermediate data is associated with correlation data, wherein the correlation data includes internal process control inputs, external heater control inputs, output control, or a combination thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, Identifying the state of the heater system based on the comparison between the nominal model and the model, Selective corrective action is taken based on the identified state of the heater system. A method for providing this.

[22] The method according to

[21] , wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, controller gain of the process control system, or a combination thereof.

[23] The process control system includes a cascade control system having a primary controller and a secondary controller, and the intermediate data includes loop data of the cascade control system, according to the method in

[21] .

[24] The identified state of the heater system is further based on a deviation between the nominal model and the model, wherein the deviation includes a proportional gain deviation, an integral gain deviation, a differential gain deviation, or a combination thereof, according to the method in

[21] .

[25] The method according to

[21] , wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, a measured value of the process variables, an alert related to the thermal system, or a combination thereof.

[26] The method according to

[21] , wherein the external heater control input is an output generated by an external device of the process control system.

[27] The method according to

[21] , wherein the internal process control input comprises pressure data, mass flow data, vibration data, strain data, temperature data, or a combination thereof.

Claims

1. A method for controlling a thermal system in an industrial process, wherein the thermal system includes a heater system and a process control system configured to generate output control of the heater system based on intermediate data generated by a process control system, Monitoring the aforementioned intermediate data, The intermediate data is associated with correlation data, wherein the correlation data includes internal process control inputs, external heater control inputs, output control, or a combination thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, Identifying the state of the heater system based on the aforementioned model, Selective corrective action is taken based on the identified state of the heater system. A method for providing this.

2. The method according to claim 1, wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, or a combination thereof.

3. The method according to claim 2, wherein the output control is based on the sum of the proportional gain data, the integral gain data, and the differential gain data.

4. The method according to claim 1, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and the intermediate data includes loop data of the cascade control system.

5. The method according to claim 4, wherein the output control is based on the sum of the proportional gain data of the secondary controller, the integral gain data of the secondary controller, and the differential gain data of the secondary controller.

6. The method according to claim 1, wherein the intermediate data includes the controller gain of the process control system.

7. The method according to claim 1, wherein the model is a mathematical model, a machine learning model, or a combination thereof.

8. The method according to claim 7, wherein the machine learning model is a supervised learning model configured to predict the state of the heater system based on the intermediate data and the correlation data.

9. The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, The determination of the deviation between the nominal model and the model, wherein the identified state of the heater system is further based on the deviation. The method according to claim 1, further comprising:

10. The method according to claim 9, wherein the deviation includes a proportional gain deviation, an integral gain deviation, a differential gain deviation, or a combination thereof.

11. The method according to claim 1, wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, measured values ​​of the process variables, alerts related to the thermal system, or a combination thereof.

12. The method according to claim 1, wherein the corrective action includes controlling the power to the heater system based on the identified state of the heater system.

13. The method according to claim 1, wherein the corrective action includes broadcasting an alert based on the identified state of the heater system, the alert indicating a material accumulation in a conduit communicably coupled to the process control system, a nominal thermal deviation of a resistive heating element communicably coupled to the process control system, or a combination thereof.

14. The method according to claim 1, wherein the external heater control input is an output generated by an external device of the process control system.

15. The method according to claim 1, wherein the internal process control input comprises pressure data, mass flow rate data, vibration data, strain data, temperature data, or a combination thereof.

16. A process control system for controlling a heater system, configured to generate output control of the heater system based on intermediate data generated by the process control system, Processor and A non-temporary computer-readable medium having instructions executable by the aforementioned processor and The instruction is provided, Monitoring the aforementioned intermediate data, The intermediate data is associated with correlation data including internal process control inputs, external heater control inputs, output control, or combinations thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, Identifying the state of the heater system based on the aforementioned model, Selective corrective action is taken based on the identified state of the heater system. A process control system equipped with the following features.

17. The process control system according to claim 16, wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, controller gain of the process control system, or a combination thereof.

18. The process control system according to claim 16, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and the intermediate data includes loop data of the cascade control system.

19. The model is configured to predict the state of the heater system based on the intermediate data and the correlation data. The aforementioned instruction further states: The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, The determination of the deviation between the nominal model and the model, wherein the identified state of the heater system is further based on the deviation. The process control system according to claim 16, comprising:

20. The process control system according to claim 16, wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, measured values ​​of the process variables, alerts related to the thermal system, or a combination thereof, and the thermal system includes a process control system configured to generate output control of the heater system and the heater system.

21. A method for controlling a thermal system in an industrial process, wherein the thermal system includes a heater system and a process control system configured to generate output control of the heater system based on intermediate data generated by a process control system, The intermediate data is associated with correlation data, wherein the correlation data includes internal process control inputs, external heater control inputs, output control, or a combination thereof. To generate a model that defines the relationship between the aforementioned intermediate data and the aforementioned correlation data, The process involves comparing the aforementioned model with a nominal model that defines the nominal relationship between the intermediate data and the correlation data, Identifying the state of the heater system based on the comparison between the nominal model and the model, Selective corrective action is taken based on the identified state of the heater system. A method for providing this.

22. The method according to claim 21, wherein the intermediate data includes proportional gain data, integral gain data, differential gain data, controller gain of the process control system, or a combination thereof.

23. The method according to claim 21, wherein the process control system includes a cascade control system having a primary controller and a secondary controller, and the intermediate data includes loop data of the cascade control system.

24. The method according to claim 21, wherein the identified state of the heater system is further based on a deviation between the nominal model and the model, the deviation including a proportional gain deviation, an integral gain deviation, a differential gain deviation, or a combination thereof.

25. The method according to claim 21, wherein the internal process control input comprises a desired set value for the performance characteristics of the heater system, a set value for controlling the heater system, process variables, a measured value of the process variables, an alert related to the thermal system, or a combination thereof.

26. The method according to claim 21, wherein the external heater control input is an output generated by an external device of the process control system.

27. The method according to claim 21, wherein the internal process control input comprises pressure data, mass flow rate data, vibration data, strain data, temperature data, or a combination thereof.

Images