Intelligent monitoring method and monitoring system for traction type hoistway construction hoist
Through intelligent monitoring methods and Bayesian network early warning system, safety hazards caused by manual monitoring of traction shaft construction elevators are solved, real-time risk assessment and early warning are realized, and monitoring efficiency and safety are improved.
Patent Information
- Application Number
- CN202411366808.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-12-10
AI Technical Summary
Due to the reliance on manual monitoring, the traction shaft construction elevator has high safety hazards and cannot monitor the operating status and internal conditions of the shaft in real time, resulting in inefficiency and insufficient safety.
Using intelligent monitoring methods, by obtaining operational data and transmitting it to cloud servers, converting timestamps into time series data, filtering and risk assessment are performed, combining Bayesian network to predict risk levels, real-time monitoring and early warning, reducing human-causing Misjudgment improves safety.
It improves the monitoring efficiency and safety of the traction shaft construction elevator, reduces misjudgment caused by human factors, ensures the order and real-time nature of the operating data, and reduces safety hazards.
Smart Images
Figure CN119100225A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of hoisting machines for hoisting shaft construction, and in particular to an intelligent monitoring method and a monitoring system for a traction-type hoisting shaft construction hoisting machine. Background Art
[0002] A traction-type hoist is a vertical transportation equipment used in construction sites, mainly used to transport personnel, materials or tools during construction. It relies on the traction of the traction machine to drive the lifting car up and down through the wire rope. Unlike traditional rack and pinion construction hoists, traction-type hoist is usually installed in the hoistway of a building, similar to a common elevator system, so it has better stability and comfort, and relatively low noise.
[0003] However, during the operation of the traction-type shaft construction elevator, there are still safety hazards such as machine failure, personnel overload, and abnormal protection above the shaft. If the operating status of the elevator cannot be fully monitored and warned in time, safety accidents may occur.
[0004] The traditional monitoring method of traction-type hoistway construction elevators mainly relies on manual monitoring, which is inefficient, with delayed feedback and limited monitoring range. It is impossible to accurately grasp the operating status of the elevator, nor to view the internal and upper protection status of the hoistway in real time. It cannot meet the requirements of intelligent and systematic management, resulting in high safety hazards. Summary of the invention
[0005] In view of the above problems in the prior art, the present invention provides an intelligent monitoring method and monitoring system for a traction-type shaft construction elevator, which solves the problem that the traction-type shaft construction elevator has high safety hazards due to manual monitoring.
[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:
[0007] On the one hand, a method for intelligent monitoring of a traction hoistway construction elevator is provided, comprising the steps of:
[0008] S1, obtaining the operation data of the traction hoist for hoisting construction, and transmitting the operation data to the upper computer;
[0009] S2. The host computer adds a timestamp to the non-time series data in the operation data and converts all the non-time series data into time series data;
[0010] S3, determining whether the timestamp of the time series data in the operation data is missing, if so, supplementing the missing timestamp by interpolation, otherwise proceeding to step S4;
[0011] S4, remove noise from the operation data through a filter, and use the host computer to align the timestamps of the operation data and upload them to the risk assessment and early warning control module of the cloud server;
[0012] S5. Use the risk assessment and early warning control module to obtain the risk level at the time corresponding to the operation data timestamp, and predict the risk level of the traction-type hoistway construction elevator at the next time according to the risk level;
[0013] S6. Operate or maintain the traction shaft construction elevator according to the predicted risk level.
[0014] In this solution, by uploading the real-time operation data to the cloud server for analysis, the monitoring efficiency can be effectively improved, the misjudgment caused by human factors can be reduced, and the safety and reliability can be improved. And by adding timestamps, all non-time series data are converted into time series data, so that each operation data has a collection time, ensuring the sequence of operation data time, so that the cloud server can evaluate and predict the risk level in real time, thereby improving the safety of the traction shaft construction elevator.
[0015] Furthermore, the method for predicting the risk level by the risk assessment and early warning control module comprises the steps of:
[0016] S5.1. Obtain the historical operation data and historical fault records of the traction-type hoistway construction elevator, and obtain the risk factor X and the corresponding risk level S that affect the normal operation of the traction-type hoistway construction elevator according to the expert evaluation method;
[0017] S5.2. Construct a Bayesian network structure based on the risk factor X and the corresponding risk level S, and determine the probability distribution P(X) of the initial state of the traction hoistway construction elevator. 1 );
[0018] S5.3. Determine the time step and data window length m for updating the Bayesian network structure, and expand the Bayesian network into a dynamic Bayesian network based on the sliding window optimization algorithm to obtain the probability distribution of the running data state transition. and the observed probability distribution P(S t |X t );
[0019] in, And tm>0, is the running data with a data window length of m, D t is the running data corresponding to time t, D t-m is the running data corresponding to time tm; X t-1 is the risk factor corresponding to time t-1, S t is the risk level S corresponding to time t, X tis the risk factor corresponding to time t;
[0020] S5.4. Predict the risk level S at time t+1 t+1 :
[0021]
[0022] Among them, α t+1 (X t+1 ), α t (X t ), α 1 (X 1 ) are X t , X t-1 and X 1 The forward probability, X t+1 is the risk factor corresponding to time t+1, is all risk levels from the initial moment to moment t, S 1 is the risk level corresponding to the initial moment.
[0023] In this solution, the sliding window optimization algorithm optimizes the dynamic Bayesian network by selecting a fixed length of running data. This method can ensure that the dynamic Bayesian network always makes predictions based on the latest running data, thereby improving the real-time performance and accuracy of the dynamic Bayesian network.
[0024] Furthermore, the non-time series data of the operation data include the operation direction, maintenance data, and fault data of the traction-type shaft construction elevator; the time series data of the operation data include the operation distance, operation speed, operation acceleration, operation times, vibration data, passenger data, operator operation data, shaft protection data, and shaft foundation pit data of the traction-type shaft construction elevator. By adding timestamps to the operation direction, maintenance data, and fault data to convert them into time series data, all operation data have time attributes, which is convenient for updating the dynamic Bayesian network.
[0025] Furthermore, the operating data D at time t t = {l t ,e t ,n t}, where l t is the running direction, maintenance data, fault data, running distance, running speed, running acceleration, running times and vibration data at time t; e t is the passenger data and operator operation data at time t; n t It is the shaft protection data and shaft foundation pit data.
[0026] Furthermore, t and n tThe information is obtained through cameras installed in the cage of the traction hoist and inside the hoistway. The cameras can respectively judge the number of passengers, whether there is water accumulation and foreign objects in the hoistway foundation pit, etc. through the personnel detection algorithm, object detection algorithm and water accumulation detection algorithm.
[0027] Furthermore, when the number of passengers is greater than 9, the traction-type hoistway construction elevator stops running and issues an overload alarm.
[0028] Furthermore, the risk level S = {low risk state, medium risk state, high risk state}, and the traction-type shaft construction elevator includes three states: normal operation, warning operation and stop operation, which correspond to the three risk levels of low risk state, medium risk state and high risk state respectively.
[0029] Furthermore, the maintenance method of step S6 is to check the operating data in the visualization window on the cloud server, obtain the faulty part of the traction shaft construction elevator, upload the maintenance suggestions in the cloud server and feed back to the maintenance personnel.
[0030] On the other hand, a monitoring system for an intelligent monitoring method of a traction-type shaft construction elevator is provided, comprising a traction-type shaft construction elevator, the traction-type shaft construction elevator comprising a data acquisition module and a hoist cage arranged in the shaft, the data acquisition module being used to obtain operating data and being electrically connected to a host computer, and the host computer being communicatively connected to a cloud server.
[0031] Furthermore, the data acquisition module includes an acceleration sensor, a vibration sensor, a rotary photoelectric encoder, a leveling sensor and two cameras; the acceleration sensor and the leveling sensor are installed on the top of the cage; the vibration sensor and the rotary photoelectric encoder are respectively installed on the motor and the motor output shaft of the traction-type shaft construction elevator; the two cameras are respectively arranged inside the cage and the shaft.
[0032] The present invention discloses an intelligent monitoring method and monitoring system for a traction-type hoistway construction elevator, which has the following beneficial effects:
[0033] The present invention can effectively improve monitoring efficiency, reduce misjudgment caused by human factors, and improve safety and reliability by uploading real-time acquired operation data to a cloud server for analysis. Moreover, all non-time series data are converted into time series data by adding a timestamp, so that each operation data has a collection time, ensuring the sequence of the operation data time, so that the cloud server can evaluate and predict the risk level in real time, thereby improving the safety of the traction hoist for hoist construction. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 It is a flow chart of the intelligent monitoring method of the traction hoistway construction elevator;
[0035] Figure 2 This is the structural diagram of the risk assessment and early warning control module;
[0036] Figure 3 A structural diagram of risk factors;
[0037] Figure 4 is the dynamic Bayesian network transfer graph;
[0038] Figure 5 Schematic diagram of data selection for sliding window optimization algorithm; DETAILED DESCRIPTION
[0039] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.
[0040] Example 1
[0041] refer to Figure 1 This embodiment provides an intelligent monitoring method for a traction-type hoistway construction elevator, comprising the steps of:
[0042] S1. Obtain the operation data of the traction shaft construction elevator in real time and transmit the operation data to the host computer.
[0043] S2. The host computer adds a timestamp to the non-time series data in the operation data and converts all the non-time series data into time series data;
[0044] S3, determining whether the timestamp of the time series data in the operation data is missing, if so, supplementing the missing timestamp by interpolation, otherwise proceeding to step S4;
[0045] Specifically, the non-time series data of the operation data include the operation direction, maintenance data, and fault data of the traction-type shaft construction elevator; the time series data of the operation data include the operation distance, operation speed, operation acceleration, operation times, vibration data, passenger data, operator operation data, shaft protection data, and shaft foundation pit data of the traction-type shaft construction elevator. By adding timestamps to the operation direction, maintenance data, and fault data to convert them into time series data, all operation data have time attributes, which is convenient for updating the dynamic Bayesian network.
[0046] S4, remove noise from the operation data through a filter, and use the host computer to align the timestamps of the operation data and upload them to the risk assessment and early warning control module of the cloud server. After the timestamps are aligned, it is ensured that all time series data can work together to provide a consistent system status.
[0047] The noise in the sensor data is removed by Kalman filtering or low-pass filtering to ensure the smoothness and accuracy of the data. The cloud server has remote monitoring, risk assessment model and data analysis functions. Supervisors can access and monitor the operating status of the traction hoist through the network and view historical operating data records.
[0048] S5. Use the risk assessment and early warning control module to obtain the risk level at the time corresponding to the operation data timestamp, and predict the risk level of the traction shaft construction elevator at the next moment based on the risk level.
[0049] Specifically, refer to Figure 2 ,The method for predicting the risk level by the risk assessment and early warning control module includes the steps of:
[0050] S5.1. Obtain the historical operation data and historical fault records of the traction-type hoistway construction elevator, and obtain the risk factor X and the corresponding risk level S that affect the normal operation of the traction-type hoistway construction elevator according to the expert evaluation method. Figure 3 , risk factor X includes three aspects: the elevator's own state, the cage's load, and the external environment of the shaft. The elevator's own state includes abnormal elevator speed, unstable elevator operation, inaccurate elevator leveling position, and abnormal guide rail components. The cage's load includes the number of people carried too far, abnormal passenger status, and non-standard operation by the operator. The external environment of the shaft includes abnormal protection above the shaft, abnormal shaft foundation pit, and abnormal conditions in the shaft.
[0051] S5.2. Construct a Bayesian network structure based on the risk factor X and the corresponding risk level S, and determine the probability distribution P(X) of the initial state of the traction hoistway construction elevator based on historical data analysis. 1 ).
[0052] S5.3. References Figure 4 and Figure 5 , determine the time step and data window length m of the Bayesian network structure update, and expand the Bayesian network into a dynamic Bayesian network according to the sliding window optimization algorithm to obtain the probability distribution of the running data state transition and the observed probability distribution P(S t |X t). The sliding window optimization algorithm optimizes the dynamic Bayesian network by selecting a fixed length of running data. This method ensures that the dynamic Bayesian network always makes predictions based on the latest running data, thereby improving the real-time performance and accuracy of the dynamic Bayesian network.
[0053] in, And tm>0, is the running data with a data window length of m, D t is the running data corresponding to time t, D t-m is the running data corresponding to time tm; X t-1 is the risk factor corresponding to time t-1, S t is the risk level S corresponding to time t, X t is the risk factor corresponding to time t; risk level S = {low risk state, medium risk state, high risk state}, the traction-type shaft construction elevator includes three states: normal operation, warning operation and stop operation, which correspond to the three risk levels of low risk state, medium risk state and high risk state respectively.
[0054] S5.4. Predict the risk level S at time t+1 t+1 :
[0055]
[0056] Among them, α t+1 (X t+1 ), α t (X t ), α 1 (X 1 ) are X t , X t-1 and X 1 The forward probability, X t+1 is the risk factor corresponding to time t+1, is all risk levels from the initial moment to moment t, S 1 is the risk level corresponding to the initial moment.
[0057] S6, operating or repairing the traction-type hoistway construction elevator according to the predicted risk level. The maintenance method of step S6 is to check the operation data in the visualization window on the cloud server, obtain the fault location of the traction-type hoistway construction elevator, upload the maintenance suggestions in the cloud server and feedback to the maintenance personnel.
[0058] In this embodiment, the operating data D at time t t = {l t ,e t ,n t}, where l tis the running direction, maintenance data, fault data, running distance, running speed, running acceleration, running times and vibration data at time t; e t is the passenger data and operator operation data at time t; n t It is the shaft protection data and shaft foundation pit data. t and n t The data is obtained by cameras installed in the cage and the inside of the shaft of the traction-type hoist. The camera can judge the number of passengers, whether there is water accumulation and foreign objects in the shaft foundation pit, etc. through the personnel number detection algorithm, object detection algorithm and water accumulation detection algorithm. When the number of passengers is greater than 9, the traction-type hoist stops running and issues an overload alarm. t ,e t ,n t The corresponding risk factors are integrated together to improve the comprehensiveness of monitoring.
[0059] Example 2
[0060] This embodiment is further limited on the basis of Embodiment 1, and the specific improvement lies in providing a monitoring system for an intelligent monitoring method of a traction-type shaft construction elevator. For other parts not mentioned, refer to Embodiment 1 or the prior art.
[0061] A monitoring system for an intelligent monitoring method of a traction-type shaft construction elevator comprises a traction-type shaft construction elevator, wherein the traction-type shaft construction elevator comprises a data acquisition module and a hoist cage arranged in the shaft, wherein the data acquisition module is used to obtain operation data and is electrically connected to a host computer, and the host computer is communicatively connected to a cloud server.
[0062] The data acquisition module includes an acceleration sensor, a vibration sensor, a rotary photoelectric encoder, a leveling sensor and two cameras; the acceleration sensor is installed on the top of the cage to obtain the acceleration data of the cage; the vibration sensor is installed on the motor and the gearbox to obtain the vibration data of the motor and the gear; the rotary photoelectric encoder is installed on the output shaft of the traction system motor to detect the running direction, distance and speed data of the traction-type shaft construction elevator; the leveling sensor is installed on the top of the cage to measure the relative position between the top of the cage and the fixed point to determine whether the traction-type shaft construction elevator is stopped in the door opening leveling area; the camera inside the cage obtains the elevator passenger data and the operator's operation data; the camera inside the shaft obtains the status data of the shaft protection, shaft foundation pit and shaft internal components.
[0063] In summary, the beneficial effects of this solution are:
[0064] 1. Through the intelligent monitoring system, the operation of the traction hoist, the inside of the cage, and the inside of the hoistway can be remotely monitored in real time. Compared with traditional manual monitoring, it reduces the cost of monitoring, improves the accuracy and efficiency of monitoring, and can effectively improve the safety and construction benefits of the project construction.
[0065] 2. The operating risk status of the traction shaft construction elevator was evaluated through real-time data from multiple sensors and a dynamic Bayesian network optimized by a sliding window algorithm, and corresponding operations were performed according to the corresponding risk levels to ensure the safety of the elevator operation.
[0066] Although the specific implementation of the invention is described in detail in conjunction with the drawings, it should not be understood as limiting the scope of protection of this patent. Within the scope described in the claims, various modifications and variations that can be made by those skilled in the art without creative work still fall within the scope of protection of this patent.
Claims
1. Intelligent monitoring method for traction hoist construction hoist, It is characterized in that Includes steps: S1, obtaining the operation data of the traction hoist for hoisting construction, and transmitting the operation data to the upper computer; S2. The host computer adds a timestamp to the non-time series data in the operation data and converts all the non-time series data into time series data; S3, determining whether the timestamp of the time series data in the operation data is missing, if so, supplementing the missing timestamp by interpolation, otherwise proceeding to step S4; S4, remove noise from the operation data through a filter, and use the host computer to align the timestamps of the operation data and upload them to the risk assessment and early warning control module of the cloud server; S5. Use the risk assessment and early warning control module to obtain the risk level at the time corresponding to the operation data timestamp, and predict the risk level of the traction-type hoistway construction elevator at the next time according to the risk level; S6. Operate or maintain the traction shaft construction elevator according to the predicted risk level.
2. The intelligent monitoring method for a traction hoistway construction elevator according to claim 1, It is characterized in that The method for predicting risk level by the risk assessment and early warning control module comprises the following steps: S5.
1. Obtain the historical operation data and historical fault records of the traction-type hoist for hoisting construction, and obtain the risk factor X and the corresponding risk level S that affect the normal operation of the traction-type hoist for hoisting construction according to the expert evaluation method; S5.
2. Construct a Bayesian network structure based on the risk factor X and the corresponding risk level S, and determine the probability distribution P(X) of the initial state of the traction hoistway construction elevator. 1 ); S5.
3. Determine the time step and data window length m for updating the Bayesian network structure, and expand the Bayesian network into a dynamic Bayesian network based on the sliding window optimization algorithm to obtain the probability distribution of the running data state transition. and the observed probability distribution P(S t |X t ); in, And tm>0, is the running data with a data window length of m, D t is the operating data corresponding to time t, D t-m is the running data corresponding to time tm; X t-1 is the risk factor corresponding to time t-1, S t is the risk level S corresponding to time t, X t is the risk factor corresponding to time t; S5.
4. Predict the risk level S at time t+1 t+1 : α 1 (X 1 )=P(S 1 |X 1 )P(X 1 ) Among them, α t+1 (X t+1 ), α t (X t ), α 1 (X 1 ) are X t , X t-1 and X 1 The forward probability, X t+1 is the risk factor corresponding to time t+1, is all risk levels from the initial moment to moment t, S 1 is the risk level corresponding to the initial moment.
3. The intelligent monitoring method for a traction-type hoistway construction elevator according to claim 2, It is characterized in that The non-time series data of the operation data include the operation direction, maintenance data, and fault data of the traction-type hoistway construction elevator; The time series data of the operation data include the operation distance, operation speed, operation acceleration, operation times, vibration data, passenger data, operator operation data, shaft protection data and shaft foundation pit data of the traction shaft construction elevator.
4. The intelligent monitoring method for a traction-type hoistway construction elevator according to claim 3, It is characterized in that Operation data D at time t t = {l t ,e t ,n t }, where l t is the running direction, running distance, running speed, running acceleration, running times and vibration data at time t; e t is the passenger data and operator operation data at time t; n t It is the shaft protection data and shaft foundation pit data.
5. The intelligent monitoring method and monitoring system of the traction type hoistway construction elevator according to claim 4, It is characterized in that e t and n t The images are obtained through cameras installed in the cage and inside the hoistway of the traction hoistway construction elevator.
6. The intelligent monitoring method and monitoring system of the traction type hoistway construction elevator according to claim 4, It is characterized in that When the number of passengers is greater than 9, the traction-type hoistway construction elevator stops running and issues an overload alarm.
7. The intelligent monitoring method for a traction-type hoistway construction elevator according to claim 2, It is characterized in that The risk level S = {low risk state, medium risk state, high risk state}, the traction-type shaft construction elevator includes three states: normal operation, warning operation and stop operation, which correspond to the three risk levels of low risk state, medium risk state and high risk state respectively.
8. The intelligent monitoring method for a traction hoistway construction elevator according to claim 1, It is characterized in that The maintenance method of step S6 is to check the operating data in the visualization window on the cloud server, obtain the fault location of the traction shaft construction elevator, upload the maintenance suggestions in the cloud server and feedback to the maintenance personnel.
9. A monitoring system for an intelligent monitoring method for a traction-type hoistway construction elevator according to any one of claims 1 to 8, It is characterized in that It includes a traction-type hoist for hoisting shaft construction, which includes a data acquisition module and a hoist cage arranged in the shaft. The data acquisition module is used to obtain operation data and is electrically connected to a host computer, and the host computer is communicatively connected to a cloud server.
10. The monitoring system of the intelligent monitoring method for traction type hoistway construction elevator according to claim 9, It is characterized in that The data acquisition module includes an acceleration sensor, a vibration sensor, a rotary photoelectric encoder, a leveling sensor and two cameras; The acceleration sensor and the leveling sensor are installed on the top of the cage; the vibration sensor and the rotary photoelectric encoder are respectively installed on the motor and the motor output shaft of the traction-type hoistway construction elevator; and two cameras are respectively arranged inside the cage and the hoistway.