CN114590690B - Elevator operation control management system based on artificial intelligence - Google Patents
Elevator operation control management system based on artificial intelligence Download PDFInfo
- Publication number
- CN114590690B CN114590690B CN202210431371.XA CN202210431371A CN114590690B CN 114590690 B CN114590690 B CN 114590690B CN 202210431371 A CN202210431371 A CN 202210431371A CN 114590690 B CN114590690 B CN 114590690B
- Authority
- CN
- China
- Prior art keywords
- riding
- human body
- dangerous
- elevator
- danger
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B25/00—Control of escalators or moving walkways
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B25/00—Control of escalators or moving walkways
- B66B25/003—Methods or algorithms therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B27/00—Indicating operating conditions of escalators or moving walkways
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B29/00—Safety devices of escalators or moving walkways
- B66B29/005—Applications of security monitors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Elevator Control (AREA)
Abstract
The invention discloses an elevator operation control management system based on artificial intelligence, which comprises an elevator operation control terminal setting module, an elevator operation speed regulation module, an elevator riding overload monitoring and prompting module, an elevator riding main body identification module, a riding main body danger state analysis module, a riding main body danger state voice prompting module, a danger riding state storage library, a control database and an emergency braking processing end. Therefore, the safety and the reliability of the operation of the elevator are improved, and the time error caused by manually adopting the operation of an emergency brake part in an emergency situation is effectively avoided.
Description
Technical Field
The invention relates to the technical field of elevator operation control, in particular to an elevator operation control management system based on artificial intelligence.
Background
The handrail elevator is an outdoor elevator with handrails, generally exists in large facilities such as malls, and can save physical strength of customers going upstairs and downstairs, so that the customers can shop with more vigor. With the rapid development of economy and the steady promotion of the living standard of people, more and more handrail elevator devices are connected with the life of people more and more, but along with the potential safety hazard brought by the handrail elevator, the potential safety hazard becomes a great problem to be solved by the modern society, and the current potential safety hazard comprises the following aspects:
(1) The speed of the conventional handrail elevator in the running process is fixed and unchanged, and intelligent control cannot be performed according to the personnel gathering density and the personnel number of passengers to be taken, so that the running efficiency of the elevator is low, and the taking experience of the passengers is further reduced;
(2) The conventional escalator lacks the monitoring on the riding state of a riding body, so that dangerous conditions of the riding body, such as dangerous actions of a human body and dangerous placement states of objects, cannot be identified in time, and further the safety of the escalator when the riding body takes the escalator is difficult to ensure;
(3) When emergency takes place for present escalator, carry out emergency braking to escalator by the manual work, because there is certain time delay in the manual work carries out emergency braking operation, be difficult to react at the very first time to influence emergency's solution, reduced the fail safe nature of elevator operation.
Disclosure of Invention
In order to overcome the defects in the background art, the embodiment of the invention provides an elevator operation control management system based on artificial intelligence, which can effectively solve the problems related to the background art.
The purpose of the invention can be realized by the following technical scheme:
an elevator operation control management system based on artificial intelligence comprises an elevator operation control terminal setting module, an elevator operation speed regulating module, an elevator riding overload monitoring prompting module, an elevator riding main body recognition module, a riding main body dangerous state analysis module, a riding main body dangerous state voice prompting module, a dangerous riding state storage library, a control database and an emergency brake processing end;
the elevator operation control terminal setting module is respectively connected with an elevator operation speed regulating module, an elevator riding overload monitoring prompting module, an elevator riding main body recognition module and a riding main body danger state voice prompting module, the elevator riding main body recognition module is connected with a riding main body danger state analyzing module, the elevator operation speed regulating module is connected with a control database, the elevator riding overload monitoring prompting module is connected with the control database, and the riding main body danger state analyzing module is respectively connected with the riding main body danger state voice prompting module, a danger riding state storage library, the control database and an emergency braking processing end;
the elevator operation control terminal setting module is used for setting a human body infrared sensor and an infrared thermal imager in a pre-boarding area of the elevator, numbering all steps on the escalator according to a preset sequence, and setting intelligent cameras, voice prompters and weight sensors on all the steps, wherein the number of the steps is 1,2.
The elevator running speed regulating module is used for sensing a human body by a human body infrared sensor at an elevator pre-landing area, converting the running state of the escalator from an energy-saving state to a normal running state when the human body infrared sensor senses that the human body approaches, collecting a thermal image at the elevator pre-landing area by an infrared thermal imager at the elevator pre-landing area, further separating personnel gathering density at the elevator pre-landing area from the thermal image, and matching the personnel gathering density with elevator running speeds corresponding to various personnel gathering densities stored in a control database, so that the elevator running speed corresponding to the personnel gathering density is obtained, and the current elevator running speed is regulated and controlled to be in accordance with the elevator running speed corresponding to the personnel gathering density;
the elevator riding overload monitoring and prompting module is used for acquiring the actual bearing weight of the corresponding step by the weight sensor on each step after the escalator normally runs, comparing the actual bearing weight of each step with the nuclear load capacity of a single step stored in the control database, recording the step as an overload step if the actual bearing weight of a certain step is greater than the nuclear load capacity of the single step, acquiring the step number, starting a voice prompter at the overload step based on the overload step number, and performing overload voice prompt;
the elevator riding main body identification module is used for acquiring a region environment image corresponding to each step by an intelligent camera at each step, analyzing whether a riding main body exists in the region environment image or not, and identifying the type of the elevator riding main body if the riding main body exists; the elevator riding main body type comprises a human body and an object, the step number of which the riding main body type is the human body and the step number of which the riding main body type is the object are obtained at the moment, and then regional environment images of which the riding main body type is the human body and which correspond to all steps form a human body regional environment image set;
the riding main body danger state analysis module is used for analyzing the danger state of each riding main body type to obtain a human body danger step number and an object danger step number, sending the human body danger step number and the object danger step number to the riding main body danger state voice prompt module, and sending the human body danger step number to the emergency brake processing end, wherein the riding main body danger state analysis module comprises a human body danger state analysis unit and an object danger state analysis unit;
the riding main body dangerous state voice prompt module is used for receiving the human body dangerous step number and the object dangerous step number sent by the riding main body dangerous state analysis module, and further starting a voice prompt at the corresponding step to perform corresponding voice prompt;
the dangerous riding state storage library is used for storing action characteristics corresponding to various dangerous riding behaviors;
the control database is used for storing the nuclear load capacity of a single step, the area of a pre-landing position of the elevator, the running speed of the elevator corresponding to the concentration density of various personnel, the step area of the single step, the danger coefficient range corresponding to various danger levels, the danger level corresponding to emergency braking operation, the danger influence factors corresponding to various contact part names, the reference value of the area of the elevator occupied by the human body and the reference value of the contact distance;
the emergency braking processing end is used for receiving the human body dangerous ladder serial numbers sent by the riding main body dangerous state analyzing module and further identifying the dangerous coefficients of dangerous riding behaviors corresponding to the human body dangerous ladders, so that the dangerous levels of the dangerous riding behaviors corresponding to the riding main body dangerous ladders are obtained, and the emergency braking operation is started.
Further, the specific method for analyzing the personnel gathering density at the pre-boarding area of the elevator from the thermal image is as follows:
a1, obtaining the number of people at the pre-boarding area of the elevator from a thermal image collected from a thermal infrared imager, and recording the number as n;
a2, extracting the area of the pre-climbing position of the elevator in the control database and recording the area as m 1 ；
a3, calculating the personnel gathering density at the elevator pre-landing area according to the personnel number at the elevator pre-landing area and the area of the elevator pre-landing area in the control database, wherein the specific calculation formula is as follows:
where p represents the people accumulation density at the pre-landing area of the elevator.
Further, the analysis manner of whether the riding subject corresponds to the analysis area environment image is as follows:
b1, performing region division on the environment images of each region to obtain environment images of each subregion, and performing gray scale integration processing on the environment images of each subregion to obtain a gray scale value of the environment images of each subregion;
and b2, comparing the gray values of the environment images of the sub-areas in the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are inconsistent, indicating that the riding main body exists in the environment images of the areas, and simultaneously acquiring the number of the corresponding step of the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are consistent, indicating that the riding main body does not exist in the environment images of the areas.
The human body dangerous state analyzing unit is further configured to extract human body riding action features of the regional environment images corresponding to each step stored in the human body regional environment image set, match the human body riding action features with action features corresponding to various dangerous riding actions stored in the dangerous riding state repository, indicate that a human body in the step regional environment has dangerous riding actions if matching of the human body riding action features corresponding to a certain step is successful, mark the step as a human body dangerous step, and acquire a number corresponding to the human body dangerous step.
Further, the object dangerous state analyzing unit is configured to extract the object placement state of the environment image of the region corresponding to each step stored in the object region environment image set, and the specific steps of the object dangerous state analyzing unit are as follows:
c1, marking the ladder with the riding main body type of an object as an object ladder, and acquiring the number of each object ladder, which can be marked as 1,2, a.
c2, extracting the area of the object ladder corresponding to each object ladder from the object region environment image set, comparing the area with the ladder area of a single ladder stored in the control database, calculating the ratio coefficient corresponding to each object ladder,the calculation formula is
Wherein epsilon p Expressed as the fractional coefficient, M, corresponding to the p-th object step p Expressed as the area of the object occupying the ladder corresponding to the p-th object ladder, M 2 ' step area expressed as a single step;
c3, comparing the proportion coefficient corresponding to each object step with a preset value, if the proportion coefficient corresponding to a certain object step is larger than the preset value, indicating that the object placed on the object step is in a dangerous placing state, and marking the step as the step of the object to be determined;
c4, identifying the human body contour of each step of the object to be determined, and analyzing whether a human body exists at the step corresponding to each step of the object to be determined; if a human body exists at a step corresponding to a certain undetermined object step, recording the undetermined object step as an object dangerous step, acquiring the object dangerous step number, if no human body exists at the step corresponding to the certain undetermined object step, scanning a similar step corresponding to the undetermined object step, performing human body contour recognition on each similar step, and if a human body can be recognized by a certain similar step, taking the similar step as an associated step of the undetermined object step, recording the associated step as an object dangerous step, and acquiring the object dangerous step number.
Further, the specific identification method for the risk coefficient for identifying the dangerous riding behavior corresponding to each human body dangerous step is as follows:
d1: extracting the regional environment image corresponding to each human body dangerous ladder from the human body regional environment image set based on the human body dangerous ladder serial number, and further obtaining the human body occupied ladder area from the regional environment image set, and recording the area as S f F is expressed as human hazard step number, f =1,2 f The area of the human body at the f-th human body dangerous ladder is represented;
d2: extracting the name of the contact part of the human body and the steps from the human body region environment image set based on the human body danger step number;
d3: human body extracted from human body region environment image set based on human body danger ladder numbering and ladder connectionThe distance from the contact point to the center of the step is denoted as the contact distance l f ，l f Expressed as the contact distance at the fth personal hazard step;
d4, matching the names of the human body and the contact part of the steps corresponding to each human body dangerous step with the dangerous influence factors corresponding to the names of various contact parts in the control database to obtain the dangerous influence factors corresponding to each human body dangerous step;
and d5, counting the danger coefficients of the dangerous riding behaviors of the main body corresponding to the dangerous riding steps of each human body based on the occupied ladder area, the contact distance and the dangerous influence factors of the human body corresponding to the dangerous steps of each human body.
Further, the risk coefficient calculation formula of the dangerous riding behavior of each human body ladder corresponding to the riding main body is specifically as follows:
wherein
The danger coefficient, s, expressed as the dangerous riding behavior of the corresponding riding main body at the f-th personal dangerous step 0 Expressed as the reference value of the area of the human body occupying the ladder, l 0 Expressed as a contact distance reference value, λ f Expressed as the corresponding risk impact factor at the fth individual human risk step.
Further, the specific identification method of the danger level of the dangerous riding behavior of each human body ladder corresponding to the riding main body is as follows: and comparing the danger coefficient of the dangerous riding behavior of the riding main body corresponding to each human body danger step with the danger coefficient range corresponding to various danger levels in the control database, thereby obtaining the danger level of the dangerous riding behavior of the riding main body corresponding to each human body danger step.
Further, the initiating emergency braking operation is specifically operative to: and matching the danger level of the dangerous riding behavior of each human body ladder corresponding to the riding main body with the danger level corresponding to emergency braking, and starting emergency braking operation if the danger level of the dangerous riding behavior of the riding main body corresponding to a certain human body ladder is successfully matched with the danger level corresponding to emergency braking.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
according to the elevator pre-climbing system, the human body infrared sensor and the thermal infrared imager at the elevator pre-climbing area sense the approach of a human body and acquire the thermal image at the elevator pre-climbing area, when the infrared sensor senses the approach of the human body, the elevator running state is changed from an energy-saving state to a normal running state, the number of people is acquired through the thermal image acquired by the thermal infrared imager at the elevator pre-climbing area, and then the number of people and the area of the elevator pre-climbing area are compared to calculate the current people gathering density, so that the current elevator running speed is regulated and controlled to be in accordance with the elevator running speed corresponding to the people gathering density. The invention improves the elevator running efficiency and passenger riding experience, and avoids the problem that the passenger experience is poor because the speed of the conventional handrail elevator is unchanged when the personnel gathering density is high;
the elevator riding main body type is identified through the intelligent cameras at each ladder position of the elevator, the riding state of each riding main body type is monitored according to the riding main body type, the dangerous condition of each riding main body is identified in time, and corresponding voice prompt is started; for example, when the riding main body is an object, the placing state of each object at each ladder of the elevator is identified, and then the corresponding voice prompt is carried out on the human body in the area where each object is located; when the type of the riding main body is a human body, the action characteristics of the human body when the elevator is taken are identified, the action characteristics of the human body when the elevator is taken are matched with the action characteristics corresponding to various dangerous riding behaviors stored in a dangerous riding state storage library, and if the action characteristics corresponding to a certain ladder are successfully matched, corresponding voice prompt is started, so that the safety of elevator operation is greatly improved, and potential safety hazards caused by lack of pertinence and lack of riding state monitoring of the riding main body of the current escalator are remedied to a certain extent;
according to the invention, the danger level corresponding to the danger coefficient of the human body step with dangerous behaviors is matched with the danger level corresponding to emergency braking, and if the matching is successful, the emergency braking operation is immediately carried out, so that the time error caused by the fact that a worker needs to react and then carry out the emergency braking operation due to the sudden occurrence of an emergency situation is avoided, the time delay existing in the emergency braking operation of the current escalator is solved, the safety reliability of the operation of the elevator and the solving effect of emergency situations are greatly improved, and the safety guarantee is provided for people to take the elevator in the future;
according to the invention, the weight sensors are arranged at the steps of the escalator so as to sense the actual bearing weight of each step of the escalator, the sensed actual bearing weight of each step is compared with the nuclear load weight of a single step stored in the control database, if the actual bearing weight of a certain step is greater than the nuclear load weight of the single step, the state is an overweight state, and then the overload voice prompt is carried out through the voice prompter at each step, the overload prompt of the escalator is carried out on the whole escalator, the overload prompt in the invention is carried out on each step, and is more targeted, so that the overload prompt is more accurate, and meanwhile, the potential safety hazard caused by overload of passengers is avoided to a great extent.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic diagram of the module connection according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the invention provides an elevator operation control management system based on artificial intelligence, which comprises an elevator operation control terminal setting module, an elevator operation speed regulation and control module, an elevator riding overload monitoring prompt module, an elevator riding main body identification module, a riding main body danger state analysis module, a riding main body danger state voice prompt module, a danger riding state storage library, a control database and an emergency braking processing terminal, wherein the elevator riding overload monitoring prompt module is used for monitoring the elevator riding, the elevator riding main body identification module is used for analyzing the elevator riding main body danger state;
the elevator operation control terminal is provided with a module which is respectively connected with an elevator operation speed regulation and control module, an elevator riding overload monitoring and prompting module, an elevator riding main body recognition module and a riding main body dangerous state voice prompting module, an elevator riding main body recognition module and a riding main body dangerous state analyzing module are connected, an elevator operation speed regulation and control module is connected with a control database, an elevator riding overload monitoring and prompting module is connected with a control database, and a riding main body dangerous state analyzing module is respectively connected with a riding main body dangerous state voice prompting module, a dangerous riding state storage library, a control database and an emergency braking processing end.
The elevator operation control terminal setting module is used for setting a human body infrared sensor and an infrared thermal imager in an elevator pre-landing area, numbering all steps existing on the escalator according to a preset sequence to be 1,2, a.
The elevator operation speed regulating and controlling module is used for sensing a human body by a human body infrared sensor at an elevator pre-landing area, converting the operation state of the escalator from an energy-saving state to a normal operation state when the human body infrared sensor senses that the human body approaches, collecting a thermal image at the elevator pre-landing area by an infrared thermal imager at the elevator pre-landing area, further separating personnel gathering density at the elevator pre-landing area from the thermal image, and matching the personnel gathering density with the elevator operation speed corresponding to various personnel gathering densities stored in a control database, thereby obtaining the elevator operation speed corresponding to the personnel gathering density, and regulating and controlling the current elevator operation speed to be in line with the elevator operation speed corresponding to the personnel gathering density.
The technical scheme is further optimized, the human body infrared sensor and the thermal infrared imager at the elevator pre-landing area sense the approach of a human body and collect thermal images at the elevator pre-landing area, when the infrared sensor senses the approach of the human body, the running state of the elevator is changed from an energy-saving state to a normal running state, the number of people is obtained through the thermal images collected by the thermal infrared imager at the elevator pre-landing area, and then the number of people and the area of the elevator pre-landing area are compared to calculate the current people gathering density, so that the current elevator running speed is regulated and controlled to be in accordance with the elevator running speed corresponding to the people gathering density. The invention improves the elevator running efficiency and passenger riding experience, and avoids the poor passenger experience caused by the unchanged speed of the conventional handrail elevator when the personnel gathering density is high.
The specific method for analyzing the personnel gathering density at the pre-boarding area of the elevator from the thermal image is as follows:
a1, obtaining the number of people at the pre-boarding area of the elevator from a thermal image collected from a thermal infrared imager, and recording the number as n;
a2, extracting the area of the pre-climbing position of the elevator in the control database and recording the area as m 1 ；
a3, calculating the personnel gathering density at the elevator pre-landing area according to the personnel number at the elevator pre-landing area and the area of the elevator pre-landing area in the control database, wherein the specific calculation formula is as follows:
where p represents the people accumulation density at the pre-landing area of the elevator.
The elevator riding overload monitoring and prompting module is used for acquiring the actual bearing weight of corresponding steps by the weight sensors on the steps after the escalator normally runs, comparing the actual bearing weight of each step with the single step nuclear load weight stored in the control database, recording the steps as overload steps if the actual bearing weight of a certain step is larger than the single step nuclear load weight, acquiring the step number, starting the voice prompter at the overload step based on the overload step number, and performing overload voice prompt.
In the embodiment, the weight sensors are arranged at the steps of the escalator so as to sense the actual bearing weight of each step of the escalator, the sensed actual bearing weight of each step is compared with the single step nuclear load weight stored in the control database, if the actual bearing weight of a certain step is greater than the single step nuclear load weight, the state is an overweight state, overload voice prompt is performed through the voice prompters at each step, the current overload prompt of the escalator is to perform overload prompt on the whole escalator, the overload prompt in the invention is to perform overload prompt at each step, and is more targeted, so that the overload prompt is more accurate, and meanwhile, the potential safety hazard caused by overload of passengers is avoided to a great extent.
The elevator riding main body identification module is used for acquiring a region environment image corresponding to each step by an intelligent camera at each step, analyzing whether a riding main body exists in the region environment image or not, and identifying the type of the elevator riding main body if the riding main body exists; the elevator riding main body type comprises a human body and an object, the step number of which the riding main body type is the human body and the step number of which the riding main body type is the object are obtained at the moment, and then the area environment images of which the riding main body type is the human body and corresponding to all steps form a human body area environment image set, and the area environment images of which the riding main body type is the object and corresponding to all steps form an object area environment image set.
The analysis method for analyzing whether the riding subject corresponds to the area environment image includes:
b1, performing region division on the environment images of each region to obtain environment images of each subregion, and performing gray scale integration processing on the environment images of each subregion to obtain a gray scale value of the environment images of each subregion;
and b2, comparing the gray values of the environment images of the sub-areas in the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are inconsistent, indicating that the riding main body exists in the environment images of the areas, and simultaneously acquiring the number of the corresponding step of the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are consistent, indicating that the riding main body does not exist in the environment images of the areas.
In the embodiment, the type of the elevator riding main body is identified through the intelligent cameras at each step of the elevator, the riding state of each riding main body type is monitored according to the riding main body type, the dangerous condition of each riding main body is identified in time, and corresponding voice prompt is started; for example, when the riding main body is an object, the placing state of each object at each ladder of the elevator is identified, and then the corresponding voice prompt is carried out on the human body in the area where each object is located; when the type of the taking main body is a human body, the action characteristics of the human body when the elevator is taken are identified, the action characteristics of the human body when the elevator is taken are matched with the action characteristics corresponding to various dangerous taking actions stored in a dangerous taking state storage library, and if the action characteristics corresponding to a certain ladder are successfully matched, corresponding voice prompt is started.
The riding main body danger state analysis module is used for analyzing the danger state of each riding main body type to obtain a human body danger step number and an object danger step number, sending the human body danger step number and the object danger step number to the riding main body danger state voice prompt module, and sending the human body danger step number to the emergency brake processing end, wherein the riding main body danger state analysis module comprises a human body danger state analysis unit and an object danger state analysis unit;
the human body dangerous state analysis unit is used for extracting human body riding action characteristics of the regional environment images corresponding to the steps stored in the human body regional environment image set, matching the human body riding action characteristics with action characteristics corresponding to various dangerous riding actions stored in the dangerous riding state storage library, if matching of the human body riding action characteristics corresponding to a certain step is successful, indicating that the human body in the step regional environment has dangerous riding actions, marking the step as a human body dangerous step, and acquiring a number corresponding to the human body dangerous step.
In this embodiment, human riding motion features are extracted from the environment images of the corresponding regions of each step stored in the human body region environment image set, and a specific extraction method for the human riding motion features is as follows: and focusing and amplifying the environment images of the corresponding regions of the steps stored in the human body region environment image set to extract sub-images of all parts of the human body, capturing the shape and position characteristics of the extracted sub-images of all parts of the human body, and simultaneously measuring and acquiring the position change characteristics and the distance from each step of the sub-images of all parts of the human body to serve as the characteristics for identifying the riding action of the human body.
The object dangerous state analysis unit is used for extracting the object placing state of the environment image of each step corresponding area stored in the object area environment image set, and the corresponding specific steps are as follows:
c1, marking the ladder with the riding main body type of an object as an object ladder, and acquiring the number of each object ladder, which can be marked as 1,2, a.
c2, extracting the object occupying area corresponding to each object step from the object region environment image set, comparing the object occupying area with the step area of a single step stored in the control database, and calculating the occupying ratio coefficient corresponding to each object step, wherein the calculation formula is
Wherein epsilon p Expressed as the fractional coefficient, M, corresponding to the p-th object step p Expressed as the area of the object occupying the ladder corresponding to the p-th object ladder, M 2 ' step area expressed as a single step;
c3, comparing the proportion coefficient corresponding to each object step with a preset value, if the proportion coefficient corresponding to a certain object step is larger than the preset value, indicating that the object placed on the object step is in a dangerous placing state, and marking the step as the step of the object to be determined;
c4, identifying the human body contour of each step of the object to be determined, and analyzing whether a human body exists at the step corresponding to each step of the object to be determined; if a human body exists at a step corresponding to a certain undetermined object step, recording the undetermined object step as an object dangerous step, acquiring the object dangerous step number, if no human body exists at the step corresponding to the certain undetermined object step, scanning a similar step corresponding to the undetermined object step, performing human body contour recognition on each similar step, and if a human body can be recognized by a certain similar step, taking the similar step as an associated step of the undetermined object step, recording the associated step as an object dangerous step, and acquiring the object dangerous step number.
The riding main body dangerous state voice prompt module is used for receiving the human body dangerous step number and the object dangerous step number sent by the riding main body dangerous state analysis module, and further starting a voice prompt at the corresponding step to perform corresponding voice prompt;
it should be noted that, the voice prompter at the corresponding step is started to perform corresponding voice prompt, specifically, the voice prompter at the dangerous step based on the human body performs human body dangerous voice prompt and the voice prompter at the dangerous step based on the object performs object dangerous voice prompt.
The dangerous riding state storage library is used for storing action characteristics corresponding to various dangerous riding behaviors;
it should be noted that various dangerous ride activities include playing in elevators, leaning on handrails, crossing multiple elevator levels between legs, climbing in elevators, etc.
The control database is used for storing the nuclear load capacity of a single step, the area of the pre-landing position of the elevator, the running speed of the elevator corresponding to the concentration density of various personnel, the step area of the single step, the danger coefficient range corresponding to various danger levels, the danger level corresponding to emergency braking operation, the danger influence factors corresponding to various contact part names, the reference value of the area of the human body occupying the step and the reference value of the contact distance.
The emergency braking processing end is used for receiving the human body dangerous ladder serial numbers sent by the riding main body dangerous state analyzing module and further identifying the dangerous coefficients of dangerous riding behaviors corresponding to the human body dangerous ladders, so that the dangerous levels of the dangerous riding behaviors corresponding to the riding main body dangerous ladders are obtained, and the emergency braking operation is started.
Further optimize this technical scheme, the danger level that the human ladder department danger coefficient that will have dangerous behavior corresponds matches with the danger level that emergency braking corresponds, if match successfully, then carry out emergency braking operation immediately, avoided taking place suddenly because of emergency, the staff need react the time error that the back is carried out emergency braking operation again and is caused, the time delay that current handrail elevator exists has been solved, the fail safe nature of elevator operation and emergency's solution is greatly improved, the elevator is taken in the people in the future and the safety guarantee is provided.
In this embodiment, a method for specifically identifying a risk coefficient of a dangerous riding behavior corresponding to each human body dangerous step is as follows:
d1: extracting the regional environment image corresponding to each human body dangerous ladder from the human body regional environment image set based on the human body dangerous ladder serial number, and further obtaining the human body occupied ladder area from the regional environment image set, and recording the area as S f F is expressed as human hazard step number, f =1,2 f The area of the human body at the f-th human body dangerous ladder is represented;
d2: extracting the name of the contact part of the human body and the steps from the human body region environment image set based on the human body danger step number;
it should be noted that the names of the contact portions between the human body and the steps include: buttocks, hands, legs, feet, waist, back, etc.;
d3: extracting the distance from the human body to the step center position from the human body region environment image set based on the human body dangerous step serial number, and recording the distance as the contact distance l f ，l f Expressed as the contact distance at the fth personal hazard step;
d4, matching the names of the human body and the contact part of the steps corresponding to each human body dangerous step with the dangerous influence factors corresponding to the names of the various contact parts in the control database to obtain the dangerous influence factors corresponding to each human body dangerous step;
d5, counting the danger coefficients of dangerous riding behaviors of the main body corresponding to each human body dangerous step based on the human body occupied step area, the contact distance and the dangerous influence factor corresponding to each human body dangerous step;
in this embodiment, the risk coefficient calculation formula of each human body risk step corresponding to the dangerous riding behavior of the riding subject is specifically as follows:
wherein
The danger coefficient, s, expressed as the dangerous riding behavior of the corresponding riding main body at the f-th personal dangerous step 0 Expressed as the reference value of the area of the human body occupying the ladder, l 0 Expressed as a contact distance reference value, λ f Expressed as the corresponding risk impact factor at the fth human risk step.
The specific identification method of the danger level of each human body danger step corresponding to the dangerous riding behavior of the riding main body comprises the following steps: and comparing the danger coefficient of the dangerous riding behavior of the riding main body corresponding to each human body danger step with the danger coefficient range corresponding to various danger levels in the control database, thereby obtaining the danger level of the dangerous riding behavior of the riding main body corresponding to each human body danger step.
The operation of starting the emergency braking operation is specifically as follows: and matching the danger level of the dangerous riding behavior of each human body ladder corresponding to the riding main body with the danger level corresponding to emergency braking, and starting emergency braking operation if the danger level of the dangerous riding behavior of the riding main body corresponding to a certain human body ladder is successfully matched with the danger level corresponding to emergency braking.
Further optimize this technical scheme, the danger level that the human body ladder department danger coefficient that will have dangerous behavior corresponds matches with the danger level that emergency braking corresponds, if match successfully, then carry out emergency braking operation immediately, avoided taking place suddenly because of emergency, the staff need react the time error that the back again caused by emergency braking operation, the time delay of current handrail elevator emergency braking operation existence has been solved, the fail safe nature of elevator operation and emergency's solution effect have been improved greatly, the elevator is taken to the people in the future and the safety guarantee is provided.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (7)
1. An elevator operation control management system based on artificial intelligence is characterized by comprising an elevator operation control terminal setting module, an elevator operation speed regulating and controlling module, an elevator riding overload monitoring and prompting module, an elevator riding main body recognition module, a riding main body danger state analyzing module, a riding main body danger state voice prompting module, a danger riding state storage library, a control database and an emergency braking processing end;
the elevator operation control terminal setting module is respectively connected with an elevator operation speed regulating module, an elevator riding overload monitoring prompting module, an elevator riding main body recognition module and a riding main body danger state voice prompting module, the elevator riding main body recognition module is connected with a riding main body danger state analyzing module, the elevator operation speed regulating module is connected with a control database, the elevator riding overload monitoring prompting module is connected with the control database, and the riding main body danger state analyzing module is respectively connected with the riding main body danger state voice prompting module, a danger riding state storage library, the control database and an emergency braking processing end;
the elevator operation control terminal setting module is used for setting a human body infrared sensor and an infrared thermal imager in an elevator pre-boarding area, numbering all steps existing on the escalator according to a preset sequence to be 1,2, a.
The elevator running speed regulating module is used for sensing a human body by a human body infrared sensor at an elevator pre-landing area, converting the running state of the escalator from an energy-saving state to a normal running state when the human body infrared sensor senses that the human body approaches, collecting a thermal image at the elevator pre-landing area by an infrared thermal imager at the elevator pre-landing area, further separating personnel gathering density at the elevator pre-landing area from the thermal image, and matching the personnel gathering density with elevator running speeds corresponding to various personnel gathering densities stored in a control database, so that the elevator running speed corresponding to the personnel gathering density is obtained, and the current elevator running speed is regulated and controlled to be in accordance with the elevator running speed corresponding to the personnel gathering density;
the elevator riding overload monitoring and prompting module is used for acquiring the actual bearing weight of the corresponding step by the weight sensor on each step after the escalator normally runs, comparing the actual bearing weight of each step with the nuclear load capacity of a single step stored in the control database, recording the step as an overload step if the actual bearing weight of a certain step is greater than the nuclear load capacity of the single step, acquiring the step number, starting a voice prompter at the overload step based on the overload step number, and performing overload voice prompt;
the elevator riding main body identification module is used for acquiring area environment images corresponding to all steps by the intelligent cameras at all steps, analyzing whether a riding main body exists in the area environment images or not, and identifying the type of the elevator riding main body if the riding main body exists; the elevator riding main body type comprises a human body and an object, the step number of which the riding main body type is the human body and the step number of which the riding main body type is the object are obtained, then the area environment images of which the riding main body type is the human body corresponding to all steps form a human body area environment image set, and the area environment images of which the riding main body type is the object corresponding to all steps form an object area environment image set;
the riding main body danger state analysis module is used for analyzing the danger states of all riding main body types to obtain human body danger step numbers and object danger step numbers, sending the human body danger step numbers and the object danger step numbers to the riding main body danger state voice prompt module, and sending the human body danger step numbers to the emergency brake processing end, wherein the riding main body danger state analysis module comprises a human body danger state analysis unit and an object danger state analysis unit;
the riding main body dangerous state voice prompt module is used for receiving the human body dangerous step number and the object dangerous step number sent by the riding main body dangerous state analysis module, and further starting a voice prompt at the corresponding step to perform corresponding voice prompt;
the dangerous riding state storage library is used for storing action characteristics corresponding to various dangerous riding behaviors;
the control database is used for storing the nuclear load capacity of a single step, the area of a pre-landing position of the elevator, the running speed of the elevator corresponding to the concentration density of various personnel, the step area of the single step, the danger coefficient range corresponding to various danger levels, the danger level corresponding to emergency braking operation, the danger influence factors corresponding to various contact part names, the reference value of the area of the elevator occupied by the human body and the reference value of the contact distance;
the emergency braking processing end is used for receiving the human body dangerous step numbers sent by the riding main body dangerous state analysis module and further identifying the dangerous coefficients of dangerous riding behaviors corresponding to the human body dangerous steps, so that the dangerous levels of the dangerous riding behaviors corresponding to the riding main body dangerous riding behaviors of the human body dangerous steps are obtained, and the emergency braking operation is started;
the specific identification method for the danger coefficients for identifying dangerous riding behaviors corresponding to the dangerous steps of the human body comprises the following steps of:
d1: extracting the region environment image corresponding to each human body danger ladder from the human body region environment image set based on the human body danger ladder serial number, and further acquiring the human body ladder occupying area from the region environment image set, and recording the area as S f F is expressed as human hazard step number, f =1,2 f The area of the human body at the f-th human body dangerous ladder is represented;
d2: extracting the name of the contact part of the human body and the steps from the human body region environment image set based on the human body danger step number;
d3: extracting the distance from the human body to the step center position from the human body region environment image set based on the human body danger step serial number, and extracting the distance from the human body to the step center positionIs expressed as a contact distance l f ，l f Expressed as the contact distance at the fth personal hazard step;
d4, matching the names of the human body and the contact part of the steps corresponding to each human body dangerous step with the dangerous influence factors corresponding to the names of the various contact parts in the control database to obtain the dangerous influence factors corresponding to each human body dangerous step;
d5, counting the danger coefficients of dangerous riding behaviors of the main body corresponding to each human body dangerous step based on the human body occupied step area, the contact distance and the dangerous influence factor corresponding to each human body dangerous step;
the risk coefficient calculation formula of the dangerous riding behavior of the riding main body corresponding to each human body danger step is specifically as follows:
wherein
The danger coefficient, s, expressed as the dangerous riding behavior of the corresponding riding main body at the f-th personal dangerous step 0 Expressed as the reference value of the area of the human body occupying the ladder, l 0 Expressed as a contact distance reference value, λ f Expressed as the corresponding risk impact factor at the fth human risk step.
2. The artificial intelligence based elevator operation control management system according to claim 1, wherein: the specific method for analyzing the personnel gathering density at the elevator pre-landing area from the thermal image comprises the following steps:
a1, obtaining the number of people at the pre-boarding area of the elevator from a thermal image collected from a thermal infrared imager, and recording the number as n;
a2, extracting the area of the pre-climbing position of the elevator in the control database and recording the area as m 1 ；
a3, calculating the personnel gathering density at the elevator pre-landing area according to the personnel number at the elevator pre-landing area and the area of the elevator pre-landing area in the control database, wherein the specific calculation formula is as follows:
where p represents the people accumulation density at the pre-landing area of the elevator.
3. The artificial intelligence based elevator operation control management system according to claim 1, wherein: whether the analysis mode corresponding to the riding main body exists in the analysis area environment image is as follows:
b1, performing region division on the environment images of each region to obtain environment images of each subregion, and performing gray scale integration on the environment images of each subregion to obtain a gray scale value of the environment images of each subregion;
and b2, comparing the gray values of the environment images of the sub-areas in the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are inconsistent, indicating that the riding main body exists in the environment images of the areas, and simultaneously acquiring the number of the corresponding step of the environment images of the areas, if the gray values of the environment images of the sub-areas in the environment images of the areas are consistent, indicating that the riding main body does not exist in the environment images of the areas.
4. The artificial intelligence based elevator operation control management system according to claim 1, wherein: the human body dangerous state analysis unit is used for extracting human body riding action characteristics of the regional environment images corresponding to the steps stored in the human body regional environment image set, matching the human body riding action characteristics with action characteristics corresponding to various dangerous riding actions stored in the dangerous riding state storage library, if matching of the human body riding action characteristics corresponding to a certain step is successful, indicating that dangerous riding actions exist in the human body of the regional environment of the step, marking the step as a human body dangerous step, and acquiring a number corresponding to the human body dangerous step.
5. The artificial intelligence based elevator operation control management system according to claim 1, wherein: the object dangerous state analysis unit is used for extracting the object placing state of the environment image of the corresponding region of each ladder stored in the object region environment image set, and the corresponding specific steps are as follows:
c1, marking the ladder with the riding body type of an object as an object ladder, and acquiring the number of each object ladder, which can be marked as 1,2., p., k;
c2, extracting the area of the object ladder corresponding to each object ladder from the object region environment image set, comparing the area with the ladder area of a single ladder stored in the control database, and calculating the proportion coefficient corresponding to each object ladder, wherein the calculation formula is
Wherein epsilon p Expressed as the fractional coefficient, M, corresponding to the p-th object step p Expressed as the area of the object occupying the ladder corresponding to the p-th object ladder, M 2 ' step area expressed as a single step;
c3, comparing the proportion coefficient corresponding to each object step with a preset value, if the proportion coefficient corresponding to a certain object step is larger than the preset value, indicating that the object placed on the object step is in a dangerous placing state, and marking the step as the step of the object to be determined;
c4, identifying the human body contour of each step of the object to be determined, and analyzing whether a human body exists at the step corresponding to each step of the object to be determined; if a human body exists at a step corresponding to a certain undetermined object step, recording the undetermined object step as an object dangerous step, acquiring the object dangerous step number, if no human body exists at the step corresponding to the certain undetermined object step, scanning a similar step corresponding to the undetermined object step, performing human body contour recognition on each similar step, and if a human body can be recognized by a certain similar step, taking the similar step as an associated step of the undetermined object step, recording the associated step as an object dangerous step, and acquiring the object dangerous step number.
6. The artificial intelligence based elevator operation control management system according to claim 1, wherein: the specific identification method of the danger level of each human body danger step corresponding to the dangerous riding behavior of the riding main body comprises the following steps: and comparing the danger coefficient of the dangerous riding behavior of the riding main body corresponding to each human body danger step with the danger coefficient range corresponding to various danger levels in the control database, thereby obtaining the danger level of the dangerous riding behavior of the riding main body corresponding to each human body danger step.
7. The artificial intelligence based elevator operation control management system according to claim 1, wherein: the operation of starting the emergency braking operation is specifically as follows: and matching the danger level of the dangerous riding behavior of each human body ladder corresponding to the riding main body with the danger level corresponding to emergency braking, and starting emergency braking operation if the danger level of the dangerous riding behavior of the riding main body corresponding to a certain human body ladder is successfully matched with the danger level corresponding to emergency braking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210431371.XA CN114590690B (en) | 2022-04-22 | 2022-04-22 | Elevator operation control management system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210431371.XA CN114590690B (en) | 2022-04-22 | 2022-04-22 | Elevator operation control management system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114590690A CN114590690A (en) | 2022-06-07 |
| CN114590690B true CN114590690B (en) | 2023-01-06 |
Family
ID=81820546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210431371.XA Active CN114590690B (en) | 2022-04-22 | 2022-04-22 | Elevator operation control management system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114590690B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434145B (en) * | 2023-04-21 | 2024-04-16 | 北京日立电梯工程有限公司 | Escalator passenger dangerous behavior analysis and monitoring system based on image recognition |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203865811U (en) * | 2014-04-22 | 2014-10-08 | 贵州天义电梯成套设备有限公司 | Load control device for escalator |
| CN210393378U (en) * | 2019-06-06 | 2020-04-24 | 快意电梯股份有限公司 | Automatic staircase safety arrangement based on AI intelligent monitoring |
| CN111573489A (en) * | 2020-05-27 | 2020-08-25 | 永康龙飘传感科技有限公司 | Step elevator capable of measuring loads of all steps |
| CN111646352A (en) * | 2020-07-17 | 2020-09-11 | 陈明亮 | Elevator safety operation monitoring management system based on machine vision |
| CN112794197B (en) * | 2020-12-28 | 2022-03-15 | 广州地铁设计研究院股份有限公司 | Rail transit escalator control system and method |
-
2022
- 2022-04-22 CN CN202210431371.XA patent/CN114590690B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114590690A (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764190B (en) | Video monitoring method for off-bed and on-bed states of old people | |
| CN114590690B (en) | Elevator operation control management system based on artificial intelligence | |
| CN109573772B (en) | General elevator health degree evaluation system | |
| CN108509897A (en) | A kind of human posture recognition method and system | |
| CN110481606B (en) | Subway passenger flow guiding system and method based on visual identification technology | |
| JP2013173595A (en) | Elevator arrival time estimating device and elevator system | |
| CN113391239B (en) | Mutual inductor anomaly monitoring method and system based on edge calculation | |
| CN113401760A (en) | Elevator operation fault supervision system based on big data | |
| CN111646352A (en) | Elevator safety operation monitoring management system based on machine vision | |
| CN108750899A (en) | Staircase automatic emergency stop device and its control method | |
| CN113015122B (en) | Assembly type building quality monitoring and analyzing method based on Internet of things and wireless sensor technology | |
| CN117133110B (en) | Gymnasium safety risk early warning method and system based on machine vision | |
| CN116434145B (en) | Escalator passenger dangerous behavior analysis and monitoring system based on image recognition | |
| CN112408135B (en) | Equipment data exception management method based on remote monitoring | |
| CN109052098A (en) | Lift car overload detecting method based on image procossing | |
| CN115618973B (en) | Transformer substation operation monitoring anti-error analysis processing system based on centralized control station | |
| CN115410113A (en) | Fall detection method and device based on computer vision and storage medium | |
| CN116433029A (en) | Power operation risk assessment method, system, equipment and storage medium | |
| CN111591846B (en) | Method, device and system for managing sitting and falling ladder behaviors | |
| CN116969284B (en) | Elevator remote control management system and method | |
| CN113800348B (en) | Intelligent community elevator management system | |
| CN115192004A (en) | Intelligent monitoring system for falling of old people | |
| CN114998828B (en) | Offshore platform personnel stair ascending and descending management method based on Internet of things platform | |
| CN214269876U (en) | Escalator safety monitoring system based on sensor | |
| CN112347939B (en) | Ladder-taking non-civilized key identification method based on multi-dimensional features |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221221 Address after: Room 1708, Building 3, Phase II, Sunshine Yuehai Garden, No. 3818, Baishi Road, Yuegui Community, Yuehai Street, Nanshan District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Fengfan Information Technology Co.,Ltd. Address before: 430030 No. 457, Jianshe Avenue, Qiaokou District, Wuhan City, Hubei Province Applicant before: Wuhan yijiecheng Digital Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |