Artificial intelligence enhanced elevator control system and method

Abstract

The invention discloses an artificial intelligence enhanced elevator control system and method, and the system comprises a Lico AI Cube which is provided with a communication interface which is in communication connection with an elevator controller, a microphone and a loudspeaker which are in two-way voice communication with an elevator, a wireless module which is in wireless communication with an intelligent terminal, and a display which is used for displaying elevator parameters and operation states. The Lico AI Cube is used for collecting historical operation data of the elevator through the communication interface; the Lico AI Cube is provided with a microphone and a loudspeaker, and bidirectional voice communication between a user and an elevator system is achieved. The interface enables a user to interact with the system for troubleshooting, maintenance, and performance queries. The Lico AI Cube integrates advanced hardware components including a microphone, a speaker, a display, and a communication interface so as to be able to effectively interact with an elevator controller. The performance of an elevator system is improved in real time by means of a machine learning (ML) algorithm and artificial intelligence (AI) through a neural processing unit (NPU) running on a Linux-based operating system and a central processing unit (CPU) based on an ARM, the downtime of the system is shortened, and the running safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator control, and in particular to an artificial intelligence enhanced elevator control system and method. Background Art

[0002] Elevator systems are critical to the infrastructure of modern buildings and require precise control and high operational reliability. Traditional elevator maintenance and diagnostic methods often lack the ability to efficiently and intelligently handle the operating dynamics of elevators, resulting in potential downtime, inefficient troubleshooting, and reactive maintenance. Summary of the invention

[0003] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art and to provide an artificial intelligence enhanced elevator control system and method.

[0004] According to the first aspect of the present invention, an artificial intelligence enhanced elevator control system includes: Lico AI Cube, wherein the Lico AI Cube is provided with a communication interface for communicating with an elevator controller, a microphone and a speaker for two-way voice communication with the elevator, a wireless module for wireless communication with an intelligent terminal, and a display for displaying elevator parameters and operating status, and the Lico AI Cube collects historical operating data of the elevator through the communication interface; the Lico AI Cube includes a neural processing unit for performing machine learning tasks, a central processing unit based on an operating system, a local machine learning module, a predictive maintenance module, a dynamic parameter adjustment module, and a control and diagnosis module, and the local machine learning module is used to detect anomalies, errors and performance deviations in the elevator system; the predictive maintenance module analyzes the historical operating data through a time series analysis algorithm to predict potential faults and generate preventive maintenance guidance; the dynamic parameter adjustment module uses real-time data analysis and machine learning algorithms to adjust the elevator operating parameters to adapt to changing usage requirements and environmental factors; the control and diagnosis module is used to diagnose and control elevator functions.

[0005] The control method according to the second aspect of the present invention is applied to an artificial intelligence enhanced elevator control system, comprising the following steps:

[0006] Step 1, the Lico AI Cube communicates with the elevator controller to obtain the performance data of the elevator;

[0007] Step 2: Use K-means clustering algorithm and Gaussian mixture model to detect anomalies in the elevator system to obtain performance deviations.

[0008] According to some embodiments of the present invention, step 2 includes parallel steps 2.1 and 2.2, wherein step 2.1 includes: classifying the error information by a natural language processing algorithm to form a corresponding maintenance requirement, and executing step 3.1;

[0009] Step 3.1, generating a maintenance plan, wherein the maintenance plan includes an operation list of maintenance tasks;

[0010] The method further includes step 2.2, performing statistical analysis on the system log by using a time series analysis algorithm, and predicting the elevator performance trend, and then comparing the current performance data with the elevator performance trend to obtain the performance deviation, and executing step 3.2;

[0011] Step 3.2: adjusting the elevator operating state according to the performance deviation to optimize the elevator performance.

[0012] The predictive maintenance method according to the third aspect of the present invention is applied to an artificial intelligence enhanced elevator control system, comprising:

[0013] Step S1, the Lico AI Cube communicates with the elevator controller to obtain historical data of elevator operation and a component database of elevator components, wherein the component database includes the expected service life of the elevator components;

[0014] Step S2, performing statistical analysis on the historical data by using a time series analysis algorithm to predict the current service life of the component;

[0015] Step S3, comparing the current service life of the component with the expected service life of the component to determine whether the component is about to expire;

[0016] If not, return to step S2;

[0017] If the component is about to expire, issue a component expiration warning and execute step S4;

[0018] If the component is expired, a component expiration warning is issued and step S5 is executed;

[0019] Step S4, issuing a preventive maintenance alarm, and executing step S6;

[0020] Step S5, issuing an emergency replacement alarm, and executing step S6;

[0021] Step S6, providing a parts replacement list and maintenance guide.

[0022] A dynamic parameter adjustment method according to a fourth aspect of an embodiment of the present invention is applied to an artificial intelligence enhanced elevator control system, comprising:

[0023] Step 1) Real-time recording of elevator call time period, elevator call frequency, and elevator call floor;

[0024] Step 2) Statistically analyzing the elevator call time period, the elevator call frequency, and the elevator call floor through a machine learning algorithm to obtain a busy elevator call time period, an idle time period, a busy elevator call area, and an idle floor, and establishing a prediction model;

[0025] Step 3) According to the prediction model, the elevator speed is increased during busy elevator call periods; multiple elevators are allocated to operate in busy elevator call areas; during idle periods, the elevator cars are guided to idle floors with low usage rates to optimize the allocation of elevator parking floors to balance the loss of infrastructure.

[0026] According to some embodiments of the present invention, multiple elevators work as an elevator group to find the best parking floor by analyzing elevator status, operation mode, user priority, elevator group coordination mode and energy efficiency.

[0027] According to the embodiment of the present invention, the artificial intelligence enhanced elevator control system and method have at least the following beneficial effects: Lico AI Cube uses neural processing unit (NPU) and central processing unit (CPU) to improve the performance of the elevator system in real time, reduce system downtime and improve operation safety with the help of machine learning (ML) algorithm and artificial intelligence (AI). 1. Lico AICub combines machine learning to detect anomalies, errors and performance deviations in the elevator system based on AI drive (neural processing unit, central processing unit based on operating system), and analyzes historical operation data with time series analysis algorithm to predict potential faults and generate preventive maintenance guidance, so as to achieve early detection and preventive correction. Users can monitor the operation status of the elevator system, real-time alarms and system warnings through the display or the mobile application for wireless communication with Lico AI Cub, so as to respond quickly when problems occur. That is, through real-time monitoring, predictive maintenance and autonomous troubleshooting, the elevator performance is optimized, the operation downtime is reduced, and the safety is improved; it provides an intelligent and efficient solution for operators, engineers and maintenance personnel. 2. The dynamic parameter adjustment module analyzes and adjusts the elevator operation parameters in real time to adapt to the changing usage needs and environmental factors, optimizing the elevator performance while saving energy.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings;

[0030] Figure 1 It is a schematic diagram of an AI-enhanced elevator control system;

[0031] Figure 2 is a flow chart of the control method;

[0032] Figure 3 is a flow chart of the predictive maintenance approach;

[0033] Figure 4 is a schematic diagram of the dynamic parameter adjustment method. DETAILED DESCRIPTION

[0034] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0035] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships 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, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0036] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0037] Reference Figures 1 to 4 The present invention provides an artificial intelligence enhanced elevator control system comprising: Lico AI Cube, which is provided with a communication interface for communicating with an elevator controller, a microphone and a speaker for two-way voice communication with the elevator, a wireless module for wireless communication with an intelligent terminal, and a display for displaying elevator parameters and operating status. The Lico AI Cube collects historical operating data of the elevator through the communication interface; the Lico AI Cube is equipped with a microphone and a speaker to realize two-way voice communication between the user and the elevator system. The interface enables the user to interact with the system for troubleshooting, maintenance, and performance query.

[0038] Lico AI Cube is compatible with smartphones, tablets and laptops through wireless modules, allowing users to monitor elevator status and receive alerts through their devices. The Lico AI Cube device is equipped with the Lico application, which helps users interact with the Lico AI Cube intelligently and assists them in all elevator-related operations.

[0039] The device’s display is a small, high-resolution Organic Light Emitting Diode (OLED) screen that shows system status, alarms and user settings, ensuring intuitive, instant feedback.

[0040] Lico AI Cube communicates with the elevator controller via reliable data transmission protocols including RS485 and CAN bus, facilitating seamless integration into existing elevator systems.

[0041] Connectivity is further extended through wireless communication standards including WiFi, Bluetooth and Near Field Communication (NFC), enabling remote data exchange, user access authentication and control.

[0042] Furthermore, the Lico AI Cube has magnetic parts on its shell, which can be securely mounted on the metal surface in the elevator machine room, ensuring flexible installation options.

[0043] The Lico AI Cube includes a neural processing unit for performing machine learning tasks, a central processing unit based on an operating system, a local machine learning module, a predictive maintenance module, a dynamic parameter adjustment module, and a control and diagnosis module. The local machine learning module is used to detect anomalies, errors, and performance deviations in the elevator system; the predictive maintenance module analyzes the historical operation data through a time series analysis algorithm to predict potential failures and generate preventive maintenance guidance; the dynamic parameter adjustment module uses real-time data analysis and machine learning algorithms to adjust the elevator operating parameters to adapt to changing usage requirements and environmental factors; the control and diagnosis module is used to diagnose and control elevator functions.

[0044] That is, Lico AI Cube integrates advanced hardware components including microphones, speakers, displays, and communication interfaces to effectively interact with elevator controllers. It uses a neural processing unit (NPU) and an ARM-based central processing unit (CPU) running on a Linux-based operating system to use machine learning (ML) algorithms and artificial intelligence (AI) to improve the performance of the elevator system in real time, reduce system downtime, and improve operational safety.

[0045] Furthermore, it also contains a Large Language Model (LLM) that has been optimized to enable seamless communication based on voice or text, making it easy to understand different languages.

[0046] like Figure 2 The present invention further includes a control method, which is applied to an artificial intelligence enhanced elevator control system and comprises the following steps:

[0047] Step 1, the Lico AI Cube communicates with the elevator controller to obtain the performance data of the elevator;

[0048] Step 2: Use K-means clustering algorithm and Gaussian mixture model to detect anomalies in the elevator system to obtain performance deviations.

[0049] Step 2 includes parallel steps 2.1 and 2.2, wherein step 2.1 includes: classifying the error information (serious error, warning, information) through a natural language processing algorithm to form corresponding maintenance requirements (serious error corresponds to emergency maintenance, warning corresponds to planned maintenance), and executing step 3.1;

[0050] Step 3.1, generating a maintenance plan, wherein the maintenance plan includes an operation list of maintenance tasks;

[0051] The method further includes step 2.2, performing statistical analysis on the system log by using a time series analysis algorithm, and predicting the elevator performance trend, and then comparing the current performance data with the elevator performance trend to obtain the performance deviation, and executing step 3.2;

[0052] Step 3.2: adjusting the elevator operating state according to the performance deviation to optimize the elevator performance.

[0053] like Figure 3 The present invention also includes a predictive maintenance method applied to an artificial intelligence enhanced elevator control system, comprising:

[0054] Step S1, the Lico AI Cube communicates with the elevator controller to obtain historical data of elevator operation and a component database of elevator components, wherein the component database includes the expected service life of the elevator components;

[0055] Step S2, performing statistical analysis on the historical data by using a time series analysis algorithm to predict the future state of the system;

[0056] Step S3, compare the current service life of the component with the expected service life of the component to determine whether the component is about to expire (for determination of expiration, for example, a life difference X = expected service life of the component - current service life is set, and when the life difference is less than a value A, it can be determined that the component is about to expire, and the value A needs to be determined according to the specific application situation);

[0057] If not, return to step S2;

[0058] If the component is about to expire, issue a component expiration warning and execute step S4;

[0059] If the component is expired, a component expiration warning is issued and step S5 is executed;

[0060] Step S4, issuing a preventive maintenance alarm, and executing step S6;

[0061] Step S5, issuing an emergency replacement alarm, and executing step S6;

[0062] Step S6, providing a parts replacement list and maintenance guide.

[0063] That is, Lico AI Cube uses time series forecasting to analyze historical data and predict future states. It maintains a comprehensive database of all elevator components, including the expected service life of these components. By comparing current data with expected service life data, warnings are issued for components that are about to expire, and alarms are issued for components that have expired. Each component has related installation, troubleshooting, and replacement documents (based on these documents, parts replacement lists and maintenance guides are given), which are available in multiple formats such as images, Word documents, PDFs, text files, videos, and audio files. These documents answer common questions, help detect potential faults early and perform preventive maintenance, thereby preventing unexpected downtime. LicoAI Cube assists maintenance personnel by listing expired parts and providing guidance on replacement or inspection procedures to ensure that maintenance work is comprehensive and effective.

[0064] That is, Lico AI Cub combines machine learning with AI drive (neural processing unit, operating system-based central processing unit) to detect anomalies, errors, and performance deviations in the elevator system. It also combines time series analysis algorithms to analyze historical operating data to predict potential failures and generate preventive maintenance guidance, thereby achieving a double insurance of early detection and preventive correction.

[0065] The present invention also includes a dynamic parameter adjustment method, which is applied to an artificial intelligence enhanced elevator control system, comprising:

[0066] Step 1) Real-time recording of elevator call time period, elevator call frequency, and elevator call floor through user flow sensors, occupancy sensors, environmental sensors, IoT sensors, etc.

[0067] Step 2) Statistically analyzing the elevator call time period, the elevator call frequency, and the elevator call floor data through a machine learning algorithm to obtain a busy elevator call time period, an idle time period, a busy elevator call area, and an idle floor, and establishing a prediction model;

[0068] Step 3) According to the prediction model, the elevator speed is increased during busy elevator call periods; multiple elevators are allocated to operate in busy elevator call areas; during idle periods, the elevator cars are guided to idle floors with low usage rates to optimize the allocation of elevator parking floors to balance the loss of infrastructure.

[0069] That is, Lico AI Cube is an intelligent management system that aims to improve the efficiency and responsiveness of building operations through advanced automation technology. By leveraging real-time data analysis and machine learning algorithms, the system dynamically adjusts key operating parameters to adapt to changing usage needs and environmental factors. For example, Lico AI Cube continuously monitors elevator traffic patterns - such as peak hours, user waiting times, and demand on specific floors - to autonomously calibrate elevator speeds and operating routes. During busy hours, it may prioritize faster ascent / descent speeds, or allocate more cars to busy traffic areas, while reducing the speed of idle elevators during idle hours to save energy. Similarly, it optimizes the allocation of parking floors by guiding cars to idle floors with low usage based on real-time occupancy sensors, balancing the loss of various infrastructures and reducing the time users wait for elevators.

[0070] The system’s energy-saving modes are equally adaptive: it might dim lighting in unoccupied areas, adjust HVAC output based on ambient temperature fluctuations, or scale back non-essential systems during off-peak hours (all while ensuring user comfort and safety). By collecting data from elevator controllers, IoT sensors, historical trends, and predictive models, the Lico AI Cube not only reacts to immediate conditions, but also predicts future needs, continuously optimizing its decisions over time. This creates a harmonious ecosystem that seamlessly balances energy efficiency, operational life, and user satisfaction.

[0071] In some embodiments, multiple elevators work as an elevator group to find the best parking floor by analyzing elevator status, operating mode, user priority, elevator group coordination mode, and energy efficiency. When elevators are in a group, parking spaces are dynamically allocated. Lico AI Cube uses real-time data to improve elevator efficiency by intelligently determining the best parking floor during idle periods. The search path for finding the best parking floor includes elevator status (in operation, faulty, under maintenance), operating mode, user priority, elevator coordination mode within the group (such as parallel or series), and energy efficiency.

[0072] For single-person elevators, high-demand areas are predicted using factors such as time of day, traffic trends, and user behavior. For example, parking near the lobby during the morning rush or near the cafeteria during lunch reduces wait times by pre-positioning the elevator closer to expected calls. For group elevator systems, multiple elevator units use reinforcement learning to balance distribution across floors. This minimizes redundant movements, avoids clustering, and dynamically adapts to elevator call events. Benefits include shorter wait times, lower energy consumption, and constantly learning from changing patterns, the system maintains optimal performance, making it ideal for smart buildings designed to optimize efficiency and sustainability.

[0073] The control and diagnostic module is able to initiate various diagnostic tests, including door operation test, unexpected car movement protection (UCMP) test and self-learning run, to verify the functionality of the elevator subsystems and ensure smooth operation.

[0074] It is easy for those skilled in the art to understand that the above preferred embodiments can be freely combined and superimposed without conflict.

[0075] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or directly or indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. An artificial intelligence enhanced elevator control system, characterized in that: include: Lico AI Cube, which is provided with a communication interface for communicating with the elevator controller, a microphone and a speaker for two-way voice communication with the elevator, a wireless module for wireless communication with the smart terminal, and a display for displaying the operation status of the elevator. The LicoAI Cube collects the historical operation data of the elevator through the communication interface; The Lico AICube includes a neural processing unit for performing machine learning tasks, a central processing unit based on an operating system, a local machine learning module, a predictive maintenance module, a dynamic parameter adjustment module, and a control and diagnosis module. The local machine learning module is used to detect anomalies, errors, and performance deviations in the elevator system; The predictive maintenance module analyzes the historical operation data through a time series analysis algorithm to predict potential failures and generate preventive maintenance guidance; The dynamic parameter adjustment module uses real-time data analysis and machine learning algorithms to adjust elevator operating parameters to adapt to changing usage requirements and environmental factors; The control and diagnosis module is used to diagnose and control elevator functions.

2. The artificial intelligence enhanced elevator control system according to claim 1, characterized in that: The shell of the Lico AICube is provided with magnetic parts to facilitate installation on the metal wall in the elevator room.

3. A control method, applied to the artificial intelligence enhanced elevator control system according to claim 1, characterized in that: The steps include: Step 1, the Lico AI Cube communicates with the elevator controller to obtain the performance data of the elevator; Step 2: Use K-means clustering algorithm and Gaussian mixture model to detect anomalies in the elevator system to obtain performance deviations.

4. The control method according to claim 3, characterized in that: Step 2 includes parallel steps 2.1 and 2.2, wherein step 2.1 includes: classifying the error information by a natural language processing algorithm to form corresponding maintenance requirements, and executing step 3.1; Step 3.1, generating a maintenance plan, wherein the maintenance plan includes an operation list of maintenance tasks; The method further includes step 2.2, performing statistical analysis on the system log by using a time series analysis algorithm, and predicting the elevator performance trend, and then comparing the current performance data with the elevator performance trend to obtain the performance deviation, and executing step 3.2; Step 3.2: adjusting the elevator operating state according to the performance deviation to optimize the elevator performance.

5. A predictive maintenance method, applied to the artificial intelligence enhanced elevator control system according to claim 1, characterized in that: include: Step S1, the Lico AICube communicates with the elevator controller to obtain historical data of elevator operation and a component database of elevator components, wherein the component database includes the expected service life of the elevator components; Step S2, performing statistical analysis on the historical data by using a time series analysis algorithm to predict the current service life of the component; Step S3, comparing the current service life of the component with the expected service life of the component to determine whether the component is about to expire; If not, return to step S2; If the component is about to expire, issue a component expiration warning and execute step S4; If the component is expired, a component expiration warning is issued and step S5 is executed; Step S4, issuing a preventive maintenance alarm, and executing step S6; Step S5, issuing an emergency replacement alarm, and executing step S6; Step S6, providing a parts replacement list and maintenance guide.

6. A dynamic parameter adjustment method, applied to the artificial intelligence enhanced elevator control system according to claim 1, characterized in that: include: Step 1) Real-time recording of elevator call time period, elevator call frequency, and elevator call floor; Step 2) Statistically analyzing the elevator call time period, the elevator call frequency, and the elevator call floor through a machine learning algorithm to obtain a busy elevator call time period, an idle time period, a busy elevator call area, and an idle floor, and establishing a prediction model; Step 3) according to the prediction model, the elevator speed is increased during the busy elevator call period; in the busy elevator call area, multiple elevators are allocated to operate; During idle periods, the elevator cars are guided to idle floors with low usage rates to optimize the allocation of elevator floors and balance the loss of infrastructure.

7. The dynamic parameter adjustment method according to claim 6, characterized in that: Multiple elevators work as a group to find the best parking floor by analyzing elevator status, operating mode, user priority, elevator group coordination mode and energy efficiency.

Images