CN113157728B - Method for identifying circulation working conditions of underground diesel scraper - Google Patents
Method for identifying circulation working conditions of underground diesel scraper Download PDFInfo
- Publication number
- CN113157728B CN113157728B CN202110200986.7A CN202110200986A CN113157728B CN 113157728 B CN113157728 B CN 113157728B CN 202110200986 A CN202110200986 A CN 202110200986A CN 113157728 B CN113157728 B CN 113157728B
- Authority
- CN
- China
- Prior art keywords
- working condition
- data
- scraper
- time
- engine
- 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 26
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 238000007637 random forest analysis Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000004519 manufacturing process Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000004140 cleaning Methods 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 6
- 239000003921 oil Substances 0.000 claims description 9
- 230000007935 neutral effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 239000010705 motor oil Substances 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 239000010720 hydraulic oil Substances 0.000 claims description 4
- 239000002826 coolant Substances 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 10
- 238000011160 research Methods 0.000 abstract description 5
- 239000000463 material Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000110 cooling liquid Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The invention provides a method for identifying the circulation working condition of an underground diesel scraper, and belongs to the technical field of analysis of the working condition of the underground diesel scraper. The method comprises the steps of firstly obtaining circulation working condition operation data and a working condition conversion time record table of an underground diesel scraper, dividing the circulation working condition types of the underground diesel scraper into four working conditions of no-load driving, loading, heavy-load transportation and unloading, carrying out manual working condition calibration on historical data, then carrying out data cleaning and filtering treatment on the historical data, carrying out feature selection on the filtered data by utilizing a Relieff algorithm, determining working condition identification feature parameters, obtaining a final sample set, training a working condition identification random forest model, and inputting real-time production data of the scraper into the random forest model so as to realize real-time working condition identification. The method is simple and effective, has strong operability, does not depend on a scraper dynamics model, has strong expansibility, and has important significance for scraper fault diagnosis and intelligent control research based on working conditions.
Description
Technical Field
The invention relates to the technical field of analysis of working conditions of an underground diesel scraper, in particular to a method for identifying the circulation working conditions of the underground diesel scraper.
Background
The working condition refers to the condition that the equipment plays its function under different conditions, and is the working condition of the equipment under the condition that the equipment has direct relation with the action. According to the actual working condition of the underground scraper, it can be found that the underground scraper always works in a circulating and reciprocating mode, and the working condition and state change characteristic of the scraper in one working cycle represents the running state of the underground scraper. Because the underground scraper has different working conditions during working, the possible fault states under different working conditions are different.
Research shows that fault diagnosis based on working conditions is beneficial to improving the diagnosis and prediction recognition accuracy of the health state of the underground scraper, avoiding unnecessary maintenance and reasonably arranging resources. Based on the control method, intelligent control and scientific control of the underground scraper are further facilitated. Therefore, the method for identifying the operation condition of the underground scraper is researched, and an important guiding function is realized for the subsequent establishment of an underground scraper health diagnosis and judgment system, the evaluation and monitoring of the health state and the diagnosis and prediction of faults.
Along with the development of internet technology, internet of things technology and computer technology, the underground scraper is provided with corresponding sensors meeting certain precision requirements at different positions, so that sensor data reflecting the working state of the scraper in real time can be generated in the production process and stored in a server, and the working conditions of the scraper can be analyzed by acquiring the data by means of certain computer technology.
Disclosure of Invention
The invention aims to provide a method for identifying the circulation working condition of an underground diesel scraper, which is used for solving the problem that the circulation working condition of the underground diesel scraper cannot be identified rapidly and effectively in the prior art and providing guiding significance for subsequent fault diagnosis, health intelligent management and control based on the working condition.
According to the method, firstly, circulation working condition operation data and a working condition conversion time record table of an underground diesel scraper are obtained, then the circulation working condition types of the underground diesel scraper are divided into four working conditions of no-load driving, loading, heavy-load transportation and unloading, manual working condition calibration is carried out on historical data, then data cleaning and filtering treatment are carried out on the historical data, characteristic selection is carried out on the filtered data by utilizing a Relieff algorithm, working condition identification characteristic parameters are determined, a final sample set is obtained, finally, a random forest model is identified by training the working condition, and real-time production data of the scraper are input into the random forest model so as to realize real-time working condition identification.
The method specifically comprises the following steps:
(1) Acquiring circulating working condition operation data and a working condition conversion time record table of the underground diesel scraper;
(2) Dividing the circulation working conditions of the underground diesel scraper into four working conditions of no-load running, loading, heavy-load transportation and unloading, and carrying out working condition calibration on the data obtained in the step (1);
(3) Performing data cleaning and filtering treatment on the data obtained in the step (1);
(4) Performing feature selection on the filtered data by utilizing a ReliefF algorithm, and determining a working condition identification feature parameter to obtain a final sample set;
(5) Training a working condition recognition random forest model;
(6) And inputting real-time production data of the scraper into a random forest model to realize the identification of real-time working conditions.
The circulating working condition operation data of the underground diesel scraper in the step (1) comprises engine oil temperature, engine oil pressure, engine intake manifold temperature, engine intake manifold pressure, engine coolant temperature, gearbox oil pressure, hydraulic oil temperature, brake loop inflation pressure, large arm and bucket pressure, front axle brake pressure, rear axle brake pressure, vehicle speed, steering pump pressure, engine rotating speed, engine torque, engine fuel rate, engine load, accelerator pedal position and real-time gear of the scraper; the working condition change time record list comprises the occurrence time of air load running, loading, heavy load transportation and unloading in each circulation working condition during the experiment of the circulation working condition of the scraper.
In the step (2), the mechanism analysis and the operation data analysis of the scraper are combined, and the circulation working conditions are divided into no-load running, loading, heavy-load transportation and unloading, so that the algorithm difficulty is reduced, the recognition precision is improved, and the requirements of other researches such as follow-up fault diagnosis based on the working conditions are met; and (3) calibrating the data under the manual working condition, namely adding a series of tag data reflecting the real-time working condition after the historical data.
The data cleaning in the step (3) comprises the processing of the vacancy value and the abnormal value: aiming at the vacancy values, judging whether the neutral gear time is the neutral gear time at the moment according to mechanism analysis, directly deleting the neutral gear time, and carrying out interpolation processing on the vacancy values which occur in the non-neutral gear time; for abnormal values, namely, only data of the engine oil temperature, the engine cooling liquid temperature, the gearbox oil pressure, the hydraulic oil temperature and the brake oil temperature are not lost, or data which does not accord with production reality and logic, such as the engine oil temperature, the engine cooling liquid temperature is 0, can be deleted directly; and carrying out data filtering processing, namely carrying out weighted average filtering processing on the sensor data of each dimension in the experimental data for more than 10 times, and smoothing the data on the basis of keeping the change trend of the data.
The ReliefF algorithm in the step (4) is a multi-class feature selection algorithm, wherein feature parameters are determined by a threshold value in the ReliefF algorithm, and parameters with feature weights larger than the threshold value are selected as feature parameters according to the size of the threshold value.
The step (5) is specifically as follows: and (3) inputting training samples obtained by data cleaning, filtering and reliefF feature selection of experimental data after the working conditions are calibrated into a random forest model, wherein the operation data obtained in the step (1) are features of the training samples, and the working condition types are target attributes of the training samples.
The step (6) is specifically as follows: inputting real-time sensor data acquired by daily production of the scraper into the random forest model trained in the step (5) to identify the real-time working condition of the scraper.
The technical scheme of the invention has the following beneficial effects:
(1) The invention divides the circulation working conditions of the underground diesel scraper into four types of no-load running, loading, heavy-load transportation and unloading, does not distinguish working conditions of no-load advancing or retreating, heavy-load advancing, retreating and the like, simplifies the program, improves the recognition precision, and meets the requirements of researches such as follow-up fault diagnosis, intelligent control and the like;
(2) The invention adopts multiple weighted average filtering treatment, thereby realizing the smoothing of data and improving the accuracy of working condition identification;
(3) The invention adopts the Relieff algorithm to select the characteristics, can acquire the characteristic attribute most relevant to the working condition category, reduces the redundancy of data, reduces the calculated amount of the algorithm and improves the speed of the working condition identification. Besides, the algorithm does not depend on a scraper dynamics model, gets rid of dependence on expert knowledge, and is strong in expansibility;
(4) The invention can provide guidance for the fault diagnosis, intelligent control and scientific control of the scraper based on the working condition, and has great significance.
Drawings
FIG. 1 is a schematic flow chart of a method for identifying the circulation condition of a Sandvik LH514 type scraper according to an embodiment of the present invention;
FIG. 2 is a diagram of a data transmission path of a Sandvik LH514 scraper, provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a working flow of a Sandvik LH514 scraper according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the circulation conditions of a Sandvik LH514 scraper in accordance with an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The invention provides a method for identifying the circulation condition of an underground diesel scraper.
According to the method, firstly, circulation working condition operation data and a working condition conversion time record table of an underground diesel scraper are obtained, then the circulation working condition types of the underground diesel scraper are divided into four working conditions of no-load driving, loading, heavy-load transportation and unloading, manual working condition calibration is carried out on historical data, then data cleaning and filtering treatment are carried out on the historical data, characteristic selection is carried out on the filtered data by utilizing a Relieff algorithm, characteristic parameters of working condition identification are determined, a final sample set is obtained, a random forest model of working condition identification is trained finally, and real-time production data of the scraper are input into the random forest model to realize real-time working condition identification.
The following describes specific embodiments.
Example 1
The source of data for one embodiment of the present invention is the pretty-copper ore some Sandvik LH514 scooper. Taking this as an example, the invention discloses a method for identifying the circulation condition of an underground diesel scraper, as shown in fig. 1, comprising the following steps:
step S1: acquiring historical operating data of circulation working conditions of the Sandvik LH514 type scraper and a working condition conversion time record table:
the data transmission path of the scraper is shown in fig. 2, the data generated by the scraper during operation is collected by a memory on the device, then transmitted to a MOM Server for registering, and finally transmitted to an SQL Server for storing. Wherein the acquisition interval of the sensor data is 5s. Before working condition analysis, the operating data of the scraper circulation working condition is extracted from the SQL Server database by using Python.
The working condition transformation time recording table is recorded manually, and has the following two problems, namely, first, the working condition transformation is recorded manually with certain hysteresis; secondly, the manual recording time precision is of the order of minutes, and the difference between the manual recording time precision and the acquisition interval of the sensor 5s is large.
Step S2: the circulation working conditions of the scraper are classified into four working conditions of no-load running, loading, heavy-load transportation and unloading, and manual working condition calibration is carried out on the historical data.
Specifically, the determination of the cycle condition category is determined based on the following analysis. In the actual production process, the scraper runs back and forth in the underground tunnel, and the carrying work of the materials is completed through the processes of shoveling, transporting, unloading and the like, as shown in fig. 3. By field investigation of the operation process of the actual mine underground scraper, the circulating working condition of the underground scraper is found to have an L-shaped working circulating characteristic, and can be divided into 6 parts as shown in fig. 4:
(1) No-load advancing: the scraper starts from a turning point, the steering oil cylinder drives the whole truck to turn to a material point, and the tipping oil cylinder acts to put down the bucket to be inserted into a material pile.
(2) And (3) combined shovel loading: after the scraper advances and is inserted into the material pile, the diesel engine full throttle works, and the scraper keeps low-speed and high-torque advance until wheels slip. The steering pump and the working pump are simultaneously operated to provide power for the lifting cylinder and the tipping cylinder. The lift cylinder and tilt cylinder alternate until the bucket is nearly flat-ended.
(3) Heavy load backward steering: the scraper starts to retreat, starts from a material point, and the steering oil cylinder works and turns 90 degrees to return to a turning point.
(4) Heavy load advancing: the scraper starts from a turning point, and is transported forward to a lifting cylinder to work at a position reaching a discharging point, and the large arm lifts.
(5) And (3) unloading: at the discharge point, the steering pump works together with the working pump as a tipping cylinder to power the bucket, and the bucket is retracted after tipping and discharging.
(6) Idle load backing: the scraper retreats, falls down the big arm, retreats to the turning point after no load.
When no-load running is considered, the forward or backward movement is distinguished, the significance of the follow-up relevant research based on the working condition is not great, the difficulty of the working condition identification is increased, and the accuracy of the working condition identification is seriously affected. The same applies to heavy-duty transportation. Thus, the circulation conditions are divided into no-load travel, loading, heavy-load transportation and unloading.
Specifically, the historical data is calibrated under the manual working condition, and the error of manual recording time is considered, so that preliminary analysis is needed to be carried out by combining experimental data. Analysis shows that the big arm and the bucket pressure of the scraper respectively have a clear lifting process during loading and unloading. And then, by combining data such as the speed of the scraper, the position of an accelerator pedal and the like, the manually recorded working condition transition time is corrected to the second level, and then, the corresponding working condition of each group of data is determined. The embodiment of the invention prescribes the working condition label as follows: empty travel is designated 1, loading is designated 2, heavy load transportation is designated 3, and unloading is designated 4.
Step S3: and performing data processing on the historical data, including data cleaning and data filtering:
data cleansing includes the handling of outliers and nulls.
Specifically, the abnormal value is mainly the case that the data time node is inconsistent with the sampling time node, and the sampling period of the known sensor is 5s, so that the abnormal value can be directly removed in consideration of the problem of a sensing acquisition system.
Specifically, the vacancy values mainly exist in two cases: firstly, large-area deletion or total deletion; and secondly, the defect is occasionally caused. The consideration for all missing data is that the data of the time nodes are directly rejected because of the problem of the sensing acquisition system. In addition, due to the limitations of the sensing system, not all dimensional attributes exist data, and according to the principle of the data classification method, part of irrelevant data can be deleted before the data is analyzed. For relatively independent and completely random missing data, the data cannot be indirectly deduced through correlation with other parameters, and then the data interpolation is utilized for filling. The analysis shows that partial loss of the oil pressure of the gearbox and the oil temperature of the brake hydraulic pressure is easy to occur, and the linear interpolation is adopted to fill the gap value due to slow pressure and temperature change.
The data filtering method adopts weighted average filtering, and the effect of the weighted average filtering on the sensor data is not obvious through experiments, the data waveform is in a saw tooth shape, and the data waveform is smoothed after 30 times of filtering treatment.
Step S4: and (3) performing feature selection by using a ReliefF algorithm, wherein when the threshold value is set to be 0.02, the feature parameters for identifying the working condition of the scraper truck are the following 10-dimensional features: vehicle speed, engine oil temperature, engine coolant temperature, engine load, engine intake manifold temperature, boom and bucket pressure, brake hydraulic oil temperature, rear axle brake pressure, engine torque, front axle brake pressure.
And storing the corresponding working condition label data as a new list into the data selected by the characteristics to obtain final sample data. And randomly dividing the sample data with the labels into two groups, wherein one group is used as a training sample set, and the other group is used as a test sample set.
Step S5: training the random forest model by using training sample set data to obtain a random forest model with the identified working condition; and testing the classification effect of the working condition identification random forest model by using a test sample set, optimizing model parameters, and ensuring that the accuracy rate of the final working condition identification is up to 97%.
Step S6: inputting real-time data acquired by a sensor in the daily production process of the scraper into the working condition recognition random forest model, carrying out real-time working condition recognition, and outputting the working condition category of each time node.
In summary, the method for identifying the circulation condition of the underground diesel scraper provided by the embodiment of the invention considers the defect of the sensing acquisition system and processes the abnormal value and the blank value of the data; in order to reduce the influence of data noise, multiple weighted average filtering is adopted, so that the data is smoothed; and then, a Relieff algorithm is used for feature selection, so that the data redundancy is reduced, and the algorithm operation speed is improved; and finally training a random forest model to realize the recognition of the circulation working condition, wherein the accuracy rate is as high as 97%. In short, the method is simple and effective, has strong operability, does not depend on a scraper dynamics model, has strong expansibility, and has important significance for the study of scraper fault diagnosis, intelligent control and scientific management and control based on working conditions.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (2)
1. The method for identifying the circulation working condition of the underground diesel scraper is characterized by comprising the following steps:
(1) Acquiring circulating working condition operation data and a working condition conversion time record table of the underground diesel scraper;
(2) Dividing the circulation working conditions of the underground diesel scraper into four working conditions of no-load running, loading, heavy-load transportation and unloading, and carrying out working condition calibration on the data obtained in the step (1);
(3) Performing data cleaning and filtering treatment on the data obtained in the step (1);
(4) Performing feature selection on the data subjected to the filtering processing in the step (3) by utilizing a reliefF algorithm, and determining characteristic parameters of working condition identification to obtain a final sample set;
(5) Training a working condition recognition random forest model;
(6) Inputting real-time production data of the scraper into the random forest model in the step (5) to realize the identification of real-time working conditions;
the circulation working condition operation data of the underground diesel scraper in the step (1) comprises engine oil temperature, engine oil pressure, engine intake manifold temperature, engine intake manifold pressure, engine coolant temperature, gearbox oil pressure, hydraulic oil temperature, brake loop inflation pressure, big arm and bucket pressure, front axle brake pressure, rear axle brake pressure, vehicle speed, steering pump pressure, engine rotating speed, engine torque, engine fuel rate, engine load, accelerator pedal position and real-time gear of the scraper; the working condition change time record table comprises the occurrence time of idle load running, loading, heavy load transportation and unloading in each circulating working condition when the circulating working condition of the scraper is tested, and the idle load running or the idle load backing and the heavy load running and backing working conditions are not distinguished;
the data cleaning in the step (3) comprises the processing of a blank value and an abnormal value: aiming at the vacancy values, judging whether the neutral gear time is the neutral gear time at the moment according to mechanism analysis, directly deleting the neutral gear time, and performing interpolation processing on the vacancy values of the neutral gear time; direct deletion is carried out on abnormal values which do not accord with production reality and logic; filtering, namely carrying out weighted average filtering on the sensor data of each dimension in the experimental data for at least 10 times, and smoothing the data on the basis of keeping the change trend of the data;
the characteristic parameters in the step (4) are determined by a threshold value in a ReliefF algorithm, and parameters with characteristic weights larger than the threshold value are selected as the characteristic parameters according to the size of the threshold value;
the step (5) specifically comprises the following steps: inputting training samples obtained after data cleaning, filtering and ReliefF feature selection of experimental data after the working conditions are calibrated into a random forest model, wherein the operation data obtained in the step (1) are features of the training samples, and the working condition types are target attributes of the training samples;
the step (6) specifically comprises the following steps: inputting real-time sensor data acquired by daily production of the scraper into the random forest model trained in the step (5) to identify the real-time working condition of the scraper.
2. The method for identifying the circulation condition of the underground diesel scraper according to claim 1, wherein the method comprises the following steps: and (3) calibrating the data in the step (2) under the manual working condition, namely adding a list of tag data reflecting the real-time working condition after the historical data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110200986.7A CN113157728B (en) | 2021-02-23 | 2021-02-23 | Method for identifying circulation working conditions of underground diesel scraper |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110200986.7A CN113157728B (en) | 2021-02-23 | 2021-02-23 | Method for identifying circulation working conditions of underground diesel scraper |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113157728A CN113157728A (en) | 2021-07-23 |
CN113157728B true CN113157728B (en) | 2024-03-19 |
Family
ID=76883580
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110200986.7A Active CN113157728B (en) | 2021-02-23 | 2021-02-23 | Method for identifying circulation working conditions of underground diesel scraper |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113157728B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117807443B (en) * | 2024-02-29 | 2024-05-14 | 江苏海平面数据科技有限公司 | Training method of tractor working condition identification model and tractor working condition identification method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109034220A (en) * | 2018-07-13 | 2018-12-18 | 福州大学 | A kind of intelligent photovoltaic array method for diagnosing faults based on optimal rotation forest |
CN109058771A (en) * | 2018-10-09 | 2018-12-21 | 东北大学 | The pipeline method for detecting abnormality of Markov feature is generated and is spaced based on sample |
CN109190304A (en) * | 2018-10-16 | 2019-01-11 | 南京航空航天大学 | Gas path component fault signature extracts and fault recognition method in a kind of aero-engine whole envelope |
CN109459586A (en) * | 2018-12-05 | 2019-03-12 | 智灵飞(北京)科技有限公司 | A kind of unmanned plane accelerometer scaling method based on LM algorithm |
CN110532613A (en) * | 2019-07-26 | 2019-12-03 | 中国船舶重工集团公司第七一九研究所 | Ship power system operation mode recognition method and device |
CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
CN111709490A (en) * | 2020-06-24 | 2020-09-25 | 河北工业大学 | Fan health state assessment method based on GRU neural network |
CN112381965A (en) * | 2020-11-03 | 2021-02-19 | 浙大城市学院 | Aeroengine health state identification system and method based on data mining |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10712738B2 (en) * | 2016-05-09 | 2020-07-14 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for industrial internet of things data collection for vibration sensitive equipment |
-
2021
- 2021-02-23 CN CN202110200986.7A patent/CN113157728B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109034220A (en) * | 2018-07-13 | 2018-12-18 | 福州大学 | A kind of intelligent photovoltaic array method for diagnosing faults based on optimal rotation forest |
CN109058771A (en) * | 2018-10-09 | 2018-12-21 | 东北大学 | The pipeline method for detecting abnormality of Markov feature is generated and is spaced based on sample |
CN109190304A (en) * | 2018-10-16 | 2019-01-11 | 南京航空航天大学 | Gas path component fault signature extracts and fault recognition method in a kind of aero-engine whole envelope |
CN109459586A (en) * | 2018-12-05 | 2019-03-12 | 智灵飞(北京)科技有限公司 | A kind of unmanned plane accelerometer scaling method based on LM algorithm |
CN110532613A (en) * | 2019-07-26 | 2019-12-03 | 中国船舶重工集团公司第七一九研究所 | Ship power system operation mode recognition method and device |
CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
CN111709490A (en) * | 2020-06-24 | 2020-09-25 | 河北工业大学 | Fan health state assessment method based on GRU neural network |
CN112381965A (en) * | 2020-11-03 | 2021-02-19 | 浙大城市学院 | Aeroengine health state identification system and method based on data mining |
Non-Patent Citations (2)
Title |
---|
Carolin Lübbe 等.Feature based random forest nurse care activity recognition using accelerometer data.《UbiComp/ISWC '20 Adjunct: Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers》.2020,408–413. * |
变工况下柴油机故障在线监测与维修决策优化方法研究与应用;赖岳华;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20210115(第01期);C039-46 * |
Also Published As
Publication number | Publication date |
---|---|
CN113157728A (en) | 2021-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11175274B2 (en) | Systems and methods for remaining useful life prediction of a fluid | |
CN113157728B (en) | Method for identifying circulation working conditions of underground diesel scraper | |
US7464063B2 (en) | Information processor, state judging unit and diagnostic unit, information processing method, state judging method and diagnosing method | |
US8364440B2 (en) | System for evaluating the productivity of a working machine and its driver | |
AU2014250851B2 (en) | Vehicle and operator guidance by pattern recognition | |
CA2610223C (en) | A system for measuring the performance of a forest machine | |
CN109359524B (en) | Loader condition identification model construction and identification method | |
CN113358369A (en) | Load spectrum analysis method and system for electric drive system of mining dump truck | |
EP3308127B1 (en) | Method and system for detection of torque deviations of an engine in a vehicle | |
CN115081749A (en) | Bayesian optimization LSTM-based shield tunneling load advanced prediction method and system | |
CN112298155A (en) | Method for predicting energy consumption of hybrid power truck based on variable time domain model | |
CN113029619A (en) | Underground scraper fault diagnosis method based on C4.5 decision tree algorithm | |
CN115586023A (en) | Fault diagnosis method and system for rail vehicle transmission system | |
US7742863B2 (en) | Method and device for controlling a work function of a vehicle and a work vehicle comprising the control device | |
CN113505415A (en) | Bridge rapid detection method based on deep learning | |
CN1734246A (en) | Judging method of vehicle loading condition | |
Schlosser et al. | Agricultural tractor engines from the perspective of Agriculture 4.0 | |
CN111038520A (en) | Hydrostatic travel drive, mobile work machine with travel drive, and method for data input | |
EP3494332B1 (en) | Controller for controlling a vehicle driveline and method of calibrating a vehicle driveline controller | |
DE102012203196A1 (en) | Diagnosis for hydrocarbon conversion | |
JP3963896B2 (en) | Construction machine fuel condition identification method | |
US20240273954A1 (en) | Selective capture of work machine productivity factors based on work state estimation | |
CN116737845B (en) | Economic vehicle speed analysis method and system | |
CN114013501B (en) | Electro-hydraulic steering fault-tolerant control method and terminal | |
CN117391060A (en) | Vehicle test data processing 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 | ||
GR01 | Patent grant |