CN114386451B - Contact net hanger fault diagnosis alarm method based on sensor information perception - Google Patents
Contact net hanger fault diagnosis alarm method based on sensor information perception Download PDFInfo
- Publication number
- CN114386451B CN114386451B CN202111474206.4A CN202111474206A CN114386451B CN 114386451 B CN114386451 B CN 114386451B CN 202111474206 A CN202111474206 A CN 202111474206A CN 114386451 B CN114386451 B CN 114386451B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- hanger
- fault diagnosis
- independent component
- 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 41
- 238000003745 diagnosis Methods 0.000 title claims abstract description 30
- 230000008447 perception Effects 0.000 title claims description 6
- 230000001133 acceleration Effects 0.000 claims abstract description 36
- 238000012880 independent component analysis Methods 0.000 claims abstract description 16
- 238000012706 support-vector machine Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000002159 abnormal effect Effects 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 12
- 230000005484 gravity Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000006386 neutralization reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention relates to a catenary hanger fault diagnosis method based on an acceleration sensor, which comprises the following steps: sensors for measuring vertical acceleration and horizontal acceleration are arranged in the overhead line system hanger; preprocessing sensor acquired data, calculating time domain and frequency domain statistical characteristics of each piece of data subjected to cross preprocessing, and selecting significant characteristics to establish a support vector machine model; and then carrying out fault diagnosis on the group of data by using a trained support vector machine model, judging whether the hanger is faulty or not, if so, carrying out independent component analysis on the fault data, comparing the fault data with a threshold value in a normal condition, judging an abnormal time period, and judging a fault interval and a fault position according to the train operation speed. According to the scheme, the hanger can be monitored in real time through the background, fault diagnosis and positioning are performed, fault alarm information can be sent out timely, and maintenance personnel are informed of unfolding maintenance work.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring of overhead contact systems, in particular to a fault diagnosis and alarm method for overhead contact system droppers based on sensor information perception.
Background
The pantograph and the overhead contact system are one of important equipment of the electrified railway, the proportion of overhead contact system faults in the electrified railway equipment faults is large, and the dropper is an important part of the high-speed railway overhead contact system equipment and is arranged between the carrier rope and the contact line. Once the hanger breakage fault occurs, the operation is interrupted, and the important loss is brought to the national economy and even the life safety of people is threatened.
The existing overhead line system fault detection is mainly developed in terms of overhead line system reliability and maintenance strategies: in the aspect of reliability of the overhead line system, through analyzing the life characteristics of the hanger wire, the intensity reliability of the overhead line system is analyzed, and a corresponding failure model is designed to optimize the maintenance strategy, so that ideal early warning can be basically realized, but the influence of actual weather and the like is not considered; in the aspect of the maintenance strategy of the overhead line system, the optimization of the maintenance strategy can be realized by analyzing the current maintenance strategy and organization mode of the overhead line system and designing a corresponding mathematical model of the maintenance strategy, but the fault cannot be well diagnosed and notified. The existing research from the reliability of the overhead line system requires to establish a failure model from the aspects of physical structure, chemical performance and the like, does not consider the external influences such as weather, friction and the like of the hanger in operation, and lacks certain practicability; the timeliness and the systematicness of maintenance can be realized from the maintenance strategy of the overhead line system, but the fault diagnosis is lacking to a certain extent.
Disclosure of Invention
The invention aims to provide a fault diagnosis and alarm method for a catenary dropper based on sensor information perception, which can monitor, diagnose and position the state of the dropper in real time, send out faults in time and inform maintenance personnel of timely maintenance.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
a catenary dropper fault diagnosis method based on an acceleration sensor comprises the following specific steps:
1) Sensors for measuring vertical acceleration and horizontal acceleration are arranged in the overhead line system hanger;
2) Preprocessing the data acquired by the sensor by adopting a maximum and minimum value method, calculating time domain and frequency domain statistical characteristics of the preprocessed data in each span, and selecting significant characteristics;
3) Performing fault diagnosis by using a model trained by a support vector machine method, judging whether the hanger is faulty or not, and if so, performing independent component analysis on fault data;
4) The method of independent component analysis is used to compare the fault data with the threshold value (control limit) in normal condition, judge the abnormal time, and judge the fault interval and the fault position according to the train running speed.
In the step 1), the contact net dropper is as follows: and the bearing rope supporting point, the bearing rope midspan, the contact line locating point and the contact line midspan.
In the step 2), the pretreatment mode is normalized elimination dimension.
In step 2), calculating the time domain and frequency domain statistical characteristics of the data after each mid-span preprocessing, wherein the method comprises the following steps:
Waveform factor, kurtosis factor, root mean square frequency and frequency standard deviation of vertical acceleration in carrier cable midspan;
Maximum value, minimum value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak factor, kurtosis factor, pulse factor, margin, gravity center frequency, mean square frequency and frequency variance of horizontal acceleration of the carrier cable;
Maximum value, minimum value, mean value, average value of absolute value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak factor, kurtosis factor, pulse factor, margin, gravity center frequency, mean square frequency, frequency variance of the contact line mid-span vertical acceleration;
standard deviation, root mean square, waveform factor, kurtosis factor of horizontal acceleration of the contact line span.
Further, in step 2), the selection manner of the salient features is as follows: through time-frequency analysis, the characteristic which can distinguish normal and fault conditions obviously in the time-frequency domain characteristic is selected as the obvious characteristic.
In step 3), the fault diagnosis mode is as follows: and classifying and identifying the normal and fault data by using the trained support vector machine model, and judging whether the hanger is faulty or not.
In step 4), independent Component Analysis (ICA) is performed on the data diagnosed as fault, the ICA is used to unmixe the original signal to obtain an independent component signal, and HotellingT 2 and a Square Prediction Error (SPE) statistical method are used to perform fault diagnosis, the former introduces a main model statistic I 2 and an auxiliary model statisticThe latter introduces SPE statistics.
In step 4), the determination method of the threshold value in the normal condition is as follows: and performing kernel density estimation on the statistic by using a kernel function density estimation method to obtain the distribution of fault detection statistic I 2、I2 e and SPE, and determining a threshold value in normal condition.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the statistics of acceleration signals of the monitoring points of the contact network are calculated from two aspects of time domain and frequency domain, the characteristics are screened, then a support vector machine model is established for fault diagnosis, and the accuracy rate of fault identification can reach more than 94.1%. When the hanger failure is determined to occur after diagnosis, a method of independent component analysis is used for calculating failure statistics, a kernel function is used for estimating probability density functions of the failure statistics, a control limit is determined, and finally failure sites are determined. The method provided by the invention has high fault recognition accuracy; the fault rate of the hanger breakage in the test section can be judged, and the specific fault position can be positioned.
Drawings
FIG. 1 is a flow chart of a fault diagnosis alarm method of the present invention;
FIG. 2 is a layout of an acceleration sensor;
FIG. 3 is a graph showing average accuracy of results across SVMs;
in fig. 4, (a), (b) and (c) are I 2、I2 e, SPE statistic kernel density estimation probability density diagrams, respectively.
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
Aiming at the difficult problem that the fault of the broken string of the overhead line system is difficult to automatically diagnose, the invention provides a fault diagnosis method of the suspended string based on an acceleration sensor, which specifically comprises the following steps:
(1) Sensors for measuring vertical acceleration and horizontal acceleration are arranged in the overhead line system hanger;
The overhead contact system hanger is characterized in that: carrier support points, carrier midspan, contact line anchor points and contact line midspan.
(2) Preprocessing acceleration data acquired by a sensor by using a maximum and minimum value method, calculating time domain and frequency domain statistical characteristics of the preprocessed data in each span, and selecting significant characteristics;
The preprocessing means is to normalize and eliminate dimension, calculate the time domain and frequency domain statistical characteristics of the data after preprocessing in each span, and obtain significant characteristics through time-frequency analysis;
the calculating the time domain and frequency domain statistical characteristics of the data after each mid-span preprocessing comprises the following steps:
Maximum value, minimum value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak factor, kurtosis factor, pulse factor, margin, gravity center frequency, mean square frequency and frequency variance of horizontal acceleration of the carrier cable;
Maximum value, minimum value, mean value, average value of absolute value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak factor, kurtosis factor, pulse factor, margin, gravity center frequency, mean square frequency, frequency variance of the contact line mid-span vertical acceleration;
standard deviation, root mean square, waveform factor, kurtosis factor of horizontal acceleration of the contact line span.
The selection mode of the remarkable characteristics is as follows: through time-frequency analysis, the characteristic which can distinguish normal and fault conditions obviously in the time-frequency domain characteristic is selected as the obvious characteristic.
(3) Then, carrying out model training solving on the group of data by using a support vector machine method, carrying out fault diagnosis by using the obtained model, judging whether a hanger fracture fault occurs in the span section, and if the hanger fracture fault is diagnosed, carrying out next step of analyzing the fault position;
the fault diagnosis mode is as follows: and classifying and identifying the normal data and the fault data by using the trained support vector machine model.
(4) The method of independent component analysis is used to compare fault data with statistic control limit (threshold value) determined in normal condition, judge abnormal time period and judge that it is fault zone according to train running speed.
The independent component analysis process comprises the following steps: and unmixing the original signals to obtain independent component signals, performing fault diagnosis by using HotellingT 2 and a Square Prediction Error (SPE) statistical method, and performing kernel density estimation on the statistics by using a kernel function density estimation method to obtain fault detection statistics I 2、I2 e and the control limit of the SPE.
And detecting fault data based on the control limit, judging a time period when the fault data exceeds the control limit, further determining a time point when the fault occurs, and determining a fault position based on the intermediate time point and the train speed.
The method is described in detail below by way of specific examples:
The method is used for fault diagnosis of the hanger of the high-speed rail contact net, the data used are vibration signal data collected by a 6C system of the high-speed rail contact net, and the fault diagnosis and positioning of the high-speed rail contact net are carried out by combining the signal data characteristic extraction method with the support vector machine model classification method and the independent component analysis method. The flow chart of the fault diagnosis alarm method of the invention is shown in figure 1, and mainly comprises the steps of installation and data acquisition of monitoring equipment, solving of a monitoring model and fault diagnosis. The specific operation steps are as follows:
step 1) installing sensors at a carrier rope supporting point 1, a supporting point 2 and a midspan position of a contact net, and a locating point 2 and a midspan position of a contact line, and monitoring mechanical characteristic parameters between the contact net and a pantograph in a high-speed rail operation process in real time: vertical acceleration and horizontal acceleration of the carrier cable supporting point 1, vertical acceleration and horizontal acceleration of the carrier cable supporting point 2, vertical acceleration and horizontal acceleration of the carrier cable span, vertical acceleration and horizontal acceleration of the contact line span, and vertical acceleration and horizontal acceleration of the contact line positioning point 2.
As shown in fig. 2, mechanical characteristics such as acceleration of different positions of the carrier rope and the contact line are collected by using vibration measuring equipment for monitoring the carrier rope and the contact line, wherein # 1, # 2 and # 3 are vibration measuring equipment for supporting point 1 and span-neutralization supporting point 2 in sequence, and # 4 and # 5 are vibration measuring equipment for the contact line span-neutralization positioning point 2 in sequence.
Step 2) preprocessing the data, eliminating dimension influence, calculating statistical characteristic parameters of time domain and frequency domain, taking pulsating wind 1 as an example, and selecting obvious characteristics after time-frequency analysis:
Waveform factor, kurtosis factor, root mean square frequency and frequency standard deviation of vertical acceleration in carrier cable midspan; maximum value, minimum value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak factor, kurtosis factor, pulse factor, margin, gravity center frequency, mean square frequency and frequency variance of horizontal acceleration of the carrier cable; maximum value, minimum value, average value (rectifying average value) of absolute value, peak value, standard deviation, kurtosis, root mean square, waveform factor, peak value factor, kurtosis factor, pulse factor, margin of the vertical acceleration in the contact line span; center of gravity frequency, mean square frequency, frequency variance; the standard deviation, root mean square, waveform factor and kurtosis factor of the 21-cross contact line mid-span horizontal acceleration are 38 in total.
Step 3) the data are divided into a test set and a training set, wherein the test set accounts for 25% of the samples, namely 10 samples (5 positive examples, 5 negative examples), and the training set accounts for 75% of the samples, namely 30 samples (15 positive examples, 15 negative examples). Training a support vector machine model by using the significant features as attributes and training set data, and testing classification accuracy on a test set; fig. 3 shows that when the average value of the SVM classification accuracy is compared for 30 times for different spans of data, normal data and fault data can be classified at 94.44% accuracy in 21 spans, and the accuracy of separating the normal data from the fault data in other spans is very low, so that the 21 spans can be judged to be dropper fracture sections.
Step 4) performing fault interval diagnosis on the span diagnosed as a fault by using an independent component analysis method, unmixing an original signal by using an ICA method to obtain an independent component signal, providing fault statistics I 2、I2 e and SPE by using HotellingT 2 and a Square Prediction Error (SPE) statistical method to perform fault diagnosis, performing kernel density estimation on the statistics by using a kernel function density estimation method, and taking a case that pulsating wind is 1 as an example, wherein the kernel density estimation probability densities of the I 2、I2 e and SPE statistics are as shown in fig. 4, and determining the control limits respectively are: 62.11, 21.216, 265.48. The fault data is detected, the time period when the fault data exceeds the control limit is respectively 10.66-11.75, 11.21-11.71 and 10.668-11.394, and the time statistics of the middle point of the time period exceeding the statistic is maximum because the train is in a constant speed running process, so that the time points when the fault occurs are 11.205s,11.46s and 11.03s, the three statistic middle time points are averaged to 11.2303s, the train speed per hour is 250km/h, the train is known to be positioned at 29.884m of the beginning of the 21 span, the length of the 21 span is 50m, the span center dropper is positioned at 25m, and the fault position near the 21 span center [ error 4.884m ] can be determined.
The content of the invention is not limited to the examples listed, and any equivalent transformation to the technical solution of the invention that a person skilled in the art can take on by reading the description of the invention is covered by the claims of the invention.
Claims (2)
1. The utility model provides a catenary dropper fault diagnosis alarm method based on sensor information perception which is characterized in that:
the method comprises the following steps:
1) Sensors for measuring vertical acceleration and horizontal acceleration are arranged in the overhead line system hanger;
2) Preprocessing the data acquired by the sensor by adopting a maximum and minimum value method, calculating time domain and frequency domain statistical characteristics of the preprocessed data in each span, and selecting significant characteristics;
3) Performing fault diagnosis by using a model trained by a support vector machine method, judging whether the hanger is faulty or not, and if so, performing independent component analysis on fault data;
4) Comparing fault data with a threshold value in normal working conditions by using an independent component analysis method, judging abnormal time, and judging a fault interval and a fault position according to train operation speed;
In the step 2), the pretreatment mode is normalized elimination dimension; the selection mode of the remarkable characteristics is as follows: through time-frequency analysis, selecting the characteristic which can obviously distinguish normal and fault conditions in the time-frequency domain characteristics as the obvious characteristic;
In step 3), the fault diagnosis mode is as follows: classifying and identifying normal and fault data by using a trained support vector machine model, and judging whether the hanger is faulty or not;
In the step 4), the independent component analysis process is as follows: unmixing an original signal by using independent component analysis to obtain an independent component signal, and performing fault diagnosis by using HotellingT 2 and an SPE statistical method, wherein the former introduces a main model statistic I 2 and an auxiliary model statistic I 2 e, and the latter introduces an SPE statistic;
In step 4), the threshold value determination method in the normal working condition is as follows: and performing kernel density estimation on the statistic by using a kernel function density estimation method to obtain the distribution of fault detection statistic I 2、I2 e and SPE, and determining a threshold value in a normal working condition.
2. The overhead line system hanger fault diagnosis and alarm method based on sensor information perception according to claim 1, wherein the method comprises the following steps:
The overhead contact system hanger is characterized in that: carrier support points, carrier midspan, contact line anchor points and contact line midspan.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111474206.4A CN114386451B (en) | 2021-12-03 | 2021-12-03 | Contact net hanger fault diagnosis alarm method based on sensor information perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111474206.4A CN114386451B (en) | 2021-12-03 | 2021-12-03 | Contact net hanger fault diagnosis alarm method based on sensor information perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114386451A CN114386451A (en) | 2022-04-22 |
| CN114386451B true CN114386451B (en) | 2024-05-03 |
Family
ID=81196011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111474206.4A Active CN114386451B (en) | 2021-12-03 | 2021-12-03 | Contact net hanger fault diagnosis alarm method based on sensor information perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114386451B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114564874B (en) * | 2022-04-29 | 2022-09-02 | 中铁第一勘察设计院集团有限公司 | Fault simulation-oriented contact network three-dimensional visualization model construction method and system |
| CN114936487A (en) * | 2022-04-29 | 2022-08-23 | 中铁第一勘察设计院集团有限公司 | Method and system for positioning contact net positioner fault |
| CN115169405B (en) * | 2022-07-14 | 2024-02-02 | 北京威控科技股份有限公司 | Hotel guest room equipment fault diagnosis method and system based on support vector machine |
| CN117454262B (en) * | 2023-12-22 | 2024-03-22 | 华东交通大学 | Contact network fault identification method, system, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708009A (en) * | 2016-11-25 | 2017-05-24 | 哈尔滨工程大学 | Ship dynamic positioning measurement system multiple-fault diagnosis method based on support vector machine clustering |
| CN111721324A (en) * | 2020-05-15 | 2020-09-29 | 中铁第一勘察设计院集团有限公司 | Contact net dropper breakage detection method based on acceleration signals |
| CN112033463A (en) * | 2020-09-02 | 2020-12-04 | 哈尔滨工程大学 | Nuclear power equipment state evaluation and prediction integrated method and system |
| CN113537328A (en) * | 2021-07-07 | 2021-10-22 | 大连理工大学人工智能大连研究院 | Rotary machine fault diagnosis method and device based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7251924B2 (en) * | 2018-04-24 | 2023-04-04 | 株式会社日立製作所 | Failure diagnosis device, failure diagnosis method, and machine to which failure diagnosis device is applied |
-
2021
- 2021-12-03 CN CN202111474206.4A patent/CN114386451B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708009A (en) * | 2016-11-25 | 2017-05-24 | 哈尔滨工程大学 | Ship dynamic positioning measurement system multiple-fault diagnosis method based on support vector machine clustering |
| CN111721324A (en) * | 2020-05-15 | 2020-09-29 | 中铁第一勘察设计院集团有限公司 | Contact net dropper breakage detection method based on acceleration signals |
| CN112033463A (en) * | 2020-09-02 | 2020-12-04 | 哈尔滨工程大学 | Nuclear power equipment state evaluation and prediction integrated method and system |
| CN113537328A (en) * | 2021-07-07 | 2021-10-22 | 大连理工大学人工智能大连研究院 | Rotary machine fault diagnosis method and device based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114386451A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114386451B (en) | Contact net hanger fault diagnosis alarm method based on sensor information perception | |
| CN104091070B (en) | Rail transit fault diagnosis method and system based on time series analysis | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN111260822B (en) | Rail transit vehicle health state analysis method and terminal based on big data | |
| CN108069308A (en) | A kind of electric staircase failure diagnosis method based on sequential probability | |
| CN108645634B (en) | Rail vehicle fault diagnosis device | |
| CN104925613A (en) | Online safety detection prewarning device of elevator and detection prewarning method thereof | |
| CN107844067B (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| CN111721324B (en) | Contact net dropper breakage detection method based on acceleration signals | |
| CN110405537B (en) | Method for establishing guide rail precision prediction model based on deep learning | |
| CN109249960A (en) | A kind of Riding-type Monorail Switch comprehensive monitor system | |
| CN113562562A (en) | Elevator safety early warning monitoring system and judgment method thereof | |
| CN109917213B (en) | Contact network detection fault early warning method based on dimensionality reduction fusion and factor analysis | |
| CN110790101A (en) | Elevator trapping false alarm identification method based on big data analysis | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN111776006B (en) | Pre-alarming method and device for train axle temperature | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| CN113988326A (en) | Subway equipment maintenance optimization method and system | |
| CN113222187B (en) | Intelligent monitoring method for brake health of shared power-assisted vehicle | |
| CN114660181A (en) | Safety monitoring system, early warning system and detection method based on acoustic emission sensor | |
| CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
| CN111076750B (en) | Device and method for detecting looseness of catenary dropper wire clamp | |
| CN102837711B (en) | Infrared waveform based intelligent identification method for railway bearing | |
| CN115724314A (en) | Elevator fault detection early warning system and method | |
| CN115639423A (en) | Internet-based intelligent distribution box monitoring control method and 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 |