CN113674447A - System and method for detecting voiceprint fault of industrial equipment - Google Patents
System and method for detecting voiceprint fault of industrial equipment Download PDFInfo
- Publication number
- CN113674447A CN113674447A CN202110778974.2A CN202110778974A CN113674447A CN 113674447 A CN113674447 A CN 113674447A CN 202110778974 A CN202110778974 A CN 202110778974A CN 113674447 A CN113674447 A CN 113674447A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- information
- path
- node
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 107
- 238000007689 inspection Methods 0.000 claims abstract description 90
- 230000007246 mechanism Effects 0.000 claims abstract description 10
- 230000002093 peripheral effect Effects 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000005856 abnormality Effects 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 3
- 210000003128 head Anatomy 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000002555 auscultation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- MKXZASYAUGDDCJ-NJAFHUGGSA-N dextromethorphan Chemical compound C([C@@H]12)CCC[C@]11CCN(C)[C@H]2CC2=CC=C(OC)C=C21 MKXZASYAUGDDCJ-NJAFHUGGSA-N 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- 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
- G10L17/00—Speaker identification or verification techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a voiceprint fault detection system and method for industrial equipment, and relates to the field of industrial equipment inspection and the technical field of information acquisition. In the invention: and a plurality of path nodes matched with the positions of key mechanisms in the machine are set in the RFID path information. And the normal voiceprint module is used for presetting normal voiceprint information on the RFID path. And the voiceprint comparison module is used for acquiring the real-time voiceprint information detected by the voiceprint detection module and comparing the real-time voiceprint information with the normal voiceprint information. And the node time domain detection module outputs a node time domain detection signal when the routing inspection equipment moves to a path node in the RFID path. According to the invention, a manpower detection mode of a common inspection system is scientific and technical, peripheral paths and nodal time domain sounds of the machine are collected and monitored, a fault rate analysis model is built, the sound fault rate of the operation of the machine is efficiently and accurately analyzed and judged, and technicians can find abnormality in time and carry out subsequent targeted maintenance plans conveniently.
Description
Technical Field
The invention belongs to the field of industrial equipment inspection and the technical field of information acquisition, and particularly relates to a system and a method for detecting a voiceprint fault of industrial equipment.
Background
In the current field of industrial equipment inspection, the inspection function of machine equipment is based on common inspection, and whether the equipment runs in an abnormal state or not is confirmed by observing with eyes or hearing by ears of an inspector in many times. The basic experience inspection mode has the great disadvantage that not every inspection personnel has enough experience reserve to realize the observation and detection of inspection work, in addition, the problems can be found only when the inspection personnel is embodied outside the equipment through visual observation and ear listening modes so as to see the equipment to have major soft faults, and when the equipment has slight problems in operation, human eyes and hearing can not be identified, so that a more scientific and effective diagnosis system is more suitable for the current industrial equipment inspection, the faults of the equipment are eliminated in the initial stage from the perspective of higher technology, and the occurrence of major accidents is avoided.
In addition, some existing detection devices, such as various sound sensors, are installed on a specialized detection device, and can already detect the operation sound of the device, but technicians place fault detection devices on the machine devices at will in the actual sound fault detection process of the machine devices, and do not consider that the structural features of various positions in the machine devices are different, and the structural complexity, reliability and the like during operation are greatly different. The existing sound fault detection mode of the machine equipment with one cutting tool obviously does not accord with the efficient and accurate sound fault detection principle.
Disclosure of Invention
The invention aims to provide a voiceprint fault detection system and a voiceprint fault detection method for industrial equipment.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a voiceprint fault detection system for industrial equipment.
And (3) routing inspection equipment configuration: and the RFID path sensing module senses path information on the RFID path bars in real time. The voiceprint detection module acquires voiceprint information in real time;
the main controller is internally provided with: and the path storage module is used for storing the peripheral RFID path information of the corresponding machine, and a plurality of path nodes matched with the positions of key mechanisms in the machine are set in the RFID path information. And the normal voiceprint module is preset with normal voiceprint information on the peripheral RFID paths of the machines when the machines operate. And the voiceprint comparison module is used for acquiring the real-time voiceprint information detected by the voiceprint detection module, comparing the real-time voiceprint information with the normal voiceprint information and outputting a voiceprint state reference value. And when the routing inspection equipment moves to a path node in the RFID path, the node time domain detection module outputs a node time domain detection signal and controls the routing inspection equipment to perform stagnation voiceprint detection of a node reference time length preset by the system at the current path node position.
As an optimal technical scheme of the voiceprint fault detection system of the industrial equipment, the voiceprint fault detection system comprises the following steps: the inspection equipment is driven by a handheld or automatic moving device, and the automatic moving device comprises a walking mechanism for walking and a lifting mechanism for adjusting the real-time height of the inspection equipment; and a path storage module in the detection system transmits the real-time RFID path information to a mobile driving device of the inspection equipment through a communication network.
As an optimal technical scheme of the voiceprint fault detection system of the industrial equipment, the voiceprint fault detection system comprises the following steps: the handheld inspection equipment is provided with a sound alarm, when the handheld inspection equipment approaches a path node in an RFID path, the detection system drives the sound alarm to act, and the sound alarm gives a 'parking' voice; firstly, after the handheld inspection equipment stays at the current path node for the reference time length of the node, the sound alarm is closed; and secondly, when the handheld inspection equipment does not stay at the current path node for the reference time of the node, the sound alarm gives out return voice.
As an optimal technical scheme of the voiceprint fault detection system of the industrial equipment, the voiceprint fault detection system comprises the following steps: the handheld inspection equipment is provided with a handle and an alignment head for aligning the RFID path bar; the inspection equipment is provided with a wireless communication module for transmitting voiceprint detection information and prompt information.
As an optimal technical scheme of the voiceprint fault detection system of the industrial equipment, the voiceprint fault detection system comprises the following steps: a plurality of voiceprint detection modules are arranged on the patrol inspection equipment, and the voiceprint detection modules are uniformly arranged around the periphery of the RFID path sensing module.
As an optimal technical scheme of the voiceprint fault detection system of the industrial equipment, the voiceprint fault detection system comprises the following steps: the system display platform is used for storing and displaying voiceprint polling information of polling equipment and machine information which is being polled; and the inspection equipment acquires the machine information corresponding to the current RFID path bar, wherein the machine information comprises the current position information of the machine.
The invention relates to a voiceprint fault detection method for industrial equipment, which comprises the following steps:
(1) under the condition that the machine normally operates, a detection system pre-collects voiceprint information on an RFID path and establishes a normal state voiceprint information exclusive information base;
the inspection equipment collects voiceprint information along the RFID path bar of the machine, and the multiple voiceprint information detected by any voiceprint detection module at any position point in the RFID path is set as [ A ] in sequence1，A2...An]；
(2) The detection system analyzes and establishes a voiceprint inspection normal relation of any detection position point of the machine;
wherein,
is [ A ]1，A2...An]Has a mean value of [ A ]1，A2...An]Standard deviation of (d);
(3) the detection system obtains the subsequent voiceprint information detected by the voiceprint detection module, judges the failure probability of the output machine, and sets the voiceprint information detected by the voiceprint detection module as AxJudging the following conditions and outputting the fault probability:
①
outputting a fault probability value as a low risk fault rate;
②
or
Outputting the fault probability value as a medium risk fault rate;
③
or
Outputting a fault probability value as a high risk fault rate;
④
or
And outputting a fault signal of the machine to prompt shutdown maintenance.
As an optimal technical scheme of the method for detecting the voiceprint fault of the industrial equipment, the method comprises the following steps: and when the routing inspection equipment inspects the path nodes, performing time-domain voiceprint detection on the path nodes, performing initial model establishment of a voiceprint inspection normal relation of the total voiceprint information value and the voiceprint information extreme value in unit time in the node reference time length, performing normal parameterization contrast analysis in the subsequent normalizing inspection process, and outputting the time-domain normal risk fault rate of the path nodes.
As an industrial facility of the inventionA preferred technical scheme of the method for detecting the voiceprint failure comprises the following steps: when the time-domain voiceprint at the path node is detected, the reference time length of the node is related to the complexity or reliability of the current machine node; let the complexity or reliability of the current machine node be KxThen the node reference time length P of the current machine nodexThen P is presentx∝Kx[KxTo complexity of]，Px∝Kx -1[KxFor reliability]。
The invention has the following beneficial effects:
1. according to the method, peripheral paths and nodal time domain sounds of the machine are collected and monitored based on the distribution, complexity and reliability of operation components in the machine, a fault rate analysis model is built, the sound fault rate of the operation of the machine is efficiently and accurately analyzed and judged, technicians can find abnormality in time and perform subsequent targeted maintenance plans conveniently, and focus attention and inspection are given to some machines which start to have fault risks.
2. Compared with the existing equipment soft fault inspection and diagnosis system, the invention can scientifically and technically carry out the manpower detection mode of the common inspection system, and more accurately detect and diagnose whether the running equipment has running abnormity through the change of the running voiceprint of the equipment.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic view of a part of the structural configuration of the inspection equipment for performing sound detection on RFID paths on the periphery of a machine in the invention;
FIG. 2 is a logic diagram of some modules of the inspection equipment and the main controller in the invention
FIG. 3 is a schematic diagram of a part of system logic for voiceprint fault detection of the apparatus of the present invention;
in the drawings, the components represented by the respective reference numerals are listed below:
1-an RFID path bar; 2-path node; 3, routing inspection of the handheld equipment; 301-RFID path sensing module; 302-voiceprint detection module; 303-a handle; 304-alignment head.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The patrol device 3 is provided with an RFID path sensing module 301 and a voiceprint detection module 302. The RFID path sensing module 301, the RFID path sensing module 301 senses the path information on the RFID path bar 1 in real time. The voiceprint detection modules 302 are uniformly arranged around the periphery of the RFID path sensing module 301, and the voiceprint detection modules 302 acquire voiceprint information in real time. The voiceprint detection modules 302 on the inspection equipment 3 are provided with a plurality of voiceprint detection modules 302, and the voiceprint detection modules 302 are uniformly arranged around the periphery of the RFID path sensing module 301.
The inspection equipment 3 is driven by a handheld or automatic moving device, and the handheld inspection equipment is provided with a handle 303 and an alignment head 304 for aligning the RFID path strip 1; the automatic moving device comprises a walking mechanism for walking and a lifting mechanism for adjusting the real-time height of the inspection equipment 3.
The inspection equipment 3 is provided with a wireless communication module for transmitting voiceprint detection information and prompt information; and the inspection equipment 3 acquires the machine information corresponding to the current RFID path bar, wherein the machine information comprises the current position information of the machine. And the system display platform is used for storing and displaying the voiceprint polling information of the polling equipment 3 and the machine information which is polling.
Example two
Based on the first embodiment, a path storage module, a normal voiceprint module, a voiceprint comparison module and a node time domain detection module are configured in the main controller.
The route storage module is used for storing the peripheral RFID route information of the corresponding machine, and a plurality of route nodes 2 matched with the positions of key mechanisms in the machine are set in the RFID route information; the path storage module transmits the real-time RFID path information to the mobile driving device of the inspection equipment 3 through a communication network.
The normal voiceprint module is preset with normal voiceprint information sent out on the RFID paths at the periphery of the machine when the machines operate;
the voiceprint comparison module is used for acquiring real-time voiceprint information detected by the voiceprint detection module, comparing the real-time voiceprint information with normal voiceprint information and outputting a voiceprint state reference value;
and when the routing inspection equipment 3 moves to a path node in the RFID path, the node time domain detection module outputs a node time domain detection signal and controls the routing inspection equipment 3 to perform stagnation voiceprint detection of a node reference time length preset by the system at the current path node position.
EXAMPLE III
Based on the first embodiment and the second embodiment, the handheld inspection equipment is provided with the sound alarm, when the handheld inspection equipment approaches a path node in an RFID path, the detection system drives the sound alarm to act, and the sound alarm gives out stop voice.
Firstly, when the handheld inspection equipment continuously stays at a current path node and the staying time reaches a node reference time length, the sound alarm is closed; and secondly, when the handheld inspection equipment does not continuously stay at the node of the current path and the stay time is shorter than the reference time length of the node, the sound alarm gives out return voice.
Example four
The method for detecting the voiceprint fault of the industrial equipment depends on the first embodiment, the second embodiment and the third embodiment, and specifically comprises the following contents:
(1) the detection system performs pre-acquisition under normal operation conditions of the machineAnd establishing a normal state voiceprint information exclusive information base by the voiceprint information on the RFID path. The patrol equipment 3 collects voiceprint information along the RFID path bar 1 of the machine, and sets multiple times of voiceprint information detected by any voiceprint detection module 302 at any position point in the RFID path as [ A ] in sequence1，A2...An]。
(2) In the detection system, the voiceprint inspection normal relation of any detection position point of the machine is analyzed and established, and the specific voiceprint inspection normal relation is as follows:
(3) Through the voiceprint polling normal relationship, the detection system obtains subsequent voiceprint information detected by the voiceprint detection module 302, and judges and outputs the machine fault probability. In the actual inspection process, the voiceprint detection module 302 detects that the voiceprint information is AxThere are the following cases:
①
outputting a fault probability value as a low risk fault rate; ②
Or
Outputting the fault probability value as a medium risk fault rate; ③ of
Or
Output fault summaryThe rate value is a high risk failure rate; fourthly
Or
Outputting a machine fault signal.
In addition, when the routing inspection equipment 3 inspects the path node 2, time-domain voiceprint detection is carried out on the path node 2, an early-stage model establishment of the voiceprint inspection normal relation of the total voiceprint information value and the voiceprint information extreme value in unit time is carried out in the node reference time length, normal parameterization comparative analysis is carried out in the subsequent normalizing inspection process, and the time-domain normal risk fault rate of the path node 2 is output.
EXAMPLE five
Based on the fourth embodiment, when the time-domain voiceprint detection is performed at the path node 2, the node reference duration is related to the complexity or reliability of the current machine node; the complexity or reliability of the current machine node is assumed [ the complexity and reliability of the machine node are generally inversely related, and at the machine node, the internal structure construction component is complex or the operation environment is harsh, so that the reliability is low; otherwise, at the node of the machine, the operation structure assembly is simple, the structure is reasonable, the operation environment is good, and the reliability is highxThen the node reference time length P of the current machine nodex. Wherein KxFor complexity, P is presentx∝Kx；KxFor reliability, there is Px∝Kx -1。
EXAMPLE six
In the system configuration of the present invention, the fault detection system includes: the system comprises inspection equipment 3, a fault detector (voiceprint detection module 302) and a system display platform.
And the fault detector is used for detecting the time domain of the path and the node of the equipment to be inspected, collecting the sound source of the detected equipment, and analyzing and judging the sound.
And the management end is connected with the inspection equipment 3 or the inspection terminal, and is used for receiving and storing the data sent by the inspection equipment 3.
The detection process takes a handheld inspection device as an example:
the handheld inspection equipment is held by hands, and inspection work is carried out according to a specified inspection plan; when the specified equipment inspection position is reached, the handheld inspection equipment is used for carrying out specified voiceprint collection on the equipment to be detected; after collecting related voiceprint information, the handheld inspection equipment compares the collected voiceprint information with the normal voiceprint preset by the handheld inspection equipment in the previous period; so as to analyze the change value of the voiceprint of the equipment by data, and whether the obtained change value is in a specified range or not; and finally obtaining the operation result of the equipment.
The portable industrial equipment fault detection method provided by the embodiment comprehensively improves the detection speed and accuracy of the equipment and the working efficiency of a user, and solves the difficulty in operation detection of the equipment in the past. This equipment only need carry out auscultation formula scanning to the equipment that detects, can collect the sound of the equipment that detects, judges this operation equipment and the sound when normal operation through the sound size and the leading sound to operation equipment and carries out contrastive analysis, reachs the accurate running state of equipment operation.
In the description herein, references to the terms "embodiment" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. An industrial equipment voiceprint fault detection system comprises a machine to be detected, and is characterized in that:
the periphery of the machine is pasted with an RFID path bar (1), and the detection system comprises inspection equipment (3) and a main controller;
the inspection equipment (3) is configured:
the RFID path sensing module (301), the RFID path sensing module (301) senses the path information on the RFID path bar (1) in real time;
the voiceprint detection module (302), the voiceprint detection module (302) obtaining voiceprint information in real time;
the main controller is internally provided with:
the path storage module stores RFID path information of the periphery of the corresponding machine, and a plurality of path nodes (2) matched with the positions of key mechanisms in the machine are set in the RFID path information;
the normal voiceprint module is preset with normal voiceprint information on the peripheral RFID paths of the machines when the machines operate;
the voiceprint comparison module acquires real-time voiceprint information detected by the voiceprint detection module, compares the real-time voiceprint information with normal voiceprint information and outputs a voiceprint state reference value;
when the routing inspection equipment (3) moves to a path node in the RFID path, the node time domain detection module outputs a node time domain detection signal to control the routing inspection equipment (3) to perform stagnation voiceprint detection of a node reference time length preset by the system at the current path node position.
2. The industrial equipment voiceprint failure detection system of claim 1, wherein:
the inspection equipment (3) is driven by a handheld or automatic moving device, and the automatic moving device comprises a walking mechanism for walking and a lifting mechanism for adjusting the real-time height of the inspection equipment (3);
and a path storage module in the detection system transmits the real-time RFID path information to a mobile driving device of the inspection equipment (3) through a communication network.
3. The industrial equipment voiceprint failure detection system of claim 2, wherein:
the handheld inspection equipment is provided with a sound alarm, when the handheld inspection equipment approaches a path node in an RFID path, the detection system drives the sound alarm to act, and the sound alarm gives a 'parking' voice;
firstly, after the handheld inspection equipment stays at the current path node for the reference time length of the node, the sound alarm is closed;
and secondly, when the handheld inspection equipment does not stay at the current path node for the reference time of the node, the sound alarm gives out return voice.
4. The industrial equipment voiceprint failure detection system of claim 2, wherein:
the handheld inspection device is provided with a handle (303) and an alignment head (304) for aligning the RFID path bar (1);
the inspection equipment (3) is provided with a wireless communication module for transmitting voiceprint detection information and prompt information.
5. The industrial equipment voiceprint failure detection system of claim 1, wherein:
voiceprint detection module (302) on equipment (3) of patrolling and examining are equipped with a plurality of, and a plurality of voiceprint detection module (302) are evenly around establishing in RFID route sensing module (301) periphery.
6. The industrial equipment voiceprint failure detection system of claim 1, wherein:
the system comprises a system display platform, a voice print inspection device and a computer, wherein the system display platform is used for storing and displaying voiceprint inspection information of inspection equipment (3) and machine information which is being inspected;
the inspection equipment (3) acquires machine information corresponding to the current RFID path bar (1), and the machine information comprises current position information of the machine.
7. An industrial equipment voiceprint failure detection method, which is characterized in that the industrial equipment voiceprint failure detection system of any one of claims 1 to 6 is adopted, and the method comprises the following steps:
(1) under the condition that the machine normally operates, a detection system pre-collects voiceprint information on an RFID path and establishes a normal state voiceprint information exclusive information base;
the inspection equipment (3) collects voiceprint information along the RFID path bar (1) of the machine, and a plurality of times of voiceprint information detected by any voiceprint detection module (302) at any position point in the RFID path are sequentially set as [ A ]1，A2...An]；
(2) The detection system analyzes and establishes a voiceprint inspection normal relation of any detection position point of the machine;
wherein,
is [ A ]1，A2...An]Has a mean value of [ A ]1，A2...An]Standard deviation of (d);
(3) the detection system obtains subsequent voiceprint information detected by the voiceprint detection module (302), judges the failure probability of the output machine, and sets the voiceprint information detected by the voiceprint detection module (302) as AxJudging the following conditions and outputting the fault probability:
①
outputting a fault probability value as a low risk fault rate;
②
or
Outputting the fault probability value as a medium risk fault rate;
③
or
Outputting a fault probability value as a high risk fault rate;
④
or
Outputting a machine fault signal.
8. The industrial equipment voiceprint failure detection method of claim 7, wherein:
when the routing inspection equipment (3) inspects the route node (2), time-domain voiceprint detection is carried out on the route node (2), an early-stage model of the voiceprint inspection normal relation of the total voiceprint information value and the voiceprint information extreme value in unit time is established in the node reference time length, normal parameterization comparative analysis is carried out in the subsequent normalizing inspection process, and the time-domain normal risk fault rate of the route node (2) is output.
9. The industrial equipment voiceprint failure detection method of claim 8, wherein:
when the time-domain voiceprint detection is carried out at the path node (2), the reference time length of the node is related to the complexity or reliability of the current machine node;
let the complexity or reliability of the current machine node be KxThen the node reference time length P of the current machine nodexThen P is presentx∝Kx[KxTo complexity of]，Px∝Kx -1[KxFor reliability]。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110778974.2A CN113674447A (en) | 2021-07-09 | 2021-07-09 | System and method for detecting voiceprint fault of industrial equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110778974.2A CN113674447A (en) | 2021-07-09 | 2021-07-09 | System and method for detecting voiceprint fault of industrial equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674447A true CN113674447A (en) | 2021-11-19 |
Family
ID=78538817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110778974.2A Pending CN113674447A (en) | 2021-07-09 | 2021-07-09 | System and method for detecting voiceprint fault of industrial equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674447A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104793605A (en) * | 2015-04-10 | 2015-07-22 | 北京金控自动化技术有限公司 | Method for judging equipment faults by means of normal distribution |
| CN109658539A (en) * | 2018-12-11 | 2019-04-19 | 中海油安全技术服务有限公司 | Method for inspecting, device, server and the computer storage medium of chemical industrial park |
| CN109781410A (en) * | 2019-01-22 | 2019-05-21 | 北京君林科技股份有限公司 | A kind of Bearing Fault Detection Method and device of Application on Voiceprint Recognition |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
| CN111783485A (en) * | 2020-05-22 | 2020-10-16 | 北京市地铁运营有限公司运营二分公司 | Train inspection platform, terminal and system |
| CN112033656A (en) * | 2020-08-27 | 2020-12-04 | 杭州电子科技大学 | Mechanical system fault detection method based on broadband spectrum processing |
| CN112099393A (en) * | 2020-08-19 | 2020-12-18 | 张家口卷烟厂有限责任公司 | System and method for monitoring operation and judging abnormality of cigarette machine equipment |
| CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
-
2021
- 2021-07-09 CN CN202110778974.2A patent/CN113674447A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104793605A (en) * | 2015-04-10 | 2015-07-22 | 北京金控自动化技术有限公司 | Method for judging equipment faults by means of normal distribution |
| CN109658539A (en) * | 2018-12-11 | 2019-04-19 | 中海油安全技术服务有限公司 | Method for inspecting, device, server and the computer storage medium of chemical industrial park |
| CN109781410A (en) * | 2019-01-22 | 2019-05-21 | 北京君林科技股份有限公司 | A kind of Bearing Fault Detection Method and device of Application on Voiceprint Recognition |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
| CN111783485A (en) * | 2020-05-22 | 2020-10-16 | 北京市地铁运营有限公司运营二分公司 | Train inspection platform, terminal and system |
| CN112099393A (en) * | 2020-08-19 | 2020-12-18 | 张家口卷烟厂有限责任公司 | System and method for monitoring operation and judging abnormality of cigarette machine equipment |
| CN112033656A (en) * | 2020-08-27 | 2020-12-04 | 杭州电子科技大学 | Mechanical system fault detection method based on broadband spectrum processing |
| CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109001649B (en) | Intelligent power supply diagnosis system and protection method | |
| CN110208022A (en) | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning | |
| US20230162484A1 (en) | Apparatus and method for generating learning data for artificial intelligence model | |
| CN107479540B (en) | Method for diagnosing faults and system | |
| CN109029582A (en) | A kind of Power Transformer Faults on-line detecting system based on many kinds of parameters acquisition | |
| CN104090252B (en) | Comprehensive detecting system and method for cable type fault indicator | |
| CN112859769B (en) | Energy consumption monitoring device in intelligent production equipment and operation method thereof | |
| KR102392951B1 (en) | Equipment failure prediction system having multi-channel sensors for receiving acoustic signals in the ultrasonic band | |
| CN112326583A (en) | Intelligent toxic gas detection system and method based on Internet of things | |
| CN202210709U (en) | Distribution transformer real time monitoring system | |
| CN116824731A (en) | Intelligent inspection method and equipment for thermal power plant | |
| CN110487327A (en) | A kind of condition monitoring system of mechanical equipment electrical system | |
| CN111159487A (en) | Predictive maintenance intelligent system for automobile engine spindle | |
| CN114035555B (en) | PLC controller fault detection system | |
| CN112276946A (en) | Robot application system based on industrial internet platform | |
| CN209805505U (en) | Mobile inspection device for power distribution room | |
| CN113674447A (en) | System and method for detecting voiceprint fault of industrial equipment | |
| CN114326668A (en) | Auxiliary diagnosis and analysis device for automobile vibration noise fault | |
| CN113055085A (en) | Power communication network operation and maintenance device | |
| CN116796261B (en) | Closed switch equipment mechanical characteristic prediction method based on artificial intelligence | |
| CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
| CN111711267A (en) | Intelligent inspection system of gas generator set | |
| CN114049697B (en) | Inspection auxiliary system | |
| CN115815778A (en) | Ultrasonic welding online monitoring system and method based on power and frequency analysis | |
| CN111313966B (en) | Centralized monitoring and early warning equipment based on optical fiber network maintenance |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211119 |
|
| RJ01 | Rejection of invention patent application after publication |