CN110790105B

CN110790105B - Elevator door system diagnosis and decline time prediction method and diagnosis and prediction system

Info

Publication number: CN110790105B
Application number: CN201911143054.2A
Authority: CN
Inventors: 董亚明; 毛晴; 袁武水; 杨家荣; 丁晟; 金宇辉; 张筱
Original assignee: Shanghai Mitsubishi Elevator Co Ltd; Shanghai Electric Group Corp
Current assignee: Shanghai Mitsubishi Elevator Co Ltd; Shanghai Electric Group Corp
Priority date: 2019-11-20
Filing date: 2019-11-20
Publication date: 2021-11-16
Anticipated expiration: 2039-11-20
Also published as: CN110790105A

Abstract

The invention relates to a method and a system for predicting diagnosis and decay time of an elevator door system, relating to the technical field of elevator detection and aiming at solving the problem that the maintenance work efficiency of the elevator door system is not high possibly caused by a mode of periodic maintenance in the prior art. The method comprises the following steps: acquiring a plurality of vibration characteristic values corresponding to vibration data of an elevator door system during operation and a plurality of operation characteristic values corresponding to operation data; determining at least one principal component characteristic value representing a state of the elevator door system based on the plurality of vibration characteristic values and the plurality of operation characteristic values; inputting at least one principal component characteristic value into a health assessment model to obtain a health condition parameter value; determining a state of the elevator door system based on the health parameter value. The embodiment of the invention determines the state of the elevator door system through the corresponding characteristic value in the operation process, thereby improving the maintenance efficiency of the elevator door system.

Description

Elevator door system diagnosis and decline time prediction method and diagnosis and prediction system

Technical Field

The invention relates to the technical field of elevator detection, in particular to a method and a system for predicting elevator door system diagnosis and decay time.

Background

The urbanization process of China is continuously accelerated, high-rise buildings are growing year by year, and elevators are increasingly becoming convenient vertical transportation tools for people to go out. Because the elevator frequency of use is great, its potential safety hazard receives everyone's concern increasingly, especially elevator's door system once break down will influence the normal operating of complete machine, even cause passenger's injures and deaths.

Generally, a method of repairing an elevator door system is to determine a failure source and repair or replace a failed component when the state of the elevator door system is determined to be a failure state. The method comprises the steps of determining that the state of the elevator door system is a fault state, and periodically detecting faults when a user arrives at the elevator door.

However, when the elevator door system is degraded in performance to a certain extent, if maintenance is performed according to a certain period, the elevator door system may fail during the period, which may cause untimely maintenance, thereby affecting the normal operation of the whole machine, or when a user regularly arrives at the elevator door system for fault detection, the elevator door system is found not to fail, which causes unnecessary waste of elevator stopping and maintenance labor.

To sum up, the maintenance mode of current elevator door system maintenance efficiency is not high.

Disclosure of Invention

The invention provides a method and a system for predicting diagnosis and decay time of an elevator door system, which are used for solving the problem that the maintenance work efficiency of the elevator door system is not high possibly due to a periodic maintenance mode in the prior art.

In a first aspect, a method for diagnosing an elevator door system provided in an embodiment of the present invention includes:

acquiring a plurality of vibration characteristic values corresponding to vibration data of an elevator door system during operation and a plurality of operation characteristic values corresponding to operation data;

determining at least one principal component characteristic value representing a state of an elevator door system based on the plurality of vibration characteristic values and the plurality of operation characteristic values;

inputting the at least one principal component characteristic value into a health assessment model to obtain a health condition parameter value;

determining a state of the elevator door system based on the health parameter value.

According to the method, the characteristic value representing the state of the elevator door system can be obtained by obtaining the vibration data and the operation data of the elevator door system in the operation process of the elevator door system, then the health condition parameter value is calculated through the characteristic value, and then whether the elevator door system is in a normal state or a fault state or other states is determined through the health condition parameter value, so that the state of the elevator door system can be automatically determined in the elevator door system in operation, and the maintenance efficiency is improved.

In one possible implementation, determining a state of the elevator door system based on the health parameter value includes:

if the health condition parameter value is larger than a preset early warning threshold value, determining that the state of the elevator door system is a normal state;

if the health condition parameter value is not larger than a preset alarm threshold value, determining that the state of the elevator door system is a fault state;

if the health condition parameter value is not greater than the preset early warning threshold value and is greater than the preset alarm threshold value, determining that the state of the elevator door system is in a sub-health state;

and the preset alarm threshold value is smaller than the preset early warning threshold value.

The method can compare the health condition parameter value with the threshold value, for example, the health condition parameter value is compared with the preset early warning threshold value, when the health condition parameter value is greater than the preset early warning threshold value, the state of the elevator door system is determined to be a normal state, the health condition parameter value is compared with the preset alarm threshold value, when the health condition parameter value is less than or equal to the preset alarm threshold value, the state of the elevator door system is determined to be a fault state, the health condition parameter value is compared with the preset early warning threshold value and the preset alarm threshold value, the health condition parameter value is not greater than the preset early warning threshold value and is greater than the preset alarm threshold value, the state of the elevator door system is determined to be a sub-health state, and the state of the elevator door can be accurately determined through the comparison of the threshold values.

In one possible implementation, after determining the state of the elevator door system according to the health parameter value, the method further includes:

if the state of the elevator door system is in a sub-health state, inputting the at least one principal component characteristic value into a type diagnosis model, and determining the type of the sub-health state of the elevator door system; or

And if the state of the elevator door system is a fault state, inputting the at least one principal component characteristic value into a type diagnosis model, and determining the type of the fault state of the elevator door system.

According to the method, the principal component characteristic value can be input into the type diagnosis model, the type of the state of the elevator door can be determined, for example, when the elevator door system is in a sub-health state, the type of the sub-health state can be determined, when the elevator door system is in a fault state, the type of the fault state can be determined, and the maintenance efficiency of the elevator door system can be improved through the determined type.

if the state of the elevator door system is a normal state, inputting the preset early warning threshold value, the preset alarm threshold value and the health condition parameter value into a prediction time model, and determining a first prediction time length for the state of the elevator door system to decline from the normal state to a sub-health state and a second prediction time length for the state of the elevator door system to decline from the normal state to a fault state; or

And if the state of the elevator door system is in a sub-health state, inputting the preset alarm threshold value and the health condition parameter value into a prediction time model, and determining a third prediction duration for the state of the elevator door system to decline from the sub-health state to a fault state.

In the method, the health condition parameter value can be obtained through the health evaluation model, the health condition parameter value is input into the prediction time model, the change time length is determined, for example, when the state of the elevator door system is in a normal state, a preset early warning threshold value, a preset alarm threshold value and the health condition parameter value are input into the prediction time model, the first prediction time length that the state of the elevator door system is changed from the normal state to a sub-health state and the second prediction time length that the state of the elevator door system is degraded from the normal state to a fault state are determined, when the state of the elevator door system is in the sub-health state, the preset alarm threshold value, the health condition parameter value and the current time are input into the prediction time model, the third prediction time length that the state of the elevator door system is changed from the sub-health state to the fault state is determined, and therefore a user can arrange work in advance according to the first prediction time length, the second prediction time length and the third prediction time length, and the elevator door system is maintained in time, so that the elevator door system is prevented from being broken down.

In one possible implementation, determining at least one principal component characteristic value representing a state of the elevator door system from the plurality of acceleration characteristic values and the plurality of operation characteristic values includes:

obtaining a plurality of principal component characteristic values by adopting a principal component analysis method for the plurality of acceleration characteristic values and the plurality of operation characteristic values;

determining the cumulative contribution rate corresponding to each principal component characteristic value;

and extracting principal component characteristic values corresponding to the cumulative contribution rates of the previous preset number of the cumulative contribution rates larger than the preset value as principal component characteristic values representing the state of the elevator door system.

According to the method, the plurality of principal component characteristic values can be obtained by adopting a principal component analysis method for the plurality of acceleration characteristic values and the plurality of operation characteristic values, the obtained principal component characteristic values are more, the accumulated contribution rate corresponding to each principal component characteristic value can be adopted, the principal component characteristic values of which the accumulated contribution rate is greater than the previous preset number in the preset values and which represent the state of the elevator door system are selected, namely, the fewer principal component characteristic values with high specific gravity are selected from the plurality of principal component characteristic values and input into the health assessment model, and the calculation efficiency of the health assessment model is improved.

In a second aspect, a method for predicting a decay time of an elevator door system provided in an embodiment of the present invention includes:

determining a health condition parameter value of an elevator door system according to vibration data and operation data of the elevator door system during operation;

and inputting the health condition parameters and a preset state threshold value of state decline of the elevator door system into a prediction time model, and determining the prediction duration of the state decline of the elevator door system from the current state to other states.

According to the method, the prediction time model can be input according to the determined health condition parameter values, and the prediction time length of the state of the elevator door system declining from the current state to other states is determined, so that a user can predict the time length and arrange work in advance, the maintenance of the elevator door system is carried out in time, and the elevator door system is prevented from being out of order.

In a possible implementation manner, if the current state is a normal state, the other states include a sub-health state and a fault state, and the predicted duration includes a first predicted duration that falls from the normal state to the sub-health state and a second predicted duration that falls from the normal state to the fault state;

if the current state is a sub-health state, the other states comprise fault states, and the predicted time length comprises a third predicted time length from the normal state to the fault state.

According to the method, when the state of the elevator door system is in a normal state, the first prediction time length for changing the state of the elevator door system from the normal state to the sub-health state and the second prediction time length for declining from the normal state to the fault state can be determined, and when the state of the elevator door system is in the sub-health state, the third prediction time length for changing the state of the elevator door system from the sub-health state to the fault state is determined, so that when the state is changed, a user can work according to time arrangement in advance, and the maintenance efficiency of the elevator is improved.

In a possible implementation manner, if the current state is a normal state, the state threshold includes a preset early warning threshold and a preset alarm threshold;

and if the current state is a sub-health state, the state threshold value comprises a preset alarm threshold value.

According to the method, the preset early warning threshold value, the preset alarm threshold value and the health condition parameter value can be input into the prediction time model in a normal state, the first prediction time length and the second prediction time length are determined, if the current state is a sub-health state, the preset alarm threshold value and the health condition parameter value are input into the prediction time model, the third prediction time length is determined, and different prediction time lengths can be obtained according to different parameters.

In one possible implementation, the determining a health parameter value of an elevator door system from vibration data and operational data of the elevator door system while operating comprises:

determining a plurality of vibration characteristic values corresponding to the vibration data and a plurality of operation characteristic values corresponding to the operation data when the elevator door system operates;

determining at least one principal component characteristic value representing a state of the elevator door system based on the plurality of vibration characteristic values and the plurality of operational characteristic values;

and inputting the at least one principal component characteristic value into a health assessment model to obtain a health condition parameter value of the elevator door system.

According to the method, because more principal component characteristic values are obtained, the accumulated contribution rate corresponding to each principal component characteristic value can be adopted, the principal component characteristic values with the accumulated contribution rate larger than the number of the principal component characteristic values in the preset value and indicating the state of the elevator door system are selected, namely, fewer principal component characteristic values with high specific gravity are selected from the plurality of principal component characteristic values and input into the health assessment model, and the calculation efficiency of health assessment is improved.

In a third aspect, an elevator door diagnosis and prediction system provided in an embodiment of the present invention includes:

the characteristic extraction module is used for acquiring a plurality of vibration characteristic values corresponding to the vibration data and a plurality of operation characteristic values corresponding to the operation data when the elevator door system operates, and determining at least one principal component characteristic value representing the state of the elevator door system according to the plurality of vibration characteristic values and the plurality of operation characteristic values;

the health state evaluation module is used for inputting the at least one principal component characteristic value into a health evaluation model to obtain a health state parameter value; determining a state of the elevator door system based on the health parameter value;

and the fault prediction module is used for inputting the health condition parameters and a preset state threshold value of state decline of the elevator door system into a prediction time model and determining the prediction duration of the state decline of the elevator door system from the current state to other states.

In a possible implementation manner, the feature extraction module is specifically configured to:

and adopting a principal component analysis method for the acceleration characteristic values and the operation characteristic values to obtain a plurality of principal component characteristic values, determining an accumulated contribution rate corresponding to each principal component characteristic value, and extracting the principal component characteristic values corresponding to the accumulated contribution rates of the previous preset number of which the accumulated contribution rates are greater than a preset value as the principal component characteristic values representing the state of the elevator door system.

In a possible implementation manner, the health status evaluation module is specifically configured to:

if the health condition parameter value is larger than a preset early warning threshold value, determining that the state of the elevator door system is a normal state; if the health condition parameter value is not greater than a preset alarm threshold value, determining that the state of the elevator door system is a fault state; if the health condition parameter value is not greater than a preset early warning threshold value and is greater than a preset alarm threshold value, determining that the state of the elevator door system is in a sub-health state; and the preset alarm threshold value is smaller than the preset early warning threshold value.

In a possible implementation manner, if the current state is a normal state, the other states include a sub-health state and a fault state, the predicted time length includes a first predicted time length from the normal state to the sub-health state and a second predicted time length from the normal state to the fault state, and the state threshold includes a preset early warning threshold and a preset alarm threshold;

if the current state is a sub-health state, other states comprise a fault state, the predicted time length comprises a third predicted time length from the normal state to the fault state, and the state threshold comprises a preset alarm threshold.

In one possible implementation, the system further includes:

the fault diagnosis module is used for inputting the at least one principal component characteristic value into a type diagnosis model and determining the type of the sub-health state of the elevator door system if the state of the elevator door system is the sub-health state; or if the state of the elevator door system is a fault state, inputting the at least one principal component characteristic value into a type diagnosis model, and determining the type of the fault state of the elevator door system.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the elevator door system diagnostic method of any one of the first aspect embodiments or the elevator door system decay time prediction method of any one of the second aspect embodiments.

In a fifth aspect, embodiments of the present invention provide a storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the elevator door system diagnosis method according to any one of the embodiments of the first aspect or perform the elevator door system degradation time prediction method according to any one of the embodiments of the second aspect.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention and are not to be construed as limiting the invention.

Fig. 1 is a flow chart of a method of diagnosing an elevator door system provided according to an embodiment of the present invention;

fig. 2 is a flow chart of another method of diagnosing an elevator door system provided in accordance with an embodiment of the present invention;

fig. 3 is a flowchart of a method for predicting a decay time of an elevator door system according to an embodiment of the present invention;

fig. 4 is a block diagram of an elevator door diagnostic prediction system according to an embodiment of the present invention;

fig. 5 is a block diagram of another elevator door diagnostic prediction system provided in accordance with an embodiment of the present invention;

fig. 6 is a block diagram of an electronic device according to an embodiment of the present invention;

fig. 7 is a block diagram of another electronic device provided in accordance with an embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

Some of the words that appear in the text are explained below:

1. the term "and/or" in the embodiments of the present invention describes an association relationship of associated objects, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

2. The term "electronic equipment" in the embodiments of the present invention refers to equipment that is composed of electronic components such as integrated circuits, transistors, and electronic tubes, and functions by applying electronic technology (including) software, and includes electronic computers, robots controlled by the electronic computers, numerical control or program control systems, and the like.

The application scenario described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not form a limitation on the technical solution provided in the embodiment of the present invention, and it can be known by a person skilled in the art that with the occurrence of a new application scenario, the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems. Wherein, in the description of the present invention, unless otherwise indicated, "a plurality" means.

At present, a method for maintaining an elevator door system is that a user periodically detects a fault at an elevator door and maintains the elevator after finding the fault of the elevator. However, the elevator door system may malfunction in a periodic period, which may result in that the maintenance is not in time, or when the user regularly arrives at the elevator door system for fault detection, the elevator door system is found not to malfunction, which results in unnecessary elevator stopping and waste of maintenance labor.

Therefore, the embodiment of the invention provides the elevator door system diagnosis method, the method adopts the health assessment model, can determine the state of the elevator door system, can automatically determine the state of the elevator door system through the elevator door system in operation, does not need a user to arrive at the elevator door regularly for shutdown inspection, and improves the maintenance efficiency.

With respect to the above scenario, the following describes an embodiment of the present invention in further detail with reference to the drawings of the specification.

As shown in fig. 1, the method for diagnosing an elevator door system according to an embodiment of the present invention includes the following steps:

s100: and acquiring a plurality of vibration characteristic values corresponding to the vibration data of the elevator door system during operation and a plurality of operation characteristic values corresponding to the operation data.

The method for obtaining the vibration characteristic values corresponding to the vibration data of the elevator door system during operation comprises the steps of obtaining the vibration data of the elevator door system during operation, and then calculating the vibration characteristic values according to the vibration data.

As one example, the vibration data of an elevator door system while in operation can be a vibration acceleration. Such as installing a detector in an elevator door to obtain the vibration acceleration of the elevator door system.

From the vibration acceleration, respective parameter values of the vibration acceleration in three directions of X, Y, Z are calculated, and the respective parameter values are taken as vibration characteristic values.

Specific individual parameter values include, but are not limited to, some or all of the following:

mean of the acceleration in X, Y, Z three directions;

the variance of acceleration in X, Y, Z three directions;

the maximum of the acceleration in X, Y, Z three directions;

the square root amplitude of the acceleration in X, Y, Z three directions;

the minimum of acceleration in X, Y, Z three directions;

absolute average of acceleration in X, Y, Z three directions;

skewness of acceleration in X, Y, Z three directions;

root mean square values of acceleration in three directions of X, Y, Z;

the kurtosis of acceleration in the three directions X, Y, Z;

peak-to-peak acceleration in X, Y, Z three directions;

x, Y, Z waveform indexes of acceleration in three directions;

peak indicators of acceleration in X, Y, Z three directions;

pulse indexes of acceleration in X, Y, Z three directions;

margin indexes of acceleration in X, Y, Z three directions;

a kurtosis indicator of acceleration in three directions X, Y, Z;

yaw rate of acceleration in three directions X, Y, Z.

The specific calculation formula is shown in the following table, wherein x in the table represents the vibration acceleration,

means representing acceleration, x_iRepresenting the ith vibration acceleration, and N representing the number of vibration accelerations acquired during an acquisition cycle, where an acquisition cycle may be a period of time in a state, such as a period of time in a normal state, a period of time in a sub-healthy state, or a period of time in a fault state.

The characteristic value of the vibration acceleration can reflect the vibration condition of the elevator door system.

For example, the peak may detect shock vibration.

The mean value reflects the trend of the variation of the vibration acceleration.

The root mean square value is used for reflecting the numerical value of the vibration acceleration.

The skewness is used for reflecting the asymmetric condition of the vibration acceleration on the ordinate Y.

The kurtosis is that the amplitude of the vibration acceleration is performed to the fourth power in one period, and the higher amplitude in the period is highlighted.

The peak index is the peak value divided by the root mean square value, and reflects the discrete condition of the vibration acceleration in one period.

The pulse index is the peak value divided by the absolute average value, and can reflect the impact vibration.

The kurtosis index represents the height of the actual kurtosis relative to the normal kurtosis, and can reflect the impact characteristics of vibration.

The margin index is the maximum value of the vibration acceleration divided by the square root amplitude, and can reflect the vibration condition of the mechanical equipment under the abrasion condition.

The skewness index is the cube of skewness divided by the root mean square value, and can reflect the asymmetric symmetry of the vibration acceleration.

The waveform index is the root mean square value divided by the absolute average value, and reflects the waveform change in the vibration acceleration period.

The variance reflects the degree of deviation between the vibration acceleration and its mean.

The maximum value is the maximum value of the vibration acceleration.

The minimum value is the minimum value of the vibration acceleration.

The absolute average is an average of the vibration acceleration in terms of value.

The peak value is the value difference between the maximum value and the minimum value of the vibration acceleration.

The method for acquiring the plurality of operation characteristic values corresponding to the operation data of the elevator door system during operation comprises the steps of acquiring the operation data of the elevator door system during operation and then calculating the plurality of operation characteristic values according to the operation data.

As one example, the operational data of the elevator door system during operation includes Q-axis current, motor voltage, D-axis current, a plurality of operational speeds of the elevator door during operation, a plurality of positions of the car during operation of the elevator door, two-phase current corresponding to the D-axis, two-phase current corresponding to the Q-axis, motor voltage, and elevator loop resistance.

The Q axis and the D axis are two coordinate axes used for describing the frequency conversion of the three-phase asynchronous motor in the elevator door system, and the Q axis current, the D axis current, the two-phase current corresponding to the D axis and the two-phase current corresponding to the Q axis can reflect the frequency conversion condition of the three-phase asynchronous motor.

Specific operating characteristic values include, but are not limited to, some or all of the following:

and calculating the accumulated electric energy of the Q-axis current according to the Q-axis current and the motor voltage in the acquisition period.

And calculating the accumulated electric energy of the D-axis current according to the D-axis current and the motor voltage in the acquisition period.

And calculating the sum of the speed errors, the square of the speed error, the numerical value of the speed error, the positive maximum value of the speed error and the negative maximum value of the speed error according to a plurality of running speeds of the elevator door in the running process in the acquisition period.

And calculating errors between the running speeds and the standard speed respectively according to the running speeds of the elevator door in the running process in the acquisition period, and extracting the position of the cage corresponding to the maximum positive error of the running speed from the positions of the cage in the running process of the elevator door.

And calculating errors between the running speeds and the standard speed respectively according to the running speeds of the elevator door in the running process in the acquisition period, and extracting the position of the cage corresponding to the maximum negative error of the running speed from the positions of the cage in the running process of the elevator door.

The initial position of the elevator car when the elevator door system is in the current state is extracted from a plurality of positions of the elevator car in the running process of the elevator door.

The end position of the car when the elevator door system changes the current state is extracted from a plurality of positions of the car during the operation of the elevator door.

And calculating the sum of positive values of the two-phase current corresponding to the collected D axis.

And calculating the sum of the negative values of the two-phase current corresponding to the acquired D axis.

And calculating the sum of positive values of the two-phase current corresponding to the collected Q axis.

And calculating the sum of the negative values of the two-phase current corresponding to the acquired Q axis.

And calculating the heat energy consumed by the motor according to the motor voltage and the elevator loop resistance in the acquisition period, and calculating the difference value between the electric energy and the heat energy consumed by the motor in the acquisition period as the mechanical energy of the motor.

S101: at least one principal component characteristic value representing the state of the elevator door system is determined based on the plurality of vibration characteristic values and the plurality of operation characteristic values.

Although the extracted vibration characteristic values and the operation characteristic values can reflect the operation characteristics of the elevator door system, some characteristic values in the extracted vibration characteristic values and the operation characteristic values have correlation, and the reflected states of the elevator door system are similar, for example: wherein, receive the impact when the bearing in the elevator door system breaks down for the kurtosis obviously changes, and the kurtosis index reflects the impact characteristic in the vibration signal simultaneously, so there is the correlation between kurtosis and the kurtosis index. The waveform indicator is an absolute average of the root mean square value, so that the root mean square value and the waveform indicator have correlation.

Therefore, in order to reduce the input value into the health parameter value characteristic value, the vibration characteristic value and/or the operating characteristic value with correlation are processed. The invention proposes to calculate a principal component characteristic value from at least one vibration characteristic value and/or at least one operating characteristic value. Specifically, the method comprises the following steps: obtaining a plurality of principal component characteristic values by adopting a principal component analysis method for the plurality of acceleration characteristic values and the plurality of operation characteristic values;

The method for analyzing the main components comprises the following steps: and calculating covariance between at least one acceleration characteristic value and/or at least one operation characteristic value, judging correlation between the plurality of acceleration characteristic values and the plurality of operation characteristic values, and combining characteristic values with the correlation in the acceleration characteristic values and/or the operation characteristic values to obtain principal component characteristic values. Wherein, a plurality of principal component characteristic values are not correlated.

The mode of determining the cumulative contribution rate corresponding to each principal component characteristic value is as follows: principal component analysis method uses p original variables (i.e. a plurality of acceleration characteristic values and a plurality of operation characteristic values) X₁、X₂、，…，X_nIs decomposed into p mutually independent principal component characteristic values Y₁、Y₂、，…，Y_pThe variance after decomposition is r_kCan pass through

Is the k-th principal component eigenvalue Y_kThe contribution rate of (c). Wherein the first principal component characteristic value Y₁Has the largest contribution rate of Y₂、，…，Y_pThe contribution rates of (a) and (b) are successively decreased. If only m principal component eigenvalues are taken, then it will be

Is a principal component eigenvalue Y₁、Y₂、，…，Y_mThe cumulative contribution rate of.

S102: and inputting at least one principal component characteristic value into the health assessment model to obtain a health condition parameter value.

Specifically, a gaussian mixture model may be used to establish the health assessment model, where the gaussian mixture model is:

in the above formula, μ and σ are mean and covariance, respectively.

The health assessment model was:

wherein x' is at least one principal component characteristic value to be input, x is at least one principal component characteristic value in normal state of the elevator door system, and g₂(x ') represents a numerical value obtained by inputting x' to the formula g (x). g₁(x) The main component characteristic value x of the normal state of the elevator door system is input into a numerical value obtained by a formula g (x), namely the numerical value when the state of the elevator door system is the normal state.

When the model is trained, a plurality of vibration characteristic values corresponding to the vibration historical data of the elevator door system in operation and a plurality of operation characteristic values corresponding to the operation historical data are obtained, principal component characteristics are obtained according to the plurality of vibration characteristic values and the plurality of operation characteristic values, and the principal component characteristics are calibrated. For example: and when the at least one principal component characteristic value is extracted when the state of the elevator door system is a normal state, calibrating the principal component characteristic value to be a normal state. And when the at least one principal component characteristic value is extracted when the state of the elevator door system is in a sub-health state, calibrating the principal component characteristic value to be in the sub-health state. And when the at least one principal component characteristic value is extracted when the state of the elevator door system is a fault state, calibrating the principal component characteristic value as the fault state.

Firstly, training g (x) by using at least one principal component characteristic value calibrated to be in a normal state, training values of mu and sigma, and obtaining a value g in the normal state₁(x) In that respect Then, the principal component characteristic value and the corresponding calibration in the normal state, the principal component characteristic value and the corresponding calibration in the sub-health state, the principal component characteristic value and the corresponding calibration in the fault state are adopted to form a training set, and the value g in the normal state is used₁(x) Adding the training set to the health assessment model, and training the health assessment model by using the training set, wherein the training set is input g₂(x'), training a health assessment model.

Thus, the acquired at least one principal component characteristic value of the elevator door system can be input into the health assessment model to obtain a value of the health condition parameter CV representing the operating state of the elevator door system.

S103: determining a state of the elevator door system based on the health parameter value.

In the operation process of the elevator door system, since the elevator door system is gradually damaged, that is, the performance degradation of the system is gradually performed, and when the elevator door system is damaged to a certain extent, the failure of the elevator door is determined, the state in which the performance degradation is performed is defined as a sub-health state, which is a state of the elevator door system that does not need to be repaired immediately, for example: slight friction of the guide rail, abrasion of the door slider, abrasion of the hanging wheel and increase of vibration of the door leaf. The invention makes the state of the elevator door system damaged to a certain degree be a failure state, and the failure state is the state of the elevator door system needing immediate repair. The fault state is, for example: not hanging heavy bob, foreign body stop gate, man-made stop gate, wind pressure trouble.

As an example, determining the state of an elevator door system based on a health parameter value is performed as follows: if the health condition parameter value is larger than a preset early warning threshold value, determining that the state of the elevator door system is a normal state; the normal state is a state of an elevator door system that does not require repair. The preset early warning threshold value is a threshold value of the elevator door system from a normal state to a sub-health state.

If the health condition parameter value is not greater than a preset alarm threshold value, determining that the state of the elevator door system is a fault state; the fault state is the state of an elevator door system which needs to be repaired immediately; the preset alarm threshold value is a threshold value of the elevator door system from a sub-health state to a failure state.

If the health condition parameter value is not larger than a preset early warning threshold value and is larger than a preset alarm threshold value, determining that the state of the elevator door system is in a sub-health state; a sub-health state is a state of an elevator door system that does not require immediate repair;

Wherein the health condition reference CV value ranges from 0 to 1. The higher the health reference CV value, the higher the degree of coincidence of the two states. Conversely, if the health reference CV value is lower than the warning value, this means that some degradation is likely to occur, and the lower the value, the more degradation, and appropriate maintenance measures need to be implemented.

In the embodiment of the invention, a plurality of principal component characteristic values of the elevator door system in a normal state, a plurality of principal component characteristic values of the elevator door system in a sub-health state and a plurality of principal component characteristic values of the elevator door system in a fault state are obtained through historical data, and the principal component characteristic values are obtained in the same way as the way of the steps S100 and S101. Inputting each principal component characteristic value in the sub-health state into a health assessment model to obtain a plurality of health condition parameter values CV in the sub-health state₂Will fail stateInputting each principal component characteristic value into a health assessment model to obtain health condition parameter values CV under a plurality of fault states₃。

From values of health parameters CV in a plurality of sub-health states₂In the sub-health state, the maximum health condition parameter value max (CV) is extracted₂) As a predetermined warning threshold value CV_T1。

From the health parameter values CV in a plurality of fault states₃In the fault state, the maximum health condition parameter value max (CV) is extracted₃) As a predetermined alarm threshold value CV_T2。

Wherein, each principal component characteristic value under normal state can be input into the health assessment model to obtain multiple health condition parameter values CV under normal state₁。

From a plurality of normal state health parameter values CV₁In the normal state, the average value CV of the parameter values of the health condition is calculated₁. If max (CV)₂) Less than average value (CV)₁) When the value is less than the maximum health condition parameter max (CV) in the sub-health state₂) As a predetermined warning threshold value CV_T1。

Wherein the health status parameter value CV calculated at the current moment>CV_T1When the elevator door system is in a normal state, the state of the elevator door system is in a normal state; when CV is_T2≤CV<CV_T1When the elevator door system is in a sub-health state, the elevator door system carries out early warning on the sub-health state; when CV is less than or equal to CV_T2When the elevator door system is in a fault state, the elevator door system gives an alarm of the fault state.

Since the performance of the elevator door system is gradually degraded, the invention can obtain the time left by changing the normal state into the sub-health state when the state of the elevator door system is the normal state, so that a maintenance plan is not required to be arranged in the time, or the time left by changing the normal state into the fault state of the elevator door system is considered, or the time left by changing the sub-health state into the fault state when the state of the elevator door system is the sub-health state is considered, so that the maintenance is early warned, and a maintenance strategy is arranged, thereby improving the maintenance efficiency. Specifically, the method comprises the following steps:

if the state of the elevator door system is a normal state, inputting a preset early warning threshold value, a preset alarm threshold value and a health condition parameter value into a prediction time model, and determining a first prediction time length for the state of the elevator door system to decline from the normal state to a sub-health state and a second prediction time length for the state of the elevator door system to decline from the normal state to a fault state; the first prediction time period is the time left for the state of the elevator door system to decline from the normal state to the sub-healthy state, and the second prediction time period is the time left for the state of the elevator door system to decline from the normal state to the fault state. Or the like, or, alternatively,

and if the state of the elevator door system is in the sub-health state, inputting a preset alarm threshold value and a health condition parameter value into the prediction time model, and determining a third prediction duration for the state of the elevator door system to decline from the sub-health state to the fault state. The third predicted time period is the time remaining for the state of the elevator door system to decay from the sub-healthy state to the failed state.

Wherein, the prediction time model can be established by using a prophet model. The prophet model may be:

y(t)＝p(t)+L(t)β+ε

where p (t) is a trend term fitting the non-periodic variation of piecewise linear or logistic growth in the time series, β is a parameter, ε is an error term that follows a normal distribution, and L (t) is the health parameter CV value at time t. The formula of the trend term p (t) is:

where C refers to the carrying capacity, k is the growth rate, and m is the offset.

According to the prophet model and the trend term p (t), a prediction time model can be obtained as follows:

Δt＝t-t₀

wherein, t₀At the current time, t is the time of the change of state of the elevator door system. When the actual process is carried out, the prediction time model can obtain the current time t₀. Or the current time t may be entered₀Into a predictive temporal model.

When the state of the elevator door system is normal, a preset early warning threshold value CV is set_T1Current health condition parameter CV in the normal state_{Is just}Inputting the values into the prediction time model to obtain:

Δt₁＝t₁-t₀

t₁the time when the state of the elevator door system changes from a normal state to a sub-healthy state.

By predicting the time model, t can be calculated₁Then, a first prediction time length delta t for the state of the elevator door system to decline from the normal state to the sub-health state is calculated₁。

When the state of the elevator door system is normal, a preset alarm threshold value CV is set_T2Current health condition parameter CV in the normal state_{Is just}Inputting the values into the prediction time model to obtain:

Δt₂＝t₂-t₀

t₂the moment when the state of the elevator door system decays from a normal state to a fault state.

By predicting the time model, t can be calculated₂Then, a second predicted time length delta t for the state of the elevator door system to decline from the normal state to the fault state is calculated₂。

When the elevator door is tiedWhen the system state is a sub-health state, a preset alarm threshold value CV is set_T2Current health condition parameter CV in sub-health state_AInputting the values into the prediction time model to obtain:

Δt₃＝t₃-t₀

t₃the failure time when the state of the elevator door system is degraded from a sub-health state to a fault state.

By predicting the time model, t can be calculated₃And then calculating a third predicted time period delta t for the state of the elevator door system to decline from the sub-health state to the fault state₃。

When the model is trained, a training set is obtained, and each unit in the training set comprises the health condition parameter value at the current time, the current time and the calibrated remaining time of the state change corresponding to the current time. Taking a unit as an example, specifically, the health condition parameter value at the current time and the threshold value corresponding to the state change of the elevator door system at the current time are obtained from the historical data, and the time of the state change corresponding to the health condition parameter value at the current time is obtained, for example, if the state of the elevator door system corresponding to the health condition parameter value at the current time is a normal state, the remaining time from the normal state to a sub-health state is obtained as a calibration value, and the threshold value corresponding to the state change of the elevator door system at the current time is a preset early warning threshold value. And training and predicting beta, epsilon, C, k and m in the time model by adopting the training set.

Thus, the first predicted time length delta t of the elevator door system can be real-time₁A second predicted time length delta t₂Third predicted time length delta t₃And (6) performing prediction. When the state of the elevator door system is normal, inputting a preset early warning threshold value, a preset alarm threshold value and a health condition parameter value into a prediction time model, and determining a first prediction time delta t of the elevator door system₁Second predicted durationΔt₂The first prediction time length Δ t₁A second predicted time length delta t₂Sent to maintenance personnel who can predict the time length delta t₁A second predicted time length delta t₂The elevator door system is not maintained in the elevator, and other matters are reasonably arranged. At the first predicted time period of reaching Δ t₁A second predicted time length delta t₂Thereafter, the maintenance personnel may base the first predicted time period Δ t on₁Detecting the health state of the elevator door system to obtain a health state parameter value, judging whether the moment is in a sub-health state, and allowing maintenance personnel to predict the time length delta t according to the second prediction time length₂And detecting the health state of the elevator door system to obtain a health state parameter value, and judging whether the elevator door system is in a fault state at the moment.

If the state of the elevator door system is in a sub-health state, inputting a preset alarm threshold value and a health condition parameter value into a prediction time model, and determining a third prediction time duration delta t of the elevator door system₃The third predicted time period Δ t₃Sent to maintenance personnel who can be at the third predicted time period deltat₃The elevator door system is maintained, and elevator fault items are reasonably arranged. At the third predicted time period of reaching Δ t₃And then, the maintenance personnel can detect the health state of the elevator door system to obtain the health state parameter value, judge whether the elevator door system is in the fault state at the moment, and if so, maintain the elevator door system.

Since the above-mentioned sub-health status types include a plurality of types, the fault status types include a plurality of types, and the maintenance means of each type are different, in order to improve the maintenance efficiency, the present invention proposes a method for determining the sub-health status type or the fault status type by at least one principal component feature value, and the specific implementation method may be:

if the state of the elevator door system is in a sub-health state, inputting at least one principal component characteristic value into a type diagnosis model, and determining the type of the sub-health state of the elevator door system; or

And if the state of the elevator door system is a fault state, inputting at least one principal component characteristic value into a type diagnosis model, and determining the type of the fault state of the elevator door system.

In an embodiment of the invention, a type diagnostic model of an elevator door system may be constructed using a gradient lifting tree algorithm (GBDT):

in the formula, β represents a weight of each base learner model; alpha represents the parameter of each base learner model, N represents the number of base learners, and the model parameter

Can be expressed by the following formula:

wherein L (y)_iAnd f (z)) is a loss function, and M represents the number of elements in the training set.

In the training process, a training set Z may be obtained first, where Z { (Z)₁,y₁)，(z₂,y₂)，(z₃,y₃)，…，(z_n,y_n) Z in the training set represents at least one principal component characteristic value corresponding to the type of the state, and y is a label of the type of the state. The training set Z specifically includes at least one principal component feature value corresponding to each type of fault state, and a label of the type of fault state. At least one principal component characteristic value corresponding to each type of sub-health state, and a label of the type of sub-health state. And inputting the elements in the training set Z into F (Z) to obtain a result, inputting the label and the result in the training set Z into a loss function, and adjusting beta and alpha through the loss function to train.

When the health state parameter CV value satisfies: CV of_T2≤CV<CV_T1When the type diagnosis model is started, the type diagnosis model can judge the sub-state of the elevator door systemThe type of the health state gives an early warning to maintenance personnel, the type of the sub-health state is sent to the maintenance personnel, and the maintenance personnel can carry out adaptive maintenance on the elevator door system according to the type of the sub-health state and reasonably arrange elevator fault items.

When the health state parameter CV value satisfies: CV is less than or equal to CV_T2And when the elevator door system is in the fault state, the type diagnosis model is started, the type diagnosis model can judge the type of the current fault state of the elevator door system, an alarm is given to maintenance personnel, the type of the fault state is sent to the maintenance personnel, and the maintenance personnel can carry out adaptive emergency repair on the elevator door system according to the type of the fault state. Based on the judgment information, maintenance personnel can be better guided to carry out maintenance work on the elevator door.

The whole process of the present invention is described below by a specific embodiment:

referring to fig. 2, an embodiment of the present invention provides a method for diagnosing an elevator door system, including:

step S200: acquiring a plurality of vibration characteristic values corresponding to vibration data of an elevator door system during operation and a plurality of operation characteristic values corresponding to operation data;

step S201: determining at least one principal component characteristic value representing a state of the elevator door system based on the plurality of vibration characteristic values and the plurality of operation characteristic values;

step S202: inputting at least one principal component characteristic value into a health assessment model to obtain a health condition parameter value;

step S203: if the health condition parameter value is larger than a preset early warning threshold value, determining that the state of the elevator door system is a normal state, inputting the preset early warning threshold value, the preset alarm threshold value and the health condition parameter value into a prediction time model, and determining a first prediction time length for the state of the elevator door system to decline from the normal state to a sub-health state and a second prediction time length for the state of the elevator door system to decline from the normal state to a fault state;

step S204: and if the health condition parameter value is not larger than the preset alarm threshold value, determining that the state of the elevator door system is a fault state, inputting at least one principal component characteristic value into a type diagnosis model, and determining the type of the fault state of the elevator door system.

Step S205: if the health condition parameter value is not larger than the preset early warning threshold value and is larger than the preset alarm threshold value, the state of the elevator door system is determined to be in a sub-health state, the preset alarm threshold value and the health condition parameter value are input into the prediction time model, the third prediction duration of the state of the elevator door system declining from the sub-health state to the fault state is determined, at least one principal component characteristic value is input into the type diagnosis model, and the type of the sub-health state of the elevator door system is determined.

Since the elevator door system is managed by managing a plurality of elevator doors, maintenance time of the elevator door system needs to be planned in advance, so that collision of maintenance time can be avoided. Based on this, the embodiment of the present invention further provides a method for predicting a decay time of an elevator door system, which is shown in fig. 3, and the method includes:

s300: and determining the health condition parameter value of the elevator door system according to the vibration data and the operation data of the elevator door system during operation.

The method for determining the health condition parameter value may be the method for determining the health condition parameter value described in the above elevator door system diagnosis method, and will not be described in detail herein.

S301: and inputting the health condition parameters and a preset state threshold value of state decline of the elevator door system into the prediction time model, and determining the prediction time length of the state of the elevator door system from the current state to other states.

The method for predicting the decline time of the elevator door system provided by the embodiment of the invention can determine the forecast time of the state of the elevator door system declining from the current state to other states by combining the health assessment model and the forecast time model, so that a user can arrange work in advance according to the forecast time, maintain the elevator door system in a timing manner, and improve the maintenance efficiency of the elevator door system.

If the current state is a normal state, the other states comprise a sub-health state and a fault state, and the prediction duration comprises a first prediction duration declining from the normal state to the sub-health state and a second prediction duration declining from the normal state to the fault state; the state threshold comprises a preset early warning threshold and a preset alarm threshold;

if the current state is a sub-health state, other states comprise fault states, and the prediction duration comprises a third prediction duration which is reduced from the normal state to the fault state; the state threshold comprises a preset alarm threshold.

It should be noted that, the prediction time model in the method for predicting the decay time of the elevator door system according to the embodiment of the present invention may adopt the prediction time model introduced in the method for diagnosing the elevator door system.

When the current state of the elevator door system is a normal state, inputting a preset early warning threshold value, a preset alarm threshold value and a health condition parameter value into a prediction time model to obtain a first prediction time length for the state of the elevator door system to decline from the normal state to a sub-health state and a second prediction time length for the state of the elevator door system to decline from the normal state to a fault state; and when the current state of the elevator door system is in a sub-health state, inputting a preset alarm threshold value and a health condition parameter value into the prediction time model, and determining a third prediction duration of the state of the elevator door system from the sub-health state to a fault state. The determination manners of the first predicted time length, the second predicted time length and the third predicted time length can also refer to the determination manners of the first predicted time length, the second predicted time length and the third predicted time length introduced in the elevator door system diagnosis method, and are not described in detail herein.

The elevator door system diagnosis method and the elevator door system decay time prediction method introduced above can be executed by one elevator door diagnosis prediction system. The embodiment of the invention provides a diagnosis and prediction system for an elevator door. As described in connection with fig. 4, the elevator door diagnostic prediction system 400 includes: the system comprises a feature extraction module 401, a health state evaluation module 402 and a health state evaluation module 402, wherein the feature extraction module 401 is connected with the health state evaluation module 402, and a fault prediction module 403 is connected with the health state evaluation module 402.

The characteristic extraction module 401 is configured to obtain a plurality of vibration characteristic values corresponding to vibration data of the elevator door system during operation and a plurality of operation characteristic values corresponding to operation data, and determine at least one principal component characteristic value representing a state of the elevator door system according to the plurality of vibration characteristic values and the plurality of operation characteristic values;

a health status evaluation module 402, configured to input the at least one principal component feature value into a health evaluation model, so as to obtain a health status parameter value; determining a state of the elevator door system based on the health parameter value;

and a fault prediction module 403, configured to input the health condition parameter and a preset state threshold value of state decline of the elevator door system into a prediction time model, and determine a prediction duration of state decline of the elevator door system from a current state to another state.

Optionally, the feature extraction module 401 is specifically configured to:

Optionally, the health status evaluation module 402 is specifically configured to:

Optionally, if the current state is a normal state, the other states include a sub-health state and a fault state, the prediction duration includes a first prediction duration declining from the normal state to the sub-health state, and a second prediction duration declining from the normal state to the fault state, and the state threshold includes a preset early warning threshold and a preset alarm threshold;

Optionally, as shown in fig. 5, the elevator door diagnosis and prediction system 400 further includes, in addition to the above-mentioned feature extraction module 401, the health status evaluation module 402, and the failure prediction module 403: the fault diagnosis module 404 and the fault diagnosis module 404 are connected with the health status evaluation module 402 and the feature extraction module 401.

A fault diagnosis module 404, configured to, if the state of the elevator door system is a sub-health state, input the at least one principal component feature value into a type diagnosis model, and determine a type of the sub-health state of the elevator door system; or if the state of the elevator door system is a fault state, inputting the at least one principal component characteristic value into a type diagnosis model, and determining the type of the fault state of the elevator door system.

As shown in fig. 6, an embodiment of the present invention further provides an electronic device 600, which includes: a processor 610 and a memory 620 for storing processor-executable instructions.

Wherein the processor is configured to execute the instructions to implement the elevator door system diagnostic method of any of the above embodiments or the method of predicting a degradation of an elevator door system state of any of the above embodiments.

In an exemplary embodiment, a storage medium comprising instructions, such as the memory 620 comprising instructions, executable by the processor 610 of the electronic device 600 to perform the above-described method is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an embodiment of the present invention, when the electronic device may include other structures besides the memory and the processor, specifically as shown in fig. 7, an embodiment of the present invention provides an electronic device 700, including: a power supply 710, a processor 720, a memory 730, an input unit 740, a display unit 750, a communication interface 760, and a Wireless Fidelity (Wi-Fi) module 770. Those skilled in the art will appreciate that the configuration of the electronic device shown in fig. 7 does not constitute a limitation of the electronic device, and the electronic device provided by the embodiments of the present application may include more or less components than those shown, or may combine some components, or may be arranged in different components.

The following describes each component of the electronic device 700 in detail with reference to fig. 7:

the Wi-Fi technology belongs to a short-distance wireless transmission technology, and the electronic device 700 may connect to an Access Point (AP) through a Wi-Fi module 770, thereby implementing Access to a data network. The Wi-Fi module 770 can be used for receiving and transmitting data in the communication process.

The electronic device 700 may be physically connected to other electronic devices via the communication interface 760. Optionally, the communication interface 760 is connected to the communication interfaces of the other electronic devices through a cable, so as to implement data transmission between the electronic device 700 and the other electronic devices.

The electronic device 700 may be connected to the user terminal through the communication interface 760 or the Wi-Fi module 770, and transmit a first time period to the user terminal when the state of the elevator door system is a normal state; when the state of the elevator door system is in a sub-health state, the second duration and/or the type of the sub-health state are/is sent to the user terminal; when the state of the elevator door system is a fault state, the type of the fault state is sent to a user terminal.

In the embodiment of the present application, the electronic device 700 is capable of implementing a communication service and sending information to other contacts, so that the electronic device 700 needs to have a data transmission function, that is, the electronic device 700 needs to include a communication module inside. Although fig. 7 shows communication modules such as the Wi-Fi module 790 and the communication interface 780, it is understood that at least one of the above components or other communication modules (e.g., bluetooth module) for implementing communication exists in the electronic device 700 for data transmission.

The memory 730 may be used to store software programs and modules. The processor 720 executes various functional applications and data processing of the electronic device 700 by executing the software programs and modules stored in the memory 730, and after the processor 720 executes the program codes in the memory 730, part or all of the processes in fig. 1 or part or all of the processes in fig. 3 according to the embodiment of the present invention can be implemented.

Alternatively, the memory 730 may mainly include a program storage area and a data storage area. The storage program area can store an operating system, various application programs (such as communication application), a face recognition module and the like; the storage data area may store data (such as various multimedia files like pictures, video files, etc., and face information templates) created according to the use of the electronic device, and the like.

Further, the memory 730 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 740 may be used to receive numerical or character information input by a user and generate key signal inputs related to user settings and function control of the electronic device 700, for example, input an activation instruction, thereby causing the processor to perform the above-described elevator door system diagnosis method.

Optionally, the input unit 740 may include a touch panel 741 and other input electronic devices 742.

The touch panel 741, also referred to as a touch screen, may collect touch operations performed by a user on or near the touch panel 741 (for example, operations performed by the user on or near the touch panel 741 using any suitable object or accessory such as a finger or a stylus), and drive a corresponding connection device according to a preset program. Alternatively, the touch panel 741 may include two parts, namely, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 720, and can receive and execute commands sent by the processor 720. In addition, the touch panel 741 can be implemented by using various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave.

Optionally, the input electronics 742 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 750 may be used to display information input by or provided to the user and various menus of the electronic device 700, for example, a first time period, a second time period, a type of sub-health state, a type of fault state. The display unit 750 is a display system of the electronic device 700, and is used for presenting an interface to implement human-computer interaction.

The display unit 750 may include a display panel 751. Alternatively, the Display panel 751 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

Further, the touch panel 741 may cover the display panel 751, and when the touch panel 741 detects a touch operation on or near the touch panel 741, the touch panel transmits the touch operation to the processor 720 to determine a type of the touch event, and then the processor 720 provides a corresponding visual output on the display panel 751 according to the type of the touch event.

Although in fig. 7, the touch panel 741 and the display panel 751 are two separate components to implement input and output functions of the electronic device 700, in some embodiments, the touch panel 741 and the display panel 751 can be integrated to implement input and output functions of the electronic device 700.

The processor 720 is a control center of the electronic device 700, connects various components using various interfaces and lines, and implements various functions and processes data of the electronic device 700 by running or executing software programs and/or modules stored in the memory 730 and calling data stored in the memory 730, thereby implementing various services based on the electronic device.

Optionally, the processor 720 may include one or more processing units. Optionally, the processor 720 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 720.

The electronic device 700 also includes a power source 710 (such as a battery) for powering the various components. Optionally, the power supply 710 may be logically connected to the processor 720 through a power management system, so as to implement functions of managing charging, discharging, power consumption, and the like through the power management system.

It is to be noted that, according to the embodiment of the present invention, the processor 720 may execute the processor 610 in fig. 6, and the memory 730 stores contents of the processor 610.

The embodiment of the invention also provides a computer program product, and when the computer program product runs on electronic equipment, the electronic equipment executes the method for implementing any one of the elevator door system diagnosis method and the elevator door system decay time prediction method.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims

1. An elevator door system diagnostic method, comprising:

determining a state of the elevator door system based on the health parameter value;

determining a state of the elevator door system based on the health parameter value, comprising:

if the health condition parameter value is not greater than a preset early warning threshold value and is greater than a preset alarm threshold value, determining that the state of the elevator door system is in a sub-health state;

wherein the preset alarm threshold is smaller than the preset early warning threshold;

after determining the state of the elevator door system according to the health parameter value, the method further comprises:

2. The elevator door system diagnostic of claim 1, wherein after determining the state of the elevator door system based on the health parameter value, further comprising:

3. The elevator door system diagnostic method of claim 1, wherein determining at least one principal component characteristic value representing a state of the elevator door system based on the plurality of acceleration characteristic values and the plurality of operational characteristic values comprises:

4. A method for predicting the decay time of an elevator door system is characterized by comprising the following steps:

inputting the health condition parameters and a preset state threshold value of state decline of the elevator door system into a prediction time model, and determining the prediction duration of the state decline of the elevator door system from the current state to other states;

if the current state is a normal state, the other states comprise a sub-health state and a fault state, and the prediction duration comprises a first prediction duration declining from the normal state to the sub-health state and a second prediction duration declining from the normal state to the fault state;

if the current state is a sub-health state, the other states comprise fault states, and the predicted time length comprises a third predicted time length from the normal state to the fault state;

if the current state is a normal state, the state threshold value comprises a preset early warning threshold value and a preset alarm threshold value;

5. The method of predicting elevator door system degradation time of claim 4, wherein determining the health parameter value of the elevator door system based on the vibration data and the operational data of the elevator door system during operation comprises:

6. An elevator door diagnostic prediction system, comprising:

the fault prediction module is used for inputting the health condition parameters and a preset state threshold value of state decline of the elevator door system into a prediction time model and determining the prediction duration of the state decline of the elevator door system from the current state to other states;

if the current state is a normal state, other states comprise a sub-health state and a fault state, the prediction time length comprises a first prediction time length declining from the normal state to the sub-health state and a second prediction time length declining from the normal state to the fault state, and the state threshold comprises a preset early warning threshold and a preset alarm threshold;

7. The elevator door diagnostic prediction system of claim 6, wherein the feature extraction module is specifically configured to:

8. The elevator door diagnostic prediction system of claim 6, wherein the health status assessment module is specifically configured to:

9. The elevator door diagnostic prediction system of claim 6, wherein the system further comprises:

10. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the elevator door system diagnostic method of any one of claims 1 to 3 or the elevator door system decay time prediction method of any one of claims 4 to 5.

11. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the elevator door system diagnostic method of any one of claims 1 to 3 or perform the method of predicting elevator door system degradation time of any one of claims 4 to 5.