CN116881673B - Shield tunneling machine operation and maintenance method based on big data analysis - Google Patents
Shield tunneling machine operation and maintenance method based on big data analysis Download PDFInfo
- Publication number
- CN116881673B CN116881673B CN202311139849.2A CN202311139849A CN116881673B CN 116881673 B CN116881673 B CN 116881673B CN 202311139849 A CN202311139849 A CN 202311139849A CN 116881673 B CN116881673 B CN 116881673B
- Authority
- CN
- China
- Prior art keywords
- data
- acquisition
- time period
- current time
- operation data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000005641 tunneling Effects 0.000 title claims abstract description 22
- 238000007405 data analysis Methods 0.000 title claims abstract description 21
- 238000012423 maintenance Methods 0.000 title claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 230000008569 process Effects 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 12
- 230000008859 change Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/003—Arrangement of measuring or indicating devices for use during driving of tunnels, e.g. for guiding machines
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/06—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geochemistry & Mineralogy (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of electric digital data processing, in particular to a shield tunneling machine operation and maintenance method based on big data analysis. The method comprises the following steps: acquiring operation data of each acquisition moment in the current time period in the operation process of the shield machine; obtaining the fluctuation degree of the data according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data; obtaining a weight of the fluctuation degree of the data based on the acquisition frequency of the operation data in the current time period; obtaining a data value evaluation index based on the data fluctuation degree and the weight; acquiring the adjusted acquisition frequency according to the data value evaluation index; and acquiring the operation data of the shield machine in a future time period by utilizing the adjusted acquisition frequency, and further judging whether to perform early warning. The method saves the time for analyzing the abnormality of the shield machine operation data and the storage space of the operation data, and improves the reliability of abnormality early warning.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a shield tunneling machine operation and maintenance method based on big data analysis.
Background
The shield machine is used as underground engineering construction equipment and plays an important role in projects such as urban subways, tunnels and the like. However, the shield tunneling machine may have some problems in operation and maintenance, such as equipment failure. In order to improve the operation and maintenance efficiency of the shield machine and reduce the operation and maintenance cost, the operation state of the shield machine needs to be monitored to judge whether the abnormal condition exists.
In the conventional abnormality analysis of the equipment of the shield machine, data in the running process of the shield machine is generally collected in real time by using a sensor, and the collected data is stored, so that the abnormality analysis is performed. In the prior art, the fixed acquisition frequency is generally set to acquire the operation data in the operation process of the shield machine, and all the acquired operation data are stored and analyzed, however, in the operation process of the shield machine, the acquired data are mostly normal data due to smaller fault probability, the information value of the normal data is smaller, the occupied space is larger when the normal data are stored, the analysis time is more, the analysis efficiency is lower, and therefore, how to adaptively adjust the acquisition frequency of the operation data of the shield machine based on the abnormal condition of the operation data of the shield machine is an urgent problem to be solved.
Disclosure of Invention
In order to solve the problems that the existing method cannot adaptively determine the acquisition frequency of the shield machine operation data, and further the acquired operation data occupy a larger storage space and have lower analysis efficiency, the invention aims to provide a shield machine operation and maintenance method based on big data analysis, and the adopted technical scheme is as follows:
the invention provides a shield tunneling machine operation and maintenance method based on big data analysis, which comprises the following steps:
acquiring operation data of each acquisition moment in the current time period in the operation process of the shield machine;
obtaining the fluctuation degree of the data according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data; obtaining a weight of the fluctuation degree of the data based on the acquisition frequency of the operation data in the current time period; obtaining a data value evaluation index based on the data fluctuation degree and the weight;
adjusting the acquisition frequency of the operation data according to the data value evaluation index to obtain an adjusted acquisition frequency; acquiring the operation data of the shield machine in a future time period by utilizing the adjusted acquisition frequency;
judging whether to perform early warning according to the difference condition of the operation data of the shield machine in a future time period.
Preferably, the obtaining the data fluctuation degree according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data includes:
respectively calculating the product of the time difference between each acquisition time and the last acquisition time and a preset first super parameter to be used as a first product corresponding to each acquisition time; determining the negative correlation normalization result of the first product as a first characteristic value of each acquisition moment; wherein the preset first super parameter is greater than 0;
calculating the average value of the running data at all the acquisition moments in the current time period; respectively determining squares of differences between running data of all the acquisition moments and the average value of the running data in the current time period as data differences of all the acquisition moments;
and obtaining the data fluctuation degree according to the first characteristic values of all the acquisition moments in the current time period and the data difference.
Preferably, the degree of fluctuation of the data is calculated using the following formula:
wherein M is the fluctuation degree of data, n is the total number of acquisition moments in the current time period,for the nth acquisition instant in the current time period, < >>For the i-th acquisition time in the current time period, < >>For presetting a first superparameter->For the operation data of the ith acquisition time in the current time period,/or->The exp () is an exponential function based on a natural constant, and e is a natural constant, which is the average value of running data at all acquisition moments in the current time period.
Preferably, the obtaining the weight of the data fluctuation degree based on the collection frequency of the operation data in the current time period includes:
recording the product of the acquisition frequency of the operation data in the current time period and a preset second super parameter as a second product; wherein the preset second super parameter is greater than 0;
and determining the negative correlation normalization result of the second product as a weight of the fluctuation degree of the data.
Preferably, the obtaining the data value evaluation index based on the data fluctuation degree and the weight value includes:
recording the product of the data fluctuation degree and the weight as a third product;
and calculating a negative correlation normalization result of the third product, and determining a difference value between a constant 1 and the normalization result as a data value evaluation index.
Preferably, the adjusting the collection frequency of the operation data according to the data value evaluation index to obtain an adjusted collection frequency includes:
calculating the ratio of the data value evaluation index to a preset third super parameter, and recording the difference value between the ratio and a constant 1 as a second characteristic value; wherein a third super parameter is preset to be larger than 0;
and obtaining an adjusted acquisition frequency according to the second characteristic value and the acquisition frequency of the operation data in the current time period, wherein the second characteristic value and the acquisition frequency of the operation data in the current time period are in positive correlation with the adjusted acquisition frequency.
Preferably, the obtaining the adjusted collection frequency according to the second characteristic value and the collection frequency of the operation data in the current time period includes:
taking a value of an exponential function taking the natural constant as a base and the second characteristic value as an index as an adjustment coefficient;
and determining the upward rounded value of the product of the acquisition frequency of the operation data in the current time period and the adjustment coefficient as the adjusted acquisition frequency.
Preferably, the judging whether to perform early warning according to the difference condition of the operation data of the shield machine in the future time period includes:
obtaining the data abnormality degree according to the difference condition of the operation data of the shield machine in the future time period;
judging whether to perform abnormal early warning on the shield machine or not based on the data abnormality degree.
Preferably, the obtaining the data anomaly degree according to the difference condition of the operation data of the shield tunneling machine in the future time period includes:
calculating variances of the operation data of the shield machine at all the acquisition moments in a future time period;
and obtaining the data abnormality degree according to the variance, wherein the variance and the data abnormality degree are in positive correlation.
Preferably, judging whether to perform abnormality pre-warning on the shield machine based on the data abnormality degree includes:
judging whether the data abnormality degree is larger than a preset abnormality degree threshold value, and if so, carrying out abnormality early warning on the shield machine; if the detected value is less than or equal to the preset value, the shield machine is not subjected to abnormal early warning.
The invention has at least the following beneficial effects:
the invention considers that the acquisition frequency of the traditional method is always fixed when the shield machine operation data is acquired, however, in the shield machine operation process, the acquired data is mostly normal data because the probability of the shield machine faults is smaller, the information value of the normal data is smaller, the occupied space is larger when the normal data is stored, and the analysis efficiency is lower when the normal data is analyzed, so the invention obtains the data fluctuation degree according to the time difference between each acquisition time and the last acquisition time and the difference of the operation data in the current time period, obtains the weight of the data fluctuation degree based on the acquisition frequency of the operation data in the current time period, further obtains the data value evaluation index, and the fluctuation degree of the operation data of the shield machine in the current time period is larger, the method and the device have the advantages that the more likely to be abnormal, when the shield machine is abnormal, the analysis value of the operation data is higher, so that the acquisition frequency of the operation data is adjusted according to the data value evaluation index to obtain the adjusted acquisition frequency, namely, the acquisition frequency of the operation data is adaptively determined, the operation data of the shield machine in a future time period is acquired based on the adjusted acquisition frequency, the acquisition frequency of the operation data with higher data value is improved, the acquisition frequency of the operation data with lower data value is reduced, the more abnormal operation data is obtained, the more frequent acquisition of the operation data is ensured, the useful data is not lost, the unnecessary calculation amount is reduced, the time for abnormal analysis of the operation data of the shield machine and the storage space of the operation data are saved, and the reliability of shield machine early warning is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a shield tunneling machine operation and maintenance method based on big data analysis according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a shield machine operation and maintenance method based on big data analysis according to the invention with reference to the attached drawings and the preferred embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a concrete scheme of a shield machine operation and maintenance method based on big data analysis, which is specifically described below with reference to the accompanying drawings.
The shield machine operation and maintenance method based on big data analysis is implemented:
the specific scene aimed at by this embodiment is: in the operation process of the shield machine, an abnormal phenomenon may occur, when the shield machine is abnormal, early warning needs to be performed in time to remind workers to overhaul in time, the service life of the shield machine is prolonged, meanwhile, the follow-up working efficiency is guaranteed, the operation state of the shield machine is judged by analyzing the change condition of the operation data in the operation process of the shield machine, the operation data in the operation process of the shield machine is collected by considering that the conventional method generally sets fixed collection frequency, but the failure probability is smaller in the operation process of the shield machine, therefore, the collected data are mostly normal data, the information value of the normal data is smaller, the occupied space is larger when the normal data are stored, the consumption time is more when the normal data are analyzed, therefore, the embodiment is based on the fluctuation condition of the operation data of the shield machine in the current time period, the collection frequency of the operation data is adjusted, the operation data of the shield machine is collected by using the adjusted collection frequency, the more frequently the operation data are collected, the useful data are not lost, and meanwhile, the storage space of the reliability of the shield machine is also saved.
The embodiment provides a shield tunneling machine operation and maintenance method based on big data analysis, as shown in fig. 1, the shield tunneling machine operation and maintenance method based on big data analysis of the embodiment comprises the following steps:
step S1, acquiring operation data of each acquisition moment in the current time period in the operation process of the shield machine.
The method comprises the steps that firstly, operation data of a shield machine in a current time period are obtained, the operation data comprise pressure, temperature and vibration frequency, specifically, a pressure sensor, a temperature sensor and a vibration sensor are installed on shield machine equipment, the pressure sensor is used for collecting the pressure data in the operation process of the shield machine, the temperature sensor is used for collecting the temperature data in the operation process of the shield machine, the vibration sensor is used for collecting the vibration data in the operation process of the shield machine, the collection frequency of the operation data of the shield machine in the current time period is set to be 1Hz, namely, the operation data are collected once per second, and in specific application, an implementer can set according to specific conditions. The current time period is a set formed by all historical time points with time intervals smaller than or equal to the preset time length from the current time point, and the preset time length is 1 hour in the embodiment, so that the current time period in the embodiment is the last hour, and in specific application, an implementer can set the preset time length according to specific conditions.
So far, the embodiment obtains the operation data of each acquisition time in the current time period in the operation process of the shield machine, and obtains the operation data to reflect the operation state of the shield machine.
Step S2, obtaining the fluctuation degree of the data according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data; obtaining a weight of the fluctuation degree of the data based on the acquisition frequency of the operation data in the current time period; and obtaining a data value evaluation index based on the data fluctuation degree and the weight.
In the embodiment, the operation data of the shield machine at each acquisition time in the current time period are acquired, the probability of faults of the shield machine is small in the operation process of the shield machine, and most of the acquired data are normal data. Whereas normal data is usually recurring and does not fluctuate significantly. Therefore, the normal data cannot provide more effective information of the running state of the equipment, the data value of the normal data is low, and the collected data with low value also occupies a large amount of storage space, so that the analysis time of the data is increased. The fluctuation condition of the operation data in the normal operation process of the shield machine is small, and if the shield machine fails, the operation data can generate larger fluctuation. In the operation process of the shield machine, the data volume of the collected operation data is large, most of the collected operation data is normal data, the normal data cannot reflect the abnormal operation state of the shield machine equipment, and the shield machine equipment abnormality is usually reflected by the abnormal operation data. Therefore, the value of normal data is smaller, and the value of abnormal data is larger. In the operation process of the shield tunneling machine equipment, normal data usually have certain regularity and stability, namely the normal data have certain degree of regularity fluctuation. Therefore, the embodiment analyzes the fluctuation condition of the acquired operation data in the current time period, calculates the data value evaluation index of the shield machine operation data in the current time period based on the fluctuation condition, adjusts the acquisition frequency of the shield machine operation data in the future time period based on the data value evaluation index, and reduces the acquisition frequency of the part with lower data value, so that a great amount of data analysis time is saved and the analysis efficiency is improved on the basis of ensuring more accurate analysis results.
The fluctuation degree of the data may have small change along with the change of time, so when analyzing the overall fluctuation degree of the operation data in the current time period, each operation data needs to be endowed with a corresponding weight value to reduce the influence of the operation data far away from the current time on the overall fluctuation condition of all the operation data in the current time period, so that the weight value of the operation data at the collection time far away from the current time is smaller, and the overall fluctuation influence degree of all the operation data in the current time period is smaller; the weighting value of the operation data at the acquisition time which is closer to the current time is larger, and the fluctuation influence degree of the operation data on the whole of all operation data in the current time period is larger.
Specifically, the product of the time difference between each acquisition time and the last acquisition time and the preset first super parameter is calculated respectively and is used as a first product corresponding to each acquisition time; determining the negative correlation normalization result of the first product as a first characteristic value of each acquisition moment; calculating the average value of the running data at all the acquisition moments in the current time period; respectively determining squares of differences between running data of all the acquisition moments and the average value of the running data in the current time period as data differences of all the acquisition moments; and obtaining the data fluctuation degree according to the first characteristic values of all the acquisition moments in the current time period and the data difference. The specific calculation formula of the data fluctuation degree is as follows:
wherein M is the fluctuation degree of data, n is the total number of acquisition moments in the current time period,for the nth acquisition instant in the current time period, < >>For the i-th acquisition time in the current time period, < >>For presetting a first superparameter->For the operation data of the ith acquisition time in the current time period,/or->The exp () is an exponential function based on a natural constant, and e is a natural constant, which is the average value of running data at all acquisition moments in the current time period.
In this embodiment, the preset first super parameter is 0.01, and in a specific application, an implementer may set the preset first super parameter according to a specific situation, but it needs to be ensured that the preset first super parameter is greater than 0.Representing a first product corresponding to the ith acquisition moment in the current time period, +.>Representing the current time periodIn the first characteristic value of the i-th acquisition time, the first characteristic value is used as a weight value, and the larger the time interval between the acquisition time of the running data and the last acquisition time in the current time period is, the smaller the corresponding weight value is, and the smaller the influence on the overall fluctuation condition of all the running data in the current time period is; />The data difference representing the ith acquisition time is used for reflecting the difference condition between the running data of the ith acquisition time in the current time period and the average value of the running data of all the acquisition times in the current time period. If the difference between the running data of each acquisition time and the average value of the running data of all the acquisition times in the current time period is larger, the fluctuation degree of the running data in the current time period is larger; if the difference between the running data of each acquisition time and the average value of the running data of all the acquisition times in the current time period is smaller, the fluctuation degree of the running data in the current time period is smaller. It should be noted that, in this embodiment, the time difference between each collection time and the last collection time in the current period is represented by the time interval between the last collection time and other collection times in the current period, and as other embodiments, other methods may be used to represent the time difference between each collection time and the last collection time in the current period, for example: according to the time sequence, the operation data at all the acquisition moments in the current time period are arranged to obtain a corresponding operation data sequence, the difference value between the sequence number of the last operation data in the operation data sequence and the sequence number of each operation data in the operation data sequence is calculated respectively, the difference value is used for representing the time difference between each acquisition moment and the last acquisition moment in the current time period, namely the difference value is used for replacing the time difference between each acquisition moment and the last acquisition moment in the data fluctuation degree calculation formula in the embodimentAnd further obtaining the fluctuation degree of the data.
According to the embodiment, the data acquisition frequency is adaptively adjusted according to the fluctuation degree of the data, so that the acquisition frequency of the operation data is continuously changed, the more the acquisition frequency of the operation data is increased, the more frequent the data sampling is indicated, the more frequent the acquisition frequency of the operation data is, the smaller the time interval between samples is, and the more obvious the detail change of the data is; the less frequent the acquisition frequency of the operation data is, the larger the time interval between samples is, the less obvious the detail change of the data is, therefore, the fluctuation degree of the operation data needs to be given with a weight according to the different acquisition frequencies of the operation data, the less frequent data acquisition weight is larger, the detail change is amplified, and the influence caused by the different acquisition frequencies of the operation data is avoided.
Specifically, the product of the acquisition frequency of the operation data in the current time period and a preset second super parameter is recorded as a second product; and determining the negative correlation normalization result of the second product as a weight of the fluctuation degree of the data. The specific calculation formula of the weight of the data fluctuation degree is as follows:
wherein P is a weight of the degree of fluctuation of the data,for presetting a second superparameter->E is a natural constant, which is the acquisition frequency of the operation data in the current time period.
Representing a second product. In this embodiment, the preset second super-parameter is 0.01, and in a specific application, an implementer may set the preset second super-parameter according to a specific situation, but it needs to be ensured that the preset second super-parameter is greater than 0. The larger the acquisition frequency of the shield machine operation data in the current time period is, the smaller the weight of the data fluctuation degree is; the smaller the acquisition frequency of the shield machine operation data in the current time period is, the larger the weight of the data fluctuation degree is.
So far, the embodiment obtains the data fluctuation degree and the weight of the data fluctuation degree, and when the data fluctuation degree is larger and the corresponding weight is also larger, the shield machine is more likely to have abnormal operation in the current time period, so that the operation data of the shield machine is more important, namely the evaluation value of the operation data of the shield machine in the current time period is higher, the acquisition frequency of the operation data needs to be increased at the moment, and the operation state of the shield machine can be reflected more accurately by the operation data acquired later. Based on this, the present embodiment will determine the data value evaluation index from the data fluctuation degree and the weight of the data fluctuation degree.
Specifically, the product of the degree of fluctuation of the data and the weight is recorded as a third product; and calculating a negative correlation normalization result of the third product, and determining a difference value between a constant 1 and the normalization result as a data value evaluation index. The specific calculation formula of the data value evaluation index is as follows:
wherein V is a data value evaluation index.
The larger the data fluctuation degree is and the larger the weight of the data fluctuation degree is, the higher the abnormal degree of the data is, the higher the probability of the shield machine to fail is, and the attention degree of the operation data in the future time period needs to be improved, namely the acquisition frequency of the operation data is improved; the smaller the data fluctuation degree and the smaller the weight of the data fluctuation degree, the lower the abnormal degree of the operation data is, the lower the probability of the fault of the shield machine is, the less the attention to the operation data in the future time period is, and the acquisition frequency of the operation data can be properly reduced.
So far, the method provided by the embodiment is adopted to obtain the data value evaluation index.
Step S3, adjusting the acquisition frequency of the operation data according to the data value evaluation index to obtain an adjusted acquisition frequency; and acquiring the operation data of the shield machine in a future time period by utilizing the adjusted acquisition frequency.
The embodiment has obtained the data value evaluation index, the greater the abnormal degree of the operation data is, the more system faults are easily caused, the higher the attention degree is needed, and the acquisition frequency of the operation data is improved, so the embodiment adjusts the acquisition frequency of the operation data according to the data value evaluation index to obtain the adjusted acquisition frequency.
Specifically, calculating the ratio of the data value evaluation index to a preset third super parameter, and recording the difference value between the ratio and a constant 1 as a second characteristic value; wherein a third super parameter is preset to be larger than 0; obtaining an adjusted acquisition frequency according to the second characteristic value and the acquisition frequency of the operation data in the current time period, wherein the second characteristic value and the acquisition frequency of the operation data in the current time period are in positive correlation with the adjusted acquisition frequency; in this embodiment, the value of the exponential function with the natural constant as a base and the second eigenvalue as an exponent is used as an adjustment coefficient; and determining the upward rounded value of the product of the acquisition frequency of the operation data in the current time period and the adjustment coefficient as the adjusted acquisition frequency. The specific calculation formula of the adjusted acquisition frequency is as follows:
wherein,for the adjusted acquisition frequency +.>For the sensor acquisition frequency before adjustment, V is a data value evaluation index, < + >>For presetting a third super parameter->To round the symbol up.
The value of the preset third super parameter in this embodiment is 0.5, and in a specific application, the practitioner can set the value according to the specific situation.Representing the second characteristic value. When the data value evaluation index is larger, the attention of the operation data is increased, namely the acquisition frequency of the operation data is reduced, and the calculated second characteristic value is larger, which means that the acquisition frequency of the operation data needs to be increased more; when the data value evaluation index is smaller, the attention of the operation data should be reduced, namely, the acquisition frequency of the operation data is reduced, and the smaller the calculated second characteristic value is, the more the acquisition frequency of the operation data needs to be reduced.
By adopting the method, the adjusted acquisition frequency is obtained, and the operation data of the shield machine at each acquisition time in a future time period is acquired by using the adjusted acquisition frequency, wherein the future time period in the embodiment is a set formed by all future time with a time interval smaller than a preset time length from the current time, and the preset time length is still 1 hour, so that the future time period in the embodiment is one hour after the current time, and in specific application, an implementer can set according to specific situations.
By adopting the method provided by the embodiment, the operation data of the shield machine at each acquisition time in the future time period can be acquired.
And S4, judging whether to perform early warning according to the difference condition of the operation data of the shield machine in the future time period.
The method provided by the embodiment can obtain the operation data of the shield machine at each acquisition time in the future time period, and the larger the difference between the operation data of the shield machine in the future time period is, the more abnormal the operation data is indicated, so that the embodiment can determine the degree of data abnormality based on the difference condition of the operation data of the shield machine in the future time period, and further judge whether the operation state of the shield machine is abnormal or not according to the degree of data abnormality.
Specifically, the variance of the operation data of the shield machine at all the acquisition time in the future time period is calculated, the data abnormality degree is obtained according to the variance, and the variance and the data abnormality degree are in positive correlation. As a specific embodiment, a calculation formula of the degree of data abnormality is given, where the specific calculation formula of the degree of data abnormality is:
wherein C is the degree of data abnormality, m is the total number of acquisition moments in a future time period,for the operation data of the j-th acquisition time in the future time period,/for the time of the j-th acquisition>For the mean value of the running data at all acquisition times in the future time period, exp () is an exponential function based on a natural constant.
The greater the data abnormality degree is, the more likely the abnormality occurs in the operation state of the shield machine, so the embodiment will judge the operation state of the shield machine based on the magnitude relation between the data abnormality degree and the preset abnormality degree. Specifically, judging whether the data abnormality degree is greater than a preset abnormality degree threshold value, if so, indicating that the running state of the shield machine is abnormal, and carrying out abnormality early warning on the shield machine to remind a worker of timely overhauling; if the operation state of the shield machine is smaller than or equal to the operation state, the operation state of the shield machine is not abnormal, and the shield machine is not subjected to abnormal early warning. The preset degree of abnormality in the present embodiment is 0.5, and in a specific application, the practitioner can set according to the specific situation.
So far, by adopting the method provided by the embodiment, the intelligent monitoring of the running state of the shield machine is completed.
In the embodiment, the acquisition frequency of the traditional method is always fixed when the shield machine is used for acquiring the operation data of the shield machine, however, in the operation process of the shield machine, the probability of occurrence of faults of the shield machine is smaller, so that most of acquired data is normal data, the information value of the normal data is smaller, the occupied space is larger when the normal data is stored, and the analysis efficiency is lower when the normal data is analyzed.
It should be noted that: the foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. The shield tunneling machine operation and maintenance method based on big data analysis is characterized by comprising the following steps of:
acquiring operation data of each acquisition moment in the current time period in the operation process of the shield machine;
obtaining the fluctuation degree of the data according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data; obtaining a weight of the fluctuation degree of the data based on the acquisition frequency of the operation data in the current time period; obtaining a data value evaluation index based on the data fluctuation degree and the weight;
adjusting the acquisition frequency of the operation data according to the data value evaluation index to obtain an adjusted acquisition frequency; acquiring the operation data of the shield machine in a future time period by utilizing the adjusted acquisition frequency;
judging whether to perform early warning according to the difference condition of the operation data of the shield machine in a future time period;
the obtaining the data fluctuation degree according to the time difference between each acquisition time and the last acquisition time in the current time period and the difference of the operation data comprises the following steps:
respectively calculating the product of the time difference between each acquisition time and the last acquisition time and a preset first super parameter to be used as a first product corresponding to each acquisition time; determining the negative correlation normalization result of the first product as a first characteristic value of each acquisition moment; wherein the preset first super parameter is greater than 0;
calculating the average value of the running data at all the acquisition moments in the current time period; respectively determining squares of differences between running data of all the acquisition moments and the average value of the running data in the current time period as data differences of all the acquisition moments;
obtaining the fluctuation degree of the data according to the first characteristic values of all the acquisition moments in the current time period and the data difference;
the degree of fluctuation of the data is calculated using the following formula:
wherein M is the fluctuation degree of data, n is the total number of acquisition moments in the current time period,for the nth acquisition instant in the current time period, < >>For the i-th acquisition time in the current time period, < >>For presetting a first superparameter->For the operation data of the ith acquisition time in the current time period,/or->The exp () is an exponential function based on a natural constant, and e is a natural constant, which is the average value of running data at all acquisition moments in the current time period.
2. The method for operating and maintaining the shield tunneling machine based on big data analysis according to claim 1, wherein said obtaining the weight of the fluctuation degree of the data based on the collection frequency of the operation data in the current time period comprises:
recording the product of the acquisition frequency of the operation data in the current time period and a preset second super parameter as a second product; wherein the preset second super parameter is greater than 0;
and determining the negative correlation normalization result of the second product as a weight of the fluctuation degree of the data.
3. The method for operating and maintaining a shield tunneling machine based on big data analysis according to claim 1, wherein said obtaining a data value evaluation index based on the degree of fluctuation of the data and the weight comprises:
recording the product of the data fluctuation degree and the weight as a third product;
and calculating a negative correlation normalization result of the third product, and determining a difference value between a constant 1 and the normalization result as a data value evaluation index.
4. The method for operating and maintaining the shield tunneling machine based on big data analysis according to claim 1, wherein said adjusting the collection frequency of the operation data according to the data value evaluation index to obtain the adjusted collection frequency comprises:
calculating the ratio of the data value evaluation index to a preset third super parameter, and recording the difference value between the ratio and a constant 1 as a second characteristic value; wherein a third super parameter is preset to be larger than 0;
and obtaining an adjusted acquisition frequency according to the second characteristic value and the acquisition frequency of the operation data in the current time period, wherein the second characteristic value and the acquisition frequency of the operation data in the current time period are in positive correlation with the adjusted acquisition frequency.
5. The method for operating and maintaining the shield tunneling machine based on big data analysis according to claim 4, wherein obtaining the adjusted acquisition frequency according to the second characteristic value and the acquisition frequency of the operation data in the current time period comprises:
taking a value of an exponential function taking the natural constant as a base and the second characteristic value as an index as an adjustment coefficient;
and determining the upward rounded value of the product of the acquisition frequency of the operation data in the current time period and the adjustment coefficient as the adjusted acquisition frequency.
6. The method for operating and maintaining the shield tunneling machine based on big data analysis according to claim 1, wherein the judging whether to perform early warning according to the difference condition of the operating data of the shield tunneling machine in the future time period comprises:
obtaining the data abnormality degree according to the difference condition of the operation data of the shield machine in the future time period;
judging whether to perform abnormal early warning on the shield machine or not based on the data abnormality degree.
7. The method for operating and maintaining the shield tunneling machine based on big data analysis according to claim 6, wherein the obtaining the degree of data anomaly according to the difference of the operating data of the shield tunneling machine in the future time period comprises:
calculating variances of the operation data of the shield machine at all the acquisition moments in a future time period;
and obtaining the data abnormality degree according to the variance, wherein the variance and the data abnormality degree are in positive correlation.
8. The method for operating and maintaining a shield tunneling machine based on big data analysis according to claim 6, wherein determining whether to perform abnormality pre-warning on the shield tunneling machine based on the degree of abnormality of the data comprises:
judging whether the data abnormality degree is larger than a preset abnormality degree threshold value, and if so, carrying out abnormality early warning on the shield machine; if the detected value is less than or equal to the preset value, the shield machine is not subjected to abnormal early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311139849.2A CN116881673B (en) | 2023-09-06 | 2023-09-06 | Shield tunneling machine operation and maintenance method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311139849.2A CN116881673B (en) | 2023-09-06 | 2023-09-06 | Shield tunneling machine operation and maintenance method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116881673A CN116881673A (en) | 2023-10-13 |
| CN116881673B true CN116881673B (en) | 2023-12-19 |
Family
ID=88260881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311139849.2A Active CN116881673B (en) | 2023-09-06 | 2023-09-06 | Shield tunneling machine operation and maintenance method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116881673B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117108294B (en) * | 2023-10-16 | 2024-01-12 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Intelligent monitoring system for faults of shield tunneling machine |
| CN117423225B (en) * | 2023-10-23 | 2024-09-06 | 东华理工大学 | Disaster remote sensing early warning system based on high-speed railway operation |
| CN118033409B (en) * | 2024-04-15 | 2024-06-14 | 三峡金沙江川云水电开发有限公司 | GCB arc extinguishing chamber switch resistance testing method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358347A (en) * | 2017-07-05 | 2017-11-17 | 西安电子科技大学 | Equipment cluster health state evaluation method based on industrial big data |
| CN109779649A (en) * | 2019-02-13 | 2019-05-21 | 上海大学 | Shield driving axis real-time deviation correcting system and method based on big data |
| WO2021115116A1 (en) * | 2019-12-13 | 2021-06-17 | 中兴通讯股份有限公司 | Early-warning method and apparatus for performance indicator, and device and storage medium |
| CN116579663A (en) * | 2023-07-05 | 2023-08-11 | 江苏慧远智能科技有限公司 | Abnormal early warning method in unloading process of powder tank truck |
| CN116701973A (en) * | 2023-08-09 | 2023-09-05 | 无锡市明通动力工业有限公司 | Motor abnormal vibration detection early warning method based on big data |
-
2023
- 2023-09-06 CN CN202311139849.2A patent/CN116881673B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358347A (en) * | 2017-07-05 | 2017-11-17 | 西安电子科技大学 | Equipment cluster health state evaluation method based on industrial big data |
| CN109779649A (en) * | 2019-02-13 | 2019-05-21 | 上海大学 | Shield driving axis real-time deviation correcting system and method based on big data |
| WO2021115116A1 (en) * | 2019-12-13 | 2021-06-17 | 中兴通讯股份有限公司 | Early-warning method and apparatus for performance indicator, and device and storage medium |
| CN116579663A (en) * | 2023-07-05 | 2023-08-11 | 江苏慧远智能科技有限公司 | Abnormal early warning method in unloading process of powder tank truck |
| CN116701973A (en) * | 2023-08-09 | 2023-09-05 | 无锡市明通动力工业有限公司 | Motor abnormal vibration detection early warning method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 盾构施工大数据异常检测的研究与应用;李刚;陈刚;;中国市政工程(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116881673A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116881673B (en) | Shield tunneling machine operation and maintenance method based on big data analysis | |
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| CN112580961B (en) | Power grid information system based operation risk early warning method and device | |
| CN117093879A (en) | Intelligent operation management method and system for data center | |
| CN117407700B (en) | Method for monitoring working environment in live working process | |
| CN117195018B (en) | Mining water pump intelligent monitoring system based on multiple sensors | |
| KR102126577B1 (en) | A Monitoring System of Photovoltaic Generation Using Multi-channel Module Sensors | |
| CN117290802B (en) | Host power supply operation monitoring method based on data processing | |
| CN110866616A (en) | Fault early warning method and device for secondary equipment of transformer substation | |
| EP3309682A1 (en) | Data collection system and method, and method for reducing the quantity of measurement data | |
| CN110569248A (en) | Improved SPC (selective pressure control) residential water supply leakage monitoring and early warning method | |
| CN115220396B (en) | Intelligent monitoring method and system for numerical control machine tool | |
| CN117423225B (en) | Disaster remote sensing early warning system based on high-speed railway operation | |
| CN112710474A (en) | Diesel engine state evaluation method based on real-time vibration data | |
| CN118019190B (en) | Intelligent lighting system based on pedestrian perception | |
| CN115800552A (en) | Intelligent regulation and control system and method for super capacitor operation power frequency modulation | |
| CN113092152B (en) | Composite monitoring device and method for vibration temperature of mobile equipment | |
| CN116071053B (en) | Reciprocating compressor state early warning system based on digital twinning | |
| CN114662058B (en) | Wireless station monitoring method and device | |
| CN112415168B (en) | Water quality monitoring management system based on internet | |
| CN101923605B (en) | Wind pre-warning method for railway disaster prevention | |
| CN113513304A (en) | Balance degree detection method based on electric diagram of pumping unit | |
| CN117536691B (en) | Fully-mechanized coal mining face equipment parameter monitoring method and system | |
| CN118604532B (en) | Fault analysis-based power distribution network fault positioning method and system | |
| CN118296666B (en) | Data storage early warning method and system for information system |
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 |