Innovation

AI Supervisory Control System

Mitsubishi Electric's application of breakthrough Artificial Intelligence technology to elevator control has resulted in improved operational efficiency and new functions that can be configured to suit a variety of building types. Two basic systems are available, including the ∑AI-22C System and ∑AI-2200C System which are designed for small or medium-sized buildings with three to four cars in the elevator group, and the ∑AI-2200C System for larger buildings with three to eight cars in the elevator group. The ∑AI-2200C System is especially suitable for buildings with dynamic traffic conditions throughout the day and peak carrying times.

Cooperative Optimization Assignment
Energy-saving Operation – Allocation Control
Dynamic Rule-set Optimizer
Immediate Prediction Indication
Destination Oriented Allocation System (DOAS)

Cooperative Optimization Assignment

Forecasting a near-future hall call to reduce long waits

When a hall call is registered, the algorithm predicts a near-future call that could require long waits. Through evaluation of the registered hall call and the forecasted call, the best car is assigned. All cars work cooperatively for optimum operation.

Energy-saving Operation — Allocation Control

Maximizing operational efficiency and minimizing energy consumption

This system selects the elevator in a group that best balances operational efficiency and energy consumption. Priority is given to operational efficiency during peak hours and energy efficiency during non-peak hours. Car allocation that maximizes operational efficiency does not necessarily translate to energy efficiency. A car uses energy efficiently when it travels down with a heavy load, or up with a light load. Accordingly, if multiple cars have the same traveling distance, this system chooses the car that requires the least energy. Through a maximum 10% reduction in energy consumption compared to our conventional system, this system allows building owners to cut energy costs without sacrificing passenger convenience.

Dynamic Rule-set Optimizer

Selects optimum car allocation through “rule-set” simulation

The neural network technology has enabled the system to continually and accurately predict the passengertraffic within intervals of several minutes. A high-speed reduced instruction set computer (RISC) runsreal-time simulations using multiple rule-sets and the predicted passenger traffic to select the rule-set whichoptimizes transport efficiency.

Simulation example and performance results of each rule-set

The diagram below shows an example during a morning up peak time. An ideal rule-set is selected every few minutes according to the predicted traffic conditions.

Performance results of each rule-set (average waiting time)

Immediate Prediction Indication

Easing stress of waiting at Elevator lobby

When a passenger has registered a hall call, the designated car is selected and the corresponding hall lantern immediately lights up. To inform the passenger of the car arrival, the hall lantern flashes on and off for three seconds before the arrival.

Destination Oriented Allocation System (DOAS)

Passengers register their destination floor using a hall operating panel before entering the elevator, eliminating the need to press the button inside the car. Furthermore, dispersing passengers by destination prevents congestion in cars and minimizes waiting and travel time.

Enhance Convenience

DOAS Integrated with Security Gate

Extended feature for more security

The destination floor can be registered automatically after passing a card over a card reader at the security gate entrance. DOAS integrated with security gates provides a seamless journey and enhances security in the building.