Intelligent management system for digital construction elevator

Abstract

The invention relates to the technical field of intelligent management of construction elevators, in particular to a digital intelligent management system for construction elevators, which comprises an operation monitoring module used for collecting operation state data of each construction elevator in real time through a sensor network, detecting fault conditions and performing early warning; the intelligent scheduling module is used for intelligently distributing transportation tasks based on the passenger flow data, the material transportation demand data and the operation state data of each construction elevator; the predictive maintenance module is used for acquiring key component parameters of each construction elevator, predicting the residual life according to the key component parameters in combination with a fault model, and generating a maintenance work order in advance so as to reduce the fault rate; the authority management module is used for limiting unauthorized personnel to use the construction elevator; and the digital archive management module is used for recording the operation state, the fault history and the maintenance record of the construction elevator and generating a complete equipment life cycle archive. According to the invention, fine and informatization management of the whole life cycle of the construction elevator can be realized.

Description

Technical Field

[0001] This application relates to the field of intelligent management technology for construction elevators, and in particular to a digital intelligent management system for construction elevators. Background Technology

[0002] In construction scenarios, construction elevators are core equipment for personnel transportation and material transfer. Their operating efficiency, safety performance, and maintenance costs directly affect project progress and construction safety.

[0003] In the current construction industry, construction elevator management generally faces many pain points. For example, traditional management methods rely on manual inspections to record operating status, making it impossible to collect key data such as speed, load, and floor positioning in real time. Faults are difficult to detect in a timely manner, leading to prolonged downtime and even safety accidents. Transportation task allocation relies on manual experience, often resulting in some elevators being idle while others are congested. The "post-fault repair" or "regular maintenance" models have different advantages. The former is prone to project stoppages due to sudden faults, increasing maintenance costs, while the latter may lead to resource waste due to over-maintenance or create safety hazards due to insufficient maintenance. When elevators need to be scrapped or faults need to be traced, historical data cannot be quickly retrieved, increasing management costs and decision-making difficulties.

[0004] Therefore, there is an urgent need for a digital construction elevator management system that can achieve intelligent decision-making in order to solve the pain points of traditional management. Summary of the Invention

[0005] Therefore, it is necessary to provide a digital intelligent management system for construction elevators that can achieve refined and information-based management of the entire life cycle of construction elevators, addressing the aforementioned technical issues.

[0006] In a first aspect, this application provides a digital construction elevator intelligent management system, the system comprising: an operation monitoring module, an intelligent scheduling module, a predictive maintenance module, an access control module, and a digital file management module; The operation monitoring module is used to collect real-time operation status data of each construction elevator through a sensor network, and to detect faults and issue early warnings based on the operation status data. The intelligent scheduling module is used to intelligently allocate transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator. The predictive maintenance module is used to obtain the key component parameters of each construction elevator, and based on the key component parameters and the fault model, predict the remaining life and generate maintenance work orders in advance to reduce the failure rate. The access control module is used to restrict unauthorized personnel from using the construction elevator through IC card verification, facial recognition, or password verification. The digital archive management module is used to record the operating status, fault history and maintenance records of construction elevators, and generate a complete equipment lifecycle archive.

[0007] In one embodiment, the digital construction elevator intelligent management system also includes a data visualization module, which is used to display operating curves, early warning logs and maintenance statistics through a large screen or mobile terminal to support managers in carrying out refined and closed-loop supervision.

[0008] In one embodiment, the digital construction elevator intelligent management system further includes a remote diagnostic and support module, which uploads real-time operating status data and fault codes to a cloud platform when a fault occurs, so that experts can view them and provide maintenance solutions.

[0009] In one embodiment, the digital construction elevator intelligent management system also includes a safety early warning module, which uses a camera to identify whether on-site personnel are wearing safety helmets or have entered dangerous areas, and automatically triggers an audible and visual alarm.

[0010] In one embodiment, the digital construction elevator intelligent management system further includes an energy consumption management module, which is used to collect energy consumption data of each construction elevator in real time and provide energy-saving optimization solutions based on operation mode analysis.

[0011] In one embodiment, the operating status data includes operating speed, operating direction, load, current floor, and door open / close status.

[0012] In one embodiment, the digital construction elevator intelligent management system also includes an inspection module, which is used to achieve unattended inspection by using a lightweight inspection robot in conjunction with multimodal perception.

[0013] In one embodiment, the intelligent allocation of transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator includes: Real-time collection of passenger flow data, material transportation demand data, and operating status data of each construction elevator; cleaning and correlation of the collected data; screening out transportation tasks to be assigned and construction elevators that can undertake the tasks. The transportation tasks to be assigned are prioritized using a pre-defined rule engine. For each sorted transportation task, the optimal construction elevator is calculated using a combination model of mixed integer programming and reinforcement learning. Based on the calculated optimal construction elevator, transportation tasks are intelligently allocated.

[0014] In one embodiment, obtaining the key component parameters of each construction elevator, and based on the key component parameters and a fault model to predict the remaining lifespan, generating maintenance work orders in advance to reduce the failure rate includes: Obtain the key component parameters and historical fault data of each construction elevator, and construct a fault model based on the key component parameters and the historical fault data. The fault model includes a statistical sub-model and a machine learning sub-model. Obtain the failure probability output by the statistical sub-model and the remaining lifetime prediction value output by the machine learning sub-model, and adjust the remaining lifetime prediction value according to the failure probability to obtain the remaining lifetime of the key component. Maintenance work orders are generated in advance based on the remaining lifespan of the key components to reduce the failure rate.

[0015] In one embodiment, the step of acquiring key component parameters and historical fault data of each construction elevator, and constructing a fault model based on the key component parameters and the historical fault data, includes: Obtain the key component parameters and historical fault data of each construction elevator; Based on the historical failure data of the key components, the statistical sub-model is trained by fitting the model parameters through maximum likelihood estimation or state transition matrix. Based on the key component parameters, the machine learning sub-model is trained using the actual remaining lifespan of the key component from its current parameter state to failure as a label. By integrating the statistical sub-model and the machine learning sub-model, a fault model is obtained.

[0016] In summary, this application includes the following beneficial technical effects: The system combines real-time early warning from the operation monitoring module with unauthorized control from the access management module, shortening fault warning time, eliminating unauthorized operations, and reducing the incidence of safety accidents. The intelligent scheduling module dynamically allocates transportation tasks based on multi-dimensional data, reducing elevator idle time and passenger waiting time, and improving overall transportation efficiency. The predictive maintenance module predicts remaining lifespan and generates maintenance work orders in advance, enabling proactive maintenance, reducing downtime, and lowering the failure rate. The digital archive management module records the construction elevator's operating status, fault history, and maintenance records, generating a complete equipment lifecycle archive that facilitates traceability and data analysis, providing a reliable basis for management decisions. Through the collaborative work of multiple modules, this system covers the entire elevator usage process, from operation monitoring, scheduling, and maintenance to access management and archive recording, with data sharing and interoperability. It provides a "digital, intelligent, and closed-loop" solution for construction elevator management, achieving refined and information-based management of the entire lifecycle of construction elevators. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the main structure of a digital construction elevator intelligent management system in one embodiment; Figure 2This is a schematic diagram of the structure of a digital construction elevator intelligent management system in another embodiment. Detailed Implementation

[0018] This invention provides a digital intelligent management system for construction elevators.

[0019] The embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0020] In the description of the embodiments disclosed in this invention, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0021] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the intelligent management system for digital construction elevators in this invention includes: an operation monitoring module, an intelligent scheduling module, a predictive maintenance module, an access control module, and a digital file management module; The operation monitoring module is used to collect real-time operation status data of each construction elevator through a sensor network, and to detect faults and issue early warnings based on the operation status data; The intelligent scheduling module is used to intelligently allocate transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator; The predictive maintenance module is used to obtain the key component parameters of each construction elevator, and based on the key component parameters and the failure model, predict the remaining life and generate maintenance work orders in advance to reduce the failure rate. The access control module is used to restrict unauthorized personnel from using construction elevators through IC card verification, facial recognition, or password verification. The digital record management module is used to record the operating status, fault history and maintenance records of construction elevators, generating a complete equipment lifecycle record.

[0022] Specifically, the digital construction elevator intelligent management system includes an operation monitoring module, an intelligent scheduling module, a predictive maintenance module, an access control module, and a digital record management module. The operation monitoring module serves as the system's perception center, its core function being the real-time collection of construction elevator operation data and the generation of fault warnings. A sensor network covers each construction elevator, collecting real-time operation status data including speed, direction, load, current floor, and door open / close status. The raw data collected by the sensors is transmitted to the system backend via wired (Ethernet) or wireless (LoRa, 5G) methods. The backend analyzes the data in real-time and performs threshold comparisons. For example, an overload warning is triggered when the load exceeds the rated load by 10%, and an overspeed warning signal is immediately generated when the operating speed exceeds the rated speed by 15%, simultaneously sending a speed reduction command to the elevator control cabinet. At the same time, the system pushes fault warning information (including warning type, elevator number, and occurrence time) to the management personnel's mobile terminal or on-site control console to ensure timely response.

[0023] The intelligent scheduling module serves as the system's decision-making brain, intelligently allocating transportation tasks based on multi-dimensional data. This solves the problems of traditional scheduling relying on experience and wasting resources. Specifically, it collects real-time passenger flow data (counting passengers through facial recognition via cameras inside the elevator car or through infrared sensors in the waiting areas on each floor), material transportation demand data (submitted by construction teams via the system's app, including material type, weight, origin and destination floors, and priority), and elevator operation status data (synchronously obtained from the operation monitoring module, including the current location, remaining load, operating speed, and malfunction status of each elevator). The collected data is then preprocessed, and transportation tasks are intelligently allocated based on the preprocessed passenger flow data, material transportation demand data, and the operation status data of each construction elevator. The system sends the allocation results (task details, elevator number, and estimated completion time) to the elevator control cabinet and relevant personnel. The elevator adjusts its operating path according to the instructions and provides feedback on the execution results after completing the task.

[0024] The predictive maintenance module achieves proactive maintenance by analyzing key component parameters and predicting faults using fault models, replacing traditional reactive or periodic maintenance. Specifically, it acquires key component parameters and historical data for each construction elevator. Key components include the traction machine (parameters include operating temperature, vibration frequency, and motor current), wire rope (parameters include wear, tension, and number of broken wires), control cabinet (parameters include voltage, current, and contactor operation count), and safety gear (parameters include trigger pressure and response time). Parameters are read through dedicated sensors or the elevator control system. Historical fault data is retrieved from the digital record management module, including the fault types, occurrence times, causes, and maintenance records of key components over the past 1-3 years. Fault models are constructed using key component parameters and historical data, and the remaining lifespan of key components is predicted using these models. When the remaining lifespan of a key component falls below a preset threshold, the system automatically generates a maintenance work order. The work order includes the elevator number to be maintained, the name of the key component, current parameters, remaining lifespan, recommended maintenance time, required spare parts, and maintenance operation instructions. The work order is pushed to the maintenance personnel's mobile device and linked to the digital record management module to ensure traceability.

[0025] The access control module acts as a system security barrier, restricting unauthorized personnel from using the elevators through multiple authentication methods to ensure operational safety and accountability. Specifically, it supports three authentication methods: IC card verification, facial recognition, and password verification, meeting the needs of different scenarios. The system sets granular permissions for each type of authorized personnel, including the elevator range they can operate, the time period they can use, and the type of materials they can transport (e.g., only allowing the transport of people, prohibiting the transport of heavy materials). Simultaneously, it automatically records each authentication (authenticator, time, elevator number, and operation content) and synchronizes it to the digital record management module for easy accountability in the event of a malfunction or accident.

[0026] The digital record management module serves as the system's data warehouse, integrating elevator lifecycle data to form a complete digital record. This supports management decisions and historical traceability. Specifically, it synchronously collects data from other modules, including operational status data, historical fault data, maintenance records, and access control records. All data is stored using a distributed database, supporting efficient reading and writing of massive amounts of data and long-term storage. An independent equipment lifecycle record is generated for each elevator, categorized by year and month. Management personnel can quickly query data by elevator number, time range, and data type through the system's web or mobile terminal. The record data supports management decisions; for example, analyzing historical fault data of a certain elevator reveals that "the traction machine failure frequency is twice that of other elevators," prompting a decision for in-depth inspection. It also allows for the calculation of all elevator maintenance costs and optimization of spare parts procurement plans (increasing inventory of frequently failing components).

[0027] In one embodiment, the digital construction elevator intelligent management system also includes a data visualization module, which is used to display operating curves, early warning logs and maintenance statistics through a large screen or mobile terminal to support managers in conducting refined and closed-loop supervision.

[0028] Specifically, the data visualization module serves as a decision support window for the digital construction elevator intelligent management system. It aims to transform data collected from various system modules into intuitive visual charts, enabling managers to quickly grasp the overall operational status of the elevator and achieve refined, closed-loop supervision. Specifically, the data originates from the operation monitoring module (real-time operating speed, load, and other time-series data), the predictive maintenance module (number of maintenance work orders and completion rate), and the safety early warning module (fault early warning logs), etc. These modules are linked in real-time via API interfaces and visualized on large screens or mobile devices. The large screen can display the 24-hour operating speed trend of the elevator using a line graph, the frequency of daily early warning types using a bar chart, and the maintenance completion rate using a pie chart. The mobile device can display core indicators in a card format, with clicks allowing users to view detailed data. When an "unprocessed" alert appears in the alert log displayed on the large screen / mobile device, the administrator can directly click on the log entry. The system will automatically redirect to the fault details page of the operation monitoring module to view the elevator's real-time video and raw sensor data at the time of the alert. After processing, the administrator marks the alert as "resolved" on the mobile device. The module will automatically update the processing status of the alert log and synchronize it to the digital file management module, forming a closed loop of supervision records and avoiding the omission or duplicate processing of alert information.

[0029] In one embodiment, the digital construction elevator intelligent management system also includes a remote diagnostic and support module, which uploads real-time operating status data and fault codes to the cloud platform when a fault occurs, so that experts can view them and provide maintenance solutions.

[0030] Specifically, the remote diagnostics and support module serves as the system's expert collaboration hub, addressing the pain points of insufficient on-site personnel experience and lengthy expert arrival times in traditional fault handling. It achieves efficient collaboration through a cloud platform, enabling "fault data upload - remote expert analysis - solution feedback." Specifically, after the operation monitoring module detects a fault code, it automatically retrieves real-time data from the five minutes prior to the fault, packages it into an encrypted data packet, and transmits it to the cloud platform via 5G. If the upload fails, it caches the data locally. The cloud platform matches experts according to the fault type and pushes a viewing link containing the fault number. Experts can view real-time data, video playback, and historical archives, edit repair plans online, and synchronize the data to the on-site personnel's mobile devices. On-site personnel mark the repair progress, and experts can provide remote guidance. After the fault is resolved, the module generates a fault review report and archives it in the archive module for future reference.

[0031] In one embodiment, the digital construction elevator intelligent management system also includes a safety early warning module, which uses a camera to identify whether on-site personnel are wearing safety helmets or have entered dangerous areas, and automatically triggers an audible and visual alarm.

[0032] Specifically, the safety early warning module uses computer vision technology to identify personnel violations (not wearing a safety helmet, entering a dangerous area), achieving "automatic identification - audible and visual alarm - early warning push," compensating for the shortcomings of manual inspections. Specifically, high-definition infrared cameras are installed inside the construction elevator car, at landing entrances and exits, and in dangerous areas around the elevator shaft. In addition to the cameras, infrared human body sensors are simultaneously deployed in these dangerous areas. When the camera's recognition accuracy decreases due to dust or obstruction, the infrared sensors can trigger the camera to automatically adjust its angle and turn on supplementary lighting after detecting a person entering, improving recognition accuracy. Based on the YOLOv8 target detection algorithm, the system performs real-time detection of personnel head images captured by the cameras to identify whether personnel on site are wearing safety helmets. Dangerous areas are marked by the cameras, establishing a virtual electronic fence. When the algorithm detects a human silhouette entering the fence (staying for more than 3 seconds), it automatically determines that the person has entered a dangerous area. Upon identification of a violation, an audible and visual alarm (voice prompt + flashing red light) is triggered, and an early warning is simultaneously pushed to the safety officer's mobile device for rapid response.

[0033] In one embodiment, the digital construction elevator intelligent management system also includes an energy consumption management module, which is used to collect energy consumption data of each construction elevator in real time and provide energy-saving optimization solutions based on operation mode analysis.

[0034] Specifically, the energy management module provides personalized energy-saving solutions through energy consumption statistics and analysis to reduce elevator operating costs. Smart energy meters are installed in the elevator power supply circuit to collect energy consumption data every minute. This data, combined with elevator status data (empty, full load, standby, start / stop) from the operation monitoring module, is used to calculate the energy consumption percentage under different states. For example, if an elevator's empty running time accounts for 22% of its total daily running time, but its energy consumption percentage reaches 19%, the main source of energy waste is identified. An energy consumption model is constructed to analyze the energy consumption percentage under empty, full load, and start / stop conditions, fitting a load-energy consumption curve to pinpoint waste points. Solutions are generated for these waste points (such as shutting down some elevators during non-operating periods). After implementation, energy consumption changes are compared, an energy-saving effect report is generated, and the data is synchronized to the digital record management module.

[0035] In one embodiment, the operating status data includes operating speed, operating direction, load, current floor, and door open / close status.

[0036] Specifically, the operating speed is directly related to the risk of elevator overspeed and is the core indicator for determining whether an overspeed warning has been triggered; the operating direction provides the intelligent scheduling module with the elevator's up / down dynamics to avoid scheduling conflicts; the load is the direct basis for overload warnings and also provides a load margin reference for the intelligent scheduling module to allocate material transportation tasks; the current floor ensures accurate elevator positioning to avoid false floor reports that could lead to people boarding the wrong elevator or materials being delivered incorrectly; the door opening / closing status is used to identify malfunctions such as doors not being closed properly or doors being abnormally opened, preventing elevators from falling or trapping people while the doors are open.

[0037] In one embodiment, the intelligent management system for digital construction elevators also includes an inspection module, which enables unattended inspection through a lightweight inspection robot in conjunction with multimodal perception.

[0038] Specifically, the inspection module is the core of unmanned operation and maintenance. It replaces manual inspection with a "lightweight robot + multimodal perception" approach, achieving full coverage inspection of areas that are difficult and pose high safety risks for manual inspection, such as elevator machine rooms, shafts, and landing doors. This improves inspection efficiency and data accuracy while reducing labor costs and operational risks. The robot itself features a lightweight wheeled design and is equipped with a high-definition camera to capture equipment details. Managers set inspection plans through the system backend, including inspection areas, frequency, and locations. The robot generates an environmental map upon its initial scan and subsequently plans its path using the A* algorithm. Upon reaching the preset inspection points, the robot automatically adjusts the camera angle and collects image data according to a pre-set image capture list. The module then uses image recognition algorithms to analyze the inspection images. After each daily inspection, the module automatically generates an inspection report, which is synchronized to the digital file management module as a basis for elevator maintenance and safety assessments.

[0039] In one embodiment, intelligent allocation of transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator includes: Real-time data collection of passenger flow, material transportation demand, and operational status of each construction elevator is performed. The collected data is cleaned and correlated to filter out transportation tasks to be assigned and construction elevators capable of undertaking such tasks. A preset rule engine prioritizes the transportation tasks to be assigned, and for each assigned task, a combined model of mixed integer programming and reinforcement learning is used to calculate the optimal construction elevator to undertake the task. Based on the calculated optimal construction elevator, the transportation task is intelligently assigned.

[0040] Specifically, real-time data collection is performed on passenger flow, material transport demand, and the operational status of each construction elevator. The collected data is cleaned and correlated to remove outliers and establish data relationships (e.g., matching "10 people waiting on the 15th floor" with "the remaining load capacity of the available elevator (number 3) near the 15th floor is 500kg (capable of carrying 6 people)"). Simultaneously, transport tasks to be assigned (e.g., "10 people from the 1st to the 20th floor," "3 tons of steel bars from the ground to the 18th floor") and elevators capable of handling them are selected (excluding elevators that are faulty, overloaded, or under maintenance). A pre-defined rule engine prioritizes transport tasks, with rules including higher priority for personnel transport than material transport, higher-floor tasks over lower-floor tasks, and clustering tasks within the same area. For each ranked task, a combined model of mixed integer programming and reinforcement learning is used to calculate the optimal elevator to handle it. Among them, the mixed integer programming model is used to determine the initial solution with the shortest transportation time and the lowest energy consumption; the reinforcement learning model optimizes the initial solution based on historical scheduling data (such as the completion efficiency and failure rate of a certain elevator in similar tasks in the past 30 days) to avoid scheduling deviations caused by the difference between theoretical optimality and actual operation. For example, if a certain elevator has the shortest theoretical transportation time, but historical data shows that it has a higher failure rate during peak hours, the reinforcement learning model will lower its priority and select the second-best but more stable elevator.

[0041] In one embodiment, key component parameters of each construction elevator are obtained, and based on these parameters and a fault model, the remaining lifespan is predicted to generate maintenance work orders in advance to reduce the failure rate. Obtain the key component parameters and historical fault data of each construction elevator. Based on the key component parameters and historical fault data, construct a fault model, which includes a statistical sub-model and a machine learning sub-model. Obtain the fault probability output by the statistical sub-model and the remaining life prediction value output by the machine learning sub-model. Adjust the remaining life prediction value according to the fault probability to obtain the remaining life of the key components. Based on the remaining life of the key components, generate maintenance work orders in advance to reduce the failure rate.

[0042] Specifically, the system acquires key component parameters and historical fault data for each construction elevator, constructing a fusion fault model combining a statistical sub-model and a machine learning sub-model. This model outputs two core results: the fault probability from the statistical sub-model (e.g., a 25% probability of wire rope failure within the next 7 days) and the remaining life prediction from the machine learning sub-model (e.g., a remaining life of 28 days for the wire rope). The system adjusts the remaining life prediction based on the fault probability. For example, when the fault probability exceeds 20%, the remaining life prediction is reduced by 10% (e.g., from 28 days to 25 days) to ensure a more conservative and safer prediction. When the remaining life of a key component falls below a preset threshold (e.g., a remaining life of the wire rope below 20 days), the system automatically generates a maintenance work order to reduce the failure rate.

[0043] In one embodiment, acquiring the key component parameters and historical fault data of each construction elevator, and constructing a fault model based on the key component parameters and historical fault data includes: Acquire the key component parameters and historical fault data of each construction elevator; based on the historical fault data of the key components, fit the model parameters through maximum likelihood estimation or state transition matrix to train a statistical sub-model; based on the key component parameters, use the actual remaining lifespan of the key component from the current parameter state to the fault as a label to train a machine learning sub-model; fuse the statistical sub-model and the machine learning sub-model to obtain the fault model.

[0044] Specifically, when training the statistical sub-model, based on historical failure data of key components, one of the following models is selected: Weibull lifetime distribution model, Poisson process model, or Markov chain model. The model parameters are fitted using maximum likelihood estimation or a state transition matrix, enabling the statistical sub-model to output the failure probability P of the target component within a predetermined future time window T. The machine learning sub-model is trained using key component parameters as input features (at least four types) and the actual remaining lifespan of the key component from its current parameter state to failure as the label. One of the following models is selected: XGBoost regression, random forest regression, or lightweight LSTM model. The training and test sets are divided in a 7:3 ratio, and the input features are standardized before training, enabling the machine learning sub-model to output the predicted remaining lifespan of the key component. The statistical and machine learning sub-models are then integrated to construct a failure model.

[0045] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A digital construction elevator intelligent management system, characterized in that, include: The system includes a monitoring module, an intelligent scheduling module, a predictive maintenance module, an access control module, and a digital archive management module. The operation monitoring module is used to collect real-time operation status data of each construction elevator through a sensor network, and to detect faults and issue early warnings based on the operation status data. The intelligent scheduling module is used to intelligently allocate transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator. The predictive maintenance module is used to obtain the key component parameters of each construction elevator, and based on the key component parameters and the fault model, predict the remaining life and generate maintenance work orders in advance to reduce the failure rate. The access control module is used to restrict unauthorized personnel from using the construction elevator through IC card verification, facial recognition, or password verification. The digital archive management module is used to record the operating status, fault history and maintenance records of construction elevators, and generate a complete equipment lifecycle archive.

2. The intelligent management system for digital construction elevators according to claim 1, characterized in that, It also includes a data visualization module, which is used to display operating curves, early warning logs and maintenance statistics on large screens or mobile devices to support managers in conducting refined and closed-loop supervision.

3. The intelligent management system for digital construction elevators according to claim 1, characterized in that, It also includes a remote diagnostics and support module, which uploads real-time operating status data and fault codes to the cloud platform when a fault occurs, so that experts can view them and provide repair solutions.

4. The intelligent management system for digital construction elevators according to claim 1, characterized in that, It also includes a safety warning module, which uses cameras to identify whether on-site personnel are wearing safety helmets or have entered dangerous areas, and automatically triggers audible and visual alarms.

5. The intelligent management system for digital construction elevators according to claim 1, characterized in that, It also includes an energy management module, which is used to collect energy consumption data for each construction elevator in real time and provide energy-saving optimization solutions based on operation mode analysis.

6. The intelligent management system for digital construction elevators according to claim 1, characterized in that, The operating status data includes operating speed, operating direction, load, current floor, and door open / close status.

7. The intelligent management system for digital construction elevators according to claim 1, characterized in that, It also includes an inspection module, which uses a lightweight inspection robot in conjunction with multimodal perception to achieve unattended inspection.

8. The intelligent management system for digital construction elevators according to claim 1, characterized in that, The intelligent allocation of transportation tasks based on passenger flow data, material transportation demand data, and the operating status data of each construction elevator includes: Real-time collection of passenger flow data, material transportation demand data, and operating status data of each construction elevator; cleaning and correlation of the collected data; screening out transportation tasks to be assigned and construction elevators that can undertake the tasks. The transportation tasks to be assigned are prioritized using a pre-defined rule engine. For each sorted transportation task, the optimal construction elevator is calculated using a combination model of mixed integer programming and reinforcement learning. Based on the calculated optimal construction elevator, transportation tasks are intelligently allocated.

9. The intelligent management system for digital construction elevators according to claim 1, characterized in that, The process of obtaining key component parameters for each construction elevator, and based on these parameters and a fault model to predict remaining lifespan and generate maintenance work orders in advance to reduce the failure rate includes: Obtain the key component parameters and historical fault data of each construction elevator, and construct a fault model based on the key component parameters and the historical fault data. The fault model includes a statistical sub-model and a machine learning sub-model. Obtain the failure probability output by the statistical sub-model and the remaining lifetime prediction value output by the machine learning sub-model, and adjust the remaining lifetime prediction value according to the failure probability to obtain the remaining lifetime of the key component. Maintenance work orders are generated in advance based on the remaining lifespan of the key components to reduce the failure rate.

10. A digital construction elevator intelligent management system according to claim 9, characterized in that, The process of acquiring key component parameters and historical fault data of each construction elevator, and constructing a fault model based on the key component parameters and the historical fault data, includes: Obtain the key component parameters and historical fault data of each construction elevator; Based on the historical failure data of the key components, the statistical sub-model is trained by fitting the model parameters through maximum likelihood estimation or state transition matrix. Based on the key component parameters, the machine learning sub-model is trained using the actual remaining lifespan of the key component from its current parameter state to failure as a label. By integrating the statistical sub-model and the machine learning sub-model, a fault model is obtained.

Images