Method for operating a fan system and fan system having a backward curved centrifugal fan
Inventors
Eberle, Walter • Rau, Alexander • Wystup, Ralph • Nase, Rainer • Humm, Markus
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11746794-B2
Publication Date
2023-09-05
Expiration Date
Abstract
A method for operating a fan system as well as such a fan system. The fan system has a control device having an artificial neural network. The control device controls an electric motor of a backward curved centrifugal fan. The centrifugal fan creates a gas flow that is characterized by an actual flow value, particularly the actual value of a volume flow rate. The actual flow value is not detected by a sensor means, but determined by means of the artificial neural network depending from input variables and based thereon, the electric motor is open loop or closed loop controlled by means of the control device. The motor current and the motor voltage as well as their time-dependent behavior that can be the time derivative (e.g. gradient of first order) or that can be at least one preceding value at a preceding point in time, are provided to an input layer of the artificial neural network. It is particularly advantageous, if the artificial neural network determines an actual value of an output pressure that is fed back internally or externally forming an input variable for the input layer.
Core Innovation
A fan system with a control device and a backward curved centrifugal fan creates a gas flow characterized by at least one actual flow rate value (pa(kT), Q(kT); pa(takt), Q(takt)). The method determines an operation parameter (U(kT); U(takt)) forming a correcting variable and determines at least one operation parameter (I(kT); I(takt)) forming at least one actual system variable that characterizes motor operation conditions of the centrifugal fan in a continuous or time-discrete manner.
The correcting variable (U(kT); U(takt)) and the at least one actual system variable (I(kT); I(takt)) are provided to an artificial neural network of the control device. The artificial neural network determines the at least one actual flow rate value (Q(kT); Q(takt)) based on the correcting variable (U(kT); U(takt)), the actual system variable (I(kT); I(takt)), and a time-dependent change (I((k-1)T); dI) of the actual system variable (I((k-1)T); dI).
The method checks whether the correcting variable (U(kT); U(takt)) has to be modified based on the determined at least one actual flow rate value (Q(kT), Q(takt)), and the actual flow value (pa(kT), pa(takt)) determined by the artificial neural network is fed back to an input layer of the artificial neural network. In further implementations, the artificial neural network input layer receives an actual value of the at least one actual system variable for an actual point in time together with the time-dependent change of the actual system variable, and a time-dependent change of the correcting variable (dU) for the actual point in time is additionally submitted.
Claims Coverage
The independent claims are clm-00001, clm-00005, and clm-00020. Across these independent claims, the inventive features comprise using an artificial neural network to determine an actual gas flow rate value from a motor correcting variable and motor-related system variables, including time-dependent changes and feedback into the network input layer.
Determining flow rate by ANN from correcting variable and actual system variable with time-dependent change
A method for operating a fan system where a correcting variable (U(kT); U(takt)) and at least one actual system variable (I(kT); I(takt)) are provided to an artificial neural network, and the artificial neural network determines the at least one actual flow rate value (Q(kT); Q(takt)) based on the correcting variable and the actual system variable and a time-dependent change (I((k-1)T); dI) of the actual system variable.
Checking and modifying correcting variable based on ANN-determined actual flow rate value
Checking whether the correcting variable (U(kT); U(takt)) has to be modified based on the determined at least one actual flow rate value (Q(kT), Q(takt)).
Feeding ANN-determined actual flow value back to the input layer
Feeding an actual flow value (pa(kT), pa(takt)) of the at least one actual flow rate value determined by the artificial neural network back to an input layer of the artificial neural network.
ANN input layer includes preceding system variable value
An input layer is used to which an actual value of the at least one actual system variable (I(kT); I(takt)) and of the correcting variable (U(kT); U(takt)) for an actual point in time (kT) and a preceding value of the actual system variable (I((k-1)T)) to a preceding point in time ((k-1)T) is submitted.
ANN input layer includes time-dependent changes including dU of the correcting variable
The artificial neural network input layer receives an actual value of the at least one actual system variable for an actual point in time as well as a time-dependent change of the actual system variable (dI) for the actual point in time, and additionally a time-dependent change of the correcting variable (dU) for the actual point in time is submitted.
The claim coverage centers on an artificial neural network that calculates the actual gas flow rate value for operating a backward curved centrifugal fan using a correcting variable and at least one actual motor-related system variable, explicitly incorporating time-dependent changes. The independent claims also require deciding whether to modify the correcting variable based on the ANN output, with at least one implementation feeding the ANN-determined actual flow value back into the network input layer, and additional independent coverage specifying ANN input contents including preceding values and time-dependent changes of the correcting variable (dU).
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?