The proposed multi-layer perceptron ANN, based on a back propagation training algorithm, is able to take as inputs: loads, data concerning the type of day (e.g. weekday/holiday), time of the day and weather data.
Vegetation had a limited effect, input load being transported mostly outside the growing season.
The efficiency of buffer zone to mitigate phosphate losses varied depending on the input load.
Simulation results show that the control effects can tackle the input load disturbances and the delay perturbation more effectively.
The load duration distribution (LDD) method is used to obtain the short-term stress cycles from the input load time series of global response analysis.
Aimed at attaining the targeted river TN concentration (2 mg L−1), required input load reductions for PS, DS and upstream inflow were estimated.
An important aspect of the proposed approach is the ability to join directly the pdf of the input load with that of the response.
We devised a vibration triggering system consisting of a fixture and an electromagnetic shaker to generate an input load reproducing the excitation signal from the road to the instrument panel without distortion.
This mapping transforms a high-dimensional random parameter vector, which may represent the stochastic input load as well as any uncertain structural parameters, into a random variable with unknown distribution, which represents the uncertain structural response.
Since the robust compliance can be formulated as the scalar product of the uncertain input load and output displacement vectors, the idea of "aggregation" used in the field of control is introduced to assess the value of the robust compliance.
In addition, its rated input load capacitance is high, similar to that observed in CSAs.
