Intelligent fire-fighting elevator data acquisition method and system based on intermittent grading

Abstract

The application belongs to the technical field of data acquisition, and proposes an intelligent fire elevator data acquisition method and system based on intermittent grading, specifically: first, the intelligent fire elevator data acquisition component contains a vibration acquisition module, the acceleration is obtained through the vibration acquisition module, a preset basic intermittent section is obtained, and the intermittent series is established according to the basic intermittent section, then the loss reference state is obtained by decoupling analysis according to the acceleration and the intermittent series, then the performance loss early warning factor of the loss reference state is determined, and finally the data of the fire elevator is collected combined with the performance loss early warning factor. The calculation based on the loss reference state can effectively identify the influence of wind vibration or other vibrations existing in the building on the motor in the intelligent fire elevator, and timely estimate the occurrence degree effect of potential performance loss risk, reduce the storage of unnecessary or redundant data, and further reduce the negative effect of redundant data and invalid data on the constructed prediction model.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of data collection, and particularly relates to an intelligent fire elevator data collection method and system based on intermittent grading. BACKGROUND

[0002] Fire elevators are elevator systems designed for emergency situations such as fires, which can ensure the safe evacuation of people in buildings in emergency situations. Fire elevators not only have the functions of conventional elevators, but also have the escort function of fire safety, that is, the working ability to deal with fire, toxic gas or earthquake and other fire scenes.

[0003] Among them, in the application process of daily elevators, the operation of the elevator often faces a large wind vibration or vibration phenomenon, especially in high-rise buildings, the frequency and intensity of the vibration phenomenon are more obvious. Although the design of the fire elevator can usually ensure that it can maintain a certain functionality under the influence of long-term wind vibration and vibration, if the influence is too frequent and strong, it may cause wear and tear of some systems of the elevator, including the motor, the braking system, the control panel, etc. The cumulative effect of these wear and tear over a long period of time can cause equipment aging, increase maintenance costs, and reduce the response speed and stability of the elevator, which can easily lead to a reduction in the fire performance of the fire elevator in a fire scene, including structural material fire resistance, electrical circuit damage, and device aging and loose connections. Therefore, it is urgent to collect data on the vibration damage of the daily operation of the fire elevator to build a prediction model to resist the performance reduction caused by the vibration of the fire elevator. The prediction model limits the operating intensity of the fire elevator, including shutdown, limiting the operating floor, limiting the running speed, etc. However, due to the large number of sensors provided by the fire elevator itself, and the uniqueness of the fire elevators in different buildings, traditional data collection cannot accurately locate the time point of the occurrence of effective data, which can easily lead to data redundancy, and the prediction model built by the traditional data collection has sensitivity defects. The effective data is actually the probability time point of the occurrence of fire performance damage, but if only the data of the time point of the occurrence of vibration is collected, the time sequence characteristics of the vibration may be ignored. Due to the power of the elevator motor, an intelligent fire elevator data collection method based on intermittent grading is urgently needed. SUMMARY

[0004] The present application aims to provide an intelligent fire elevator data collection method and system based on intermittent grading to solve one or more technical problems in the prior art, and at least provide a beneficial choice or create conditions.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an intelligent fire elevator data collection method based on intermittent grading is provided, the method comprising the following steps:

[0006] The intelligent fire-fighting elevator data acquisition assembly comprises a vibration acquisition module, and the acceleration is obtained through the vibration acquisition module; a basic intermittent section is preset, and an intermittent series is established according to the basic intermittent section; the loss reference state is obtained through decoupling analysis according to the acceleration and the intermittent series; the performance loss early warning factor of the loss reference state is determined; and the data of the fire-fighting elevator is acquired in combination with the performance loss early warning factor.

[0007] Further, the intelligent fire-fighting elevator data acquisition assembly comprises a vibration acquisition module, and the acceleration is obtained through the vibration acquisition module; a basic intermittent section is preset, and an intermittent series is established according to the basic intermittent section; the loss reference state is obtained through decoupling analysis according to the acceleration and the intermittent series; the performance loss early warning factor of the loss reference state is determined; and the data of the fire-fighting elevator is acquired in combination with the performance loss early warning factor.

[0008] The vibration acquisition module is arranged in the motor compartment of the elevator, because the motor compartment and the elevator shaft are common positions for the elevator to face the influence of vibration. Since the motor compartment is arranged with the motor, the control device and the speed reducer during the operation of the elevator, the running state of the motor compartment itself will bring certain vibration, so the vibration data of wind vibration or building vibration recognition is more significant and sensitive. The vibration measurement of the elevator shaft has obvious dispersion, and the walls, tracks and other components of the shaft will have a certain buffering or absorption effect on the vibration, so the monitoring of the occurrence of the fire-fighting performance loss must have the problems of hysteresis and adaptability.

[0009] The vibration acquisition module comprises an acceleration sensor, and the acceleration sensor adopts any one of a piezoelectric acceleration sensor, a fiber-optic acceleration sensor or a MEMS acceleration sensor.

[0010] The acceleration is obtained through real-time measurement by the acceleration sensor.

[0011] The vibration acquisition module transmits data through LoRa communication technology, Wi-Fi or 5G network. The vibration acquisition module sends the collected real-time elevator acceleration data to the central server, and the server stores and processes the data in real time. At the same time, the elevator operation mode is adjusted according to the data feedback, including adjusting the elevator speed, limiting the running floor, etc. The acceleration is obtained through real-time measurement by the acceleration sensor and stored in an array in the computer. Each element of the array is the acceleration component in different directions in three-dimensional space.

[0012] Through the network function, the environment acquisition module and the cloud server form a distributed collaborative architecture. Through the enhanced data processing capacity and real-time response capacity, the emergency response efficiency and reliability of the intelligent fire-fighting elevator in different environmental changes are improved. At the same time, the system supports remote control and intelligent optimization function, which is convenient for software updating or iteration to continuously improve the stability and intelligent level of the system.

[0013] Further, the method for presetting a basic intermittent section and establishing an intermittent series according to the basic intermittent section is:

[0014] The basic interval section is set to 1-10 minutes;

[0015] The essence of the basic interval section is the length of the time period, that is, when the basic interval section is set to 5 minutes, the length of each basic interval section is 5 minutes, which is the basic unit of data collection for modeling; at any time, there is only one corresponding basic interval section.

[0016] A preset integer variable is used as the interval number KL, and the value range of the interval number is KL∈[1, 15], for any interval number KL, it represents the time period of the interval section of KL basic interval sections.

[0017] For example, when the representative interval section KL takes the value of 5 and the basic interval section is 3 minutes, the interval number is 5, which corresponds to a representative interval section of 15 minutes.

[0018] By changing the interval section KL, more diverse time period data collection is enhanced to analyze the changing trend of elevator vibration in a more flexible cycle.

[0019] Further, the method for decoupling analysis of acceleration and interval number to obtain the loss reference state is:

[0020] For any time, the basic interval section to which the time belongs is the current basic interval section, and any interval number is selected from the current basic interval section as an operation level to calculate the range of loss indicator data in the representative interval section corresponding to the operation level. The ratio of the obtained range value to the maximum value of the length of each acceleration of the current basic interval section is recorded as the loss reference state of the operation level; wherein the loss indicator data is the power value of the motor of the elevator in the uniform motion state.

[0021] The representative interval section corresponding to the operation level represents a time period of the representative interval section in the reverse time direction from the first time of the current interval section.

[0022] The power consumption of the motor is usually closely related to the vibration, load and running speed of the elevator, and by analyzing the change of the motor power, it can be inferred whether the performance loss occurs during the operation of the elevator.

[0023] Further, the method for determining the performance loss warning factor of the loss reference state is: preset a monitoring time period TCr, TCr∈[2, 6] hours, and each basic interval section is recorded as a reference node in the monitoring time period;

[0024] Obtain the loss reference state of each reference node and form a sequence Wsf.Ls;

[0025] Calculate the mean and standard deviation of the elements in the sequence Wsf.Ls. If the element is less than or equal to the sum of the mean and three times the standard deviation, and greater than or equal to the difference between the mean and three times the standard deviation, then record the corresponding reference node as a low-order loss point; otherwise, record it as a high-order loss point. The mathematical expression for determining whether a reference node is a low-order loss point is: Wsf.Ls.mean-3 Wsf.Ls.err≤Wsf.Ls(k1)≤Wsf.Ls.mean+3 Wsf.Ls.err; where Wsf.Ls.mean represents the mean of the elements in the sequence Wsf.Ls, Wsf.Ls.err represents the standard deviation of the elements in the sequence Wsf.Ls, Wsf.Ls(k1) represents the k1th element in the sequence Wsf.Ls, and k1 is the sequence number of the element in the sequence.

[0026] The time scale of the loss reference effective state obtained from the low-order loss point and its corresponding loss reference effective state constitute a low-loss binary group. The set constructed by the low-loss binary group within the monitoring period is interpolated with cubic splines using the plrep and splev functions to obtain a smooth curve. The corresponding fitting value of the benchmark node on the smooth curve obtained by fitting is used as the curve value of the benchmark node. The plrep and splev functions are called in Python.

[0027] The absolute value of the difference between the curve value of any high-order loss point and its corresponding loss reference state is recorded as the loss difference; the loss difference of each high-order loss point is obtained and a difference evaluation sequence is constructed; the upper quartile Xes.sl, lower quartile Xes.xl and interquartile range Xes.jl in the difference evaluation sequence are obtained respectively, where the interquartile range is the difference between the upper quartile and the lower quartile; the loss stable interval is constructed according to the difference evaluation sequence as (Xes.xl-k2×Xes.jl,Xes.sl+k2×Xes.jl); where k2 is a preset amplitude coefficient, and its value range is k2∈[1,20];

[0028] The amplitude coefficient is used to compensate for the insufficient density of high-order loss points. When the time gaps between high-order loss points are more uniform, a smaller value is selected. Otherwise, a larger value is selected, thereby reducing the risk of collecting unnecessary model data due to excessive sensitivity to a certain extent.

[0029] The principle of obtaining the loss stable interval is actually to define an interval based on the quartile analysis of the loss difference. The loss difference of the high-order loss point can effectively identify and distinguish the stable stage and the abnormal fluctuation stage of the performance loss of the elevator. The upper quartile and the lower quartile represent the high and low loss fluctuation degrees of the intelligent fire elevator system based on intermittent grading under normal operation, and the interquartile range reflects the volatility between the two. Meanwhile, the loss stable interval enhances the sensitivity of the prediction model, can accurately capture the small fluctuations of the elevator loss, and can eliminate redundant risk signals by concentrating on analyzing the loss difference.

[0030] If the current reference node belongs to the marked low-order loss point, the performance loss early warning factor is assigned as FALSE; otherwise, if the current reference node belongs to the loss stable interval, the performance loss early warning factor is assigned as FALSE, otherwise the performance loss early warning factor is assigned as TRUE. The current reference node represents the reference node corresponding to the current time; the performance loss early warning factor assigned as FALSE represents that no risk occurs, and the performance loss early warning factor assigned as TRUE represents that a risk occurs.

[0031] Since the determination of the performance loss early warning factor needs to process the loss difference, it can effectively filter redundant data and quantify the performance loss risk of the intelligent fire elevator system based on intermittent grading. However, the acquisition of the high-order loss point excessively depends on the loss reference state, which leads to strong data sensitivity, thus causing the loss difference to deviate, the assumption of the loss stable interval to be unreasonable, and finally causing decision deviation and unnecessary model data collection. Especially in the period with low density of high-order loss points, this problem is more prominent. However, the prior art cannot effectively compensate for this deviation. In order to eliminate this influence, the present application proposes a more preferred solution as follows:

[0032] Preferably, the method for determining the performance loss early warning factor based on the loss reference state is:

[0033] A preset monitoring period TCr is set, TCr∈[2,10] hours. In the monitoring period, each basic intermittent section is recorded as a reference node. The loss reference state of each reference node in the monitoring period is obtained and a reference loss state sequence is formed.

[0034] The reference nodes corresponding to the maximum elements in the reference loss state sequence are recorded as edge nodes.

[0035] The difference between any edge node and its left and right adjacent reference nodes in the loss reference state is calculated, and the maximum value in the difference is selected as the loss critical value of the edge node.

[0036] The principle of obtaining the loss critical value here is actually obtained by calculating the difference between the edge node and its left and right adjacent reference nodes. The loss critical value directly reflects the performance loss difference between each time point in the elevator, is the embodiment of potential performance loss risk, and quantifies the degree of elevator performance fluctuation. If the loss critical value is large, it means that the power consumption of the elevator has a significant abnormal fluctuation, and the risk probability increases. If the loss critical value is small, it means that the difference between the loss reference states of adjacent reference nodes is small, and the elevator system runs smoothly. It is the performance of the elevator in light load or continuous smooth running, so the acquisition of the loss critical value is an effective evaluation means for elevator fault prediction.

[0037] The number of edge nodes is denoted as sdn; the time interval between any edge node and its previous edge node is denoted as a loss trend value, and the sequence composed of all loss trend values is denoted as Gn.Ls;

[0038] The loss trend values of each edge node are used for DBSCAN density clustering algorithm, and all edge nodes are divided into several clusters, denoted as trend clustering cluster, wherein the neighborhood radius of DBSCAN density clustering algorithm is the upper quartile of Gn.Ls sequence, and the minimum point number is the intermittent level of the current reference node;

[0039] According to the edge node and the loss critical value, the early warning evaluation level Evyp of each trend clustering cluster is obtained:

[0040]

[0041] Where j1 is the serial number of the edge node in the trend clustering cluster, sn is the number of edge nodes in the trend clustering cluster, Lopp j1 is the loss reference state of the j1th edge node in the trend clustering cluster, MLopp is the average value of the loss reference states of all edge nodes, LCocv j1 is the sequence number of the loss critical value of the j1th edge node in the trend clustering cluster when the loss critical values of all edge nodes are arranged in descending order, avg{} is the average value function, and exp() is the exponential function with natural constant e as the base;

[0042] ​The early warning evaluation level of each trend clustering cluster is minimum-maximum normalized and recorded as a loss risk state value. If the loss risk state value of a trend clustering cluster is greater than or equal to 0.5, the trend clustering cluster is marked as a risk type cluster, otherwise it is marked as a non-risk type cluster. The maximum value of the loss critical value in the trend clustering cluster is recorded as the critical peak value of the trend clustering cluster. The Euclidean distance between the current reference node and the critical peak value of any trend clustering cluster is recorded as the current critical distance. The trend clustering cluster with the minimum value of the pre-critical distance is selected as the target cluster. If the target cluster is a risk type cluster, the performance loss early warning factor of the current reference node is assigned as TRUE, otherwise the performance loss early warning factor is assigned as FALSE.

[0043] If the target cluster cannot be found, it is considered that the performance loss early warning factor of each reference node in the monitoring period TCr is FALSE. Therefore, the performance loss early warning factor of the current reference node is assigned as FALSE.

[0044] Beneficial effects: Since the performance loss early warning factor is calculated based on acceleration and intermittent series, real-time analysis of elevator vibration data is performed. Therefore, based on the calculation of the loss reference state, wind-induced vibration or other vibrations existing in the building can effectively identify the impact of the motor in the intelligent fire elevator, and timely estimate the degree of potential performance loss risk.

[0045] Further, the method for collecting data from the fire elevator in combination with the performance loss early warning factor is:

[0046] For any basic intermittent section, if more than half of the intermittent series correspond to the performance loss early warning factor, the determination result is true, and it is defined that the basic intermittent section has a risk of performance loss.

[0047] When the performance loss risk occurs, the intermittent series with the maximum value of the loss reference state is selected as the storage target intermittent series. The representative intermittent section corresponding to the storage target intermittent series is recorded as the target intermittent section. The environmental data in the target intermittent section is stored in the cloud.

[0048] The environmental data packet includes not only the data of the acceleration sensor, but also the running speed, pressure, temperature, camera, motor power and other modeling data serving the prediction model.

[0049] Preferably, all undefined variables in the present application can be manually set thresholds if not specifically defined.

[0050] The application further provides an intelligent fire-fighting elevator data acquisition system based on intermittent grading, which comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the intelligent fire-fighting elevator data acquisition method based on intermittent grading when executing the computer program, and the intelligent fire-fighting elevator data acquisition system based on intermittent grading can run in a desktop computer, a notebook computer, a palm computer, a cloud data center and other computing devices, and the executable system can comprise, but is not limited to, a processor, a memory, a server cluster, and the processor executes the computer program to run in the following system units:

[0051] An environment arrangement unit is arranged to acquire acceleration through a vibration acquisition module.

[0052] An intermittent grading unit is arranged to preset a basic intermittent section and establish an intermittent grading according to the basic intermittent section.

[0053] A loss analysis unit is arranged to obtain a loss reference state by decoupling analysis according to the acceleration and the intermittent grading.

[0054] A loss determination unit is arranged to determine a performance loss early warning factor for the loss reference state.

[0055] A data acquisition unit is arranged to acquire data from a fire-fighting elevator in combination with the performance loss early warning factor.

[0056] The application provides an intelligent fire-fighting elevator data acquisition method and system based on intermittent grading, which can effectively identify the influence of wind vibration or other vibrations existing in a building on a motor in an intelligent fire-fighting elevator through real-time acquisition and analysis of elevator vibration data based on the calculation of a loss reference state, timely estimate the occurrence degree of potential performance loss risks, dynamically effectively screen data in a modeling data acquisition process, reduce the storage of unnecessary or redundant data, further reduce the negative effects of redundant data and invalid data on a constructed prediction model, and prevent the constructed model from having the problems of insufficient adaptability or insufficient accuracy.

[0057] In this method, elevator data during vibration is obtained through the intermittent grading method, which can effectively collect time sequence characteristics under different vibration periods or vibration rules, provide more timely and accurate support for subsequent fault diagnosis, performance optimization and prediction, and further guarantee the safety, stability and long-period operation reliability of the elevator. BRIEF DESCRIPTION OF DRAWINGS

[0058] The above and other features of the present application will become more apparent by describing in detail the embodiments thereof with reference to the attached drawings in which:

[0059] Figure 1 Fig. 1 shows a flow chart of the intelligent fire elevator data acquisition method based on intermittent grading;

[0060] Figure 2 Fig. 2 shows a structural diagram of the intelligent fire elevator data acquisition system based on intermittent grading. DETAILED DESCRIPTION

[0061] The concept, specific structure and generated technical effects of the present application will be described clearly and completely below in combination with embodiments and drawings to fully understand the purpose, scheme and effects of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0062] As Figure 1 Fig. 1 shows a flow chart of the intelligent fire elevator data acquisition method based on intermittent grading, and the intelligent fire elevator data acquisition method based on intermittent grading according to the embodiments of the present application will be described below in combination with Figure 1 The method comprises the following steps:

[0063] Embodiment 1: The intelligent fire elevator data acquisition assembly comprises a vibration acquisition module, and the acceleration is obtained through the vibration acquisition module; a basic intermittent section is preset, and the intermittent grading is established according to the basic intermittent section; the loss reference state is obtained through decoupling analysis according to the acceleration and the intermittent grading; the performance loss early warning factor is determined for the loss reference state; and the data is collected from the fire elevator in combination with the performance loss early warning factor.

[0064] Further, the method for obtaining the acceleration through the vibration acquisition module in the intelligent fire elevator data acquisition assembly is as follows: the intelligent fire elevator data acquisition assembly comprises a vibration acquisition module, and the vibration acquisition module is arranged in the motor compartment of the elevator.

[0065] The vibration acquisition module comprises an acceleration sensor, and the acceleration sensor is an optical fiber type acceleration sensor.

[0066] The acceleration is obtained through real-time measurement by the acceleration sensor.

[0067] Further, the method for presetting the basic intermittent section and establishing the intermittent grading according to the basic intermittent section is as follows:

[0068] Set the basic rest period to 3 minutes;

[0069] An integer variable is preset as the intermittent series KL, and the value of the intermittent series is 15. For any intermittent series KL, it represents an intermittent segment with a time period of KL basic intermittent segments.

[0070] Furthermore, the method for obtaining the loss reference effective state based on the decoupling analysis of acceleration and intermittent series is:

[0071] At any moment, the basic intermittent segment belonging to that moment is the current basic intermittent segment. Any intermittent series from the current basic intermittent segment is selected as the calculation level. The range of the loss characteristic data corresponding to the calculation level in the intermittent segment is calculated. The ratio of the obtained range value to the maximum value of each acceleration module length in the current basic intermittent segment is recorded as the loss reference effective state of the calculation level; the loss characteristic data is the power value of the elevator motor when it is in a uniform motion state.

[0072] Furthermore, the method for determining the performance loss warning factor of the loss reference effectiveness state is as follows: a monitoring period TCr is preset, with a value of 5 hours, and each basic intermittent segment within the monitoring period is recorded as a reference node;

[0073] Obtain the loss reference state of each benchmark node and form a sequence recorded as Wsf.Ls;

[0074] Calculate the mean and standard deviation of the elements in the sequence Wsf.Ls. If the element is less than or equal to the sum of the mean and three times the standard deviation, and greater than or equal to the difference between the mean and three times the standard deviation, then record the corresponding reference node as a low-order loss point; otherwise, record it as a high-order loss point.

[0075] The threshold of three standard deviations above and below the mean was chosen to ensure statistical significance: according to the 3σ criterion for a normal distribution, the probability of data falling within the range of μ ± 3σ is 99.7%, and values ​​outside this range are considered significant outliers. This threshold effectively distinguishes between low-order loss points with normal fluctuations and high-order loss points with extreme anomalies, ensuring that warnings are triggered only for severe vibrations that significantly affect motor performance, balancing sensitivity with false alarm rate to avoid misjudgments.

[0076] The time scale of the loss reference state obtained from the low-order loss point and its corresponding loss reference state constitute a low-loss binary group. The cubic spline interpolation of the set constructed by the low-loss binary group within the monitoring period is performed using the plrep and splev functions to obtain a smooth curve.

[0077] The absolute value of the difference between the curve value of any high-order loss point and the corresponding loss reference state is recorded as the loss difference; the loss differences of each high-order loss point are obtained to form a difference evaluation sequence; the upper quartile Xes.sl, the lower quartile Xes.xl and the interquartile range Xes.jl in the difference evaluation sequence are obtained respectively; a loss plateau interval (Xes.xl-k2*Xes.jl, Xes.sl+k2*Xes.jl) is constructed according to the difference evaluation sequence; wherein k2 is an amplitude coefficient, and the value of k2 is 4;

[0078] If the current reference node belongs to the marked low-order loss point, the performance loss warning factor is assigned as FALSE; otherwise, if the current reference node belongs to the loss plateau interval, the performance loss warning factor is assigned as FALSE, otherwise the performance loss warning factor is assigned as TRUE.

[0079] Further, the method of collecting data from the fire elevator in combination with the performance loss warning factor is:

[0080] For any basic intermittent section, if more than half of the intermittent stages correspond to the performance loss warning factor whose determination result is true, it is defined that the performance loss risk occurs in the basic intermittent section;

[0081] When the performance loss risk occurs, the intermittent stage with the largest value of the loss reference state is selected as the storage target intermittent stage, the intermittent stage corresponding to the representative intermittent stage is recorded as the target intermittent stage, and the environmental data in the target intermittent stage is stored in the cloud.

[0082] The environmental data packet includes not only the data of the acceleration sensor, but also the running speed, pressure, temperature, camera and motor power.

[0083] The application purpose of the elevator data stored in the cloud is to collect vibration loss data through the daily operation of the fire elevator, construct a prediction model against the performance loss caused by the vibration of the fire elevator, limit the operation intensity of the fire elevator through the prediction model, including shutdown, limiting operation floors, limiting running speed, etc. Finally, a monitoring and control closed loop with microcomputer group ecological self-adaptation is formed.

[0084] Embodiment 2: The elevator data collection method of embodiment 2 is the same as that of embodiment 1, and the difference lies in that the method of determining the performance loss warning factor for the loss reference state is:

[0085] A preset monitoring period TCr is taken as 5 hours, and each basic intermittent section is recorded as a reference node in the monitoring period; the loss reference state of each reference node in the monitoring period is obtained to form a reference loss state sequence;

[0086] Each maximum element in the reference loss state sequence is recorded as a boundary node.

[0087] The difference between the loss reference state of any edge node and its left and right adjacent reference nodes is calculated, and the maximum value in the difference is selected as the loss critical value of the edge node;

[0088] The number of edge nodes is denoted as sdn, and the time interval between any edge node and its previous edge node is denoted as a loss trend value, and all loss trend values form a sequence denoted as Gn.Ls;

[0089] The DBSCAN density clustering algorithm is used for the loss trend value of each edge node, and all edge nodes are divided into several clusters, denoted as trend clustering cluster,

[0090] The early warning evaluation level Evyp of each trend clustering cluster is calculated according to the edge nodes and the loss critical value:

[0091] ;

[0092] where j1 is the serial number of the edge node in the trend clustering cluster, sn is the number of edge nodes in the trend clustering cluster, Lopp j1 is the loss reference state of the j1th edge node in the trend clustering cluster, MLopp is the average value of the loss reference states of all edge nodes, LCocv j1 is the serial number of the loss critical value of the j1th edge node in the trend clustering cluster when the loss critical values of all edge nodes are arranged in descending order, avg{} is the average value function, and exp() is the exponential function with the natural constant e as the base. All variables in the calculation process are dimensionless parameters to ensure the mathematical consistency of the formula, and statistical normalization processing is performed to objectively quantify the risk level of different clustering clusters. The loss reference state is a dimensionless parameter calculated by the ratio of the motor power difference to the maximum value of the acceleration module, which is used to quantify the correlation between vibration and motor performance fluctuations.

[0093] The early warning evaluation levels of each trend clustering cluster are normalized by the minimum-maximum method, and are denoted as loss risk state values. If the loss risk state value of a trend clustering cluster is greater than or equal to 0.5, the trend clustering cluster is marked as a risk type cluster, otherwise it is marked as a non-risk type cluster. The maximum value of the loss critical value in the trend clustering cluster is denoted as the critical peak value of the trend clustering cluster. The Euclidean distance between the current reference node and the critical peak value of any trend clustering cluster is denoted as the current critical distance, and the trend clustering cluster with the smallest critical distance is selected as the target cluster. If the target cluster is a risk type cluster, the performance loss early warning factor of the current reference node is assigned as TRUE, otherwise it is assigned as FALSE.

[0094] The loss risk state value is processed by minimum-maximum normalization, and the value range is [0, 1], therefore, 0.5 is selected as the threshold, which is a commonly used binary classification midpoint segmentation method in statistics, so as to balance the decision boundary of the risk and non-risk clusters, and avoid the model deviation caused by too high threshold or too low threshold.

[0095] The embodiment of the application provides an intelligent fire-fighting elevator data acquisition system based on intermittent grading. Figure 2 As shown in the figure, the embodiment of the application provides an intelligent fire-fighting elevator data acquisition system based on intermittent grading, which comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps in the above-mentioned embodiment of the intelligent fire-fighting elevator data acquisition method based on intermittent grading when executing the computer program.

[0096] The system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor executes the computer program to run in the following units of the system:

[0097] The environmental arrangement unit is used for acquiring acceleration through the vibration acquisition module;

[0098] The intermittent grading unit is used for presetting a basic intermittent section and establishing intermittent grading according to the basic intermittent section;

[0099] The loss analysis unit is used for obtaining a loss reference state by decoupling analysis according to the acceleration and the intermittent grading;

[0100] The loss determination unit is used for determining a performance loss early warning factor for the loss reference state.

[0101] The data acquisition unit is used for acquiring data from the fire-fighting elevator in combination with the performance loss early warning factor.

[0102] The intelligent fire-fighting elevator data acquisition system based on intermittent grading can run in a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The system can comprise, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of the intelligent fire-fighting elevator data acquisition system based on intermittent grading, and does not constitute a limitation on the intelligent fire-fighting elevator data acquisition system based on intermittent grading, and can comprise more or less components, or combine certain components, or different components, for example, the intelligent fire-fighting elevator data acquisition system based on intermittent grading can also comprise an input / output device, a network access device, a bus, etc.

[0103] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor. The processor is a control center of the intermittent hierarchical intelligent fire elevator data acquisition system running system, and connects all parts of the intermittent hierarchical intelligent fire elevator data acquisition system running system through various interfaces and lines.

[0104] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the intermittent hierarchical intelligent fire elevator data acquisition system by running or executing the computer program and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0105] Although the description of the present application has been quite detailed and particularly described with respect to several embodiments, it is not intended to be limited to any of these details or embodiments or any special embodiment, so as to effectively cover the intended scope of the present application. In addition, the present application is described above in the embodiments that the inventors can foresee, and the purpose is to provide a useful description, and non-essential modifications to the present application that have not yet been foreseen can still represent equivalent modifications of the present application.

Claims

1. An intelligent fire elevator data acquisition method based on intermittent classification is characterized by: The method comprises the following steps: a vibration acquisition module is included in the data acquisition component of the intelligent fire elevator, and acceleration is acquired through the vibration acquisition module; a basic intermittent segment is preset, and an intermittent series is established based on the basic intermittent segment; a loss reference effective state is obtained through decoupling analysis of acceleration and intermittent series; a performance loss warning factor is determined for the loss reference effective state; and data is collected from the fire elevator in combination with the performance loss warning factor. The method for determining the performance loss warning factor for the loss reference effectiveness state is as follows: presetting a monitoring period TCr, and recording each basic intermittent segment as a reference node within the monitoring period; Obtain the loss reference state of each benchmark node and form a sequence recorded as Wsf.Ls; Calculate the mean and standard deviation of the elements in the sequence Wsf.Ls. If the element is less than or equal to the sum of the mean and three times the standard deviation, and greater than or equal to the difference between the mean and three times the standard deviation, then record the corresponding reference node as a low-order loss point; otherwise, record it as a high-order loss point. The time scale of the loss reference state obtained from the low-order loss point and its corresponding loss reference state constitute a low-loss binary group. The cubic spline interpolation of the set constructed by the low-loss binary group within the monitoring period is performed using the plrep and splev functions to obtain a smooth curve. The absolute value of the difference between the curve value of any high-order loss point and its corresponding loss reference state is recorded as the loss difference; the loss difference of each high-order loss point is obtained and a difference evaluation sequence is constructed; the upper quartile Xes.sl, lower quartile Xes.xl, and interquartile range Xes.jl in the difference evaluation sequence are obtained respectively; the loss stationary interval is constructed based on the difference evaluation sequence as (Xes.xl-k2×Xes.jl, Xes.sl+k2×Xes.jl); where k2 is the preset amplitude coefficient; If the current benchmark node belongs to the marked low-order loss point, the performance loss warning factor is assigned to FALSE; otherwise, if the current benchmark node belongs to the loss stable interval, the performance loss warning factor is assigned to FALSE, otherwise, the performance loss warning factor is assigned to TRUE.

2. The intelligent fire elevator data acquisition method based on intermittent classification according to claim 1 is characterized in that: The method of obtaining acceleration through the vibration acquisition module is as follows: the intelligent fire elevator data acquisition scenario includes a vibration acquisition module, which is arranged in the motor compartment of the elevator; The vibration acquisition module includes an acceleration sensor, which is a piezoelectric acceleration sensor, an optical fiber acceleration sensor or a MEMS acceleration sensor. The acceleration is obtained by real-time measurement using an acceleration sensor.

3. The intelligent fire elevator data acquisition method based on intermittent grading according to claim 1 is characterized in that: The method of presetting the basic interval segment and establishing the interval progression based on the basic interval segment is as follows: setting the basic interval segment to 1-10 minutes; An integer variable is preset as the intermittent series KL, and the value range of the intermittent series is KL∈[1,15]. For any intermittent series KL, the intermittent segment it represents is the time period of KL basic intermittent segments.

4. The intelligent fire elevator data acquisition method based on intermittent grading according to claim 1 is characterized in that: The method for obtaining the loss reference effective state based on the decoupling analysis of acceleration and intermittent series is as follows: at any moment, the basic intermittent segment belonging to that moment is the current basic intermittent segment, and any intermittent series from the current basic intermittent segment is selected as the operation level. The range of the loss characteristic data corresponding to the operation level in the intermittent segment is calculated, and the ratio of the obtained range value to the maximum value of each acceleration modulus in the current basic intermittent segment is recorded as the loss reference effective state of the operation level. The loss characteristic data is the power value of the motor when the elevator is in a uniform motion state.

5. The intelligent fire elevator data acquisition method based on intermittent grading according to claim 1 is characterized in that: The method for determining the performance loss warning factor for the loss reference effect state can be replaced by: presetting a monitoring period TCr, and recording each basic intermittent segment as a reference node within the monitoring period; Obtain the loss reference status of each benchmark node during the monitoring period and form a benchmark loss status sequence; The reference nodes corresponding to each maximum value element in the reference loss state sequence are recorded as adjacent nodes; Calculate the difference between the loss reference effective state of any adjacent node and its left and right adjacent reference nodes, and select the maximum value of the difference as the loss critical value of the adjacent node; The number of adjacent nodes is recorded as sdn; the time interval between any adjacent node and its previous adjacent node is recorded as the loss trend value, and the sequence of all loss trend values ​​is recorded as Gn.Ls; The loss trend value of each adjacent node is clustered using the DBSCAN density clustering algorithm to divide all adjacent nodes into several clusters, which are recorded as trend clusters; The early warning assessment level of each trend cluster is calculated based on the edge nodes and loss critical value. The early warning assessment level of each trend cluster is normalized to the minimum and maximum value and recorded as the loss risk status value. If the loss risk status value of a trend cluster is greater than or equal to 0.5, the trend cluster is marked as a risk type cluster; otherwise, it is marked as a non-risk type cluster. The maximum value of the loss critical value in the trend cluster is recorded as the critical peak value of the trend cluster. The Euclidean distance between the current benchmark node and the critical peak value of any trend cluster is recorded as the current critical distance. The trend cluster with the minimum previous critical distance is selected as the target cluster. If the target cluster is a risk type cluster, the performance loss warning factor of the current benchmark node is assigned to TRUE, otherwise the performance loss warning factor is assigned to FALSE.

6. The intelligent fire elevator data acquisition method based on intermittent grading according to claim 1 is characterized in that: The method of collecting data from fire elevators in combination with the performance loss warning factor is as follows: for any basic intermittent segment, if the judgment result of the performance loss warning factor corresponding to more than half of the intermittent levels is true, then the risk of performance loss occurring in the basic intermittent segment is defined; When the risk of performance loss occurs, the interval level with the maximum value of the loss reference effect state is selected as the storage target interval level, and the interval segment corresponding to the storage target interval level is recorded as the target interval segment, and the environmental data within the target interval segment is stored in the cloud.

7. Intelligent fire elevator data acquisition system based on intermittent classification, characterized by: The intelligent fire elevator data acquisition system based on intermittent grading includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intelligent fire elevator data acquisition method based on intermittent grading according to any one of claims 1 to 6 are implemented. The intelligent fire elevator data acquisition system based on intermittent grading runs on a desktop computer, a laptop computer, a PDA, and a computing device in a cloud data center.

Images