An elevator group control method and system

Abstract

The present invention discloses an elevator group control method and system, which proposes an elevator group control method and system, obtains the elevator physical characteristics and passenger up-and-down behavior characteristics of the elevators to be controlled in the target building in the previous cycle, and constructs a non-linear dynamic mathematical model; obtains the passenger flow data of the elevators to be controlled in the target building in the previous cycle, and combines machine learning algorithms and recursive least squares method to establish a passenger flow prediction model considering system time delay; through the model predictive controller, combines the non-linear dynamic mathematical model and the passenger flow prediction model, predicts the states and outputs at multiple future moments, and combines the preset control objective function and constraint conditions to formulate an optimal control action sequence; according to the calculated optimal control action sequence, sends specific control instructions to each elevator, enables the elevator to operate according to the predetermined plan, and completes the update of the elevator group control method.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator group control, and particularly to an elevator group control method and system. Background Art

[0002] In modern buildings and urban infrastructure, elevators, as an important part of vertical transportation, their operating efficiency, safety, and passenger comfort are the key indicators for measuring the performance of elevator systems. With the continuous increase of high-rise buildings and the development of the intelligent trend, the control of a single elevator can no longer meet the efficient and personalized transportation needs of large commercial complexes, super high-rise residential buildings, or office buildings. Therefore, elevator group control systems have emerged.

[0003] Traditional single elevator control systems mainly focus on the scheduling and service of a single elevator, while elevator group control integrates multiple elevators and conducts unified management and optimal scheduling to maximize the overall performance. This technology involves complex data analysis, prediction algorithms, and an efficient communication network, which can obtain the status information of each elevator in real time (such as position, load, destination requests, etc.), and dynamically generate the optimal scheduling strategy based on this data. Provide a fast response channel for special groups or emergency situations to ensure the safe evacuation ability of the building.

[0004] However, existing elevator group control technologies still face a series of challenges, including how to process massive real-time data, design more advanced intelligent scheduling algorithms to cope with complex changes in floor traffic flow patterns, and improve the stability and reliability of the system while ensuring service quality. Summary of the Invention

[0005] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title, and such simplifications or omissions shall not be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides an elevator group control method and system, which can solve the problems mentioned in the background art.

[0008] To solve the above technical problems, the present invention provides the following technical solution. An elevator group control method includes:

[0009] Obtain the elevator physical characteristics and the passenger up and down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, and construct a non-linear dynamic mathematical model, wherein the elevator control method used in the previous cycle of the elevator is any existing control method;

[0010] Obtain the passenger flow data of the elevators to be controlled in the target building in the previous cycle, and establish a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method;

[0011] Through the model predictive controller, combine the non-linear dynamic mathematical model and the passenger flow prediction model, predict the states and outputs at multiple future moments, and formulate an optimal control action sequence by combining a preset control objective function and constraint conditions;

[0012] According to the calculated optimal control action sequence, send specific control instructions to each elevator, make the elevator operate according to the predetermined plan, and complete the update of the elevator group control method.

[0013] As a preferred solution of the elevator group control method described in the present invention, wherein: obtain the elevator physical characteristics and passenger up and down behavior characteristics in the previous cycle of the elevators to be controlled in the target building, and construct a non-linear dynamic mathematical model, and the elevator control method used in the previous cycle of the elevator is any existing control method, including:

[0014] The elevator physical characteristics at least include the elevator floor z(t), elevator speed v(t), passenger capacity, and the movement of the passenger car C(t), where t represents the elevator operation time;

[0015] The passenger up and down behavior characteristics at least include the passenger entry and exit conditions on each floor;

[0016] The non-linear dynamic mathematical model includes an elevator position change equation and a passenger capacity change equation:

[0017] The elevator position change equation is expressed as:

[0018]

[0019] Where m is the total mass of the elevator and passengers, T e is the traction force provided by the traction motor, which is related to the elevator position, speed, and passenger capacity, F f is the friction force related to the elevator speed and passenger capacity, which increases with the increase of speed and passenger capacity, F d is the damping force considering the influence of personnel changes, which is related to the elevator speed and personnel distribution, and u(t) represents the force of the current control signal acting on the elevator system, represents the acceleration of the elevator car;

[0020] The passenger capacity change equation is expressed as:

[0021]

[0022] Where Pin (t, z(t)) and P out (t, z(t)) respectively represent the number of passengers entering and leaving the elevator on floor z(t) at time t.

[0023] As a preferred solution of the elevator group control method described in the present invention, wherein: obtaining the elevator physical characteristics and the passenger up and down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, constructing a non-linear dynamic mathematical model, and the elevator control method used in the previous cycle of the elevator is any existing control method, further including: estimating the unknown parameters or function forms in the model according to the actual data combined with the system identification technology;

[0024] The traction force T e Is estimated according to the elevator traction characteristics and the passenger capacity, and the estimation formula is as follows:

[0025] T e (z(t), v(t), C(t)) = k t z(t) + c v v(t) + k c C(t)

[0026] The frictional force F f The estimation formula is as follows:

[0027] F i (z(t), v(t), C(t)) = μ i (m1 + C(t)k p )v(t)

[0028] The damping force F d The estimation formula is as follows:

[0029] F d (z(t), v(t), C(t)) = k d v(t) + k c ′C(t)v(t)

[0030] Wherein, m1 represents the inherent mass of the elevator, k t Represents the correlation coefficient between the traction force and the elevator position, c v Represents the correlation coefficient between the traction force and the elevator speed, k c Represents the correlation coefficient between the traction force and the passenger capacity, μ i Represents the friction coefficient, that is, the resistance characteristics of the internal and external environments of the system, k p Represents the influence coefficient of the unit passenger capacity on the friction force increment, reflecting the additional friction force brought by the increase in the number of passengers, k d Represents the damping coefficient linearly related to the elevator speed, k c ′ Represents the damping coefficient related to the passenger capacity and speed.

[0031] As a preferred solution of the elevator group control method described in the present invention, wherein: the step of obtaining the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and establishing a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method includes:

[0032] First, establish a preliminary prediction model using machine learning algorithms. Select a machine learning method using time series data, and its prediction model is expressed as:

[0033] P pred (t + 1) = LSTM(P(t), P(t - 1),..., P(t - n))

[0034] where P(t) is the passenger flow at time t, n is the length of the historical window, and LSTM is a trained long short-term memory network model;

[0035] Secondly, considering the system time delay factor, if there is a time delay effect in the system, introduce a time delay variable to improve the model. The improved model is expressed as:

[0036] P pred (t + τ) = F(LSTM(P(t), P(t - 1),..., P(t - n)), τ)

[0037] where τ is the time delay parameter of the system, and F is a function that corrects the prediction result by combining time delay information;

[0038] Thirdly, use the recursive least squares method for parameter update:

[0039] Initialize the model parameter θ;

[0040] For each time step t, update the model parameter θ according to the actually observed passenger flow data P obs (t + τ):

[0041]

[0042] Finally, embed the passenger flow prediction model into the non-linear dynamic mathematical model.

[0043] As a preferred solution of the elevator group control method described in the present invention, wherein: the step of predicting the states and outputs at multiple future moments by combining the non-linear dynamic mathematical model and the passenger flow prediction model through a model predictive controller, and formulating an optimal control action sequence by combining a preset control objective function and constraint conditions includes:

[0044] Assume that there are multiple elevators E1, E2,.., E among the elevators to be controlled in the target building MIn serving the passenger requests on multiple floors F1, F2, ..., F N the preset control objective function is expressed as:

[0045]

[0046] where w 1i is the weight factor for the average waiting time of passengers of elevator E i and w 2i is the weight factor for the energy consumption of elevator E i ; denotes the average waiting time of passengers on floor F i served by elevator E j at the t-th moment within the prediction horizon, and E i (t) represents the energy consumed by elevator E i at the t-th moment within the prediction horizon, S i (k) is the state vector of elevator E i at the t-th moment, and the state vector includes at least the current position, speed, and passenger capacity information. U represents the penalty term, λ represents the penalty factor of this penalty term, and k represents the time step.

[0047] As a preferred solution of the elevator group control method described in the present invention, wherein: the step of predicting the states and outputs at multiple future moments by the model predictive controller in combination with the non-linear dynamic mathematical model and the passenger flow prediction model, and formulating the optimal control action sequence in combination with the preset control objective function and the constraint conditions further includes:

[0048] The constraint conditions include:

[0049] To prevent continuous stops at the same floor, a minimum floor stop interval constraint is established:

[0050] t stop ≤t i,j -t i,j-1 , j = 2, 3, ..., N i , i = 1, 2, .., M

[0051] where t i,j represents the time when elevator E i arrives at the j-th floor;

[0052] A response time constraint for the passenger call request is established:

[0053] t response ≤t j,arrival -t i,call i = 1, 2, ..., M

[0054] A system balance constraint is established:

[0055]

[0056] Among them, N f represents the total number of floors of the building, and P i,j (k) is the service demand of the elevator E i at the j-th floor at time k. The service demand includes at least the number of passengers and the number of service requests. P avg,j is the average service demand expected to be achieved by all elevators at the j-th floor. B is a set threshold for controlling the imbalance degree of the system.

[0057] As a preferred solution of the elevator group control method described in the present invention, among them: the constraint conditions further include:

[0058] Establish a priority constraint: The response priorities of elevators on the lowest three floors and the highest three floors are higher than those on any other floor;

[0059] To prevent multiple elevators from going to the same floor simultaneously, causing congestion or empty running, establish a cooperative scheduling constraint:

[0060]

[0061] Among them, M1 represents the number of elevator devices participating in cooperative scheduling, and T i,end (D d ) is the time point when the i-th d elevator device completes its current task within the scheduling period D a . T j,start (D d + 1) is the time when the j-th d device starts a new task in the immediately following scheduling period D b + 1. D min is the set minimum time interval threshold;

[0062] When multiple elevators are running in the same shaft, establish a safety distance constraint:

[0063]

[0064] Among them, represents the position of the elevator at time k, represents the position of the elevator at time k. M2 represents the number of elevator floors in the same shaft when multiple elevators are running in the same shaft, and h ij (k) represents the safety distance compensation value calculated based on the elevator length and the current position.

[0065] An elevator group control system, characterized in that it includes:

[0066] The first model establishment module is used to obtain the elevator physical characteristics and the passenger up-and-down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, and construct a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method.

[0067] The second model establishment module is used to obtain the passenger flow data in the previous cycle of the elevator to be controlled in the target building, and establish a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method.

[0068] The optimal sequence acquisition module is used to predict the states and outputs at multiple future moments through a model predictive controller in combination with the non-linear dynamic mathematical model and the passenger flow prediction model, and formulate an optimal control action sequence in combination with a preset control objective function and constraint conditions.

[0069] The operation and update module is used to send specific control instructions to each elevator according to the calculated optimal control action sequence, make the elevator operate according to a predetermined plan, and complete the update of the elevator group control method.

[0070] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the method described above are implemented.

[0071] A computer-readable storage medium stores a computer program. It is characterized in that when the computer program is executed by a processor, the steps of the method described above are implemented.

[0072] The beneficial effects of the present invention: The present invention provides an elevator group control method and system, which obtains the elevator physical characteristics and the passenger up-and-down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, constructs a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method; obtains the passenger flow data in the previous cycle of the elevator to be controlled in the target building, and establishes a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method; predicts the states and outputs at multiple future moments through a model predictive controller in combination with the non-linear dynamic mathematical model and the passenger flow prediction model, and formulates an optimal control action sequence in combination with a preset control objective function and constraint conditions; sends specific control instructions to each elevator according to the calculated optimal control action sequence, makes the elevator operate according to a predetermined plan, and completes the update of the elevator group control method.

[0073] The elevator group control method and system provided by the present invention have the following advantages:

[0074] 1. Improve elevator operation efficiency: By constructing a nonlinear dynamic mathematical model and a passenger flow prediction model, the optimal scheduling of elevator clusters can be achieved, the passenger waiting time can be reduced, and the elevator operation efficiency can be improved.

[0075] 2. Improve passenger comfort: According to passenger flow forecast, reasonably allocate elevator passenger capacity to avoid elevator overload or empty load, and improve passenger comfort.

[0076] 3. Enhance system stability: Through the model predictive controller, the elevator operation strategy is adjusted in real time to ensure the stable operation of the elevator cluster in complex environments.

[0077] 4. Simplify operation and maintenance management: Through unified management and control of elevator clusters, the workload of operation and maintenance personnel can be simplified and the level of building management can be improved.

[0078] 5. Strong adaptability: The elevator cluster control method and system proposed in the present invention can be applied to buildings of different types and sizes and have wide adaptability.

[0079] The present invention not only provides a new technical solution for elevator cluster control, but also provides strong support for building automation management and intelligent development. As an intelligent control system, the elevator cluster control method and system have broad application prospects and market potential. With the continuous upgrading of building construction and management in the future, the present invention will bring significant economic and social benefits to the elevator industry and building automation field. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0081] Figure 1 A method flow chart of an elevator cluster control method and system provided by one embodiment of the present invention;

[0082] Figure 2 An internal structural diagram of a computer device of an elevator cluster control method and system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0083] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0084] Embodiment 1

[0085] Referring to Figure 1-2 , which is the first embodiment of the present invention. This embodiment provides an elevator group control method and system, including an elevator group control method and an elevator group control system. Among them, an elevator group control method includes:

[0086] S101: Obtain the elevator physical characteristics and passenger up and down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, and construct a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method;

[0087] Among them, obtaining the elevator physical characteristics and passenger up and down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, and constructing a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method includes:

[0088] Specifically, the elevator physical characteristics at least include the elevator floor z(t), elevator speed v(t), passenger capacity, and the movement of the passenger car C(t), where t represents the elevator operation time;

[0089] In an optional embodiment, the elevator physical characteristics may further include the number of elevator runs, elevator operation time, elevator load rate, etc.;

[0090] Furthermore, the passenger up and down behavior characteristics at least include the passenger entry and exit situations on each floor;

[0091] In an optional embodiment, the passenger up and down behavior characteristics may further include the number of times passengers go up and down, the time when passengers go up and down, passengers' riding habits, etc.

[0092] It should be noted that the previous cycle is at least greater than one month. In the embodiments of the present application, the cycle is set to three months;

[0093] In the embodiments of the present application, in order to make up for the three-month lead time, a digital twin model is established to obtain simulation data. In actual applications, in order to obtain accurate data, the digital twin modeling operation can be omitted, and directly obtain the elevator physical characteristics and passenger up and down behavior characteristics in the previous cycle of the elevator to be controlled in the target building, and construct a non-linear dynamic mathematical model;

[0094] It should be noted that the physical characteristics of the elevator to be controlled in the target building in the previous cycle and the behavior characteristics of the passengers going up and down the stairs can be obtained by establishing a mathematical twin model under response conditions based on the selected existing control method, and the data of the previous cycle can be obtained through the mathematical twin model. This allows the updated elevator cluster control method to be used in a timely manner after the elevator is established in the target building.

[0095] It should be noted that the steps for establishing a mathematical twin model for elevator cluster control can be as follows:

[0096] Step 1: Collect elevator physical property data: Collect the operating status information of elevators in at least three buildings of the same type as the target building, with the same personnel distribution and personnel functions, including but not limited to the current floor, speed, direction, load, fault status, maintenance records and other real-time or historical data. For example, if the target building is a shopping mall and the building height plus the basement is eight floors, then collect the operating status information of elevators in at least three shopping malls in the same area with eight floors plus the basement.

[0097] Collect passenger behavior data: statistics on the frequency of passengers entering and exiting the elevator, waiting time, destination floor distribution, peak hours, etc. on each floor during different time periods. Even more accurate passenger flow and route selection can be obtained through smart card systems or monitoring systems.

[0098] Step 2: Clean the collected data and remove invalid or abnormal data points.

[0099] Perform preprocessing operations such as normalization, binning, or time series analysis on the data according to analysis requirements.

[0100] Step three: extract key indicators reflecting elevator performance and characteristic variables of passenger behavior patterns from the original data, such as elevator utilization rate, average response time, passenger density distribution, etc.

[0101] The time windows and relevant features required to build a passenger demand forecasting model.

[0102] Step 4: Establish a physical model of the elevator system to simulate the actual operation process and physical constraints of the elevator.

[0103] Design a passenger behavior model, considering the behavioral patterns of passengers in different scenarios and their impact on elevator scheduling.

[0104] Step five, understand and combine the selected existing elevator control strategies (such as shortest path priority, minimum number of transfers, load balance, etc.), convert these strategies into mathematical expressions, and incorporate them into the twin model as decision rules.

[0105] Step 6: Use the real data from the previous cycle to drive the twin model, and repeatedly adjust the parameters and optimize the algorithm through the simulation platform, so that the model can accurately reflect the behavior of the actual elevator system under given conditions.

[0106] Utilize machine learning or deep learning techniques to further enhance the model's prediction and decision-making capabilities in unknown situations.

[0107] Step 7: Apply the trained and optimized mathematical twin model to the elevator cluster control of the next cycle, update the model parameters in real time, and dynamically adjust the control strategy to adapt to the changing environment and requirements.

[0108] Step 8: Obtain the data of the simulated first three months through the mathematical twin model.

[0109] It should be noted that establishing a digital twin model can greatly reduce the update time of control methods, and can also comprehensively improve the intelligent level and operation efficiency of elevator cluster management.

[0110] Furthermore, the non-linear dynamic mathematical model includes the elevator position change equation and the passenger capacity change equation:

[0111] Among them, the elevator position change equation is expressed as:

[0112]

[0113] Among them, m is the total mass of the elevator and passengers, T e is the traction force provided by the traction motor, which is related to the elevator position, speed and passenger capacity, F f is the frictional force related to the elevator speed and passenger capacity, which increases with the increase of speed and passenger capacity, F d is the damping force considering the influence of personnel changes, which is related to the elevator speed and personnel distribution, and u(t) represents the force exerted by the current control signal on the elevator system, represents the acceleration of the elevator car;

[0114] Furthermore, the passenger capacity change equation is expressed as:

[0115]

[0116] Among them, P in (t,z(t)) and P out (t,z(t)) respectively represent the number of passengers entering and leaving the elevator at floor z(t) at time t.

[0117] Further, obtain the elevator physical characteristics and passenger up-and-down behavior characteristics in the previous cycle of the target building's elevator to be controlled, and construct a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method, and it also includes: estimating unknown parameters or function forms in the model according to actual data combined with system identification technology;

[0118] Traction force T e Estimate according to the elevator traction characteristics and passenger capacity. The estimation formula is as follows:

[0119] T e (z(t), v(t), C(t)) = k t z(t) + c v v(t) + k c C(t)

[0120] Frictional force F f The estimation formula is as follows:

[0121] F i (z(t), v(t), C(t)) = μ i (m1 + C(t)k p )v(t)

[0122] Damping force F d The estimation formula is as follows:

[0123] F d (z(t), v(t), C(t)) = k d v(t) + k c ′C(t)v(t)

[0124] Among them, m1 represents the inherent mass of the elevator, k t represents the correlation coefficient between the traction force and the elevator position, c v represents the correlation coefficient between the traction force and the elevator speed, k c represents the correlation coefficient between the traction force and the passenger capacity, μ i represents the friction coefficient, that is, the resistance characteristics of the internal and external environments of the system, k p represents the influence coefficient of unit passenger capacity on the friction force increment, reflecting the additional friction force brought by the increase in the number of passengers, k d represents the damping coefficient linearly related to the elevator speed, k c ′ represents the damping coefficient related to the passenger capacity and speed.

[0125] It should be noted that the physical characteristics of the elevator to be controlled in the target building and the behavior characteristics of passengers going up and down the stairs in the previous cycle are obtained, and a non-linear dynamic mathematical model is constructed to describe the physical behavior and operation law of the elevator system, providing a basis for the subsequent formulation of control strategies. Considering the actual working characteristics of the elevator (such as speed, position, load, etc.) helps to accurately simulate the dynamic response of the elevator. Incorporating existing control methods into the model can evaluate the impact of the current control strategy on the performance of the elevator system and provide a basis for optimizing the control.

[0126] S102: Obtain the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and establish a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method;

[0127] Obtaining the passenger flow data of the elevator to be controlled in the target building in the previous cycle and establishing a passenger flow prediction model considering system time delay includes:

[0128] First, use machine learning algorithms to establish a preliminary prediction model. Select the machine learning method using time series data, and its prediction model is expressed as:

[0129] P pred (t + 1) = LSTM(P(t), P(t - 1),..., P(t - n))

[0130] Where P(t) is the passenger flow at time t, n is the length of the historical window, and LSTM is a trained long short-term memory network model;

[0131] Secondly, considering the system time delay factor, if there is a time delay effect in the system, then introduce a time delay variable to improve the model. The improved model is expressed as:

[0132] P pred (t + τ) = F(LSTM(P(t), P(t - 1),..., P(t - n)), τ)

[0133] Where τ is the time delay parameter of the system, and F is a function that corrects the prediction result by combining time delay information;

[0134] Thirdly, use the recursive least squares method for parameter update:

[0135] Initialize the model parameter θ;

[0136] For each time step t, update the model parameter θ according to the actually observed passenger flow data P obs (t + τ):

[0137]

[0138] Finally, embed the passenger flow prediction model into the nonlinear dynamic mathematical model.

[0139] It should be noted that obtaining the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and establishing a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method can predict the passenger entry and exit conditions of each floor in the future time period, make good elevator dispatching plans in advance, and reduce the passenger waiting time. By combining machine learning algorithms and recursive least squares method to handle the time delay problem, the accuracy and adaptability of the prediction model are improved. It has good prediction ability for the traffic peaks and valleys at different times, and can effectively cope with the passenger flow demand fluctuations at different time periods.

[0140] S103: Through the model predictive controller, combine the nonlinear dynamic mathematical model and the passenger flow prediction model, predict the states and outputs at multiple future moments, and combine the preset control objective function and constraint conditions to formulate an optimal control action sequence;

[0141] Through the model predictive controller, combine the nonlinear dynamic mathematical model and the passenger flow prediction model, predict the states and outputs at multiple future moments, and combine the preset control objective function and constraint conditions to formulate an optimal control action sequence, including:

[0142] Suppose there are multiple elevators E1, E2,.., E in the elevator to be controlled in the target building M serving multiple floors F1, F2,..., F N of passenger requests, then the preset control objective function is expressed as:

[0143]

[0144] where, w 1i is the weight factor of elevator E i for the average passenger waiting time, w 2i is the weight factor of elevator E i for the energy consumption, represents the average waiting time of passengers in elevator E i serving floor F j at the t-th moment within the prediction time domain, E i (t) represents the energy consumed by elevator E i at the t-th moment within the prediction time domain, S i (k) is the state vector of elevator E i at the t-th moment. The state vector includes at least the current position, speed, and passenger capacity information. U represents the penalty term, λ represents the penalty factor of this penalty term, and k represents the time step.

[0145] By combining a model predictive controller with a non - linear dynamic mathematical model and a passenger flow prediction model, the states and outputs at multiple future moments are predicted, and an optimal control action sequence is formulated in combination with a preset control objective function and constraint conditions. It also includes:

[0146] The constraint conditions include:

[0147] To prevent continuous stops on the same floor, a minimum floor stop interval constraint is established:

[0148] t stop ≤t i,j -t i,j-1 ,j = 2,3,...,N i ,i = 1,2,..,M

[0149] Among them, t i,j represents the time when elevator E i arrives at the j - th floor;

[0150] A response time constraint for passenger call requests is established:

[0151] t response ≤t j,arrival -t i,call i = 1,2,...,M

[0152] A system balance constraint is established:

[0153]

[0154] Among them, N f represents the total number of floors in the building, P i,j (k) is the service demand of elevator E i at the j - th floor at time k. The service demand includes at least the number of passengers and the number of service requests. P avg,j is the average service demand that all elevators expect to reach at the j - th floor, and B is a set threshold for controlling the degree of imbalance of the system.

[0155] The constraint conditions also include:

[0156] A priority constraint is established: The response priority of elevators on the lowest three floors and the highest three floors is higher than that on any other floor;

[0157] To prevent multiple elevators from going to the same floor simultaneously, causing congestion or empty running, a cooperative scheduling constraint is established:

[0158]

[0159] Among them, M1 represents the number of elevator devices participating in cooperative scheduling, T i,end (D d) is the time point when the elevator device No. i completes its current task within the scheduling period D. T(D + 1) is the time when the device No. j starts a new task in the immediately following scheduling period D + 1. D is the set minimum time interval threshold; d Within it, the i-th a elevator device completes its current task at time point T j,start (D d + 1) is the time when the j-th d device starts a new task in the immediately following scheduling period D b + 1. D min is the set minimum time interval threshold;

[0160] When multiple elevators are running in the same shaft, a safety distance constraint is established:

[0161]

[0162] Among them, represents the position of the elevator at time k, represents the position of the elevator at time k. M2 represents the number of elevator floors in the same shaft when multiple elevators are running in the same shaft. h(k) represents the safety distance compensation value calculated based on the elevator length and the current position. ij (k) represents the safety distance compensation value calculated according to the elevator length and the current position.

[0163] In an optional embodiment, the following constraint conditions can also be considered:

[0164] Speed constraint: The maximum and minimum running speeds of the elevator are restricted:

[0165] v min ≤ v i (k) ≤ v max , i = 1, 2,..., m

[0166] Among them, m represents the number of elevators, v(k) represents the speed of the i-th elevator at time k, v represents the minimum speed threshold, and v represents the maximum speed threshold. i (k) represents the speed of the i-th elevator at time k, v min represents the minimum speed threshold, and v max represents the maximum speed threshold.

[0167] Acceleration constraint: The maximum and minimum accelerations of the elevator are restricted:

[0168]

[0169] Among them, m represents the number of elevators, a represents the minimum acceleration threshold, and a represents the maximum acceleration threshold. min represents the minimum acceleration threshold, and a max represents the maximum acceleration threshold.

[0170] Passenger capacity limit, a single elevator cannot be overloaded:

[0171] C min ≤ C i(k) ≤ C max , i = 1, 2, …, m

[0172] where C i (k) represents the passenger capacity of the i-th elevator at time k, C min represents the minimum passenger capacity, C max represents the maximum passenger capacity;

[0173] Emergency situation handling constraint:

[0174] Assume there is a Boolean variable EB(t) used to indicate whether an emergency situation occurs. If an emergency situation occurs, then EB(t) = true = 1. In the emergency state, the target floor of the elevator is forcibly set to the safe floor G safe ,

[0175]

[0176] where represents the target floor of the i-th elevator at time t, represents the target floor calculated under the normal scheduling strategy.

[0177] Speed and acceleration limits. In the emergency state, the maximum allowable speed and acceleration of the elevator can be expressed as:

[0178]

[0179]

[0180] where and are respectively the maximum speed and acceleration of the i-th elevator at time t, ν emergency and a emergency are the limit values in the emergency state, v normal and a normal are the limit values in the normal state.

[0181] It should be noted that by using the model predictive controller to combine the non-linear dynamic model with the passenger flow prediction model, the prediction of the states and outputs at multiple future moments is realized. Combining the preset control objective function and constraint conditions, the optimal control action sequence is formulated. The overall operation efficiency and service quality of the elevator group system are improved, enabling the elevator to meet the real-time passenger flow demand while taking into account energy conservation and equipment utilization rate.

[0182] S104: According to the calculated optimal control action sequence, send specific control instructions to each elevator, so that the elevator operates according to the predetermined plan, and complete the update of the elevator group control method.

[0183] Suppose the optimal control action sequence obtained through Model Predictive Control (MPC) is as follows:

[0184] {u * (k|t), u * (k + 1|t),..., u * (k + N p |t)}

[0185] where k represents the current time, t represents the start time of the plan, N ρ is the number of steps within the prediction horizon, and u is the control vector, which may include control variables such as elevator speed, acceleration, and target floor.

[0186] For each future time k + i (i = 0, 1,..., N p - 1), the corresponding elevator commands are extracted from the optimal control actions:

[0187] Target floor command: If u * (k + i|t) contains the target floor information f target , then send a command to the elevator to go to that floor.

[0188] Operating mode command: If the model takes into account elevator operating modes such as acceleration, deceleration, stop and wait, etc., then issue commands according to the corresponding speed and acceleration set values.

[0189] According to the real - time time t and the preset time interval, send the corresponding control commands to each elevator control system at the correct time point. For example, for the command of the i - th step, it is sent at the moment t + i·Δt, where Δt is the prediction step size.

[0190] The actual elevator system will execute the commands after receiving them, and there will be state feedback. Adjust the subsequent control strategy according to the feedback results, thereby completing the online update of the elevator group control method.

[0191] In an alternative embodiment, the conditions for completing the online update can be determined to meet any two or more of the following conditions:

[0192] 1. Instruction execution confirmation: A sign of the update completion is that all elevators have received and started to execute the instructions in the corresponding optimal control action sequence.

[0193] 2. System state convergence: It can be judged whether the update is effective by monitoring whether the system performance indicators (such as passenger waiting time, elevator utilization rate, etc.) reach the preset goals or gradually approach the optimized ideal values. For example, if the average waiting time of the system continues to be lower than a certain threshold for several consecutive time periods, it can be regarded as the update completion.

[0194] 3. Real-time feedback and iterative adjustment: In practical applications, due to environmental changes and model prediction errors, the elevator group control system needs to continuously receive real-time feedback and make fine adjustments based on the feedback results. Therefore, the update completion condition may be to set a number of cycles N or a certain performance improvement index to reach a stable standard, which is expressed as follows:

[0195] |P(t) - P*| < ε, t = k, …, k + N

[0196] where P(t) is the actual performance index at time t (such as the average waiting time of passengers), P * is the optimization target value, and ε is a very small positive number representing the allowable deviation range.

[0197] 4. No violation of constraints occurs: Ensure that during the entire update process, all elevator operations do not violate the pre-set physical constraint conditions, such as speed limits, passenger capacity limits, etc.

[0198] In an optional embodiment, the actual operating state of the elevator and the passenger flow situation are monitored in real time, actual data is collected and compared with the prediction results, and the parameters of the prediction model and the optimization algorithm are continuously corrected according to the deviation, so that the scheduling strategy can be continuously improved and adapted to the actual situation, thereby improving the accuracy and robustness of the scheduling decision.

[0199] It should be noted that according to the calculated optimal control action sequence, specific instructions are sent to each elevator to ensure that the elevator operates efficiently and orderly according to the plan. The real-time optimization adjustment of the elevator group control system is realized, the control strategy is dynamically updated according to the actual operating conditions and prediction results, and the robustness and adaptability of the system are enhanced. In the process of continuous cyclic execution and feedback, the elevator group control system always maintains the best working state, continuously improving the service level of the vertical traffic inside the building.

[0200] In summary, the present invention proposes an elevator group control method, which obtains the elevator physical characteristics and the passenger's up and down behavior characteristics in the previous cycle of the elevators to be controlled in the target building, constructs a non-linear dynamic mathematical model, and the elevator control method used in the previous cycle of the elevator is any existing control method; obtains the passenger flow data in the previous cycle of the elevators to be controlled in the target building, and combines machine learning algorithms and recursive least squares method to establish a passenger flow prediction model considering system time delay; through a model predictive controller, combines the non-linear dynamic mathematical model and the passenger flow prediction model, predicts the states and outputs at multiple future times, and combines a preset control objective function and constraint conditions to formulate an optimal control action sequence; according to the calculated optimal control action sequence, sends specific control instructions to each elevator to make the elevator operate according to the predetermined plan, and completes the update of the elevator group control method.

[0201] The elevator cluster control method and system provided by the present invention have the following advantages:

[0202] 1. Improve elevator operation efficiency: By constructing a nonlinear dynamic mathematical model and a passenger flow prediction model, the optimal scheduling of elevator clusters can be achieved, the passenger waiting time can be reduced, and the elevator operation efficiency can be improved.

[0203] 2. Improve passenger comfort: According to passenger flow forecast, reasonably allocate elevator passenger capacity to avoid elevator overload or empty load, and improve passenger comfort.

[0204] 3. Enhance system stability: Through the model predictive controller, the elevator operation strategy is adjusted in real time to ensure the stable operation of the elevator cluster in complex environments.

[0205] 4. Simplify operation and maintenance management: Through unified management and control of elevator clusters, the workload of operation and maintenance personnel can be simplified and the level of building management can be improved.

[0206] 5. Strong adaptability: The elevator cluster control method and system proposed in the present invention can be applied to buildings of different types and sizes and have wide adaptability.

[0207] The present invention not only provides a new technical solution for elevator cluster control, but also provides strong support for building automation management and intelligent development. As an intelligent control system, the elevator cluster control method and system have broad application prospects and market potential. With the continuous upgrading of building construction and management in the future, the present invention will bring significant economic and social benefits to the elevator industry and building automation field.

[0208] In a preferred embodiment, an elevator cluster control system includes:

[0209] The first model building module is used to obtain the physical characteristics of the elevator to be controlled in the target building in the previous cycle and the characteristics of the passenger's upstairs and downstairs behavior, and to build a nonlinear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method;

[0210] The second model building module is used to obtain the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and to establish a passenger flow prediction model taking into account the system time lag by combining the machine learning algorithm and the recursive least squares method;

[0211] The optimal sequence acquisition module is used to predict the state and output at multiple future moments by combining the model predictive controller with the nonlinear dynamic mathematical model and the passenger flow prediction model, and formulate the optimal control action sequence in combination with the preset control objective function and constraint conditions;

[0212] An operation and update module, configured to send specific control instructions to each elevator according to the calculated optimal control action sequence, so that the elevator operates according to a predetermined plan and complete the update of the elevator group control method.

[0213] The above-mentioned unit modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0214] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 2 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an elevator group control method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0215] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0216] Obtain the elevator physical characteristics and the behavior characteristics of passengers getting on and off the elevator in the previous cycle of the elevator to be controlled in the target building, and construct a non-linear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method;

[0217] Obtain the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and establish a passenger flow prediction model considering system time delay by combining machine learning algorithms and recursive least squares method;

[0218] Through a model predictive controller, combine the non-linear dynamic mathematical model and the passenger flow prediction model, predict the states and outputs at multiple future moments, and combine the preset control objective function and constraint conditions to formulate an optimal control action sequence;

[0219] According to the calculated optimal control action sequence, specific control instructions are sent to each elevator, enabling the elevator to operate according to the predetermined plan and completing the update of the elevator group control method.

[0220] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0221] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0222] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0223] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0224] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the process Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0225] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0226] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An elevator cluster control method, characterized in that: include: Obtain the physical characteristics of the elevator to be controlled in the target building in the previous cycle and the characteristics of the passenger's going up and down stairs behavior, and construct a nonlinear dynamic mathematical model, wherein the elevator control method used in the previous cycle of the elevator is any existing control method; Establish a mathematical twin model under response conditions and obtain data from the previous cycle through the mathematical twin model; Obtain the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and establish a passenger flow prediction model that takes into account system time lag by combining machine learning algorithm and recursive least squares method; By combining the nonlinear dynamic mathematical model and the passenger flow prediction model through a model predictive controller, the states and outputs at multiple future moments are predicted, and an optimal control action sequence is formulated in combination with a preset control objective function and constraints; The constraints include minimum stop floor interval constraints, response time constraints for passenger call requests, system balance constraints, priority constraints, coordinated scheduling constraints, safety distance constraints, speed constraints, acceleration constraints, passenger capacity limit constraints, and emergency handling constraints; According to the calculated optimal control action sequence, specific control instructions are sent to each elevator to make the elevator run according to the predetermined plan and complete the update of the elevator cluster control method; The control instructions include target floor instructions and operation mode instructions; When any two or more of the following conditions are met, the method update is completed: The results of instruction execution confirmation, system state convergence, real-time feedback and iterative adjustment reach stable values, and no constraint violations occur; The physical characteristics of the elevator to be controlled in the target building in the previous cycle and the characteristics of the passenger's upstairs and downstairs behavior are obtained to construct a nonlinear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method including: The physical characteristics of the elevator include at least the elevator floor , Elevator speed , passenger capacity and passenger car movement , t represents the elevator running time; The passenger going up and down stairs behavior characteristics at least include the passengers entering and leaving each floor; The nonlinear dynamic mathematical model includes the elevator position change equation and the passenger capacity change equation: The position change equation of the elevator is expressed as: Where m is the total mass of the elevator and passengers, It is the traction force provided by the traction motor, which is related to the elevator position, speed and passenger capacity. It is the friction force related to the elevator speed and passenger capacity, which increases with the increase of speed and passenger capacity. It is the damping force that takes into account the impact of personnel changes and is related to the elevator speed and personnel distribution. Indicates the force of the current control signal acting on the elevator system, Indicates the acceleration of the elevator car; The passenger capacity variation equation is expressed as: in, and Respectively indicate time On the floor The number of passengers entering and leaving the elevator; The method further comprises: estimating unknown parameters or function forms in the model according to actual data combined with system identification technology; obtaining the physical characteristics of the elevator to be controlled in the target building in the previous cycle and the characteristics of the passenger's going up and down stairs behavior, and constructing a nonlinear dynamic mathematical model, wherein the elevator control method used in the previous cycle of the elevator is any existing control method; The traction force According to the elevator traction characteristics and passenger capacity, the estimation formula is as follows: The friction force The estimation formula is as follows: The damping force The estimation formula is as follows: in, represents the inherent mass of the elevator, represents the correlation coefficient between the traction force and the elevator position, It represents the correlation coefficient between traction force and elevator speed, represents the correlation coefficient between traction and passenger capacity, represents the friction coefficient, that is, the resistance characteristics between the system's internal and external environment, It represents the influence coefficient of unit passenger capacity on the friction increment, reflecting the additional friction caused by the increase in the number of passengers. represents the damping coefficient that is linearly related to the elevator speed, Indicates the damping coefficient related to passenger capacity and speed.

2. The elevator cluster control method according to claim 1, characterized in that: The method of obtaining the passenger flow data of the elevator to be controlled in the target building in the previous cycle and establishing a passenger flow prediction model considering the system time lag by combining the machine learning algorithm and the recursive least squares method includes: First, a preliminary prediction model is established using a machine learning algorithm. The machine learning method using time series data is selected, and its prediction model is expressed as: in, It's in time The passenger flow at the moment, n is the length of the historical window, and LSTM is a trained long short-term memory network model; Secondly, consider the system time lag factor. If the system has a time lag effect, introduce the time lag variable to improve the model. The improved model is expressed as: in, is the time-delay parameter of the system, and F is the function that corrects the prediction results by combining the time-delay information; Again, the recursive least squares method is used to update the parameters: Initialize model parameters ; For each time step , based on the actual observed passenger flow data Update model parameters : Finally, the passenger flow prediction model is embedded into the nonlinear dynamic mathematical model.

3. The elevator cluster control method according to claim 2, characterized in that: The model predictive controller combines the nonlinear dynamic mathematical model and the passenger flow prediction model to predict the state and output at multiple future moments, and formulates the optimal control action sequence in combination with the preset control objective function and constraint conditions, including: Assume that there are multiple elevators to be controlled in the target building Serving multiple floors The preset control objective function is expressed as: in, It's an elevator For the weight factor of the average waiting time of passengers, It's an elevator For the weight factor of energy consumption, Indicates that in the prediction time domain At this moment, passengers are in the elevator Serving the floor The average waiting time, Indicates that in the prediction time domain Moment, elevator The energy consumed, It's an elevator In the The state vector at the moment, the state vector at least includes the current position, speed, and passenger capacity information, represents the penalty term, represents the penalty factor of the penalty term, and k represents the time step.

4. The elevator cluster control method according to claim 3, characterized in that: The method of combining the nonlinear dynamic mathematical model and the passenger flow prediction model with the model predictive controller to predict the states and outputs at multiple future moments, and formulating the optimal control action sequence in combination with the preset control objective function and constraint conditions also includes: The constraints include: To prevent consecutive stops on the same floor, establish a minimum stop floor interval constraint: in, Indicates elevator Arrive at Layer time; Establish a response time constraint for passenger summon requests: Establish system balance constraints: in, Indicates the total number of floors in the building. It is at the moment When the elevator In the The service demand of the layer includes at least the number of passengers and the number of service requests. All elevators are in The average service demand expected to be achieved by the layer, It is a threshold value used to control the imbalance degree of the system.

5. The elevator cluster control method according to claim 4, characterized in that: The constraints include: Establish priority constraints: the elevator response priority of the lowest three floors and the highest three floors is higher than the response priority of any other floors; To prevent multiple elevators from going to the same floor at the same time and causing congestion or empty travel, collaborative scheduling constraints are established: in, Indicates the number of elevator equipment involved in collaborative scheduling, In the scheduling cycle within, no. The time when the elevator equipment completes its current task, In the next scheduling cycle In The time when the device starts a new task, is the minimum time interval threshold set; When multiple elevators are running in the same shaft, establish safe distance constraints: ， in, Indicates elevator At the time k, Indicates elevator At the time k, Indicates the number of elevator floors in the same shaft when multiple elevators are running in the same shaft. Indicates the safety distance compensation value calculated based on the elevator length and current position.

6. An elevator cluster control system using the method as claimed in claim 1, characterized in that: include: The first model building module is used to obtain the physical characteristics of the elevator to be controlled in the target building in the previous cycle and the characteristics of the passenger's going up and down stairs behavior, and build a nonlinear dynamic mathematical model. The elevator control method used in the previous cycle of the elevator is any existing control method; The second model building module is used to obtain the passenger flow data of the elevator to be controlled in the target building in the previous cycle, and to establish a passenger flow prediction model taking into account the system time lag by combining the machine learning algorithm and the recursive least squares method; An optimal sequence acquisition module is used to predict the state and output at multiple future moments by combining the nonlinear dynamic mathematical model and the passenger flow prediction model through a model prediction controller, and formulate an optimal control action sequence in combination with a preset control objective function and constraint conditions; The operation and update module is used to send specific control instructions to each elevator according to the calculated optimal control action sequence, so that the elevator can run according to the predetermined plan and complete the update of the elevator cluster control method.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images