摘要:
In one example embodiment, a gas turbine system includes a gas turbine, a compressor bleed valve, various sensors, and a valve health assessment system. The compressor bleed valve bleeds a portion of air received by the compressor during certain operating modes. The valve health assessment system includes a processor that uses a neural network model to generate a first failure mode predictor of the compressor bleed valve by processing operational data provided by the various sensors. The processor also generates a second failure mode predictor of the compressor bleed valve by using empirical data and a valve transfer function. The processor further generates a third failure mode predictor of the compressor bleed valve by using predictive data and a prediction model. The processor then applies a holistic procedure to the three failure mode predictors to derive a probability of occurrence of a failure in the compressor bleed valve.
摘要:
An obtaining step for obtaining a measurement of the monitored parameter as measured by a sensor and corresponding to an operating point of the engine, the operating point being defined by at least one regulation parameter of the engine; an estimation step for estimating a value of the monitored parameter for this operating point on the basis of a regulated value or a filtered setpoint value of the at least one regulation parameter of the engine defining the operating point; a comparison step for comparing an error between the measurement of the monitored parameter and its estimate relative to at least one threshold determined on the basis of an uncertainty on the error evaluated for the operating point; and a notification step for sending a notification in the event of the at least one threshold being crossed.
摘要:
A power generation system is disclosed. In one embodiment, the power generation system includes a fuel source to provide fuel, a turbogenerator, coupled to the fuel source, to generate AC power, and a power controller electrically coupled to the turbogenerator. The power controller includes a first power converter to convert the AC power to DC power on a DC bus, and a second power converter to convert the DC power on the DC bus to an output power to supply a load. The power controller to regulate the fuel to the turbogenerator, independent of a DC voltage on the DC bus. A capacitor, such as an electrochemical capacitor or a hybrid capacitor, is coupled to the DC bus to source instantaneous power to and sink instantaneous power from the DC bus, due to load changes, to stabilize the DC voltage on the DC bus.
摘要:
Systems and methods that include and/or leverage a neural network to approximate the steady-state performance of a turbine engine are provided. In one exemplary aspect, the neural network is trained to model a physics-based, steady-state cycle deck. When properly trained, novel input data can be input into the neural network, and as an output of the network, one or more performance indicators indicative of the steady-state performance of the turbine engine can be received. In another aspect, systems and methods for approximating the steady-state performance of a “virtual” or target turbine engine based at least in part on a reference neural network configured to approximate the steady-state performance of a “fielded” or reference turbine engine are provided.
摘要:
Systems and methods for adjusting blade tip clearance targets and utilizing the adjusted targets to optimize the clearances between the blade tips and surrounding shrouds of a turbine engine are provided. In one exemplary aspect, one or more engine controllers utilize a machine-learned model to customize blade tip clearance targets based on the way an engine has been uniquely operated in the past for a particular flight mission. Present flight data associated with a present flight of a given flight mission is obtained. A model blade tip clearance target is adjusted based at least in part on the machine-learned model and the present flight data. The machine-learned model is trained at least in part on past flight data indicative of the manner in which the turbine engine has been operated for one or more past flights of the flight mission. An adjusted blade tip clearance target is then generated.
摘要:
A method for a computer-aided control of a technical system is provided. The method involves use of a cooperative learning method and artificial neural networks. In this context, feed-forward networks are linked to one another such that the architecture as a whole meets an optimality criterion. The network approximates the rewards observed to the expected rewards as an appraiser. In this way, exclusively observations which have actually been made are used in optimum fashion to determine a quality function. In the network, the optimum action in respect of the quality function is modeled by a neural network, the neural network supplying the optimum action selection rule for the given control problem. The method is specifically used to control a gas turbine.
摘要:
A power generation system is disclosed. In one embodiment, the power generation system includes a fuel source to provide fuel, a turbogenerator, coupled to the fuel source, to generate AC power, and a power controller electrically coupled to the turbogenerator. The power controller includes a first power converter to convert the AC power to DC power on a DC bus, and a second power converter to convert the DC power on the DC bus to an output power to supply a load. The power controller to regulate the fuel to the turbogenerator, independent of a DC voltage on the DC bus. A capacitor, such as an electrochemical capacitor or a hybrid capacitor, is coupled to the DC bus to source instantaneous power to and sink instantaneous power from the DC bus, due to load changes, to stabilize the DC voltage on the DC bus.
摘要:
A method of characterizing a turbine engine, the method comprising: steps of using measurements from an accelerometer monitoring a particular turbine engine while it is starting to detect the energy released by any contact during said starting between the rotor and the stator of the turbine engine, and of associating any such detection of contact with thermodynamic data measured on the particular turbine engine; and then a recognition training step, based on the associations, to enable a thermal context of the turbine engine to be used to recognize the presence of a rotor thermal unbalance to be taken into account in order to avoid contacts between the rotor and the stator on starting.
摘要:
A gas turbine engine optimization control device estimates a specific fuel consumption using a given control parameter of a variable mechanism, determines a change between a specific fuel consumption estimation value by the control parameter of the variable mechanism in a previous operation period and a specific fuel consumption estimation value by the control parameter of the variable mechanism in this operation period, determines a new control parameter of the variable mechanism with which the specific fuel consumption estimation value approaches a minimum, adds the new control parameter of the variable mechanism to a preset control parameter initial value, and sets the addition value to be a control parameter command value of the variable mechanism in a next operation period.
摘要:
A method for modeling the performance of a gas turbine engine is provided. The method includes the steps of: 1) providing a processor; 2) inputting flight condition parameter data and engine output parameter data into a gas turbine engine model operating on the processor, which model includes a physics-based engine model that uses the flight condition parameter data to produce estimated engine output parameter data, and determines residuals from the engine output parameter data and the estimated engine output parameter data; 3) partitioning the flight condition parameter data and residuals into training data and testing data; 4) performing a correlation reduction on the training data, which analysis produces correlation adjusted training data; 5) performing an orientation reduction on the correlation adjusted training data, which reduction produces orientation adjusted training data; 6) reviewing the orientation adjusted training data relative to at least one predetermined criteria, and iteratively repeating the steps of performing a correlation reduction and an orientation reduction using the orientation adjusted training data if the criteria is not satisfied, and if the criteria is satisfied outputting the orientation adjusted training data; 7) producing estimated corrections to the orientation adjusted training data using one or more neural networks; 8) evaluating the neural adjusted data using the partitioned testing data; and 9) modeling the performance of the gas turbine using the estimated corrections to the orientation adjusted training data.