# US 2026/0073232 A1 · Mass analyzer calibration via reinforcement learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0073232 A1 - Document ID: US20260073232A1 - Status: Published application - Kind: A1 - Application number: 18/971,893 - Filed: 2024-12-06 - Published: 2026-03-12 - Earliest claimed: 2024-09-09 - Assignees: Thermo Fisher Scientific (Bremen) GmbH - Applicants: Thermo Fisher Scientific (Bremen) GmbH - Inventors: Amelia Corinne Peterson - Web page: https://patentgrep.com/patent/US20260073232A1 ## CPC - G06N 3/092: Reinforcement learning - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 3/08: Learning methods - H01J 49/0009: {Calibration of the apparatus} - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H) ## Abstract Systems/techniques are provided for facilitating mass analyzer calibration via reinforcement learning. In various embodiments, a system can predict, via execution of one or more reinforcement learning neural networks on present-time state data of a mass analyzer of a scientific instrument, what adjustments to one or more operational parameters of the mass analyzer would cause the mass analyzer to approach a calibrated state, wherein the one or more operational parameters include an electrode voltage of the mass analyzer or a timing control of the mass analyzer. In various aspects, the system can modify the one or more operational parameters based on the adjustments, thereby causing the mass analyzer to approach the calibrated state. ## Claims ### Claim 1 A system, comprising: a processor that executes computer-executable components stored in a non-transitory computer-readable memory, wherein the computer-executable components comprise: a calibration component that predicts, via execution of one or more reinforcement learning neural networks on present-time state data of a mass analyzer of a scientific instrument, what adjustments to one or more operational parameters of the mass analyzer would cause the mass analyzer to approach a calibrated state, wherein the one or more operational parameters include an electrode voltage of the mass analyzer or a timing control of the mass analyzer; and an execution component that modifies the one or more operational parameters based on the adjustments, thereby causing the mass analyzer to approach the calibrated state. ### Claim 2 (depends on 1) The system of claim 1, wherein the computer-executable components comprise: a training component that trains the one or more reinforcement learning neural networks. ### Claim 3 (depends on 2) The system of claim 2, wherein the one or more reinforcement learning neural networks comprise: a parameter adjustment neural network that: receives, as input, state data of the mass analyzer; and produces, as output, parameter adjustments based on such inputted state data; a target parameter adjustment neural network whose internal weights lag those of the parameter adjustment neural network; a parameter valuation neural network that: receives, as input, the state data and the parameter adjustments; and produces, as output, a scalar that represents a valuation of the parameter adjustments; and a target parameter valuation neural network whose internal weights lag those of the parameter valuation neural network. ### Claim 4 (depends on 2) The system of claim 2, wherein the training component utilizes a prioritized experience replay buffer having pre-populated tuples, wherein each pre-populated tuple comprises a respective state, one or more respective parameter adjustments, a respective reward, and a respective resultant state, and wherein the pre-populated tuples are derived from one or more prior calibrations of the mass analyzer. ### Claim 5 (depends on 4) The system of claim 4, wherein the one or more prior calibrations collectively form a state-action trajectory, and wherein the pre-populated tuples are computed from endpoints of one or more sliding windows that are run along the state-action trajectory. ### Claim 6 (depends on 5) The system of claim 5, wherein the training component utilizes the pre-populated tuples only when valuations of the pre-populated tuples are higher than corresponding valuations of tuples that are derived from parameter adjustments predicted by the one or more reinforcement learning neural networks. ### Claim 7 (depends on 2) The system of claim 2, wherein the present-time state data comprises: one or more first scalars associated with an isotope ratio fidelity of the mass analyzer; one or more second scalars associated with an extent of mass error dispersion due to space charge of the mass analyzer; one or more third scalars associated with a transmission of the mass analyzer; and one or more fourth scalars associated with a resilience to coalescence due to space charge of the mass analyzer. ### Claim 8 (depends on 7) The system of claim 7, wherein: the training component determines: the one or more first scalars via a first mapping function executed on a partial isotope ratio fidelity of the mass analyzer; the one or more second scalars via a second mapping function executed on a partial extent of mass error dispersion due to space charge of the mass analyzer; the one or more third scalars via a third mapping function executed on a partial transmission of the mass analyzer; and the one or more fourth scalars via a fourth mapping function executed on a partial resilience to coalescence due to space charge of the mass analyzer. ### Claim 9 (depends on 1) The system of claim 1, wherein the mass analyzer is an orbital trapping mass analyzer. ### Claim 10 A computer-implemented method, comprising: predicting, by a device operatively coupled to a processor and via execution of one or more reinforcement learning neural networks on present-time state data of a mass analyzer of a scientific instrument, what adjustments to one or more operational parameters of the mass analyzer would cause the mass analyzer to approach a calibrated state, wherein the one or more operational parameters include an electrode voltage of the mass analyzer or a timing control of the mass analyzer; and modifying, by the device, the one or more operational parameters based on the adjustments, thereby causing the mass analyzer to approach the calibrated state. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, further comprising: training, by the device, the one or more reinforcement learning neural networks. ### Claim 12 (depends on 11) The computer-implemented method of claim 11, wherein the one or more reinforcement learning neural networks comprise: a parameter adjustment neural network that: receives, as input, state data of the mass analyzer; and produces, as output, parameter adjustments based on such inputted state data; a target parameter adjustment neural network whose internal weights lag those of the parameter adjustment neural network; a parameter valuation neural network that: receives, as input, the state data and the parameter adjustments; and produces, as output, a scalar that represents a valuation of the parameter adjustments; and a target parameter valuation neural network whose internal weights lag those of the parameter valuation neural network. ### Claim 13 (depends on 11) The computer-implemented method of claim 11, wherein the training utilizes a prioritized experience replay buffer having pre-populated tuples, wherein each pre-populated tuple comprises a respective state, one or more respective parameter adjustments, a respective reward, and a respective resultant state, and wherein the pre-populated tuples are derived from one or more prior calibrations of the mass analyzer. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, wherein the one or more prior calibrations collectively form a state-action trajectory, and wherein the pre-populated tuples are computed from endpoints of one or more sliding windows that are run along the state-action trajectory. ### Claim 15 (depends on 14) The computer-implemented method of claim 14, wherein the training utilizes the pre-populated tuples only when valuations of the pre-populated tuples are higher than corresponding valuations of tuples that are derived from parameter adjustments predicted by the one or more reinforcement learning neural networks. ### Claim 16 (depends on 11) The computer-implemented method of claim 11, wherein the present-time state data comprises: one or more first scalars associated with an isotope ratio fidelity of the mass analyzer; one or more second scalars associated with an extent of mass error dispersion due to space charge of the mass analyzer; one or more third scalars associated with a transmission of the mass analyzer; and one or more fourth scalars associated with a resilience to coalescence due to space charge of the mass analyzer. ### Claim 17 (depends on 16) The computer-implemented method of claim 16, wherein: the device determines: the one or more first scalars via a first mapping function executed on a partial isotope ratio fidelity of the mass analyzer; the one or more second scalars via a second mapping function executed on a partial extent of mass error dispersion due to space charge of the mass analyzer; the one or more third scalars via a third mapping function executed on a partial transmission of the mass analyzer; and the one or more fourth scalars via a fourth mapping function executed on a partial resilience to coalescence due to space charge of the mass analyzer. ### Claim 18 (depends on 10) The computer-implemented method of claim 10, wherein the mass analyzer is an orbital trapping mass analyzer. ### Claim 19 A computer program product for facilitating mass analyzer calibration via reinforcement learning, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to: access present-time state data of a mass analyzer of a mass spectrometer; predict, via execution of one or more reinforcement learning neural networks on the present-time state data, what adjustments to one or more electrode voltages of the mass analyzer would cause the mass analyzer to get closer to a calibrated state; and increase or decrease the one or more electrode voltages according to the predicted adjustments, thereby causing the mass analyzer to be calibrated. ### Claim 20 (depends on 19) The computer program product of claim 19, wherein the program instructions are executable to cause the processor to: train the one or more reinforcement learning neural networks according to a deep deterministic policy gradient technique that includes a prioritized experience replay buffer which is pre-populated with data derived from prior calibrations of the mass analyzer.