Elevator risk early warning management method and system

Abstract

The invention discloses an elevator risk early warning management method and system, and generally relates to the technical field of elevator intelligent early warning management. The method comprises the steps that the stable operation stage of the elevator in the operation process is determined through a state judgment model; part point position parameters of the multiple parts of the elevator in the stable operation stage are obtained, and feature parameters of the part point position parameters of the multiple parts are obtained through a preset feature parameter function; according to the feature parameters of the component point location parameters of the multiple components, determining the mass fraction of the component point location parameter of each component in the multiple components, and screening target parameters in the component point location parameters of each component in the multiple components according to the mass fractions; and according to the target parameter and the elevator early warning function, an elevator early warning state is determined and transmitted to an elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator early warning state. The accuracy of the judgment safety level can be improved, and meanwhile the efficiency of confirming the early warning state of the elevator can be improved.

Description

Technical Field

[0001] The present disclosure generally relates to the technical field of elevator intelligent early warning management, and more particularly to an elevator risk early warning management method and system. Background Art

[0002] With the acceleration of urbanization, there are more and more high-rise buildings in my country. The number and demand of elevators as vertical transportation tools have increased sharply.

[0003] As a mechanized means of transportation with a life cycle, elevators require regular manual inspections to ensure their safety. Generally, the inspection cycle is determined based on the service life of the elevator.

[0004] However, during the use of elevators, there are many parts involved, and the degree of damage of each part and the actual inspection cycle and preset method may be different. Therefore, this regular inspection method cannot meet the actual needs of protecting elevator safety, and there are still major loopholes in the convenience of elevator early warning management. Summary of the invention

[0005] In view of the above defects or deficiencies in the related technology, it is desired to provide an elevator risk warning management method and system, which can solve the problem that there are many parts involved in the use of the elevator, and the degree of damage of each part and the actual inspection cycle and preset method may be different. Therefore, this regular inspection method cannot meet the actual needs of protecting the safety of the elevator and ensure the healthy operation of the elevator.

[0006] In a first aspect, a method for early warning management of elevator risks is provided, the method comprising: Determining the stable operation stage of the elevator during operation by means of a state determination model; Obtaining component position parameters of multiple components of the elevator in a stable operation stage, and obtaining characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function, wherein the characteristic parameters include: information entropy values ​​of the component position parameters of the multiple components and information redundancy of the component position parameters of the multiple components; Determining a quality score of the component point parameters of each of the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and screening target parameters in the component point parameters of each of the multiple components according to the quality score; According to the target parameters and the elevator warning function, the elevator warning state is determined and transmitted to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state, and the elevator warning state is used to indicate the safety level of the elevator.

[0007] In the present application, the elevator early warning state determination model is used to determine the stable operation stage of the elevator in the operation process, and then the component point parameters of multiple components of the elevator in the stable operation stage are obtained, and the characteristic parameters of the component point parameters of multiple components are obtained by presetting the characteristic parameter function, wherein the characteristic parameters include the information entropy value of the component point parameters of multiple components and the information redundancy of the component point parameters of multiple components; then, according to the characteristic parameters of the component point parameters of multiple components, the quality score of the component point parameters of each component in the multiple components is determined, and the target parameters in the component point parameters of each component in the multiple components are screened according to the quality score; finally, the elevator early warning state used to indicate the elevator safety level is determined and transmitted to the management system through the target parameters and the elevator early warning function, so that the elevator management system generates an elevator state identification according to the elevator early warning state. In this way, by observing the component point parameters of each of the multiple component points in the elevator, the component point parameters are judged and screened, and the target parameters that best represent the elevator quality at each point are selected, and the elevator safety level is determined by combining the target parameters with the elevator early warning function. In this way, the actual health status of the elevator can be obtained during the operation of the elevator, avoiding the hidden dangers of elevator safety failures caused by untimely elevator inspections during regular inspections and warranty inspections when failures occur, thereby greatly improving the accuracy of elevator early warnings. At the same time, since the data ultimately involved in judging the safety level of the elevator are the parameters with higher quality scores among the component point parameters of multiple components, while improving the accuracy of judging the safety level, it can also improve the efficiency of confirming the elevator early warning status and save the resources consumed in confirming the elevator early warning status.

[0008] In a second aspect, an elevator risk warning management system is provided, the system comprising: A determination unit, used to determine the stable operation stage of the elevator during operation through a state determination model; An acquisition unit is used to acquire component position parameters of multiple components of the elevator in a stable operation stage, and acquire characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function, wherein the characteristic parameters include: information entropy values ​​of the component position parameters of the multiple components and information redundancy of the component position parameters of the multiple components; An execution unit, configured to determine a quality score of the component point parameter of each of the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and to filter target parameters in the component point parameter of each of the multiple components according to the quality score; The determination unit is further used to determine the elevator warning state according to the target parameters and the elevator warning function and transmit it to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state, and the elevator warning state is used to indicate the safety level of the elevator.

[0009] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0010] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the program is executed by a processor, the method described in the first aspect is implemented.

[0011] In a fifth aspect, a computer program product is provided. The computer program product includes instructions, and the instructions are executed by a processor to implement the method described in the first aspect.

[0012] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A flow chart of an elevator risk warning management method provided in an embodiment of the present application; Figure 2 The multi-parameter start-stop long waveform signal of the elevator component provided in the embodiment of the present application; Figure 3 A single start-stop vibration waveform diagram provided in an embodiment of the present application; Figure 4 The time domain waveform diagram and multi-eigenvalue amplitude trend diagram provided in the embodiments of the present application; Figure 5 The automatic recognition effect of the stable operation phase data during the start and stop process of the elevator provided in the embodiment of the present application; Figure 6 Main parameters and auxiliary parameters of a conventionally configured elevator provided in an embodiment of the present application; Figure 7 An hourly health trend diagram of a faulty elevator provided in an embodiment of the present application; Figure 8 As shown in the elevator equipment health classification warning diagram provided in the embodiment of the present application; Fig. 9 A schematic diagram of the structure of an elevator risk warning management device provided in an embodiment of the present application; Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0015] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0016] Elevators are special equipment, and their failures are receiving more and more attention from the society. Among them, the failure of elevator mechanical equipment is one of the important factors affecting the safe operation of elevators. Mechanical equipment failure may not only cause the elevator to stop operating, but also cause serious safety accidents. These mechanical failures include traction machine bearing failure, traction wire rope breakage, wire rope wear, traction wheel wear, return rope wheel wear, brake wear too tight or too loose, gear box wear and bearing failure, base looseness, guide rail wear, abnormal car shaking, etc.

[0017] Elevators are generally subject to regular manual inspections in accordance with factory regulations to ensure elevator safety. Generally, the inspection cycle is determined based on the service life of the elevator and whether the elevator has mechanical failures. In other words, the current maintenance methods for elevator warning status mainly rely on regular or condition-based maintenance. These two methods are difficult to intervene in time for gradual and slowly changing faults or faults that occur in a short period of time. Elevators often run with faults, which brings risks to the safe operation of elevators.

[0018] However, during the use of elevators, there are many parts involved, and the degree of damage of each part and the actual inspection cycle and preset method may be different. Therefore, this regular inspection method cannot meet the actual needs of protecting elevator safety.

[0019] Based on this, this application proposes an elevator risk warning management method, device, equipment and medium, which can solve the problem that there are many parts involved in the use of elevators, and the degree of damage of each part and the actual inspection cycle and preset method may be different. Therefore, this regular inspection method cannot meet the actual needs of protecting elevator safety and ensuring the healthy operation of elevators.

[0020] Figure 1 FIG. 1 is a flow chart of an elevator risk warning management method provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps 301 to 304: Step 301: Determine the stable operation stage of the elevator during operation through a state determination model.

[0021] In the embodiment of the present application, in order to ensure the accuracy of the determination process of elevator risks, the parameters used to determine the elevator risks are collected during the stable operation stage. The data obtained during the stable operation stage can more accurately and comprehensively reflect the actual and accurate situation of the elevator operation.

[0022] In the embodiment of the present application, a state sensor can be provided for the elevator, the elevator operation state parameters can be collected through a speed sensor, and the elevator operation state parameters can be measured through a state determination model, so as to determine the stable operation stage of the elevator.

[0023] Step 302: Obtain component position parameters of multiple components of the elevator in a stable operation phase, and obtain characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function.

[0024] In the embodiment of the present application, the above-mentioned characteristic parameters include: information entropy values ​​of component point parameters of the multiple components and information redundancy of component point parameters of the multiple components.

[0025] In the embodiment of the present application, the component position parameters of the above-mentioned multiple components may include one position or multiple positions of each component of the multiple components of the elevator.

[0026] Exemplarily, for an elevator, its components may include a traction machine, a car, and a main brake. By obtaining the current quality status of each component, the overall quality status of the elevator can be obtained. For example, one or more monitoring points are set on the traction machine, and monitoring sensors are set at one or more monitoring points to collect the traction machine position parameters of one or more monitoring points; correspondingly, when the component is a car, one or more monitoring points are set on the car, and monitoring sensors are set at one or more monitoring points to collect the car position parameters of one or more monitoring points; correspondingly, when the component is a brake, one or more monitoring points are set on the brake, and monitoring sensors are set at one or more monitoring points to collect the brake position parameters of one or more monitoring points.

[0027] Exemplarily, the component point parameters of the above-mentioned multiple components may include different index parameters of the test point of each component.

[0028] In an example, the index parameters of the test points of each component mentioned above may include: effective value, peak value, true peak value, warpage, etc., but are not limited thereto.

[0029] It is understandable that for the component point parameters obtained by the monitoring point, for the component point parameters of each component point, the component point parameters obtained in the stable operation stage can be further decomposed to facilitate the subsequent screening and simplification of the characteristic parameters corresponding to the component point parameters generated by the component point data, so as to extract the data that best represents the operation quality as the characteristic parameters, and perform subsequent processing and calculation based on the characteristic parameters. In this way, the consumption of computing resources can be further reduced, and the efficiency of determining the elevator warning state can be improved.

[0030] In an embodiment of the present application, the above-mentioned preset characteristic parameter function may include an information entropy value function for calculating the information entropy value of component point parameters of multiple components, and an information redundancy function for calculating the information redundancy of component point parameters of multiple components.

[0031] In an embodiment of the present application, the above-mentioned information entropy value and information redundancy can be obtained by an entropy weight method. Specifically, the information entropy, redundancy and parameter weight of component point parameters of multiple components can be calculated by the entropy weight method.

[0032] It is understandable that the entropy weight method can ensure that the determination of weights is objective and scientific, thereby avoiding the interference of subjective factors in weight selection. Especially when there are many measuring points on each component, such as the horizontal measuring point, vertical measuring point, and axial measuring point of the traction machine, which indicator of the measuring point parameters is used as the main parameter can be analyzed by the entropy weight method. The characteristic parameters confirmed in this way are very important for determining the elevator warning status, and can determine the effective parameters for determining the elevator warning status.

[0033] Furthermore, the parameters and corresponding weights determined by the entropy weight method are the key methods for accurately predicting the elevator warning status. This method defines the target parameters of the subsequent warning model, such as the main input parameters (main parameters) and auxiliary input parameters (auxiliary parameters).

[0034] In the embodiment of the present application, the above-mentioned preset characteristic parameter function can be preset or customized by the user. It can be understood that the preset characteristic parameter function can convert the collected and acquired component point parameters into characteristic parameters that can be used to indicate the elevator warning state in the future. Please refer to the subsequent description for details, which will not be repeated here.

[0035] Step 303: determining quality scores of the component point parameters of the plurality of components according to the characteristic parameters of the component point parameters of the plurality of components, and screening target parameters among the component point parameters of the plurality of components according to the quality scores.

[0036] It is understandable that, based on the foregoing content, the amount of characteristic parameter data obtained during the stable operation of each component is still large, and not all of these characteristic parameters can achieve a high accuracy when used to determine the elevator warning status. Therefore, from the two aspects of saving computing resources and obtaining a higher accuracy elevator warning status, the characteristic parameters can be quality judged, and the characteristic parameters with higher quality scores among the multiple characteristic parameters corresponding to each component are obtained as the target parameters for determining the elevator warning status, thereby obtaining a more accurate elevator warning status.

[0037] Step 304: According to the target parameters and the elevator warning function, the elevator warning state is determined and transmitted to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state.

[0038] In an embodiment of the present application, the above-mentioned elevator warning status is used to indicate the safety level of the above-mentioned elevator.

[0039] In the embodiment of the present application, the above-mentioned elevator warning function can be preset or customized by the user.

[0040] In the embodiment of the present application, the above-mentioned elevator management system can be a visualization system, a voice system, or a text output system.

[0041] In one example, when the elevator management system can be a visualization system, the elevator status indicator can be directly displayed on the screen of the visualization system, so that the elevator management personnel can immediately view the current real-time elevator warning status, and then arrange personnel to check according to the elevator status indicator or know the elevator status that does not need to be checked.

[0042] In one example, when the elevator management system can be a voice system, the elevator status identification can be directly output through the voice system, so that the elevator management personnel can hear the current real-time elevator warning status at the first time, and then arrange personnel to check according to the elevator status identification or know the elevator status that does not need to be checked.

[0043] In one example, when the elevator management system can be a text output system, the text corresponding to the elevator status identification can be directly sent to the management terminal of the elevator manager, so that the elevator manager can know the current real-time elevator warning status at the first time, and then arrange personnel to check according to the elevator status identification or know the elevator status that does not need to be checked.

[0044] In the method provided by the embodiment of the present application, the elevator early warning state judgment model is used to determine the stable operation stage of the elevator in the operation process, and then the component point parameters of the multiple components of the elevator in the stable operation stage are obtained, and the characteristic parameters of the component point parameters of the multiple components are obtained by presetting the characteristic parameter function, wherein the characteristic parameters include the information entropy value of the component point parameters of the multiple components and the information redundancy of the component point parameters of the multiple components; then, according to the characteristic parameters of the component point parameters of the multiple components, the quality score of the component point parameters of each component in the multiple components is determined, and the target parameters in the component point parameters of each component in the multiple components are screened according to the quality score; finally, the elevator early warning state used to indicate the elevator safety level is determined and transmitted to the management system through the target parameters and the elevator early warning function, so that the elevator management system generates an elevator state identifier according to the elevator early warning state. In this way, by observing the component point parameters of each of the multiple component points in the elevator, the component point parameters are judged and screened, and the target parameters that best represent the elevator quality at each point are selected, and the elevator safety level is determined by combining the target parameters with the elevator early warning function. In this way, the actual health status of the elevator can be obtained during the operation of the elevator, avoiding the hidden dangers of elevator safety failures caused by untimely elevator inspections during regular inspections and warranty inspections when failures occur, thereby greatly improving the accuracy of elevator early warnings. At the same time, since the data ultimately involved in judging the safety level of the elevator are the parameters with higher quality scores among the component point parameters of multiple components, while improving the accuracy of judging the safety level, it can also improve the efficiency of confirming the elevator early warning status and save the resources consumed in confirming the elevator early warning status.

[0045] In another embodiment of the present application, a specific implementation method for determining the stable operation state of an elevator is also provided. Exemplarily, the specific implementation of "determining the stable operation stage of the elevator during operation through a state determination model" mentioned above includes: collecting component state parameters of multiple components of the elevator when the state parameters of the elevator start operation are obtained; and determining the stable operation stage of the elevator during operation according to the component state parameters through the state determination model.

[0046] Exemplarily, the state determination model may be a random forest model.

[0047] It can be understood that the random forest model can effectively process the high-dimensional multi-parameter data of component vibration of multiple components in the elevator (for example, the traction machine) under running conditions by integrating multiple decision trees, so as to improve the accuracy and robustness of the model and provide a basis for identifying the stable operation process of the equipment.

[0048] Exemplarily, the above-mentioned component status parameters can be data obtained from monitoring points set at each of the multiple components of the elevator. By inputting these data into the random forest model, the data corresponding to the stable operation stage of the elevator can be determined through the model, and these data can be used as the final data for determining the early warning status of the elevator.

[0049] Optionally, for the above-mentioned state determination model, the embodiment of the present application also provides a training method for the state determination model. Exemplarily, the elevator risk warning management method provided in the embodiment of the present application includes: obtaining the past operating parameters of the above-mentioned elevator, and setting the above-mentioned past operating parameters as sample data; training the initial state determination model through the above-mentioned sample data, and obtaining the first test data of the above-mentioned initial state determination model; when the difference between the above-mentioned first test data and the above-mentioned sample data is greater than a preset threshold, training the above-mentioned initial state determination model through the above-mentioned sample data, and obtaining the second test data of the above-mentioned initial state determination model; when the difference between the above-mentioned second test data and the above-mentioned sample data is greater than the preset threshold, determining that the above-mentioned initial state determination model is the above-mentioned state determination model.

[0050] Exemplarily, the above-mentioned past operating parameters include past parameters of various component points in the process from starting to stopping the above-mentioned elevator, and the above-mentioned sample data includes the corresponding relationship between the operating parameters and the status results.

[0051] Exemplarily, the above-mentioned past operation parameters may include parameters of each component point in the process of the elevator being started and stopped multiple times.

[0052] It can be understood that these past operating parameters are the parameters that the state determination model can use to determine the operating state of the elevator after training is completed.

[0053] Exemplarily, the above-mentioned past operating parameters are actually acquired by sensors at monitoring points set on multiple components of the elevator during the operation of the elevator, and have been pre-processed to extract useful parameters that can characterize different states of the elevator.

[0054] Furthermore, the operation state of the elevator from start-up to stop-operation can be characterized by the vibration of the elevator, such as vibration acceleration. That is, the operation parameters in the previous operation parameters of each component point can be the vibration acceleration of each component point, and the state result can be the elevator operation state corresponding to the vibration acceleration, which is start-up, speed increase, steady speed or speed reduction, and finally the different stages of elevator stop operation. That is, different vibration accelerations can correspond to different elevator operation states.

[0055] For example, if the component of the elevator is a traction machine, the vibration acceleration measurement point of the elevator traction machine can be used as the analysis object, all the data of the vibration acceleration measurement point can be obtained, and different index parameters therein can be extracted as the first test data and the operating states corresponding to the different index parameters for training. The first test data may include the mean, variance, standard deviation, peak value, kurtosis, etc. of the vibration acceleration measurement point of the traction machine during the operation process. Among them, different means, different variances, different standard deviations, different peak values ​​and different kurtosis.

[0056] Exemplarily, the first test data includes a correspondence between operating parameters and first test status results.

[0057] Exemplarily, the above-mentioned preset threshold may be preset or user-defined.

[0058] Exemplarily, the preset threshold may be used to indicate: consistency between the first test status result in the first test data and the status result in the sample data.

[0059] In one example, when the test status result in the first test data is different from the status result in the above-mentioned sample data, that is, assuming that the first test status result is startup, and the status result in the sample data is speed increase, then the difference between the first test data and the sample data is greater than a preset threshold, that is, the consistency between the first test data and the sample data is insufficient, and training needs to be continued to obtain the second test data. When the second test status result in the second test data is consistent with the status result in the sample data, it means that the initial status determination model has been trained and a status determination model that can be put into use is formed.

[0060] In one example, the labeled sample data can be divided into a training set and a test set, the training set data is used to train the initial state determination model, and the test set data is used to evaluate the performance of the state determination model. Finally, the trained state determination model is applied to real-time data to identify the complete operation and stop process of the elevator.

[0061] Exemplarily, when the initial state determination model is an initial random forest model, the training process using the training set in the sample data is as follows: First calculate the splitting criteria. Commonly used splitting criteria include Gini Impurity and Information Gain. Here, we choose Gini Impurity, and its formula is:

[0062] Among them, D is the training set, C is the number of categories, and pi is the proportion of the i-th category.

[0063] In the selected feature set Fsplit, the feature that makes the splitting criterion optimal is selected for splitting, where Fsplit is m features randomly selected from M features,

[0064] The final prediction result of the initial random forest model is obtained by voting and averaging the prediction results of all decision trees (regression problem). Each tree outputs a continuous value, and the final prediction result is the average of the prediction values ​​of all trees. Assuming that the prediction values ​​of T trees for input sample x are y1, y2, …, yT, the final prediction result is:

[0065] The initial random forest model can evaluate the importance of features by calculating how often the features are split in the tree. The calculation formula for feature importance is:

[0066] Where Trees is the set of all decision trees, ΔError(t,f) is the error reduction of feature f in tree t, SplitCount(t,f) is the number of times feature f is used as a split node in tree t, and TotalSplits(t) is the total number of split nodes in tree t.

[0067] The higher the frequency of a feature as a split node in all trees, the greater the role of the data of this feature in the model. This is because high-frequency split features can effectively divide the data set into purer subsets, thus helping to improve the predictive power of the random forest model.

[0068] It should be noted that Random Forest is an ensemble learning method, mainly used for classification and regression tasks. It improves the accuracy and robustness of the model by building multiple decision trees and aggregating their prediction results. The core idea of ​​Random Forest is to reduce the overfitting problem of a single decision tree by introducing randomness and diversity.

[0069] In the embodiment of the present application, vibration sensors can be installed at different positions of the elevator to collect vibration data during the elevator startup, speed increase, stable operation, speed reduction and stop process; then the data of the startup phase is marked as 1, the data of the speed increase phase is marked as 2, the data of the stable operation phase is marked as 3, the data of the speed reduction phase is marked as 4, and the data of the stop phase is marked as 5. Figure 2 , Figure 2 Used to characterize the multi-parameter start-stop long waveform signal of elevator components. Figure 3 It is used to characterize the single start-stop vibration waveform diagram, wherein the car 21, the traction machine 22, and the sound pressure 23.

[0070] In the above Figure 2 and Figure 3 Extract various characteristic indicators of vibration parameters (i.e. the aforementioned parameters of each component point): mean value, standard deviation, maximum value, minimum value, peak-to-peak value, root mean square (RMS), kurtosis, and skewness. Then normalize the characteristic indicators to ensure that all characteristics are at the same level. Figure 4 The time domain waveform and multi-eigenvalue amplitude trend diagram are shown.

[0071] Divide the collected data set into a training set and a test set, usually with a ratio of 70% training set and 30% test set. Use the training set to train the random forest classifier and use the accuracy to evaluate the model performance. Use the trained model to predict the new vibration data, identify which stage the data belongs to, and filter out the data marked as the stable operation stage based on the model prediction results. Figure 5 , Figure 5 The figure shows the automatic recognition effect of the stable operation phase data during the elevator start-stop process, and the measurement point used is the traction machine vibration data. Figure 5 It includes a prediction part 51 and a test part 52.

[0072] In another embodiment of the present application, a specific implementation method for determining the characteristic parameters of an elevator is also provided. Exemplarily, the specific implementation of the aforementioned "obtaining component point parameters of multiple components of the elevator in the stable operation stage, and obtaining characteristic parameters of the component point parameters of multiple components by preset characteristic parameter functions" includes: performing standardization processing on different component point parameters of each component parameter of the component point parameters of the multiple components to obtain standardized parameters of different component point parameters; determining the weight coefficient of each standardized parameter in the standardized parameters by a weight function according to the standardized parameters; determining the information entropy value of each point information in the component point information and the information redundancy of each point by combining the weight coefficients of the different indicators by an information entropy function.

[0073] Exemplarily, the above-mentioned standardization processing may be a processing of performing data standardization using a positive indicator method.

[0074] Exemplarily, the component point parameters of the above-mentioned multiple components may be index parameters of multiple indexes of component point positions obtained by taking the vibration measurement points in components such as the elevator traction machine, the elevator car and the elevator brake as analysis objects.

[0075] Furthermore, the above-mentioned component point parameters may include a plurality of index parameters corresponding to the vibration acceleration of each vibration measuring point and a plurality of index parameters corresponding to the vibration velocity parameter of each vibration measuring point.

[0076] Specifically, a single vibration measurement point can correspond to multiple component point parameters. Each component point parameter can include multiple commonly used index parameters. For example, we select four commonly used index parameters: effective value, peak value, true peak value, and warpage. Use the following formula for standardization:

[0077] in, is the original value of the i-th sample parameter under the j-th indicator parameter; is the minimum value of the jth indicator parameter, is the maximum value under the j-th indicator parameter.

[0078] Assuming that the elevator is in a stable operation stage for 6 seconds, the above four indicator parameters, namely the effective value of the elevator within 6 seconds, the peak value of the elevator, the true peak value of the elevator and the tilt of the elevator are used to indicate the trend value within these 6 seconds. One indicator parameter corresponds to each second, and the weight coefficient of each indicator parameter can be calculated. The specific formula is as follows:

[0079] in, is the weight coefficient of the i-th sample parameter under the j-th indicator parameter, and n is the number of samples.

[0080] Then calculate the information entropy value of the jth indicator parameter of information entropy and information redundancy :

[0081]

[0082]

[0083] In another embodiment of the present application, a specific implementation method for determining elevator target parameters using elevator characteristic parameters is also provided. Exemplarily, the specific implementation of "determining the quality score of the component point parameters of each component in the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and screening the target parameters in the component point parameters of each component in the multiple components according to the quality score" mentioned above includes: according to the information entropy value and the information redundancy, through a sorting function, obtaining the quality score of the component point parameters of each component in the multiple components corresponding to the information entropy value and the information redundancy; sorting the quality score of the component point parameters of each component in the multiple components to determine the main parameters and auxiliary parameters.

[0084] Combined with the above content, according to the information redundancy obtained , calculate the quality score of the index parameter of each point information in each component point information, is the quality score, and the following formula is the ranking function.

[0085]

[0086] After obtaining the component parameters of each of the multiple components, that is, the quality scores corresponding to the indicator parameters, the quality scores of each indicator parameter in each component are classified and sorted: finally, the following parameter contents of each indicator parameter in each component are confirmed: main parameters, auxiliary parameters, light parameters, and discarded parameters, among which the main parameters and auxiliary parameters are the target parameters that we need to select in the end, and can be used to obtain the parameters of the elevator warning status.

[0087] Furthermore, the basic scores of the main parameters and the auxiliary parameters are weighted and summed to obtain the elevator warning state corresponding to the health state, and the full score is 100 points.

[0088] like Figure 6 The main parameters and auxiliary parameters are shown. Taking a conventionally configured elevator as an example, the main parameters required for model input include the effective peak value and true peak value of horizontal vibration acceleration of the traction machine, the effective peak value of horizontal and axial vibration acceleration of the car, and the auxiliary parameters include the effective value of horizontal vibration velocity of the traction machine and the true peak value of horizontal vibration acceleration of the car. The number and type of main parameters and auxiliary parameters can be finally determined by the above entropy weight method according to the configuration.

[0089] In another embodiment of the present application, a specific implementation method for determining the elevator warning state is also provided. Exemplarily, the specific implementation of "determining the elevator warning state according to the target parameters and the elevator warning function" mentioned above includes: obtaining the basic parameter score through the above-mentioned elevator health function in combination with the above-mentioned main parameters and the above-mentioned auxiliary parameters; according to the above-mentioned basic parameter score, confirming the operation score corresponding to each parameter of each component in the above-mentioned elevator through the above-mentioned elevator operation function; obtaining the operation score corresponding to each parameter of each component and the preset operation weight coefficient; confirming the overall operation score of the elevator in combination with the operation score corresponding to each component and the above-mentioned elevator warning function; determining the elevator warning state according to the above-mentioned overall operation score of the elevator.

[0090] Exemplarily, the above elevator health function is preset in advance, and may also be customized by the user.

[0091] Exemplarily, the parameter basic score is used to indicate the basic quality of different index parameters of the component point corresponding to the target parameter, and the parameter basic score s is determined by the parameter basic score function. 1 : First, in s 0For 100 points:

[0092] Among them, the number of main parameters is na, the number of auxiliary parameters is nb, s0 represents the full score of the operation, and s1 represents the basic score of the parameter.

[0093] Further, parameter basic score:

[0094] The basic scores corresponding to the main parameter s2_my and the auxiliary parameter s2_ay are:

[0095] Furthermore, according to the basic parameter score, the operation score corresponding to each parameter of each component can be obtained, that is, it is used to judge the condition of each parameter of each component during the operation of the elevator, and then used to judge the quality of the overall component during the operation. Specifically, as described in the following formula, this formula is the elevator operation function:

[0096] Among them, s3_my is the parameter operation score of the main parameter, s3_ay is the parameter operation score of the auxiliary parameter, k1 is the characteristic value state coefficient, k2 is the degradation coefficient, and the calculation formula of k1 is as follows. k1 is calculated by the fixed danger threshold and hourly average of the main parameters and auxiliary parameters of the elevator, reflecting the distance between the value of the component point parameter of the measuring point of each component and the fixed danger threshold recommended by the vibration standard: k 1 =(v a -v r ) / (v a -v h ) Among them, va is a fixed danger threshold, vr is an hourly average, and vh is If k1 is less than 0, it is set to 0; if it is greater than 0.95, it is directly set to 1.

[0097] k2 is mainly given by the rate of change of the daily average index of each component's measuring point. The daily average of each component's measuring point on that day is compared with the average of the previous week, and then different coefficients are assigned according to the situation. Specifically, the value of k2 needs to first determine the daily average value of the parameter index and compare it with the 50% fixed danger threshold. If it is less than this value, k2=1, and the impact of the change rate on the operation score is not considered; if it is greater than this value, continue to compare the daily average value of the component point parameter with the average of its daily average value of the previous week, and use the following formula to get the value of k2: k 2 =1-(b-50)×0.02 Among them, b is the ratio of the daily average value of the component point parameter to the fixed danger threshold. The fixed danger threshold is derived from the standard and statistical values. In particular, the measurement positions of various components of the elevator are used to measure the component point parameters of the sensors set at various measuring points on the elevator, that is, various indicator data.

[0098] like Figure 7 , Figure 7 This is the hourly health trend chart of the faulty elevator machine, which is used to characterize the hourly health trend of the faulty elevator machine.

[0099] Exemplarily, when the operating score corresponding to each parameter of each component is determined, the overall operating score of each component is calculated.

[0100] Specifically, the weighted sum of the main parameters and auxiliary parameters of each component is used to obtain the component operation score s4, and the weighted summation formula is shown in the following formula. The weighted summation formula includes the above-mentioned preset operation weight coefficient, which can be preset in advance or customized by the user.

[0101]

[0102] Among them, Nxna is the number of main parameters of the component-related measuring points, and Nxnb is the number of auxiliary parameters of the component-related measuring points.

[0103] Exemplarily, according to the operation score s4 calculated above, in the quality characterization method: the value range is set between 0 and 1, then the operation quality of the component is s4 / 100.

[0104] Exemplarily, the elevator early warning function can be used to determine the elevator whole machine operation score. Specifically, the elevator whole machine operation score is the comprehensive calculation score of the main parameters and auxiliary parameters of the above-mentioned components, that is, the following elevator overall operation score S5.

[0105] s 5 =

[0106] Exemplarily, according to the above-calculated elevator overall operation score S5, the quality representation method is: the value range is set between 0 and 1, and the overall operation quality of the elevator is s5 / 100.

[0107] Finally, the elevator warning status is determined based on the overall operation quality s5 / 100 of the elevator.

[0108] For example, when there is no abnormality in the elevator equipment as a whole, the health of the components and the whole machine is between 0.85 and 1, with small fluctuations within this range. As the health of the equipment continues to deteriorate, the corresponding health value will gradually decrease. According to conventional practice, when the health is between 0.70 and 0.85, it is in the "warning" state; when the health is between 0.60 and 0.7, it is in the "alarm" state; when the health is between 0.5 and 0.6, it is in the "dangerous" state; once the health is 0.5, the elevator should be maintained.

[0109] Specifically, Figure 8 As shown, Figure 8 As shown in the elevator equipment health classification warning diagram, the line mark with a value of 0.85 is the warning point. Through testing, this method has achieved good warning effects on abnormal conditions of components such as elevator traction machines and cars.

[0110] Exemplarily, there is a preset corresponding relationship between the above-mentioned elevator overall operation score and the elevator warning status.

[0111] Furthermore, there is a preset corresponding relationship between the elevator warning state and the elevator warning state.

[0112] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the training rule determination method described in the present application is implemented. For example, the following can be executed: Figure 1 The individual steps of the method are shown.

[0113] The present invention provides a computer program product, which includes instructions that are executed by a processor when the processor executes the instructions. Figure 1 The individual steps of the method are shown.

[0114] It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order or that all illustrated operations must be performed to achieve desired results.

[0115] Fig. 9 This is a block diagram of an elevator risk warning management system according to an embodiment of the present application. Fig. 9 The device includes a determining unit 601, an acquiring unit 602 and an executing unit 603.

[0116] A determination unit 601 is used to determine the stable operation stage of the elevator during operation through a state determination model; An acquisition unit 602 is used to acquire component position parameters of multiple components of the elevator in a stable operation stage, and acquire characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function, wherein the characteristic parameters include: information entropy values ​​of the component position parameters of the multiple components and information redundancy of the component position parameters of the multiple components; An execution unit 603 is used to determine a quality score of the component point parameter of each component in the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and filter the target parameters in the component point parameter of each component in the multiple components according to the quality score; The determination unit 601 is also used to determine the elevator warning state according to the target parameters and the elevator warning function and transmit it to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state, and the elevator warning state is used to indicate the safety level of the elevator.

[0117] In one embodiment, the determination unit 601 is specifically configured to, when the state parameters of the elevator startup operation are acquired, collect component state parameters of multiple components of the elevator; The state determination model is used to determine the stable operation stage of the elevator during operation according to the component state parameters.

[0118] In one embodiment, the execution unit 603 is further used to obtain the previous operation parameters of the elevator and set the previous operation parameters as sample data, wherein the previous operation parameters include the previous parameters of each component point during the process from the start-up operation to the stop-operation of the elevator, and the sample data includes the corresponding relationship between the operation parameters and the status results; Training an initial state determination model through the sample data, and obtaining first test data of the initial state determination model; When the difference between the first test data and the sample data is greater than a preset threshold, training the initial state determination model by training the initial state determination model with the sample data, and obtaining second test data for the initial state determination model; When the difference between the second test data and the sample data is greater than a preset threshold, the initial state determination model is determined to be the state determination model.

[0119] In one embodiment, the acquisition unit 602 is specifically configured to perform standardization processing on different component point parameters of each component point parameter of the plurality of component point parameters to obtain standardized parameters of the different component point parameters; According to the standardized parameters, determining a weight coefficient of each standardized parameter in the standardized parameters by a weight function; The information entropy value of each point information in the point information of each component and the information redundancy of each point are determined by combining the weight coefficients of the different indicators through the information entropy function.

[0120] In one embodiment, the execution unit 603 is specifically used to obtain, according to the information entropy value and the information redundancy, a quality score of the component point parameter of each component in the multiple components corresponding to the information entropy value and the information redundancy through a sorting function; The quality scores of the component point parameters of each of the multiple components are sorted to determine the main parameters and the auxiliary parameters.

[0121] In one embodiment, the determination unit 601 is specifically configured to obtain a parameter basic score by combining the main parameter and the auxiliary parameter through the elevator health function; According to the parameter basic score, the operation score corresponding to each parameter of each component in the elevator is determined through the elevator operation function; According to the operation score corresponding to each parameter of each component and the preset operation weight coefficient, the operation score corresponding to each component of the elevator is obtained; Determine the overall operation score of the elevator by combining the operation score corresponding to each component and the elevator early warning function; Determine the elevator warning status according to the overall elevator operation score It should be understood that the units recorded in the elevator risk warning management system correspond to the various steps in the method described in the accompanying drawings. Therefore, the operations and features described above for the method are also applicable to the elevator risk warning management system and the units contained therein, and will not be repeated here. The elevator risk warning management system can be pre-implemented in a browser or other security application of a computer device, or can be loaded into a browser or its security application of a computer device by downloading or the like. The corresponding units in the elevator risk warning management system can cooperate with the units in the computer device to implement the solution of the embodiment of the present application.

[0122] For the several modules or units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0123] It should be noted that for details not disclosed in the elevator risk warning management system of the embodiment of the present application, please refer to the details disclosed in the above embodiments of the present application, which will not be repeated here.

[0124] Reference below Fig.10, Fig.10 A schematic diagram of the structure of a computer device suitable for implementing the embodiments of the present application is shown. Fig.10 As shown, the computer system 1700 includes a central processing unit (CPU) 1701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1702 or the program loaded from the storage part 1708 to the random access memory (RAM) 1703. In the RAM 1703, various programs and data required for the operation instructions of the system are also stored. The CPU 1701, the ROM 1702, and the RAM 1703 are connected to each other through a bus 1704. An input / output (I / O) interface 1705 is also connected to the bus 1704.

[0125] The following components are connected to the I / O interface 1705: an input section 1706 including a keyboard, a mouse, etc.; an output section 1707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1708 including a hard disk, etc.; and a communication section 1709 including a network interface card such as a LAN card, a modem, etc. The communication section 1709 performs communication processing via a network such as the Internet. A drive 1710 is also connected to the I / O interface 1705 as needed. A removable medium 1711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1710 as needed, so that a computer program read therefrom is installed into the storage section 1708 as needed.

[0126] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1709, and / or installed from a removable medium 1711. When the computer program is executed by the central processing unit (CPU) 1701, the above-mentioned functions defined in the system of the present application are executed.

[0127] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0128] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be set in a processor. For example, it may be described as: a processor includes a first receiving module, a second receiving module, and a sending module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0130] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the elevator risk warning management method described in the present application.

[0131] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present application (but not limited to) by each other to form a technical solution.

Claims

1. An elevator risk early warning management method, characterized in that: include: Determining the stable operation stage of the elevator during operation by means of a state determination model; Obtain component position parameters of multiple components of the elevator in a stable operation stage, and obtain characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function, wherein the characteristic parameters include: information entropy values ​​of the component position parameters of the multiple components and information redundancy of the component position parameters of the multiple components; Determining a quality score of the component point parameters of each of the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and screening target parameters in the component point parameters of each of the multiple components according to the quality score; According to the target parameters and the elevator warning function, the elevator warning state is determined and transmitted to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state, and the elevator warning state is used to indicate the safety level of the elevator.

2. The method according to claim 1, characterized in that The method of determining the stable operation stage of the elevator during operation by using a state determination model includes: When the state parameters of the elevator startup operation are obtained, collecting the component state parameters of a plurality of components of the elevator; The state determination model is used to determine the stable operation stage of the elevator during operation according to the component state parameters.

3. The method according to claim 1, characterized in that The method further comprises: Acquire the past operation parameters of the elevator, and set the past operation parameters as sample data, wherein the past operation parameters include the past parameters of each component point during the process from starting to stopping the elevator, and the sample data includes the corresponding relationship between the operation parameters and the status results; Training an initial state determination model through the sample data, and obtaining first test data of the initial state determination model; When the difference between the first test data and the sample data is greater than a preset threshold, training the initial state determination model by training the initial state determination model with the sample data, and obtaining second test data for the initial state determination model; When the difference between the second test data and the sample data is greater than a preset threshold, the initial state determination model is determined to be the state determination model.

4. The method according to claim 1, characterized in that: The step of obtaining component position parameters of a plurality of components of the elevator in a stable operation stage, and obtaining characteristic parameters of the component position parameters of the plurality of components by using a preset characteristic parameter function, includes: Performing standardization processing on different component point parameters of each component point parameter of the plurality of components to obtain standardized parameters of the different component point parameters; According to the standardized parameters, determining a weight coefficient of each standardized parameter in the standardized parameters by a weight function; The information entropy value of each point information in the point information of each component and the information redundancy of each point are determined by combining the weight coefficients of the different indicators through the information entropy function.

5. The method according to claim 1, characterized in that Determining the quality score of the component point parameter of each component in the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and screening the target parameters in the component point parameter of each component in the multiple components according to the quality score, includes: According to the information entropy value and the information redundancy, a quality score of a component point parameter of each component in a plurality of components corresponding to the information entropy value and the information redundancy is obtained through a ranking function; The quality scores of the component point parameters of each of the multiple components are sorted to determine the main parameters and the auxiliary parameters.

6. The method according to claim 1, characterized in that Determining the elevator warning state according to the target parameter and the elevator warning function includes: By combining the elevator health function with the main parameters and the auxiliary parameters, a basic parameter score is obtained; According to the parameter basic score, the operation score corresponding to each parameter of each component in the elevator is determined through the elevator operation function; According to the operation score corresponding to each parameter of each component and the preset operation weight coefficient, the operation score corresponding to each component of the elevator is obtained; Determine the overall operation score of the elevator by combining the operation score corresponding to each component and the elevator early warning function; The elevator warning state is determined according to the overall elevator operation score.

7. An elevator risk warning management system, characterized in that: The system comprises: A determination unit, used to determine the stable operation stage of the elevator during operation through a state determination model; An acquisition unit is used to acquire component position parameters of multiple components of the elevator in a stable operation stage, and acquire characteristic parameters of the component position parameters of the multiple components through a preset characteristic parameter function, wherein the characteristic parameters include: information entropy values ​​of the component position parameters of the multiple components and information redundancy of the component position parameters of the multiple components; An execution unit, configured to determine a quality score of the component point parameter of each of the multiple components according to the characteristic parameters of the component point parameters of the multiple components, and to filter target parameters in the component point parameter of each of the multiple components according to the quality score; The determination unit is further used to determine the elevator warning state according to the target parameters and the elevator warning function and transmit it to the elevator management system, so that the elevator management system generates an elevator state identifier according to the elevator warning state, and the elevator warning state is used to indicate the safety level of the elevator.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising instructions, characterized in that: When the instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images