CN116679669B - Screening system fault diagnosis method and system - Google Patents
Screening system fault diagnosis method and system Download PDFInfo
- Publication number
- CN116679669B CN116679669B CN202310669448.1A CN202310669448A CN116679669B CN 116679669 B CN116679669 B CN 116679669B CN 202310669448 A CN202310669448 A CN 202310669448A CN 116679669 B CN116679669 B CN 116679669B
- Authority
- CN
- China
- Prior art keywords
- output
- screening system
- vibrating screen
- variable
- input
- 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
- 238000012216 screening Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003745 diagnosis Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 92
- 238000001914 filtration Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 14
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 9
- 238000013500 data storage Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000009191 jumping Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011151 fibre-reinforced plastic Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a screening system fault diagnosis method and a screening system fault diagnosis system, wherein the method comprises the following steps: the method comprises the steps that an integral input variable and an integral output variable of a screening system under normal working conditions are obtained in an offline modeling part, and an input/output model is built; the method comprises the steps that an integral input variable and an integral output variable of a screening system, and a single input variable and a single output variable of each vibrating screen system are obtained at the current moment in an online diagnosis part; based on the method and combining an input/output model, obtaining a screening system monitoring amount, a screening system monitoring amount threshold value, each vibrating screen monitoring amount and each vibrating screen monitoring amount threshold value; and comparing the obtained monitoring quantity with a corresponding monitoring quantity threshold value to judge whether the screening system has faults or not. The invention can diagnose whether the screening system has faults and fault categories 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.
Description
Technical Field
The invention belongs to the technical field of data analysis, and particularly relates to a screening system fault diagnosis method and system.
Background
The vibrating screen is mainly applied to screening operation and is widely applied to a plurality of industries such as mines, coal, cement, building materials and the like. The principle of the vibrating screen is as follows: after the material falls into the vibrating screen, the material rapidly advances, loosens and passes through the screen, so that the separation of different granularity in the material is realized, and the screening operation is completed. In the configuration, at least one vibrating screen is generally configured, each vibrating screen is matched with an upstream adjustable frequency feeder for use, the material screened by the vibrating screen is divided into an upper screen part and a lower screen part, and the materials are conveyed to a downstream link through an upper screen conveying belt and a lower screen conveying belt respectively, so that the screening system is formed by the above equipment. For a system with multiple configurations of vibrating screens, the vibrating screens are equally configured.
Screening systems are commonly used in the processes of crushing and the like in the industry, and are an important link of the whole production process. The stable operation of the screening system directly affects the classification effect, product quality, yield and production efficiency. If the system fails, the grading efficiency is directly reduced, and the yield and the production efficiency of the whole process are affected. If the vibrating screen fails, only ore feeding is stopped, and the vibrating screen is stopped for maintenance, so that production is interrupted, and the yield is affected. Therefore, if the online fault diagnosis of the screening system is realized to detect abnormal working conditions and prompt timely intervention of production operation and operation maintenance personnel, timely adjustment of production and inspection of equipment are realized, which is of great significance in guaranteeing production and equipment management.
The whole screening system comprises a vibrating screen, a vibrating screen feeder and a belt conveyor. The belt conveyor is generally provided with fault detection devices such as a deviation, slipping and tearing switch and the like, so that chain protection and alarm of a single belt conveyor are realized, and the vibrating screen feeder are generally provided with no fault detection device, but the addition of the fault detection device means that the fault diagnosis cost is increased.
Although the invention patent with the application number of CN201410371534.5 and the invention name of fault diagnosis method of crushing and screening process discloses the reason for diagnosing the fault occurrence of the crushing and screening process, the fault diagnosis rule table in the patent is artificially pre-established in nature, has poor adaptability to dynamic change of a screening system, and has errors between diagnosis results and actual conditions.
Therefore, how to accurately provide fault diagnosis information of the screening system provides important basis for later production, operation and maintenance decisions and becomes a key problem of current research.
Disclosure of Invention
In view of the above problems, the present invention provides a screening system fault diagnosis method and system that at least solves some of the above technical problems.
In one aspect, the embodiment of the invention provides a fault diagnosis method of a screening system, which is applied to the screening system, wherein the screening system comprises an upper screen belt conveyor, a lower screen belt conveyor and m vibrating screen systems; wherein the ith vibrating screen system comprises an ith vibrating screen and an ith feeder; the method comprises an offline modeling part and an online diagnosis part;
the offline modeling section includes the steps of:
acquiring an integral input variable and an integral output variable of the screening system under a normal working condition, and constructing an input/output model of the screening system;
the on-line diagnosis section includes the steps of:
acquiring an integral input variable and an integral output variable of a screening system at the current moment, and combining the input and output model to acquire a monitoring quantity of the screening system and a corresponding monitoring quantity threshold value of the screening system;
acquiring single input variables and single output variables of each vibrating screen system at the current moment, and acquiring each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables;
comparing the monitoring quantity of each vibrating screen with the threshold value of the monitoring quantity of each vibrating screen to judge whether each vibrating screen fails or not;
if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with the threshold value of the monitoring quantity of the screening system so as to judge whether the screening system has faults or not.
Further, the obtaining the integral input variable and the integral output variable of the screening system at the current moment specifically includes:
acquiring single input variables of each vibrating screen system at the current moment; the single input variables of all vibrating screen systems at the current moment are formed into an integral input variable of the screening system; wherein the product of the feeding current and the feeding frequency of the ith feeder is used as a single input variable of the ith vibrating screen system;
acquiring current, historical current maximum, current undersize current and historical current maximum of the undersize belt of the over-screen belt; obtaining a first ratio by dividing the current of the on-screen belt by the maximum value of the historical current of the on-screen belt; obtaining a second ratio by dividing the current of the undersize belt by the historical current maximum value of the undersize belt; and taking the sum of the first ratio and the second ratio as an integral output variable of the screening system.
Further, the input-output model is expressed as:
wherein the method comprises the steps of
A(q -1 )＝1+a 1 q -1 +…+a n q -n
B i (q -1 )＝b i1 q -1 +…+b in q -n
θ＝[a 1 … an b 11 … b 1n … b m1 … b mn ] T ∈R (m+1)×n
Wherein z (k) represents the overall output variable; u (u) i (k) A single input variable representing an ith vibratory screen system; e (k) represents white noise; b (B) i (q -1 ) And A (q) -1 ) All represent the operator q with respect to unit delay -1 Is a function of (2); θ represents a parameter vector, the number of parameter elements is (m+1) ×n, and the parameter elements are real numbers; r represents a real number.
Further, the screening system monitor threshold is expressed as:
therein, jth α Representation screening systemMonitoring a quantity threshold; l represents the length of the data set under normal working conditions; n represents the model order of the input-output model; alpha represents the confidence under normal working conditions; f (F) a (. Cndot.) represents the F distribution percentile function with α as confidence.
Further, each vibrating screen monitoring amount threshold value is obtained by the following method:
acquiring a hysteresis order p of each vibrating screen system, a sampling period T corresponding to an input/output model and a data set prediction length l, wherein the current response follow-up time T' of the vibrating screen is caused by the change of the feeding frequency of a feeder;
initializing hysteresis orders p of each vibrating screen system;
let p > T'/T+1 be an integer and l > 2p, based on which the monitor threshold F for each vibrating screen is calculated α (p，l-2p)。
Further, the screening system monitoring amount is expressed as:
wherein T is 2 (k) Representing the monitoring quantity of the screening system; epsilon oe (k) Representing the output error of the input/output model at the current moment k;representing the output error mean value under the normal working condition data set; Λ type normal Representing the variance of the output error under the normal operating condition data set.
Further, the i-th vibrating screen monitoring amount is obtained by the following method:
taking the vibrating screen current of the ith vibrating screen as a single output variable of the ith vibrating screen system;
based on the single input variable and the single output variable, calculating an i-th vibrating screen monitoring amount according to the following formula:
wherein y is i (k) Is a single output variable; p represents the hysteresis order of the vibrating screen system; k represents the current time; f (F) i (k) Indicating the monitoring quantity of the ith vibrating screen;
a data vector containing a single input variable and a single output variable at the time k;
a gain vector representing data containing a single input variable and a single output variable at time k;
a covariance matrix representing data containing single input variables and single output variables at time k;
a parameter estimation vector representing data including a single input variable and a single output variable at time k;
a data matrix containing single input variables and single output variables at the moment k;
the square sum of prediction residual errors of output variables containing single input variables and single output variables at the moment k is represented, wherein the meaning of RSS is residual sum of squares;
a data vector containing a single output variable at time k;
a gain vector representing data containing a single output variable at time k;
a covariance matrix representing data containing single output variables at time k;
a parameter estimation vector representing data containing a single output variable at time k;
a data matrix containing single output variables at the moment k;
representing the input of a variable containing a single output at time kAnd outputting the sum of squares of the variable prediction residual errors.
Further, the method further comprises the following steps: if the screening system has faults, judging the fault type of the screening system; the judging method comprises the following steps:
filtering the whole output variable at the current moment to obtain an output filtering value;
based on the input-output model, obtaining an overall output predicted value;
comparing the output filtered value with the overall output predicted value: if the output filtering value is smaller than the integral output predicted value, indicating overload fault of the feeder; and if the output filter value is larger than the integral output predicted value, indicating that the belt conveyor is overloaded.
On the other hand, the embodiment of the invention also provides a screening system fault diagnosis system, which applies the method, and comprises the following steps: an offline modeling subsystem and an online diagnostic subsystem;
the off-line modeling subsystem is used for acquiring the integral input variable and the integral output variable of the screening system under the normal working condition and constructing an input-output model of the screening system;
the online diagnosis subsystem is used for acquiring the integral input variable and the integral output variable of the screening system at the current moment and combining the input and output model to acquire the monitoring quantity of the screening system and the corresponding monitoring quantity threshold value of the screening system; obtaining single input variables and single output variables of each vibrating screen system at the current moment, and obtaining each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables; comparing the monitoring quantity of each vibrating screen with the threshold value of the monitoring quantity of each vibrating screen to judge whether each vibrating screen fails or not; if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with the threshold value of the monitoring quantity of the screening system so as to judge whether the screening system has faults or not.
Further, the online diagnostic subsystem includes a fault classification module;
the fault classification module is used for classifying fault types of the screening system when faults exist in the screening system; the specific classification method comprises the following steps:
filtering the whole output variable at the current moment to obtain an output filtering value;
based on the input-output model, obtaining an overall output predicted value;
comparing the output filtered value with the overall output predicted value: if the output filtering value is smaller than the integral output predicted value, indicating overload fault of the feeder; and if the output filter value is larger than the integral output predicted value, indicating that the belt conveyor is overloaded.
Compared with the prior art, the screening system fault diagnosis method and system have the following beneficial effects: the invention can diagnose whether the screening system has faults and fault categories 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.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic flow chart of a fault diagnosis method of a screening system according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a screening system according to an embodiment of the present invention.
FIG. 3 is a schematic flow chart of another method for diagnosing faults in a screening system according to an embodiment of the present invention
Fig. 4 is a schematic diagram of a screening system fault diagnosis system framework according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In one aspect, an embodiment of the present invention provides a method for diagnosing faults of a screening system, which is applied to a screening system, wherein the screening system includes an on-screen belt conveyor, an under-screen belt conveyor, and m vibrating screen systems; wherein the ith vibrating screen system comprises an ith vibrating screen and an ith feeder; referring to FIG. 1, the method includes an offline modeling portion and an online diagnostic portion; wherein:
the offline modeling part comprises the following steps:
acquiring an integral input variable and an integral output variable of the screening system under a normal working condition, and constructing an input/output model of the screening system;
the on-line diagnosis part comprises the following steps:
acquiring an integral input variable and an integral output variable of a screening system at the current moment, and combining an input and output model to acquire a monitoring quantity of the screening system and a corresponding monitoring quantity threshold of the screening system; obtaining single input variables and single output variables of each vibrating screen system at the current moment, and obtaining each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables; comparing the monitoring quantity of each vibrating screen with a threshold value of the monitoring quantity of each vibrating screen so as to judge whether each vibrating screen has faults or not; if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with the threshold value of the monitoring quantity of the screening system to judge whether the screening system has faults or not.
The method may be performed by an electronic device.
The following will explain the above steps in detail.
Recording the longest response time of the current of m belt conveyors as T and the sampling period as T, which are caused by the change of the feeding frequency of the feeder; model order n > T/T+1 is an integer. Modeling is performed by using a normal working condition data set with the length of L. The input-output model is expressed as follows:
wherein the method comprises the steps of
A(q -1 )＝1+a 1 q -1 +…+a n q -n
B i (q -1 )＝b i1 q -1 +…+b in q -n
θ＝[a 1 … a n b 11 … b 1n … b m1 … b mn ] T ∈R (m+1)×n
a＝[a 1 a 2 … a n ] T
Wherein z (k) represents the overall output variable; u (u) i (k) A single input variable representing an ith vibratory screen system; e (k) is white noise with the mean value of 0; b (B) i (q -1 ) And A (q) -1 ) All represent the operator q with respect to unit delay -1 Is a function of (2); θ represents a parameter vector, and the number of elements is (m+1) ×n; a represents A (q -1 ) A parameter vector; r represents a real number. Specifically, the optimization algorithm such as the steepest descent method, the random approximation method and the like is adopted to calculate theta, so as to obtain a.
The mode of acquiring the integral input variable and the integral output variable under the normal working condition in the online monitoring process is consistent with the mode of acquiring the integral input variable and the integral output variable under the current moment in the offline modeling process.
The method for acquiring the integral input variable of the screening system at the current moment specifically comprises the following steps: acquiring single input variables of each vibrating screen system at the current moment; the single input variables of all vibrating screen systems at the current moment are formed into an integral input variable of the screening system; wherein the product of the feeding current and the feeding frequency of the ith feeding machine is used as a single input variable of the ith vibrating screen systemu i (k)；
The method for acquiring the integral output variable of the screening system at the current moment specifically comprises the following steps: acquiring current, historical current maximum, current undersize current and historical current maximum of the undersize belt of the over-screen belt; obtaining a first ratio by dividing the current of the on-screen belt by the maximum value of the historical current of the on-screen belt; obtaining a second ratio by dividing the current of the undersize belt by the historical current maximum value of the undersize belt; taking the sum z (k) of the first ratio and the second ratio as an integral output variable of the screening system; wherein k is the sampling time; i is an integer of [1, m ].
In the specific calculation process, based on an input/output model, obtaining a monitoring amount of a screening system and a monitoring amount threshold of the screening system; and obtaining each vibrating screen monitoring amount and each vibrating screen monitoring amount threshold value based on the single input variable and the single output variable of each vibrating screen system at the current moment.
In the process of on-line fault diagnosis, initial parameters need to be acquired, including: sampling period T and model order n, which are consistent with offline modeling. Setting a filter coefficient mu of a normal working condition data length L and a confidence coefficient alpha, z (k) z And calculate the screening system monitor threshold Jth as follows α ：
Meanwhile, the hysteresis order p of each vibrating screen system, the follow-up time t' of the current response of the vibrating screen caused by the change of the feeding frequency of the feeder and the predicted length l of the data set are obtained; initializing hysteresis orders p of each vibrating screen system; let p > T'/T+1 be an integer and l > 2p, based on which the monitor threshold F for each vibrating screen is calculated α (p, l-2 p); wherein F is α () Representing the F distribution percentile function with alpha confidence.
The output error of the input/output model under the normal working condition data set is obtained according to the following steps and stored:
and calculate the mean value and variance of the output error, and record them as respectivelyΛ normal 。
The screening system monitoring amount is then expressed as:
wherein T is 2 (k) Representing the monitoring quantity of the screening system; epsilon oe (k) Representing the output error of the input/output model at the current moment k;representing an output error mean; v normal Representing the output error variance.
Taking the product of the feeding current and the feeding frequency of the ith feeding machine as a single input variable u of the ith vibrating screen system i (k) The method comprises the steps of carrying out a first treatment on the surface of the The vibrating screen current of the ith vibrating screen is used as a single output variable y of the ith vibrating screen system i (k) The method comprises the steps of carrying out a first treatment on the surface of the Based on the single input variable and the single output variable, calculating the monitoring amount of the ith vibrating screen according to the following formula:
wherein y is i (k) Is a single output variable; p represents the hysteresis order of the vibrating screen system; k represents the current time; f (F) i (k) Indicating the monitoring quantity of the ith vibrating screen;
a data vector containing a single input variable and a single output variable at the time k;
a gain vector representing data containing a single input variable and a single output variable at time k;
a covariance matrix representing data containing single input variables and single output variables at time k;
a parameter estimation vector representing data including a single input variable and a single output variable at time k;
a data matrix containing single input variables and single output variables at the moment k;
the square sum of prediction residual errors of output variables containing single input variables and single output variables at the moment k is represented, wherein the meaning of RSS is residual sum of squares;
a data vector containing a single output variable at time k;
a gain vector representing data containing a single output variable at time k;
a covariance matrix representing data containing single output variables at time k;
parameter estimation vector representing data containing single output variable at k time
A data matrix containing single output variables at the moment k;
and the square sum of the prediction residual errors of the output variables containing single output variables at the moment k is represented.
Filtering and calculating z (k) according to the following mode to obtain an output filtering value z f (k) And stored therein.
z f (k)＝μ z z(k)+(1-μ z )z f (k-1)
Wherein mu z A filter coefficient representing z (k);
calculating the integral output predicted value of the input-output model according to the following methodAnd stored therein.
In the diagnosis process, firstly, the vibrating screen is monitored by an amount F i (k) And a vibrating screen monitoring quantity threshold F α (p, l-2 p) comparison; if F i (k) Less than F α (p, l-2 p), indicating that the vibrating screen fails, and collecting k+1 time data to enter a new round of calculation; if F i (k) Greater than or equal to F a (p, l-2 p), the screening system is monitored by an amount T 2 (k) With screening System monitoring quantity threshold Jth α Comparing; if T 2 (k) Less than or equal to Jth α The screening system is normally operated, and the data at the moment k+1 is acquired and enters a new round of calculation; if T 2 (k) Greater than Jth α The screening system is indicated to have faults, and the specific fault type is judged at the moment; the judging method comprises the following steps: will output the filtered value z f (k) And the integral output predicted valueComparison was performed: if z f (k) Less than->Indicating overload faults of the feeder, and collecting k+1 time data to enter a new round of calculation; if z f (k) Is greater than->The overload fault of the belt conveyor is indicated, and the data at the moment k+1 is acquired and enters a new calculation.
The above is further explained by a specific embodiment:
referring to fig. 2, an embodiment of the present invention includes a screening system comprising an on-screen belt conveyor, an under-screen belt conveyor, and 2 vibratory screen systems; wherein, vibrating screen current, feeder feed frequency, current of on-screen and under-screen conveyor belt are all integrated into the factory DCS (Distributed ControlSystem, decentralized control system).
And (4) recording that the feeding frequency change of the feeder causes the longest response time of 2 belt conveyor currents to be about t=7s, and the sampling period T=2s, and taking the integer of n=4 by taking the integer of n > T/T+1 of the model order.
Selecting 2-5 sections u 1 (k)、u 2 (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 { u } 1 (k)，u 2 (k) Z (k), the data set length is denoted as L. The effective dataset is L-n in length. And using the data set, establishing an input and output model of the screening system offline, and calculating the mean value and variance of the output error of the model.
The input-output model is expressed as:
wherein e (k) is white noise with an average value of 0; q -1 Is a unit delay operator;
let θ= [ a ] 1 … a 4 b 11 … b 14 b 21 … b 24 ] T ∈R 12 Wherein θ represents a parameter vector;
taking α= [ a ] 1 a 2 a 3 a 4 ] T 。
And (5) calculating the model output error of the normal working condition data set according to the following formula.
Wherein,to augment the data vector.
And find ε oe (k) Mean and variance of (1), respectively, are recorded asΛ normal 。
The method for acquiring the integral input variable of the screening system at the current moment specifically comprises the following steps: the product of the feed current and the feed frequency of the feeder # 1 (i.e., feeder # 1 in fig. 2) at the present time k is denoted as u 1 (k) The product of the feeding current and the feeding frequency at time k for the feeder # 2 (i.e., the # 2 feeder in fig. 2) is denoted as u 2 (k) The method comprises the steps of carrying out a first treatment on the surface of the Then u will be 1 (k) As a single input variable to the 1 st vibratory screen system; will u 2 (k) As a single input variable to the 2 nd vibratory screen system; will u 1 (k) And u 2 (k) All serve as integral input variables of the screening system.
The method for acquiring the integral output variable of the screening system at the current moment specifically comprises the following steps: acquiring current, historical current maximum, current undersize current and historical current maximum of the undersize belt of the over-screen belt; obtaining a first ratio by dividing the current of the on-screen belt by the maximum value of the historical current of the on-screen belt; obtaining a second ratio by dividing the current of the undersize belt by the historical current maximum value of the undersize belt; taking the sum z (k) of the first ratio and the second ratio as an integral output variable of the screening system; where k is the sampling instant.
Referring to the on-line flow chart of a screening system fault diagnosis method shown in fig. 3, the following description will proceed with specific steps, which are merely for convenience of description, and are not limiting to the specific implementation steps of the present invention.
S1, initializing a monitoring quantity threshold value, and setting confidence coefficient alpha=95% and filter coefficient mu z =0.9. The sampling period T and the model order n need to be consistent with offline modeling, and are respectively t=2s and n=4. The subsystem hysteresis order p=4, the prediction length l=10, and the forgetting factor λ=0.99 is set.
S2, acquiring and calculating { u } at the current k moment from DCS 1 (k)，u 2 (k)，z(k)，y 1 (k)，y 2 (k) Reading { u } from DCS historian database 1 (k-1)，u 2 (k-1)，z(k-1)}、{u 1 (k-2)，u 2 (k-1)，z(k-2)}、{u 1 (k-3)，u 2 (k-1)，z(k-3)}、{u 1 (k-4)，u 2 (k-1)，z(k-4) }, u 1 (k-l)，y 1 (k-1)}～{u 1 (k-l+1-p)，y 1 (k-l+1-p)}；
The screening system monitoring threshold Jth is calculated according to the following mode α 。
The monitor thresholds for each vibrating screen are calculated as follows: f (F) α (p，l-2p)。
Filtering and calculating z (k) according to the following mode to obtain an output filtering value z f (k) And stored therein.
z f (k)＝μ z z(k)+(1-μ z )z f (k-1)
S3, calculating model output error epsilon according to the following mode oe (k) And stored therein.
H + (k)＝[z(k) z(k-1) … z(k-4) u 1 (k-1) … u 1 (k-4)
u 2 (k-1) … u 2 (k-4) -ε oe (k-1) … -ε oe (k-4)] T
S4, calculating monitoring quantity T of screening system according to the following condition 2 (k)：
S5, calculating the overall output predicted value of the input/output model according to the following modeAnd stored therein.
Wherein,
s6, calculating parameter vector according to the following conditionAnd stores:
s7, calculating the monitoring quantity F of the 1 st vibrating screen according to the following formula 1 (k)：
S8, calculating parameter vector according to the following conditionAnd stored. />
S9, calculating the monitoring quantity F of the No. 2 vibrating screen according to the following mode 2 (k)：
S10, judging F 1 (k) Whether or not it is smaller than F α (p, l-2 p), if yes, alarming a 'No. 1 vibrating screen fault', writing back to the DCS, and jumping to S2; if not, go to S11.
S11, judging F 2 (k) Whether or not it is smaller than F α (p, l-2 p), if yes, alarming the 'No. 2 vibrating screen fault', writing back to the DCS, and jumping to S2; if not, go to S12.
S12, judging a first monitoring quantity T 2 (k) Whether or not to be less than Jth α If so, go to S2. If not, then judge z f (k) Whether or not to be smaller thanIf z f (k) Less than->And alarming the fault of overload fault of the feeder, writing back to the DCS, and jumping to S2. If z f (k) Is greater than->And alarming the overload fault of the belt conveyor, writing back to the DCS, and jumping to S2./>
In the specific implementation process, if the fault diagnosis method flow can be continuously performed, or the flow is ended.
Referring to fig. 4, an embodiment of the present invention provides a screening system fault diagnosis system, which applies the method described above, and the system includes: an offline modeling subsystem and an online diagnostic subsystem;
and the off-line modeling system is used for off-line building of the input and output models of the screening system. Constructing a data set through the integral input variable and the integral output variable of the screening system under the normal working condition, and constructing an input-output model of the screening system according to the integral input variable and the integral output variable; the off-line modeling sub-system provides the model order n, the modeling data set length L, the calculated parameter theta, the model output error mean and variance, and the maximum value of the belt current on the vibrating screen and under the screen to an on-line diagnosis module.
The on-line diagnosis subsystem is used for acquiring the integral input variable and the integral output variable of the screening system at the current moment and combining the input and output model to acquire the monitoring quantity of the screening system and the corresponding threshold value of the monitoring quantity of the screening system; obtaining single input variables and single output variables of each vibrating screen system at the current moment, and obtaining each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables; comparing the monitoring quantity of each vibrating screen with a threshold value of the monitoring quantity of each vibrating screen so as to judge whether each vibrating screen has faults or not; if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with a threshold value of the monitoring quantity of the screening system to judge whether the screening system has faults or not;
the on-line diagnosis subsystem comprises an initialization module, a data acquisition and preprocessing module, a subsystem monitoring amount calculation module, a system monitoring amount calculation module, a data storage module, a fault classification module and a fault output module;
the initialization module is used for initializing the adoption period T, the model order n, the modeling data set length L, the parameter theta, the confidence coefficient alpha, the subsystem hysteresis order p, the prediction length L and the forgetting factor lambda, and the module calculates the monitoring threshold Jth α 、F α (p，l-2p)。
The data acquisition and preprocessing module is used for acquiring the ith station at the current k momentData y of vibrating screen i (k) Collecting current and frequency of i vibrating screen feeders at the current moment, and directly obtaining product u of the current and the frequency i (k) And collecting the current of the conveying belt on the vibrating screen and the current of the conveying belt under the screen at the current moment, dividing the current by the maximum value of the current and the current, and obtaining the sum of the current and the current to obtain z (k). And acquisition history database reads z (k-1), z (k-2), …, z (k-n), and { u } i (k-1)，y i (k-1)}～{u i (k-l+1-p)，y i (k-l+1-p) }. The module carries out filtering calculation on z (k) to obtain z f (k) A. The invention relates to a method for producing a fibre-reinforced plastic composite Reading z from a data storage module prior to computation f (k-1) and outputting the filtering result to the data storage module for storage.
The subsystem monitoring amount calculating module is used for calculating F i (k) A. The invention relates to a method for producing a fibre-reinforced plastic composite Reading from a data storage module Calculation ofAnd output to the data storage module for storage. Calculated F i (k) And outputting to a fault classification module.
The system monitoring amount calculating module is used for calculating the fault diagnosis monitoring amount T 2 (k) Andand judging the fault type. Read from data storage module before calculation>Epsilon oe (k-1)、ε oe (k-2)、...、ε oe (k-n) and calculating the result of this period +.>ε oe (k) And outputting the data to a data storage module for storage.
The data storage module is used for storing the z calculated by the data acquisition and preprocessing module each time f (k) And provides z prior to calculation by this module f (k-1); also used for each calculation of the monitoring amount calculation module of the storage systemε oe (k) And provides +.>Epsilon oe (k-1)、ε oe (k-2)、...、ε oe (k-n); also used for the calculation of the monitoring amount calculation module of the storage subsystemAnd provides +.>
The fault classification module is used for storing a threshold Jth α And F α (p, l-2 p) reading F from subsystem monitoring calculation i (k) Judgment F i (k) Whether or not it is smaller than F α (p, l-2 p), and judges the fault diagnosis monitor amount T 2 (k) Whether or not it is smaller than a threshold Jth α The method comprises the steps of carrying out a first treatment on the surface of the Judgment of z f (k) Whether or not to be smaller thanTo comprehensively diagnose the fault category and output category information to the fault output module.
The fault output module is used for receiving the category output by the fault classification module and outputting an alarm signal.
In summary, the fault diagnosis method and system for the screening system provided by the embodiment of the invention can utilize the current and frequency signals of the ore feeding belt of the vibrating screen, the current signals of the belt conveyor on the vibrating screen and under the screen, and the current signals of the vibrating screen to realize fault diagnosis of the screening system and provide fault meaning for operators.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. A screening system fault diagnosis method is applied to a screening system, and the screening system comprises an upper screen belt conveyor, a lower screen belt conveyor and m vibrating screen systems; wherein the ith vibrating screen system comprises an ith vibrating screen and an ith feeder; wherein the method comprises an offline modeling part and an online diagnosis part;
the offline modeling section includes the steps of:
acquiring an integral input variable and an integral output variable of the screening system under a normal working condition, and constructing an input/output model of the screening system;
the on-line diagnosis section includes the steps of:
acquiring an integral input variable and an integral output variable of a screening system at the current moment, and combining the input and output model to acquire a monitoring quantity of the screening system and a corresponding monitoring quantity threshold value of the screening system;
acquiring single input variables and single output variables of each vibrating screen system at the current moment, and acquiring each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables;
comparing the monitoring quantity of each vibrating screen with the threshold value of the monitoring quantity of each vibrating screen to judge whether each vibrating screen fails or not;
if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with the monitoring quantity threshold value of the screening system to judge whether the screening system has faults or not;
the input-output model is expressed as:
wherein the method comprises the steps of
A(q -1 )＝1+a 1 q -1 +…+a n q -n
B i (q -1 )＝b i1 q -1 +…+b in q -n
θ＝[a 1 … a n b 11 … b 1n … b m1 … b mn ] T ∈R (m+1)×n
Wherein z (k) represents the overall output variable; u (u) i (k) A single input variable representing an ith vibratory screen system; e (k) represents white noise; b (B) i (q -1 ) And A (q) -1 ) All represent the operator q with respect to unit delay -1 Is a function of (2); θ represents a parameter vector, the number of parameter elements is (m+1) ×n, and the parameter elements are real numbers; r represents a real number; m represents the number of vibrating screen systems; i epsilon [1, m]And i is an integer.
2. The method for diagnosing faults of a screening system according to claim 1, wherein the step of obtaining the integral input variable and the integral output variable of the screening system at the current moment specifically comprises the steps of:
acquiring single input variables of each vibrating screen system at the current moment; the single input variables of all vibrating screen systems at the current moment are formed into an integral input variable of the screening system; wherein the product of the feeding current and the feeding frequency of the ith feeder is used as a single input variable of the ith vibrating screen system;
acquiring current, historical current maximum, current undersize current and historical current maximum of the undersize belt of the over-screen belt; obtaining a first ratio by dividing the current of the on-screen belt by the maximum value of the historical current of the on-screen belt; obtaining a second ratio by dividing the current of the undersize belt by the historical current maximum value of the undersize belt; and taking the sum of the first ratio and the second ratio as an integral output variable of the screening system.
3. A screening system fault diagnosis method according to claim 1, wherein said screening system monitor threshold is expressed as:
therein, jth α Representing a screening system monitoring amount threshold; l represents the length of the data set under normal working conditions; n represents the model order of the input-output model; alpha represents the confidence under normal working conditions; f (F) α (. Cndot.) represents the F distribution percentile function with α as confidence.
4. A screening system fault diagnosis method according to claim 1, wherein each screen monitor threshold is obtained by:
acquiring a hysteresis order p of each vibrating screen system, a sampling period T corresponding to an input/output model and a data set prediction length l, wherein the current response follow-up time T' of the vibrating screen is caused by the change of the feeding frequency of a feeder;
initializing hysteresis orders p of each vibrating screen system;
let p>T'/T+1 is an integer, and l>2p, calculating the monitoring quantity threshold value F of each vibrating screen based on the threshold value α (p,l-2p)。
5. A screening system fault diagnosis method according to claim 1, wherein said screening system monitoring amount is expressed as:
wherein T is 2 (k) Indicating screenMonitoring quantity of a subsystem; epsilon oe (k) Representing the output error of the input/output model at the current moment k;representing the output error mean value under the normal working condition data set; Λ type normal Representing the variance of the output error under the normal working condition data set; z (k) represents the overall output variable; u (u) i (k) A single input variable representing an ith vibratory screen system; b (B) i (q -1 ) And A (q) -1 ) All represent the operator q with respect to unit delay -1 Is a function of (2).
6. A screening system fault diagnosis method as claimed in claim 2, wherein the i-th vibrating screen monitoring amount is obtained by:
taking the vibrating screen current of the ith vibrating screen as a single output variable of the ith vibrating screen system;
based on the single input variable and the single output variable, calculating an i-th vibrating screen monitoring amount according to the following formula:
wherein y is i (k) Is a single output variable; p represents the hysteresis order of the vibrating screen system; k represents the current time; f (F) i (k) Indicating the monitoring quantity of the ith vibrating screen;
a data vector containing a single input variable and a single output variable at the time k;
a gain vector representing data containing a single input variable and a single output variable at time k;
a covariance matrix representing data containing single input variables and single output variables at time k;
a parameter estimation vector representing data including a single input variable and a single output variable at time k;
a data matrix containing single input variables and single output variables at the moment k;
the square sum of prediction residual errors of output variables containing single input variables and single output variables at the moment k is represented, wherein the meaning of RSS is residual sum ofsquares;
a data vector containing a single output variable at time k;
a gain vector representing data containing a single output variable at time k;
a covariance matrix representing data containing single output variables at time k;
parameter estimation vector representing data containing single output variable at k time
A data matrix containing single output variables at the moment k;
the square sum of output variable prediction residual errors containing single output variables at the moment k is represented;
l represents a predicted length; λ represents a forgetting factor.
7. A screening system fault diagnosis method according to claim 1, further comprising: if the screening system has faults, judging the fault type of the screening system; the judging method comprises the following steps:
filtering the whole output variable at the current moment to obtain an output filtering value;
based on the input-output model, obtaining an overall output predicted value;
comparing the output filtered value with the overall output predicted value: if the output filtering value is smaller than the integral output predicted value, indicating overload fault of the feeder; and if the output filter value is larger than the integral output predicted value, indicating that the belt conveyor is overloaded.
8. A screening system fault diagnosis system, characterized in that the method according to any one of claims 1-7 is applied; the system comprises: an offline modeling subsystem and an online diagnostic subsystem;
the off-line modeling subsystem is used for acquiring the integral input variable and the integral output variable of the screening system under the normal working condition and constructing an input-output model of the screening system;
the online diagnosis subsystem is used for acquiring the integral input variable and the integral output variable of the screening system at the current moment and combining the input and output model to acquire the monitoring quantity of the screening system and the corresponding monitoring quantity threshold value of the screening system; obtaining single input variables and single output variables of each vibrating screen system at the current moment, and obtaining each vibrating screen monitoring quantity and corresponding vibrating screen monitoring quantity threshold values based on the single input variables and the single output variables; comparing the monitoring quantity of each vibrating screen with the threshold value of the monitoring quantity of each vibrating screen to judge whether each vibrating screen fails or not; if each vibrating screen operates normally, comparing the monitoring quantity of the screening system with the monitoring quantity threshold value of the screening system to judge whether the screening system has faults or not;
the input-output model is expressed as:
wherein the method comprises the steps of
A(q -1 )＝1+a 1 q -1 +…+a n q -n
B i (q -1 )＝b i1 q -1 +…+b in q -n
θ＝[a 1 … a n b 11 … b 1n … b m1 … b mn ] T ∈R (m+1)×n
Wherein z (k) represents the whole transfusionOutputting a variable; u (u) i (k) A single input variable representing an ith vibratory screen system; e (k) represents white noise; b (B) i (q -1 ) And A (q) -1 ) All represent the operator q with respect to unit delay -1 Is a function of (2); θ represents a parameter vector, the number of parameter elements is (m+1) ×n, and the parameter elements are real numbers; r represents a real number; m represents the number of vibrating screen systems; i epsilon [1, m]And i is an integer.
9. The screening system fault diagnosis system according to claim 8, wherein said on-line diagnosis subsystem includes a fault classification module;
the fault classification module is used for classifying fault types of the screening system when faults exist in the screening system; the specific classification method comprises the following steps:
filtering the whole output variable at the current moment to obtain an output filtering value;
based on the input-output model, obtaining an overall output predicted value;
comparing the output filtered value with the overall output predicted value: if the output filtering value is smaller than the integral output predicted value, indicating overload fault of the feeder; and if the output filter value is larger than the integral output predicted value, indicating that the belt conveyor is overloaded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310669448.1A CN116679669B (en) | 2023-06-07 | 2023-06-07 | Screening system fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310669448.1A CN116679669B (en) | 2023-06-07 | 2023-06-07 | Screening system fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116679669A CN116679669A (en) | 2023-09-01 |
| CN116679669B true CN116679669B (en) | 2024-03-26 |
Family
ID=87788666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310669448.1A Active CN116679669B (en) | 2023-06-07 | 2023-06-07 | Screening system fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116679669B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4994986A (en) * | 1989-01-27 | 1991-02-19 | International Business Machines Corporation | Online performance monitoring and fault diagnosis technique for direct current motors as used in printer mechanisms |
| KR20050055379A (en) * | 2003-12-08 | 2005-06-13 | 주식회사 포스코 | Diagnosis device for performance abnormality of vibrating screen and the method |
| CN104133468A (en) * | 2014-07-30 | 2014-11-05 | 北京矿冶研究总院 | Fault diagnosis method for crushing and screening process |
| CN104390657A (en) * | 2014-11-05 | 2015-03-04 | 浙江大学 | Generator set operating parameter measuring sensor fault diagnosis method and system |
| CN108152064A (en) * | 2017-12-26 | 2018-06-12 | 华侨大学 | A kind of vibrating screen fault signature extracting method and failure monitoring system |
| CN109675935A (en) * | 2019-03-06 | 2019-04-26 | 北京科技大学 | A kind of IPCA operation of rolling on-line fault diagnosis method becoming control limit |
| CN110064495A (en) * | 2019-04-23 | 2019-07-30 | 徐州徐工矿业机械有限公司 | The online joint control control method of movable Crushing screening plant and control system |
| CN110083860A (en) * | 2019-03-13 | 2019-08-02 | 东北大学 | A kind of industrial method for diagnosing faults based on correlated variables selection |
| CN114091188A (en) * | 2021-10-29 | 2022-02-25 | 中南大学 | Shield tunneling machine hydraulic drive cutter head system modeling and fault diagnosis method and device |
| CN114398800A (en) * | 2022-01-27 | 2022-04-26 | 矿冶科技集团有限公司 | Fault diagnosis method and device for crusher system |
| CN115212996A (en) * | 2021-04-15 | 2022-10-21 | 国家能源聊城发电有限公司 | Fault diagnosis system for coal mill |
| CN116011982A (en) * | 2022-11-21 | 2023-04-25 | 淮南平圩第三发电有限责任公司 | Online monitoring method and system for breakage of grinding roller of coal mill |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190384255A1 (en) * | 2018-06-19 | 2019-12-19 | Honeywell International Inc. | Autonomous predictive real-time monitoring of faults in process and equipment |
-
2023
- 2023-06-07 CN CN202310669448.1A patent/CN116679669B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4994986A (en) * | 1989-01-27 | 1991-02-19 | International Business Machines Corporation | Online performance monitoring and fault diagnosis technique for direct current motors as used in printer mechanisms |
| KR20050055379A (en) * | 2003-12-08 | 2005-06-13 | 주식회사 포스코 | Diagnosis device for performance abnormality of vibrating screen and the method |
| CN104133468A (en) * | 2014-07-30 | 2014-11-05 | 北京矿冶研究总院 | Fault diagnosis method for crushing and screening process |
| CN104390657A (en) * | 2014-11-05 | 2015-03-04 | 浙江大学 | Generator set operating parameter measuring sensor fault diagnosis method and system |
| CN108152064A (en) * | 2017-12-26 | 2018-06-12 | 华侨大学 | A kind of vibrating screen fault signature extracting method and failure monitoring system |
| CN109675935A (en) * | 2019-03-06 | 2019-04-26 | 北京科技大学 | A kind of IPCA operation of rolling on-line fault diagnosis method becoming control limit |
| CN110083860A (en) * | 2019-03-13 | 2019-08-02 | 东北大学 | A kind of industrial method for diagnosing faults based on correlated variables selection |
| CN110064495A (en) * | 2019-04-23 | 2019-07-30 | 徐州徐工矿业机械有限公司 | The online joint control control method of movable Crushing screening plant and control system |
| CN115212996A (en) * | 2021-04-15 | 2022-10-21 | 国家能源聊城发电有限公司 | Fault diagnosis system for coal mill |
| CN114091188A (en) * | 2021-10-29 | 2022-02-25 | 中南大学 | Shield tunneling machine hydraulic drive cutter head system modeling and fault diagnosis method and device |
| CN114398800A (en) * | 2022-01-27 | 2022-04-26 | 矿冶科技集团有限公司 | Fault diagnosis method and device for crusher system |
| CN116011982A (en) * | 2022-11-21 | 2023-04-25 | 淮南平圩第三发电有限责任公司 | Online monitoring method and system for breakage of grinding roller of coal mill |
Non-Patent Citations (1)
| Title |
|---|
| 振动筛在线故障诊断系统研究与应用;张丽娜;中国优秀硕士学位论文全文数据库;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116679669A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102017129227B4 (en) | Numerical control and machine learning device | |
| DE69212048T2 (en) | Apparatus and method using a real time expert system to predict tool life and diagnose tool wear | |
| US5511004A (en) | Diagnostic method for an evolutionary process | |
| EP1435023B1 (en) | Method and system for analysing control circuit performance in industrial process | |
| US7827006B2 (en) | Heat exchanger fouling detection | |
| CN101421679B (en) | Process monitoring technique and related actions | |
| US8732100B2 (en) | Method and apparatus for event detection permitting per event adjustment of false alarm rate | |
| CN110366031A (en) | A kind of monitoring abnormal state and method for diagnosing faults digitizing workshop MES system view-based access control model | |
| CN1185841A (en) | Device in a process system for detecting events | |
| KR20210125015A (en) | Systems and methods for detecting and measuring anomalies in signaling originating from components used in industrial processes | |
| EP3296822B1 (en) | Model-plant mismatch detection using model parameter data clustering for paper machines or other systems | |
| JP7493930B2 (en) | Information processing method, information processing device, production system, program, and recording medium | |
| CN117786373B (en) | Equipment operation diagnosis system based on big data corrugated paper processing | |
| WO2019226846A1 (en) | Competency gap identification of an operators response to various process control and maintenance conditions | |
| JP2000305620A (en) | Diagnostic tool to be used for process control system | |
| CN114398800B (en) | Fault diagnosis method and device for crusher system | |
| CN116679669B (en) | Screening system fault diagnosis method and system | |
| CN116705272A (en) | Comprehensive evaluation method for equipment health state based on multidimensional diagnosis | |
| CN116339267B (en) | Automatic production line control system based on Internet of things | |
| Ashfahani et al. | Autonomous deep quality monitoring in streaming environments | |
| CN115356990A (en) | Material yard equipment fault prediction method and system based on deep learning and storage medium | |
| EP1755013A2 (en) | Method for verifying manufactured parts | |
| US11334061B2 (en) | Method to detect skill gap of operators making frequent inadvertent changes to the process variables | |
| CN118068819B (en) | Large model data management system for high quality diagnostics and decision making | |
| RU2784925C1 (en) | System and method for detecting and measuring anomalies in signalling originating from components used in industrial processes |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Qing Inventor after: Wang Qingkai Inventor after: Guo Zhenyu Inventor after: Sun Xuefang Inventor after: Zhao Haili Inventor after: Zhang Ning Inventor after: Lu Bo Inventor after: Yang Shanglin Inventor after: Mo Xuelei Inventor before: Zhao Haili Inventor before: Wang Qingkai Inventor before: Guo Zhenyu Inventor before: Wang Qing Inventor before: Sun Xuefang Inventor before: Zhang Ning Inventor before: Lu Bo Inventor before: Yang Shanglin Inventor before: Mo Xuelei |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |