CN117566379A - Fault diagnosis method and device for mining belt conveyor system - Google Patents
Fault diagnosis method and device for mining belt conveyor system Download PDFInfo
- Publication number
- CN117566379A CN117566379A CN202210925611.1A CN202210925611A CN117566379A CN 117566379 A CN117566379 A CN 117566379A CN 202210925611 A CN202210925611 A CN 202210925611A CN 117566379 A CN117566379 A CN 117566379A
- Authority
- CN
- China
- Prior art keywords
- belt conveyor
- data
- matrix
- module
- fault
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005065 mining Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 54
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 80
- 238000013500 data storage Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 4
- 230000003416 augmentation Effects 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000012369 In process control Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010965 in-process control Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/02—Control devices, e.g. for safety, warning or fault-correcting detecting dangerous physical condition of load carriers, e.g. for interrupting the drive in the event of overheating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/02—Control or detection
- B65G2203/0266—Control or detection relating to the load carrier(s)
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Conveyors (AREA)
Abstract
The invention provides a fault diagnosis method and device for a mining belt conveyor system, and relates to the technical field of fault diagnosis. Including offline modeling and online fault diagnosis. For offline modeling, establishing a model of the belt conveyor system based on subspace identification technology; for online fault diagnosis, initializing parameters, and obtaining a fault diagnosis residual value and a fault detection threshold value; on-line calculating fault diagnosis monitoring quantity, and judging whether the variable exceeds a fault detection threshold value or not; if the threshold value is exceeded, a fault exists, and an alarm is given. The invention can diagnose whether the belt conveyor system has faults in real time, accurately provides alarm information for field staff, and provides decision basis for operation adjustment and equipment operation and maintenance of the production process.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method and device for a mining belt conveyor system.
Background
A belt conveyor is a device that conveys materials in a continuous manner by friction drive. The belt conveyor is widely applied to industries such as wharfs, mines, metallurgy, grains, papermaking and the like. In the mine field, belt conveyors are mainly used for the transport of ores. Under complex geological conditions and severe environments, mine transportation faces serious challenges of variable working conditions and large load randomness, so that benign operation of a transportation system is ensured through overall process management of mine transportation. Belt conveyor systems are the most important element in the transportation of ores. If the link fails, the equipment efficiency and the transportation efficiency are directly reduced, even the system is stopped and the production is interrupted, and the yield is affected. In real production, belt conveyors often fail due to mineral plugging problems and overload problems. If the on-line fault diagnosis of the belt conveyor system is realized, the abnormal working conditions are detected, production operation and maintenance personnel are prompted to intervene in time, production is regulated, equipment is checked, and the method has important significance in guaranteeing production and equipment management.
Aiming at the problem that the No. 1 belt conveyor conveys ores to the No. 2 belt conveyor, the ores are blocked or overloaded. The quantity of ores carried on the belt conveyor 1 and the belt conveyor 2 can be reflected from the side by the current detected by the belt conveyor 1 and the belt conveyor 2 in the running process, and the current quantity data of the belt conveyor 1 and the belt conveyor 2 can be acquired by means of an electric dragging system of equipment. Based on considering the system mechanism characteristics, the method fully analyzes the data of the electric current of the No. 1 and No. 2 belt conveyor to diagnose faults, and is a simple, effective and low-cost fault diagnosis method of the belt conveyor system. And alarm the blocking condition in time, so as to avoid subsequent hazard upgrading.
The invention patent 202111347306.0 'system for detecting the faults of the coal conveying belt' essentially completes the task of judging the faults based on different training sets by analyzing real-time belt images, the neural network has no better interpretation, the diagnosis result often lacks persuasion, and at least two identical industrial cameras are needed when the method is implemented, so that the device cost is higher. The invention patent with the application number of 202011355753.6, namely a vibration signal amplifying device for monitoring belt faults, proposes to judge abnormal vibration of a belt by physically amplifying fault vibration frequency when the belt runs, and the device needs to be provided with a vibration sensor, so that fault diagnosis cost is increased; and the service life state parameter of the belt needs to be acquired, and the parameter cannot be accurately acquired. In the two methods, a more complex method is adopted to judge whether the belt conveyor is in fault or not.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a fault diagnosis method and device for a mining belt conveyor system, which can diagnose whether the mining belt conveyor system has faults or not in real time, accurately provide alarm information for production personnel and provide decision basis for operation adjustment and equipment operation and maintenance of the production process.
In order to solve the technical problems, the invention adopts the following technical scheme:
in one aspect, the invention provides a fault diagnosis method for a mining belt conveyor system, which comprises the following steps:
setting a No. 1 belt conveyor to convey goods to a No. 2 belt conveyor, taking a current value of the No. 1 belt conveyor as an input variable of a subspace identification algorithm, taking the current value of the No. 2 belt conveyor as an output variable, namely a predicted current value of the No. 2 belt conveyor, initializing parameters, obtaining a subspace identification model of a belt conveyor system through offline modeling, establishing an extended state space model by using fault-free data, calculating to obtain an extended observable matrix and a Toeplitz matrix based on a subspace identification technology, and obtaining a coefficient matrix estimated value;
on-line diagnosis initialization parameters including initialization model orders, setting modeling data set length, data matrix expansion dimension, input and output variable dimension, confidence level, fault detection threshold, input and output variable filter coefficients, and loading coefficient matrix estimated values calculated by off-line modeling;
collecting current value data of the No. 1 belt conveyor and the No. 2 belt conveyor at the current moment on line, and storing the current value data; filtering and storing the acquired data;
establishing an online expansion state space model by using the coefficient matrix estimated value calculated by offline modeling, and calculating and outputting a predicted current value and a residual error value of the No. 2 belt conveyor; calculating a monitoring quantity by using a variance matrix of the residual error;
and judging whether the monitoring quantity exceeds a fault detection threshold value to perform fault detection, and outputting an alarm signal.
Further, in offline modeling, the current value of the No. 1 belt conveyor is used as an input variable I of a subspace identification algorithm 1 (k)∈R l Predicted current value of No. 2 belt conveyor as output variablex is a state vector, W, T, G, Q is a system matrix, k is a sampling time, and a state space model of discrete time is established as follows:
x(k+1)=Wx(k)+TI 1 (k)
in matrix sequenceWherein p represents the number of past data, f represents the number of future data, N represents the system order, N represents the expansion dimension of the data matrix, l is the input variable dimension, and m is the output variable dimension, wherein p is more than or equal to f > N; input variable delta (k), output variable E (k), future Hankel input matrix delta f The past Hankel input matrix delta p And a future Hankel output matrix E f The definition is as follows:
Δ(k)=[I 1 (k) I 1 (k+1) … I 1 (k+N-1)]∈R l×N
based on the state space model, the extended state space model is expressed as,
wherein X is k For a state sequence, the following is defined:
X k =[x(k)x(k+1) … x(k+N-1)]∈R n×N
wherein, the observable matrix xi is expanded f And Toeplitz matrixEach having the form:
obtaining based on subspace identification technologyAnd->Is a function of the estimated value of (2); />Is xi f Is a space orthogonal to (a); identify->Andthe process of (2) is as follows:
first collecting data, forming an augmentation data matrix V by input and output data f ;
For an augmented data matrix V f SVD decomposition is carried out:
wherein A consists of the first (lf+n) left singular vectors corresponding to non-zero singular values in Σ, A ⊥ Left singular vectors, which are the remaining (mf-n), which correspond to zero singular values in Σ; similar to A and A ⊥ B and B ⊥ Consists of right singular vectors;
let A ⊥T The front mf column and the rear lf column of (A) are respectively A mf And A lf Then the extended observable matrix xi can be obtained f And Toeplitz matrix
Due to the sum of xi fIs composed of a system matrix W, T, G, Q, so W, G is directly extended from the observable matrix xi f Is extracted from the structure of (2); after estimating the system matrices W and G, the system matrices W and G are then divided by the Toeplitz matrix using least squares>Estimating system matrixes T and Q; thereby obtaining an estimated value of the system matrix W, T, G, Q in the state space model of the current relationship of the conveyor belt.
In the on-line diagnosis, the current value of the No. 1 belt conveyor is used as an input variable I 1 (k) The extended state space model is established through the estimated value of the identified coefficient matrix W, T, G, Q and expressed as:obtaining a current predictive value of the No. 2 belt conveyor>Defining the output residual signal expression of the system as:
calculating variance matrix sigma of residual r And storing a variance matrix of the residual error;
the monitoring quantity J is calculated through the obtained residual signal r (k), and is compared with a fault detection threshold value, so that fault detection is realized, and the specific process is as follows:
first, determining chi-square distribution of fault detection threshold α And set a fault detection threshold J th ,J th =χ α /2;
Defining a monitoring amount J, and calculating the monitoring amount J through a residual signal r (k):
wherein sigma r A variance matrix for the residual;
defining a fault detection method:
and comparing the monitored quantity with a threshold value, thereby realizing fault detection.
On the other hand, the invention also provides a fault diagnosis device of the mining belt conveyor system, which comprises an offline modeling module and an online diagnosis module;
the off-line modeling module is used for off-line establishing a subspace identification model of the belt conveyor system; after the module models the initialization parameters offline, calculating to obtain an observable matrix, a Toeplitz matrix and an estimated value of a coefficient matrix, and providing the estimated value of the coefficient matrix to an online diagnosis module;
the online diagnosis module is used for diagnosing the faults of the belt conveyor system online and receiving the parameters output by the offline modeling module; the module acquires current value data of the No. 1 belt conveyor and the No. 2 belt conveyor on line, performs fault detection, and outputs alarm prompts.
The online diagnosis module comprises an initialization module, a data acquisition and filtering module, a fault detection module and a data storage module;
the initialization module is used for initializing the order of the model, setting the length of a modeling data set, the extension dimension of a data matrix, the dimension of input and output variables, the confidence level, the fault detection threshold value, the filter coefficients of the input and output variables and loading the estimated value of the coefficient matrix from the data storage module.
The data acquisition and filtering module is used for acquiring current value data of the No. 1 belt conveyor at the current moment, simultaneously acquiring current of the No. 2 belt conveyor at the current moment, and storing the acquired data into the data storage module; filtering calculation is carried out on the collected data, and the filtered output data is stored in a data storage module;
the fault detection module is used for calculating and outputting a predicted current value, a residual value and a monitoring quantity of the No. 2 belt conveyor; before calculation, reading historical acquisition data and historical prediction data from a data storage module, and outputting the results of the prediction current, the residual value and the monitoring quantity calculated in the period to the data storage module for storage; judging whether the calculated monitoring quantity is larger than a fault detection threshold value, if not, indicating that no fault occurs, and collecting data at the next moment to perform new calculation; if yes, indicating that a fault occurs, and outputting an alarm signal;
the data storage module is used for storing various variables of the initialization module: initializing a model order, modeling a data set length, an expansion dimension of a data matrix, an input and output variable dimension, a confidence level, a threshold value, a filter coefficient of an input and output variable, an estimated value of a coefficient matrix, currents of No. 1 and No. 2 belt conveyors in data collection, output data of a filter module and residual signals calculated each time, and providing historical filter data, historical collection data, historical prediction data, monitoring quantity and residual values before calculation of a fault detection module.
The beneficial effects of adopting above-mentioned technical scheme to produce lie in: the fault diagnosis method and device for the mining belt conveyor system can diagnose the whole system in real time based on the belt conveyor electric current data of No. 1 and No. 2, can accurately provide fault diagnosis information for production personnel, has definite physical meaning of diagnosis results, has strong interpretation, and can provide important basis for production, operation and maintenance decisions. The invention fully utilizes the No. 1 and No. 2 belt conveyor electric current data to diagnose the system faults on the basis of considering the system mechanism characteristics, and a sensor is not required to be additionally installed, so that the invention is a simple, effective and low-cost fault diagnosis method.
Drawings
FIG. 1 is a flow chart of a fault diagnosis method of a mining belt conveyor system provided by an embodiment of the invention;
FIG. 2 is a mining belt conveyor system according to an embodiment of the invention;
FIG. 3 is a flowchart of an online fault diagnosis method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a fault diagnosis device for a conveying process of a mining belt conveyor, which is provided by the embodiment of the invention.
FIG. 5 shows the output current detection result of the mining belt conveyor provided by the embodiment of the invention in a fault-free state in the conveying process; wherein, the graph (5 a) is a current value curve of the No. 1 belt conveyor in a fault-free state, the graph (5 b) is a comparison curve of a current value and a predicted current value of the No. 2 belt conveyor in the fault-free state, the graph (5 c) is a current prediction residual error value curve of the No. 2 belt conveyor in the fault-free state, and the graph (5 d) is a fault detection result in the fault-free state; FIG. 5e is an enlarged view of a portion of FIG. 5 b;
FIG. 6 is a detection result of a blocking fault of the No. 1 belt conveyor in the conveying process of the mining belt conveyor provided by the embodiment of the invention; wherein, the graph (6 a) is a current value curve of the No. 1 belt conveyor under the fault, the graph (6 b) is a comparison curve of a current value and a predicted current value of the No. 2 belt conveyor under the fault, the graph (6 c) is a current predicted residual error value curve of the No. 2 belt conveyor under the fault, and the graph (6 d) is a fault detection result under the fault;
fig. 7 is a detection result of overload faults of the No. 2 belt conveyor in the conveying process of the mining belt conveyor provided by the embodiment of the invention; wherein, fig. 7a is a current value curve of the No. 1 belt conveyor under the fault, fig. 7b is a comparison curve of a current value and a predicted current value of the No. 2 belt conveyor under the fault, fig. 7c is a current predicted residual error value curve of the No. 2 belt conveyor under the fault, and fig. 7d is a fault detection result under the fault.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1, the embodiment provides a fault diagnosis method for a mining belt conveyor system, which is specifically described below.
The mining belt conveyor system of this embodiment is composed of a No. 1 belt conveyor and a No. 2 belt conveyor, as shown in fig. 2. The current of the belt conveyor is integrated into the plant DCS (Distributed Control System, decentralized control system). The current value of the No. 1 belt conveyor is used as an input variable of a subspace identification algorithm and is recorded as I at the moment k 1 (k),I 1 (k)∈R l The predicted current value of the No. 2 belt conveyor is taken as an output variable and is recorded as the k momentSince p.gtoreq.f > n, p=10, f=5, system state x (k), n=2, l=m=1, n=7 are taken in this embodiment.
Selecting 2-5 sections I 1 (k) Time series data with larger fluctuation and normal operation of the system are spliced to be used as a normal working condition data set. Each sample of the dataset is { I } 1 (k)、I 2 (k) The length of the data set is denoted as L, the length of the effective data set is denoted as L-f, and the data set is used to establish a subspace identification model of the belt conveyor system offline according to steps S101-S102 in FIG. 1.
The subspace identification model of the belt conveyor system is established as follows:
current value of No. 1 belt conveyor is used as input variable I of subspace identification algorithm 1 (k)∈R l Predicted current value of No. 2 belt conveyor as output variablex is a state vector, W, T, G, Q is a system matrix, k is a sampling time, and a state space model of discrete time is established as follows:
x(k+1)=Wx(k)+TI 1 (k)
wherein the input/output vectors and the Hankel input/output matrices in the past and future are:
Δ(k)=[I 1 (k)I 1 (k+1) … I 1 (k+7-1)]∈R 1×7
E(k)=[I 2 (k)I 2 (k+1) … I 2 (k+7-1)]∈R 1×7
the extended state space model is:
wherein,
the input/output data is then formed into an augmentation matrix V 5 :
For an augmented data matrix V f SVD decomposition is carried out:
let A ⊥T The first 5 columns and the last 5 columns of (A) 5 And a 5 Then there is
Thereby identifyingAnd-> Is xi 5 And then an estimated value of the coefficient matrix W, T, G, Q.
Therefore, the current value I of the No. 1 belt conveyor 1 (k) As input, the current prediction output value of the No. 2 belt conveyor can be obtained through the identified state space modelDefining the output residual signal expression of the system as:
referring to an on-line fault diagnosis flowchart of a fault diagnosis method of a belt conveyor system shown in fig. 3, the method includes the following steps S501 to S507.
S501, initializing, including initializing the order N of a model, setting the length of a modeling data set, the expansion dimension N of a data matrix, and input and outputVariable dimensions l and m, confidence α, fault detection threshold, filter coefficients μ for input and output variables I1 、μ I2 The coefficient matrix W, T, G, Q is loaded.
In this embodiment, the confidence level α=0.05 is set, and I is input 1 (k) Filter coefficient mu I2 =0.8,μ I1 =0.9. Let p=10, f=5, system state x (k), let n=2, l=m=1, n=7. The fault detection threshold J is calculated by the following method th :
J th =γ 0.05 /2
S502, collecting { I } at the current k moment from DCS 1 (k)、I 2 (k) Reading { I } from DCS historian database 1 (k-1),I 2 (k-1)}、{I 1 (k-2),I 2 (k-2)}、{I 1 (k-3),I 2 (k-3)}、{I 1 (k-4),I 2 (k-4)}。
S503, calculating I according to the following formula 2 (k) Filtered valuesAnd stores:
calculate I as follows 1 (k) Filtered valuesAnd stores:
s504, calculating a predicted output value according to the following formulaThus obtaining E' f And stored therein.
S505, the residual signal r (k) is calculated and stored as follows.
S506, the monitoring amount J is calculated according to the following formula and stored.
S507, judging whether the monitoring amount J is greater than the fault detection threshold J th 。
If not, step S502 is skipped.
If yes, alarming the 'belt conveyor fault', writing back to the DCS, and jumping to the step S502.
In the specific implementation process, if the fault diagnosis and analysis method flow can be continuously performed, or the flow is ended.
In summary, according to the fault diagnosis method provided by the embodiment of the invention, the fault diagnosis of the belt conveyor system can be realized by using the current values of the No. 1 and No. 2 belt conveyors, and fault alarm is provided for operators.
The embodiment also provides a fault diagnosis device of the mining belt conveyor system, which comprises an offline modeling module and an online diagnosis module as shown in fig. 4.
And the off-line modeling module is used for off-line establishing a linear subspace identification model of the belt conveyor system. The module provides the coefficient matrix W, T, G, Q found by the model to an online diagnostic module.
And the online diagnosis module is used for diagnosing the faults of the belt conveyor system online. And receiving each parameter output by the offline modeling module. The module acquires DCS data on line, performs fault detection, and writes the result back to the DCS.
The online diagnosis module comprises the following sub-modules: the system comprises an initialization module, a data acquisition and filtering module, a fault detection module and a data storage module.
An initialization module for initializing the model order n, the modeling data set length L, the parameter p, f, N, L, the confidence coefficient alpha, loading the coefficient matrix W, T, G, Q, and calculating the fault detection threshold J th The amount J is monitored.
The data acquisition and filtering module is used for establishing communication with the DCS and acquiring a No. 1 belt conveyor current value I at the current k moment from the DCS 1 (k) The current value I of the No. 2 belt conveyor at the current moment is collected simultaneously 2 (k) And collecting historical data. The communication protocol used in this embodiment may be OPC UA (Object Linking and Embedding for Process Control Unified Architecture, unified architecture of object linking and embedding technology in process control) or other communication interfaces or APIs (Application Programming Interface, application program interface) supported by the control system. The module pair I 1 (k)、I 2 (k) Filtering calculation is carried out to obtainReading from a data storage module prior to computationAnd outputting the filtering result to a data storage module for storage.
The fault detection module is used for calculating and outputting a predicted current value, a residual value and a monitoring quantity of the No. 2 belt conveyor. Reading historical data from the data storage module before calculation and calculating the result of the periodr (k) and the monitoring quantity J are output to a data storage module for storage; judging whether the monitoring quantity J is larger than the fault detection threshold J th And writing the alarm information back to the control system.
The data storage module is used for storing the calculation of the data acquisition and filtering module each timeAnd provided prior to calculation by this module/>Also for storing the +.>r (k) and the monitored quantity J, and provides historical data before calculation by this module.
By using the device and the method of the embodiment, the fault detection is carried out on the current data of the No. 1 belt conveyor and the No. 2 belt conveyor in a certain mine beneficiation 14000T control system, and three detection results as shown in fig. 5, 6 and 7 are obtained. The ore is transferred from the No. 1 belt conveyor to the No. 2 belt conveyor, and the current trend of No. 1 and No. 2 should be consistent. If not, a failure may occur.
As shown in fig. 5, the detection result is a normal fault-free detection result, and the monitored amount in fig. 5d does not exceed the threshold line, and therefore, the detection result is a fault-free detection result in a case where the monitored amount is smaller than the threshold value.
As shown in fig. 6, in the graph (6 d), it can be seen that the monitored amount exceeds the threshold value at 4796, and a fault occurs, so that the cause of the fault needs to be analyzed: the current of the No. 1 belt conveyor is shown in the figure (6 a), the current value is 265.76 at the time of 4794, the current value is 279.88 at the time of 4795, the current belongs to the rising stage, and the current detected by the No. 1 belt conveyor and the No. 2 belt conveyor in the running process can reflect the quantity of the ore carried on the No. 1 belt conveyor from the side surface, so that the larger the quantity of the ore is, the larger the current is. At this time, it was analyzed that the amount of ore on the No. 1 belt conveyor was increasing. Fig. 6b shows the current of the No. 2 belt conveyor, and it can be seen from this figure that the current value is 95.18 at 4794, 90.36 at 4795, and the number of ores on the No. 2 belt conveyor is decreasing when the current falls. From this analysis, the No. 1 belt conveyor was found to have a material blockage.
As shown in fig. 7, in the graph (7 d), it can be seen that the monitored amount exceeds the threshold value at 4145, and a fault occurs, so that the cause of the fault needs to be analyzed: fig. 7a shows the current of the No. 1 belt conveyor, the current value is 131.88 at 4143, the current value is 118 at 4144, the current belongs to the descending stage, and the current detected by the No. 1 belt conveyor and the No. 2 belt conveyor in the running process can reflect the quantity of the ore carried on the No. 1 belt conveyor from the side surface, so that the larger the quantity of the ore is, the larger the current is. At this time, it was analyzed that the amount of ore on the No. 1 belt conveyor was decreasing. Fig. 7b shows the current of the No. 2 belt conveyor, and it can be seen from this figure that the current value is 125.08 at 4143 and 130.78 at 4144, and the current belongs to the rising stage, and the number of ores on the No. 2 belt conveyor increases. The overload condition of the No. 2 belt conveyor is illustrated.
The method and the device can diagnose whether the belt conveyor system has faults in real time, accurately provide alarm information for field staff, and provide decision basis for operation adjustment and equipment operation and maintenance of the production process.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions, which are defined by the scope of the appended claims.
Claims (8)
1. A fault diagnosis method for a mining belt conveyor system is characterized by comprising the following steps of: the method comprises offline modeling and online diagnosis;
firstly, setting a current value of the No. 1 belt conveyor to convey cargoes to the No. 2 belt conveyor, wherein the current value of the No. 1 belt conveyor is used as an input variable of a subspace identification algorithm, and the current value of the No. 2 belt conveyor is used as an output variable, namely a predicted current value of the No. 2 belt conveyor; after initializing parameters, obtaining a subspace identification model of the belt conveyor system through offline modeling, establishing an extended state space model by using fault-free data, and calculating an extended observable matrix and a Toeplitz matrix based on subspace identification technology so as to obtain a coefficient matrix estimated value;
on-line diagnosing initialization parameters, and collecting and storing current value data of the No. 1 belt conveyor and the No. 2 belt conveyor at the current moment; filtering and storing the acquired data;
establishing an online expansion state space model by using the coefficient matrix estimated value calculated by offline modeling, and calculating and outputting a predicted current value and a residual error value of the No. 2 belt conveyor; calculating a monitoring quantity by using a variance matrix of the residual error;
and judging whether the monitoring quantity exceeds a fault detection threshold value to perform fault detection, and outputting an alarm signal.
2. The mining belt conveyor system fault diagnosis method according to claim 1, characterized in that: the initialization parameters before offline modeling and the online diagnosis initialization parameters comprise an initialization model order, and the modeling data set length, the expansion dimension of a data matrix, the dimension of input and output variables, the confidence coefficient, the fault detection threshold value and the filter coefficients of the input and output variables are set; the on-line diagnosis initialization further comprises loading coefficient matrix estimated values calculated by off-line modeling.
3. The mining belt conveyor system fault diagnosis method according to claim 2, characterized in that: in the offline modeling, the current value of the No. 1 belt conveyor is used as an input variable I of a subspace identification algorithm 1 (k)∈R l Predicted current value of No. 2 belt conveyor as output variablex is a state vector, W, T, G, Q is a system matrix, k is a sampling time, and a state space model of discrete time is established as follows:
x(k+1)=Wx(k)+TI 1 (k)
in the matrix sequence, p represents the number of past data, f represents the number of future data, N represents the system order, N represents the expansion dimension of the data matrix, l is the input variable dimension, and m is the output variable dimension, wherein p is more than or equal to f > N; input variable delta (k), output variable E (k), future Hankel input matrix delta f The past Hankel input matrix delta p And a future Hankel output matrix E f The definition is as follows:
Δ(k)=[I 1 (k) I 1 (k+1)…I 1 (k+N-1)]∈R l×N
based on the state space model, the extended state space model is expressed as,
wherein X is k For a state sequence, the following is defined:
X k =[x(k) x(k+1)…x(k+N-1)]∈R n×N
wherein, the observable matrix xi is expanded f And Toeplitz matrixEach having the form:
obtaining based on subspace identification technologyAnd->Is a function of the estimated value of (2); />Is xi f Is a space orthogonal to the (c) plane.
4. The mining belt conveyor system fault diagnosis method according to claim 3, characterized in that: obtaining based on subspace identification technologyAnd->The procedure for the estimation of (2) is as follows:
first collecting data, forming an augmentation data matrix V by input and output data f ;
For an augmented data matrix V f SVD decomposition is carried out:
wherein A consists of the first (lf+n) left singular vectors corresponding to non-zero singular values in Σ, A ⊥ Left singular vectors, which are the remaining (mf-n), which correspond to zero singular values in Σ; similar to A and A ⊥ B and B ⊥ Consists of right singular vectors;
order theThe front mf column and the rear lf column of (A) are respectively A mf And A lf Then the extended observable matrix xi can be obtained f And Toeplitz matrix
Due to xi f Andis composed of a system matrix W, T, G, Q, so W, G is directly extended from the observable matrix xi f Is extracted from the structure of (2); after estimating the system matrices W and G, the system matrices W and G are then divided by the Toeplitz matrix using least squares>Estimating system matrixes T and Q; thereby obtaining an estimated value of the system matrix W, T, G, Q in the state space model of the current relationship of the conveyor belt.
5. The mining belt conveyor system fault diagnosis method according to claim 4, characterized in that: in the on-line diagnosis, the current value of the No. 1 belt conveyor is used as an input variable I 1 (k) The extended state space model is established through the estimated value of the identified coefficient matrix W, T, G, Q and expressed as:obtaining a current predictive value of the No. 2 belt conveyor>Defining the output residual signal expression of the system as:
calculating variance matrix sigma of residual r And storing a variance matrix of the residual error;
and calculating a monitoring quantity J through the obtained residual signal r (k), and comparing the monitoring quantity with a fault detection threshold value so as to realize fault detection.
6. The mining belt conveyor system fault diagnosis method according to claim 5, characterized in that: the specific process of fault detection is as follows:
first, determining chi-square distribution of fault detection threshold α And set a fault detection threshold J th ,J th =χ α /2;
Defining a monitoring amount J, and calculating the monitoring amount J through a residual signal r (k):
wherein sigma r A variance matrix for the residual;
the fault detection method is defined as follows:
and comparing the monitored quantity with a threshold value to obtain a fault detection result.
7. A fault diagnosis device for a mining belt conveyor system, which is used for realizing the fault diagnosis method for the mining belt conveyor system according to claim 1, and is characterized in that: the device comprises an offline modeling module and an online diagnosis module;
the off-line modeling module is used for off-line establishing a subspace identification model of the belt conveyor system; after the module models initialization parameters offline, an extended state space model is established through fault-free data, an observable matrix, a Toeplitz matrix and a coefficient matrix estimated value are obtained through calculation based on subspace identification technology, and the coefficient matrix estimated value is provided for an online diagnosis module;
the online diagnosis module is used for diagnosing the faults of the belt conveyor system online and receiving the parameters output by the offline modeling module; after initializing parameters online, the module establishes an online expansion state space model by using coefficient matrix estimated values calculated by offline modeling, and calculates and outputs a predicted current value and a residual error value of the No. 2 belt conveyor; calculating a monitoring quantity by using a variance matrix of the residual error; and judging whether the monitoring quantity exceeds a fault detection threshold value to perform fault detection, and outputting an alarm prompt.
8. The mining belt conveyor system fault diagnosis device of claim 7, wherein: the online diagnosis module comprises an initialization module, a data acquisition and filtering module, a fault detection module and a data storage module;
the initialization module is used for initializing the order of the model, setting the length of a modeling data set, the expansion dimension of a data matrix, the dimension of input and output variables, the confidence level, the fault detection threshold value, the filter coefficients of the input and output variables and loading the estimated value of the coefficient matrix from the data storage module;
the data acquisition and filtering module is used for acquiring current value data of the No. 1 belt conveyor at the current moment, simultaneously acquiring current of the No. 2 belt conveyor at the current moment, and storing the acquired data into the data storage module; filtering calculation is carried out on the collected data, and the filtered output data is stored in a data storage module;
the fault detection module is used for calculating and outputting a predicted current value, a residual value and a monitoring quantity of the No. 2 belt conveyor; before calculation, reading historical acquisition data and historical prediction data from a data storage module, and outputting the results of the prediction current, the residual value and the monitoring quantity calculated in the period to the data storage module for storage; judging whether the calculated monitoring quantity is larger than a fault detection threshold value, if not, indicating that no fault occurs, and collecting data at the next moment to perform new calculation; if yes, indicating that a fault occurs, and outputting an alarm signal;
the data storage module is used for storing various variables of the initialization module: initializing a model order, modeling a data set length, an expansion dimension of a data matrix, an input and output variable dimension, a confidence level, a threshold value, a filter coefficient of an input and output variable, an estimated value of a coefficient matrix, currents of No. 1 and No. 2 belt conveyors in data collection, output data of a filter module and residual signals calculated each time, and providing historical filter data, historical collection data, historical prediction data, monitoring quantity and residual values before calculation of a fault detection module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210925611.1A CN117566379A (en) | 2022-08-03 | 2022-08-03 | Fault diagnosis method and device for mining belt conveyor system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210925611.1A CN117566379A (en) | 2022-08-03 | 2022-08-03 | Fault diagnosis method and device for mining belt conveyor system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117566379A true CN117566379A (en) | 2024-02-20 |
Family
ID=89890516
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210925611.1A Pending CN117566379A (en) | 2022-08-03 | 2022-08-03 | Fault diagnosis method and device for mining belt conveyor system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117566379A (en) |
-
2022
- 2022-08-03 CN CN202210925611.1A patent/CN117566379A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7017861B2 (en) | Anomaly detection system and anomaly detection method | |
JP7282184B2 (en) | Systems and methods for detecting and measuring anomalies in signals originating from components used in industrial processes | |
US7308385B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
US20140365179A1 (en) | Method and Apparatus for Detecting and Identifying Faults in a Process | |
JP5179086B2 (en) | Industrial process monitoring method and monitoring system | |
US20120271782A1 (en) | Method and apparatus for event detection permitting per event adjustment of false alarm rate | |
US11630028B2 (en) | Method and controller for deciding whether a bearing is faulty or not | |
US11436693B2 (en) | Machine learning device and machine learning method for learning correlation between shipment inspection information and operation alarm information for object | |
US20190180152A1 (en) | Data driven method for automated detection of anomalous work pieces during a production process | |
Lahdhiri et al. | A new fault detection index based on Mahalanobis distance and kernel method | |
CN114398800B (en) | Fault diagnosis method and device for crusher system | |
CN117932322B (en) | Flour equipment fault diagnosis method and system | |
Roemer et al. | Prognostics | |
Kubota et al. | Anomaly detection from online monitoring of system operations using recurrent neural network | |
CN117566379A (en) | Fault diagnosis method and device for mining belt conveyor system | |
CN112733446A (en) | Data-driven self-adaptive anomaly detection method | |
JP6579163B2 (en) | Process condition diagnosis method and condition diagnosis apparatus | |
CN112052714A (en) | Data-driven machine learning for modeling aircraft sensors | |
US20230177406A1 (en) | Device and method for interpreting a predicting of at least one failure of a system | |
CN112966785B (en) | Intelligent constellation state identification method and system | |
Aggoune et al. | Neyman–Pearson Test for Fault Detection in the Process Dynamics | |
CN110045716B (en) | Method and system for detecting and diagnosing early fault of closed-loop control system | |
Fuente et al. | Fault detection and identification method based on multivariate statistical techniques | |
CN113454553B (en) | System and method for detecting and measuring anomalies in signaling originating from components used in industrial processes | |
CN118172910A (en) | Safety pre-warning system of coal mine overhead manned device based on convolutional neural network |
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 |