Elevator lifting state monitoring method and system

Abstract

The invention discloses an elevator lifting state monitoring method and system. The method comprises the steps that equipment operation data, behavior data of passengers in an elevator car and elevator car environment data in the elevator lifting process are collected; calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the operation state of the elevator according to the safe operation index; according to the passenger behavior data, utilizing a pre-trained deep learning network model to identify a passenger behavior mode; the elevator passenger state is analyzed according to the passenger behavior mode, and the elevator environment state is analyzed according to the elevator car environment data; and according to the elevator running state, the elevator passenger state and the elevator environment state, elevator lifting is comprehensively monitored. According to the embodiment of the invention, various data sources can be collected and analyzed, and real-time monitoring and early warning of safe operation of the elevator are realized, so that the intelligent level and the use safety of the elevator are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of elevators, and in particular to a method and system for monitoring the lifting and lowering status of an elevator. Background Art

[0002] As an indispensable vertical transportation tool in modern buildings, the safety and reliability of elevators directly affect the life safety and user experience of passengers. With the acceleration of urbanization, the frequency of elevator use is increasing, so it is particularly important to monitor the operating status of elevators in real time. At present, traditional elevator monitoring methods mainly rely on regular maintenance and inspections, and usually cannot capture abnormal conditions during the operation of elevators in real time. This is a problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide an elevator lifting status monitoring method and system to solve the deficiencies in the prior art, which can collect and analyze multiple data sources to achieve real-time monitoring and early warning of the safe operation of the elevator, thereby improving the intelligence level and safety of the elevator.

[0004] An embodiment of the present application provides a method for monitoring an elevator lifting state, the method comprising: Collect equipment operation data, passenger behavior data and cabin environment data during the elevator lifting process; Calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the elevator operation status based on the safe operation index; According to the occupant behavior data, using a pre-trained deep learning network model, identifying occupant behavior patterns; Analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; The elevator lifting is comprehensively monitored according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0005] Optionally, calculating the safe operation index of the elevator according to the equipment operation data includes: Obtain the maximum continuous normal operation days of the elevator from the last maintenance to the current time and the number of failures of the elevator from the last maintenance to the current time in the equipment operation data, and quantify the maximum continuous normal operation days and the reciprocal of the number of failures as sub-scores, respectively, wherein the last maintenance of the elevator is maintenance within a fixed maintenance cycle that is not related to the repair; Obtaining the current load of the elevator in the equipment operation data, and calculating the difference between the preset rated load and the current load of the elevator; Obtaining the car vibration frequency in the equipment operation data, and calculating the ratio of a preset safety threshold frequency to the car vibration frequency; Obtaining the current elevator running speed in the equipment running data, and calculating the ratio of the preset maximum elevator running speed to the current elevator running speed; The elevator's safe operation index is calculated based on the calculated sub-scores, differences and ratios.

[0006] Optionally, analyzing the elevator operation status based on the safety operation index includes: It is determined whether the safety operation index falls within a preset safety range. If so, the elevator operation state is determined to be a non-intervention state; otherwise, the elevator operation state is determined to be an intervention-required state.

[0007] Optionally, analyzing the elevator occupant status according to the occupant behavior pattern and analyzing the elevator environment status according to the car environment data includes: Determine whether the passenger behavior pattern belongs to a preset abnormal behavior pattern, and if so, determine that the elevator passenger state is an intervention-required state, otherwise determine that the elevator passenger state is a non-intervention state; It is determined whether the elevator environment data has any abnormality in the preset environment parameters. If so, the elevator environment state is determined to be an intervention-required state; otherwise, the elevator environment state is determined to be a non-intervention state.

[0008] Optionally, the comprehensive monitoring of the elevator lifting according to the elevator operation state, the elevator occupant state and the elevator environment state includes: Calculating a comprehensive intervention index of the elevator according to the intervention-required state of the elevator operation state, the elevator occupant state, and the elevator environment state; The intervention level corresponding to the comprehensive intervention index is determined, and the elevator is given a graded warning and intervened according to the intervention level to achieve comprehensive monitoring of the elevator lifting.

[0009] Optionally, the comprehensive intervention index of the elevator is the sum of the weights of the state types corresponding to the intervention-requiring state, wherein the state types include: elevator operation state, elevator occupant state and elevator environment state, the weight of the elevator operation state is greater than the weight of the elevator occupant state, and the weight of the elevator occupant state is greater than the weight of the elevator environment state.

[0010] Another embodiment of the present application provides an elevator lifting state monitoring system, the system comprising: The collection module is used to collect equipment operation data, passenger behavior data in the car, and car environment data during the elevator lifting process; A calculation module, used to calculate a safe operation index of the elevator according to the equipment operation data, and analyze the elevator operation status based on the safe operation index; an identification module, for identifying the occupant behavior pattern based on the occupant behavior data using a pre-trained deep learning network model; An analysis module, configured to analyze the elevator occupant status according to the occupant behavior pattern, and to analyze the elevator environment status according to the car environment data; The monitoring module is used to comprehensively monitor the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0011] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0012] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0013] Compared with the prior art, the present invention provides a method for monitoring the lifting and lowering status of an elevator, which collects equipment operation data, passenger behavior data in a car, and car environment data during the lifting and lowering process of the elevator; calculates the safe operation index of the elevator according to the equipment operation data, and analyzes the elevator operation status based on the safe operation index; identifies passenger behavior patterns according to the passenger behavior data using a pre-trained deep learning network model; analyzes the elevator passenger status according to the passenger behavior pattern, and analyzes the elevator environment status according to the car environment data; comprehensively monitors the lifting and lowering of the elevator according to the elevator operation status, the elevator passenger status, and the elevator environment status, so that a variety of data sources can be collected and analyzed to achieve real-time monitoring and early warning of the safe operation of the elevator, thereby improving the intelligence level and safety of use of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A hardware structure block diagram of a computer terminal of an elevator lifting state monitoring method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an elevator lifting state monitoring method provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an elevator lifting state monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0016] The embodiment of the present invention firstly provides a method for monitoring the lifting state of an elevator, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0017] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of an elevator lifting state monitoring method provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0018] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the elevator lifting state monitoring method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0019] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0020] See also Figure 2 The embodiment of the present invention provides a method for monitoring the lifting state of an elevator, which may include the following steps: S201, collecting equipment operation data, passenger behavior data in the elevator car, and elevator car environment data during the elevator lifting process; This step is the basis for monitoring the elevator's lifting status, and aims to fully understand the comprehensive status of the elevator during operation through real-time collection of multi-dimensional data. A specific implementation method may include: 1. Equipment operation data collection: Install high-precision sensors on key components of the elevator (such as motors, brakes, guide rails, cars, etc.). These sensors can monitor various operation data of the elevator in real time, including motor speed, current load, car vibration frequency, operating speed, fault status, etc.

[0021] The collected raw signals are processed through data filtering and denoising algorithms (such as Kalman filtering) to ensure the accuracy and reliability of the data. This step is critical and helps eliminate environmental interference and equipment noise.

[0022] Set the frequency (e.g., sampling once per second) to continuously monitor the elevator operation status and ensure dynamic update of real-time data. Use timestamps to mark the data for timing matching during subsequent analysis.

[0023] 2. Collecting passenger behavior data in the car: Install high-resolution cameras in the car and use computer vision technology to identify passenger behavior patterns (such as crowding status, passengers getting on and off the car, etc.). Use face recognition and image segmentation technology to collect the number of passengers and their dynamics.

[0024] In addition to video surveillance, sound sensors and pressure sensors are set up to analyze the sounds of passengers' activities and the pressure changes in the car, and then determine whether the passengers have abnormal behavior (such as impatience, crowding, etc.). Each passenger behavior data needs to be attached with corresponding labels, such as the time of getting on and off the elevator, the change in the number of passengers, etc., to provide a basis for subsequent pattern recognition.

[0025] 3. Cabin environment data collection: Install temperature sensors, humidity sensors, light sensors, and gas sensors (such as CO2, smoke detectors, etc.) to monitor the environmental parameters in the cabin in real time. Upload environmental data to the central monitoring system via wireless networks to ensure the real-time and accessibility of data. Not only pay attention to the static data of the environment, but also respond to environmental changes (such as abnormal temperature, increased carbon dioxide concentration, etc.) and make real-time records.

[0026] 4. Final data aggregation and storage: Store the three types of data to ensure the efficiency of data query and subsequent analysis. The design takes into account the rapid retrieval of data, cross-dimensional query capabilities, and data security. Data visualization tools can also be used to display various elevator operating indicators, passenger behavior, and environmental status in real time, which is convenient for subsequent analysis and decision support.

[0027] This step provides a comprehensive and detailed data foundation for monitoring the elevator's lifting status. By collecting equipment operation data, mechanical failures can be monitored and operating efficiency can be optimized; by collecting passenger behavior data, potential safety hazards can be identified in advance and the passenger experience can be improved; by monitoring environmental data, abnormal conditions in the car can be responded to in a timely manner to ensure passenger safety.

[0028] S202, calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the operation status of the elevator based on the safe operation index; This step is a crucial part of the elevator lifting status monitoring process, which aims to evaluate the safety of the elevator in a quantitative way and provide decision support. The calculation of the safe operation index (SOI) comprehensively considers multiple operating indicators of the elevator, so that the safety status of the elevator can be expressed as a single value, which is convenient for monitoring and analysis.

[0029] In this step, various equipment operation data are used as the basis for calculating SOI, including the number of consecutive normal operation days of the elevator, the number of failures, the current load, the vibration frequency of the car and the operating speed. The quantitative conversion of these data enables complex operating conditions to be processed at the numerical level. By setting preset safety standards and performance indicators, and applying weighted formulas, each quantitative data is comprehensively evaluated. This can not only reflect the normal operation of the elevator, but also detect potential problems in a timely manner, forming a dynamic monitoring mechanism. Based on the calculated safe operation index, by comparing with the preset safety range, it is determined whether the elevator's operating state is "intervention required" or "non-intervention state". This judgment will directly affect the subsequent management and maintenance decisions of the elevator.

[0030] Specifically, the safe operation index of the elevator is calculated according to the equipment operation data, and the maximum continuous normal operation days of the elevator from the last maintenance to the current time and the number of failures of the elevator from the last maintenance to the current time in the equipment operation data can be obtained, and the reciprocals of the maximum continuous normal operation days and the number of failures are quantified as sub-scores respectively, wherein the last maintenance of the elevator is maintenance within a fixed maintenance cycle that is not related to maintenance; This step provides a basic score for operational safety by analyzing the elevator's continuous normal operation time and the number of failures. These two indicators comprehensively reflect the stability and reliability of the elevator in actual operation. The maximum number of continuous normal operation days reflects the health of the elevator, while the number of failures directly affects safety. By quantifying these data, the operation cycle and potential risks of the elevator can be accurately evaluated.

[0031] Obtaining the current load of the elevator in the equipment operation data, and calculating the difference between the preset rated load and the current load of the elevator; In this step, the actual load of the elevator is compared with its rated load capacity, and the difference between the two is calculated to evaluate whether the elevator is within the safe operating range. By analyzing the load difference, overloading can be effectively prevented and the elevator can be ensured to operate within the safe load range, thereby protecting the safety of the equipment and passengers.

[0032] Obtaining the car vibration frequency in the equipment operation data, and calculating the ratio of a preset safety threshold frequency to the car vibration frequency; This step aims to determine the stability and operating status of the elevator by analyzing the vibration frequency of the car. The ratio of vibration frequencies can reveal potential mechanical failures or abnormal operation. The calculation of the ratio can help to warn of mechanical problems early, allowing maintenance personnel to take necessary preventive measures before failure occurs and extend the service life of the elevator.

[0033] Obtaining the current elevator running speed in the equipment running data, and calculating the ratio of the preset maximum elevator running speed to the current elevator running speed; By calculating the ratio of the current operating speed to the maximum safe speed, the elevator is ensured to operate within the set safe speed range, thereby ensuring the safety of passengers. Speed ​​monitoring can be used to identify in real time whether the elevator is overspeeding or experiencing other abnormalities, thereby improving the safety of elevator operation and preventing accidents caused by overspeeding.

[0034] The safe operation index of the elevator is calculated based on the calculated sub-scores, differences and ratios. A calculation formula for the safe operation index of an elevator can be: Among them, the is the safety operation index, is the sub-score for the maximum number of consecutive uptime days, is the preset rated load, the is the current load of the elevator, is the vibration frequency of the car (which can be collected in real time by a vibration sensor installed in the car, and the vibration mode of the car is usually analyzed by frequency analysis), The preset safety threshold frequency (set according to industry standards and elevator-related technical specifications, usually set by the manufacturer, and can be based on the design and operating environment of the equipment), is the preset maximum elevator running speed, is the current elevator running speed, is the sub-score of the inverse of the number of failures, is a tiny constant (usually set to a very small positive number such as 0.001), is a regularization constant (e.g. K=10) to adjust the dimension of the formula (to ensure that the value of the safety operation index has a reasonable range for easy comparison and analysis). , , , , is the corresponding weight coefficient.

[0035] By integrating operating data of different dimensions (such as stability, load, vibration, speed, etc.) into a single indicator, complex operating conditions can be analyzed and compared under a unified standard; SOI can reflect the safety status of the elevator in real time, help maintenance personnel identify potential risks and anomalies, and take timely measures to reduce safety hazards; the safe operation index provides a scientific basis for elevator management and maintenance decisions, helping managers to formulate effective monitoring and maintenance strategies; the digitization of SOI enables relevant personnel (such as maintenance personnel, property managers and users) to quickly understand the operating status of the elevator and promote information transmission and sharing.

[0036] Specifically, based on analyzing the elevator operation state according to the safety operation index, it can be determined whether the safety operation index falls within the preset safety range. If it does, the elevator operation state is determined to be a non-intervention state, otherwise, the elevator operation state is determined to be an intervention-required state. Assume that after investigation and experiments, the research team found that the elevator's safety operation index should be close to 70 to 90 during normal operation, and in the case of a fault or high risk, the SOI should be lower than 50 (intervention is possible if it is lower than 70, but the risk is lower), then the preset safety range is [70,90].

[0037] In this step, you first need to obtain the calculated safety operation index (SOI). Then, compare this value with the preset safety range. The preset safety range is usually a range set based on historical data, industry standards and equipment performance indicators to guide the safety management of elevators.

[0038] If the SOI falls within the preset safety range, it means that the elevator is in normal operation, and various indicators such as the number of consecutive normal operation days, load, vibration frequency and operating speed are at an acceptable safety level. Therefore, the elevator's operating state can be determined to be "non-intervention state". This means that no additional intervention or maintenance measures are required, and the elevator can continue to operate normally. If the SOI does not fall within the preset safety range, it means that the elevator has potential safety risks and may require inspection, maintenance or other intervention measures. At this time, the elevator's operating state is determined to be "intervention required state", and maintenance personnel need to pay attention to such situations and take necessary inspection and maintenance measures to ensure the safety and reliability of the elevator.

[0039] In practical applications, since there are mature elevator operation status monitoring technologies in the prior art, this application can further refine the operation status classification through the existing elevator operation status monitoring technology and the safety operation index. For example, when the monitoring result of the existing elevator operation status monitoring technology is a normal state (no intervention) and the safety operation index corresponds to normal (no intervention), the comprehensive analysis of the elevator operation status is a normal state (no intervention state, the lowest risk); when the monitoring result of the existing elevator operation status monitoring technology is a normal state (no intervention) and the safety operation index corresponds to abnormal (intervention required), the comprehensive analysis of the elevator operation status is an abnormal state (intervention required state, low risk); when the monitoring result of the existing elevator operation status monitoring technology is an abnormal state (intervention required) and the safety operation index corresponds to abnormal (intervention required), the comprehensive analysis of the elevator operation status is an abnormal state (intervention required state, high risk). It should be noted that when the monitoring result of the existing elevator operation status monitoring technology is a normal state (no intervention), the corresponding safety operation index will also be normal (no intervention). In addition, the monitoring result of the existing elevator operation status monitoring technology is a preliminary monitoring, which has certain errors. Further combination with the safety operation index can improve the monitoring accuracy, thereby further reducing the risk of elevator operation.

[0040] S203, identifying the occupant behavior pattern using a pre-trained deep learning network model according to the occupant behavior data; In this step, the system analyzes the passenger behavior data inside the elevator car. Passenger behavior data can include the time when passengers get on and off the car, the number of passengers, the time they stay in the car, the changes in passengers' body posture (such as standing, sitting, leaning against the car wall, etc.), and even identify the emotional state of individual passengers (such as anxiety, relaxation).

[0041] With this data, the system uses a deep learning model that has been trained with a large amount of data to identify and analyze the occupant's behavior patterns. This model is usually based on a convolutional neural network (CNN) or a recurrent neural network (RNN), the latter of which is particularly suitable for processing time series data, such as changes in occupant behavior. The deep learning model accepts occupant behavior data as input, extracts features and patterns through a multi-layer network structure, and finally generates a classification or label for occupant behavior (such as "normal", "abnormal", "anxious", etc.).

[0042] By identifying the behavior patterns of passengers, the system can promptly detect potential abnormal behaviors (for example, overly anxious passengers may press buttons multiple times or attempt to force open the door), and take appropriate measures (such as issuing warnings, notifying monitoring personnel, etc.), thereby improving the safety of passengers; deep learning behavior pattern recognition can help the elevator system better understand the needs of passengers, and then conduct intelligent scheduling and services. For example, if it is recognized that the passenger has not pressed the target floor button for a long time, the system can actively ask the passenger's needs; through the analysis of passenger behavior, the property management party can obtain detailed data on passenger usage habits, and then optimize elevator maintenance and scheduling to improve operational management efficiency; after identifying specific behavior patterns, the system can set corresponding rules to form an intelligent early warning mechanism. For example, when a passenger is found to have abnormal behavior, the system can send early warning information to the management personnel in real time to facilitate timely response.

[0043] Specifically, a high-definition camera can be installed inside the elevator car to capture a video stream of the passenger's behavior in real time. Frames at fixed intervals (e.g., 5 frames per second) are extracted from the real-time video to reduce the computational burden. Image enhancement processing (e.g., denoising, contrast adjustment) is performed to ensure the quality of the extracted data. The processed image frames are input into a pre-trained convolutional neural network (CNN) to extract action features (e.g., passenger standing, walking, sitting, etc.). The extracted action features are analyzed using a time series model (e.g., long short-term memory network, LSTM) to understand the passenger's action changes and behavior patterns. A deep learning model based on facial expression recognition is used to analyze the passenger's expression and identify the emotional state (e.g., anxiety, relaxation, happiness, etc.). Emotions are combined with action states to form comprehensive behavioral features as input for classification. The above-extracted comprehensive behavioral features are input into a fully connected classification layer (e.g., a softmax layer), and the model outputs the passenger's behavior pattern (e.g., "normal", "anxious", "urgent", etc.) based on the training data.

[0044] This occupant behavior pattern recognition method based on video stream analysis can effectively utilize the visual data inside the elevator to realize dynamic monitoring and analysis of occupant behavior, improve elevator safety and passenger experience, and does not rely on any additional sensors, making the system implementation easier and more economical.

[0045] S204, analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; At this stage, the system aims to determine the status of passengers in the elevator car by analyzing the occupant's behavior pattern, and at the same time, evaluate whether there are any abnormalities in the elevator's working environment in combination with the environmental data in the car. The two analysis results will be integrated to provide a basis for the safe operation of the elevator. By identifying the occupant's behavior pattern, the system can determine the occupant's status. For example, whether there are emotions such as anxiety, impatience or uneasiness, which may reflect the occupant's sense of security in the operation of the elevator, or the existence of urgent physical or behavioral abnormalities, etc. In this process, the system will compare the occupant's current behavior with the preset behavior pattern to ensure effective identification. The cabin environmental data may include temperature, humidity, light intensity, smoke concentration, etc. When these environmental parameters are compared with the preset standards, the system can identify whether there are any abnormal conditions (such as high temperature, insufficient light or smoke, etc.).

[0046] Specifically, it can be determined whether the passenger behavior pattern belongs to a preset abnormal behavior pattern. If so, the elevator passenger state is determined to be an intervention-required state; otherwise, the elevator passenger state is determined to be a non-intervention state. The occupant behavior patterns identified by deep learning or other machine learning methods can be compared with a set of preset abnormal behavior patterns. These preset abnormal behavior patterns can be based on past data analysis or industry standards, and are designed to quickly identify behaviors that may affect occupant safety. If the identified behavior pattern matches the abnormal pattern, the system will mark the occupant status as "intervention required". In this case, the system can automatically activate the alarm mechanism or notify the management staff to check and intervene; conversely, if it is identified as normal behavior, the system will mark the status as "no intervention status".

[0047] It is determined whether the elevator environment data has any abnormality in the preset environment parameters. If so, the elevator environment state is determined to be an intervention-required state; otherwise, the elevator environment state is determined to be a non-intervention state.

[0048] In this step, the system monitors the environmental data in the car in real time and compares it with the preset environmental parameters. These environmental parameters can include temperature, air quality, noise level, smoke concentration, etc. When the actual monitoring value exceeds the normal range, the system will determine the environmental status of the car. If the identified environmental data does not meet the preset standards, the system will mark the elevator environmental status as "intervention status" and take necessary measures, such as ventilation, alarm or notification of maintenance personnel; if the environmental data is normal, the system will mark it as "no intervention status".

[0049] S205, comprehensively monitoring the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0050] At this stage, the system integrates data on the elevator's operating status, passenger status, and car environment status to comprehensively monitor the elevator's overall operation. By comprehensively analyzing this data, the system can make an accurate assessment of the elevator's safety and comfort, and issue an alarm or recommend intervention measures when necessary. Among them, the elevator operating status: including data such as the elevator's speed, load, and fault records, to help determine whether the elevator is in normal working condition; the elevator passenger status: by identifying the passenger's behavior patterns, determine whether the passenger has anxiety, urgency, and other situations that require attention; the elevator environment status: analyze the environmental data in the car (such as temperature, air quality, etc.) to ensure that passengers take the elevator in a comfortable environment. By combining these three states, the system can form a complete assessment of the elevator's operating status and decide whether intervention is needed.

[0051] Specifically, the comprehensive intervention index of the elevator may be calculated according to the intervention-required state of the elevator operation state, the elevator occupant state, and the elevator environment state; The comprehensive intervention index of the elevator is calculated by quantifying the state types marked as "intervention required" in the elevator operation state, occupant state and environmental state analyzed above. This index provides a basis for subsequent intervention decisions and indicates the safety level and intervention needs of the elevator in the current state.

[0052] Among them, the comprehensive intervention index of the elevator can be the sum of the weights of the state types corresponding to the intervention state, that is, the intervention state is quantified as 1, and the non-intervention state is quantified as 0. The state types include: elevator operation state, elevator occupant state and elevator environment state. The weight of the elevator operation state is greater than the weight of the elevator occupant state, and the weight of the elevator occupant state is greater than the weight of the elevator environment state. For example, the weight of the elevator operation state is 0.5, the weight of the occupant state is 0.3, and the weight of the environment state is 0.2. These weights can be flexibly adjusted according to specific actual conditions.

[0053] The intervention level corresponding to the comprehensive intervention index is determined, and the elevator is given a graded warning and intervened according to the intervention level to achieve comprehensive monitoring of the elevator lifting.

[0054] Based on the calculated comprehensive intervention index, the system will compare it with the preset intervention level to determine what level of intervention is needed for the current situation. This classification can be low, medium, high, etc., corresponding to different response strategies.

[0055] Standard thresholds for each level can be predefined. For example, a comprehensive intervention index between 0 and 0.5 is a low level, indicating that the elevator is in good condition; 0.5 to 0.8 is a medium level, indicating that there is a potential risk and needs attention; more than 0.8 is a high level, indicating that the elevator has a serious problem and requires immediate intervention. Corresponding response measures are formulated according to different levels. The low level can only record and monitor, the medium level can automatically prompt relevant personnel, and the high level will start the emergency response procedure, and the maintenance personnel need to be notified immediately for inspection and processing. During the operation of the elevator, the system can continuously monitor the changes in the comprehensive intervention index and dynamically adjust the intervention strategy according to the changes to ensure the safety and comfort of the passengers.

[0056] It can be seen that the equipment operation data, the passenger behavior data in the car and the car environment data during the elevator lifting process are collected; the elevator safety operation index is calculated according to the equipment operation data, and the elevator operation status is analyzed based on the safety operation index; according to the passenger behavior data, the passenger behavior pattern is identified using a pre-trained deep learning network model; the elevator passenger status is analyzed according to the passenger behavior pattern, and the elevator environment status is analyzed according to the car environment data; according to the elevator operation status, the elevator passenger status and the elevator environment status, the elevator lifting is comprehensively monitored, so that multiple data sources can be collected and analyzed, and real-time monitoring and early warning of the safe operation of the elevator can be realized, thereby improving the intelligence level and safety of the elevator.

[0057] Another embodiment of the present invention provides an elevator lifting state monitoring system, see Figure 3 , the system may include: The collection module 301 is used to collect equipment operation data, passenger behavior data in the elevator car, and elevator car environment data during the elevator lifting process; A calculation module 302, configured to calculate a safe operation index of the elevator according to the equipment operation data, and analyze the elevator operation status based on the safe operation index; The identification module 303 is used to identify the occupant behavior pattern based on the occupant behavior data using a pre-trained deep learning network model; An analysis module 304, configured to analyze the elevator occupant status according to the occupant behavior pattern, and analyze the elevator environment status according to the car environment data; The monitoring module 305 is used to comprehensively monitor the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0058] It can be seen that the equipment operation data, the passenger behavior data in the car and the car environment data during the elevator lifting process are collected; the elevator safety operation index is calculated according to the equipment operation data, and the elevator operation status is analyzed based on the safety operation index; according to the passenger behavior data, the passenger behavior pattern is identified using a pre-trained deep learning network model; the elevator passenger status is analyzed according to the passenger behavior pattern, and the elevator environment status is analyzed according to the car environment data; according to the elevator operation status, the elevator passenger status and the elevator environment status, the elevator lifting is comprehensively monitored, so that multiple data sources can be collected and analyzed, and real-time monitoring and early warning of the safe operation of the elevator can be realized, thereby improving the intelligence level and safety of the elevator.

[0059] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0060] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps: S201, collecting equipment operation data, passenger behavior data in the elevator car, and elevator car environment data during the elevator lifting process; S202, calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the operation status of the elevator based on the safe operation index; S203, identifying the occupant behavior pattern using a pre-trained deep learning network model according to the occupant behavior data; S204, analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; S205, comprehensively monitoring the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0061] It can be seen that the equipment operation data, the passenger behavior data in the car and the car environment data during the elevator lifting process are collected; the elevator safety operation index is calculated according to the equipment operation data, and the elevator operation status is analyzed based on the safety operation index; according to the passenger behavior data, the passenger behavior pattern is identified using a pre-trained deep learning network model; the elevator passenger status is analyzed according to the passenger behavior pattern, and the elevator environment status is analyzed according to the car environment data; according to the elevator operation status, the elevator passenger status and the elevator environment status, the elevator lifting is comprehensively monitored, so that multiple data sources can be collected and analyzed, and real-time monitoring and early warning of the safe operation of the elevator can be realized, thereby improving the intelligence level and safety of the elevator.

[0062] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0063] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0064] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program: S201, collecting equipment operation data, passenger behavior data in the elevator car, and elevator car environment data during the elevator lifting process; S202, calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the operation status of the elevator based on the safe operation index; S203, identifying the occupant behavior pattern using a pre-trained deep learning network model according to the occupant behavior data; S204, analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; S205, comprehensively monitoring the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

[0065] It can be seen that the equipment operation data, the passenger behavior data in the car and the car environment data during the elevator lifting process are collected; the elevator safety operation index is calculated according to the equipment operation data, and the elevator operation status is analyzed based on the safety operation index; according to the passenger behavior data, the passenger behavior pattern is identified using a pre-trained deep learning network model; the elevator passenger status is analyzed according to the passenger behavior pattern, and the elevator environment status is analyzed according to the car environment data; according to the elevator operation status, the elevator passenger status and the elevator environment status, the elevator lifting is comprehensively monitored, so that multiple data sources can be collected and analyzed, and real-time monitoring and early warning of the safe operation of the elevator can be realized, thereby improving the intelligence level and safety of the elevator.

[0066] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A method for monitoring the lifting state of an elevator, characterized in that: The method comprises: Collect equipment operation data, passenger behavior data and cabin environment data during the elevator lifting process; Calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the elevator operation status based on the safe operation index; According to the occupant behavior data, using a pre-trained deep learning network model, identifying occupant behavior patterns; Analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; The elevator lifting is comprehensively monitored according to the elevator operation status, the elevator occupant status and the elevator environment status.

2. The method according to claim 1, characterized in that Calculating the safe operation index of the elevator according to the equipment operation data includes: Obtain the maximum continuous normal operation days of the elevator from the last maintenance to the current time and the number of failures of the elevator from the last maintenance to the current time in the equipment operation data, and quantify the maximum continuous normal operation days and the reciprocal of the number of failures as sub-scores, respectively, wherein the last maintenance of the elevator is maintenance within a fixed maintenance cycle that is not related to the repair; Obtaining the current load of the elevator in the equipment operation data, and calculating the difference between the preset rated load and the current load of the elevator; Obtaining the car vibration frequency in the equipment operation data, and calculating the ratio of a preset safety threshold frequency to the car vibration frequency; Obtaining the current elevator running speed in the equipment running data, and calculating the ratio of the preset maximum elevator running speed to the current elevator running speed; The elevator's safe operation index is calculated based on the calculated sub-scores, differences and ratios.

3. The method according to claim 2, characterized in that The step of analyzing the elevator operation status based on the safety operation index includes: It is determined whether the safety operation index falls within a preset safety range. If so, the elevator operation state is determined to be a non-intervention state; otherwise, the elevator operation state is determined to be an intervention-required state.

4. The method according to claim 3, characterized in that Analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data, includes: Determine whether the passenger behavior pattern belongs to a preset abnormal behavior pattern, and if so, determine that the elevator passenger state is an intervention-required state, otherwise determine that the elevator passenger state is a non-intervention state; It is determined whether the elevator environment data has any abnormality in the preset environment parameters. If so, the elevator environment state is determined to be an intervention-required state; otherwise, the elevator environment state is determined to be a non-intervention state.

5. The method according to claim 4, characterized in that The comprehensive monitoring of the elevator lifting according to the elevator operation state, the elevator passenger state and the elevator environment state includes: Calculating a comprehensive intervention index of the elevator according to the intervention-required state of the elevator operation state, the elevator occupant state, and the elevator environment state; The intervention level corresponding to the comprehensive intervention index is determined, and the elevator is given a graded warning and intervened according to the intervention level to achieve comprehensive monitoring of the elevator lifting.

6. The method according to claim 5, characterized in that The comprehensive intervention index of the elevator is the sum of the weights of the state types corresponding to the intervention-required state, wherein the state types include: elevator operation state, elevator occupant state and elevator environment state, the weight of the elevator operation state is greater than the weight of the elevator occupant state, and the weight of the elevator occupant state is greater than the weight of the elevator environment state.

7. An elevator lifting state monitoring system, characterized in that: The system comprises: The collection module is used to collect equipment operation data, passenger behavior data in the car, and car environment data during the elevator lifting process; A calculation module, used for calculating a safe operation index of the elevator according to the equipment operation data, and analyzing the elevator operation status based on the safe operation index; an identification module, for identifying the occupant behavior pattern based on the occupant behavior data using a pre-trained deep learning network model; An analysis module, used for analyzing the elevator occupant status according to the occupant behavior pattern, and analyzing the elevator environment status according to the car environment data; The monitoring module is used to comprehensively monitor the elevator lifting according to the elevator operation status, the elevator occupant status and the elevator environment status.

8. The system according to claim 7, characterized in that The computing module is specifically used for: Obtain the maximum continuous normal operation days of the elevator from the last maintenance to the current time and the number of failures of the elevator from the last maintenance to the current time in the equipment operation data, and quantify the maximum continuous normal operation days and the reciprocal of the number of failures as sub-scores, respectively, wherein the last maintenance of the elevator is maintenance within a fixed maintenance cycle that is not related to the repair; Obtaining the current load of the elevator in the equipment operation data, and calculating the difference between the preset rated load and the current load of the elevator; Obtaining the car vibration frequency in the equipment operation data, and calculating the ratio of a preset safety threshold frequency to the car vibration frequency; Obtaining the current elevator running speed in the equipment running data, and calculating the ratio of the preset maximum elevator running speed to the current elevator running speed; The elevator's safe operation index is calculated based on the calculated sub-scores, differences and ratios.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 6 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 6.

Images