The invention relates to a method for controlling a passenger transport system, which transport system comprises at least two passenger conveyors, as e.g. escalators or elevators, which transport system comprises a control for the passenger conveyors and for controlling passenger flow in the transport system. The control is connected to a passenger flow determination device for establishing a passenger flow reference value of the actual passenger flow to be expected in the passenger transport system, and which control further comprises a passenger guide system for controlling passenger flow in the transport system, which passenger guide system uses a cost function considering a set of system control parameters as passenger riding time, energy consumption, passenger waiting time, passenger transport capacity, maintenance demand, etc. The control uses a transport model simulating the function of the hardware components of the transport system under consideration of correlated system operating parameters as e.g. number of active passenger conveyors, passenger conveyor speed, still-stand times, door opening times etc. in connection with passenger flow,

whereby the passenger flow reference value is input to the transport model and in an optimization process the system operating parameters are optimized under use of the transport model to meet the passenger flow reference value under consideration of at least one significant system control parameter from said set of system control parameters to achieve a best set of system operating parameters. The best set of system operating parameters is applied to the control of the passenger transport system.

Provided are an elevator charging system, a management server, a moving body, a moving body server, a charging method, and a storage medium storing program that make it possible to charge usage fees reflecting the demand of moving bodies. In a charging system (1), cars (5) transport moving bodies (11) between a plurality of floors. A communication unit (7a) receives usage requests each corresponding to one of the moving bodies (11). Each of the requests includes information about a call requesting assignment to one of the cars (5), and information about a desired price for a usage fee. An assignment unit (8) assigns each call to one of the cars (5) while prioritizing calls in requests having higher priority, based on information including the desired prices. A storage unit (9a) stores therein the fees charged for the requests of which the calls have been assigned.

Apparatuses, methods and computer programs for elevator call allocation with adaptive multi-objective optimization are disclosed. At least some of the disclosed embodiments may allow adaptively and smoothly changing an objective function according to passenger traffic. This in turn may allow minimizing waiting times in all traffic situations compared to using a fixed objective function. Furthermore, at least some of the disclosed embodiments may allow adaptively and smoothly changing the objective function according to the traffic while taking user preferences into consideration via a single transit time target parameter.

The present disclosure includes a data generation unit to generate a normalized finite element as training data, a strain computation unit to compute reference strain values based on the generated training data, a deep learning network including a plurality of layers each having a preset weight and to generate a matching matrix, in which the reference strain values and displacements set for the training data match each other based on arbitrary attribute information and geometric information as position information related to variable points, and a training control unit to train the deep learning network based on a cost function by which differences between strain values computed according to the matching matrix and the reference strain values are equal to or smaller than a threshold value.