Urban elevator cluster electricity-saving monitoring system based on AI learning

Abstract

The invention discloses an urban elevator cluster power-saving monitoring system based on AI learning, relates to the field of elevator control and energy saving, and aims to solve the problems that in a traditional system, a single elevator runs disorderly, a power-saving strategy is not iterated and is very fixed, AI application is not wide, and monitoring is not completely covered. The system comprises a centralized control management unit, a transmission layer and a field control unit. The centralized control management unit comprises a monitoring platform and a sensing layer AI learning module, the monitoring platform can realize data visualization, abnormity alarm and remote intervention, and the sensing layer AI learning module is responsible for data preprocessing, strategy model training and iterative optimization. The field control unit can collect elevator energy consumption, people flow and running state data and can also execute start-stop control, speed adjustment, standby dormancy and other power-saving actions. According to the invention, elevator cluster co-work scheduling and continuous electricity-saving efficiency are realized, the operation and maintenance cost of the elevator is reduced, and the elevator waiting time of the user is shortened.

Description

Technical Field

[0001] This invention relates to the field of elevator control and energy-saving technology, specifically to an AI-based urban elevator cluster energy-saving monitoring system. Background Technology

[0002] Current elevator monitoring technology suffers from numerous technical challenges and is insufficient to meet the energy consumption optimization and intelligent control requirements of various elevator usage scenarios, including cities, residential communities, and commercial complexes. Most systems employ a single-elevator independent control model supplemented by remote monitoring, lacking a unified control mode and the ability to output overall scheduling strategies. This results in multiple elevators operating out of sequence, leading to high empty-run rates and significant energy waste. Furthermore, existing systems suffer from incomplete monitoring coverage. The transmission layer is only responsible for data forwarding, disconnected from the AI ​​decision-making of centralized control and the actions of on-site control. On-site units are functionally limited, offering only data acquisition or simple control capabilities, unable to collaborate with the AI ​​learning module at the centralized control end. This prevents the formation of a complete process from data acquisition to decision-making and subsequent optimization, thus limiting the energy-saving effect and intelligence level of elevator clusters. Summary of the Invention

[0003] The purpose of this invention is to provide an AI-based energy-saving monitoring system for urban elevator clusters that can solve the above-mentioned problems.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An AI-based urban elevator cluster energy-saving monitoring system includes a centralized control management unit, a transmission layer, and a field control unit.

[0006] The centralized control management unit is interconnected with the field control unit through the transmission layer; the centralized control management unit is used to output the hardware and software combination of AI power saving strategy; the transmission layer is used for low-latency connection of decision instructions and execution actions; the field control unit is used to collaboratively complete elevator data acquisition and power saving control operations.

[0007] Preferably, the centralized control management unit includes a monitoring platform and a perception layer AI learning module.

[0008] Preferably, the monitoring platform includes PC-based management software, mobile-based management software, a data visualization module, and an alarm module.

[0009] Preferably, the perception layer AI learning module includes an LSTM deep learning model, a data preprocessing module, and a policy optimization module.

[0010] Preferably, the transmission layer includes a 5G communication module, an Ethernet gateway, and an edge computing node; the uplink transmission delay of the collected data to the centralized control management unit in the transmission layer is ≤500ms, and the downlink transmission delay of the power-saving strategy to the field control unit is ≤300ms.

[0011] Preferably, the transmission layer encrypts the transmitted data using AES-256 encryption; at the same time, real-time data is temporarily stored through edge computing nodes to avoid data congestion in the centralized control management unit.

[0012] Preferably, the field control unit includes a data acquisition unit and a power-saving control unit.

[0013] Preferably, the data acquisition unit includes an energy consumption sensor, an infrared people flow counter, and an operating status sensor. The energy consumption sensor is used to collect elevator voltage, current, and power data. The infrared people flow counter is used to count people flow data. The operating status sensor is used to collect elevator load, speed, and start / stop status data.

[0014] Preferably, the energy-saving control unit includes an elevator controller interface module, a start / stop control unit, a speed adjustment unit, and a standby / sleep unit.

[0015] Beneficial effects

[0016] This invention achieves intelligent energy-saving technology for elevator clusters in different urban scenarios. Simultaneously, through an AI learning module, it can generate energy-saving strategies in real time, enabling coordinated scheduling of elevator clusters and reducing energy waste. Furthermore, this invention can collect and securely transmit elevator operation data, providing timely warnings of abnormal energy consumption. This helps property management reduce maintenance costs, shortens waiting times for users, promotes the development of the elevator industry, and benefits the country and its people.

[0017] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the system structure of the present invention;

[0019] Figure 2 This is a schematic diagram of the centralized control management unit structure of the present invention;

[0020] Figure 3 This is a schematic diagram of the field control unit structure of the present invention;

[0021] 1-Centralized control management unit; 2-Transmission layer; 3-Field control unit; 4-Monitoring platform; 5-Perception layer AI learning module; 6-Data acquisition unit; 7-Power saving control unit. Detailed Implementation

[0022] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of the present invention, it should be noted that unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art will understand the specific meaning of the above terms in this invention according to the specific circumstances. Furthermore, the technical features involved in the different embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0023] like Figures 1 to 3 As shown, an AI-based urban elevator cluster energy-saving monitoring system includes a centralized control management unit 1, a transmission layer 2, and a field control unit 3.

[0024] The centralized control management unit 1 is interconnected with the field control unit 3 through the transmission layer 2 to realize data interaction. The centralized control management unit 1 is used to output the hardware and software combination of AI power saving strategy to avoid the problem of disordered operation of a single elevator. The transmission layer 2 is used to connect decision instructions and execution actions with low latency to ensure that the power saving strategy is implemented in real time. The field control unit 3 is used to coordinate the completion of elevator data acquisition and power saving control operation, forming a complete closed loop from acquisition to decision, decision to execution.

[0025] Specifically, the centralized control management unit 1 includes a monitoring platform 4 and a perception layer AI learning module 5.

[0026] Specifically, the monitoring platform 4 includes PC-based management software, mobile-based management software, a data visualization module, and an alarm module. The monitoring platform 4 has the following functions: displaying elevator energy consumption data and operating status data uploaded by the on-site control unit 3; receiving and visualizing energy-saving strategies output by the perception layer AI learning module 5; triggering audible and visual alarms and SMS alarms when the elevator experiences abnormal energy consumption, and supporting remote intervention by staff.

[0027] Specifically, the perception layer AI learning module 5 includes an LSTM deep learning model, a data preprocessing module, and a strategy optimization module. The perception layer AI learning module 5 has the following functions: performing preprocessing operations such as cleaning and normalizing the historical and real-time data uploaded by the field control unit 3; training a mapping model from scenario to energy consumption and from energy consumption to strategy based on traffic flow, time period, and load data, and outputting the corresponding cluster power saving strategy; iteratively optimizing the power saving strategy every 24 hours based on the newly uploaded elevator operation data to improve the adaptability of the strategy to the actual scenario.

[0028] Specifically, the transport layer 2 includes a 5G communication module, an Ethernet gateway, and an edge computing node; the transport layer 2 has the following functions: to realize low-latency data transmission, wherein the uplink transmission delay of the collected data to the centralized control management unit 1 is ≤500ms, and the downlink transmission delay of the power saving strategy to the field control unit 3 is ≤300ms.

[0029] Specifically, the transport layer 2 uses AES-256 encryption to encrypt the transmitted data to prevent data leakage; real-time data is temporarily stored through edge computing nodes to avoid data congestion in the centralized control management unit 1.

[0030] Specifically, the field control unit 3 includes a data acquisition unit 6 and a power-saving control unit 7.

[0031] Specifically, the data acquisition unit 6 includes an energy consumption sensor, an infrared people flow counter, and an operating status sensor. The energy consumption sensor is used to collect elevator voltage, current, and power data; the infrared people flow counter is used to count people flow data; and the operating status sensor is used to collect elevator load, speed, and start / stop status data. The data acquisition unit 6 has the following functions: real-time acquisition of energy consumption data for single elevators and elevator clusters at a sampling frequency of 100ms / time; acquisition of elevator floor call, car load, and operating speed status data; and uploading the collected data to the centralized control management unit 1 via the transmission layer 2 after packaging the various types of data.

[0032] Specifically, the energy-saving control unit 7 includes an elevator controller interface module, a start / stop control unit, a speed regulation unit, and a standby / sleep unit. The energy-saving control unit 7 has the following functions: receiving AI energy-saving strategies issued by the centralized control management unit 1; executing energy-saving actions such as start / stop control, speed regulation, and standby / sleep, where start / stop control shuts down redundant elevators during off-peak hours, speed regulation reduces the elevator's running speed when lightly loaded, and standby / sleep cuts off the power to the car lighting and ventilation when there are no calls; and transmitting the strategy execution results back to the centralized control management unit 1.

[0033] Example:

[0034] The application scenario is an urban commercial complex with 20 floors and 12 Mitsubishi LEHY-4 elevators. An AI-based energy-saving monitoring system for the urban elevator cluster is deployed.

[0035] Then, the field control unit 3 is deployed as follows: Each elevator is equipped with a data acquisition unit 6, which includes an energy consumption sensor, an infrared people flow counter, and an operating status sensor. The energy consumption sensor is model SCT-013, used to collect elevator voltage, current, and power in real time. The infrared people flow counter is model HC-SR501, which is installed in the car and at the floor entrance to count people flow. The operating status sensor is connected to the existing elevator controller to detect load, speed, and start / stop information. Then, the energy-saving control unit 7 is directly connected to the elevator controller to realize elevator start / stop, speed adjustment, and standby sleep control.

[0036] The transport layer 2 deploys 5G gateways and edge computing nodes in the building's computer room, with the 5G gateway model being Huawei 5GCPEPro3; it also includes data transmission rules, which are used for real-time control commands to be transmitted via 5G, and historical energy consumption data to be transmitted in batches via Ethernet. Its edge computing nodes temporarily store real-time data for one hour to avoid data congestion in the centralized control management unit 1.

[0037] The monitoring platform 4 of the centralized control management unit 1 is deployed on the PC terminal of the property center and also supports mobile access, i.e., access via a mini-program. It can display the energy consumption, operating status and strategy execution results of 12 elevators in real time. The AI ​​learning module 5 of the perception layer imports the historical data of the complex over the past 12 months, including the variation patterns of weekday morning peak hours (7:30-9:30), evening peak hours (17:30-19:30), and weekend pedestrian flow (30% decrease). After training with an LSTM model, it outputs the initial cluster energy-saving strategy.

[0038] When the system is running, the AI ​​learning module 5 of the perception layer generates corresponding power-saving strategies based on the flow of people at different times, which are then sent from the centralized control management unit 1 to the power-saving control unit 7 of the field control unit 3 via the transmission layer 2 for execution.

[0039] During the morning rush hour from 7:30 to 9:30, when the passenger flow density is ≥80%, the energy-saving control unit 7 starts 10 elevators and maintains a running speed of 2.5m / s. When working, the call allocation prioritizes elevators that are close by and whose load rate does not exceed 60% to reduce empty running energy consumption.

[0040] During off-peak hours (10:00-17:00 / 19:30-22:00), when the passenger density is 30%-60%, only 5 elevators will be activated, while the remaining 7 will enter sleep mode. When the elevators are in operation, they will be awakened by the power-saving control unit 7 within 3 seconds after receiving a call.

[0041] During the off-peak hours of 22:00 to 7:30 the next day, when the passenger density is ≤10%, only 2 elevators will be kept running in a loop, traversing 20 floors every 30 minutes. The power supply to the other elevators will be cut off by the power-saving control unit 7 for non-essential loads.

[0042] During operation, energy consumption data is collected every 100ms and uploaded to the centralized control management unit 1. If the energy consumption of an elevator exceeds the predicted optimal threshold due to wear and tear on a component, the monitoring platform 4 immediately triggers an alarm and promptly notifies maintenance personnel for inspection. Simultaneously, a temporary policy is issued to limit the elevator's load to control energy consumption increases. Every 24 hours, the perception layer AI learning module 5 uses the new data uploaded by the data collection unit 6 to update the training model and optimize energy-saving strategies, achieving real-time updates and real-time energy-saving effects.

[0043] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0044] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. An AI-based urban elevator cluster energy-saving monitoring system, characterized in that, It includes a centralized control management unit (1), a transmission layer (2), and a field control unit (3); The centralized control management unit (1) is interconnected with the field control unit (3) through the transmission layer (2); the centralized control management unit (1) is used to output the hardware and software combination of AI power saving strategy; the transmission layer (2) is used for low-latency connection of decision instructions and execution actions; the field control unit (3) is used to collaboratively complete elevator data acquisition and power saving control operations.

2. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 1, characterized in that, The centralized control management unit (1) includes a monitoring platform (4) and a perception layer AI learning module (5).

3. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 2, characterized in that, The monitoring platform (4) includes PC-based management software, mobile management software, a data visualization module, and an alarm module.

4. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 2, characterized in that, The perception layer AI learning module (5) includes an LSTM deep learning model, a data preprocessing module, and a policy optimization module.

5. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 1, characterized in that, The transmission layer (2) includes a 5G communication module, an Ethernet gateway, and an edge computing node; the uplink transmission delay of the data collected in the transmission layer (2) to the centralized control management unit (1) is ≤500ms, and the downlink transmission delay of the power saving strategy to the field control unit (3) is ≤300ms.

6. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 5, characterized in that, The transmission layer (2) encrypts the transmitted data using AES-256 encryption; at the same time, it temporarily stores real-time data through edge computing nodes to avoid data congestion in the centralized control management unit (1).

7. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 1, characterized in that, The field control unit (3) includes a data acquisition unit (6) and a power saving control unit (7).

8. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 7, characterized in that, The data acquisition unit (6) includes an energy consumption sensor, an infrared people flow counter, and an operating status sensor. The energy consumption sensor is used to collect elevator voltage, current, and power data. The infrared people flow counter is used to count people flow data. The operating status sensor is used to collect elevator load, speed, and start / stop status data.

9. The urban elevator cluster energy-saving monitoring system based on AI learning according to claim 7, characterized in that, The energy-saving control unit (7) includes an elevator controller interface module, a start / stop control unit, a speed adjustment unit, and a standby / sleep unit.

Images