CN117436712A - Real-time monitoring method and system for operation risk of construction hanging basket - Google Patents
Real-time monitoring method and system for operation risk of construction hanging basket Download PDFInfo
- Publication number
- CN117436712A CN117436712A CN202311765462.8A CN202311765462A CN117436712A CN 117436712 A CN117436712 A CN 117436712A CN 202311765462 A CN202311765462 A CN 202311765462A CN 117436712 A CN117436712 A CN 117436712A
- Authority
- CN
- China
- Prior art keywords
- data
- time sequence
- target time
- cluster
- data point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 239000003550 marker Substances 0.000 claims abstract description 69
- 241001123248 Arma Species 0.000 claims abstract description 36
- 238000010586 diagram Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 49
- 238000013507 mapping Methods 0.000 claims description 36
- 238000010606 normalization Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 37
- 230000000737 periodic effect Effects 0.000 description 7
- 238000005070 sampling Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007774 longterm Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 230000003313 weakening effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention relates to the technical field of data processing, in particular to a real-time monitoring method and a real-time monitoring system for operation risk of a construction hanging basket, wherein the method is used for acquiring historical inclination time sequence data of the construction hanging basket in the operation process, normalizing the historical inclination time sequence data, and taking the obtained normalized historical inclination time sequence data as target time sequence data; acquiring a marked data point in the target time sequence data; classifying the marker data points to obtain corresponding classification results; acquiring an ACF correlation coefficient diagram of the target time sequence data, and acquiring a hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient diagram and a classification result; according to the hysteresis order of each data point in the target time sequence data, an optimal ARMA model is fitted to monitor the running risk of the construction hanging basket in real time, so that the prediction performance of the ARMA model is improved, and the ARMA model can accurately monitor the running risk of the construction hanging basket in real time.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a real-time monitoring method and system for operation risk of a construction hanging basket.
Background
The construction hanging basket is important equipment in high-altitude operation, and in order to ensure life safety of workers, real-time monitoring of operation risk is important. The real-time monitoring of the construction hanging basket can help to find potential risks and dangerous situations, such as inclination, overload, sundry accumulation and the like, early; and through carrying out real-time supervision to the construction basket, can carry out real-time analysis and aassessment to the risk factor of construction basket operation in-process, this helps constantly improving safety precaution and operation regulation, improves the security of construction basket operation to reduce potential accident risk.
However, in the running process of the construction hanging basket, real-time monitoring of the hanging basket inclination is the most important one, in the prior art, an ARMA model (autoregressive moving average model) is usually trained according to historical time sequence data of the hanging basket inclination, a trained ARMA model is obtained, and then the hanging basket inclination of the construction hanging basket is predicted by using the trained ARMA model so as to help evaluate the stability and safety of the construction hanging basket and discover potential inclination risks early. However, due to the fact that different stages in the operation process of the hanging basket are affected by external environments, certain periodic fluctuation occurs to the inclination of the hanging basket, historical time sequence data of the default hanging basket inclination in the training process of the traditional ARMA model is stable, the local non-stable data fitting effect in the historical time sequence data of the hanging basket inclination is poor, the prediction performance of the trained ARMA model is poor, and the operation risk of the construction hanging basket cannot be accurately monitored in real time.
Therefore, how to improve the prediction performance of the ARMA model so as to accurately monitor the operation risk of the construction hanging basket in real time becomes a problem to be solved.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a real-time monitoring method and a real-time monitoring system for the running risk of a construction hanging basket, which are used for solving the problem of how to improve the prediction performance of an ARMA model so as to accurately monitor the running risk of the construction hanging basket in real time.
In a first aspect, an embodiment of the present invention provides a real-time monitoring method for risk of operation of a construction hanging basket, where the real-time monitoring method for risk of operation of a construction hanging basket includes the following steps:
acquiring historical inclination time sequence data of a construction hanging basket in the running process, and carrying out normalization processing on the historical inclination time sequence data, wherein the obtained normalized historical inclination time sequence data is used as target time sequence data;
acquiring the inclination change degree of each data point in the target time sequence data according to the difference between the data points, and acquiring the mark data point in the target time sequence data according to the inclination change degree of each data point in the target time sequence data;
clustering the marker data points to obtain at least one cluster, respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster, and classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result;
acquiring an ACF correlation coefficient diagram of the target time sequence data, and acquiring a hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient diagram and the classification result;
and fitting an optimal ARMA model according to the target time sequence data and the hysteresis order of each data point in the target time sequence data, and monitoring the running risk of the construction hanging basket in real time by using the optimal ARMA model.
Further, the obtaining the inclination variation degree of each data point in the target time sequence data according to the difference between the data points includes:
acquiring the data average value of all data points in the target time sequence data;
for any data point in the target time sequence data, acquiring a first difference absolute value between the data point and the data average value, carrying out negative mapping on the first difference absolute value to obtain a corresponding first mapping value, acquiring a previous adjacent data point of the data point in the target time sequence data, acquiring a second difference absolute value between the data point and the previous adjacent data point, and carrying out negative mapping on the second difference absolute value to obtain a corresponding second mapping value;
and carrying out weighted summation on the first mapping value and the second mapping value to obtain a corresponding weighted summation result, wherein the result obtained by subtracting the weighted summation result from a constant 1 is used as the inclination change degree of the data point.
Further, the acquiring the marker data point in the target time sequence data according to the inclination change degree of each data point in the target time sequence data includes:
and acquiring a preset inclination change degree threshold, and determining the data point as a marker data point if the inclination change degree of any data point in the target time sequence data is larger than or equal to the inclination change degree threshold.
Further, the step of respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster includes:
for any cluster, respectively acquiring Euclidean distances between every two adjacent data points according to the position of each data point in the cluster, calculating Euclidean distance average value between all Euclidean distances, acquiring the interval length of adjacent time primitives in the space where the cluster is located, acquiring a third difference absolute value between the Euclidean distance average value and the interval length, carrying out negative mapping on the third difference absolute value to obtain a corresponding third mapping value, and acquiring a subtraction result between a constant 1 and the third mapping value;
and obtaining a difference value between a maximum data point and a minimum data point in the cluster, carrying out negative mapping on the difference value to obtain a corresponding fourth mapping value, carrying out weighted summation on the subtraction result and the fourth mapping value, and taking the obtained weighted summation result as a data floating characteristic value of the cluster.
Further, the classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result includes:
acquiring a preset data floating characteristic value threshold, and taking all marker data points in any cluster as first type marker data points if the data floating characteristic value of any cluster is larger than or equal to the data floating characteristic value threshold;
and if the data floating characteristic value of any cluster is smaller than the data floating characteristic value threshold value, taking all the marker data points in the cluster as second-class marker data points.
Further, the obtaining the hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient graph and the classification result includes:
acquiring a last peak value point in the ACF correlation coefficient graph, taking a hysteresis order corresponding to the last peak value point as a hysteresis order of a first type of marker data point in the target time sequence data, and taking a hysteresis order corresponding to a preset number of hysteresis orders spaced after the hysteresis order corresponding to the last peak value point as a hysteresis order of a second type of marker data point in the target time sequence data;
and aiming at any one data point of non-first type marked data points and non-second type marked data points in the target time sequence data, acquiring a hysteresis order corresponding to the data points in the ACF correlation coefficient graph.
Further, the clustering the marker data points to obtain at least one cluster includes:
and clustering the marker data points by using a DBSCAN clustering algorithm to obtain at least one cluster.
In a second aspect, an embodiment of the present invention further provides a real-time monitoring system for risk of operation of a construction hanging basket, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the real-time monitoring method for risk of operation of a construction hanging basket according to the first aspect when executing the computer program.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
according to the method, historical inclination time sequence data of the construction hanging basket in the running process are obtained, normalization processing is carried out on the historical inclination time sequence data, and the obtained normalized historical inclination time sequence data are used as target time sequence data; acquiring the inclination change degree of each data point in the target time sequence data according to the difference between the data points, and acquiring the mark data point in the target time sequence data according to the inclination change degree of each data point in the target time sequence data; clustering the marker data points to obtain at least one cluster, respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster, and classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result; acquiring an ACF correlation coefficient diagram of the target time sequence data, and acquiring a hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient diagram and the classification result; and fitting an optimal ARMA model according to the target time sequence data and the hysteresis order of each data point in the target time sequence data, and monitoring the running risk of the construction hanging basket in real time by using the optimal ARMA model. According to the characteristic identification and distinguishing of all data points in the historical inclination time sequence data of the construction hanging basket, the hysteresis order of each data point in the historical inclination time sequence data is adaptively obtained in an ACF correlation coefficient graph of the historical inclination time sequence data according to distinguishing results, and then an optimal ARMA model is fitted according to the hysteresis order of each data point in the historical inclination time sequence data, so that the ARMA model achieves a weakening effect on the inclination data regarded as normal floating during fitting, achieves a strengthening effect on the inclination data which abnormally floats during fitting, the prediction performance of the ARMA model is improved, and the running risk of the construction hanging basket can be accurately monitored in real time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for monitoring running risk of a construction hanging basket in real time according to an embodiment of the present invention.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations. In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Referring to fig. 1, a method flowchart of a real-time monitoring method for risk of operation of a construction hanging basket according to an embodiment of the present invention is shown in fig. 1, where the method may include:
step S101, acquiring historical inclination time sequence data of the construction hanging basket in the running process, and carrying out normalization processing on the historical inclination time sequence data, wherein the obtained normalized historical inclination time sequence data is used as target time sequence data.
In the embodiment of the invention, the inclination angle of the construction hanging basket is measured by using sensors such as an inclination sensor, an accelerometer or a gyroscope, and the like, wherein the inclination angle refers to the included angle between the construction hanging basket and the wall surface and is in the range of. Specifically, install the sensor on the construction string basket, and ensure that the inclination that can accurately gather construction string basket, then gather construction string basket inclination in the operation in-process according to preset sampling frequency to according to sampling time with the inclination constitution gradient time sequence data that gathers in the period of time, and with the gradient time sequence data storage that gathers. Wherein the sampling frequency may be 0.1 seconds, which is not limited in the present invention.
Therefore, in the embodiment of the invention, the historical inclination time sequence data of the construction hanging basket in the running process can be obtained, and the historical inclination time sequence data is normalized to obtain normalized historical inclination time sequence data, so that each data in the historical inclination time sequence data is mapped between 0 and 1, and meanwhile, the normalized historical inclination time sequence data is taken as target time sequence data for facilitating understanding, wherein the specific normalization processing method comprises the following steps:
wherein,representing normalized data, ++>Representing the original data.
Step S102, according to the difference between the data points, the inclination change degree of each data point in the target time sequence data is obtained, and according to the inclination change degree of each data point in the target time sequence data, the mark data point in the target time sequence data is obtained.
For the inclination angle in the construction hanging basket operation scene, according to scene characteristics, the construction hanging basket is known to be relatively stable in the initial operation stage, and the inclination angle is influenced by external environment (wind or building vibration) in the gradual follow-up operation process because the construction hanging basket is adjusted and balanced for a long time, and the inclination angle shows certain periodic fluctuation, is usually smaller and has relatively stable frequency, and belongs to the normal condition; if the construction hanging basket is subjected to external impact, serious inclination or unbalance can be possibly caused under the influence of environmental problems such as machine faults or extremely strong wind, the inclination angle at the moment is suddenly changed or the inclination angle is gradually increased for a long time, so that the traditional ARMA model cannot realize more accurate data prediction and risk assessment under the complex and changeable scene requirements.
The method for acquiring the marker data point in the target time sequence data is as follows: according to the difference between the data points, the inclination change degree of each data point in the target time sequence data is obtained, and according to the inclination change degree of each data point in the target time sequence data, the mark data point in the target time sequence data is obtained. Wherein, according to the difference between the data points, the obtaining the inclination change degree of each data point in the target time sequence data includes:
acquiring the data average value of all data points in the target time sequence data;
for any data point in the target time sequence data, acquiring a first difference absolute value between the data point and the data average value, carrying out negative mapping on the first difference absolute value to obtain a corresponding first mapping value, acquiring a previous adjacent data point of the data point in the target time sequence data, acquiring a second difference absolute value between the data point and the previous adjacent data point, and carrying out negative mapping on the second difference absolute value to obtain a corresponding second mapping value;
and carrying out weighted summation on the first mapping value and the second mapping value to obtain a corresponding weighted summation result, wherein the result obtained by subtracting the weighted summation result from a constant 1 is used as the inclination change degree of the data point.
In one embodiment, the calculated expression of the degree of tilt change of any data point in the target time series data is:
wherein,indicating the degree of inclination change of the ith data point in the target time series data, +.>Represents the ith data point in the target time series data, N represents the total number of data in the target time series data,/->Represents the jth data point, < ->Data mean value representing all data points in the target time series data, +.>Representing an exponential function based on a natural constant e, < ->Representing the i-1 th data point in the target time series data, namely the data point adjacent to the i-th data point, +.>Representing the absolute value of the difference between the ith data point and the (i-1) th data point, +.>Representing a first weight, ++>Representing the second weight, 1 representing a constant, || representing taking an absolute value.
Preferably, in the embodiment of the present invention, the allocation is performed according to an empirical value:。
it should be noted that, by calculating the difference between the data average of the ith data point and all data points in the target time series dataThe method is used for representing abnormal change of the ith data point, and the smaller the difference is, the smaller the inclination change degree corresponding to the ith data point is, and the more the construction basket is in a safe running state; meanwhile, calculate the difference between the ith data point and the ith-1 data point +.>For indicating whether or not there is a large difference between the ith data point and the (i-1) th data point, the smaller the difference, the smaller the degree of inclination change corresponding to the ith data point, therefore, the difference +.>Positive correlation with inclination change degree, difference ∈>Is positively correlated with the degree of inclination change +.>The greater the value of (2), the higher the degree of change in inclination of the corresponding data point, the more the construction basket is at risk.
Wherein, according to the inclination change degree of each data point in the target time sequence data, the mark data point in the target time sequence data is obtained, which comprises the following steps:
and acquiring a preset inclination change degree threshold, and determining the data point as a marker data point if the inclination change degree of any data point in the target time sequence data is larger than or equal to the inclination change degree threshold.
In one embodiment, the inclination change threshold is set to be 0.8, and if the inclination change degree of the ith data point in the target time sequence data is greater than or equal to 0.8, the ith data point is indicated to be a data point with higher inclination change degree, so that the ith data point is marked as a marked data point, and each data point in the target time sequence data is compared with the inclination change degree threshold to obtain all marked data points in the target time sequence data.
Step S103, clustering the marked data points to obtain at least one cluster, respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster, and classifying the marked data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result.
In the embodiment of the present invention, further distinguishing processing is required for the marker data points acquired in step S102, so that the marker data points are clustered to obtain at least one cluster. Specifically, clustering the marker data points by using a DBSCAN clustering algorithm to obtain at least one cluster, wherein two parameters are determined in the DBSCAN clustering algorithm: search radiusMinimum number of neighbors +.>In order to exclude abrupt isolated data points and combine the normal periodic fluctuation change data point characteristics, the minimum neighbor parameters and the search radius are given as follows:
wherein T is the minimum time primitive under the acquisition frequency in the sample space, the search radius is set to be 2T, and the search is performed on data points in two time primitive intervals adjacent to the current point in front and behind the current point serving as the center.
It is worth noting that the search radiusConsistent with the periodic floating characteristic, clustering can be realized on data points with higher inclination degree and periodic variation, and abrupt and isolated data points can be eliminated; the minimum neighbor number is set to 2, which means that at least two marker data points with higher inclination degree exist in the range of the marker data points with higher current inclination degree during transverse clustering; search radius in DBSCAN clustering algorithm>Minimum number of neighbors +.>The setting may be performed according to the actual scene and the sampling frequency, and the present invention is not limited, for example: when the sampling frequency of the target time sequence data is 1 second, the minimum time element T in the sampling frequency in the sample space is 1, corresponding to the search radius +.>2. And the DBSCAN clustering algorithm belongs to the prior art, and is not described in detail here.
Further, after clustering the marker data points in the target time sequence data, the data points with higher inclination change degree of the isolated mutation can be removed according to the clustering result, and the data points can be screened and marked. Because the data points forming the clusters with higher inclination degree have a certain possibility of gradual change of long-term inclination, the change can not be regarded as normal condition, and the initial characteristics and risks of the construction basket influenced by external factors and conditions in the operation process exist, therefore, the clusters formed by the clusters need to be analyzed for internal floating characteristics so as to divide the marked data points into periodically floating data points and data points with long-term trend change, and in the embodiment of the invention, the data floating characteristic value of each cluster is acquired respectively according to the data point difference in each cluster, and then the marked data points are classified according to the data floating characteristic value of each cluster to obtain a corresponding classification result.
Preferably, the step of respectively obtaining the data floating characteristic value of each cluster according to the difference of the data points in each cluster includes:
for any cluster, respectively acquiring Euclidean distances between every two adjacent data points according to the position of each data point in the cluster, calculating Euclidean distance average value between all Euclidean distances, acquiring the interval length of adjacent time primitives in the space where the cluster is located, acquiring a third difference absolute value between the Euclidean distance average value and the interval length, carrying out negative mapping on the third difference absolute value to obtain a corresponding third mapping value, and acquiring a subtraction result between a constant 1 and the third mapping value;
and obtaining a difference value between a maximum data point and a minimum data point in the cluster, carrying out negative mapping on the difference value to obtain a corresponding fourth mapping value, carrying out weighted summation on the subtraction result and the fourth mapping value, and taking the obtained weighted summation result as a data floating characteristic value of the cluster.
In one embodiment, the calculation expression of the data floating eigenvalue of any cluster is:
wherein,data floating eigenvalue representing cluster C, +.>Representing an exponential function based on a natural constant e, < ->Representing the total number of marker data points contained in cluster C, +.>Representing the Euclidean distance between the ith marker data point and the i-1 th marker data point in cluster C, +.>Representing the Euclidean distance mean value between all adjacent marked data points in the cluster C, and T represents the interval length of adjacent time elements in the space where the cluster is located, namely the minimum time element under the acquisition frequency in the sample space in the clustering process, namely->Representing the largest data point in cluster C, < + >>Shows the smallest data point in cluster C, +.>Representing the first weight coefficient,/->Representing a second weight coefficient, assigning +_ based on empirical values>。
It should be noted that the number of the substrates,the value of (2) represents the difference between the Euclidean distance average and the unit length of the time elementNormalization of the function ∈>For->Carrying out normalization, wherein the smaller the difference is, the closer the normalized result is to 1, if the normalized result is close to 1, the cluster C belongs to the difference characteristic of the long-term increasing trend, the smaller the corresponding data floating characteristic value is, otherwise, if the normalized result is deviated from 1, the cluster C belongs to the periodically floating difference characteristic, and the larger the corresponding data floating characteristic value is; similarly, the difference between the largest and smallest data points in cluster C ∈>The closer to 0, the more the cluster C belongs to the periodic floating difference feature, the difference +.>The deviation from 0 indicates that cluster C belongs to the difference characteristic of long-term increasing trend, so that under the action of the inverse proportion normalization function, the difference is ∈ ->The smaller the calculation result is, the more 1 is approached, the more the difference characteristic of periodic floating is met, the larger the corresponding data floating characteristic value is, and conversely, the difference is +.>The larger the calculated result is deviated from 1, the more the difference characteristic conforming to the long-term increasing trend is obtained, and the smaller the corresponding data floating characteristic value is.
Thus, the data floating characteristic value of each cluster can be obtained.
Preferably, the classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result includes:
acquiring a preset data floating characteristic value threshold, and taking all marker data points in any cluster as first type marker data points if the data floating characteristic value of any cluster is larger than or equal to the data floating characteristic value threshold;
and if the data floating characteristic value of any cluster is smaller than the data floating characteristic value threshold value, taking all the marker data points in the cluster as second-class marker data points.
In one embodiment, the data floating eigenvalue threshold is set to be 0.7, if the data floating eigenvalue of any cluster is greater than or equal to 0.7, it is indicated that all the marker data points in the cluster are data points with normal inclination change, all the marker data points in the cluster are regarded as first type of marker data points, otherwise, all the marker data points in the cluster are regarded as non-negligible abnormal inclination change data points, and all the marker data points in the cluster are regarded as second type of marker data points.
To this end, the data points in the target time series data are divided into a first type of marker data point, a second type of marker data point, and other data points (non-first type of marker data point and non-second type of marker data point).
Step S104, an ACF correlation coefficient diagram of the target time sequence data is obtained, and the hysteresis order of each data point in the target time sequence data is obtained according to the ACF correlation coefficient diagram and the classification result.
According to the average fitting thought of the ARMA model, increasing the hysteresis order can enable the ARMA model to capture data information and trend in a longer time sequence range so as to highlight abnormal data, and conversely, reducing the hysteresis order can weaken fitting influence caused by the abnormal data. Whereas the selection of the hysteresis order is generally conventional: and using an ACF correlation coefficient graph, wherein the horizontal axis in the ACF correlation coefficient graph represents the hysteresis order, and judging whether the peak value is suddenly reduced or truncated after a certain hysteresis order by observing the existence of a remarkable peak value in the ACF correlation coefficient graph, and if no remarkable peak value change occurs after the last peak value, the hysteresis order corresponding to the last peak value is the acquired initial hysteresis order. Therefore, in the embodiment of the invention, the ACF correlation coefficient diagram of the target time sequence data is acquired first, and then the hysteresis order of each data point in the target time sequence data is acquired according to the ACF correlation coefficient diagram and the classification result, so that the hysteresis order of each data point in the target time sequence data is acquired in a self-adaptive manner. The method for obtaining the ACF correlation coefficient map belongs to the prior art, and is not described herein.
Preferably, the obtaining the hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient graph and the classification result includes:
acquiring a last peak value point in the ACF correlation coefficient graph, taking a hysteresis order corresponding to the last peak value point as a hysteresis order of a first type of marker data point in the target time sequence data, and taking a hysteresis order corresponding to a preset number of hysteresis orders spaced after the hysteresis order corresponding to the last peak value point as a hysteresis order of a second type of marker data point in the target time sequence data;
and aiming at any one data point of non-first type marked data points and non-second type marked data points in the target time sequence data, acquiring a hysteresis order corresponding to the data points in the ACF correlation coefficient graph.
In one embodiment, since the abscissa of the ACF correlation coefficient graph represents the hysteresis order and the ordinate represents the correlation coefficient between the corresponding hysteresis sequence and the target time series data, the last peak point in the ACF correlation coefficient graph is first determined, and the hysteresis order is required to be reduced when the first type of marker data point needs to weaken the inclination variation abnormality degree, so that the hysteresis order of the last peak point in the ACF correlation coefficient graph is used as the hysteresis order of the first type of marker data point in the target time series data; because the second type of marker data points belong to data points with non-negligible abnormal inclination change, the abnormality of the second type of marker data points needs to be highlighted in the fitting process of the subsequent ARMA model so as to realize better monitoring and early warning, therefore, the hysteresis order of the second type of marker data points needs to be increased, and the 1 st hysteresis order or the 2 nd hysteresis order of the last peak point after the corresponding hysteresis order in the ACF correlation coefficient graph is used as the hysteresis order of the second type of marker data points in the target time sequence data; further, for other data points (non-first type marker data points and non-second type marker data points) in the target time sequence data, which are data points with low inclination change degree, the hysteresis order corresponding to each other data point is obtained in the ACF correlation coefficient graph by using the traditional obtaining method of the hysteresis order (which belongs to the prior art and is not described here). Thus, the hysteresis order of each data point in the target time series data is obtained.
And step 105, fitting an optimal ARMA model according to the target time sequence data and the hysteresis order of each data point in the target time sequence data, and carrying out real-time monitoring on the operation risk of the construction hanging basket by using the optimal ARMA model.
In the embodiment of the invention, the ARMA model is fitted by utilizing the target time sequence data and the hysteresis order of each data point in the target time sequence data to obtain the optimal ARMA model, so that the second type of marker data points in the target time sequence data are enhanced and highlighted when the optimal ARMA model is fitted, the first type of marker data points and other data points in the target time sequence data are weakened, and the optimal fitting effect under the current scene is achieved. It should be noted that, the fitting of the ARMA model belongs to the prior art, and will not be described here.
Further, after the optimal ARMA model is obtained, predicting the inclination angle of the construction hanging basket at any moment by using the optimal ARMA model, and analyzing whether the construction hanging basket at the moment is in an operation risk state according to the predicted inclination angle, so that the operation risk of the construction hanging basket is monitored in real time.
In summary, the embodiment of the invention obtains the historical inclination time sequence data of the construction hanging basket in the running process, normalizes the historical inclination time sequence data, and takes the normalized historical inclination time sequence data as target time sequence data; acquiring the inclination change degree of each data point in the target time sequence data according to the difference between the data points, and acquiring the mark data point in the target time sequence data according to the inclination change degree of each data point in the target time sequence data; clustering the marker data points to obtain at least one cluster, respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster, and classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result; acquiring an ACF correlation coefficient diagram of the target time sequence data, and acquiring a hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient diagram and a classification result; and fitting an optimal ARMA model according to the target time sequence data and the hysteresis order of each data point in the target time sequence data, and carrying out real-time monitoring on the operation risk of the construction hanging basket by using the optimal ARMA model. According to the characteristic identification and distinguishing of all data points in the historical inclination time sequence data of the construction hanging basket, the hysteresis order of each data point in the historical inclination time sequence data is adaptively obtained in an ACF correlation coefficient graph of the historical inclination time sequence data according to distinguishing results, and then an optimal ARMA model is fitted according to the hysteresis order of each data point in the historical inclination time sequence data, so that the ARMA model achieves a weakening effect on the inclination data regarded as normal floating during fitting, achieves a strengthening effect on the inclination data which abnormally floats during fitting, the prediction performance of the ARMA model is improved, and the running risk of the construction hanging basket can be accurately monitored in real time.
Based on the same inventive concept as the method, the embodiment of the invention also provides a real-time monitoring system for the running risk of the construction hanging basket, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor realizes the steps of any one of the real-time monitoring methods for the running risk of the construction hanging basket when executing the computer program.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. The real-time monitoring method for the operation risk of the construction hanging basket is characterized by comprising the following steps of:
acquiring historical inclination time sequence data of a construction hanging basket in the running process, and carrying out normalization processing on the historical inclination time sequence data, wherein the obtained normalized historical inclination time sequence data is used as target time sequence data;
acquiring the inclination change degree of each data point in the target time sequence data according to the difference between the data points, and acquiring the mark data point in the target time sequence data according to the inclination change degree of each data point in the target time sequence data;
clustering the marker data points to obtain at least one cluster, respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster, and classifying the marker data points according to the data floating characteristic value of each cluster to obtain a corresponding classification result;
acquiring an ACF correlation coefficient diagram of the target time sequence data, and acquiring a hysteresis order of each data point in the target time sequence data according to the ACF correlation coefficient diagram and the classification result;
and fitting an optimal ARMA model according to the target time sequence data and the hysteresis order of each data point in the target time sequence data, and monitoring the running risk of the construction hanging basket in real time by using the optimal ARMA model.
2. The method for monitoring the running risk of the construction hanging basket according to claim 1, wherein the step of obtaining the inclination variation degree of each data point in the target time series data according to the difference between the data points comprises the following steps:
acquiring the data average value of all data points in the target time sequence data;
for any data point in the target time sequence data, acquiring a first difference absolute value between the data point and the data average value, carrying out negative mapping on the first difference absolute value to obtain a corresponding first mapping value, acquiring a previous adjacent data point of the data point in the target time sequence data, acquiring a second difference absolute value between the data point and the previous adjacent data point, and carrying out negative mapping on the second difference absolute value to obtain a corresponding second mapping value;
and carrying out weighted summation on the first mapping value and the second mapping value to obtain a corresponding weighted summation result, wherein the result obtained by subtracting the weighted summation result from a constant 1 is used as the inclination change degree of the data point.
3. The method for monitoring the risk of operation of a construction basket according to claim 1, wherein the step of obtaining the marker data point in the target time series data according to the inclination variation degree of each data point in the target time series data comprises the steps of:
and acquiring a preset inclination change degree threshold, and determining the data point as a marker data point if the inclination change degree of any data point in the target time sequence data is larger than or equal to the inclination change degree threshold.
4. The method for monitoring the running risk of the construction hanging basket in real time according to claim 1, wherein the step of respectively obtaining the data floating characteristic value of each cluster according to the data point difference in each cluster comprises the following steps:
for any cluster, respectively acquiring Euclidean distances between every two adjacent data points according to the position of each data point in the cluster, calculating Euclidean distance average value between all Euclidean distances, acquiring the interval length of adjacent time primitives in the space where the cluster is located, acquiring a third difference absolute value between the Euclidean distance average value and the interval length, carrying out negative mapping on the third difference absolute value to obtain a corresponding third mapping value, and acquiring a subtraction result between a constant 1 and the third mapping value;
and obtaining a difference value between a maximum data point and a minimum data point in the cluster, carrying out negative mapping on the difference value to obtain a corresponding fourth mapping value, carrying out weighted summation on the subtraction result and the fourth mapping value, and taking the obtained weighted summation result as a data floating characteristic value of the cluster.
5. The method for monitoring the running risk of the construction hanging basket according to claim 1, wherein the classifying the marker data points according to the data floating characteristic value of each cluster to obtain the corresponding classification result comprises the following steps:
acquiring a preset data floating characteristic value threshold, and taking all marker data points in any cluster as first type marker data points if the data floating characteristic value of any cluster is larger than or equal to the data floating characteristic value threshold;
and if the data floating characteristic value of any cluster is smaller than the data floating characteristic value threshold value, taking all the marker data points in the cluster as second-class marker data points.
6. The method for monitoring risk of basket operation in real time according to claim 5, wherein the step of obtaining the hysteresis order of each data point in the target time series data according to the ACF correlation coefficient map and the classification result comprises the steps of:
acquiring a last peak value point in the ACF correlation coefficient graph, taking a hysteresis order corresponding to the last peak value point as a hysteresis order of a first type of marker data point in the target time sequence data, and taking a hysteresis order corresponding to a preset number of hysteresis orders spaced after the hysteresis order corresponding to the last peak value point as a hysteresis order of a second type of marker data point in the target time sequence data;
and aiming at any one data point of non-first type marked data points and non-second type marked data points in the target time sequence data, acquiring a hysteresis order corresponding to the data points in the ACF correlation coefficient graph.
7. The method for monitoring the running risk of the construction hanging basket according to claim 1, wherein the clustering the marker data points to obtain at least one cluster comprises:
and clustering the marker data points by using a DBSCAN clustering algorithm to obtain at least one cluster.
8. A real-time monitoring system for risk of operation of a construction hanging basket, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the real-time monitoring method for risk of operation of a construction hanging basket according to any one of claims 1-7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311765462.8A CN117436712B (en) | 2023-12-21 | 2023-12-21 | Real-time monitoring method and system for operation risk of construction hanging basket |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311765462.8A CN117436712B (en) | 2023-12-21 | 2023-12-21 | Real-time monitoring method and system for operation risk of construction hanging basket |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117436712A true CN117436712A (en) | 2024-01-23 |
| CN117436712B CN117436712B (en) | 2024-04-12 |
Family
ID=89548393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311765462.8A Active CN117436712B (en) | 2023-12-21 | 2023-12-21 | Real-time monitoring method and system for operation risk of construction hanging basket |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436712B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080027716A1 (en) * | 2006-07-31 | 2008-01-31 | Vivek Rajendran | Systems, methods, and apparatus for signal change detection |
| US7587374B1 (en) * | 2006-03-20 | 2009-09-08 | The United States Of America As Represented By The Secretary Of The Navy | Data clustering method for bayesian data reduction |
| CN102736558A (en) * | 2011-04-07 | 2012-10-17 | 姚晓栋 | Numerical control machine tool thermal error real-time compensation modeling method based on time series algorithm |
| CN104268658A (en) * | 2014-09-29 | 2015-01-07 | 招商局重庆交通科研设计院有限公司 | Bridge structure safety monitoring data prediction method |
| CN110070202A (en) * | 2019-02-19 | 2019-07-30 | 浙江华云信息科技有限公司 | A method of economic output is predicted by electricity consumption data |
| CN112508275A (en) * | 2020-12-07 | 2021-03-16 | 国网湖南省电力有限公司 | Power distribution network line load prediction method and equipment based on clustering and trend indexes |
| KR20210058468A (en) * | 2019-11-14 | 2021-05-24 | 한국전자통신연구원 | Apparatus and method for artificial intelligence operator support system of intelligent edge networking |
| CN113065702A (en) * | 2021-03-31 | 2021-07-02 | 中国地质大学（武汉） | Landslide displacement multi-linear prediction method based on ST-SEEP segmentation method and space-time ARMA model |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN114429240A (en) * | 2021-12-21 | 2022-05-03 | 浙江永基智能科技有限公司 | Method and device for monitoring running state of highway equipment |
| CN218297156U (en) * | 2022-08-30 | 2023-01-13 | 重庆中科旭峰智能科技有限公司 | Monitoring and alarming device for inclination of hanging basket |
| CN115690039A (en) * | 2022-10-28 | 2023-02-03 | 武汉武岩消防科技有限公司 | Substation engineering construction site key point operation safety monitoring and control method |
| CN115726814A (en) * | 2022-10-31 | 2023-03-03 | 山东铁鹰建设工程有限公司 | Intelligent control method and system for tunnel lining trolley |
| CN116383450A (en) * | 2023-06-05 | 2023-07-04 | 沧州中铁装备制造材料有限公司 | Railway and highway logistics transportation information comprehensive management system |
| CN116449759A (en) * | 2023-05-15 | 2023-07-18 | 广东省第五建筑工程有限公司 | Intelligent monitoring method and intelligent monitoring system for building hanging basket |
| CN116545954A (en) * | 2023-07-06 | 2023-08-04 | 浙江赫斯电气有限公司 | Communication gateway data transmission method and system based on Internet of things |
| CN117056813A (en) * | 2023-10-11 | 2023-11-14 | 国网山东省电力公司营销服务中心(计量中心) | Detection method for intelligent circuit breaker data acquisition |
-
2023
- 2023-12-21 CN CN202311765462.8A patent/CN117436712B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7587374B1 (en) * | 2006-03-20 | 2009-09-08 | The United States Of America As Represented By The Secretary Of The Navy | Data clustering method for bayesian data reduction |
| US20080027716A1 (en) * | 2006-07-31 | 2008-01-31 | Vivek Rajendran | Systems, methods, and apparatus for signal change detection |
| CN102736558A (en) * | 2011-04-07 | 2012-10-17 | 姚晓栋 | Numerical control machine tool thermal error real-time compensation modeling method based on time series algorithm |
| CN104268658A (en) * | 2014-09-29 | 2015-01-07 | 招商局重庆交通科研设计院有限公司 | Bridge structure safety monitoring data prediction method |
| CN110070202A (en) * | 2019-02-19 | 2019-07-30 | 浙江华云信息科技有限公司 | A method of economic output is predicted by electricity consumption data |
| KR20210058468A (en) * | 2019-11-14 | 2021-05-24 | 한국전자통신연구원 | Apparatus and method for artificial intelligence operator support system of intelligent edge networking |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN112508275A (en) * | 2020-12-07 | 2021-03-16 | 国网湖南省电力有限公司 | Power distribution network line load prediction method and equipment based on clustering and trend indexes |
| CN113065702A (en) * | 2021-03-31 | 2021-07-02 | 中国地质大学（武汉） | Landslide displacement multi-linear prediction method based on ST-SEEP segmentation method and space-time ARMA model |
| CN114429240A (en) * | 2021-12-21 | 2022-05-03 | 浙江永基智能科技有限公司 | Method and device for monitoring running state of highway equipment |
| CN218297156U (en) * | 2022-08-30 | 2023-01-13 | 重庆中科旭峰智能科技有限公司 | Monitoring and alarming device for inclination of hanging basket |
| CN115690039A (en) * | 2022-10-28 | 2023-02-03 | 武汉武岩消防科技有限公司 | Substation engineering construction site key point operation safety monitoring and control method |
| CN115726814A (en) * | 2022-10-31 | 2023-03-03 | 山东铁鹰建设工程有限公司 | Intelligent control method and system for tunnel lining trolley |
| CN116449759A (en) * | 2023-05-15 | 2023-07-18 | 广东省第五建筑工程有限公司 | Intelligent monitoring method and intelligent monitoring system for building hanging basket |
| CN116383450A (en) * | 2023-06-05 | 2023-07-04 | 沧州中铁装备制造材料有限公司 | Railway and highway logistics transportation information comprehensive management system |
| CN116545954A (en) * | 2023-07-06 | 2023-08-04 | 浙江赫斯电气有限公司 | Communication gateway data transmission method and system based on Internet of things |
| CN117056813A (en) * | 2023-10-11 | 2023-11-14 | 国网山东省电力公司营销服务中心(计量中心) | Detection method for intelligent circuit breaker data acquisition |
Non-Patent Citations (3)
| Title |
|---|
| ZHU, Y等: "Temperature prediction of aluminum reduction cell based on integration of dual attention LSTM for non-stationary sub-sequence and ARMA for stationary sub-sequences", 《CONTROL ENGINEERING PRACTICE》, no. 138, 20 June 2023 (2023-06-20), pages 1 - 10 * |
| 张琴: "时间序列聚类在学习行为分析上的应用研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 01, 15 January 2021 (2021-01-15), pages 002 - 1106 * |
| 赵炜;屈兵;肖汝诚;: "基于季节ARIMA模型的桥梁退化预测分析", 上海公路, no. 03, 30 September 2015 (2015-09-30), pages 31 - 35 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117436712B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112188531B (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| US10496466B2 (en) | Preprocessor of abnormality sign diagnosing device and processing method of the same | |
| CN111538311B (en) | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining | |
| EP3361459B1 (en) | Method, apparatus and system for passive infrared sensor framework | |
| CN109067722A (en) | A kind of LDoS detection method based on two steps cluster and detection lug analysis joint algorithm | |
| CN117312997B (en) | Intelligent diagnosis method and system for power management system | |
| CN117113729B (en) | Digital twinning-based power equipment online state monitoring system | |
| CN111782484B (en) | Anomaly detection method and device | |
| CN114422184A (en) | Network security attack type and threat level prediction method based on machine learning | |
| CN116595426B (en) | Industrial Internet of things data intelligent acquisition management system | |
| CN116823227A (en) | Intelligent equipment management system and method based on Internet of things | |
| CN115858794B (en) | Abnormal log data identification method for network operation safety monitoring | |
| CN110956331A (en) | Method, system and device for predicting operation state of digital factory | |
| CN117076869B (en) | Time-frequency domain fusion fault diagnosis method and system for rotary machine | |
| CN117436712B (en) | Real-time monitoring method and system for operation risk of construction hanging basket | |
| JP2020123094A (en) | Sound generator, data generator, abnormality level calculator, index value calculator, and program | |
| US11847619B2 (en) | System-state monitoring method and device and storage medium | |
| KR102051227B1 (en) | Predictive diagnosis method and system of nuclear power plant equipment | |
| CN114758470B (en) | Fire early warning method and system based on fire engineering | |
| CN110662220A (en) | Wireless sensor network anomaly detection method based on time-space correlation and information entropy | |
| US20230297095A1 (en) | Monitoring device and method for detecting anomalies | |
| CN108761250A (en) | A kind of intrusion detection method based on industrial control equipment voltage and current | |
| CN111382946B (en) | Autonomous evaluation method and system for health state of equipment and industrial internet equipment | |
| KR102028845B1 (en) | Predictive diagnosis method and system of nuclear power plant equipment | |
| CN117688464B (en) | Hidden danger analysis method and system based on multi-source sensor data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |