CN110654946A - Community elevator dispatching method and system based on artificial intelligence - Google Patents

Community elevator dispatching method and system based on artificial intelligence Download PDF

Info

Publication number
CN110654946A
CN110654946A CN201910770615.5A CN201910770615A CN110654946A CN 110654946 A CN110654946 A CN 110654946A CN 201910770615 A CN201910770615 A CN 201910770615A CN 110654946 A CN110654946 A CN 110654946A
Authority
CN
China
Prior art keywords
elevator
dispatching
taking
floor
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910770615.5A
Other languages
Chinese (zh)
Other versions
CN110654946B (en
Inventor
吴海涛
金涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Terminus Technology Co Ltd
Original Assignee
Chongqing Terminus Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing Terminus Technology Co Ltd filed Critical Chongqing Terminus Technology Co Ltd
Priority to CN201910770615.5A priority Critical patent/CN110654946B/en
Publication of CN110654946A publication Critical patent/CN110654946A/en
Application granted granted Critical
Publication of CN110654946B publication Critical patent/CN110654946B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/24—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration
    • B66B1/2408—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration where the allocation of a call to an elevator car is of importance, i.e. by means of a supervisory or group controller
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B1/00—Control systems of elevators in general
    • B66B1/24—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration
    • B66B1/28—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration electrical
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/211—Waiting time, i.e. response time
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/212—Travel time
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/216—Energy consumption
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/222—Taking into account the number of passengers present in the elevator car to be allocated
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
    • B66B2201/231—Sequential evaluation of plurality of criteria
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/40—Details of the change of control mode
    • B66B2201/402—Details of the change of control mode by historical, statistical or predicted traffic data, e.g. by learning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
    • B66B2201/00—Aspects of control systems of elevators
    • B66B2201/40—Details of the change of control mode
    • B66B2201/403—Details of the change of control mode by real-time traffic data

Abstract

The invention discloses a community elevator dispatching method and a device based on artificial intelligence, wherein the method comprises the following steps: acquiring a call elevator request, a target floor of each elevator, a load state of the elevator and predicted floor information; establishing an artificial intelligent optimization model according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information; the artificial intelligence optimization model adopts a genetic algorithm to generate an implementation scheduling scheme. The method updates the scheduling scheme in real time, selects the optimal real-time scheduling scheme, enables the elevator to run efficiently, improves the service efficiency of the elevator, saves the resource consumption, and provides convenience for the trip of passengers.

Description

Community elevator dispatching method and system based on artificial intelligence
Technical Field
The invention relates to the field of elevator dispatching management of intelligent communities, in particular to a community elevator dispatching method and a community elevator dispatching system based on artificial intelligence.
Background
The high-rise buildings in a large residential community are more, each high-rise building is provided with a certain number of elevators, more people take the elevators, and particularly, long elevator waiting time is needed in peak hours, so that the optimization of the scheduling of the elevators to realize resource allocation becomes a complex problem.
The dispatching of elevators mainly involves: when a call elevator request exists, how to assign an elevator to stop at a call elevator floor to meet the request; how to set the default stopping floor of the elevator when there is no call for the elevator.
In addition, the fixed population who takes the elevator in the residential community is large (such as residents and tenants living in the community for a long time), the floating population is small (such as visitors and couriers), the target floor expected when the fixed population calls the elevator is relatively fixed, and the target floor is concentrated on the residential floor and the public floor (such as 1 floor, an underground garage floor and the like) in most cases, for the fixed population, the reasonable time for arranging the elevator can improve the resource utilization rate, and the elevator dispatching scheme is more reasonable.
Therefore, how to reasonably schedule and allocate the elevators and improve the resource utilization rate is a problem to be solved urgently by practitioners of the same industry.
Disclosure of Invention
In view of the above problems, the invention aims to solve the problems of poor adaptability to the use frequency of the elevator, lack of universality, unreasonable scheduling and low resource utilization rate.
In a first aspect, an embodiment of the present invention provides a community elevator scheduling method based on artificial intelligence, including:
acquiring a call elevator request, a target floor of each elevator, a load state of the elevator and predicted floor information;
generating an initial elevator dispatching scheme according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information;
and the initial elevator dispatching scheme adopts a genetic algorithm to generate a real-time dispatching scheme.
In one embodiment, obtaining a call request, a destination floor of each elevator, a load status of the elevator, and predicted floor information comprises:
acquiring a call elevator request, a target floor of each elevator and a load state of the elevator;
acquiring facial images of passengers waiting for taking the elevator;
comparing the facial image of the passenger waiting for taking the elevator with a historical elevator taking passenger facial database to determine whether the passenger is a fixed passenger taking the elevator for multiple times;
and when the fixed passengers taking the elevator for multiple times are determined, acquiring the high-frequency stop floors recorded in the historical elevator taking records of the passengers, and generating predicted floor information.
In one embodiment, the initial elevator dispatching plan adopts a genetic algorithm to generate a real-time dispatching plan, including:
acquiring M initial state arrays of the initial elevator dispatching scheme;
performing variation crossing on the M initial state arrays according to a genetic algorithm to generate a state array;
selecting a better state array from the state arrays to enter the next iteration;
and when the evaluation function of the comprehensive optimization in the state array accords with five elevator dispatching optimization targets, ending iteration and generating a real-time dispatching scheme.
In one embodiment, the evaluation function of the synthetic optimization is:
Figure BDA0002173438790000021
in the above formula, f1、f2、f3、f4、f5Evaluation values, w, representing five elevator dispatching optimization objectives1、w2、w3、w4、w5Representing a weight value.
In one embodiment, the five elevator dispatching optimization objectives include:
the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
In a second aspect, the present invention further provides a community elevator dispatching system based on artificial intelligence, comprising:
the elevator calling system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring an elevator calling request, a target floor of each elevator, a load state of the elevator and predicted floor information;
the initial elevator dispatching scheme generating module is used for generating an initial elevator dispatching scheme according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information;
and the real-time scheduling scheme generating module is used for generating the real-time scheduling scheme by adopting a genetic algorithm through the artificial intelligence optimization model.
In one embodiment, the obtaining module includes:
the elevator state interface submodule is used for acquiring a calling elevator request, a target floor of each elevator and the load state of the elevator;
the face image acquisition sub-module is used for acquiring face images of passengers waiting for taking the elevator;
the fixed passenger determining submodule is used for comparing the face image of the passenger waiting for taking the elevator with a historical elevator taking passenger face database and determining whether the passenger is a fixed passenger taking the elevator for multiple times;
and the predicted floor generation submodule is used for acquiring the high-frequency stop floor recorded in the passenger history elevator taking record and generating predicted floor information when the fixed passenger taking the elevator for multiple times is determined.
In one embodiment, the real-time scheduling scheme generating module includes:
the obtaining submodule is used for obtaining M initial state arrays of the initial elevator dispatching scheme;
the state array generating submodule is used for carrying out variation crossing on the M initial state arrays of the elevator dispatching scheme according to a genetic algorithm to generate a state array;
the selection submodule is used for selecting a better state array from the state arrays to enter the next iteration;
and the real-time scheduling scheme generating submodule is used for ending iteration and generating a real-time scheduling scheme when the evaluation function of the comprehensive optimization in the state array accords with five elevator scheduling optimization targets.
In one embodiment, in the real-time scheduling scheme generation submodule,
the evaluation function of the comprehensive optimization is as follows:
Figure BDA0002173438790000031
in the above formula, f1、f2、f3、f4、f5Evaluation values, w, representing five elevator dispatching optimization objectives1、w2、w3、w4、w5Representing a weight value.
In one embodiment, in the real-time scheduling scheme generation submodule,
the meeting of five elevator dispatching optimization objectives includes: the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
according to the community elevator dispatching method based on artificial intelligence, the state array of the elevator is continuously updated, the elevator dispatching optimization target is formulated, when the evaluation function of the state array reaches the set optimization target, the real-time dispatching scheme is generated, the elevator is controlled according to the real-time dispatching scheme, the instantaneity of an elevator dispatching system is improved, the operation of the elevator can be reasonably and effectively controlled, the time of the elevator such as a user is saved, the use efficiency is improved, resources are saved, and great convenience is brought to the user.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart of a community elevator dispatching method based on artificial intelligence provided by an embodiment of the invention;
FIG. 2 is a flowchart of a step S101 provided in an embodiment of the present invention;
FIG. 3 is a flowchart of step S103 according to an embodiment of the present invention;
fig. 4 is a block diagram of an artificial intelligence based community elevator dispatching system provided by an embodiment of the invention;
fig. 5 is a block diagram of an obtaining module 401 according to an embodiment of the present invention;
fig. 6 is a block diagram of a real-time scheduling scheme generating module 403 according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides a community elevator dispatching method based on artificial intelligence, including: s101 to S103;
s101, acquiring a calling elevator request, a target floor of each elevator, a load state of the elevator and predicted floor information;
the elevator calling request is an ascending or descending request input by passengers not riding on the elevator through a call panel of the elevator room; the destination floor of each elevator is the stopping floor input by passengers taking the elevator through a floor panel in the elevator; the load state of the elevator is divided into a non-full load state and a full load state, and a plurality of elevator crowding grades, such as 1-3 grades, are divided according to the actual load weight of the elevator in the non-full load state;
s102, generating an initial elevator dispatching scheme according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information;
and S103, generating a real-time scheduling scheme by the initial elevator scheduling scheme by adopting a genetic algorithm.
In the embodiment, the scheduling scheme is updated in real time by adopting the genetic algorithm, and the optimal real-time scheduling scheme is selected, so that the elevator can run efficiently, the use efficiency of the elevator is improved, the resource consumption is saved, and convenience is provided for the trip of passengers.
In one embodiment, referring to fig. 2, the obtaining of the predicted floor information in step S101 includes:
s1011, obtaining a calling elevator request, a target floor of each elevator and a load state of the elevator;
s1012, acquiring a face image of a passenger waiting for taking the elevator;
s1013, comparing the face image of the passenger waiting for taking the elevator with a historical passenger face database for taking the elevator, and determining whether the passenger is a fixed passenger taking the elevator for multiple times;
and S1014, when the fixed passenger taking the elevator for multiple times is determined, acquiring the high-frequency stop floor recorded in the passenger history elevator taking record, and generating the predicted floor information.
In this embodiment, judge whether the passenger is fixed passenger, prejudge the stop floor of fixed passenger, generate floor information in advance, can generate more reasonable elevator dispatch scheme, resources are saved reduces the waste of elevator resource, makes things convenient for the passenger to take advantage of the ladder.
In one embodiment, referring to fig. 3, the initial elevator dispatching plan in step S103 uses a genetic algorithm to generate a real-time dispatching plan, which includes:
s1031, obtaining M initial state arrays of the initial elevator dispatching scheme;
s1032, performing variation crossing on the M initial state arrays according to a genetic algorithm to generate a state array;
s1033, selecting a better state array from the state arrays and entering the next iteration;
s1034, when the comprehensive optimized evaluation function in the state array accords with the five elevator dispatching optimization targets, ending iteration and generating a real-time dispatching scheme.
In the embodiment, the initial elevator dispatching scheme is continuously updated by adopting the genetic algorithm until the optimal real-time dispatching scheme is generated, and the elevator is controlled according to the implementation dispatching scheme, so that the real-time performance of the elevator dispatching scheme is improved, the time for a user to wait for the elevator is saved, and the use efficiency of the elevator is improved.
In step S1034, the evaluation function of the comprehensive optimization is:
Figure BDA0002173438790000061
in the above formula, f1Evaluation value f showing lowering of average elevator waiting time of user2Evaluation value f showing reduction of average boarding time of user3Evaluation value f showing reduction of average number of occurrences of delamination4Evaluation value f showing reduction of average congestion degree of elevator5Evaluation value, w, representing reduced energy consumption of an elevator1Weight value, w, indicating a reduction in average elevator waiting time for a user2Weight value w representing lowering of average elevator-taking time of user3Weight value, w, representing a reduction in the number of occurrences of average delamination4Weight value w for reducing average congestion degree of elevator5Representing a weight value that reduces the energy consumption of the elevator.
In step S1034, the five elevator dispatching optimization objectives include:
the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
The artificial intelligence based community elevator dispatching method is described below by a complete embodiment.
Example 1:
specifically, the elevator dispatching is carried out by the following method steps:
1. the control system of the elevator executes step S101, namely, obtains the elevator calling request, the destination floor of each elevator and the load state of the elevator in real time; the control system of the elevator shoots the faces of passengers waiting for taking the elevator through a video camera arranged in the elevator room, and judges whether the passengers are fixed passengers taking the elevator for multiple times through comparison with a background historical elevator-taking passenger face database; if so, acquiring a high-frequency stop floor recorded in the passenger historical elevator taking record as a prediction floor;
2. the control system of the elevator executes step S102, namely, the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information which are obtained in real time are substituted into the artificial intelligent optimization model;
3. in the artificial intelligence optimization model, in step S1031, M initial state arrays (i.e., hereditary 0 th generation) of the elevator dispatching scheme are determined, and assuming that there are n elevators, each initial state array is represented as Xi(0) Wherein i is 1, 2, 3 … M;
Xi(0) is an n-dimensional array represented as:
Figure BDA0002173438790000071
wherein xi，1(0)，xi，2(0)，xi，3(0)，…，xi，n(0) Respectively representing the 1 st, 2 nd and 3 rd 3 … n elevator running direction and the stop mode in the ith initial state, xi，1(0)，xi，2(0)，xi，3(0)，…，xi，n(0) The value of (1) is 0-3, wherein 0 represents the descending and all floors with the call elevator requests stop layer by layer, 1 represents the ascending and all floors with the call elevator requests stop layer by layer, 2 represents the descending and neglects the floors with the call elevator requests, and 3 represents the ascending and neglects the floors with the call elevator requests.
5. Executing a step S1032, and carrying out mutation on the state array by adopting a genetic algorithm;
for example, taking the g-th iteration as an example, 3 individuals, namely X, are randomly selected from the population of the state arrayP1(g)、XP2(g)、XP3(g) And P1 ≠ P2 ≠ P3 ≠ i;
the generated mutation state array is as follows:
Vi(g)＝Xp1(g)+F·(Xp2(g)-Xp3(g))
where F is a scaling factor, typically chosen between [0, 2 ];
6. and crossing the state arrays, namely randomly generating a new individual in a probability mode, wherein a specific formula is as follows:
Figure BDA0002173438790000081
wherein CR is referred to as cross probability; u shapei,j(g +1) represents a new individual selected by means of probability, Vi,j(g +1) represents an individual randomly generated by means of probability, Xi,j(g) Representing the original individual value;
7. in step S1033, the better individual is selected from the state array of each generation as the new individual entering the next generation, and the selection method is:
Figure BDA0002173438790000082
wherein, Xi,j(g +1) represents a selected new individual, Ui,j(g +1) represents an individual selected by means of probability, Xi,j(g) Representing the original individual value;
9. if the step S1034 is carried out, continuously carrying out mutation, intersection and selection through inheritance of a plurality of generations until a certain generation state array of the obtained elevator dispatching scheme enables an evaluation function of the comprehensive optimization to meet requirements, and outputting the state array as a comprehensive optimization real-time dispatching scheme of the five aspects of targets;
wherein the evaluation function of the comprehensive optimization is as follows:
in the above formula, f1Evaluation value f showing lowering of average elevator waiting time of user2Evaluation value f showing reduction of average boarding time of user3Evaluation value f showing reduction of average number of occurrences of delamination4Evaluation value f showing reduction of average congestion degree of elevator5Evaluation value, w, representing reduced energy consumption of an elevator1Weight value, w, indicating a reduction in average elevator waiting time for a user2Weight value w representing lowering of average elevator-taking time of user3Weight value, w, representing a reduction in the number of occurrences of average delamination4Weight value w for reducing average congestion degree of elevator5Representing a weight value that reduces the energy consumption of the elevator.
Further, the five elevator dispatching optimization targets are as follows: (1) the average elevator waiting time of the user is reduced, wherein the elevator waiting time is the time length from the time when the user sends an elevator calling request to the time when the elevator stops at an elevator calling floor; (2) the average elevator taking time of the user is reduced, namely the time length from the time when the user takes the elevator to arrive at the target floor after the elevator stops at the elevator calling floor is mainly related to the stopping times of the elevator in the process of running from the elevator calling floor to the target floor; (3) the average floor-throwing occurrence frequency is reduced, and the floor-throwing is that the elevator passes through the floor with the elevator-calling request without stopping due to full load of the elevator, so that the overlong waiting time of a user is caused; (4) the average crowding level of the elevator is reduced, and the comfort level of a user is improved; (5) the energy consumption of the elevator is reduced, the energy consumption of the elevator is mainly related to the average number of times of stopping of the elevator, and the braking and starting processes of stopping of each time are the most energy-consuming links.
10. The direction of travel (up, down) and the stopping floors of each elevator are controlled according to the real-time scheduling scheme of the elevators.
In the embodiment, iterative inheritance is performed on the state array of the elevator according to a genetic algorithm, the state array is continuously updated, an elevator dispatching optimization target is formulated, when the evaluation function of the state array reaches the set optimization target, a real-time dispatching scheme is generated, the elevator is controlled according to the real-time dispatching scheme, the instantaneity of an elevator dispatching system is improved, the operation of the elevator can be reasonably and effectively controlled, the time of the elevator such as a user is saved, the use efficiency is improved, resources are saved, and great convenience is provided for the user.
Based on the same inventive concept, the embodiment of the invention also provides a community elevator dispatching system based on artificial intelligence, and as the principle of the problem solved by the device is similar to the community elevator dispatching method based on artificial intelligence, the implementation of the device can refer to the implementation of the method, and repeated parts are not repeated.
The community elevator dispatching system based on artificial intelligence provided by the embodiment of the invention is shown in figure 4 and comprises:
an obtaining module 401, configured to obtain a call request, a destination floor of each elevator, a load state of each elevator, and predicted floor information;
an initial elevator dispatching scheme generating module 402, configured to substitute an artificial intelligence optimization model according to the elevator calling request, the target floor of each elevator, the load state of the elevator, and the predicted floor information, and generate an initial elevator dispatching scheme;
and a real-time scheduling scheme generating module 403, configured to generate a real-time scheduling scheme by using a genetic algorithm through the artificial intelligence optimization model.
In one embodiment, referring to fig. 5, the obtaining module 401 includes:
an elevator status interface sub-module 4011 for obtaining said call request for upward or downward movement from a call panel of the elevator car, said call request being inputted by a passenger who does not take an elevator, obtaining a stop floor from a floor panel inside the elevator, said stop floor being inputted by a passenger who has taken an elevator, as said destination floor, and obtaining a load status from the elevator, said load status of the elevator being divided into an unloaded state and a loaded state, said unloaded state being divided into several elevator congestion levels, e.g. 1-3 levels, according to the actual load weight of the elevator;
a face image acquisition sub-module 4012 configured to acquire a face image of a passenger waiting to take the elevator;
the fixed passenger determining sub-module 4013 is configured to compare the facial image of the passenger waiting for taking the elevator with the historical passenger facial database for taking the elevator, and determine whether the passenger is a fixed passenger taking the elevator for multiple times;
the predicted floor generation sub-module 4014 is configured to, when it is determined that the passenger is a fixed passenger who takes an elevator multiple times, obtain a high-frequency stop floor recorded in the passenger history elevator taking record, and generate predicted floor information.
In one embodiment, referring to fig. 6, the real-time scheduling scheme generating module 403 includes:
the obtaining submodule 4031 is used for obtaining M initial state arrays of the initial elevator dispatching scheme;
the state array generating submodule 4032 is used for performing mutation intersection on the M initial state arrays of the elevator dispatching scheme according to a genetic algorithm to generate a state array;
a selecting submodule 4033, configured to select a better state array from the state arrays to enter a next iteration;
and the real-time scheduling scheme generating submodule 4034 is used for ending iteration and generating a real-time scheduling scheme when the evaluation function of the comprehensive optimization in the state array accords with the five elevator scheduling optimization targets.
In one embodiment, in the real-time scheduling scheme generation submodule,
the evaluation function of the comprehensive optimization is as follows:
Figure BDA0002173438790000111
in the above formula, f1、f2、f3、f4、f5Evaluation values, w, representing five elevator dispatching optimization objectives1、w2、w3、w4、w5Representing a weight value.
In one embodiment, in the real-time scheduling scheme generation submodule,
the meeting of five elevator dispatching optimization objectives includes: the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
In one embodiment, the acquisition sub-module 4031 determines M initial state arrays (i.e., the genetic 0 th generation) of the elevator dispatching plan, each of which is denoted X assuming a total of n elevatorsi(0) Wherein i is 1, 2, 3 … M;
Xi(0) is an n-dimensional array represented as:
Figure BDA0002173438790000112
wherein xi，1(0)，xi，2(0)，xi，3(0)，…，xi，n(0) Respectively representing the 1 st, 2 nd and 3 rd 3 … n elevator running direction and the stop mode in the ith initial state, xi，1(0)，xi，2(0)，xi，3(0)，…，xi，n(0) The value of (1) is 0-3, wherein 0 represents the descending and all floors with the call elevator requests stop layer by layer, 1 represents the ascending and all floors with the call elevator requests stop layer by layer, 2 represents the descending and neglects the floors with the call elevator requests, and 3 represents the ascending and neglects the floors with the call elevator requests.
In one embodiment, a genetic algorithm is used to mutate the state array;
for example, taking the g-th iteration as an example, 3 individuals, namely X, are randomly selected from the population of the state arrayP1(g)、XP2(g)、XP3(g) And P1 ≠ P2 ≠ P3 ≠ i;
the generated mutation state array is as follows:
Vi(g)＝Xp1(g)+F·(Xp2(g)-Xp3(g))
where F is a scaling factor, typically chosen between [0, 2 ];
moreover, the state array generating submodule 4032 intersects the state arrays, that is, randomly generates new individuals in a probabilistic manner, and the specific formula is as follows:
Figure BDA0002173438790000121
wherein CR is referred to as cross probability; u shapei,j(g +1) represents a new individual selected by means of probability, Vi,j(g +1) represents an individual randomly generated by means of probability, Xi,j(g) Representing the original individual value;
in one embodiment, the selecting submodule 4033 selects the better individual from the state array of each generation as the new individual for entering the next generation, and the selection mode is as follows:
Figure BDA0002173438790000122
wherein, Xi,j(g +1) represents a selected new individual, Ui,j(g +1) represents an individual selected by means of probability, Xi,j(g) Representing the original individual value;
in one embodiment, the real-time scheduling scheme generating sub-module 4034 obtains an evaluation function of comprehensive optimization for a certain generation of state array of the elevator scheduling scheme obtained by continuously performing mutation, intersection and selection on inheritance of a plurality of generations until the evaluation function of the comprehensive optimization meets requirements, and outputs the state array as the comprehensive optimized real-time scheduling scheme of the five aspects of the objective.
Specifically, the elevator control system is provided with an acquisition module, an initial elevator dispatching scheme generation module and a real-time dispatching scheme generation module.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A community elevator dispatching method based on artificial intelligence is characterized by comprising the following steps:
acquiring a call elevator request, a target floor of each elevator, a load state of the elevator and predicted floor information;
generating an initial elevator dispatching scheme according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information;
and the initial elevator dispatching scheme adopts a genetic algorithm to generate a real-time dispatching scheme.
2. The artificial intelligence based community elevator dispatching method of claim 1, wherein the obtaining of elevator calling requests, the destination floor of each elevator, the load status of the elevator and the predicted floor information comprises:
acquiring a call elevator request, a target floor of each elevator and a load state of the elevator;
acquiring facial images of passengers waiting for taking the elevator;
comparing the facial image of the passenger waiting for taking the elevator with a historical elevator taking passenger facial database to determine whether the passenger is a fixed passenger taking the elevator for multiple times;
and when the fixed passengers taking the elevator for multiple times are determined, acquiring the high-frequency stop floors recorded in the historical elevator taking records of the passengers, and generating predicted floor information.
3. The artificial intelligence based community elevator dispatching method of claim 1, wherein the initial elevator dispatching scheme adopts a genetic algorithm to generate a real-time dispatching scheme, comprising:
acquiring M initial state arrays of the initial elevator dispatching scheme;
performing variation crossing on the M initial state arrays according to a genetic algorithm to generate a state array;
selecting a better state array from the state arrays to enter the next iteration;
and when the evaluation function of the comprehensive optimization in the state array accords with five elevator dispatching optimization targets, ending iteration and generating a real-time dispatching scheme.
4. The artificial intelligence based community elevator dispatching method of claim 3, wherein the evaluation function of the comprehensive optimization is:
in the above formula, f1、f2、f3、f4、f5Evaluation values, w, representing five elevator dispatching optimization objectives1、w2、w3、w4、w5Representing a weight value.
5. The artificial intelligence based community elevator dispatching method of claim 3, wherein the five elevator dispatching optimization objectives comprise:
the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
6. An artificial intelligence based community elevator dispatching system, comprising:
the elevator calling system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring an elevator calling request, a target floor of each elevator, a load state of the elevator and predicted floor information;
the initial elevator dispatching scheme generating module is used for generating an initial elevator dispatching scheme according to the elevator calling request, the target floor of each elevator, the load state of the elevator and the predicted floor information;
and the real-time scheduling scheme generating module is used for generating the real-time scheduling scheme by adopting a genetic algorithm through the artificial intelligence optimization model.
7. The artificial intelligence based community elevator dispatching system of claim 6, wherein the obtaining module comprises:
the elevator state interface submodule is used for acquiring a calling elevator request, a target floor of each elevator and the load state of the elevator;
the face image acquisition sub-module is used for acquiring face images of passengers waiting for taking the elevator;
the fixed passenger determining submodule is used for comparing the face image of the passenger waiting for taking the elevator with a historical elevator taking passenger face database and determining whether the passenger is a fixed passenger taking the elevator for multiple times;
and the predicted floor generation submodule is used for acquiring the high-frequency stop floor recorded in the passenger history elevator taking record and generating predicted floor information when the fixed passenger taking the elevator for multiple times is determined.
8. The artificial intelligence based community elevator dispatching system of claim 6, wherein the real-time dispatching plan generating module comprises:
the obtaining submodule is used for obtaining M initial state arrays of the initial elevator dispatching scheme;
the state array generating submodule is used for carrying out variation crossing on the M initial state arrays of the elevator dispatching scheme according to a genetic algorithm to generate a state array;
the selection submodule is used for selecting a better state array from the state arrays to enter the next iteration;
and the real-time scheduling scheme generating submodule is used for ending iteration and generating a real-time scheduling scheme when the evaluation function of the comprehensive optimization in the state array accords with five elevator scheduling optimization targets.
9. The artificial intelligence based community elevator dispatching system of claim 8, wherein in the real-time dispatching scheme generating sub-module,
the evaluation function of the comprehensive optimization is as follows:
Figure FDA0002173438780000031
in the above formula, f1、f2、f3、f4、f5Evaluation of five Elevator scheduling optimization objectivesValue, w1、w2、w3、w4、w5Representing a weight value.
10. The apparatus according to claim 8, wherein said real-time scheduling scheme generation sub-module,
the meeting of five elevator dispatching optimization objectives includes: the average elevator waiting time of the user is reduced, the average elevator taking time of the user is reduced, the average floor throwing frequency is reduced, the average crowding degree of the elevator is reduced, and the energy consumption of the elevator is reduced.
CN201910770615.5A 2019-08-20 2019-08-20 Community elevator dispatching method and system based on artificial intelligence Active CN110654946B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910770615.5A CN110654946B (en) 2019-08-20 2019-08-20 Community elevator dispatching method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910770615.5A CN110654946B (en) 2019-08-20 2019-08-20 Community elevator dispatching method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN110654946A true CN110654946A (en) 2020-01-07
CN110654946B CN110654946B (en) 2021-01-01

Family

ID=69037507

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910770615.5A Active CN110654946B (en) 2019-08-20 2019-08-20 Community elevator dispatching method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN110654946B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111703990A (en) * 2020-07-02 2020-09-25 浪潮卓数大数据产业发展有限公司 Intelligent elevator stopping implementation method and system based on big data and face recognition
CN112794172A (en) * 2021-01-13 2021-05-14 海南大学 Data portrait and information portrait value alternating current conversion oriented carrying method and system
CN113291939A (en) * 2021-04-08 2021-08-24 上海新时达电气股份有限公司 Elevator dispatching method, device, electronic equipment and storage medium
CN113526277A (en) * 2021-07-23 2021-10-22 广州广日电梯工业有限公司 Method and device for quickly determining elevator dispatching algorithm
CN114355854A (en) * 2022-01-04 2022-04-15 四川轻化工大学 Automatic guided vehicle and elevator combined dispatching method for two-layer manufacturing workshop
CN115072508A (en) * 2022-07-18 2022-09-20 凯尔菱电（山东）电梯有限公司 Efficient dispatching method for elevators in intelligent building
CN117185063A (en) * 2023-11-08 2023-12-08 海纳云物联科技有限公司 Elevator dispatching method, device, equipment and computer storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011144025A (en) * 2010-01-15 2011-07-28 Toshiba Elevator Co Ltd Group management apparatus for elevator
CN103072858A (en) * 2013-01-28 2013-05-01 哈尔滨工业大学 Vertical dispatch method for double sub-elevator groups for energy saving
CN105492359A (en) * 2013-08-30 2016-04-13 通力股份公司 Multi-deck elevator allocation control
CN109019198A (en) * 2018-08-24 2018-12-18 广州广日电梯工业有限公司 elevator call system and method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011144025A (en) * 2010-01-15 2011-07-28 Toshiba Elevator Co Ltd Group management apparatus for elevator
CN103072858A (en) * 2013-01-28 2013-05-01 哈尔滨工业大学 Vertical dispatch method for double sub-elevator groups for energy saving
CN105492359A (en) * 2013-08-30 2016-04-13 通力股份公司 Multi-deck elevator allocation control
CN109019198A (en) * 2018-08-24 2018-12-18 广州广日电梯工业有限公司 elevator call system and method

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111703990A (en) * 2020-07-02 2020-09-25 浪潮卓数大数据产业发展有限公司 Intelligent elevator stopping implementation method and system based on big data and face recognition
CN111703990B (en) * 2020-07-02 2021-12-03 浪潮卓数大数据产业发展有限公司 Intelligent elevator stopping implementation method and system based on big data and face recognition
CN112794172A (en) * 2021-01-13 2021-05-14 海南大学 Data portrait and information portrait value alternating current conversion oriented carrying method and system
CN112794172B (en) * 2021-01-13 2022-04-01 海南大学 Data portrait and information portrait value alternating current conversion oriented carrying method and system
CN113291939B (en) * 2021-04-08 2023-02-10 上海新时达电气股份有限公司 Elevator dispatching method, device, electronic equipment and storage medium
CN113291939A (en) * 2021-04-08 2021-08-24 上海新时达电气股份有限公司 Elevator dispatching method, device, electronic equipment and storage medium
CN113526277A (en) * 2021-07-23 2021-10-22 广州广日电梯工业有限公司 Method and device for quickly determining elevator dispatching algorithm
CN113526277B (en) * 2021-07-23 2023-03-14 广州广日电梯工业有限公司 Method and device for quickly determining elevator dispatching algorithm
CN114355854A (en) * 2022-01-04 2022-04-15 四川轻化工大学 Automatic guided vehicle and elevator combined dispatching method for two-layer manufacturing workshop
CN114355854B (en) * 2022-01-04 2023-08-04 四川轻化工大学 Automatic guided vehicle and elevator joint scheduling method for two-layer manufacturing workshop
CN115072508A (en) * 2022-07-18 2022-09-20 凯尔菱电（山东）电梯有限公司 Efficient dispatching method for elevators in intelligent building
CN115072508B (en) * 2022-07-18 2022-11-11 凯尔菱电（山东）电梯有限公司 Efficient dispatching method for elevators in intelligent building
CN117185063A (en) * 2023-11-08 2023-12-08 海纳云物联科技有限公司 Elevator dispatching method, device, equipment and computer storage medium
CN117185063B (en) * 2023-11-08 2024-02-13 海纳云物联科技有限公司 Elevator dispatching method, device, equipment and computer storage medium

Also Published As

Publication number Publication date
CN110654946B (en) 2021-01-01

Similar Documents

Publication Publication Date Title
CN110654946B (en) Community elevator dispatching method and system based on artificial intelligence
US5354957A (en) Artificially intelligent traffic modeling and prediction system
CN111268522B (en) Elevator dispatching method and system based on big data analysis
JP4870863B2 (en) Elevator group optimum management method and optimum management system
US7014015B2 (en) Method and system for scheduling cars in elevator systems considering existing and future passengers
CN102328859A (en) Energy-saving elevator dispatching method and verification device thereof
CN113682908B (en) Intelligent scheduling method based on deep learning
CN105800400B (en) A kind of method for optimizing elevator dispatching management
CN1030248C (en) Elevator controlling apparatus
CN1043026C (en) Elevator group manage apparatus
CN1019288B (en) Method and apparatus for realizing elevator group control
CN113526272B (en) Elevator group control system and elevator group control equipment
CN112092670B (en) Charging pile queuing and charging management method
CN111931128A (en) Elevator configuration method, system, equipment and storage medium based on Bernoulli model
Chiang et al. Design of modern elevator group control systems
CN116902712A (en) Elevator dispatching method, elevator dispatching device and electronic equipment
CN210854833U (en) Multi-car elevator control system
Choi et al. An energy-efficient elevator operating system that considers sensor information and electricity price changes in smart green buildings
CN112700169A (en) Business process task allocation method and system based on prediction and personnel feedback
JP2728396B2 (en) Elevator control device
CN111924673B (en) Linkage elevator scheduling method, system, computer equipment and storage medium
CN115924663B (en) Intelligent elevator equipment control method based on Internet of things
KR102136022B1 (en) Reinforcement learning based elevator control apparatus
CN110127464B (en) Multi-objective elevator dispatching system and method based on dynamic optimization
CN116354199A (en) Elevator calling device based on voice interaction and calling control method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant