Traffic means controlling apparatus

• US 5,544,059 A
• Filed: 07/19/1994
• Issued: 08/06/1996
• Est. Priority Date: 07/27/1993
• Status: Expired due to Fees

• Current Assignee: Mitsubishi Denki Kabushiki Kaisha (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Denki Kabushiki Kaisha (Mitsubishi Electric Corporation)
• Inventors: Goto, Yukio, Hikita, Shiro, Iwata, Masafumi, Asuka, Masashi, Komaya, Kiyotoshi
• Primary Examiner(s): NOT, DEFINED
• Assistant Examiner(s): Walder, Jr., Stephen J.
• Application Number:
  US08/277,502
• Time in Patent Office: 749 Days
• Field of Search: 364/436, 187/391, 187/392, 187/393, 187/395
• US Class Current: 701/117
• CPC Class Codes: B66B 1/2408 where the allocation of a call to an elevator car is of importance, i.e. by means of a supervisory or group controller
• CPC Class Codes: B66B 1/2458 For elevator systems with multiple shafts and a single car per shaft
• CPC Class Codes: B66B 1/34 Details , e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
• CPC Class Codes: B66B 2201/102 Up or down call input
• CPC Class Codes: B66B 2201/211 Waiting time, i.e. response time
• CPC Class Codes: B66B 2201/222 Taking into account the number of passengers present in the elevator car to be allocated
• CPC Class Codes: B66B 2201/402 by historical, statistical or predicted traffic data, e.g. by learning
• CPC Class Codes: B66B 2201/403 by real-time traffic data
• CPC Class Codes: B66B 5/0006 Monitoring devices or performance analysers B66B5/02 takes precedence
• CPC Class Codes: B66B 5/0037 Performance analysers
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles

Abstract

The feature distinguishing part distinguishes feature modes from the traffic volume data detected by the traffic volume detecting part or from the traffic volume data estimated from the detected traffic volume data by the traffic volume estimating part, and the control parameter setting part sets the optimum control parameter according to the distinction results, further the drive controlling part controls the drive of cars on the control parameters. The distinction function constructing part constructs and modifies the distinction function of feature modes by learning prepared plural feature modes or the distinction results of past feature modes, furthermore the control result detecting part detects the control results or the drive results of cars, and corrects the control parameters. The control results or the drive results are exhibited on the user interface, and the control parameters are set and corrected from the outside by referring the results.

Claims

1. A traffic means controlling apparatus comprising:

a traffic volume detecting part that detects a traffic volume of a traffic means;

a feature distinguishing part that selects a feature mode, representing a mode of operation of the traffic means controlling apparatus, from a plurality of feature modes based upon the traffic volume detected by said traffic volume detecting part according to a distinction function;

a distinction function constructing part that constructs the distinction function of said feature distinguishing part based upon the plurality of feature modes and a plurality of feature mode traffic volumes respectively corresponding to each of the plurality of feature modes; and

a control parameter setting part that sets a control parameter for controlling the traffic means based on the feature mode selected by said feature mode distinguishing part.

2. The traffic means controlling apparatus according to claim 1 wherein said feature distinguishing part includes a feature mode distinguishing means that includes a neural network, the neural network receiving the traffic volume and an outputting an indication of the similarity of the traffic volume to the feature mode traffic volume of each of the plurality of feature modes.

3. The traffic means controlling apparatus according to claim 2 wherein said feature mode distinguishing means in said feature distinguishing part includes;

a first neural network for control for executing the distinction of said feature mode to create a first distinction result; and

a second neural network for backup for periodically executing the distinction of said feature mode to create a second distinction result;

and wherein said distinction function constructing part compares and evaluates distinction results of the first neural network and the second neural network to replace the contents of said first neural network for control with the contents of said second neural network for backup when said distinction result is superior to the first distinction result.

4. The traffic means controlling apparatus according to claim 2 wherein said feature distinguishing part further includes a feature mode detecting means that includes:

a filter for filtering the indication output by of said neural network of said feature mode distinguishing means and for providing a binary output corresponding to each of the plurality of feature modes, the binary output being indicative of whether the corresponding feature mode is the selected feature mode; and

a feature mode specifying means for selecting a feature mode from the output of said filter.

5. The traffic means controlling apparatus according to claim 4 wherein said feature mode detecting means further comprises an additional filtering means that adjusts said filter when said filter has more than one binary output indicative of a selected filter mode, and when said filter does not have an output indicative of the selected filter mode.

6. The traffic means controlling apparatus according to claim 5 wherein the filter includes a threshold value for creating the binary output, and wherein the additional filter means adjusts the filter by adjusting the threshold value.

7. The traffic means controlling apparatus according to claim 4 wherein said feature mode detecting means further comprises an additional feature mode specifying means that adds a new feature mode to the plurality of feature modes when said filter does not have an output indicative of a selected filter mode.

8. The traffic means controlling apparatus according to claim 2 wherein said distinction function constructing part further constructs the distinction function of said neural network by learning a distinction result of the distinction function that selected a previous feature mode in response to a previous traffic volume.

9. The traffic means controlling apparatus of claim 1, further comprising:

a control result detecting part that detects a control result of controlling said traffic means resulting from the feature mode selected by the feature distinguishing part; and

a user interface for receiving a user input to correct said control parameter;

wherein the control parameter setting part further comprises means for correcting said control parameter in accordance with the control result.

10. The traffic means controlling apparatus of claim 1, further comprising:

a traffic volume estimating part that estimates in real time a future traffic volume by executing the sampling processing of the traffic volume detected by said traffic volume detecting means in real time;

a control result detecting part that detects a control result of controlling said traffic means resulting from the feature mode selected by the feature distinguishing part; and

a user interface for receiving a user input to correct said control parameter;

wherein the control parameter setting part further comprises means for correcting said control parameter in accordance with the control result; and

wherein the feature distinguishing part includes means for selecting the feature mode based upon the future volume estimated by said traffic volume estimating part.

11. A traffic means controlling apparatus comprising:

a traffic volume detecting part that detects a traffic volume of a traffic means;

a feature distinguishing part that selects a feature mode, representing a mode of operation of the traffic means controlling apparatus from a plurality of feature modes based upon the traffic volume detected by said traffic volume detecting part according to a distinction function;

a distinction function constructing part that constructs the distinction function of said future distinguishing part based upon the plurality of feature modes and a plurality of feature mode traffic volumes respectively corresponding to each of the plurality of feature modes;

a control result detecting part that detects a control result of controlling said traffic means resulting from the feature mode selected by the feature distinguishing part;

a control parameter setting part that sets a control parameter for controlling the traffic means based on the feature mode selected by said feature mode distinguishing part and corrects said control parameter in accordance with the control result; and

a user interface for receiving a user input to correct said control parameter.

12. The traffic means controlling apparatus according to claim 11 wherein said control parameter setting part sets a standard value of the control parameter in accordance with said feature mode selected by said feature distinguishing part, and corrects said standard value of the control parameter by means of offline tuning in accordance with the control result detected by said control result detecting part.

13. The traffic means controlling apparatus according to claim 11 wherein said control parameter setting part sets a standard value of the control parameter in accordance with said feature mode selected by said feature distinguishing part, and corrects said standard value of the control parameter by means of online tuning in accordance with the result detected by said control result detecting part in real time.

14. The traffic means controlling apparatus according to claim 11 wherein the control result detected by the control result detecting part includes a drive result representing a response of the traffic means responsive to the selected feature mode.

15. The traffic means controlling apparatus according to claim 11 wherein said result data exhibited by said user interface includes at least one of a control result and a drive result detected by the control result detecting part.

16. The traffic means controlling apparatus according to claim 11 wherein said user interface has a function of exhibiting result data to a user, and a function of receiving a direction from a user referring said data for correcting said control parameter.

17. A traffic means controlling apparatus comprising:

a traffic volume detecting part that detects a traffic volume of a traffic means;

a traffic volume estimating part that estimates in real time a future traffic volume by executing the sampling processing of the traffic volume detected by said traffic volume detecting means in real time;

a feature distinguishing part that selects a feature mode, representing a mode or operation of the traffic means controlling apparatus, from a plurality of feature modes based upon the traffic volume estimated by said traffic volume estimating part according to a distinction function;

a distinction function constructing part that constructs the distinction function of said feature distinguishing part based upon the plurality of feature modes and a plurality of feature mode traffic volumes respectively corresponding to each of the plurality of feature modes;

a control result detecting part that detects a control result of controlling said traffic means resulting from the feature mode selected by the feature distinguishing part;

a control parameter setting part that sets a control parameter for controlling the traffic means based on the feature mode selected by said feature mode distinguishing part and corrects said control parameter in accordance with the control result detected by said control result detecting part; and

a user interface for receiving a user input to correct said control parameter.

18. The traffic means controlling apparatus according to claim 17 wherein the control result detected by the control result detecting part includes a drive result representing a response of the traffic means responsive to the selected feature mode.