Escalator self-adaptive energy-saving operation control system and method for detecting passenger flow

Abstract

This application discloses an adaptive energy-saving operation control system and method for escalators that detects passenger flow, relating to the field of intelligent control technology. It solves the technical problem in existing technologies where the threshold is generally set to a fixed value when comparing passenger flow with a threshold. This can lead to congestion and potentially stampedes during peak periods like holidays. This application utilizes data sensors to collect real-time passenger flow data entering the escalator area; it controls the escalator's start and stop based on the real-time passenger flow; it adjusts the escalator's operating speed based on the real-time passenger flow; it predicts passenger flow based on historical data; and it determines the escalator's maintenance and inspection time based on the prediction results. This system not only controls start and stop but also adjusts the operating speed based on real-time passenger flow. Appropriate speed reduction can bring exponential energy savings, directly reducing electricity costs and extending equipment lifespan.

Description

Technical Field

[0001] This application belongs to the field of intelligent control and relates to escalator adaptive energy-saving operation control technology, specifically an escalator adaptive energy-saving operation control system and method for detecting passenger flow. Background Technology

[0002] An escalator is an electromechanical device with continuously moving steps that uses fixed tracks and a drive system to transport passengers continuously. It is typically used to connect different floors or areas of different heights within a building; its application in shopping malls, subways, and train stations is becoming increasingly widespread. Escalators can be adaptively controlled based on passenger flow. During peak hours, escalators can increase their operating speed to quickly disperse passenger flow and avoid congestion. Sensors detect passenger flow, automatically entering low-speed or standby mode when no one is using the escalator, and immediately restarting when someone approaches, reducing passenger waiting time. By reducing the operating speed or stopping the escalator when no one is using it, wear on components such as steps, chains, and motors is reduced, extending their service life. Combined with passenger flow data, high-load periods can be predicted, allowing for advance maintenance planning and avoiding downtime losses due to sudden malfunctions.

[0003] Existing technologies typically control escalators by controlling their start and stop. When there are no passengers in the escalator's area, the escalator gradually stops; when passengers arrive, the escalator starts running. Simultaneously, the passenger flow is compared to a set threshold, and the escalator's operating speed is adjusted accordingly. However, in existing technologies, the threshold is usually set to a fixed value. During holidays when passenger flow increases, this can cause congestion and, in severe cases, stampede accidents. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes an escalator adaptive energy-saving operation control system and method for detecting passenger flow, which is used to solve the technical problem in the prior art where, when comparing passenger flow with a threshold, the threshold is generally set to a fixed value, which may cause congestion and even stampede accidents when passenger flow increases during holidays.

[0005] To achieve the above objectives, the first aspect of this application provides an escalator adaptive energy-saving operation control system for detecting passenger flow, comprising: an energy-saving control module, and a data acquisition module and a predictive maintenance module connected thereto; The data acquisition module is used to collect passenger flow data entering the escalator area using data sensors to obtain real-time passenger flow data. The energy-saving control module is used to control the start and stop of the escalator according to the real-time passenger flow; and to adjust the running speed of the escalator according to the real-time passenger flow. The predictive maintenance module is used to predict passenger flow based on historical passenger flow and determine the operation and maintenance inspection time of the escalator based on the prediction results.

[0006] This application automatically stops or operates at low speed when there is no passenger flow, completely eliminating idling energy consumption; it not only controls start-stop but also adjusts the operating speed according to real-time passenger flow; moderate speed reduction can bring exponential energy-saving effects; it directly reduces electricity costs and extends equipment life, indirectly reducing capital expenditures for replacing parts and the entire machine; by adaptively adjusting speed and start-stop, it reduces mechanical friction and fatigue wear of the motor, gearbox, chain, and steps at unnecessary times, significantly extending the physical service life of the escalator; the energy-saving control module is usually used in conjunction with a frequency converter to achieve smooth acceleration and deceleration of the escalator, avoiding the impact of direct start-up on the power grid and mechanical structure, and reducing the failure rate; identifying and predicting peak passenger flow periods and selecting low passenger flow periods for escalator maintenance and testing can reduce the inconvenience caused by maintenance and improve maintenance efficiency.

[0007] Preferably, the step of controlling the start and stop of the escalator based on real-time passenger flow includes: Retrieve real-time passenger flow data for the escalator area; when the real-time passenger flow data for the escalator area is 0, switch the escalator to standby mode. When the escalator is in standby mode and the real-time passenger flow is greater than 0, the escalator will be switched to running mode.

[0008] Preferably, adjusting the escalator's operating speed based on real-time passenger flow includes: Retrieve real-time passenger flow; obtain passenger flow thresholds; compare real-time passenger flow with passenger flow thresholds; wherein, passenger flow thresholds include: primary thresholds and secondary thresholds; When the real-time passenger flow is less than the first-level threshold, the escalator's operating speed is adjusted to low speed; otherwise, the real-time passenger flow is compared with the second-level threshold. When the real-time passenger flow exceeds the secondary threshold, the escalator's operating speed will be adjusted to high speed; otherwise, the escalator's operating speed will be adjusted to medium speed.

[0009] Preferably, the method for obtaining the passenger flow threshold includes: The passenger flow thresholds are divided according to time type and further categorized; the time types include: weekdays, rest days, and holidays. Construct the time decay function: ;in, The time offset from the starting point of the time type; The attenuation rate; For periodic parameters; Construct environment correction functions: ;in, Score external factors; and For the Sigmoid function parameter; Constructing intraday cycle correction factors: ;in, Within the day; This refers to peak passenger flow times. It is a daily cycle; and For amplitude parameters; The start time; Constructing a dynamic threshold model: Passenger flow thresholds for different time periods are calculated based on a dynamic threshold model; among which, The threshold for the k-th level of time type i; The baseline threshold constant; This is the seasonal adaptability coefficient; i corresponds to weekdays, rest days, and public holidays. ; indicates a first-level threshold or a second-level threshold; Adjust the coefficient for the time type.

[0010] Preferably, the method for obtaining the benchmark threshold constant includes: Obtain historical passenger flow; fit the historical passenger flow into a passenger flow curve F(t) in chronological order; solve for the first derivative f(t) of the passenger flow curve; extract the maximum and minimum values ​​of the first derivative; extract the historical passenger flow corresponding to the maximum and minimum values ​​of the first derivative from the passenger flow curve, and calculate the average value to obtain the baseline threshold constant for the first-level threshold. Obtain the maximum safe capacity of the escalator; according to the expression The baseline threshold constant for the secondary threshold is calculated; where, The reference threshold constant representing the first-level threshold; The range coefficient; This represents the maximum safe capacity of the escalator. This is for the safety factor.

[0011] Preferably, the step of predicting passenger flow based on historical passenger flow includes: Retrieve historical passenger flow data; divide the historical passenger flow data according to time type, and sort the historical passenger flow data in chronological order to obtain passenger flow sequences; among which, passenger flow sequences include: weekday passenger flow sequences, rest day passenger flow sequences, and holiday passenger flow sequences; Obtain the time type of the passenger flow to be predicted; retrieve the traffic prediction model; input the passenger flow sequence of the corresponding time type into the traffic prediction model to obtain the predicted passenger flow sequence; the traffic prediction model is built based on an artificial intelligence model.

[0012] Preferably, the traffic prediction model is built based on an artificial intelligence model, including: Obtain the standard dataset; the standard dataset includes standard input data consistent with the content attributes of the passenger flow sequence, and standard output data consistent with the content attributes of the predicted passenger flow sequence. Select a model framework and a deep learning algorithm from the artificial intelligence model library; construct the model framework based on the deep learning algorithm to obtain a deep learning model; The standard dataset is divided into training, validation, and test sets according to a set ratio; the deep learning model is trained using the training set; the internal parameters of the deep learning model are adjusted using the validation set; and the deep learning model is tested using the test set to obtain test metrics. Obtain the indicator threshold; compare the test indicator with the indicator threshold; if all test indicators are greater than the indicator threshold, then mark the deep learning model as a traffic prediction model; otherwise, rebuild and retrain the traffic prediction model.

[0013] It should be noted that the test metrics include: accuracy, recall, F1 score, and stability; the thresholds for the metrics and the division ratio of the standard dataset are set by professional technicians based on experimental simulations and adjusted according to actual requirements; when it is necessary to rebuild and retrain the discharge analysis model, the division ratio of the standard dataset, the model framework, or the deep learning algorithm are adjusted before rebuilding and retraining the model.

[0014] Preferably, determining the escalator's operation and maintenance inspection time based on the prediction results includes: Retrieve the predicted passenger flow sequence; obtain the duration of operation and maintenance monitoring; accumulate and integrate the predicted passenger flow sequence according to the duration to obtain the predicted sequence; The time period corresponding to the minimum value is selected from the predicted sequence as the operation and maintenance inspection time; and the operation and maintenance inspection time is sent to the corresponding technical personnel.

[0015] The second aspect of this application provides an adaptive energy-saving operation control method for escalators that detects passenger flow, including: Data sensors are used to collect passenger flow data entering the escalator area to obtain real-time passenger flow data. The escalator is started and stopped based on real-time passenger flow. The operating speed of the escalator is adjusted according to the real-time passenger flow. Predict passenger flow based on historical passenger volume; The maintenance and inspection time for escalators is determined based on the prediction results.

[0016] A third aspect of this application provides a computer-readable storage medium storing instructions for performing the steps of the method described in the implementation of the second aspect.

[0017] Compared with the prior art, the beneficial effects of this application are: 1. This application monitors passenger flow in the escalator area in real time. When passenger flow is zero, the escalator is switched to standby mode, avoiding energy waste when no one is using it. When there is passenger flow, it is switched to operating mode, ensuring that the escalator only operates when there is demand, effectively reducing energy consumption. A dynamic threshold model is constructed to calculate passenger flow thresholds based on different time types, external factors, and intraday cycles. Based on the comparison between real-time passenger flow and the threshold, the escalator's operating speed is adjusted to low, medium, or high speed. This allows the escalator to rationally allocate energy according to actual passenger flow demand, further improving energy efficiency. Efficiency is key; when real-time passenger flow is below the first-level threshold, the escalator's operating speed is adjusted to low speed, reducing potential risks due to low passenger volume. When real-time passenger flow exceeds the second-level threshold, the operating speed is adjusted to high speed to ensure timely crowd dispersal during peak hours, preventing overcrowding and stampedes. When real-time passenger flow is between the first and second-level thresholds, the operating speed is adjusted to medium speed, balancing efficiency and safety. Dynamically adjusting the escalator's operating speed allows for efficient capacity allocation based on passenger flow, reducing waiting time. Especially during peak hours, high-speed operation enables faster crowd dispersal, improving overall service efficiency.

[0018] 2. This application divides and sorts historical passenger flow according to time type to obtain passenger flow sequences for different time types; it considers the differences in passenger flow patterns under different time types; by processing data of different time types separately, the traffic prediction model can more accurately capture their respective characteristics and patterns, thereby improving the accuracy of prediction; it retrieves the predicted passenger flow sequences and accumulates and integrates them according to the duration of operation and maintenance testing to obtain the predicted sequence; it selects the time period corresponding to the minimum value from the predicted sequence as the operation and maintenance testing time; selecting the time period with relatively low passenger flow for operation and maintenance testing can minimize the impact on passengers' normal travel and improve the feasibility and efficiency of operation and maintenance testing; it sends the selected operation and maintenance testing time to the corresponding technical personnel to ensure that the technical personnel can prepare in advance and arrive at the site on time to carry out operation and maintenance testing work; it avoids delays caused by improper time arrangements by technical personnel and improves the timeliness and effectiveness of operation and maintenance testing work. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the system connection structure of this application; Figure 2 This is a schematic diagram illustrating the specific working steps of the energy-saving control module in this application; Figure 3 This is a schematic diagram illustrating the specific working steps of the predictive maintenance module in this application; Figure 4 This is a schematic diagram of the overall method steps of this application; Figure 5 This is a schematic diagram of the hardware deployment in this application; Figure 6 This is a schematic diagram of the speed regulation logic of this application. Detailed Implementation

[0021] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0022] Please see Figure 1 The first aspect of this application provides an adaptive energy-saving operation control system for escalators that detects passenger flow, including: an energy-saving control module, and a data acquisition module and a predictive maintenance module connected thereto; The data acquisition module is used to collect passenger flow data entering the escalator area using data sensors to obtain real-time passenger flow data. The energy-saving control module is used to control the start and stop of the escalator according to the real-time passenger flow; and to adjust the running speed of the escalator according to the real-time passenger flow. The predictive maintenance module is used to predict passenger flow based on historical passenger flow and determine the operation and maintenance inspection time of the escalator based on the prediction results.

[0023] Please see Figure 5In one possible implementation, an energy-saving box is installed in the escalator's machine room to collect and analyze data. Cameras are installed above the upper and lower entrances / exits and the middle straight section of the escalator, pointing towards the escalator path to monitor and analyze passenger flow in real time. Infrared sensors are installed at the upper and lower handrail entrances / exits to detect the number of people entering and leaving the escalator in real time. A three-phase current sensor is connected to the incoming line of the control cabinet to monitor the current during escalator operation in real time. The cameras communicate with the energy-saving box using RS485, the infrared sensors with the energy-saving box use optocouplers, and the three-phase current sensors with the energy-saving box use RS485. Based on the analyzed data, the energy-saving box connects to the escalator control system using RS485 to control the escalator's energy-saving operation.

[0024] This application automatically stops or operates at low speed when there is no passenger flow, completely eliminating idling energy consumption; it not only controls start-stop but also adjusts the operating speed according to real-time passenger flow; moderate speed reduction can bring exponential energy-saving effects; it directly reduces electricity costs and extends equipment life, indirectly reducing capital expenditures for replacing parts and the entire machine; by adaptively adjusting speed and start-stop, it reduces mechanical friction and fatigue wear of the motor, gearbox, chain, and steps at unnecessary times, significantly extending the physical service life of the escalator; the energy-saving control module is usually used in conjunction with a frequency converter to achieve smooth acceleration and deceleration of the escalator, avoiding the impact of direct start-up on the power grid and mechanical structure, and reducing the failure rate; identifying and predicting peak passenger flow periods and selecting low passenger flow periods for escalator maintenance and testing can reduce the inconvenience caused by maintenance and improve maintenance efficiency.

[0025] Please see Figure 2 The specific working steps of the energy-saving control module are as follows: S201. Retrieve the real-time passenger flow of the escalator area; when the real-time passenger flow of the escalator area is 0, adjust the escalator to standby mode; when the escalator is in standby mode and the real-time passenger flow is greater than 0, adjust the escalator to running mode.

[0026] S202. Divide the passenger flow threshold according to time type and classify the passenger flow threshold; construct the time decay function, environmental correction function and intraday cycle correction factor respectively.

[0027] A dynamic threshold model is constructed based on the time decay function, the environmental correction function, and the intraday cycle correction factor; the passenger flow threshold for different time types is calculated based on the dynamic threshold model.

[0028] Wherein, the time decay function is: ; The time offset from the starting point of the time type; The attenuation rate; For periodic parameters; environment correction function: ; Score external factors; and For the Sigmoid function parameters; intraday cycle correction factor: ; Within the day; This refers to peak passenger flow times. It is a daily cycle; and For amplitude parameters; Start time; Dynamic threshold model: ; The threshold for the k-th level of time type i; The baseline threshold constant; This is the seasonal adaptability coefficient; i corresponds to weekdays, rest days, and public holidays. ; indicates a first-level threshold or a second-level threshold; Adjust the coefficient for the time type.

[0029] In one possible implementation, the baseline threshold constant is obtained in the following ways: Obtain historical passenger flow; fit the historical passenger flow into a passenger flow curve F(t) in chronological order; solve for the first derivative f(t) of the passenger flow curve; extract the maximum and minimum values ​​of the first derivative; extract the historical passenger flow corresponding to the maximum and minimum values ​​of the first derivative from the passenger flow curve, and calculate the average value to obtain the baseline threshold constant for the first-level threshold. Obtain the maximum safe capacity of the escalator; according to the expression The baseline threshold constant for the secondary threshold is calculated; where, The reference threshold constant representing the first-level threshold; The range coefficient; This represents the maximum safe capacity of the escalator. This is for the safety factor.

[0030] It should be noted that the external factor score is set by professional technicians based on environmental and weather factors.

[0031] It should be noted that the dynamic threshold model does not simply change the speed control threshold under different time types, but rather dynamically adjusts the escalator's response strategy under different passenger flow levels based on historical passenger flow patterns and real-time environmental factors. For example, during holidays, even if the instantaneous passenger flow is the same as on weekdays, the system will lower the first and second thresholds accordingly due to the greater fluctuations in overall passenger flow and the longer peak duration during holidays, thus entering medium or high speed operation earlier to avoid congestion. On weekdays during periods of low passenger flow, the system will moderately reduce its speed to achieve energy saving without affecting passenger passage efficiency, enabling the elevator to operate at energy efficiency. Through the aforementioned dynamic threshold model, this application achieves a balance between energy saving and comfort while ensuring safe evacuation capabilities.

[0032] Example: Suppose we have historical passenger flow data for an escalator in a shopping mall: The historical passenger flow fitting curve is: F(t) = 200 + 50sin(πt / 12) + 20sin(πt / 6); the first derivative f(t) = (50π / 12)cos(πt / 12) + (20π / 6)cos(πt / 6); the maximum value of the derivative f_max occurs at t=4 (corresponding to a passenger flow of 260 people / hour); the minimum value of the derivative f_min occurs at t=10 (corresponding to a passenger flow of 140 people / hour); the first-level benchmark threshold is: B1 = (260 + 140) / 2 = 200 people / hour; Given parameters: maximum safe capacity of the escalator Q_max = 300 people / hour; range coefficient R = 1.5; safety factor θ = 0.8; based on the expression, the secondary threshold is calculated to be B2 = 240 people / hour. Time type definition: weekday (i=1); rest day (i=2); holiday (i=3); Time type adjustment coefficient: weekday: D(1) = 1.0; rest day: D(2) = 0.8 (reduced by 20%); holiday: D(3) = 0.7 (reduced by 30%). Model parameter values: λ = 0.05 (attenuation rate); τ = 12 (period parameter); μ = 0.6 (median environmental score); σ = 0.2 (distribution parameter); γ = 0.15 (daily period cosine amplitude); δ = 0.08 (daily period sine amplitude); t_p = 14 (peak passenger flow time 14:00); T_d = 24 (daily period); t_0 = 8 (starting time 8:00); Time type parameters: Weekdays: α1=0.1, β1=0.05; Rest days: α2=0.2, β2=0.1; Holidays: α3=0.3, β3=0.15; Scenario 1: Weekday (i=1) at 10:00 AM; Time parameter: t = 10 (hours); t = 10⁻⁸ = 2 (hour offset); S = 0.7 (external factor score: good weather); The first-level threshold calculated based on the dynamic threshold model is 217; the second-level threshold is 260.

[0033] Scenario 2: Holiday (i=3) 15:00; Time parameter: t = 15 (hours); t = 15 - 8 = 7 (hour offset); S = 0.9 (external factor score: promotional activities); The first-level threshold calculated based on the dynamic threshold model is 208; the second-level threshold is 250.

[0034] In another example, suppose the real-time passenger flow at a certain time on a weekday is 180, the first-level threshold is 150, and the second-level threshold is 220. The system will adjust the escalator to medium speed. On holidays, the first-level threshold is dynamically adjusted to 100, and the second-level threshold is dynamically adjusted to 150. When the passenger flow is 180, the system will first adjust the elevator from low speed to medium speed, and then from medium speed to high speed. The system can accelerate in advance to ensure evacuation efficiency.

[0035] S204. Retrieve real-time passenger flow; obtain passenger flow threshold; compare real-time passenger flow with passenger flow threshold; when real-time passenger flow is less than the first-level threshold, adjust the escalator's operating speed to low speed; otherwise, compare real-time passenger flow with the second-level threshold.

[0036] S205. When the real-time passenger flow exceeds the secondary threshold, the escalator's operating speed will be adjusted to high speed; otherwise, the escalator's operating speed will be adjusted to medium speed.

[0037] The passenger flow thresholds include: primary thresholds and secondary thresholds.

[0038] It should be noted that when adjusting the elevator's operating speed, if it is necessary to directly change the elevator's operating speed from low speed to high speed, the system will first adjust the elevator's operating speed from low speed to medium speed for a period of time before adjusting the elevator from medium speed to high speed; this can prevent the elevator from running too fast.

[0039] Example: In one possible implementation, after the escalator starts, it runs at a set rated speed of 0.5 m / s. Simultaneously, based on the detection of a camera, infrared sensor, and three-phase current sensor, when the passenger flow increases to a threshold, the escalator increases its output current and accelerates to a speed of 0.6 m / s at an acceleration of 0.05 m / s². When the passenger flow decreases to a threshold, the escalator decreases its output current and decelerates to a speed of 0.4 m / s at a deceleration of 0.05 m / s². If no one enters the escalator for a period of time, the escalator decelerates to 0 and enters a standby state until a passenger enters the detection area again, at which point the escalator starts.

[0040] Based on the above steps, this application monitors passenger flow in the escalator area in real time. When passenger flow is zero, the escalator is switched to standby mode to avoid energy waste when no one is using it. When there is passenger flow, it is switched to operating mode to ensure that the escalator only operates when there is demand, effectively reducing energy consumption. A dynamic threshold model is constructed to calculate passenger flow thresholds based on different time types, external factors, and intraday cycles. Based on the comparison between real-time passenger flow and the threshold, the operating speed of the escalator is adjusted to low, medium, or high speed. This allows the escalator to rationally allocate energy according to actual passenger flow demand, further improving energy efficiency. Resource utilization efficiency is improved. When real-time passenger flow is below the first-level threshold, the escalator's operating speed is adjusted to low speed, reducing potential risks due to low passenger volume. When real-time passenger flow exceeds the second-level threshold, the operating speed is adjusted to high speed to ensure timely evacuation of crowds during peak hours, preventing overcrowding and stampedes. When real-time passenger flow is between the first and second-level thresholds, the operating speed is adjusted to medium speed, balancing operational efficiency and safety. Dynamically adjusting the escalator's operating speed allows for reasonable allocation of capacity based on passenger flow, reducing passenger waiting time. Especially during peak hours, high-speed operation enables faster crowd evacuation, improving overall service efficiency.

[0041] Please see Figure 3 The specific working steps of the predictive maintenance module are as follows: S301. Retrieve historical passenger flow data; divide the historical passenger flow data according to time type, and sort the historical passenger flow data according to time sequence to obtain the passenger flow sequence.

[0042] The passenger flow sequence includes: weekday passenger flow sequence, rest day passenger flow sequence, and holiday passenger flow sequence.

[0043] S302. Obtain the time type of the passenger flow that needs to be predicted; retrieve the flow prediction model; input the passenger flow sequence of the corresponding time type into the flow prediction model to obtain the predicted passenger flow sequence.

[0044] In one possible implementation, the traffic prediction model is built upon an artificial intelligence model, including: Obtain the standard dataset; the standard dataset includes standard input data consistent with the content attributes of the passenger flow sequence, and standard output data consistent with the content attributes of the predicted passenger flow sequence. Select a model framework and a deep learning algorithm from the artificial intelligence model library; construct the model framework based on the deep learning algorithm to obtain a deep learning model; The standard dataset is divided into training, validation, and test sets according to a set ratio; the deep learning model is trained using the training set; the internal parameters of the deep learning model are adjusted using the validation set; and the deep learning model is tested using the test set to obtain test metrics. Obtain the indicator threshold; compare the test indicator with the indicator threshold; if all test indicators are greater than the indicator threshold, then mark the deep learning model as a traffic prediction model; otherwise, rebuild and retrain the traffic prediction model.

[0045] S303. Retrieve the predicted passenger flow sequence; obtain the duration of operation and maintenance monitoring; accumulate and integrate the predicted passenger flow sequence according to the duration to obtain the predicted sequence.

[0046] S304. Select the time period corresponding to the minimum value from the predicted sequence as the operation and maintenance inspection time; and send the operation and maintenance inspection time to the corresponding technical personnel.

[0047] Based on the above steps, this application divides and sorts historical passenger flow according to time type to obtain passenger flow sequences for different time types; it considers the differences in passenger flow patterns under different time types; by processing data of different time types separately, the traffic prediction model can more accurately capture their respective characteristics and patterns, thereby improving the accuracy of prediction; it retrieves the predicted passenger flow sequences and accumulates and integrates them according to the duration of operation and maintenance testing to obtain the predicted sequence; it selects the time period corresponding to the minimum value from the predicted sequence as the operation and maintenance testing time; selecting the time period with relatively low passenger flow for operation and maintenance testing can minimize the impact on passengers' normal travel and improve the feasibility and efficiency of operation and maintenance testing; it sends the selected operation and maintenance testing time to the corresponding technical personnel to ensure that the technical personnel can prepare in advance and arrive at the site on time to carry out operation and maintenance testing work; it avoids delays caused by improper time arrangements by technical personnel and improves the timeliness and effectiveness of operation and maintenance testing work.

[0048] Please see Figure 4 The second aspect of this application provides an adaptive energy-saving operation control method for escalators that detects passenger flow, comprising: S401. Use data sensors to collect passenger flow data entering the escalator area to obtain real-time passenger flow data. S402. Control the start and stop of escalators based on real-time passenger flow; S403. Adjust the operating speed of the escalator according to the real-time passenger flow; S404. Predict passenger flow based on historical passenger flow. S405. Determine the maintenance and inspection time of the escalator based on the prediction results.

[0049] A third aspect of this application provides a computer-readable storage medium storing instructions for performing the steps of the method described in the implementation of the second aspect embodiment.

[0050] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0051] The working principle of this application is as follows: This application uses data sensors to collect passenger flow data entering the escalator area to obtain real-time passenger flow data; controls the start and stop of the escalator based on the real-time passenger flow data; adjusts the operating speed of the escalator based on the real-time passenger flow data; predicts passenger flow data based on historical passenger flow data; and determines the maintenance and inspection time of the escalator based on the prediction results.

[0052] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. An escalator self-adapting energy-saving operation control system for detecting passenger flow, characterized in that, include: Energy-saving control module, and connected data acquisition module and predictive maintenance module; The data acquisition module is used to collect passenger flow data entering the escalator area using data sensors to obtain real-time passenger flow data. The energy-saving control module is used to control the start and stop of the escalator according to the real-time passenger flow; and at the same time, adjust the running speed of the escalator according to the real-time passenger flow. The prediction and maintenance module is used to predict passenger flow based on historical passenger flow. The maintenance and inspection time for escalators will be determined based on the forecast results. The adjustment of the escalator's operating speed based on real-time passenger flow includes: Retrieve real-time passenger flow; obtain passenger flow thresholds; compare real-time passenger flow with passenger flow thresholds; wherein, passenger flow thresholds include: primary thresholds and secondary thresholds; When the real-time passenger flow is less than the first-level threshold, the escalator's operating speed is adjusted to low speed; otherwise, the real-time passenger flow is compared with the second-level threshold. When the real-time passenger flow exceeds the secondary threshold, the escalator's operating speed will be adjusted to high speed; otherwise, the escalator's operating speed will be adjusted to medium speed. Methods for obtaining passenger flow thresholds include: The passenger flow thresholds are divided according to time type and further categorized; the time types include: weekdays, rest days, and holidays. A time decay function is constructed as: ; where, is a time offset from the start of the distance-time type; is a decay rate; is a period parameter; Constructing an environment correction function: ; wherein, is an external factor score; and is a Sigmoid function parameter; Constructing the diurnal cycle correction factor: ; wherein, is the diurnal time; is the passenger flow peak time point; is the diurnal cycle; and is the amplitude parameter; is the start time; Constructing a dynamic threshold model: Passenger flow thresholds for different time periods are calculated based on a dynamic threshold model; among which, The threshold for the k-th level of time type i; The baseline threshold constant; This is the seasonal adaptability coefficient; i corresponds to weekdays, rest days, and public holidays. ; indicates a first-level threshold or a second-level threshold; Adjust the coefficient for the time type.

2. The escalator adaptive energy-saving operation control system for detecting passenger flow according to claim 1, characterized in that, The method of controlling the start and stop of escalators based on real-time passenger flow includes: Retrieve real-time passenger flow data for the escalator area; when the real-time passenger flow data for the escalator area is 0, switch the escalator to standby mode. When the escalator is in standby mode and the real-time passenger flow is greater than 0, the escalator will be switched to running mode.

3. The escalator adaptive energy-saving operation control system for detecting passenger flow according to claim 1, characterized in that, The method for obtaining the benchmark threshold constant includes: Obtain historical passenger flow; fit the historical passenger flow into a passenger flow curve F(t) in chronological order; solve for the first derivative f(t) of the passenger flow curve; extract the maximum and minimum values ​​of the first derivative; extract the historical passenger flow corresponding to the maximum and minimum values ​​of the first derivative from the passenger flow curve, and calculate the average value to obtain the baseline threshold constant for the first-level threshold. Obtain the maximum safe capacity of the escalator; according to the expression The baseline threshold constant for the secondary threshold is calculated; where, The reference threshold constant representing the first-level threshold; The range coefficient; This represents the maximum safe capacity of the escalator. This is for the safety factor.

4. The escalator adaptive energy-saving operation control system for detecting passenger flow according to claim 1, characterized in that, The prediction of passenger flow based on historical passenger flow includes: Retrieve historical passenger flow data; divide the historical passenger flow data according to time type, and sort the historical passenger flow data in chronological order to obtain passenger flow sequences; among which, passenger flow sequences include: weekday passenger flow sequences, rest day passenger flow sequences, and holiday passenger flow sequences; Obtain the time type of the passenger flow to be predicted; retrieve the traffic prediction model; input the passenger flow sequence of the corresponding time type into the traffic prediction model to obtain the predicted passenger flow sequence; the traffic prediction model is built based on an artificial intelligence model.

5. The escalator adaptive energy-saving operation control system for detecting passenger flow according to claim 4, characterized in that, The traffic prediction model is built based on an artificial intelligence model and includes: Obtain the standard dataset; the standard dataset includes standard input data consistent with the content attributes of the passenger flow sequence, and standard output data consistent with the content attributes of the predicted passenger flow sequence. Select a model framework and a deep learning algorithm from the artificial intelligence model library; construct the model framework based on the deep learning algorithm to obtain a deep learning model; The standard dataset is divided into training, validation, and test sets according to a set ratio; the deep learning model is trained using the training set; the internal parameters of the deep learning model are adjusted using the validation set; and the deep learning model is tested using the test set to obtain test metrics. Obtain the indicator threshold; compare the test indicator with the indicator threshold; if all test indicators are greater than the indicator threshold, then mark the deep learning model as a traffic prediction model; otherwise, rebuild and retrain the traffic prediction model.

6. The escalator adaptive energy-saving operation control system for detecting passenger flow according to claim 1, characterized in that, The process of determining the operation and maintenance inspection time of the escalator based on the prediction results includes: Retrieve the predicted passenger flow sequence; obtain the duration of operation and maintenance monitoring; accumulate and integrate the predicted passenger flow sequence according to the duration to obtain the predicted sequence; The time period corresponding to the minimum value is selected from the predicted sequence as the operation and maintenance inspection time; and the operation and maintenance inspection time is sent to the corresponding technical personnel.

7. A method for adaptive energy-saving operation control of escalators based on passenger flow detection, applied to the adaptive energy-saving operation control system for escalators based on passenger flow detection as described in any one of claims 1-6, characterized in that, include: Data sensors are used to collect passenger flow data entering the escalator area to obtain real-time passenger flow data. The escalator is started and stopped based on real-time passenger flow. The operating speed of the escalator is adjusted according to the real-time passenger flow. Predict passenger flow based on historical passenger volume; The maintenance and inspection time for escalators will be determined based on the forecast results. The adjustment of the escalator's operating speed based on real-time passenger flow includes: Retrieve real-time passenger flow; obtain passenger flow thresholds; compare real-time passenger flow with passenger flow thresholds; wherein, passenger flow thresholds include: primary thresholds and secondary thresholds; When the real-time passenger flow is less than the first-level threshold, the escalator's operating speed is adjusted to low speed; otherwise, the real-time passenger flow is compared with the second-level threshold. When the real-time passenger flow exceeds the secondary threshold, the escalator's operating speed will be adjusted to high speed; otherwise, the escalator's operating speed will be adjusted to medium speed. Methods for obtaining passenger flow thresholds include: The passenger flow thresholds are divided according to time type and further categorized; the time types include: weekdays, rest days, and holidays. Construct the time decay function: ;in, The time offset from the starting point of the time type; The attenuation rate; For periodic parameters; Construct environment correction functions: ;in, Score external factors; and For the Sigmoid function parameter; Constructing intraday cycle correction factors: ;in, Within the day; This refers to peak passenger flow times. It is a daily cycle; and For amplitude parameters; The start time; Constructing a dynamic threshold model: Passenger flow thresholds for different time periods are calculated based on a dynamic threshold model; among which, The threshold for the k-th level of time type i; The baseline threshold constant; This is the seasonal adaptability coefficient; i corresponds to weekdays, rest days, and public holidays. ; indicates a first-level threshold or a second-level threshold; Adjust the coefficient for the time type.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions for performing the steps of the method described in claim 7.

Images