CN116189349A - Remote fault monitoring method and system for self-service printer - Google Patents
Remote fault monitoring method and system for self-service printer Download PDFInfo
- Publication number
- CN116189349A CN116189349A CN202310473565.0A CN202310473565A CN116189349A CN 116189349 A CN116189349 A CN 116189349A CN 202310473565 A CN202310473565 A CN 202310473565A CN 116189349 A CN116189349 A CN 116189349A
- Authority
- CN
- China
- Prior art keywords
- fault
- self
- service printer
- peak signal
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 19
- 230000009467 reduction Effects 0.000 claims abstract description 17
- 238000013135 deep learning Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 25
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 230000007547 defect Effects 0.000 claims description 14
- 238000011176 pooling Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000003745 diagnosis Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000002401 inhibitory effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F9/00—Details other than those peculiar to special kinds or types of apparatus
- G07F9/02—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus
- G07F9/026—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus for alarm, monitoring and auditing in vending machines or means for indication, e.g. when empty
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/18105—Extraction of features or characteristics of the image related to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
- G06V30/19093—Proximity measures, i.e. similarity or distance measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/418—Document matching, e.g. of document images
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/26—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for printing, stamping, franking, typing or teleprinting apparatus
- G07F17/266—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for printing, stamping, franking, typing or teleprinting apparatus for the use of a photocopier or printing device
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Accessory Devices And Overall Control Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a remote fault monitoring method and a system of a self-service printer, comprising the following steps: acquiring an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal to inhibit background noise, and generating a peak value signal; extracting the time-frequency characteristics of the peak signals, and utilizing dynamic time regularity to carry out matching judgment on the running state of the self-service printer; constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result; and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree. According to the invention, remote fault monitoring of the self-service printer is realized through acquisition and analysis of acoustic signals, manpower maintenance resources are saved, and the normal operation of the self-service printer and timeliness of fault information acquisition are ensured.
Description
Technical Field
The invention relates to the technical field of fault monitoring, in particular to a remote fault monitoring method and system of a self-service printer.
Background
At present, the internet of things technology, cloud computing technology and the like are widely applied to production, work and daily life, and more electronic products are developed towards networking and intellectualization. Printers are used as the most common electronic equipment and meet the rigid requirement of daily printing. However, the demands of people on printing are characterized by fragmentation, real-time performance, high frequency, high flexibility requirement and the like, and the traditional forms of fixed print shop modes, office printers and the like have difficulty in fully meeting the demands of printing. The competition situation of the printing equipment market also requires equipment manufacturers to continuously conduct intelligent and self-help conversion, so that the intelligent self-help printer service system is a brand new product and service generated under the stimulus of new technology, new requirements and new modes.
Because self-service printer equipment lacks special man's real-time maintenance, problem and trouble that appears often can't obtain in the first time, lead to, self-service printer in actual application process, various problems and trouble can not maintain in real time, lead to can not effectively print, if can not carry out effectual monitoring and the diagnosis to printing equipment can cause mechanical equipment's damage, consequently, need develop a system and monitor and fault diagnosis to self-service printer equipment state, guarantee its normal operating to according to the relevant part of different fault information locking, confirm the trouble part. In the implementation process, how to monitor the fault information of the self-service printer according to the running state based on deep learning, and ensuring the timeliness of the monitored information is one of the problems which cannot be solved yet.
Disclosure of Invention
In order to solve the technical problems, the invention provides a remote fault monitoring method and a remote fault monitoring system for a self-service printer.
The first aspect of the invention provides a remote fault monitoring method of a self-service printer, comprising the following steps:
collecting an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak value signal;
extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree.
In this scheme, gather the acoustic signal of self-service printer operation in-process, with the acoustic signal carries out the preliminary treatment of making an uproar falls, suppresses the background noise in the acoustic signal to generate peak value signal, specifically:
Acquiring an acoustic signal in the operation process of the self-service printer through an acoustic sensor preset in the self-service printer, and generating an acoustic signal time sequence by combining the acquired acoustic signal with a time stamp;
decomposing the acoustic signal time sequence into mutually independent components according to the signal characteristics on time sequence through empirical mode decomposition, selecting high-frequency components of the components, and selecting a threshold function for setting wavelet transformation according to the high-frequency components;
the acoustic signal is subjected to threshold processing through the threshold function, the noise content in the filtered signal is evaluated, and whether the set threshold function meets the noise reduction standard is judged;
if the wavelet transformation parameters do not meet the threshold value, setting the adaptive parameters in the threshold value function to carry out threshold value compensation, and correcting the adaptive parameters according to the multiple iteration threshold value compensation to obtain an optimal threshold value function of the wavelet transformation;
and carrying out peak extraction on the acoustic signals after noise reduction according to a preset time interval, and generating a peak signal discrete time sequence based on the extracted peak signals.
In the scheme, the time-frequency characteristics of peak signals are extracted, the time-frequency characteristics are matched and judged by utilizing dynamic time regularity, and the running state of the self-service printer is specifically:
Acquiring a peak signal under the normal operation condition of the self-service printer, extracting a time-frequency characteristic in a discrete time sequence corresponding to the peak signal, and acquiring a characteristic set corresponding to the normal operation state of the self-service printer according to the time-frequency characteristic;
generating a peak signal curve according to a feature set corresponding to a normal running state, taking the peak signal curve as a normal state peak signal curve, and acquiring similarity between the peak signal curve corresponding to the current acoustic signal of the self-service printer and the normal state peak signal curve through a dynamic time warping algorithm;
peak signal curve of normal stateCurve with current peak signalObtaining the corresponding point combination by matching>The calculation formula of the BTW distance between the two curves is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the first characteristic point in the normal state peak signal curve and the current peak signal curve respectively, < ->The last characteristic point in the normal state peak signal curve and the current peak signal curve respectively,the first combination point and the last combination point in the corresponding point combination are respectively +.>For the corresponding point combination set, +.>For the total number of corresponding point combinations->For Euclidean distance between corresponding points in the combination of peak signal curve in normal state and corresponding point of current peak signal curve, +. >Is the characteristic point on the normal state peak signal curve in the kth corresponding point combination,and k is the number of corresponding point terms, wherein the k is the characteristic point on the current peak signal curve in the kth corresponding point combination.
In the scheme, the BTW distance between a normal state peak signal curve and a current peak signal curve is obtained, and the BTW distance is used as similarity to judge;
presetting a similarity threshold, and when the similarity is larger than or equal to the preset similarity threshold, indicating that the running state of the self-service printer corresponding to the current peak signal curve is a normal state;
when the similarity is smaller than a preset similarity threshold, the current peak signal curve is indicated to correspond to the running state of the self-service printer to be an abnormal state, fault early warning of the abnormal state is generated, and fault diagnosis is conducted on the abnormal state.
In the scheme, a fault recognition model is constructed based on deep learning, fault characteristics in acoustic signals are extracted, the fault characteristics are input into the trained fault recognition model, and a fault recognition result is output, specifically:
constructing a fault recognition model according to a convolutional neural network and a gating circulation network, acquiring common fault information and corresponding acoustic signal time sequences of a self-service printer by using a big data means, regarding different fault types or fault positions as independent categories, setting data labels according to the categories, taking acoustic signal data with the labels as training data, and training the fault recognition model;
Leading the acoustic signal subjected to the current wavelet noise filtering into a fault recognition model, acquiring the characteristics of the acoustic signal subjected to the wavelet noise filtering in a convolutional neural network unit through a convolutional layer, and downsampling the extracted characteristics through a pooling layer;
importing the characteristic information after pooling operation into a gating circulation network unit, learning through the two layers of gating circulation network units, screening acoustic signal characteristics extracted by the convolutional neural network unit, and obtaining the periodicity rule of characteristic acoustic signal data characteristics;
and carrying out fault identification on the output characteristics of the gating circulation network unit by using the Softmax unit, and outputting a fault identification result.
In the scheme, the image information of the printed paper corresponding to the acoustic signals acquired by the self-service printer is acquired, the fault identification result is verified and the fault degree is analyzed according to the feature similarity of the image information and the print task, and the method specifically comprises the following steps:
matching the printing task in the running process according to the time stamp of the acoustic signal acquired by the current self-service printer, and extracting the characteristic information of the printing task according to the layout information of the printing task, wherein the characteristic information comprises color characteristics, position characteristics and texture characteristics;
Scanning the image information of the printed paper, preprocessing the image information, dividing the image information into image blocks with preset sizes according to preset dividing areas, and obtaining the information entropy of each image block;
when the information entropy of the image block is larger than a preset information entropy threshold, subdividing the image block, ensuring that the information entropy of each subdivided image block accords with a preset information entropy standard, extracting characteristic information of the image block, and comparing the extracted characteristic information with characteristic information in a printing task to obtain similarity;
marking the image blocks with similarity not meeting the preset similarity requirement, comparing frame by frame according to the layout information of the print task to obtain defect information, and carrying out matching verification on the fault information output by the fault identification model according to the defect information;
and meanwhile, evaluating the fault degree according to the similarity deviation and the defect information of the marked image blocks, and embedding the fault degree into fault early warning information.
The second aspect of the present invention also provides a remote fault monitoring system for a self-service printer, the system comprising: the remote fault monitoring system comprises a memory and a processor, wherein the memory comprises a remote fault monitoring method program of a self-service printer, and the remote fault monitoring method program of the self-service printer realizes the following steps when being executed by the processor:
Collecting an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak value signal;
extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree.
The invention discloses a remote fault monitoring method and a system of a self-service printer, comprising the following steps: acquiring an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment and background noise suppression on the acoustic signal, and generating a peak value signal; extracting the time-frequency characteristics of the peak signals, and utilizing dynamic time regularity to carry out matching judgment on the running state of the self-service printer; constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result; and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree. According to the invention, remote fault monitoring of the self-service printer is realized through acquisition and analysis of acoustic signals, manpower maintenance resources are saved, and the normal operation of the self-service printer and the timeliness of fault acquisition are ensured.
Drawings
FIG. 1 illustrates a flow chart of a remote fault monitoring method of a self-service printer of the present invention;
FIG. 2 illustrates a flow chart of a method of determining the operational status of a self-service printer in accordance with the present invention;
FIG. 3 shows a flow chart of a method for fault identification based on deep learning to build a fault identification model according to the invention;
fig. 4 shows a block diagram of a remote fault monitoring system of a self-service printer of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a remote fault monitoring method of a self-service printer of the present invention.
As shown in fig. 1, a first aspect of the present invention provides a remote fault monitoring method of a self-service printer, including:
S102, acquiring an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak signal;
s104, extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
s106, constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
s108, acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print job, and analyzing the fault degree.
The method comprises the steps that an acoustic sensor preset in the self-service printer is used for acquiring an acoustic signal in the operation process of the self-service printer, and the acquired acoustic signal is combined with a time stamp to generate an acoustic signal time sequence; decomposing the acoustic signal time sequence into mutually independent components according to the signal characteristics on time sequence through empirical mode decomposition, selecting high-frequency components of the components, and selecting a threshold function for setting wavelet transformation according to the high-frequency components; the acoustic signal is subjected to threshold processing through the threshold function, the noise content in the filtered signal is evaluated, and whether the set threshold function meets the noise reduction standard is judged; if the wavelet transformation parameters do not meet the threshold value, setting the adaptive parameters in the threshold value function to carry out threshold value compensation, and correcting the adaptive parameters according to the multiple iteration threshold value compensation to obtain an optimal threshold value function of the wavelet transformation; and carrying out peak extraction on the acoustic signals after noise reduction according to a preset time interval, and generating a peak signal discrete time sequence based on the extracted peak signals.
The method for acquiring the high-frequency component in the acoustic signal through empirical mode analysis specifically comprises the following steps: acquisition of acoustic signalsPerforming curve fitting on all maximum value points to generate an upper envelope curve, performing curve fitting on all minimum value points to generate a lower envelope curve, and calculating the average value of the upper envelope curve and the lower envelope curve; subtracting the mean value from the original acoustic signal to obtain an intermediate signal +.>Judging the intermediate signal +.>Whether the constraint condition of the eigenmode function is satisfied, if so, taking the intermediate signal as a high-frequency component relative to the mean envelope curve; if not, repeating the steps until the constraint condition is met, repeating until the participation component +.>Ending decomposition when constant or monotonic, i.e. meetingThe method comprises the steps of carrying out a first treatment on the surface of the The threshold function of wavelet transformation is set according to the high frequency component, and in wavelet transformation, commonly used thresholds for wavelet transformation include a rigrsure threshold, an sqtwolog threshold, a heursure threshold, a minimum threshold, and the like.
FIG. 2 illustrates a flow chart of a method of determining the operational status of a self-service printer in accordance with the present invention.
According to the embodiment of the invention, the time-frequency characteristics of the peak signal are extracted, and the time-frequency characteristics are matched and judged by utilizing dynamic time regularity, specifically:
S202, acquiring a peak signal under the normal operation condition of the self-service printer, extracting time-frequency characteristics in a discrete time sequence corresponding to the peak signal, and acquiring a characteristic set corresponding to the normal operation state of the self-service printer according to the time-frequency characteristics;
s204, generating a peak signal curve according to a feature set corresponding to a normal running state, taking the peak signal curve as a normal state peak signal curve, and acquiring similarity between the peak signal curve corresponding to the current acoustic signal of the self-service printer and the normal state peak signal curve through a dynamic time warping algorithm;
s206, obtaining the BTW distance between the peak signal curve in the normal state and the current peak signal curve, and judging the BTW distance as the similarity;
s208, presetting a similarity threshold, and when the similarity is larger than or equal to the preset similarity threshold, indicating that the running state of the self-service printer corresponding to the current peak signal curve is a normal state;
and S210, when the similarity is smaller than a preset similarity threshold, the current peak signal curve is indicated to be abnormal corresponding to the running state of the self-service printer, fault early warning of the abnormal state is generated, and fault diagnosis is carried out on the abnormal state.
The normal state peak signal curve is described And the current peak signal curve->Obtaining corresponding point combinations by matchingThe calculation formula of the BTW distance between the two curves is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the first characteristic point in the normal state peak signal curve and the current peak signal curve respectively, < ->The last characteristic point in the normal state peak signal curve and the current peak signal curve respectively,the first combination point and the last combination point in the corresponding point combination are respectively +.>For the corresponding point combination set, +.>For the total number of corresponding point combinations->For Euclidean distance between corresponding points in the combination of peak signal curve in normal state and corresponding point of current peak signal curve, +.>Is the characteristic point on the normal state peak signal curve in the kth corresponding point combination,and k is the number of corresponding point terms, wherein the k is the characteristic point on the current peak signal curve in the kth corresponding point combination.
FIG. 3 shows a flow chart of a method for fault identification based on deep learning to build a fault identification model according to the invention.
According to the embodiment of the invention, a fault recognition model is constructed based on deep learning, fault characteristics in acoustic signals are extracted, the fault characteristics are input into the trained fault recognition model, and a fault recognition result is output, specifically:
S302, constructing a fault recognition model according to a convolutional neural network and a gating circulation network, acquiring common fault information and corresponding acoustic signal time sequences of a self-service printer by using a big data means, regarding different fault types or fault positions as independent types, setting data labels according to the types, taking acoustic signal data with the labels as training data, and training the fault recognition model;
s304, importing the acoustic signal subjected to the current wavelet noise filtering into a fault recognition model, acquiring the characteristics of the acoustic signal subjected to the wavelet noise filtering in a convolutional neural network unit through a convolutional layer, and downsampling the extracted characteristics through a pooling layer;
s306, importing the characteristic information after pooling operation into a gating circulation network unit, learning through the two layers of gating circulation network units, screening acoustic signal characteristics extracted by the convolutional neural network unit, and obtaining a periodicity rule of characteristic acoustic signal data characteristics;
s308, the output characteristics of the gating circulation network unit are used for identifying faults by using a Softmax unit, and fault identification results are output.
The method is characterized in that input data are fully mined through a convolutional neural network in a fault recognition model, extracted features are subjected to downsampling through pooling layer operation to reduce weight parameters, the extracted features are sequentially input into two layers of gating circulating network units to learn, the time sequence features of acoustic signals are guaranteed not to be lost, the intrinsic relation and periodicity rules between the data are acquired to the greatest extent, the convolutional neural network units and the gating circulating network units are connected through a residual network, and training errors are effectively reduced through the residual network.
And verifying the fault identification result according to the feature similarity of the image information and the print task, and if the fault information output by the fault identification model is irrelevant to the printing component, that is, the fault condition cannot be directly judged through the paper printing condition, directly generating the fault information and sending the fault information.
Matching the printing task in the running process according to the time stamp of the acoustic signal acquired by the current self-service printer, and extracting the characteristic information of the printing task according to the layout information of the printing task, wherein the characteristic information comprises color characteristics, position characteristics and texture characteristics; scanning the image information of the printed paper, preprocessing the image information, dividing the image information into image blocks with preset sizes according to preset dividing areas, and obtaining the information entropy of each image block; when the information entropy of the image block is larger than a preset information entropy threshold, subdividing the image block, ensuring that the information entropy of each subdivided image block accords with a preset information entropy standard, extracting characteristic information of the image block, and comparing the extracted characteristic information with characteristic information in a printing task to obtain similarity; marking the image blocks with similarity not meeting the preset similarity requirement, comparing frame by frame according to the layout information of the print task to obtain defect information, and carrying out matching verification on the fault information output by the fault identification model according to the defect information; when the fault identification information is matched with the defect information, directly sending fault early warning according to the fault identification information; otherwise, acquiring a possibly-occurring fault set to generate early warning information and sending the early warning information; and evaluating the fault degree according to the similarity deviation of the marked image blocks and the defect information, and embedding the fault degree into fault early warning information.
According to the embodiment of the invention, a database is constructed to store, monitor and early warn fault information of the self-service printer, and the method specifically comprises the following steps:
constructing a self-service printer operation database, wherein the self-service printer operation database stores the historical operation conditions, the historical fault information and the historical operation and maintenance records of the self-service printer;
acquiring the fault degree of fault information corresponding to the acoustic signals currently acquired by the self-service printer, and retrieving threshold information corresponding to the fault information from a database;
when the fault degree is smaller than the threshold value corresponding to the fault information, storing the current fault information and the fault degree into a self-service printer operation database, constructing a fault monitoring task, and monitoring the change condition of the fault degree through the fault monitoring task;
when detecting that the change value of the current fault degree and the historical fault degree is larger than a preset change threshold or the current fault degree is larger than a fault information corresponding threshold, generating early warning information;
meanwhile, the questionnaire is pushed to the user terminal to acquire feedback information of the user on the printing condition of the self-service printer, and the running condition of the self-service printer is judged according to the feedback information.
It should be noted that the printing quality is not affected in the early period of the failure of the self-service printer, the change condition of the failure information is mastered in time by monitoring the failure degree, frequent failure early warning of the self-service printer is reduced, and unnecessary operation and maintenance management is reduced.
Fig. 4 shows a block diagram of a remote fault monitoring system of a self-service printer of the present invention.
The second aspect of the present invention also provides a remote fault monitoring system 4 for a self-service printer, the system comprising: the memory 41 and the processor 42, wherein the memory comprises a remote fault monitoring method program of the self-service printer, and the remote fault monitoring method program of the self-service printer realizes the following steps when being executed by the processor:
collecting an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak value signal;
extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree.
The method comprises the steps that an acoustic sensor preset in the self-service printer is used for acquiring an acoustic signal in the operation process of the self-service printer, and the acquired acoustic signal is combined with a time stamp to generate an acoustic signal time sequence; decomposing the acoustic signal time sequence into mutually independent components according to the signal characteristics on time sequence through empirical mode decomposition, selecting high-frequency components of the components, and selecting a threshold function for setting wavelet transformation according to the high-frequency components; the acoustic signal is subjected to threshold processing through the threshold function, the noise content in the filtered signal is evaluated, and whether the set threshold function meets the noise reduction standard is judged; if the wavelet transformation parameters do not meet the threshold value, setting the adaptive parameters in the threshold value function to carry out threshold value compensation, and correcting the adaptive parameters according to the multiple iteration threshold value compensation to obtain an optimal threshold value function of the wavelet transformation; and carrying out peak extraction on the acoustic signals after noise reduction according to a preset time interval, and generating a peak signal discrete time sequence based on the extracted peak signals.
The method for acquiring the high-frequency component in the acoustic signal through empirical mode analysis specifically comprises the following steps: acquisition of acoustic signalsPerforming curve fitting on all maximum value points to generate an upper envelope curve, performing curve fitting on all minimum value points to generate a lower envelope curve, and calculating the average value of the upper envelope curve and the lower envelope curve; subtracting the mean value from the original acoustic signal to obtain an intermediate signal +. >Judging the intermediate signal +.>Whether the constraint condition of the eigenmode function is satisfied, if so, taking the intermediate signal as a high-frequency component relative to the mean envelope curve; if not, repeating the steps until the constraint condition is met, repeating until the participation component +.>Ending decomposition when constant or monotonic, i.e. meetingThe method comprises the steps of carrying out a first treatment on the surface of the The threshold function of wavelet transformation is set according to the high frequency component, and in wavelet transformation, commonly used thresholds for wavelet transformation include a rigrsure threshold, an sqtwolog threshold, a heursure threshold, a minimum threshold, and the like.
According to the embodiment of the invention, the time-frequency characteristics of the peak signal are extracted, and the time-frequency characteristics are matched and judged by utilizing dynamic time regularity, specifically:
acquiring a peak signal under the normal operation condition of the self-service printer, extracting a time-frequency characteristic in a discrete time sequence corresponding to the peak signal, and acquiring a characteristic set corresponding to the normal operation state of the self-service printer according to the time-frequency characteristic;
generating a peak signal curve according to a feature set corresponding to a normal running state, taking the peak signal curve as a normal state peak signal curve, and acquiring similarity between the peak signal curve corresponding to the current acoustic signal of the self-service printer and the normal state peak signal curve through a dynamic time warping algorithm;
Obtaining the BTW distance between a normal state peak signal curve and a current peak signal curve, and judging the BTW distance as similarity;
presetting a similarity threshold, and when the similarity is larger than or equal to the preset similarity threshold, indicating that the running state of the self-service printer corresponding to the current peak signal curve is a normal state;
when the similarity is smaller than a preset similarity threshold, the current peak signal curve is indicated to correspond to the running state of the self-service printer to be an abnormal state, fault early warning of the abnormal state is generated, and fault diagnosis is conducted on the abnormal state.
The normal state peak signal curve is describedAnd the current peak signal curve->Obtaining corresponding point combinations by matchingThe calculation formula of the BTW distance between the two curves is:
wherein, the liquid crystal display device comprises a liquid crystal display device,peak signal curves respectively in normal stateFirst feature point in line and current peak signal curve,/and>the last characteristic point in the normal state peak signal curve and the current peak signal curve respectively,the first combination point and the last combination point in the corresponding point combination are respectively +.>For the corresponding point combination set, +.>For the total number of corresponding point combinations->For Euclidean distance between corresponding points in the combination of peak signal curve in normal state and corresponding point of current peak signal curve, +. >Is the characteristic point on the normal state peak signal curve in the kth corresponding point combination,and k is the number of corresponding point terms, wherein the k is the characteristic point on the current peak signal curve in the kth corresponding point combination.
According to the embodiment of the invention, a fault recognition model is constructed based on deep learning, fault characteristics in acoustic signals are extracted, the fault characteristics are input into the trained fault recognition model, and a fault recognition result is output, specifically:
constructing a fault recognition model according to a convolutional neural network and a gating circulation network, acquiring common fault information and corresponding acoustic signal time sequences of a self-service printer by using a big data means, regarding different fault types or fault positions as independent categories, setting data labels according to the categories, taking acoustic signal data with the labels as training data, and training the fault recognition model;
leading the acoustic signal subjected to the current wavelet noise filtering into a fault recognition model, acquiring the characteristics of the acoustic signal subjected to the wavelet noise filtering in a convolutional neural network unit through a convolutional layer, and downsampling the extracted characteristics through a pooling layer;
importing the characteristic information after pooling operation into a gating circulation network unit, learning through the two layers of gating circulation network units, screening acoustic signal characteristics extracted by the convolutional neural network unit, and obtaining the periodicity rule of characteristic acoustic signal data characteristics;
And carrying out fault identification on the output characteristics of the gating circulation network unit by using the Softmax unit, and outputting a fault identification result.
The method is characterized in that input data are fully mined through a convolutional neural network in a fault recognition model, extracted features are subjected to downsampling through pooling layer operation to reduce weight parameters, the extracted features are sequentially input into two layers of gating circulating network units to learn, the time sequence features of acoustic signals are guaranteed not to be lost, the intrinsic relation and periodicity rules between the data are acquired to the greatest extent, the convolutional neural network units and the gating circulating network units are connected through a residual network, and training errors are effectively reduced through the residual network.
The method comprises the steps of matching a printing task in the running process according to a timestamp of an acoustic signal acquired by a current self-service printer, and extracting characteristic information of the printing task according to layout information of the printing task, wherein the characteristic information comprises color characteristics, position characteristics and texture characteristics; scanning the image information of the printed paper, preprocessing the image information, dividing the image information into image blocks with preset sizes according to preset dividing areas, and obtaining the information entropy of each image block; when the information entropy of the image block is larger than a preset information entropy threshold, subdividing the image block, ensuring that the information entropy of each subdivided image block accords with a preset information entropy standard, extracting characteristic information of the image block, and comparing the extracted characteristic information with characteristic information in a printing task to obtain similarity; marking the image blocks with similarity not meeting the preset similarity requirement, comparing frame by frame according to the layout information of the print task to obtain defect information, and carrying out matching verification on the fault information output by the fault identification model according to the defect information; when the fault identification information is matched with the defect information, directly sending fault early warning according to the fault identification information; otherwise, acquiring a possibly-occurring fault set to generate early warning information and sending the early warning information; and evaluating the fault degree according to the similarity deviation of the marked image blocks and the defect information, and embedding the fault degree into fault early warning information.
The third aspect of the present invention also provides a computer readable storage medium, the computer readable storage medium including a remote fault monitoring method program of a self-service printer, the remote fault monitoring method program of the self-service printer implementing the steps of the remote fault monitoring method of the self-service printer as described in any one of the above.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The remote fault monitoring method for the self-service printer is characterized by comprising the following steps of:
collecting an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak value signal;
extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree.
2. The remote fault monitoring method of a self-service printer according to claim 1, wherein the method is characterized by collecting an acoustic signal in the operation process of the self-service printer, performing noise reduction pretreatment on the acoustic signal, suppressing background noise in the acoustic signal, and generating a peak signal, and specifically comprises the following steps:
acquiring an acoustic signal in the operation process of the self-service printer through an acoustic sensor preset in the self-service printer, and generating an acoustic signal time sequence by combining the acquired acoustic signal with a time stamp;
decomposing the acoustic signal time sequence into mutually independent components according to the signal characteristics on time sequence through empirical mode decomposition, selecting high-frequency components of the components, and selecting a threshold function for setting wavelet transformation according to the high-frequency components;
the acoustic signal is subjected to threshold processing through the threshold function, the noise content in the filtered signal is evaluated, and whether the set threshold function meets the noise reduction standard is judged;
if the wavelet transformation parameters do not meet the threshold value, setting the adaptive parameters in the threshold value function to carry out threshold value compensation, and correcting the adaptive parameters according to the multiple iteration threshold value compensation to obtain an optimal threshold value function of the wavelet transformation;
and carrying out peak extraction on the acoustic signals after noise reduction according to a preset time interval, and generating a peak signal discrete time sequence based on the extracted peak signals.
3. The remote fault monitoring method for a self-service printer according to claim 1, wherein the time-frequency characteristics of the peak signal are extracted, and the time-frequency characteristics are matched and judged by using dynamic time regularity, specifically:
acquiring a peak signal under the normal operation condition of the self-service printer, extracting a time-frequency characteristic in a discrete time sequence corresponding to the peak signal, and acquiring a characteristic set corresponding to the normal operation state of the self-service printer according to the time-frequency characteristic;
generating a peak signal curve according to a feature set corresponding to a normal running state, taking the peak signal curve as a normal state peak signal curve, and acquiring similarity between the peak signal curve corresponding to the current acoustic signal of the self-service printer and the normal state peak signal curve through a dynamic time warping algorithm;
peak signal curve of normal stateAnd the current peak signal curve->Obtaining the corresponding point combination by matching>The calculation formula of the BTW distance between the two curves is:
wherein (1)>The first peak signal curve and the current peak signal curve are respectivelyA feature point->The last characteristic point in the peak signal curve in the normal state and the current peak signal curve are respectively +. >The first combination point and the last combination point in the corresponding point combination are respectively +.>For the corresponding point combination set, +.>To the total number of corresponding point combinations , / / >For Euclidean distance between corresponding points in the combination of peak signal curve in normal state and corresponding point of current peak signal curve, +.>For the characteristic point on the normal state peak signal curve in the kth corresponding point combination, +.>And k is the number of corresponding point terms, wherein the k is the characteristic point on the current peak signal curve in the kth corresponding point combination.
4. The remote fault monitoring method for a self-service printer according to claim 3, wherein a BTW distance between a normal state peak signal curve and a current peak signal curve is obtained, and the BTW distance is used as a similarity to judge;
presetting a similarity threshold, and when the similarity is larger than or equal to the preset similarity threshold, indicating that the running state of the self-service printer corresponding to the current peak signal curve is a normal state;
when the similarity is smaller than a preset similarity threshold, the current peak signal curve is indicated to correspond to the running state of the self-service printer to be an abnormal state, fault early warning of the abnormal state is generated, and fault diagnosis is conducted on the abnormal state.
5. The remote fault monitoring method of a self-service printer according to claim 1, wherein the fault recognition model is constructed based on deep learning, fault characteristics in acoustic signals are extracted, the fault characteristics are input into the trained fault recognition model, and a fault recognition result is output, specifically:
Constructing a fault recognition model according to a convolutional neural network and a gating circulation network, acquiring common fault information and corresponding acoustic signal time sequences of a self-service printer by using a big data means, regarding different fault types or fault positions as independent categories, setting data labels according to the categories, taking acoustic signal data with the labels as training data, and training the fault recognition model;
leading the acoustic signal subjected to the current wavelet noise filtering into a fault recognition model, acquiring the characteristics of the acoustic signal subjected to the wavelet noise filtering in a convolutional neural network unit through a convolutional layer, and downsampling the extracted characteristics through a pooling layer;
importing the characteristic information after pooling operation into a gating circulation network unit, learning through the two layers of gating circulation network units, screening acoustic signal characteristics extracted by the convolutional neural network unit, and obtaining the periodicity rule of characteristic acoustic signal data characteristics;
and carrying out fault identification on the output characteristics of the gating circulation network unit by using the Softmax unit, and outputting a fault identification result.
6. The remote fault monitoring method of a self-service printer according to claim 1, wherein the method is characterized by obtaining image information of printed paper corresponding to acoustic signals collected by the self-service printer, verifying a fault identification result according to feature similarity of the image information and a print job, and analyzing a fault degree, and specifically comprises the following steps:
Matching the printing task in the running process according to the time stamp of the acoustic signal acquired by the current self-service printer, and extracting the characteristic information of the printing task according to the layout information of the printing task, wherein the characteristic information comprises color characteristics, position characteristics and texture characteristics;
scanning the image information of the printed paper, preprocessing the image information, dividing the image information into image blocks with preset sizes according to preset dividing areas, and obtaining the information entropy of each image block;
when the information entropy of the image block is larger than a preset information entropy threshold, subdividing the image block, ensuring that the information entropy of each subdivided image block accords with a preset information entropy standard, extracting characteristic information of the image block, and comparing the extracted characteristic information with characteristic information in a printing task to obtain similarity;
marking the image blocks with similarity not meeting the preset similarity requirement, comparing frame by frame according to the layout information of the print task to obtain defect information, and carrying out matching verification on the fault information output by the fault identification model according to the defect information;
and meanwhile, evaluating the fault degree according to the similarity deviation and the defect information of the marked image blocks, and embedding the fault degree into fault early warning information.
7. A remote fault monitoring system for a self-service printer, the system comprising: the remote fault monitoring system comprises a memory and a processor, wherein the memory comprises a remote fault monitoring method program of a self-service printer, and the remote fault monitoring method program of the self-service printer realizes the following steps when being executed by the processor:
collecting an acoustic signal in the operation process of the self-service printer, carrying out noise reduction pretreatment on the acoustic signal, inhibiting background noise in the acoustic signal, and generating a peak value signal;
extracting time-frequency characteristics of peak signals, and matching the time-frequency characteristics by using dynamic time regularity to judge the running state of the self-service printer;
constructing a fault recognition model based on deep learning, extracting fault characteristics in acoustic signals, inputting the fault characteristics into the trained fault recognition model, and outputting a fault recognition result;
and acquiring image information of printed paper corresponding to the acoustic signals acquired by the self-service printer, verifying a fault identification result according to the feature similarity of the image information and the print task, and analyzing the fault degree.
8. The remote fault monitoring system of a self-service printer according to claim 7, wherein the time-frequency characteristics of the peak signal are extracted, and the time-frequency characteristics are matched and judged by using dynamic time regularity, specifically:
Acquiring a peak signal under the normal operation condition of the self-service printer, extracting a time-frequency characteristic in a discrete time sequence corresponding to the peak signal, and acquiring a characteristic set corresponding to the normal operation state of the self-service printer according to the time-frequency characteristic;
generating a peak signal curve according to a feature set corresponding to a normal running state, taking the peak signal curve as a normal state peak signal curve, and acquiring similarity between the peak signal curve corresponding to the current acoustic signal of the self-service printer and the normal state peak signal curve through a dynamic time warping algorithm;
peak signal curve of normal stateCurve with current peak signalObtaining the corresponding point combination by matching>The calculation formula of the BTW distance between the two curves is:
wherein (1)>The first characteristic point in the normal state peak signal curve and the current peak signal curve respectively, < ->The last characteristic point in the peak signal curve in the normal state and the current peak signal curve are respectively +.>The first combination point and the last combination point in the corresponding point combination are respectively +.>For the corresponding point combination set, +.>For the total number of corresponding point combinations->For Euclidean distance between corresponding points in the combination of peak signal curve in normal state and corresponding point of current peak signal curve, +. >For the characteristic point on the normal state peak signal curve in the kth corresponding point combination, +.>And k is the number of corresponding point terms, wherein the k is the characteristic point on the current peak signal curve in the kth corresponding point combination.
9. The remote fault monitoring system of a self-service printer according to claim 8, wherein a BTW distance between a normal state peak signal curve and a current peak signal curve is obtained, and the BTW distance is used as a similarity to determine;
presetting a similarity threshold, and when the similarity is larger than or equal to the preset similarity threshold, indicating that the running state of the self-service printer corresponding to the current peak signal curve is a normal state;
when the similarity is smaller than a preset similarity threshold, the current peak signal curve is indicated to correspond to the running state of the self-service printer to be an abnormal state, fault early warning of the abnormal state is generated, and fault diagnosis is conducted on the abnormal state.
10. The remote fault monitoring system of a self-service printer according to claim 7, wherein the fault recognition model is constructed based on deep learning, the fault characteristics in the acoustic signals are extracted, the fault characteristics are input into the trained fault recognition model, and the fault recognition result is output, specifically:
Constructing a fault recognition model according to a convolutional neural network and a gating circulation network, acquiring common fault information and corresponding acoustic signal time sequences of a self-service printer by using a big data means, regarding different fault types or fault positions as independent categories, setting data labels according to the categories, taking acoustic signal data with the labels as training data, and training the fault recognition model;
leading the acoustic signal subjected to the current wavelet noise filtering into a fault recognition model, acquiring the characteristics of the acoustic signal subjected to the wavelet noise filtering in a convolutional neural network unit through a convolutional layer, and downsampling the extracted characteristics through a pooling layer;
importing the characteristic information after pooling operation into a gating circulation network unit, learning through the two layers of gating circulation network units, screening acoustic signal characteristics extracted by the convolutional neural network unit, and obtaining the periodicity rule of characteristic acoustic signal data characteristics;
and carrying out fault identification on the output characteristics of the gating circulation network unit by using the Softmax unit, and outputting a fault identification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310473565.0A CN116189349B (en) | 2023-04-28 | 2023-04-28 | Remote fault monitoring method and system for self-service printer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310473565.0A CN116189349B (en) | 2023-04-28 | 2023-04-28 | Remote fault monitoring method and system for self-service printer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116189349A true CN116189349A (en) | 2023-05-30 |
CN116189349B CN116189349B (en) | 2023-07-18 |
Family
ID=86452764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310473565.0A Active CN116189349B (en) | 2023-04-28 | 2023-04-28 | Remote fault monitoring method and system for self-service printer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116189349B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117232584A (en) * | 2023-11-10 | 2023-12-15 | 山东特发光源光通信有限公司 | Cable winch quality detection system based on image analysis |
CN117931103A (en) * | 2024-01-24 | 2024-04-26 | 浙江沧田智能信息科技有限公司 | Laser printer fault identification method and system based on remote interaction |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018153275A1 (en) * | 2017-02-21 | 2018-08-30 | 珠海天威飞马打印耗材有限公司 | Fault prompt method and device for 3d printer, computer device and computer-readable storage medium |
CN110808068A (en) * | 2019-11-11 | 2020-02-18 | 北京软通智城科技有限公司 | Sound detection method, device, equipment and storage medium |
CN110867196A (en) * | 2019-12-03 | 2020-03-06 | 桂林理工大学 | Machine equipment state monitoring system based on deep learning and voice recognition |
CN111736781A (en) * | 2020-05-06 | 2020-10-02 | 时时同云科技(成都)有限责任公司 | Fault type identification method and device of intelligent terminal equipment |
US20210011457A1 (en) * | 2019-07-11 | 2021-01-14 | Institute Of Automation, Chinese Academy Of Sciences | Online monitoring device and system for a 3D printing device |
CN113094218A (en) * | 2021-03-30 | 2021-07-09 | 上海汉图科技有限公司 | Method, device and equipment for identifying printer fault |
CN113889147A (en) * | 2021-10-09 | 2022-01-04 | 杭州电子科技大学 | Mechanical system voiceprint signal matching method based on dynamic time warping algorithm |
CN114372409A (en) * | 2021-12-17 | 2022-04-19 | 西安铂力特增材技术股份有限公司 | Method, device and equipment for detecting faults of 3D printing equipment and storage medium |
CN114414963A (en) * | 2022-01-20 | 2022-04-29 | 西安交通大学 | Acoustic imaging positioning system and method for intelligent monitoring of substation domain faults |
JP2022086643A (en) * | 2020-11-30 | 2022-06-09 | 凸版印刷株式会社 | Printer abnormality sign detection system, printer abnormality sign detection method and program |
CN115510901A (en) * | 2022-09-20 | 2022-12-23 | 煤炭科学技术研究院有限公司 | Fault identification method and device for carrier roller of belt conveyor |
CN115598513A (en) * | 2022-10-08 | 2023-01-13 | 出门问问创新科技有限公司(Cn) | Fault diagnosis method, fault diagnosis device, electronic device and storage medium |
-
2023
- 2023-04-28 CN CN202310473565.0A patent/CN116189349B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018153275A1 (en) * | 2017-02-21 | 2018-08-30 | 珠海天威飞马打印耗材有限公司 | Fault prompt method and device for 3d printer, computer device and computer-readable storage medium |
US20210011457A1 (en) * | 2019-07-11 | 2021-01-14 | Institute Of Automation, Chinese Academy Of Sciences | Online monitoring device and system for a 3D printing device |
CN110808068A (en) * | 2019-11-11 | 2020-02-18 | 北京软通智城科技有限公司 | Sound detection method, device, equipment and storage medium |
CN110867196A (en) * | 2019-12-03 | 2020-03-06 | 桂林理工大学 | Machine equipment state monitoring system based on deep learning and voice recognition |
CN111736781A (en) * | 2020-05-06 | 2020-10-02 | 时时同云科技(成都)有限责任公司 | Fault type identification method and device of intelligent terminal equipment |
JP2022086643A (en) * | 2020-11-30 | 2022-06-09 | 凸版印刷株式会社 | Printer abnormality sign detection system, printer abnormality sign detection method and program |
CN113094218A (en) * | 2021-03-30 | 2021-07-09 | 上海汉图科技有限公司 | Method, device and equipment for identifying printer fault |
CN113889147A (en) * | 2021-10-09 | 2022-01-04 | 杭州电子科技大学 | Mechanical system voiceprint signal matching method based on dynamic time warping algorithm |
CN114372409A (en) * | 2021-12-17 | 2022-04-19 | 西安铂力特增材技术股份有限公司 | Method, device and equipment for detecting faults of 3D printing equipment and storage medium |
CN114414963A (en) * | 2022-01-20 | 2022-04-29 | 西安交通大学 | Acoustic imaging positioning system and method for intelligent monitoring of substation domain faults |
CN115510901A (en) * | 2022-09-20 | 2022-12-23 | 煤炭科学技术研究院有限公司 | Fault identification method and device for carrier roller of belt conveyor |
CN115598513A (en) * | 2022-10-08 | 2023-01-13 | 出门问问创新科技有限公司(Cn) | Fault diagnosis method, fault diagnosis device, electronic device and storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117232584A (en) * | 2023-11-10 | 2023-12-15 | 山东特发光源光通信有限公司 | Cable winch quality detection system based on image analysis |
CN117232584B (en) * | 2023-11-10 | 2024-03-22 | 山东特发光源光通信有限公司 | Cable winch quality detection system based on image analysis |
CN117931103A (en) * | 2024-01-24 | 2024-04-26 | 浙江沧田智能信息科技有限公司 | Laser printer fault identification method and system based on remote interaction |
Also Published As
Publication number | Publication date |
---|---|
CN116189349B (en) | 2023-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116189349B (en) | Remote fault monitoring method and system for self-service printer | |
CN109905270B (en) | Method, apparatus and computer readable storage medium for locating root cause alarm | |
CN111766253A (en) | Solder paste printing quality detection method, data processing device, and computer storage medium | |
CN117235655B (en) | Intelligent heat supply abnormal condition identification method and system based on federal learning | |
CN115302963B (en) | Bar code printing control method, system and medium based on machine vision | |
CN111445058B (en) | Data analysis method, device, equipment and computer readable storage medium | |
CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
CN116843955A (en) | Microorganism classification and identification method and system based on computer vision | |
CN111259949A (en) | Fault identification model construction method, model and identification method for aircraft environmental control system | |
CN113592814A (en) | Laser welding surface defect detection method for safety explosion-proof valve of new energy power battery | |
CN115719283A (en) | Intelligent accounting management system | |
WO2024119983A1 (en) | Anomality detection method and apparatus for cable terminal of rail vehicle | |
CN117235661B (en) | AI-based direct drinking water quality monitoring method | |
CN117421692A (en) | Garbage illegal delivery identification method, device and equipment for garbage delivery station | |
CN117726965A (en) | Unattended weighing control method and system based on neural network | |
CN115871745B (en) | Intelligent maintenance method and device applied to rail transit | |
CN116723540A (en) | Quality difference detection model training and quality difference detection method for 5G network data | |
CN111507850A (en) | Authority guaranteeing method and related device and equipment | |
CN113447572B (en) | Steel rail flaw detection method, electronic device, steel rail flaw detection vehicle and readable storage medium | |
CN113657437B (en) | Power grid overhaul alarm confirmation method and system | |
CN113505960B (en) | Printing working condition online identification method, printing working condition online identification system, electronic equipment and storage medium | |
Zhang et al. | Nature scene statistics approach based on ICA for no-reference image quality assessment | |
CN115205952B (en) | Online learning image acquisition method and system based on deep learning | |
CN117357104B (en) | Audio analysis method based on user characteristics | |
DE102022103844B3 (en) | Method for optimizing a production process based on visual information and device for carrying out the method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |