# US 2025/0147474 A1 · Self Learning Control System and Method for Optimizing a Consumable Input Variable > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0147474 A1 - Document ID: US20250147474A1 - Status: Published application - Kind: A1 - Application number: 19/018,570 - Filed: 2025-01-13 - Published: 2025-05-08 - Earliest claimed: 2012-12-12 - Assignees: S.A. Armstrong Limited - Applicants: S.A. Armstrong Limited - Inventors: Marcelo Javier Acosta Gonzalez - Web page: https://patentgrep.com/patent/US20250147474A1 ## CPC - G05B 13/04: involving the use of models or simulators - F04D 15/0209: {responsive to a condition of the working fluid (F04D15/029 takes precedence)} - F04D 15/029: {for pumps operating in parallel} - F04D 27/00: Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids - G05B 13/041: {in which a variable is automatically adjusted to optimise the performance} - G05B 15/02: electric - G05B 19/042: using digital processors (G05B19/05 takes precedence) - G05D 7/0617: {specially adapted for fluid materials} - G05D 7/0682: {using a plurality of flow sources} - Y02B 30/70: Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating - 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) - F04D: NON-POSITIVE-DISPLACEMENT PUMPS (engine fuel-injection pumps F02M; ion pumps H01J41/12; electrodynamic pumps H02K44/02) - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS ## Abstract A control system for an operable system such as a flow control system or temperature control system. The system operates in a control loop to regularly update a model with respect at least one optimizable input variable based on the detected variables. The model provides prediction of use of the input variables in all possible operation points or paths of the system variables which achieve an output setpoint. In some example embodiments, the control loop is performed during initial setup and subsequent operation of the one or more operable elements in the operable system. The control system is self-learning in that at least some of the initial and subsequent parameters of the system are determined automatically during runtime. ## Claims ### Claim 1 A system in relation to one or more operable elements which result in output variables, at least one of the operable elements including a respective controllable variable speed device, wherein there is more than one operation point or path of system variables that can provide a given output setpoint, wherein at least one system variable at an operation point or path correlates to another system variable at the operation point or path, the system comprising: memory; and one or more controllers configured to execute instructions stored in the memory to operate in a loop to: detect input variables, the input variables including non-controllable variables and system controllable variables, the non-controllable variables including output demand, the system controllable variables include at least one optimizable input variable, detect the system variables, and update a model with respect to the at least one optimizable input variable, comprising calculating the updated model using established relationships between variables, the detected input variables and the detected system variables, the updated model providing, based on the established relationships between variables, prediction of use of the input variables in possible operation points or paths of the system variables which achieve an output setpoint, wherein for iterations of the loop said updating of the model is based on operating, based on one or more of the detected input variables and the detected system variables, the one or more operable elements in accordance with the updated model to provide an optimal operation point or path of the at least one system variable and the another system variable which achieves the output setpoint and which optimizes the at least one optimizable input variable; and wherein the one or more operable elements operate according to the updated model. ### Claim 2 (depends on 1) The system as claimed in claim 1, wherein the loop is performed during initial setup and subsequent operation of the one or more operable elements. ### Claim 3 (depends on 1) The system as claimed in claim 1, wherein a non controllable input variable includes a variable system hydraulic resistance. ### Claim 4 (depends on 1) The system as claimed in claim 1, wherein the one or more controllers are further configured to perform a system review through specified operation of the output variables to calibrate the at least one optimizable input variable. ### Claim 5 (depends on 4) The system as claimed in claim 4, wherein during the system review the one or more controllers are further configured to cause a plurality of valves to be fully open by reducing a speed of at least one of the controllable variable speed devices and configured to determine a minimum system hydraulic resistance as one of the system variables. ### Claim 6 (depends on 1) The system as claimed in claim 1, wherein said updating includes updating the model for subsequent iterations of the loop. ### Claim 7 (depends on 1) The system as claimed in claim 1, wherein the optimizable input variable comprises a power efficiency variable of the one or more operable elements. ### Claim 8 (depends on 1) The system as claimed in claim 1, wherein said detecting of the output variables comprises self-detecting device properties of one of the operable elements and correlating to the output variables. ### Claim 9 (depends on 1) The system as claimed in claim 1, wherein said optimizable input variable is optimized by the operating by maintaining a specified average value of the at least one optimizable input variable. ### Claim 10 (depends on 1) The system as claimed in claim 1, wherein said optimizable input variable is optimized by the operating by maintaining a specified operation range of the at least one optimizable input variable. ### Claim 11 (depends on 1) The system as claimed in claim 1, wherein said optimizable input variable is optimized by the operating by maintaining a specified distribution, detected over a specified operation time, of the at least one optimizable input variable. ### Claim 12 (depends on 1) The system as claimed in claim 1, wherein at least one optimizable input variable is a consumable input variable. ### Claim 13 (depends on 1) The system as claimed in claim 1, wherein detecting of the system variables further includes correlating at least one of the system variables from at least one self-detected device property of the one or more operable elements. ### Claim 14 (depends on 1) The system as claimed in claim 1: wherein the system is in relation to a chilled circulating system including a refrigerant, wherein the one or more operable elements includes a compressor having the respective controllable variable speed device for controlling circulation of the refrigerant, resulting in the output variables including lift and flow for the refrigerant. ### Claim 15 (depends on 1) The system as claimed in claim 1: wherein the one or more operable elements includes a control pump having the respective controllable variable speed device for controlling circulation of a circulating medium, resulting in the output variables including pressure and flow for the circulating medium. ### Claim 16 (depends on 1) The system as claimed in claim 1, wherein the output variables include a temperature variable or a flow variable to achieve the output setpoint. ### Claim 17 (depends on 1) The system as claimed in claim 1, wherein the non-controllable variables include outdoor temperature. ### Claim 18 (depends on 1) The system as claimed in claim 1, wherein when the one or more controllers determine that the one of the operable elements is performing off of the model, the one or more controllers are configured to attempt to operate the one of the operable elements to operate onto the model which achieves the output setpoint. ### Claim 19 (depends on 1) The system as claimed in claim 1, wherein when the one or more controllers determine that the one of the operable elements is performing off of the model, the one or more controllers are configured to operate at least one of the other operable elements to compensate for the one of the operable elements. ### Claim 20 (depends on 19) The system as claimed in claim 19, wherein when the one or more controllers determine that the one of the operable elements is performing off of the model, the one or more controllers are configured to stop operation of the one of the operable elements. ### Claim 21 (depends on 1) The system as claimed in claim 1, wherein the at least one optimizable input variable includes power consumed or money. ### Claim 22 (depends on 1) The system as claimed in claim 1, wherein the one or more controllers are configured to determine that the one of the operable elements is performing off of the model due to damage or underperforming. ### Claim 23 (depends on 1) The system as claimed in claim 1, wherein the updating the model comprises learning by the one or more controllers. ### Claim 24 (depends on 1) The system as claimed in claim 1, further comprising the one or more operable elements. ### Claim 25 (depends on 24) The system as claimed in claim 24, wherein the one or more controllers control the one or more operable elements in the loop. ### Claim 26 (depends on 1) The system as claimed in claim 1, wherein the system is a temperature control system and/or a flow control system. ### Claim 27 (depends on 1) The system as claimed in claim 1, wherein the loop is performed during runtime operation of the one or more operable elements. ### Claim 28 (depends on 1) The system as claimed in claim 1, wherein the established relationships between variables include one or more affinity laws. ### Claim 29 (depends on 1) The system as claimed in claim 1, wherein the established relationships are determined from one or more performance curves. ### Claim 30 A method in relation to one or more operable elements which result in output variables, at least one of the operable elements including a respective controllable variable speed device, wherein there is more than one operation point or path of system variables that can provide a given output setpoint, wherein at least one system variable at an operation point or path correlates to another system variable at the operation point or path, the method comprising: performing a loop comprising: detecting input variables, the input variables including non-controllable variables and system controllable variables, the non-controllable variables including output demand, the system controllable variables include at least one optimizable input variable, detecting the system variables, and updating a model with respect to the at least one optimizable input variable, comprising calculating the updated model using established relationships between variables, the detected input variables and the detected system variables, the updated model providing, based on the established relationships between variables, prediction of use of the input variables in possible operation points or paths of the system variables which achieve an output setpoint, wherein for iterations of the loop said updating of the model is based on operating, based on one or more of the detected input variables and the detected system variables, the one or more operable elements in accordance with the updated model to provide an optimal operation point or path of the at least one system variable and the another system variable which achieves the output setpoint and which optimizes the at least one optimizable input variable; wherein the one or more operable elements operate according to the updated model. ### Claim 31 (depends on 30) The method as claimed in claim 30, wherein the method is performed by one or more controllers. ### Claim 32 A non-transitory computer readable medium comprising instructions which are executable by one or more controllers in relation to one or more operable elements which result in output variables, at least one of the operable elements including a respective controllable variable speed device, wherein there is more than one operation point or path of system variables that can provide a given output setpoint, wherein at least one system variable at an operation point or path correlates to another system variable at the operation point or path, the instructions comprising: instructions for operating in a loop to: detect input variables, the input variables including non-controllable variables and system controllable variables, the non-controllable variables including output demand, the system controllable variables include at least one optimizable input variable, detect the system variables, and update a model with respect to the at least one optimizable input variable, comprising calculating the updated model using established relationships between variables, the detected input variables and the detected system variables, the updated model providing, based on the established relationships between variables, prediction of use of the input variables in possible operation points or paths of the system variables which achieve an output setpoint, wherein for iterations of the loop said updating of the model is based on operating, based on one or more of the detected input variables and the detected system variables, the one or more operable elements in accordance with the updated model to provide an optimal operation point or path of the at least one system variable and the another system variable which achieves the output setpoint and which optimizes the at least one optimizable input variable; wherein the one or more operable elements operate according to the updated model.