Method and system for identifying running state of vertical elevator

Abstract

The invention discloses a vertical elevator running state recognition method and system, and relates to the field of performance monitoring, the vertical elevator running state recognition system comprises an elevator management platform, and the elevator management platform is internally provided with a data acquisition module, an acquisition transmission module, a state analysis module, a state recognition module and a fault early warning module; the data collection module is used for collecting three-axis acceleration data in the elevator running process and constructing an elevator state original data set. The acquisition and transmission module is used for data transmission; the state analysis module is used for setting corresponding identification index parameters according to a historical elevator state original data set and constructing a state identification model; the state recognition module is used for recognizing the elevator running state according to the elevator state original data set; the fault early warning module is used for performing voice early warning processing according to the recognition result; the real-time performance and accuracy of elevator fault recognition are improved to a certain degree.

Description

Technical Field

[0001] The present invention relates to the technical field of performance monitoring, and in particular to a method and system for identifying the operating status of a vertical elevator. Background Art

[0002] In recent years, with the development of economy and society, high-rise buildings are everywhere, and elevators have been widely used and have become an indispensable tool for people to travel. However, during the operation of the elevator, sudden elevator failures may occur due to power failures, high adaptability, high operating frequency, aging of elevator components not replaced in time, unsafe elevator riding behavior, etc. Therefore, how to timely identify the abnormal operating status of the elevator during operation and remind the carrier to inspect and repair is a very important matter, which will greatly improve the safety of elevator operation to a certain extent.

[0003] After searching, the invention patent with Chinese patent number CN110054049A discloses a method and system for detecting the running status of an elevator. The system includes: an elevator shaft wall and an elevator car. The installation wall corresponding to each floor is installed with a controller, a wireless transmitting device and a near-field transceiver; at least two near-field transceivers are arranged at equal intervals in the installation wall corresponding to each floor along the up and down movement direction of the elevator, and the interval distance is a preset distance value; the elevator car is installed with a wireless receiving device and an elevator master control device, and the wireless receiving device is installed on the installation side wall of the elevator car, and the installation position of the wireless receiving device corresponds to that of the wireless transmitting device, and the installation side wall is a side wall perpendicular to the elevator entry and exit direction. The present invention reduces the installation precision and improves the detection efficiency and accuracy of the elevator running status information.

[0004] Compared with the prior art, the invention patent with Chinese patent number CN110054049A can improve the detection efficiency of the corresponding elevator operation status by distributing the detection of elevator arrival floor information to controllers and near-field transceiver devices installed on the walls of each floor.

[0005] However, in actual use, the above system only obtains the corresponding moving time interval and distance value through the controller and the regular transceiver to determine the corresponding operating speed, and determines the corresponding elevator operating status information through the monitoring results of the operating speed and the near-field transceiver. It does not take into account the effective identification of failure of the electrical control device during the data collection process, and by measuring the entire operating status of the elevator and then analyzing the data, it cannot effectively and in real time identify the type of fault in the operation process of the corresponding elevator. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcoming of low real-time performance in the prior art and to propose a method and system for identifying the running status of a vertical elevator.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A vertical elevator operation status identification system includes an elevator management platform, wherein the elevator management platform is provided with a data acquisition module, an acquisition transmission module, a status analysis module, a status identification module and a fault warning module;

[0009] The data acquisition module is used to collect the three-axis acceleration data of the elevator in real time under the running state, and generate the elevator running data set in the elevator running process according to the collected three-axis acceleration data, and segment the obtained elevator running data set according to the corresponding collection time to obtain the corresponding acceleration synchronization time series, and construct the original data set of the elevator state;

[0010] The acquisition and transmission module is used to monitor the operating status of the corresponding data transmission channel in real time, obtain transmission status data, perform status evaluation according to the adjacent deviation data and interval deviation data corresponding to the transmission status data, obtain status evaluation data, and select the corresponding data transmission channel for data transmission according to the status evaluation data;

[0011] The state analysis module is used to extract features from the original data set of the elevator state obtained, obtain the eigenvalues ​​corresponding to the three-axis acceleration data respectively, and construct an axial eigenvalue data set according to the corresponding eigenvalues, obtain corresponding identification index parameters according to the distribution of sample data in the axial eigenvalue data set, and construct a state recognition model;

[0012] The state recognition module is used to identify the elevator operation state in turn according to the recognition index parameters and the state recognition model, and generate operation state data;

[0013] The fault warning module is used to determine whether to issue a voice fault warning according to the operating status data.

[0014] The above technical solution further includes: the process of obtaining the elevator operation data set during the elevator operation process includes:

[0015] A three-axis acceleration sensor is arranged in the elevator, and the three-axis acceleration sensor is used to obtain elevator operation data during the operation of the elevator, and the elevator operation data includes acceleration data and time data corresponding to the X-axis, Y-axis and Z-axis respectively;

[0016] Set the sample unit period 0.5s, the number of unit sample periods m and the unit period sampling frequency n, sample and process the obtained elevator operation data according to the set data, and obtain the number of periodic continuous sampling points m×n;

[0017] The corresponding number of periodic continuously collected sample points is set as sample data, the sample data is integrated, and an elevator operation data set is generated according to the integration result.

[0018] Furthermore, the process of constructing the original data set of elevator status includes:

[0019] Obtain an elevator operation data set, and set corresponding axial sequences for the corresponding sample data in the elevator operation data set according to the acceleration data of the X-axis, Y-axis, and Z-axis;

[0020] According to the corresponding time data, the acceleration data corresponding to the sample data are respectively mapped to the axial sequences corresponding to the X-axis, the Y-axis and the Z-axis, and the acceleration synchronization time series is obtained according to the mapping results;

[0021] Each acceleration synchronization time series is segmented according to the corresponding time data, and the original data set of the elevator state is constructed based on the segmented interception results.

[0022] Furthermore, the process in which the acquisition and transmission module selects the corresponding data transmission channel to transmit the original data set of the elevator status includes:

[0023] The acquisition and transmission module is provided with a data transmission channel for data transmission, and the operation status of the corresponding data transmission channel is monitored in real time to obtain corresponding transmission status data;

[0024] The transmission status data corresponding to each data transmission channel are marked respectively according to the corresponding real-time monitoring time, and the corresponding transmission status sequence is set according to the marking result;

[0025] Preset a status monitoring cycle, and perform segmented processing on the transmission status sequence according to the status monitoring cycle to obtain a corresponding transmission status subsequence, wherein the transmission status subsequence includes a plurality of sequence elements, and the sequence elements are transmission status data corresponding to the corresponding monitoring time;

[0026] Comparing and analyzing the transmission status data corresponding to the adjacent sequence elements and the transmission status data corresponding to the interval sequence elements, respectively obtaining the corresponding adjacent deviation data and interval deviation data;

[0027] Evaluate and analyze the transmission status of the corresponding data transmission channel according to the adjacent deviation data, the interval deviation data and the corresponding transmission status data, and obtain the status evaluation data corresponding to the corresponding data transmission channel;

[0028] The acquisition and transmission module is used to select a corresponding data transmission channel according to the state evaluation data corresponding to each data transmission channel to transmit the original data set of the elevator state.

[0029] Furthermore, the process of performing feature extraction on the obtained original data set of elevator status and constructing an axial eigenvalue data set according to the feature extraction result includes:

[0030] Obtain a historical elevator status original data set, perform feature processing on the acceleration synchronization time series corresponding to the corresponding sample data in the historical elevator status original data set, respectively perform visualization processing on the acceleration synchronization time series corresponding to the X-axis, Y-axis and Z-axis, and obtain corresponding signal waveforms;

[0031] The obtained signal waveform is processed to obtain corresponding characteristic values, including peak-to-peak value PP, root mean square value RMS, kurtosis index P f , form factor S f , Peak Factor C f and Pulse Factor I f Six types;

[0032] The different types of eigenvalues ​​corresponding to the X-axis, Y-axis and Z-axis are integrated to obtain axial eigenvalue data sets corresponding to the X-axis, Y-axis and Z-axis respectively, wherein the axial eigenvalue data sets include eigenvalue data corresponding to the elevator operation status type corresponding to the sample data corresponding to the corresponding axial direction.

[0033] Furthermore, the process of obtaining corresponding identification index parameters according to the axial eigenvalue data set and constructing a state identification model includes:

[0034] Obtain an axial eigenvalue data set, and visually classify and mark the sample data corresponding to the obtained eigenvalue data set according to the elevator operation state type, wherein the elevator operation state type includes three types: emergency stop state, excessive car vibration state, and normal operation state;

[0035] Set the two-dimensional coordinates of the eigenvalue data with respect to the time series, map the 18 axial eigenvalue data sets corresponding to the X-axis, Y-axis and Z-axis to the corresponding two-dimensional coordinate system, and obtain the two-dimensional feature image according to the mapping results;

[0036] Statistically analyzing the visual classification labeling results corresponding to the elevator operation status types in each of the obtained two-dimensional feature images, and obtaining the coverage areas of the visual classification labeling results corresponding to the corresponding axial feature value data sets;

[0037] The obtained coverage area is processed based on the image analysis algorithm to obtain the regional overlap data of different visual classification marking results in the corresponding coverage area, and the coverage area with regional overlap data of 0 is linearly divided, and the identification index parameters of the type eigenvalues ​​corresponding to the corresponding axial eigenvalue data set are obtained according to the linear division results;

[0038] Preset the area overlap data limit, compare and analyze the area overlap data with the area overlap data limit, and determine whether the characteristic value type corresponding to the corresponding coverage area can be used as a single comprehensive identification indicator;

[0039] The axial eigenvalue data set corresponding to the eigenvalue type that can be used as a single comprehensive identification index is analyzed and processed based on the RBF neural network to build a state recognition model.

[0040] Furthermore, the process of identifying the elevator operation state according to the identification index parameter and the state identification model includes:

[0041] Acquire the original data set of the elevator status transmitted by the data transmission module, perform feature extraction according to the obtained original data set of the elevator status, and acquire the corresponding real-time axial feature value;

[0042] Setting up identification process links based on the obtained identification index parameters and the state identification model;

[0043] The real-time axial characteristic value is input into the corresponding identification process link, and is analyzed and processed in sequence according to the corresponding identification index parameters and the state identification model to obtain the operation state type during the operation of the corresponding elevator and generate the operation state data.

[0044] Furthermore, the process of determining whether to perform a voice fault reminder according to the operating status data includes:

[0045] A preset early warning prompt scheme includes voice prompt data corresponding to two states: an emergency elevator stop state and an excessive elevator car vibration state;

[0046] The operation status data is obtained. If the elevator operation status type is not a normal operation status, the corresponding early warning prompt scheme is obtained, and a voice fault reminder is given according to the early warning prompt scheme.

[0047] The present invention has the following beneficial effects:

[0048] 1. In the present invention, the collected elevator operation data is analyzed and processed by setting the sample unit period 0.5s, the number of unit sample periods m and the unit period sampling frequency n. While ensuring that the sample data is large enough, the real-time nature of the elevator operation data is guaranteed to a certain extent, thereby improving the real-time nature and recognition speed in the process of elevator operation status identification. In addition, by analyzing the elevator operation data within 0.5 seconds, the situation in which the electrical control device fails and the elevator operation data cannot be effectively identified when the elevator is in a power outage state is avoided.

[0049] 2. In the present invention, by extracting features from the acceleration data corresponding to the X-axis, Y-axis and Z-axis during the operation of the elevator, a corresponding axial eigenvalue data set is obtained, and different fault types are identified and analyzed through the axial eigenvalue data set, thereby improving the accuracy of the elevator operation status identification process to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of the structure of a vertical elevator operation status identification system proposed by the present invention;

[0051] Figure 2 The present invention is a flowchart of a method for identifying the operating status of a vertical elevator. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Embodiment 1

[0054] like Figure 1 As shown, a vertical elevator operation status identification system proposed by the present invention includes an elevator management platform, in which a data acquisition module, an acquisition and transmission module, a status analysis module, a status identification module and a fault warning module are arranged.

[0055] In this embodiment, the elevator management platform is used to collect real-time data corresponding to the elevator running state, extract corresponding feature data from the collected real-time data, identify the fault type under the elevator running state according to the feature data, and issue an early warning prompt according to the identification result, thereby improving the identification efficiency and accuracy of the elevator running state. The specific implementation process includes:

[0056] The data acquisition module is used to collect the three-axis acceleration data of the elevator in real time under the running state, and generate the elevator running data set in the elevator running process from the collected three-axis acceleration data, segment the obtained elevator running data set according to the corresponding acquisition time, obtain the corresponding acceleration synchronization time series according to the segmented interception processing result, and construct the original data set of the elevator state. The specific implementation process includes:

[0057] Setting up a data acquisition unit and a segment processing unit;

[0058] A triaxial acceleration sensor is arranged in the elevator, wherein the triaxial acceleration sensor includes an acceleration sensor and a time sensor, and the elevator operation data of the corresponding elevator in daily inspection and detection is obtained through the triaxial acceleration sensor, wherein the elevator operation data includes triaxial acceleration data, time data, etc. during the operation of the elevator;

[0059] A test data storage space is provided in the data acquisition unit, the elevator operation data obtained by the triaxial acceleration sensor is connected to the corresponding test data storage space, the collected data information is stored in the test data storage space, and marked according to the corresponding time data and axial data;

[0060] The sample extraction of the elevator operation data stored in the inspection and testing data storage space includes:

[0061] Set the sample unit period, collect elevator operation data in a continuous periodic sample according to the sample unit period, and preset the number of unit sample periods m and the unit period sampling frequency n;

[0062] According to the number of unit sample cycles m and the unit cycle sampling frequency n, the number of periodic continuous acquisition sample points m×n is obtained, and each periodic continuous acquisition sample point includes acceleration data of the X-axis, Y-axis and Z-axis corresponding to the real-time state of the elevator;

[0063] The number of sample points continuously collected in the inspection and testing data storage space corresponding to the period is set as sample data;

[0064] Integrate the corresponding sample data in the inspection and testing data storage space according to the obtained sample data, and generate an elevator operation data set according to the integration result;

[0065] It should be further explained that, in the specific implementation process, the unit sample period number m and the unit period sampling frequency n are respectively set to 3 and 500 Hz in the experimental test process, n=500 is selected, and the unit sample period is 0.5s. The acceleration data of the three axes X, Y, and Z of the elevator are obtained in real time within a time interval of 0.5s, and the acceleration data of the three axes X, Y, and Z are marked respectively;

[0066] Obtaining the elevator operation data set in the real-time state of the elevator through the segment processing unit;

[0067] The corresponding sample data in the elevator operation data set is processed in segments according to the labeling results corresponding to the acceleration data of the X-axis, Y-axis and Z-axis;

[0068] Set the corresponding axial sequence according to the X-axis, Y-axis and Z-axis to which the acceleration data belongs;

[0069] Map the time data corresponding to the sample data in the elevator operation data set to the corresponding position in the axial sequence;

[0070] According to the mapping results of each sample data, the acceleration synchronization time series corresponding to the X-axis, Y-axis and Z-axis are obtained;

[0071] Each acceleration synchronization time series is segmented according to the corresponding time data, and the original data set of the elevator state is constructed based on the segmented interception results.

[0072] The acquisition and transmission module is used to transmit the original data set of the elevator status to the status recognition module, and its specific implementation process includes:

[0073] Obtaining the original data set of elevator status obtained by the data acquisition module;

[0074] Setting a data transmission channel for data transmission, monitoring the operating status of the data transmission channel in real time, and obtaining transmission status data of the corresponding data transmission channel;

[0075] The transmission status data corresponding to each data transmission channel are marked respectively according to the corresponding real-time monitoring time;

[0076] According to the marking result, a corresponding transmission state sequence is set, the transmission state sequence is analyzed and processed, a state monitoring period is preset, and the transmission state sequence corresponding to each data transmission channel is segmented according to the state monitoring period, and a transmission state subsequence corresponding to the corresponding state monitoring period is obtained according to the segmentation processing result;

[0077] Analyze and process the transmission status data corresponding to each sequence element in the transmission status subsequence to obtain status evaluation data. The specific implementation process includes:

[0078] Comparing and analyzing the transmission status data corresponding to the adjacent sequence elements, respectively obtaining the adjacent deviation data LC corresponding to the adjacent sequence elements;

[0079] Compare and analyze the transmission status data corresponding to the interval sequence elements, and obtain the interval deviation data JC corresponding to the corresponding interval sequence elements respectively;

[0080] The adjacent deviation threshold LY and the interval deviation threshold JY are respectively preset, and the adjacent deviation data and the interval deviation data are state evaluated according to the adjacent deviation threshold and the interval deviation threshold to obtain the adjacent state evaluation data LP and the interval state evaluation data JP:

[0081]

[0082] Where L is the number of combinations of adjacent sequence elements corresponding to the corresponding transmission state subsequence, l is the identifier of the corresponding adjacent sequence element; K is the number of combinations of interval sequence elements corresponding to the corresponding transmission state subsequence, k is the identifier of the corresponding interval sequence element, β l and γ K are the corresponding correction coefficients respectively;

[0083] The state evaluation data ZP of the corresponding data transmission channel is obtained according to the obtained adjacent state evaluation data, interval state evaluation data and corresponding transmission state data CZ:

[0084]

[0085] Where H is the number of sequence elements in the transmission status subsequence, h is the identifier of the sequence element corresponding to the corresponding transmission status data, CZ b is the state standard data corresponding to the transmission channel, α1, α2 and α3 are the state weight coefficients respectively;

[0086] The status evaluation data obtained by each data transmission channel are comprehensively sorted, and the corresponding data transmission channel is selected according to the comprehensive sorting result. The obtained elevator status original data set is transmitted through the corresponding data transmission channel and transmitted to the status analysis module and the fault identification module respectively.

[0087] The state analysis module is used to analyze and process the obtained historical elevator state original data set, extract the axial characteristic values ​​corresponding to the three-axis acceleration respectively, and analyze and process according to the axial characteristic values, build a state recognition model, and obtain the recognition index parameters corresponding to the corresponding fault type according to the state recognition model. The specific implementation process includes:

[0088] Setting a feature analysis unit and a state analysis unit;

[0089] The feature analysis unit is used to obtain the original data set of elevator status obtained by the data transmission module, and classify the original data set of elevator status;

[0090] Preset a historical evaluation linear standard, compare and analyze the time data corresponding to the corresponding sample data in the elevator state original data set obtained in the data transmission module with the historical evaluation linear standard, and obtain the elevator state original data set belonging to the historical elevator state original data set according to the comparison and analysis result;

[0091] Acquire a historical elevator status original data set, and perform feature processing on the acceleration synchronization time series corresponding to the corresponding sample data in the historical elevator status original data set;

[0092] Feature extraction is performed on the acceleration synchronization time series corresponding to the X-axis, Y-axis and Z-axis to obtain multiple types of feature values. The specific implementation process includes:

[0093] Visualize the acceleration synchronization time series corresponding to the X-axis, Y-axis and Z-axis respectively to obtain the corresponding signal waveform diagram;

[0094] The obtained signal waveform is processed to obtain corresponding characteristic values, including peak-to-peak value PP, root mean square value RMS, kurtosis index P f , form factor S f , Peak Factor C f and Pulse Factor I f There are six types, and the meanings and calculation methods of different eigenvalues ​​are as follows:

[0095] The peak-to-peak value is the difference between the maximum value and the minimum value corresponding to the corresponding acceleration data in the corresponding signal waveform, which represents the extreme degree of the corresponding acceleration data. The calculation formula is as follows:

[0096] PP = max{xi}-min{xi};

[0097] The root mean square value is the square root of the average value of the corresponding signal in the corresponding signal waveform, which represents the smoothness of the overall movement of the corresponding elevator. The calculation formula is as follows:

[0098]

[0099] The kurtosis index is used to measure the sharpness of the signal waveform distribution, and the calculation formula is as follows:

[0100]

[0101] The waveform factor is the ratio of the root mean square value to the rectified average value, and the calculation formula is as follows:

[0102]

[0103] The peak factor is the ratio of the signal peak value to the root mean square value, which represents the extreme degree of the waveform. The calculation formula is as follows:

[0104]

[0105] The pulse factor is the ratio of the peak value to the rectified average value, which is sensitive to shocks and is calculated as follows:

[0106]

[0107] The obtained characteristic values ​​include peak-to-peak value PP, root mean square value RMS, kurtosis index P f, form factor S f , Peak Factor C f and Pulse Factor I f ;

[0108] Marking the fault types of the sample data corresponding to the original data set of the corresponding historical elevator status;

[0109] The obtained characteristic data are integrated according to the fault type marking results of the historical elevator status original data set, and the axial characteristic values ​​corresponding to the X-axis, Y-axis and Z-axis are respectively obtained, and the axial characteristic value data sets corresponding to the X-axis, Y-axis and Z-axis are respectively obtained according to the integration results, and the axial characteristic value data sets corresponding to the X-axis, Y-axis and Z-axis include characteristic value data of the type corresponding to the state type corresponding to the sample data corresponding to the corresponding axis.

[0110] The state analysis unit is used to set identification index parameters according to the characteristic value data sets corresponding to each state type, and construct a corresponding state recognition model;

[0111] Visually classify and mark the sample data corresponding to the obtained feature value data set according to the elevator operation state type, wherein the elevator operation state type includes three types: emergency stop state, excessive car vibration state, and normal operation state;

[0112] The obtained axial eigenvalue data set is set to a two-dimensional coordinate system of corresponding characteristic data with respect to the time series;

[0113] The 18 axial eigenvalue data sets corresponding to the X-axis, Y-axis and Z-axis are respectively mapped into the corresponding two-dimensional coordinate system, and the two-dimensional feature images corresponding to the corresponding axial eigenvalue data sets are obtained according to the mapping results;

[0114] Performing statistical analysis on the visual classification labeling results corresponding to the elevator operation status types in each of the obtained two-dimensional feature images;

[0115] Obtain the coverage area of ​​the visualization classification labeling result corresponding to the corresponding axial eigenvalue data set respectively;

[0116] Performing data processing on the obtained coverage area based on the image analysis algorithm, determining the regional overlapping data of different visual classification marking results in each coverage area based on the image analysis algorithm, and analyzing and processing the obtained regional overlapping data;

[0117] Obtaining the coverage area where the regional overlap data is 0, performing linear division on the obtained coverage area, and directly obtaining the identification index parameter of the type eigenvalue corresponding to the corresponding axial eigenvalue data set according to the linear division result;

[0118] Preset the area overlap data limit CX and obtain the area overlap data QC;

[0119] If QC ≥ CX, the eigenvalue type corresponding to the corresponding coverage area cannot be used as a single comprehensive identification indicator, and the linear data corresponding to the linear division result corresponding to the corresponding single comprehensive identification indicator is not directly set as the identification indicator parameter;

[0120] If QC < CX, the eigenvalue type corresponding to the corresponding coverage area can be used as a single comprehensive identification index, and the linear data corresponding to the linear division result corresponding to the corresponding single comprehensive identification index is indirectly set as the identification index parameter, and a state recognition model is constructed for the corresponding single comprehensive identification index based on the RBF neural network;

[0121] Integrate the axial eigenvalue data sets corresponding to the obtained single comprehensive identification indicators, set the identification data set according to the integration result, and divide the obtained identification data set into a training set and a validation set;

[0122] The obtained training set is analyzed and processed based on the RBF neural network, and the corresponding state recognition model is constructed. The verification set is input into the constructed state recognition model for verification analysis until the corresponding loss function tends to be stable, and the corresponding state recognition model is output;

[0123] It should be further explained that, in the specific implementation process, in the process of experimental analysis of 18 axial eigenvalue data sets, a single comprehensive identification index can only realize the state judgment of the emergency stop state, and the corresponding axial eigenvalue data sets are two single indicators of peak-to-peak value PP and root mean square value RMS corresponding to the Z axis; in addition, the state recognition model is used to identify the state of excessive car vibration and normal operation, and the state recognition model is constructed by analyzing and processing the axial eigenvalue data sets corresponding to the two horizontal measurement axes of the X-axis and the Y-axis.

[0124] The fault identification module is used to extract features from the original data set of the elevator status, obtain the corresponding real-time axial characteristic value, make a comprehensive judgment on the obtained real-time axial characteristic value according to the identification index parameter corresponding to the status identification model, and obtain the operation status data. The specific implementation process includes:

[0125] Acquire the original data set of the elevator status transmitted by the data transmission module, perform feature extraction according to the obtained original data set of the elevator status, and acquire the corresponding real-time axial feature value;

[0126] Obtain identification index parameters and corresponding state identification models obtained by the fault analysis module, and link the obtained identification index parameters with the corresponding state identification model to set up an identification process;

[0127] Mapping the obtained identification index parameters and the corresponding state identification model into the identification process link according to the corresponding identification process;

[0128] According to the corresponding identification index parameters in the identification process link and the corresponding state identification model, the real-time axial characteristic values ​​are analyzed and processed in turn to obtain the operation state type of the corresponding elevator during operation, generate operation state data according to the operation state type, and send the operation state data to the fault warning module.

[0129] The fault warning module is used to identify faults on the obtained operating status data, obtain corresponding early warning prompt schemes according to the fault identification results, and give fault reminders according to the early warning prompt schemes. The specific implementation process includes:

[0130] Obtain corresponding operation status data and corresponding operation status type. If the operation status type is a normal operation state, no early warning prompt plan is generated.

[0131] If the running state type is not a normal running state, a corresponding early warning prompt scheme is obtained, wherein the early warning prompt scheme includes voice prompt data corresponding to two states: an emergency stop state and an excessive car vibration state, wherein the corresponding voice prompt data is preset, and different voice prompt data are set according to different state types;

[0132] Obtain the corresponding voice prompt data in the early warning prompt scheme according to the corresponding fault type;

[0133] Providing fault reminders based on the acquired voice prompt data;

[0134] It should be further explained that, in the specific implementation process, the fault reminder includes in the car of the corresponding elevator and in the elevator management platform.

[0135] Embodiment 2

[0136] like Figure 2 As shown, based on the first embodiment, a method for identifying the running state of a vertical elevator is proposed, comprising the following steps:

[0137] Step 1: Collect the three-axis acceleration data of the elevator in real time, and generate the elevator operation data set in the elevator operation process according to the collected three-axis acceleration data. The obtained elevator operation data set is segmented according to the corresponding collection time to obtain the corresponding acceleration synchronization time series, and the original data set of the elevator state is constructed;

[0138] Step 2: Monitor the operating status of the corresponding data transmission channel in real time, obtain transmission status data, perform status evaluation based on adjacent deviation data and interval deviation data corresponding to the transmission status data, obtain status evaluation data, and select the corresponding data transmission channel for data transmission based on the status evaluation data;

[0139] Step 3: Extract features from the original data set of the elevator state, obtain the eigenvalues ​​corresponding to the three-axis acceleration data, and construct an axial eigenvalue data set based on the corresponding eigenvalues. According to the distribution of sample data in the axial eigenvalue data set, obtain corresponding identification index parameters, and construct a state recognition model.

[0140] Step 4: Identify the elevator operation status in turn according to the identification index parameters and the state identification model, and generate the operation status data corresponding to the corresponding elevator;

[0141] Step 5: Set the voice prompt data corresponding to the fault type, determine whether to issue a voice fault reminder based on the operating status data, and obtain the corresponding voice prompt data for early warning.

[0142] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vertical elevator operation status identification system, including an elevator management platform, characterized in that: The elevator management platform is provided with a data acquisition module, an acquisition and transmission module, a state analysis module, a state identification module and a fault warning module; The data acquisition module is used to collect the three-axis acceleration data of the elevator in real time under the running state, and generate the elevator running data set in the elevator running process according to the collected three-axis acceleration data, segment the obtained elevator running data set according to the corresponding acquisition time, obtain the corresponding acceleration synchronization time series, and construct the original data set of the elevator state; The acquisition and transmission module is used to monitor the operating status of the corresponding data transmission channel in real time, obtain transmission status data, perform status evaluation according to the adjacent deviation data and interval deviation data corresponding to the transmission status data, obtain status evaluation data, and select the corresponding data transmission channel for data transmission according to the status evaluation data; The state analysis module is used to extract features from the original data set of the elevator state obtained, obtain the eigenvalues ​​corresponding to the three-axis acceleration data respectively, and construct an axial eigenvalue data set according to the corresponding eigenvalues, obtain corresponding identification index parameters according to the distribution of sample data in the axial eigenvalue data set, and construct a state recognition model; The state recognition module is used to identify the elevator operation state in turn according to the recognition index parameters and the state recognition model, and generate operation state data; The fault warning module is used to determine whether to issue a voice fault warning according to the operating status data.

2. A vertical elevator operation status recognition system according to claim 1, characterized in that: The process of obtaining the elevator operation data set during the elevator operation process includes: A three-axis acceleration sensor is arranged in the elevator, and the three-axis acceleration sensor is used to obtain elevator operation data during the operation of the elevator, and the elevator operation data includes acceleration data and time data corresponding to the X-axis, Y-axis and Z-axis respectively; Set the sample unit period 0.5s, the number of unit sample periods m and the unit period sampling frequency n, sample and process the obtained elevator operation data according to the set data, and obtain the number of periodic continuous sampling points m×n; The corresponding number of periodic continuously collected sample points is set as sample data, the sample data is integrated, and an elevator operation data set is generated according to the integration result.

3. A vertical elevator operation status recognition system according to claim 2, characterized in that: The process of constructing the original elevator status dataset includes: Obtain an elevator operation data set, and set corresponding axial sequences for the corresponding sample data in the elevator operation data set according to the acceleration data of the X-axis, Y-axis, and Z-axis; According to the corresponding time data, the acceleration data corresponding to the sample data are respectively mapped to the axial sequences corresponding to the X-axis, the Y-axis and the Z-axis, and the acceleration synchronization time series is obtained according to the mapping results; Each acceleration synchronization time series is segmented according to the corresponding time data, and the original data set of the elevator state is constructed based on the segmented interception results.

4. A vertical elevator operation status recognition system according to claim 3, characterized in that: The process of the acquisition and transmission module selecting the corresponding data transmission channel to transmit the original data set of the elevator status includes: The acquisition and transmission module is provided with a data transmission channel for data transmission, and the operation status of the corresponding data transmission channel is monitored in real time to obtain corresponding transmission status data; The transmission status data corresponding to each data transmission channel are marked respectively according to the corresponding real-time monitoring time, and the corresponding transmission status sequence is set according to the marking result; Preset a status monitoring cycle, and perform segmented processing on the transmission status sequence according to the status monitoring cycle to obtain a corresponding transmission status subsequence, wherein the transmission status subsequence includes a plurality of sequence elements, and the sequence elements are transmission status data corresponding to the corresponding monitoring time; Comparing and analyzing the transmission status data corresponding to the adjacent sequence elements and the transmission status data corresponding to the interval sequence elements, respectively obtaining the corresponding adjacent deviation data and interval deviation data; Evaluate and analyze the transmission status of the corresponding data transmission channel according to the adjacent deviation data, the interval deviation data and the corresponding transmission status data, and obtain the status evaluation data corresponding to the corresponding data transmission channel; The acquisition and transmission module is used to select a corresponding data transmission channel according to the state evaluation data corresponding to each data transmission channel to transmit the original data set of the elevator state.

5. A vertical elevator operation status recognition system according to claim 4, characterized in that: The process of extracting features from the original data set of elevator status obtained and constructing an axial eigenvalue data set according to the feature extraction results includes: Obtain a historical elevator status original data set, perform feature processing on the acceleration synchronization time series corresponding to the corresponding sample data in the historical elevator status original data set, respectively perform visualization processing on the acceleration synchronization time series corresponding to the X-axis, Y-axis and Z-axis, and obtain corresponding signal waveforms; The obtained signal waveform is processed to obtain corresponding characteristic values, including peak-to-peak value PP, root mean square value RMS, kurtosis index P f , form factor S f , Peak Factor C f and Pulse Factor I f Six types; The different types of eigenvalues ​​corresponding to the X-axis, Y-axis and Z-axis are integrated to obtain axial eigenvalue data sets corresponding to the X-axis, Y-axis and Z-axis respectively, wherein the axial eigenvalue data sets include eigenvalue data corresponding to the elevator operation status type corresponding to the sample data corresponding to the corresponding axial direction.

6. A vertical elevator operation status recognition system according to claim 5, characterized in that: The process of obtaining corresponding identification index parameters according to the axial eigenvalue data set and constructing a state identification model includes: Obtain an axial eigenvalue data set, and visually classify and mark the sample data corresponding to the obtained eigenvalue data set according to the elevator operation state type, wherein the elevator operation state type includes three types: emergency stop state, excessive car vibration state, and normal operation state; Set the two-dimensional coordinates of the eigenvalue data with respect to the time series, map the multiple axial eigenvalue data sets corresponding to the X-axis, Y-axis and Z-axis into the corresponding two-dimensional coordinate system, and obtain the two-dimensional feature image according to the mapping results; Statistically analyzing the visual classification labeling results corresponding to the elevator operation status types in each of the obtained two-dimensional feature images, and obtaining the coverage areas of the visual classification labeling results corresponding to the corresponding axial feature value data sets; The obtained coverage area is processed based on the image analysis algorithm to obtain the regional overlap data of different visual classification marking results in the corresponding coverage area, and the coverage area with regional overlap data of 0 is linearly divided, and the identification index parameters of the corresponding type of eigenvalues ​​in the corresponding axial eigenvalue data set are obtained according to the linear division results; Preset the area overlap data limit, compare and analyze the area overlap data with the area overlap data limit, and determine whether the characteristic value type corresponding to the corresponding coverage area is used as the corresponding single comprehensive identification indicator; The axial eigenvalue data set corresponding to the eigenvalue type of a single comprehensive identification index is analyzed and processed based on the RBF neural network to construct a state recognition model.

7. A vertical elevator operation status recognition system according to claim 6, characterized in that: The process of identifying the elevator operation status according to the identification index parameters and the status identification model includes: Acquire the original data set of the elevator status transmitted by the data transmission module, perform feature extraction according to the obtained original data set of the elevator status, and acquire the corresponding real-time axial feature value; Setting up identification process links based on the obtained identification index parameters and the state identification model; The real-time axial characteristic value is input into the corresponding identification process link, and is analyzed and processed in sequence according to the corresponding identification index parameters and the state identification model to obtain the operation state type during the operation of the corresponding elevator and generate the operation state data.

8. A vertical elevator operation status recognition system according to claim 7, characterized in that: The process of determining whether to issue a voice fault reminder based on the operating status data includes: A preset early warning prompt scheme includes voice prompt data corresponding to two states: an emergency elevator stop state and an excessive elevator car vibration state; The operation status data is obtained. If the elevator operation status type is not a normal operation status, the corresponding early warning prompt scheme is obtained, and a voice fault reminder is given according to the early warning prompt scheme.

9. A method for identifying the running state of a vertical elevator corresponding to a system for identifying the running state of a vertical elevator according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Collect the three-axis acceleration data of the elevator in real time, and generate the elevator operation data set in the elevator operation process according to the collected three-axis acceleration data. The obtained elevator operation data set is segmented according to the corresponding collection time to obtain the corresponding acceleration synchronization time series, and the original data set of the elevator state is constructed; Step 2: Monitor the operating status of the corresponding data transmission channel in real time, obtain transmission status data, perform status evaluation based on adjacent deviation data and interval deviation data corresponding to the transmission status data, obtain status evaluation data, and select the corresponding data transmission channel for data transmission based on the status evaluation data; Step 3: Extract features from the original data set of the elevator state, obtain the eigenvalues ​​corresponding to the three-axis acceleration data, and construct an axial eigenvalue data set based on the corresponding eigenvalues. According to the distribution of sample data in the axial eigenvalue data set, obtain corresponding identification index parameters, and construct a state recognition model. Step 4: Identify the elevator operation status in turn according to the identification index parameters and the state identification model, and generate the operation status data corresponding to the corresponding elevator; Step 5: Set the voice prompt data corresponding to the fault type, determine whether to issue a voice fault reminder based on the operating status data, and obtain the corresponding voice prompt data for early warning.

Images