CN111626439B - Rail overhaul decision support method based on artificial intelligence - Google Patents
Rail overhaul decision support method based on artificial intelligence Download PDFInfo
- Publication number
- CN111626439B CN111626439B CN201911058756.0A CN201911058756A CN111626439B CN 111626439 B CN111626439 B CN 111626439B CN 201911058756 A CN201911058756 A CN 201911058756A CN 111626439 B CN111626439 B CN 111626439B
- Authority
- CN
- China
- Prior art keywords
- formula
- rail
- change
- substituting
- steel rail
- 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 17
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 12
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 45
- 239000010959 steel Substances 0.000 claims abstract description 45
- 230000006378 damage Effects 0.000 claims abstract description 24
- 102000016550 Complement Factor H Human genes 0.000 claims abstract description 8
- 108010053085 Complement Factor H Proteins 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- YBJHBAHKTGYVGT-ZKWXMUAHSA-N (+)-Biotin Chemical compound N1C(=O)N[C@@H]2[C@H](CCCCC(=O)O)SC[C@@H]21 YBJHBAHKTGYVGT-ZKWXMUAHSA-N 0.000 claims abstract description 6
- FEPMHVLSLDOMQC-UHFFFAOYSA-N virginiamycin-S1 Natural products CC1OC(=O)C(C=2C=CC=CC=2)NC(=O)C2CC(=O)CCN2C(=O)C(CC=2C=CC=CC=2)N(C)C(=O)C2CCCN2C(=O)C(CC)NC(=O)C1NC(=O)C1=NC=CC=C1O FEPMHVLSLDOMQC-UHFFFAOYSA-N 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 208000014674 injury Diseases 0.000 claims description 5
- 230000009528 severe injury Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000008832 photodamage Effects 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000008733 trauma Effects 0.000 claims description 2
- 208000037974 severe injury Diseases 0.000 claims 1
- 101100295776 Drosophila melanogaster onecut gene Proteins 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 abstract 1
- 208000027418 Wounds and injury Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 206010052428 Wound Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a rail overhaul decision support method based on artificial intelligence, which comprises the following specific steps: s1, acquiring characteristic data related to overhaul of a steel rail, and preprocessing the acquired characteristic data; s2, substituting the processed light and heavy damage characteristics into a damage judging formula to obtain key influence factors F; s3, substituting the processed vertical grinding side grinding damage characteristics into a damage judging formula to obtain a secondary influence factor S; s4, substituting the processed steel rail year characteristics into a year discrimination formula to obtain a history factor H; s5, substituting the key influence factors F, the secondary influence factors S and the history factors H into a formula to obtain a track change grade; s6, substituting the change grade of each section into a formula to calculate change trend data; s7, substituting the change trend data of each section into a formula and adding to obtain a change section. The invention provides a rail overhaul decision method based on multi-source data fusion, which intelligently recommends a rail change interval, changes the conventional 'one-cut' fixed mode, provides a more scientific and reasonable decision reference basis, realizes accurate rail change and promotes reasonable utilization of resources.
Description
Technical Field
The invention relates to the technical fields of railway steel rail maintenance and data analysis, in particular to a steel rail overhaul interval calculation method.
Background
The steel rail is one of the main technical equipment of the railway, is the basis of driving safety and is responsible for important transportation tasks. With the development of railways to high speed and heavy load, travel tasks are continuously increased, the travelling density is improved, the rail bears huge operation pressure, the fatigue aging speed is accelerated, the service life is seriously reduced, and the safety risk exists. In order to avoid safety accidents, railway departments determine whether the service of the steel rail is full of 10 years or whether the total load exceeds 7 hundred million tons to overhaul or change the steel rail, and the aging condition of the actual steel rail is influenced by various factors such as geographical environment, steel rail position, load distribution and the like, so that the overhaul of the 'one-cut' is based on the fact that the steel rail with the fatigue damage of the line is multiple but the service life is less than 10 years or the load is less than 7 hundred million tons and a large number of the steel rail exists, accurate rail change cannot be realized, and the waste of resources is caused. Therefore, a scientific and reasonable rail overhaul decision method is needed, and rail replacement decision support can be made according to the actual damage state of the rail.
The invention provides an intelligent overhaul decision method based on multi-source data analysis mining of a steel rail, which predicts the development trend of the damage of the steel rail by analyzing and mining the damage, abrasion, service year, total weight, environmental data and other data of the steel rail, intelligently recommends a rail replacement interval, provides data and visual decision support for the overhaul of the steel rail, avoids 'one cut', improves the scientificity of decision, improves the safety of railway operation and is suitable for the railway transportation requirement of high-speed development.
Disclosure of Invention
In view of the above, the present invention provides a rail overhaul decision support method based on artificial intelligence to effectively solve the problems existing in the above technical background.
The invention is realized by adopting the following technical scheme:
s1, acquiring characteristic data related to overhaul of a steel rail, and preprocessing the acquired characteristic data;
s2, substituting the processed light and heavy damage characteristics into a damage judging formula to obtain key influence factors F;
s3, substituting the processed vertical grinding side grinding damage characteristics into a damage judging formula to obtain a secondary influence factor S;
s4, substituting the processed steel rail year characteristics into a year discrimination formula to obtain a history factor H;
s5, substituting the key influence factors F, the secondary influence factors S and the history factors H into the formula to obtain a change grade L, and calculating a minimum change interval L according to the change grade L min ；
S6, substituting the change grade of each section into a formula to calculate change trend data FL;
s7, substituting the change trend data of each section into a formula and adding to obtain a change section.
The processing step of the S1 is as follows:
s11, collecting characteristic data related to overhaul of the steel rail, such as vertical grinding of the steel rail, side grinding of the steel rail, total passing weight, historical rail change interval, 1km of severe damage number, 1km of light damage number and steel rail year;
s12, preprocessing the collected characteristic data, and processing the missing value and the abnormal value in the data.
The key influencing factor F is the number N of severe wounds of 1km Z And is obtained by substituting the total weight M into a formula:
wherein K is 1 、K 2 The weight correction coefficient and the weight correction coefficient are respectively defined as a standard value C, G.
The secondary influencing factors S are a vertical grinding V of the steel rail and a side grinding S of the steel rail i And a number of traumas N of 1km S Substituting the formula to obtain, wherein the formula is as follows:
D. e is the wear correction factor and the damage correction factor, respectively.
The history factor H is a history change track interval H n Substituting the formula to obtain, wherein the formula is as follows:wherein t is H n The number of years of rail replacement in the last 6 years indicates that the section of steel rail is not replaced when t is 0; when t is 1 or 2, the rail is replaced recently, and the priority should be reduced; when t is larger than 2, the rail replacement frequency is high, the rail replacement is easy to damage, and the rail replacement priority is improved.
The processing step of the S5 is as follows:
s51, calculating a change grade through a formula, wherein the change grade L is obtained by substituting an important influence factor F, a secondary influence factor S and a history factor H into the formula, and the formula is as follows:
s52, calculating the minimum according to the substitution formula of the change gradeChange track interval L min . Minimum change track interval L min The calculation formula is as follows:
wherein L is B Is a standard change grade.
The change trend data FL is obtained by substituting a base length of 0.05km into a rail according to mileage N and change grade L, wherein the formula is as follows:
wherein Y is the year of the section of steel rail, C Y For the year influencing factor, O is the year.
The change track interval is obtained by substituting change trend data FL into a formula, and the formula is as follows:
interval = Σmax (FL (Hl) -Hl, 0), hl being the defined range Hl being the standard threshold value.
The beneficial effects of the invention are that
The invention provides an artificial intelligence-based rail overhaul decision support method, which is characterized in that multi-source data of rails are collected for feature extraction and intelligent analysis, rail damage conditions are visualized and data-based analysis is carried out, rail change trend analysis is formed, rail change intervals are intelligently recommended, scientific and accurate rail change is realized, and unnecessary rail change expenditure is saved.
Drawings
FIG. 1 is a flow chart of steps of an artificial intelligence rail overhaul decision support method;
FIG. 2 is a graph of the original characteristics of the rail (vertical mill, side mill, total actual number of heavy injuries, total actual number of light injuries, year of rail, total actual total weight passed);
FIG. 3 is a graph of trend analysis of rail change trend;
fig. 4 is a recommended track-change section diagram.
Detailed Description
The invention is further described by the following examples, which are given by way of illustration only and are not limiting of the scope of the invention.
In this example, a rail of 6 km length is taken as an example for data acquisition and calculation.
S1, acquiring characteristic data related to steel rail overhaul, and preprocessing the acquired characteristic data, wherein the processing steps are as follows:
s11, collecting characteristic data related to overhaul of the steel rail, namely vertical grinding of the steel rail, side grinding of the steel rail, total passing weight, historical rail change interval, 1km of severe damage number, 1km of light damage number and steel rail year;
s12, preprocessing the collected characteristic data, and processing the missing value and the abnormal value in the data;
s2, substituting the processed 1km light and heavy injury data into a formula, and calculating to obtain an important influence factor K=15.62, wherein K is 1 ＝2.2，K 2 ＝1.5，C＝4，G＝100；
S3, substituting the processed vertical grinding side grinding data into a formula, and calculating to obtain a secondary influence factor S= 2.624, wherein D=0.12 and E=0.2;
s4, substituting the processed steel rail year characteristics into a formula, and calculating to obtain a history influence factor H=0.5;
s5, obtaining a change grade evaluation through a formula and calculation, wherein the change grade L=8.62, and calculating a minimum change interval L according to the substitution of the change grade L into the formula min The segment L min =1, where L B ＝2.6；
S6, substituting the railway line with mileage N and change grade L based on 0.05km to obtain change trend data FL=8.83, as shown in FIG. 3, wherein C Y ＝0.3，O＝2009；
And S7, substituting the change trend data FL into a formula to obtain a recommended change range, as shown in fig. 4, wherein hl=0.05 and hl=6.2.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The rail overhaul decision support method based on artificial intelligence is characterized by comprising the following steps:
s1, acquiring characteristic data related to overhaul of a steel rail, and preprocessing the acquired characteristic data;
s2, substituting the processed light and heavy damage characteristics into a damage judging formula to obtain key influence factors F;
s3, substituting the processed vertical grinding side grinding damage characteristics into a damage judging formula to obtain a secondary influence factor S;
s4, substituting the processed steel rail year characteristics into a year discrimination formula to obtain a history factor H;
s5, substituting the key influence factors F, the secondary influence factors S and the history factors H into the formula to obtain a change grade L, and calculating a minimum change interval L according to the change grade L min ；
S6, substituting the change grade of each section into a formula to calculate change trend data FL;
s7, substituting the change trend data of each section into a formula to obtain a change section;
wherein the formula in S7 is:
interval = Σmax (FL (Hl) -Hl, 0), hl being the defined range Hl being the standard threshold value.
2. The rail overhaul decision support method based on artificial intelligence according to claim 1, wherein the processing step of S1 is as follows:
s11, collecting characteristic data related to overhaul of the steel rail, namely vertical grinding of the steel rail, side grinding of the steel rail, total passing weight, historical rail change interval, 1km of severe damage number, 1km of light damage number and steel rail year;
s12, preprocessing the collected characteristic data, and processing the missing value and the abnormal value in the data.
3. The method for supporting steel rail overhaul decision based on artificial intelligence according to claim 1, wherein the key influencing factor F of S2 is a number N of severe injuries of 1km Z And is obtained by substituting the total weight M into a formula:
wherein K is 1 、K 2 The weight correction coefficient and the weight correction coefficient are respectively defined as a standard value C, G.
4. The method for supporting overhaul of steel rail according to claim 1, wherein the secondary influencing factors S of S3 are V-shaped vertical grinding of steel rail and S-shaped side grinding of steel rail i And a number of traumas N of 1km S Substituting the formula to obtain, wherein the formula is as follows:
D. e is the wear correction factor and the damage correction factor, respectively.
5. The artificial intelligence-based steel rail overhaul decision support method according to claim 1, wherein the historical factor H of S4 is a historical change track interval H n Substituting the formula to obtain, wherein the formula is as follows:
wherein t is H n The number of years of rail replacement in the last 6 years indicates that the section of steel rail is not replaced when t is 0; when t is 1 or 2, the rail is replaced recently, and the priority should be reduced; when t is larger than 2, the rail replacement frequency is high, the rail replacement is easy to damage, and the rail replacement priority is improved.
6. The rail overhaul decision support method based on artificial intelligence according to claim 1, wherein the processing step of S5 is as follows:
s51, calculating a change grade through a formula, wherein the change grade L is obtained by substituting an important influence factor F, a secondary influence factor S and a history factor H into the formula, and the formula is as follows:
s52, calculating the minimum track change interval L according to the track change grade substitution formula min 。
7. The artificial intelligence based rail overhaul decision support method according to claim 6, wherein the minimum rail change interval L of S52 min The calculation formula is as follows:
wherein L is B Is a standard change grade.
8. The method for supporting overhaul of steel rail according to claim 1, wherein the change trend data FL of S6 is obtained by substituting a base length of 0.05km into a rail according to mileage N and change level L, and the formula is:
wherein Y is the year of the section of steel rail, C Y For the year influencing factor, O is the year.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058756.0A CN111626439B (en) | 2019-11-01 | 2019-11-01 | Rail overhaul decision support method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058756.0A CN111626439B (en) | 2019-11-01 | 2019-11-01 | Rail overhaul decision support method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111626439A CN111626439A (en) | 2020-09-04 |
| CN111626439B true CN111626439B (en) | 2023-12-29 |
Family
ID=72259658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911058756.0A Active CN111626439B (en) | 2019-11-01 | 2019-11-01 | Rail overhaul decision support method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111626439B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114987583A (en) * | 2022-05-18 | 2022-09-02 | 中国铁道科学研究院集团有限公司 | Steel rail overhaul prediction method and device, electronic equipment and storage medium |
| CN114834502B (en) * | 2022-05-25 | 2024-03-19 | 东莞灵虎智能科技有限公司 | Task rail break risk prediction method based on artificial intelligence and big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5978717A (en) * | 1997-01-17 | 1999-11-02 | Optram, Inc. | Computer system for railway maintenance |
| CN103714228A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and device for determining rail maintenance sections |
| CN105109517A (en) * | 2015-08-13 | 2015-12-02 | 中国神华能源股份有限公司 | Rail-flaw analyzing method and rail-flaw detecting car |
| CN108009742A (en) * | 2017-12-15 | 2018-05-08 | 北京交通大学 | A kind of method and system of definite railroad track health status |
| CN110363403A (en) * | 2019-06-27 | 2019-10-22 | 中国铁道科学研究院集团有限公司 | Railway track damage forecast method and device |
-
2019
- 2019-11-01 CN CN201911058756.0A patent/CN111626439B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5978717A (en) * | 1997-01-17 | 1999-11-02 | Optram, Inc. | Computer system for railway maintenance |
| CN103714228A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and device for determining rail maintenance sections |
| CN105109517A (en) * | 2015-08-13 | 2015-12-02 | 中国神华能源股份有限公司 | Rail-flaw analyzing method and rail-flaw detecting car |
| CN108009742A (en) * | 2017-12-15 | 2018-05-08 | 北京交通大学 | A kind of method and system of definite railroad track health status |
| CN110363403A (en) * | 2019-06-27 | 2019-10-22 | 中国铁道科学研究院集团有限公司 | Railway track damage forecast method and device |
Non-Patent Citations (1)
| Title |
|---|
| 重载铁路线路大修经济决策的研究;魏世斌等;《铁道学报》(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111626439A (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626439B (en) | Rail overhaul decision support method based on artificial intelligence | |
| CN110533229B (en) | Track maintenance time prediction method and device | |
| CN104021671B (en) | The determination methods of the road real-time road that a kind of svm combines with fuzzy Judgment | |
| CN112201038A (en) | Road network risk assessment method based on risk of bad driving behavior of single vehicle | |
| CN104751288A (en) | Segment-based multi-dimensional online quality evaluation system and method for steel coils | |
| CN112364297A (en) | Method for evaluating service state of steel rail of ordinary speed line | |
| CN110203249B (en) | Train repair process method, device and storage medium | |
| CN111847169A (en) | Elevator traction steel wire rope state monitoring and early warning system and method based on algorithm model | |
| CN111640304B (en) | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility | |
| CN113822387B (en) | Road surface damage condition index prediction method, system, equipment and medium | |
| CN113159374A (en) | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method | |
| CN116644890A (en) | Method for calculating overhaul index of high-speed railway steel rail | |
| CN116481839A (en) | Wheel state evaluation method based on objective weighting method | |
| CN110555188A (en) | analysis method for wheel parameter abrasion trend of motor train unit | |
| CN116311912A (en) | Active prevention and control method for traffic safety of national province trunk road | |
| CN113255825A (en) | Track bed defect identification method and device | |
| CN109604709A (en) | A kind of Continuous Hot Dip Galvanizing Line end trimming shears state of wear judgment method and device | |
| CN115081784A (en) | Fault prediction and health management system for locomotive wheels | |
| CN112072789B (en) | Low-voltage transformer area identification method, maintenance method and early warning method thereof | |
| CN113435675B (en) | Road grading method based on mobile dangerous chemical transportation and application thereof | |
| CN115017463A (en) | Method for managing rail turnout value | |
| CN115860730B (en) | Railway track constructor safety control system based on internet | |
| CN115496308B (en) | Road traffic marking retroreflection performance prediction method based on big data analysis | |
| CN113487144B (en) | Safety risk early warning method and system for railway group on-road operation | |
| CN117314260A (en) | Rail grinding index calculation method based on service safety |
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 |