Abstract: The invention relates to a method for operating a process system, in which method one or more actuators in the process system are set by means of one or more manipulated variable values specified by means of a control process, whereby one or more operating parameters of the process system are influenced. The control process is a self-optimizing control process which comprises the use of model-based deep reinforcement learning and the consideration of a cost function. One or more components of the process system are represented in a model by means of neural network, which model is used in the model-based deep reinforcement learning. The present invention also relates to a corresponding process system and to a method for converting a process system.

Abstract: The process and the apparatus serve for the low-temperature fractionation of air in a distillation column system, which has at least one separating column. Feed air is compressed in a main air compressor. Compressed feed air is cooled in a main heat exchanger. Cooled feed air is introduced into the distillation column system. At least one product stream is drawn off from the distillation column system, heated in the main heat exchanger and drawn off as a gaseous end product. At least one process parameter is set by a basic controller. The control of the process parameter is set by a combination of an ALC control and an MPC controller. This involves the ALC control outputting a first target value to the MPC controller.

Abstract: The process and the apparatus serve for the low-temperature fractionation of air in a distillation column system, which has at least one separating column. Feed air is compressed in a main air compressor. Compressed feed air is cooled in a main heat exchanger. Cooled feed air is introduced into the distillation column system. At least one product stream is drawn off from the distillation column system, heated in the main heat exchanger and drawn off as a gaseous end product. At least one process parameter is set by a basic controller. The control of the process parameter is set by a combination of an ALC control and an MPC controller. This involves the ALC control outputting a first target value to the MPC controller. The MPC controller calculates from the first target value a setpoint value or a change to a setpoint value for a primary setpoint value output by the ALC control.

Abstract: The process and the apparatus serve for separating a gas mixture in a separation plant. A feed gas (18) is introduced into a compressor system (6, 16) and then into the separation plant. In the event of loss or partial loss of the compressor system (6, 16) of the first feed gas compressor (6), a first auxiliary stream (91, 92) which has approximately the composition of the first product stream or approximately the composition of the feed gas is compressed (78, 89) to at least approximately the first pressure and is recirculated to the separation plant.

Abstract: The process and the apparatus serve for separating a gas mixture in a separation plant. A feed gas (18) is introduced into a compressor system (6, 16) and then into the separation plant. In the event of loss or partial loss of the compressor system (6, 16) of the first feed gas compressor (6), a first auxiliary stream (91, 92) which has approximately the composition of the first product stream or approximately the composition of the feed gas is compressed (78, 89) to at least approximately the first pressure and is recirculated to the separation plant.