CN112317109A - Cone crusher fault pre-judging method - Google Patents
Cone crusher fault pre-judging method Download PDFInfo
- Publication number
- CN112317109A CN112317109A CN202011032108.0A CN202011032108A CN112317109A CN 112317109 A CN112317109 A CN 112317109A CN 202011032108 A CN202011032108 A CN 202011032108A CN 112317109 A CN112317109 A CN 112317109A
- Authority
- CN
- China
- Prior art keywords
- oil
- crusher
- fault
- temperature
- membership function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C23/00—Auxiliary methods or auxiliary devices or accessories specially adapted for crushing or disintegrating not provided for in preceding groups or not specially adapted to apparatus covered by a single preceding group
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C2/00—Crushing or disintegrating by gyratory or cone crushers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C25/00—Control arrangements specially adapted for crushing or disintegrating
Abstract
The invention belongs to the technical detection field, and particularly relates to a method for prejudging a fault of a cone crusher. The method is characterized in that the anti-interference capability of a fault pre-judging system is improved by adopting a fuzzy reasoning method, and the false alarm probability and the missing rate are effectively reduced; in the fuzzification process, the mode that the membership function selects the combination of the triangular membership function and the trapezoidal membership function avoids the phenomenon of unreasonable domain division caused by singly using the triangular membership function; the evidence theory is adopted to fuse the reasoning results, so that the diagnosis results fully utilize the information of the crusher, and the fault pre-judgment result is more reliable; the classification with the membership degree of 1 or 0 does not participate in evidence theory fusion, so that evidence conflict of the evidence theory is avoided, and the feasibility of the algorithm is ensured; the trend information of historical data is introduced to be used as auxiliary diagnosis, the failure pre-judgment missing rate is further reduced, and the overall level of failure pre-judgment is improved.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis and detection, and particularly relates to a method for prejudging a fault of a cone crusher.
Background
The cone crusher is widely applied to a plurality of departments such as mines, smelting, building materials, roads, water conservancy and the like, and particularly plays a key role in the middle breaking and fine breaking of mine rocks. The cone crusher has high failure rate, and the failure pre-judgment and early warning are key problems to be solved urgently in mine equipment management. At present, the fault prejudgment research results of the cone crusher are not abundant, and most of researches mainly take the experience of experts and working personnel.
The traditional method for setting the alarm threshold value is weak in anti-interference capability, and a false alarm or untimely alarm phenomenon may occur when a mine crushing system is disturbed, so that production is affected or the fault degree is deepened, and loss is brought to enterprises. In practice, a great deal of expert experience is needed to process a considerable part of fuzzy information in fault prediction, and an evidence theory is mature when a fuzzy problem is processed, especially in fault prediction of mechanical equipment. Fuzzy reasoning can obtain membership degree relations of fault types corresponding to various instant messages, data fusion is carried out by combining an evidence theory, and a comprehensive fault pre-judgment result under the support of various kinds of information is calculated. The change trend of various faults can be obtained according to historical data obtained by multiple diagnoses, so that the omission ratio of the fault pre-judging system is reduced in an auxiliary mode.
Disclosure of Invention
The invention aims to provide a cone crusher fault prejudging method which improves the anti-interference capability of a fault diagnosis system and effectively reduces the false alarm probability and the missing rate.
The purpose of the invention is realized by the following technical scheme:
the invention discloses a method for prejudging the faults of a cone crusher, which is characterized by comprising the following steps of:
(1) vibrating the variable level | v according to the fault threshold and real-time requirements of the crusherxL, vertical vibration | vySelecting a trapezoidal membership function, wherein the functions comprise the temperature lot of lubricating oil, the flow rate qol of the lubricating oil, the current mmc of a main motor and the running noise rn; selecting a trapezoidal membership function and a triangular membership function to combine the differential pressure dof of the variable oil filter and the return oil temperature rot;
(2) establishing a fuzzy rule base according to crusher data which can be collected on site;
(3) carrying out fuzzy reasoning according to a Madiny algorithm to obtain fault membership degree information of each datum;
(4) fusing data with the failure membership degree not being 0 or 1 according to an evidence theory, and comprehensively obtaining a failure pre-judgment result;
(5) and calculating the fault reliability distribution variation trend of multiple diagnoses according to a least square method to assist in diagnosis.
Establishing a fuzzy rule base according to the crusher data which can be collected on site in the step (2), wherein the specifically established fuzzy rule base is as follows:
if the motor shaft horizontally vibrates | vx|>2mm or vertical vibration | vy|>1mm, the crusher is vibrated abnormally at present;
secondly, if the temperature lot of the lubricating oil is greater than 55 ℃, the temperature of the crusher is higher;
thirdly, if the temperature lot of the lubricating oil is higher than 60 ℃, the temperature of the crusher is too high;
if the differential pressure dof of the oil filter is less than 14kPa, the filter is damaged;
fifthly, if the differential pressure dof of the oil filter is larger than 127kPa, the filter is dirty;
sixthly, if the differential pressure dof of the oil filter is more than 276kPa, the filter is blocked;
seventhly, if the flow of the lubricating oil is qol <549L/min, the oil amount is insufficient;
if the flow of the lubricating oil is qol to 568L/min, the oil amount is excessive;
ninthly, if the current mmc of the main motor is less than 58A, the current is too low;
if main motor current mmc >77A, then the current is too high;
The step (5) comprises the following specific steps: and according to the diagnosis record in the starting operation time, performing function fitting on various fault pre-judgment results by using a least square method and returning to the slope to find and observe the operation state and the fault trend of the crusher.
The invention has the advantages that:
according to the cone crusher fault pre-judging method, the anti-interference capability of the fault diagnosis system is improved by adopting a fuzzy reasoning method, and the false alarm probability and the missing rate are effectively reduced; in the fuzzification process, the mode that the membership function selects the combination of the triangular membership function and the trapezoidal membership function avoids the phenomenon of unreasonable domain division caused by singly using the triangular membership function; the evidence theory is adopted to fuse the reasoning results, so that the diagnosis results fully utilize the information of the crusher, and the fault diagnosis results are more reliable; the trend information of historical data is introduced to be used as auxiliary diagnosis, the missing rate of fault diagnosis is further reduced, and the overall level of fault diagnosis is improved.
Drawings
Fig. 1 is a schematic diagram of the structure of the present invention.
Fig. 2 is a chart of the discourse domain of the return oil temperature of the crusher.
Detailed Description
The following further describes the embodiments of the present invention with reference to the drawings.
As shown in fig. 1 and 2, the method for prejudging the fault of the cone crusher is characterized by comprising the following steps:
(1) vibrating the variable level | v according to the fault threshold and real-time requirements of the crusherxL, vertical vibration | vySelecting a trapezoidal membership function, wherein the functions comprise the temperature lot of lubricating oil, the flow rate qol of the lubricating oil, the current mmc of a main motor and the running noise rn; selecting a trapezoidal membership function and a triangular membership function to combine the differential pressure dof of the variable oil filter and the return oil temperature rot;
(2) establishing a fuzzy rule base according to crusher data which can be collected on site;
(3) carrying out fuzzy reasoning according to a Madiny algorithm to obtain fault membership degree information of each datum;
(4) fusing data with the failure membership degree not being 0 or 1 according to an evidence theory, and comprehensively obtaining a failure pre-judgment result;
(5) and calculating the fault reliability distribution variation trend of multiple diagnoses according to a least square method to assist in diagnosis.
Establishing a fuzzy rule base according to the crusher data which can be collected on site in the step (2), wherein the specifically established fuzzy rule base is as follows:
if the motor shaft horizontally vibrates | vx|>2mm or vertical vibration | vy|>1mm, the crusher is vibrated abnormally at present;
secondly, if the temperature lot of the lubricating oil is greater than 55 ℃, the temperature of the crusher is higher;
thirdly, if the temperature lot of the lubricating oil is higher than 60 ℃, the temperature of the crusher is too high;
if the differential pressure dof of the oil filter is less than 14kPa, the filter is damaged;
fifthly, if the differential pressure dof of the oil filter is larger than 127kPa, the filter is dirty;
sixthly, if the differential pressure dof of the oil filter is more than 276kPa, the filter is blocked;
seventhly, if the flow of the lubricating oil is qol <549L/min, the oil amount is insufficient;
if the flow of the lubricating oil is qol to 568L/min, the oil amount is excessive;
ninthly, if the current mmc of the main motor is less than 58A, the current is too low;
if main motor current mmc >77A, then the current is too high;
The step (5) comprises the following specific steps: and according to the diagnosis record in the starting operation time, performing function fitting on various fault pre-judgment results by using a least square method and returning to the slope to find and observe the operation state and the fault trend of the crusher.
The invention is further explained below with reference to the drawings and the specific examples of the description.
Example data 1: horizontal vibration: | vx1.2mm, vibrate in the vertical direction: | vy0.7mm, lubricating oil temperature: lot 48 ℃, oil filter differential pressure: dof 120kPa, lube oil flow qol 555L/min, main motor current mmc 70A, oil return temperature: rot 42 ℃, running noise: rn is 86 dB.
Example data2: horizontal vibration: | vx1.3mm, vibrate in the vertical direction: | vy0.7mm, lubricating oil temperature: lot 49 ℃, oil filter differential pressure: 125kPa, lubricating oil flow rate qol 560L/min, main motor current mmc 71A, oil return temperature: rot 43 ℃, running noise: rn is 87 dB.
With reference to the attached figure 1, the following steps are carried out:
1) membership function selection
In order to consider the real-time performance of fault prediction, the model accuracy is considered, and meanwhile, the rapidity of model operation is also considered; the triangle membership function operation is simpler than the Gaussian membership function, and the calculation result has certain robustness and is a common fuzzification method; in order to meet the distribution condition of each fault threshold value in the theory domain and the completeness requirement of a fuzzy rule base, vibrating | v on the variable levelxL, vertical vibration | vySelecting a trapezoidal membership function, wherein the functions comprise the temperature lot of lubricating oil, the flow rate qol of the lubricating oil, the current mmc of a main motor and the running noise rn; selecting a trapezoidal membership function and a triangular membership function to combine the differential pressure dof of the variable oil filter and the return oil temperature rot;
the triangular membership function is as follows:
wherein σ>0, σ initial set value of 5, x*In order to be an accurate value,
is a converted fuzzy set; when sigma → 0, the fuzzy set of the triangular membership function becomes a fuzzy single value; when the sigma is large enough, the method has enough anti-interference capability;
the trapezoidal membership function is as follows:
wherein σ1,2>0, initial setting σ1＝σ2＝5，
The high accuracy value for the left side of the trapezoid,
is a high-precision value for the right side of the trapezoid,
is a converted fuzzy set; when in use
Then, the fuzzy set of trapezoidal membership functions becomes the fuzzy set of triangular membership functions.
2) Fuzzy rule base establishment
According to the collected crusher data which can be used for fault prediction, the input of fuzzy reasoning is defined as follows: horizontal vibration | vxL, vertical vibration | vyI, the temperature lot of the lubricating oil, the differential pressure dof of the oil filter, the flow qol of the lubricating oil, the current mmc of a main motor, the temperature rot of return oil and the running noise rn;
establishing a fuzzy rule base according to parameters of the cone crusher as follows:
if the motor shaft horizontally vibrates | vx|>2mm or vertical vibration | vy|>1mm, the crusher is vibrated abnormally at present;
secondly, if the temperature lot of the lubricating oil is greater than 55 ℃, the temperature of the crusher is higher;
thirdly, if the temperature lot of the lubricating oil is higher than 60 ℃, the temperature of the crusher is too high;
if the differential pressure dof of the oil filter is less than 14kPa, the filter is damaged;
fifthly, if the differential pressure dof of the oil filter is larger than 127kPa, the filter is dirty;
sixthly, if the differential pressure dof of the oil filter is more than 276kPa, the filter is blocked;
seventhly, if the flow of the lubricating oil is qol <549L/min, the oil amount is insufficient;
if the flow of the lubricating oil is qol to 568L/min, the oil amount is excessive;
ninthly, if the current mmc of the main motor is less than 58A, the current is too low;
if main motor current mmc >77A, then the current is too high;
3) Fuzzy inference
Different parameters represent fault degrees or types of different types of faults, domain division is carried out according to the parameter range of the crusher, and membership degree interval division is carried out; inputting the data of the cone crusher detected in real time into a fuzzy inference library, and adopting three sections in the inference process according to the existing rules in the library, namely a large precondition, a small precondition and a conclusion, wherein the large precondition is the fuzzy rule in the fuzzy inference library, the small precondition is the data measured in real time, and the conclusion is a possible fault type;
the fuzzy inference algorithm adopts a Mamdani method:
μA→B(x,y)＝[μA(x)∧μB(y)]＝μRmin(x,y) (3)
wherein the subscriptAIndicating conditions, subscripts, in fuzzy rulesBRepresenting the result in the fuzzy rule, A → B representing the knot resulting from condition AB, mu (x) and mu (y) represent membership functions; this step is to calculate the fuzzy relation matrix R, muRmin(x, y) represents an element in R; when a condition is entered, i.e. a "small precondition" a' is given:
μB'(y)＝μA'(x)oR (4)
wherein muB'(y) a membership function, μ, of B' calculated according to the fuzzy rule under the condition AA'Is the membership function of input a'; for the relation that the horizontal vibration and the vertical vibration in the fuzzy rule base pair conclusion that the abnormal vibration is 'OR', the 'large' is taken during the fuzzy operation.
The algorithm is actually used for solving the corresponding membership degree relation of each input value in the divided theoretical domain; FIG. 2 shows the domain partitioning of the return oil temperature of the crusher, which can obtain other data in the same way; substituting the two groups of data to obtain the membership degree information of each fault:
abnormal vibration-unknown 1: 0.4-0.6;
too noisy-unknown 1: 0.44-0.56;
abnormal vibration-unknown 2: 0.6-0.4;
too noisy-unknown 2: 0.48-0.52;
dirty-unclear oil filter 2: 0.71-0.29;
wherein, the number behind the Chinese character represents the group of data; the membership degree data eliminates the fault category with the membership degree of 0 or 1 so as to ensure the rationality of evidence theory use.
4) Non-zero membership fault data fusion
In order to improve the accuracy of fault prejudgment, the current values of all parameters are subjected to fuzzy reasoning and then fused by using an evidence theory; when the membership degree of a certain type of fault through fuzzy reasoning is zero, the evidence is directly removed during evidence theory fusion, because the membership degree of the fault is zero, the fault does not need to be fused, and the evidence can be considered to simplify the calculation of the evidence theory to a certain extent; the central calculation of evidence theory is as follows:
where m (P) is the confidence assignment for the fused fault type P, ms(Ai) Indicates type of failure A before fusioniBasic confidence degree distribution under the s-th parameter, wherein theta is an identification framework; c is a polynomial:
the distribution of the membership interval output by the fuzzy reasoning of each parameter is used as the input of an evidence theory, and a more reliable and comprehensive fault pre-judgment result can be obtained through fusion calculation; the fusion of the data obtained in the previous step can obtain the following fault credibility distribution:
abnormal vibration-excessive noise-unknown 1: 0.272-0.320-0.408;
abnormal vibration-loud noise-dirty oil filter-unknown 2: 0.255-0.157-0.417-0.171;
from the data, a first set of data is known, the fault type is not clear, and a second set of data may exist with the type of oil filter dirty.
5) Trend-assisted diagnosis
According to the diagnosis record in the starting operation time, performing function fitting on various fault pre-judgment results respectively to find and observe the operation state and the fault trend of the crusher; performing primary function fitting by using a least square method, and returning a slope, namely a fault change trend; the least square coefficient calculation formula is as follows:
wherein the content of the first and second substances,
it is the slope of the calculation, i.e. the rate of change of the fault trend,
respectively representing the average values of the time period and the membership degree; the method is used for an auxiliary means of fault pre-judgment, and the missing rate of the fault pre-judgment is reduced as much as possible;
trend change (slope) from first set of data to second set of data
) Respectively as follows:
abnormal vibration-excessive noise-dirty oil filter-unknown: (-0.017) - (-0.163) - (+0.417) - (-0.237); it follows that the type "dirty oil filter" has an increasing trend.
The invention has the advantages that:
according to the cone crusher fault pre-judging method, the anti-interference capability of a fault pre-judging system is improved by adopting a fuzzy reasoning method, and the false alarm probability and the omission factor are effectively reduced; in the fuzzification process, the mode that the membership function selects the combination of the triangular membership function and the trapezoidal membership function avoids the phenomenon of unreasonable domain division caused by singly using the triangular membership function; the evidence theory is adopted to fuse the reasoning results, so that the diagnosis results fully utilize the information of the crusher, and the fault pre-judgment result is more reliable; the classification with the membership degree of 1 or 0 does not participate in evidence theory fusion, so that evidence conflict of the evidence theory is avoided, and the feasibility of the algorithm is ensured; the trend information of historical data is introduced to be used as auxiliary diagnosis, the failure pre-judgment missing rate is further reduced, and the overall level of failure pre-judgment is improved.
Claims (3)
1. A method for prejudging the fault of a cone crusher is characterized by comprising the following steps:
(1) vibrating the variable level | v according to the fault threshold and real-time requirements of the crusherxL, vertical vibration | vySelecting a trapezoidal membership function, wherein the functions comprise the temperature lot of lubricating oil, the flow rate qol of the lubricating oil, the current mmc of a main motor and the running noise rn; selecting a trapezoidal membership function and a triangular membership function for the differential pressure dof and the return oil temperature rot of the variable oil filterCombining degree functions;
(2) establishing a fuzzy rule base according to crusher data which can be collected on site;
(3) carrying out fuzzy reasoning according to a Madiny algorithm to obtain fault membership degree information of each datum;
(4) fusing data with the failure membership degree not being 0 or 1 according to an evidence theory, and comprehensively obtaining a failure pre-judgment result;
(5) and calculating the fault reliability distribution variation trend of multiple diagnoses according to a least square method to assist in diagnosis.
2. The method according to claim 1, wherein the fuzzy rule base is established according to the crusher data collected in the field in the step (2), and the fuzzy rule base is specifically established as follows:
if the motor shaft horizontally vibrates | vx| > 2mm or vertical vibration | vyIf the | is more than 1mm, the crusher vibrates abnormally at present;
secondly, if the temperature lot of the lubricating oil is more than 55 ℃, the temperature of the crusher is higher;
thirdly, if the temperature lot of the lubricating oil is higher than 60 ℃, the temperature of the crusher is too high;
if the differential pressure dof of the oil filter is less than 14kPa, the filter is damaged;
if the differential pressure dof of the oil filter is larger than 127kPa, the filter is dirty;
sixthly, if the differential pressure dof of the oil filter is more than 276kPa, the filter is blocked;
seventhly, if the flow of the lubricating oil is qol <549L/min, the oil quantity is insufficient;
if the flow of the lubricating oil is qol to 568L/min, the oil amount is excessive;
ninthly, if the current mmc of the main motor is less than 58A, the current is too low;
if main motor current mmc >77A, the current is too high;
3. The method for predicting the fault of the cone crusher according to claim 1, wherein the step (5) comprises the following steps: and according to the diagnosis record in the starting operation time, performing function fitting on various fault pre-judgment results by using a least square method and returning to the slope to find and observe the operation state and the fault trend of the crusher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011032108.0A CN112317109B (en) | 2020-09-27 | 2020-09-27 | Cone crusher fault pre-judging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011032108.0A CN112317109B (en) | 2020-09-27 | 2020-09-27 | Cone crusher fault pre-judging method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112317109A true CN112317109A (en) | 2021-02-05 |
| CN112317109B CN112317109B (en) | 2022-02-18 |
Family
ID=74303435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011032108.0A Active CN112317109B (en) | 2020-09-27 | 2020-09-27 | Cone crusher fault pre-judging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112317109B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116911714A (en) * | 2023-09-11 | 2023-10-20 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for transporting articles |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030178515A1 (en) * | 2001-03-01 | 2003-09-25 | Boerhout Johannes I. | System and method of monitoring a crushing device |
| CN101745457A (en) * | 2008-12-12 | 2010-06-23 | 上海建设路桥机械设备有限公司 | Fuzzy control system and control method for gear tooth type crusher |
| CN103028480A (en) * | 2012-12-10 | 2013-04-10 | 上海凯盛节能工程技术有限公司 | Intelligent control system for vertical mill based on fuzzy PID (proportion integration differentiation) algorithm |
| CN105013599A (en) * | 2014-04-29 | 2015-11-04 | 国网山西省电力公司电力科学研究院 | Load adjusting and controlling system and method for coal mill of thermal power generating unit |
| CN106179627A (en) * | 2016-07-09 | 2016-12-07 | 青岛大学 | A kind of grinding chemical mechanical system of feeding speed fuzzy control |
| CN106563537A (en) * | 2016-11-07 | 2017-04-19 | 西安交通大学 | Mill load detection method based on vibration signals of throwing-down area and sliding area of surface of barrel |
| CN110142084A (en) * | 2019-04-09 | 2019-08-20 | 江西理工大学 | Crusher chamber wear monitoring method and its monitoring of structures |
| CN110193420A (en) * | 2019-05-17 | 2019-09-03 | 徐州徐工矿业机械有限公司 | One kind is for movable Crushing screening station failure diagnostic system and method |
| CN110322018A (en) * | 2019-06-19 | 2019-10-11 | 上海电力学院 | A kind of power plant fans fault early warning system based on fuzzy reasoning |
| CN111207067A (en) * | 2019-06-05 | 2020-05-29 | 杭州电子科技大学 | Air compressor fault diagnosis method based on fuzzy support vector machine |
-
2020
- 2020-09-27 CN CN202011032108.0A patent/CN112317109B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030178515A1 (en) * | 2001-03-01 | 2003-09-25 | Boerhout Johannes I. | System and method of monitoring a crushing device |
| CN101745457A (en) * | 2008-12-12 | 2010-06-23 | 上海建设路桥机械设备有限公司 | Fuzzy control system and control method for gear tooth type crusher |
| CN103028480A (en) * | 2012-12-10 | 2013-04-10 | 上海凯盛节能工程技术有限公司 | Intelligent control system for vertical mill based on fuzzy PID (proportion integration differentiation) algorithm |
| CN105013599A (en) * | 2014-04-29 | 2015-11-04 | 国网山西省电力公司电力科学研究院 | Load adjusting and controlling system and method for coal mill of thermal power generating unit |
| CN106179627A (en) * | 2016-07-09 | 2016-12-07 | 青岛大学 | A kind of grinding chemical mechanical system of feeding speed fuzzy control |
| CN106563537A (en) * | 2016-11-07 | 2017-04-19 | 西安交通大学 | Mill load detection method based on vibration signals of throwing-down area and sliding area of surface of barrel |
| CN110142084A (en) * | 2019-04-09 | 2019-08-20 | 江西理工大学 | Crusher chamber wear monitoring method and its monitoring of structures |
| CN110193420A (en) * | 2019-05-17 | 2019-09-03 | 徐州徐工矿业机械有限公司 | One kind is for movable Crushing screening station failure diagnostic system and method |
| CN111207067A (en) * | 2019-06-05 | 2020-05-29 | 杭州电子科技大学 | Air compressor fault diagnosis method based on fuzzy support vector machine |
| CN110322018A (en) * | 2019-06-19 | 2019-10-11 | 上海电力学院 | A kind of power plant fans fault early warning system based on fuzzy reasoning |
Non-Patent Citations (7)
| Title |
|---|
| 乔晓娇等: "基于模糊证据推理的突发事件风险分析模型", 《系统工程理论与实践》 * |
| 孙璐等: "破碎机故障诊断系统总体设计", 《中国矿山工程》 * |
| 孙璐等: "神经网络技术在破碎机故障诊断中的应用", 《矿冶》 * |
| 谢忠秋等: "《应用统计学》", 28 February 2006, 立信会计出版社 * |
| 赵云峰等: "基于模糊和证据理论的变压器本体绝缘状态评估方法", 《电力系统保护与控制》 * |
| 陆晓峰等: "基于Mamdani模糊神经...敏轨道电路故障诊断方法研究", 《铁道标准设计》 * |
| 黄政淳等: "模糊神经网络在破碎机故障诊断系统中的应用", 《微计算机信息》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116911714A (en) * | 2023-09-11 | 2023-10-20 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for transporting articles |
| CN116911714B (en) * | 2023-09-11 | 2023-12-08 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for transporting articles |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112317109B (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chang et al. | A fuzzy multi-criteria decision making method for technology transfer strategy selection in biotechnology | |
| Yeh et al. | Fuzzy assessment of FMEA for a sewage plant | |
| CN112101790B (en) | Water body monitoring video and data linkage early warning method and system | |
| Mariajayaprakash et al. | Optimization of process parameters through fuzzy logic and genetic algorithm–A case study in a process industry | |
| CN104820716A (en) | Equipment reliability evaluation method based on data mining | |
| CN106124982A (en) | Automatic expert's resultant fault diagnostic system of a kind of Wind turbines and diagnostic method | |
| CN112317109B (en) | Cone crusher fault pre-judging method | |
| CN115526422B (en) | Coal mine gas explosion risk prediction method | |
| CN104238530A (en) | Sensor fault diagnosis technology-based interlock alarm system | |
| CN110388315A (en) | Oil transfer pump fault recognition method, apparatus and system based on Multi-source Information Fusion | |
| CN106506485A (en) | Cyberspace security postures perception analysis method and system | |
| CN111126853B (en) | Hydraulic engineering risk early warning analysis method and system based on fuzzy FMEA | |
| CN104571084A (en) | Further diagnosis method and device for root causes of failure of main fan set | |
| CN114385765B (en) | Production time prediction method of trailing suction hopper dredger based on track data | |
| CN105005644A (en) | Method for detecting fault of three-phase asynchronous motor | |
| CN105160147B (en) | A kind of cutter changing time decision-making technique based on state-space model and fuzzy theory | |
| CN204086977U (en) | A kind of interlock alarm system based on sensor fault diagnosis technology | |
| CN116735222A (en) | Method for detecting fault of lubricating oil filter of gas turbine | |
| KR102155384B1 (en) | Information processing system and method for monitoring a complex system | |
| CN116165939A (en) | Remote supervision system and method for environmental protection equipment based on big data | |
| CN109840563A (en) | A kind of Fault Diagnosis of Fan method based on three-dimensional membership function fuzzy logic system | |
| CN111199504B (en) | Block chain-based decentralization fire control maintenance supervision method | |
| Amiri et al. | Economic-statistical design of adaptive X-bar control chart: a Taguchi loss function approach | |
| CN115212996A (en) | Fault diagnosis system for coal mill | |
| CN107371125A (en) | Wireless sensor network fault restorative procedure and device based on particle cluster algorithm |
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 |