CN114997749B - Intelligent scheduling method and system for power personnel - Google Patents

Intelligent scheduling method and system for power personnel Download PDF

Info

Publication number
CN114997749B
CN114997749B CN202210919919.5A CN202210919919A CN114997749B CN 114997749 B CN114997749 B CN 114997749B CN 202210919919 A CN202210919919 A CN 202210919919A CN 114997749 B CN114997749 B CN 114997749B
Authority
CN
China
Prior art keywords
audio signal
fault
power personnel
electric power
machine
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
Application number
CN202210919919.5A
Other languages
Chinese (zh)
Other versions
CN114997749A (en
Inventor
杨健
陈春玲
周焱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Priority to CN202210919919.5A priority Critical patent/CN114997749B/en
Publication of CN114997749A publication Critical patent/CN114997749A/en
Application granted granted Critical
Publication of CN114997749B publication Critical patent/CN114997749B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G06Q10/063112—Skill-based matching of a person or a group to a task
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • 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
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • 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
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Strategic Management (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Signal Processing (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an intelligent scheduling method and system for power personnel, wherein the method comprises the following steps: acquiring an audio signal sample when the machine works, and determining whether the machine has a fault according to the audio signal sample; if the machine is judged to have a fault, determining the fault type of the machine according to the audio signal sample; constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the fault repair times of the electric power personnel, the repair success rate of the electric power personnel and the fault type of the machine; and solving the intelligent scheduling problem to obtain an intelligent scheduling scheme. The invention can accurately schedule power personnel in the first time based on the type of the machine fault, thereby completing the maintenance of the machine fault.

Description

Intelligent scheduling method and system for power personnel
Technical Field
The invention relates to an intelligent scheduling method and system for power personnel, and belongs to the technical field of power Internet of things and the technical field of intelligent scheduling of power systems.
Background
As an important infrastructure related to national security and national economic life cycle, the power system not only can stably and reliably operate under a normal environment, but also can timely and accurately find out system problems when some problems occur in the system, and accurately dispatch power personnel to minimize economic loss, thereby better ensuring the electricity consumption experience of residents. Therefore, how to quickly find out the problem after the system has a problem, and accurately schedule power personnel, so as to reduce the economic loss caused by power failure becomes a key problem to be solved urgently.
However, most of the existing intelligent scheduling methods for power personnel have some disadvantages, for example, when a certain machine fails, only a problem in the power system can be determined, but a fault type of the certain machine cannot be accurately fed back. Based on this situation, there are problems in scheduling electric power personnel, such as scheduling one electric power personnel, but he has no experience in repairing the machine failure, and then only scheduling other electric power personnel to perform the repair, which wastes a lot of time, and during this period, may be accompanied by great economic loss.
Disclosure of Invention
Aiming at the problems and the defects in the prior art, the invention provides the intelligent dispatching method for the electric power personnel, which is used for realizing the accurate dispatching of the electric power personnel by combining the machine fault prediction fault classification result and the maintenance experience of the dispatching personnel.
In order to achieve the technical purpose, the invention adopts the following scheme.
On one hand, the invention provides an intelligent scheduling method for power personnel, which comprises the following steps:
acquiring an audio signal sample when the machine works, and determining whether the machine has a fault according to the audio signal sample;
if the machine is judged to have a fault, determining the fault type of the machine according to the audio signal sample;
constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the fault repair success times of the electric power personnel, the repair success rate and the machine fault type;
and solving the intelligent scheduling problem to obtain an intelligent scheduling scheme.
Further, constructing an intelligent scheduling problem, comprising: determining the number of dispatchable electric power personnel, and comparing the number of dispatchable electric power personnel with the number of audio signal samples with faults;
if the number of dispatchable electric power personnel is less than or equal to the number of audio signal samples with faults, solving the intelligent dispatching problem of the first electric power personnel;
electric power personnel number recording assuming schedulableLThe set of power personnel is represented as
Figure 96967DEST_PATH_IMAGE001
(ii) a According to the historical maintenance records of the electric power personnel, a maintenance file of each electric power personnel is established, and the electric power personnellMaintenance profile = { machine fault typekPerson of electric powerlSuccessfully repairing failure typeskNumber of times of
Figure 996921DEST_PATH_IMAGE002
Person of electric powerlRepairing failure typeskSuccess rate of
Figure 939469DEST_PATH_IMAGE003
，
Figure 908562DEST_PATH_IMAGE004
｝，KRepresenting the number of known fault types, the firstK+1 fault type represents other unknown types of faults;
suppose that the current time is commonMA failed audio signal sample, each sample
Figure 125917DEST_PATH_IMAGE005
,m=1,2,…,MIs expressed as
Figure 611869DEST_PATH_IMAGE006
Wherein
Figure 256477DEST_PATH_IMAGE007
Is shown asmThe type of machine fault in the audio signal sample isK+Failure type of 1 typekThe probability of (d);
calculating the importance of each audio signal sample with faults
Figure 712866DEST_PATH_IMAGE008
In which
Figure 202753DEST_PATH_IMAGE009
Representing the type of faultkThe priority of (2);
according to importance
Figure 811720DEST_PATH_IMAGE010
Size, before selection from large to smallLThe audio signal samples with faults are stored and the selected samples are indexed in the fault audio signal sample set
Figure 361650DEST_PATH_IMAGE011
Performing the following steps;
the first power personnel intelligent scheduling problem is expressed as follows:
Figure 39756DEST_PATH_IMAGE012
；
wherein,
Figure 598913DEST_PATH_IMAGE013
indicating electric personnel
Figure 311655DEST_PATH_IMAGE014
Scheduling strategy of (1), electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine failure of an audio signal sample, then
Figure 783218DEST_PATH_IMAGE015
Otherwise
Figure 214200DEST_PATH_IMAGE016
；
Figure 311469DEST_PATH_IMAGE017
For electric power personnel
Figure 878716DEST_PATH_IMAGE018
Successfully repairing failure typeskThe number of times of the operation of the motor,
Figure 770449DEST_PATH_IMAGE019
for electric power personnel
Figure 173879DEST_PATH_IMAGE018
Repairing failure typeskThe success rate of the process is improved,
Figure 74839DEST_PATH_IMAGE020
indicating electric personnel
Figure 496593DEST_PATH_IMAGE018
Scheduling policy of, electric power personnel
Figure 824807DEST_PATH_IMAGE018
Scheduling policy ofExpressed as: if the power personnel
Figure 712604DEST_PATH_IMAGE018
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 151675DEST_PATH_IMAGE021
Otherwise
Figure 427936DEST_PATH_IMAGE022
。
Further, constructing an intelligent scheduling problem, including: determining the number of dispatchable electric power personnel, and comparing the number of dispatchable electric power personnel with the number of determined audio signal samples with faults; if the number of dispatchable power personnel is larger than the number of audio signal samples with faults, solving a second power personnel intelligent dispatching problem, and finally obtaining a power personnel intelligent dispatching scheme;
the second power personnel intelligent scheduling problem is expressed as follows:
Figure 927050DEST_PATH_IMAGE023
；
wherein,
Figure 288761DEST_PATH_IMAGE024
indicating electric personnel
Figure 282256DEST_PATH_IMAGE014
Scheduling strategy of (1), electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 678603DEST_PATH_IMAGE025
Otherwise, otherwise
Figure 348618DEST_PATH_IMAGE026
；LThe number of the electric power personnel can be dispatched,
Figure 932046DEST_PATH_IMAGE027
for electric power personnellSuccessfully repairing a failure typekThe number of times of the operation of the motor,
Figure 978500DEST_PATH_IMAGE028
for electric power personnellRepairing failure typeskThe success rate of the process is improved,
Figure 229353DEST_PATH_IMAGE029
，Krepresenting the number of known fault types, the firstK+The 1 fault type represents the other unknown type of fault,
Figure 821002DEST_PATH_IMAGE030
for electric power personnel
Figure 891726DEST_PATH_IMAGE031
Successfully repairing the failure typekThe number of times of the above-mentioned operations,
Figure 476291DEST_PATH_IMAGE032
for personnel of electric power
Figure 581651DEST_PATH_IMAGE033
Repairing failure typeskThe success rate of the process is increased,
Figure 593469DEST_PATH_IMAGE034
indicating electric personnel
Figure 433380DEST_PATH_IMAGE031
Scheduling policy of, electric power personnel
Figure 290478DEST_PATH_IMAGE035
The scheduling policy of (a) is expressed as: if the power personnel
Figure 515923DEST_PATH_IMAGE036
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 698642DEST_PATH_IMAGE037
Otherwise
Figure 743959DEST_PATH_IMAGE038
，
Figure 418129DEST_PATH_IMAGE039
Is shown asmThe type of machine fault in the audio signal sample isKProbability of one of +1 types of failure,Mis the total number of audio signal samples for which a fault exists.
Further, determining whether the machine has a fault based on the audio signal sample includes:
extracting the feature vector of the Mel frequency cepstrum coefficient of the audio signal sample when the machine works, and reconstructing the feature vector of the Mel frequency cepstrum coefficient through an encoder and a decoder;
and comparing the reconstruction result with an abnormal score threshold value to determine whether the machine has a fault.
Still further, extracting the mel-frequency cepstrum coefficient feature vector of the audio signal sample when the machine is working comprises:
converting the audio signal sample frequency into a mel frequency;
the audio signal samples are pre-emphasized by a high pass filter, such that the audio signal samples remain in the entire band from low frequencies to high frequencies, the high pass filter being:
Figure 763660DEST_PATH_IMAGE040
；
wherein,ais a pre-emphasis coefficient;
Figure 851702DEST_PATH_IMAGE041
a system function representing a high pass filter;
windowing each section of single-frame signal, dividing the audio signal sample after pre-emphasis into a plurality of sections of single-frame signals, wherein each section of single-frame signal corresponds to a frequency spectrum;
the windowing operation is as follows:
Figure 649893DEST_PATH_IMAGE042
；
wherein,
Figure 114373DEST_PATH_IMAGE043
in order to be a function of the windowing,Nin order to be the frame length,nis the number of frames.
Calculating the relation between the frequency and the amplitude by using short-time fast Fourier transform; the short-time fast Fourier transform formula is:
Figure 65142DEST_PATH_IMAGE044
；
wherein,x(n) Is a firstnThe amplitude of the signal of the frame,E(n) Is the transformed energy signal;
discrete cosine transform is carried out on the audio signal sample to obtain a Mel frequency cepstrum coefficient, and the formula is as follows:
Figure 324085DEST_PATH_IMAGE045
；
Figure 343994DEST_PATH_IMAGE046
；
wherein,f(n) Representing samples of an audio signalnThe signal of the frame in the time domain,F(n) Is the coefficient after the cosine transform and,C(n) Is an audio signal samplenA compensation coefficient for the frame;
finally, the feature vector of the low-order Mel frequency cepstrum coefficient describing the audio data is obtainedMFCCThe data form is as follows:
Figure 408902DEST_PATH_IMAGE047
；
wherein F 11 Mel-frequency cepstral coefficients representing a 1 st frame of the 1 st audio signal sample; f N1 Mel-frequency cepstral coefficients representing an nth frame of the 1 st audio signal sample; f M1 Merr-frequency cepstrum coefficient, F, representing the 1 st frame of the Mth audio signal sample MN The mel-frequency cepstral coefficients of the nth frame representing the mth audio signal sample.
Further, reconstructing the mel-frequency cepstrum coefficient feature vector by an encoder and a decoder, comprising:
encoder E input feature vector
Figure 197866DEST_PATH_IMAGE048
Converting the feature vector of the Mel frequency cepstrum coefficient of the obtained audio signal sample into potential feature vector
Figure 644022DEST_PATH_IMAGE049
Expressed as:
Figure 416806DEST_PATH_IMAGE050
；
wherein
Figure 223088DEST_PATH_IMAGE051
Is a parameter of the encoder;
decoder D will be latent feature vector
Figure 132138DEST_PATH_IMAGE052
Reconstructing into input feature vectors
Figure 998463DEST_PATH_IMAGE053
Expressed as:
Figure 743697DEST_PATH_IMAGE054
；
wherein
Figure 353669DEST_PATH_IMAGE055
Is a parameter of the decoder;
in the above two formulas:
Figure 117226DEST_PATH_IMAGE056
subscriptiIndicates that it is currently the secondiA feature vector;sthe total number of feature vectors.
Still further, compare the result of rebuilding with unusual score threshold and confirm whether there is a fault in the machine, the concrete step includes: adjusting parameters of the encoder and decoder to minimize an error between the reconstructed data and the input data, the reconstruction error function being:
Figure 420031DEST_PATH_IMAGE057
；
Figure 649631DEST_PATH_IMAGE058
is an error function;
Figure 797716DEST_PATH_IMAGE059
representing the input feature vector as
Figure 681358DEST_PATH_IMAGE060
Obtaining a reconstruction error value;
taking reconstruction error as an abnormal score of an audio signalSThe manner of determining whether a machine has a fault is as follows:
Figure 889485DEST_PATH_IMAGE061
；
Figure 858579DEST_PATH_IMAGE062
when the input feature vector is X, the obtained reconstruction error value,
Figure 810354DEST_PATH_IMAGE063
is a set anomaly score threshold.
Further, if it is determined that the machine has a fault, classifying by using the CNN model to obtain a fault type of the machine, including:
taking the Mel frequency cepstrum coefficient feature vector of the audio signal sample judged to have the fault on the machine as the input of the CNN model, and outputting the probability result that the audio signal is of the known fault type through the softmax function; for one audio signal sample X, assume that the machine fault type result output via the softmax layer is:
Figure 299235DEST_PATH_IMAGE064
；
wherein,
Figure 678264DEST_PATH_IMAGE065
the type of machine fault output for the single node of softmax iskThe probability of (a) of (b) being,Krepresenting the number of known fault types, the firstK+1 type of fault represents other unknown types of fault and satisfies
Figure 134653DEST_PATH_IMAGE066
；
The type of the machine fault with the maximum output probability is the final determined result.
In a second aspect, the present invention further provides an intelligent scheduling system for power personnel, including: the system comprises a fault judgment module, a fault type judgment module and a scheduling scheme solving module;
the fault judgment module is used for acquiring an audio signal sample when the machine works and determining whether the machine has a fault according to the audio signal sample;
the fault type judging module is used for determining the fault type of the machine according to the audio signal sample if the machine is judged to have a fault;
the scheduling scheme solving module is used for constructing an intelligent scheduling problem according to the number of schedulable electric personnel, the failure repair success times of the electric personnel, the repair success rate and the machine failure type; and solving the intelligent scheduling problem to obtain an intelligent scheduling scheme.
The intelligent scheduling method for the power personnel provided by the invention has the following advantages:
the method accurately schedules the corresponding power personnel with rich maintenance experience based on the fault type of the machine, and rapidly and efficiently realizes scheduling with minimum economic loss; aiming at personnel scheduling, the problem of power personnel scheduling for maximizing the average repair rate of machine faults under different conditions is established, the intelligent scheduling of power personnel can be realized, and the time consumed by the scheduling of the power personnel can be effectively reduced;
the method adopts the self-encoder to reconstruct the input feature vector, has strong feature representation capability, has relatively simple network structure and is easy to train, thereby improving the realizability of the system;
the method combines unsupervised learning and supervised learning, effectively solves the problem of acquiring the audio signals of abnormal work of the machine, and greatly reduces the difficulty of acquiring training samples.
Drawings
Fig. 1 is a flowchart of a power personnel scheduling method according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of an embodiment of a method for determining whether a machine has a fault;
fig. 3 is a structure of a CNN model used in the embodiment of the present invention.
Detailed Description
The present invention is further illustrated by the following detailed description in conjunction with the accompanying drawings, which are included to provide a further understanding of the invention and are not intended to limit its scope, as various equivalent modifications of the invention will become apparent to those skilled in the art after reading the present invention and fall within the scope of the appended claims.
Example 1
The intelligent scheduling method for the power personnel comprises the following steps:
acquiring an audio signal sample when the machine works, and determining whether the machine has a fault according to the audio signal sample;
if the machine is judged to have a fault, determining the fault type of the machine according to the audio signal sample;
constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the fault repair success times of the electric power personnel, the repair success rate of the electric power personnel and the fault type of the machine;
and solving the intelligent scheduling problem to obtain an intelligent scheduling scheme.
In this embodiment, constructing an intelligent scheduling problem includes: determining the number of dispatchable electric power personnel, and comparing the number of dispatchable electric power personnel with the number of audio signal samples with faults;
if the number of schedulable power personnel is less than or equal to the number of audio signal samples with faults, solving an intelligent scheduling problem of the first power personnel;
before establishing the first electric power personnel intelligent scheduling problem, the number of the electric power personnel which can be scheduled is assumed to be recordedLWherein the set of power personnel can be represented as
Figure 624540DEST_PATH_IMAGE067
. Establishing a maintenance file of each power maintenance personnel according to the historical maintenance records of the power personnellMaintenance profile of = { machine fault typekElectric power personnellSuccessfully repairing a failure typekNumber of times of
Figure 482775DEST_PATH_IMAGE068
Electric power personnellRepairing failure typeskSuccess rate of
Figure 517858DEST_PATH_IMAGE069
，
Figure 461543DEST_PATH_IMAGE070
｝， KRepresenting the number of known fault types, aK+1 fault type represents other unknown types of faults;
suppose that the current time is commonMA sample of the audio signal with a fault, each sample
Figure 755121DEST_PATH_IMAGE071
,m=1,2,…,MIs expressed as a fault classification result of
Figure 467863DEST_PATH_IMAGE072
Wherein
Figure 188694DEST_PATH_IMAGE073
Is shown asmThe type of machine fault in the audio signal sample isK+Failure type of 1 typekThe probability of (d);
calculating the importance of each audio signal sample with faults
Figure 104828DEST_PATH_IMAGE074
Wherein
Figure 936518DEST_PATH_IMAGE075
Representing the type of faultkThe priority of (2);
according to importance
Figure 769345DEST_PATH_IMAGE076
Size, before selection from large to smallLThe audio signal samples with faults are stored and the selected samples are indexed in the fault audio signal sample set
Figure 661078DEST_PATH_IMAGE077
Performing the following steps;
the first power personnel intelligent scheduling problem is expressed as follows:
Figure 313776DEST_PATH_IMAGE012
；
wherein,
Figure 949157DEST_PATH_IMAGE078
indicating electric personnel
Figure 384293DEST_PATH_IMAGE014
Scheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 712506DEST_PATH_IMAGE079
Otherwise
Figure 852500DEST_PATH_IMAGE080
(ii) a The first power personnel intelligent scheduling problem (P1) is solved by adopting a Hungarian algorithm;Lthe number of the dispatchable electric power personnel is,kfor the type of failure of the machine,Krepresenting the number of known fault types, the firstK+The 1 fault type represents the other unknown type of fault,
Figure 25992DEST_PATH_IMAGE081
for electric power personnel
Figure 318565DEST_PATH_IMAGE082
Successfully repairing a failure typekThe number of times of the above-mentioned operations,
Figure 552100DEST_PATH_IMAGE083
for personnel of electric power
Figure 179390DEST_PATH_IMAGE082
Repairing failure typeskThe success rate of the process is increased,
Figure 422153DEST_PATH_IMAGE084
indicating electric personnel
Figure 552920DEST_PATH_IMAGE082
Scheduling policy of, electric power personnel
Figure 957356DEST_PATH_IMAGE082
The scheduling policy of (a) is expressed as: if the power personnel
Figure 822675DEST_PATH_IMAGE082
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 869129DEST_PATH_IMAGE085
Otherwise
Figure 854402DEST_PATH_IMAGE086
。
And if the number of dispatchable electric power personnel is greater than the number of audio signal samples with faults, solving the intelligent dispatching problem of the second electric power personnel, and finally obtaining the intelligent dispatching scheme of the electric power personnel.
The second power personnel intelligent scheduling problem is expressed as follows:
Figure 695319DEST_PATH_IMAGE087
；
wherein,
Figure 31623DEST_PATH_IMAGE088
indicating electric personnellScheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 366920DEST_PATH_IMAGE089
Otherwise
Figure 472279DEST_PATH_IMAGE090
(ii) a The second power personnel intelligent scheduling problem (P2) is solved by adopting a Hungarian algorithm;Lthe number of the electric power personnel can be dispatched,kin the case of a type of machine failure,
Figure 484098DEST_PATH_IMAGE091
for electric power personnellThe number of times of repair of (a),
Figure 307697DEST_PATH_IMAGE092
for personnel of electric powerlThe success rate of the repair of the steel pipe, Krepresenting the number of known fault types, the firstK+The 1 fault type represents the other unknown type of fault,
Figure 430374DEST_PATH_IMAGE093
for electric power personnel
Figure 427059DEST_PATH_IMAGE094
Successfully repairing the failure typekThe number of times of the above-mentioned operations,
Figure 609779DEST_PATH_IMAGE095
for electric power personnel
Figure 920675DEST_PATH_IMAGE094
Repair failure type ofkThe success rate of the process is increased,
Figure 581463DEST_PATH_IMAGE096
indicating electric personnel
Figure 661415DEST_PATH_IMAGE094
Scheduling policy of, electric power personnel
Figure 765768DEST_PATH_IMAGE094
The scheduling policy of (a) is expressed as: if the power personnel
Figure 298380DEST_PATH_IMAGE094
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 28439DEST_PATH_IMAGE097
Otherwise
Figure 228476DEST_PATH_IMAGE098
，
Figure 487419DEST_PATH_IMAGE099
Is shown asmThe type of machine fault in the audio signal samples isK+Probability of a failure type of the types in 1,Mis the total number of audio signal samples for which a fault exists.
The method is based on the fault type of the machine and accurately dispatches the corresponding power personnel with rich maintenance experience, and the dispatching is quickly and efficiently realized with the minimum economic loss; aiming at personnel scheduling, the problem of power personnel scheduling for maximizing the average repair rate of machine faults under different conditions is established, the intelligent scheduling of power personnel can be realized, and the time consumed by the scheduling of the power personnel can be effectively reduced.
Example 2
The embodiment provides an intelligent scheduling method for power personnel, which trains a self-encoder by using audio signal samples when different machines work normally and possibly existing interference audio signal samples in the environment, so that the MFCC characteristics of the audio signal samples can be reconstructed with the lowest reconstruction error, and then reconstructs the MFCC characteristics of the audio signal samples in a test set by using the trained self-encoder, thereby judging whether a machine fault occurs according to the reconstruction error. In addition, training a CNN model by using an audio signal sample of abnormal work of a machine to realize a fault classification function, and constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the fault repair success times of the electric power personnel, the repair success rate of the electric power personnel and the fault type of the machine; solving the intelligent scheduling problem to obtain an intelligent scheduling scheme, so that accurate scheduling can be realized for power personnel when a certain type of fault occurs in a certain machine, and the machine maintenance efficiency is improved.
As shown in fig. 1, the present embodiment includes the following steps:
step 101: collecting a plurality of groups of audio signal samples when different machines work normally, possibly existing interference audio signal samples and a small number of frequently occurring audio signal samples when the machines work abnormally in an electric power scene, and then filtering noise interference generated by non-main influence factors through a plurality of filters;
step 102: pre-emphasis, framing, windowing, fast Fourier transform, mel filtering and discrete cosine transform are carried out on the collected audio signal samples, and finally low-order MFCC characteristic values capable of describing the audio signal samples, namely Mel frequency cepstrum coefficient characteristic vectors, are obtained;
step 103: the extracted Mel frequency cepstrum coefficient feature vector of the audio signal sample when the machine normally works is used as the input of a self-encoder, so that the feature vector of the Mel frequency cepstrum coefficient of the audio signal sample can be fully learned, and the Mel frequency cepstrum coefficient feature vector of the audio signal sample can be reconstructed with the lowest reconstruction error;
step 104: reconstructing MFCC characteristics of audio signals in a test set by using a trained self-encoder, wherein the test set comprises a machine normal working audio signal sample, an environmental interference audio signal sample and a machine abnormal working audio signal sample;
step 105: by contrasting the eigenvectors before reconstruction
Figure 523640DEST_PATH_IMAGE100
And the reconstructed feature vector
Figure 526231DEST_PATH_IMAGE101
Taking the error between the two as the abnormal score of the audio signal sampleSIf the abnormal score is givenSGreater than a certain set abnormality score threshold
Figure 580774DEST_PATH_IMAGE102
If the input audio signal sample is the audio signal of the abnormal work of the machine (namely the machine fault), otherwise, the input audio signal sample is the audio signal of the normal work of the machine or some interference audio signal in the environment;
step 106: on the basis of step 105, if
Figure 276198DEST_PATH_IMAGE103
And if the machine is abnormal, inputting the Mel frequency cepstrum coefficient feature vector of the audio signal sample into the CNN model to judge the type of the machine fault. Because the number of training samples of the CNN model is insufficient, the output probability of the CNN model is generally low, and the machine fault is defined as other unknown type faults.
Step 107: based on the machine fault type and the number of machine faults determined in step 106, if number of power personnelLLess than machine fault numberMI.e. the total number of audio signal samples with faults, priority is given to the power personnel to the importance
Figure 48982DEST_PATH_IMAGE076
The machine fault with the largest value to minimize the loss due to machine fault, and therefore before the selectionLIs of importance
Figure 605996DEST_PATH_IMAGE076
Maximum value of machine fault, marked
Figure 515046DEST_PATH_IMAGE104
，
Figure 115792DEST_PATH_IMAGE074
；
Wherein
Figure 375872DEST_PATH_IMAGE075
Representing the type of faultkThe priority of (2);
and establishing the following scheduling problem, wherein the objective function is to maximize the mean repair rate of the machine fault, and can be expressed as:
Figure 720266DEST_PATH_IMAGE012
；
wherein,
Figure 749402DEST_PATH_IMAGE078
indicating a scheduling policy of the power personnel, if the power personnellIs scheduled for maintenancemA machine failure in an abnormal sample, then
Figure 534430DEST_PATH_IMAGE079
Otherwise, otherwise
Figure 16227DEST_PATH_IMAGE080
. The problem (P1) is solved by adopting Hungarian algorithm.
If the number of electric power personnelLGreater than the total number of audio signal samples with faultsMThen another power personnel scheduling problem is established that maximizes the mean repair rate of machine failures:
Figure 164312DEST_PATH_IMAGE087
；
the problem (P2) is still solved by the Hungarian algorithm.
And solving the two scheduling problems to finally obtain the optimal scheduling strategy of the power personnel.
As shown in fig. 2, determining whether a machine is malfunctioning based on an audio signal sample includes:
extracting the feature vector of the Mel frequency cepstrum coefficient of the audio signal sample when the machine works, and reconstructing the feature vector of the Mel frequency cepstrum coefficient through an encoder and a decoder;
and comparing the reconstruction result with an abnormal score threshold value to determine whether the machine has a fault.
Extracting a mel frequency cepstrum coefficient feature vector of an audio signal sample when a machine works, comprising the following steps:
converting the frequency of the audio signal sample into a mel frequency;
the audio signal samples are pre-emphasized by a high pass filter, such that the audio signal samples remain in the entire band from low frequencies to high frequencies, the high pass filter being:
Figure 47954DEST_PATH_IMAGE105
；
wherein,ais a pre-emphasis coefficient;
Figure 256082DEST_PATH_IMAGE106
a system function representing a high pass filter;
windowing each section of single-frame signal, dividing the audio signal sample after pre-emphasis into a plurality of sections of single-frame signals, wherein each section of single-frame signal corresponds to a frequency spectrum;
the windowing operation is as follows:
Figure 975907DEST_PATH_IMAGE107
；
wherein,
Figure 927683DEST_PATH_IMAGE108
in order to be a function of the windowing,Nin order to be the frame length,nis the frame number;
calculating the relation between the frequency and the amplitude by using short-time fast Fourier transform; the short-time fast fourier transform formula is:
Figure 931411DEST_PATH_IMAGE109
；
wherein,x(n) Is as followsnThe amplitude of the signal of the frame,E(n) Is the transformed energy signal;
because the frequency domain signal has a lot of redundant information, the energy amplitude of the frequency domain needs to be reduced by the filter bank, each frequency band is represented by a value, and the frequency is converted into the Mel frequency of the human ear for sound perception, the conversion formula is as follows:
Figure 310439DEST_PATH_IMAGE110
；
wherein,fthe unit is Hz for the original frequency of the audio.
The original audio frequency is the frequency of the audio signal sample itself, and then converted into mel frequency by mel frequency conversion formula. The pre-emphasis is performed to maintain the audio signal in the entire frequency band from low frequencies to high frequencies because the high frequency part of the signal is lost due to the friction of the sounding structure. Framing is for the purpose of facilitating signal study. Windowing is because after framing, there is overlap between frames, and the inter-frame spectrum is not stable, so windowing is needed to flatten the spectrum. The fast fourier transform operation is to transform a time domain signal into an energy distribution on the time-frequency domain.
Discrete cosine transform is carried out on the audio signal sample to obtain a Mel frequency cepstrum coefficient, and the formula is as follows:
Figure 766829DEST_PATH_IMAGE045
；
Figure 7448DEST_PATH_IMAGE046
；
wherein,f(n) Representing samples of an audio signalnThe signal of the frame in the time domain,F(n) Is the coefficient after the cosine transform and,C(n) Is an audio signal samplenA compensation coefficient for the frame;
finally obtaining the low-order Mel frequency cepstrum coefficient feature vector for describing audio dataMFCC，
The data form is as follows:
Figure 600104DEST_PATH_IMAGE047
；
wherein F 11 Mel-frequency cepstral coefficients representing a 1 st frame of the 1 st audio signal sample; f N1 Mel-frequency cepstral coefficients representing an nth frame of the 1 st audio signal sample; f M1 Merr-frequency cepstrum coefficient, F, representing the 1 st frame of the Mth audio signal sample MN The mel-frequency cepstral coefficients of the nth frame representing the mth audio signal sample.
Reconstructing the mel-frequency cepstrum coefficient characteristic vector through an encoder and a decoder according to the mel-frequency cepstrum coefficient characteristics, wherein the method specifically comprises the following steps:
encoder E will input feature vectors
Figure 150034DEST_PATH_IMAGE100
I.e. conversion of the feature vector of the mel-frequency cepstral coefficients of the acquired audio signal samples into a latent feature vector
Figure 93719DEST_PATH_IMAGE049
Namely:
Figure 387297DEST_PATH_IMAGE050
；
wherein
Figure 850770DEST_PATH_IMAGE111
Is a parameter of the encoder;
decoder D will be latent feature vector
Figure 571602DEST_PATH_IMAGE049
Reconstructing into input feature vectors
Figure 737004DEST_PATH_IMAGE101
Namely:
Figure 834273DEST_PATH_IMAGE112
；
wherein
Figure 401520DEST_PATH_IMAGE113
Is a parameter of the decoder;
in the above two formulas:
Figure 41056DEST_PATH_IMAGE114
subscript ofiIndicates that it is currently the secondiA feature vector;sis the total number of feature vectors.
Comparing the reconstruction result with an abnormal score threshold to determine whether the machine has a fault, the method comprises the following specific steps:
adjusting parameters of the encoder and decoder to minimize an error between the reconstructed data and the input data, the reconstruction error function being:
Figure 693754DEST_PATH_IMAGE115
；
Figure 594714DEST_PATH_IMAGE116
is an error function;
Figure 750889DEST_PATH_IMAGE117
representing the input feature vector as
Figure 79102DEST_PATH_IMAGE100
The resulting reconstructed error value.
Taking reconstruction error as an abnormal score of an audio signalSThe manner of determining whether a machine has a fault is as follows:
Figure 969829DEST_PATH_IMAGE118
；
Figure 408900DEST_PATH_IMAGE119
when the input feature vector is X, the obtained reconstruction error value,
Figure 950740DEST_PATH_IMAGE120
is a set anomaly score threshold.
In this embodiment, if there is a fault, the CNN model is used to classify the fault type of the machine, and the structure of the CNN model is shown in fig. 3 and includes:
the method comprises the following steps of taking MFCC features (namely Mel frequency cepstrum coefficient feature vectors) of audio signals when the audio signals are judged to be in machine faults as input of a CNN model, outputting probability results that the audio signals are known fault types through a softmax function, and finally analyzing a probability array to obtain the types of the audio signals, wherein the process is as follows:
taking the mel-frequency cepstrum coefficient feature vector of the audio signal sample determined as the machine with a fault as the input of the CNN model, wherein the result output by the softmax layer of the convolutional neural network is a classification probability matrix, which needs to be converted into a classification result, and the audio signal is output as a probability result of a known fault type through the softmax function;
for one sample X, the fault classification result output through the softmax layer is assumed to be, for one audio signal sample X, and the machine fault type result output through the softmax layer is assumed to be:
Figure 184275DEST_PATH_IMAGE121
；
wherein,
Figure 811566DEST_PATH_IMAGE122
the type of machine fault output for the single node of softmax iskThe probability of (a) of (b) being,Krepresenting the number of known fault types, the firstK+1 fault types represent other unknown types of faults and satisfy
Figure 788749DEST_PATH_IMAGE123
；
The type of the machine fault with the highest output probability is the final determined result.
The invention considers the unsupervised learning based on the self-encoder and the supervised learning of the CNN model, solves the problem that a large number of abnormal audio signal samples are needed, and the self-encoder has simpler structure and is easy to train; the possibility of machine abnormality is measured by constructing a reconstruction error function, so that whether the machine has a fault or not can be effectively judged; by establishing a power personnel scheduling problem for maximizing the average repair rate of machine faults and utilizing the Hungarian algorithm, the optimal power personnel scheduling strategy can be finally obtained.
Example 3
Correspondingly to the intelligent scheduling method for power personnel provided by the above embodiment, the embodiment provides an intelligent scheduling system for power personnel, including: the system comprises a fault judgment module, a fault type judgment module and a scheduling scheme solving module;
the fault judgment module is used for acquiring an audio signal sample when the machine works and determining whether the machine has a fault according to the audio signal sample;
the fault type judging module is used for determining the fault type of the machine according to the audio signal sample if the machine is judged to have a fault;
the scheduling scheme solving module is used for constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the failure repair success times of the electric power personnel, the repair success rate and the machine failure type; and solving the intelligent scheduling problem to obtain an intelligent scheduling scheme.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (7)

1. The intelligent scheduling method for the power personnel is characterized by comprising the following steps:
acquiring an audio signal sample when the machine works, and determining whether the machine has a fault according to the audio signal sample;
if the machine is judged to have a fault, determining the fault type of the machine according to the audio signal sample;
constructing an intelligent scheduling problem according to the number of dispatchable electric power personnel, the fault repair success times of the electric power personnel, the repair success rate and the machine fault type;
solving the intelligent scheduling problem to obtain an intelligent scheduling scheme;
constructing an intelligent scheduling problem, comprising: determining the number of dispatchable electric power personnel, and comparing the number of dispatchable electric power personnel with the number of audio signal samples with faults;
if the number of dispatchable electric power personnel is less than or equal to the number of audio signal samples with faults, solving the intelligent dispatching problem of the first electric power personnel;
electric staff number recording assuming schedulableLEstablishing maintenance files of each power personnel according to historical maintenance records of the power personnelCounter, electric power personnellMaintenance profile of = { machine fault typekElectric power personnellSuccessfully repairing a failure typekNumber of times of
Figure 747577DEST_PATH_IMAGE001
Electric power personnellRepairing failure typeskSuccess rate of
Figure 375611DEST_PATH_IMAGE002
，
Figure 547967DEST_PATH_IMAGE003
｝，KRepresenting the number of known fault types, the first K+1 fault type represents other unknown types of faults;
suppose that the current time is commonMA failed audio signal sample, each sample
Figure 437425DEST_PATH_IMAGE004
,m=1,2,…,MIs expressed as a fault classification result of (a),
Figure 378837DEST_PATH_IMAGE005
；
wherein
Figure 944816DEST_PATH_IMAGE006
Is shown asmThe type of machine fault in the audio signal sample isK+Failure type of 1 typekThe probability of (d);
calculating the importance of each audio signal sample with faults
Figure 604467DEST_PATH_IMAGE007
Wherein
Figure 297617DEST_PATH_IMAGE008
Representing the type of faultkThe priority of (2);
according to importance
Figure 93535DEST_PATH_IMAGE009
Size, before selection from large to smallLThe audio signal samples with faults are stored and the selected samples are indexed in the fault audio signal sample set
Figure 597459DEST_PATH_IMAGE010
Performing the following steps;
the first power personnel intelligent scheduling problem is expressed as follows:
Figure 213249DEST_PATH_IMAGE011
；
wherein,
Figure 710089DEST_PATH_IMAGE012
indicating electric personnellScheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine failure of an audio signal sample, then
Figure 360513DEST_PATH_IMAGE014
Otherwise
Figure 550186DEST_PATH_IMAGE016
；
Figure 168118DEST_PATH_IMAGE018
For personnel of electric power
Figure 203070DEST_PATH_IMAGE019
Successfully repairing a failure typekThe number of times of the above-mentioned operations,
Figure 708001DEST_PATH_IMAGE020
for electric power personnel
Figure 68575DEST_PATH_IMAGE019
Repairing failure typeskThe success rate of the process is increased,
Figure 236837DEST_PATH_IMAGE021
indicating electric personnel
Figure 75480DEST_PATH_IMAGE019
Scheduling policy of, electric power personnel
Figure 700497DEST_PATH_IMAGE019
The scheduling policy of (a) is expressed as: if the power personnel
Figure 966393DEST_PATH_IMAGE019
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 309650DEST_PATH_IMAGE023
Otherwise
Figure 935672DEST_PATH_IMAGE025
；
If the number of dispatchable power personnel is larger than the number of audio signal samples with faults, solving a second power personnel intelligent dispatching problem, and finally obtaining a power personnel intelligent dispatching scheme;
the second power personnel intelligent scheduling problem is expressed as follows:
Figure 680774DEST_PATH_IMAGE026
；
wherein,
Figure 117571DEST_PATH_IMAGE027
indicating electric personnellScheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 682545DEST_PATH_IMAGE028
Otherwise
Figure 613723DEST_PATH_IMAGE029
；LThe number of the electric power personnel can be dispatched,
Figure 478911DEST_PATH_IMAGE030
for electric power personnellSuccessfully repairing failure typeskThe number of times of the operation of the motor,
Figure 86610DEST_PATH_IMAGE031
for electric power personnellRepairing failure typeskThe success rate of the process is increased,
Figure 138879DEST_PATH_IMAGE032
，Krepresenting the number of known fault types, the firstK+The 1 fault type represents the other unknown type of fault,
Figure 123016DEST_PATH_IMAGE033
for electric power personnel
Figure 826399DEST_PATH_IMAGE034
Successfully repairing the failure typekThe number of times of the operation of the motor,
Figure 870578DEST_PATH_IMAGE035
for electric power personnel
Figure 878985DEST_PATH_IMAGE034
Repairing failure typeskThe success rate of the process is increased,
Figure 666813DEST_PATH_IMAGE036
indicating electric personnel
Figure 975434DEST_PATH_IMAGE034
Scheduling policy of, electric power personnel
Figure 938318DEST_PATH_IMAGE034
The scheduling policy of (a) is expressed as: if the power personnel
Figure 965180DEST_PATH_IMAGE034
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 25539DEST_PATH_IMAGE037
Otherwise, otherwise
Figure 719826DEST_PATH_IMAGE038
，
Figure 840229DEST_PATH_IMAGE039
Is shown asmThe type of machine fault in the audio signal sample isKProbability of a certain fault type of +1 types,Mtotal number of audio signal samples for which a fault exists;
and solving the first power personnel intelligent scheduling problem and the second power personnel intelligent scheduling problem by adopting a Hungarian algorithm.
2. The intelligent dispatching method for electric power personnel as claimed in claim 1, wherein the step of determining whether the machine has a fault according to the audio signal samples comprises the following steps:
extracting the feature vector of the Mel frequency cepstrum coefficient of the audio signal sample when the machine works, and reconstructing the feature vector of the Mel frequency cepstrum coefficient through an encoder and a decoder;
and comparing the reconstruction result with an abnormal score threshold value to determine whether the machine has a fault.
3. The intelligent electric power personnel scheduling method of claim 2, wherein the extraction of mel-frequency cepstrum coefficient feature vectors of audio signal samples during the operation of the machine comprises the following specific steps:
converting the audio signal sample frequency into a mel frequency;
the audio signal samples are pre-emphasized by a high pass filter, such that the audio signal samples remain in the entire band from low frequencies to high frequencies, the high pass filter being:
Figure 603654DEST_PATH_IMAGE040
；
wherein,ais a pre-emphasis coefficient;
Figure 467705DEST_PATH_IMAGE041
a system function representing a high pass filter;
windowing each section of single-frame signal, dividing the audio signal sample after pre-emphasis into a plurality of sections of single-frame signals, wherein each section of single-frame signal corresponds to a frequency spectrum;
the windowing operation is as follows:
Figure 750919DEST_PATH_IMAGE042
；
wherein,
Figure 42223DEST_PATH_IMAGE043
in order to be a function of the windowing,Nin order to make the frame length longer,nis the frame number;
calculating the relation between the frequency and the amplitude by using short-time fast Fourier transform; the short-time fast fourier transform formula is:
Figure 528830DEST_PATH_IMAGE044
；
wherein,x(n) Is a firstnThe amplitude of the signal of the frame,E(n) Is the transformed energy signal;
discrete cosine transform is carried out on the audio signal sample to obtain a Mel frequency cepstrum coefficient, and the formula is as follows:
Figure 196572DEST_PATH_IMAGE045
；
Figure 599871DEST_PATH_IMAGE046
；
wherein,f(n) Representing samples of an audio signalnThe signal of the frame in the time domain,F(n) Is the coefficient after the cosine transform and,C(n) Is an audio signal samplenA compensation coefficient for the frame;
finally, the feature vector of the low-order Mel frequency cepstrum coefficient describing the audio data is obtainedMFCC，
The data form is as follows:
Figure 62077DEST_PATH_IMAGE047
；
wherein F 11 Mel-frequency cepstral coefficients representing a 1 st frame of the 1 st audio signal sample; f N1 Mel-frequency cepstral coefficients representing an nth frame of the 1 st audio signal sample; f M1 Merr-frequency cepstrum coefficient, F, representing the 1 st frame of the Mth audio signal sample MN The mel-frequency cepstral coefficients of the nth frame representing the mth audio signal sample.
4. The intelligent electric power personnel scheduling method of claim 2 wherein reconstructing the mel-frequency cepstrum coefficient feature vector by the encoder and decoder comprises:
encoder E input feature vector
Figure 285248DEST_PATH_IMAGE048
Converting the feature vector of the Mel frequency cepstrum coefficient of the obtained audio signal sample into potential feature vector
Figure 271527DEST_PATH_IMAGE049
Expressed as:
Figure 263754DEST_PATH_IMAGE050
；
wherein
Figure 162440DEST_PATH_IMAGE051
Is a parameter of the encoder;
decoder D will be latent feature vector
Figure 872907DEST_PATH_IMAGE052
Reconstructing into input feature vectors
Figure 882451DEST_PATH_IMAGE053
Expressed as:
Figure 482846DEST_PATH_IMAGE054
；
wherein
Figure 552434DEST_PATH_IMAGE055
Is a parameter of the decoder;
Figure 750197DEST_PATH_IMAGE056
subscriptiIndicates that it is currently the firstiA feature vector;sthe total number of feature vectors.
5. The intelligent dispatching method for the electric power personnel as claimed in claim 4, wherein the reconstruction result is compared with the abnormal score threshold value to determine whether the machine has a fault, and the specific steps comprise:
adjusting parameters of the encoder and decoder to minimize an error between the reconstructed data and the input data, the reconstruction error function being:
Figure 563432DEST_PATH_IMAGE057
；
Figure 530251DEST_PATH_IMAGE058
is an error function;
Figure 754428DEST_PATH_IMAGE059
representing the input feature vector as
Figure 173908DEST_PATH_IMAGE060
Obtaining a reconstruction error value;
taking reconstruction error as an abnormal score of an audio signalSThe manner of determining whether a machine has a fault is as follows:
Figure 790834DEST_PATH_IMAGE061
；
Figure 612159DEST_PATH_IMAGE062
when the input feature vector is X, the obtained reconstruction error value,
Figure 39861DEST_PATH_IMAGE063
is a set anomaly score threshold.
6. The intelligent scheduling method for power personnel according to claim 2, wherein if it is determined that the machine has a fault, classifying by using a CNN model to obtain a fault type of the machine comprises:
taking the Mel frequency cepstrum coefficient feature vector of the audio signal sample judged to have the fault on the machine as the input of the CNN model, and outputting the probability result that the audio signal is of the known fault type through the softmax function; for one audio signal sample X, assume that the machine fault type result output via the softmax layer is:
Figure 946637DEST_PATH_IMAGE064
；
wherein,
Figure 101675DEST_PATH_IMAGE065
the type of machine fault output for the single node of softmax iskThe probability of (a) of (b) being,Krepresenting the number of known fault types, the firstK+1 fault types represent other unknown types of faults and satisfy
Figure 777507DEST_PATH_IMAGE066
；
The type of the machine fault with the highest output probability is the final determined result.
7. Electric power personnel intelligent dispatching system, its characterized in that includes: the system comprises a fault judgment module, a fault type judgment module and a scheduling scheme solving module;
the fault judgment module is used for acquiring an audio signal sample when the machine works and determining whether the machine has a fault according to the audio signal sample;
the fault type judging module is used for determining the fault type of the machine according to the audio signal sample if the machine is judged to have a fault;
the scheduling scheme solving module is used for constructing an intelligent scheduling problem according to the number of schedulable electric personnel, the failure repair success times of the electric personnel, the repair success rate and the machine failure type; solving the intelligent scheduling problem to obtain an intelligent scheduling scheme;
determining the number of dispatchable electric power personnel, and comparing the number of dispatchable electric power personnel with the number of audio signal samples with faults;
if the number of dispatchable electric power personnel is less than or equal to the number of audio signal samples with faults, solving the intelligent dispatching problem of the first electric power personnel;
electric staff number recording assuming schedulableLAccording to the historical maintenance records of the electric power personnel, a maintenance file of each electric power personnel is established, and the electric power personnellOfRepair file = { machine fault typekElectric power personnellSuccessfully repairing a failure typekNumber of times of
Figure 609065DEST_PATH_IMAGE001
Electric power personnellRepairing failure typeskSuccess rate of
Figure 268717DEST_PATH_IMAGE002
，
Figure 961866DEST_PATH_IMAGE003
｝，KRepresenting the number of known fault types, the first K+1 fault type represents other unknown types of faults;
suppose that the current time is commonMA failed audio signal sample, each sample
Figure 23363DEST_PATH_IMAGE067
,m=1,2,…,MIs expressed as
Figure 510976DEST_PATH_IMAGE005
Wherein
Figure 140148DEST_PATH_IMAGE006
Is shown asmThe type of machine fault in the audio signal sample isK+Failure type of 1 typekThe probability of (d);
calculating the importance of each audio signal sample with faults
Figure 902567DEST_PATH_IMAGE007
Wherein
Figure 287412DEST_PATH_IMAGE008
Representing the type of faultkThe priority of (2);
according to importance
Figure 477085DEST_PATH_IMAGE009
Size, before selection from large to smallLThe audio signal samples with faults are stored and the selected samples are indexed in the fault audio signal sample set
Figure 580170DEST_PATH_IMAGE010
Performing the following steps;
the first power personnel intelligent scheduling problem is expressed as follows:
Figure 129969DEST_PATH_IMAGE068
；
wherein,
Figure 900479DEST_PATH_IMAGE069
indicating electric personnellScheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine failure of an audio signal sample, then
Figure 995474DEST_PATH_IMAGE070
Otherwise
Figure 851435DEST_PATH_IMAGE071
；
Figure 690078DEST_PATH_IMAGE017
For electric power personnel
Figure 65826DEST_PATH_IMAGE019
Successfully repairing a failure typekThe number of times of the operation of the motor,
Figure 331723DEST_PATH_IMAGE072
for electric power personnel
Figure 674979DEST_PATH_IMAGE019
Repairing failure typeskThe success rate of the process is increased,
Figure 51734DEST_PATH_IMAGE021
indicating electric personnel
Figure 780524DEST_PATH_IMAGE019
Scheduling policy of, electric power personnel
Figure 482901DEST_PATH_IMAGE019
The scheduling policy of (a) is expressed as: if the power personnel
Figure 47875DEST_PATH_IMAGE019
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 228320DEST_PATH_IMAGE073
Otherwise, otherwise
Figure 38714DEST_PATH_IMAGE074
；
If the number of dispatchable power personnel is larger than the number of audio signal samples with faults, solving a second power personnel intelligent dispatching problem, and finally obtaining a power personnel intelligent dispatching scheme;
the second power personnel intelligent scheduling problem is expressed as follows:
Figure 380834DEST_PATH_IMAGE026
；
wherein,
Figure 698682DEST_PATH_IMAGE027
indicating electric personnellScheduling policy of, electric power personnellThe scheduling policy of (a) is expressed as: if the power personnellIs scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 682819DEST_PATH_IMAGE028
Otherwise
Figure 136934DEST_PATH_IMAGE029
；LThe number of the dispatchable electric power personnel is,
Figure 164802DEST_PATH_IMAGE030
for electric power personnellSuccessfully repairing a failure typekThe number of times of the above-mentioned operations,
Figure 704367DEST_PATH_IMAGE031
for electric power personnellRepairing failure typeskThe success rate of the process is increased,
Figure 226616DEST_PATH_IMAGE032
，Krepresenting the number of known fault types, the firstK+The 1 fault type represents the other unknown type of fault,
Figure 800816DEST_PATH_IMAGE033
for electric power personnel
Figure 501050DEST_PATH_IMAGE034
Successfully repairing the failure typekThe number of times of the operation of the motor,
Figure 527912DEST_PATH_IMAGE035
for electric power personnel
Figure 853851DEST_PATH_IMAGE034
Repairing failure typeskThe success rate of the process is increased,
Figure 282559DEST_PATH_IMAGE036
indicating electric personnel
Figure 668541DEST_PATH_IMAGE034
Scheduling policy of, electric power personnel
Figure 166387DEST_PATH_IMAGE034
Is scheduled byThe strategy is represented as: if the power personnel
Figure 296017DEST_PATH_IMAGE034
Is scheduled for maintenancemA machine fault in a sample of the audio signal, then
Figure 579231DEST_PATH_IMAGE037
Otherwise, otherwise
Figure 870535DEST_PATH_IMAGE038
，
Figure 606410DEST_PATH_IMAGE039
Denotes the firstmThe type of machine fault in the audio signal sample isKProbability of one of +1 types of failure,Mthe total number of samples of the audio signal for which a fault exists.
CN202210919919.5A 2022-08-02 2022-08-02 Intelligent scheduling method and system for power personnel Active CN114997749B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210919919.5A CN114997749B (en) 2022-08-02 2022-08-02 Intelligent scheduling method and system for power personnel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210919919.5A CN114997749B (en) 2022-08-02 2022-08-02 Intelligent scheduling method and system for power personnel

Publications (2)

Publication Number Publication Date
CN114997749A CN114997749A (en) 2022-09-02
CN114997749B true CN114997749B (en) 2022-11-11

Family

ID=83021790

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210919919.5A Active CN114997749B (en) 2022-08-02 2022-08-02 Intelligent scheduling method and system for power personnel

Country Status (1)

Country Link
CN (1) CN114997749B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115511397B (en) * 2022-11-23 2023-04-07 广东华居科技有限公司 Intelligent work order data dispatching method and system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110689258A (en) * 2019-09-25 2020-01-14 重庆戴普思科技有限公司 Vehicle maintenance task scheduling method and system
CN111325095B (en) * 2020-01-19 2024-01-30 西安科技大学 Intelligent detection method and system for equipment health state based on acoustic wave signals
CN112258065A (en) * 2020-10-29 2021-01-22 上海电气集团股份有限公司 Method, device and equipment for determining maintenance and dispatching sequence

Also Published As

Publication number Publication date
CN114997749A (en) 2022-09-02

Similar Documents

Publication Publication Date Title
Principi et al. Unsupervised electric motor fault detection by using deep autoencoders
CN111914873B (en) Two-stage cloud server unsupervised anomaly prediction method
CN111259921B (en) Transformer sound abnormality detection method based on improved wavelet packet and deep learning
CN106662072B (en) Wind-driven generator method for monitoring state and system
CN112885372B (en) Intelligent diagnosis method, system, terminal and medium for power equipment fault sound
CN110046562B (en) Health monitoring method and device for wind power system
CN107220469B (en) Method and system for estimating state of fan
CN112660745B (en) Intelligent diagnosis method and system for carrier roller fault and readable storage medium
CN111695209A (en) Rotary machine small sample health assessment method driven by meta-depth learning
CN112504673B (en) Carrier roller fault diagnosis method, system and storage medium based on machine learning
Hussain et al. Vibration analysis and time series prediction for wind turbine gearbox prognostics
CN114997749B (en) Intelligent scheduling method and system for power personnel
CN115563563A (en) Fault diagnosis method and device based on transformer oil chromatographic analysis
CN114186379A (en) Transformer state evaluation method based on echo network and deep residual error neural network
CN111488935A (en) Coal mill fault diagnosis method based on neural network unified modeling
CN116738204A (en) Power load data anomaly detection method based on generation of countermeasure transformers
Jarwar et al. NEAT: A resilient deep representational learning for fault detection using acoustic signals in IIoT environment
CN113435228A (en) Motor bearing service life prediction and analysis method based on vibration signal modeling
CN117217730A (en) Power equipment fault identification method, device, equipment, medium and product
CN110927497A (en) Point switch fault detection method and device
CN117828531A (en) Bearing fault diagnosis method based on multi-sensor multi-scale feature fusion
CN113392888A (en) Rail transit traction motor fault identification method, storage medium and electronic equipment
CN113270110A (en) ZPW-2000A track circuit transmitter and receiver fault diagnosis method
CN115406630A (en) Method for detecting faults of wind driven generator blades through passive acoustic signals based on machine learning
CN115982621A (en) Rotary machine residual service life prediction method based on time convolution network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant