CN110201606B - System, method and device for monitoring top hammer of cubic press - Google Patents
System, method and device for monitoring top hammer of cubic press Download PDFInfo
- Publication number
- CN110201606B CN110201606B CN201910470900.5A CN201910470900A CN110201606B CN 110201606 B CN110201606 B CN 110201606B CN 201910470900 A CN201910470900 A CN 201910470900A CN 110201606 B CN110201606 B CN 110201606B
- Authority
- CN
- China
- Prior art keywords
- cubic press
- top hammer
- time domain
- audio data
- processing unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000005236 sound signal Effects 0.000 claims abstract description 118
- 238000012545 processing Methods 0.000 claims abstract description 77
- 238000004458 analytical method Methods 0.000 claims description 32
- 238000003909 pattern recognition Methods 0.000 claims description 17
- 238000012806 monitoring device Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 7
- 238000007689 inspection Methods 0.000 abstract description 6
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 18
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000004519 manufacturing process Methods 0.000 description 11
- 102100026436 Regulator of MON1-CCZ1 complex Human genes 0.000 description 9
- 101710180672 Regulator of MON1-CCZ1 complex Proteins 0.000 description 9
- 238000000354 decomposition reaction Methods 0.000 description 7
- 238000012216 screening Methods 0.000 description 6
- 230000004807 localization Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 229910003460 diamond Inorganic materials 0.000 description 2
- 239000010432 diamond Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- RVCKCEDKBVEEHL-UHFFFAOYSA-N 2,3,4,5,6-pentachlorobenzyl alcohol Chemical compound OCC1=C(Cl)C(Cl)=C(Cl)C(Cl)=C1Cl RVCKCEDKBVEEHL-UHFFFAOYSA-N 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- JPNWDVUTVSTKMV-UHFFFAOYSA-N cobalt tungsten Chemical compound [Co].[W] JPNWDVUTVSTKMV-UHFFFAOYSA-N 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
- B01J3/00—Processes of utilising sub-atmospheric or super-atmospheric pressure to effect chemical or physical change of matter; Apparatus therefor
- B01J3/06—Processes using ultra-high pressure, e.g. for the formation of diamonds; Apparatus therefor, e.g. moulds or dies
Landscapes
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a monitoring system, a method and a device for a top hammer of a cubic press, wherein the system comprises the following components: the device comprises a data processing unit, an audio signal processing unit and a microphone array arranged on a cubic press; the microphone array is connected with the input end of the audio signal processing unit, and the data processing unit is connected with the output end of the audio signal processing unit; the microphone array is used for acquiring sound signals emitted by a top hammer of the cubic press in real time; the audio signal processing unit is used for processing the sound signal and sending the processed sound signal to the data processing unit; the data processing unit is used for analyzing the state of the anvil according to the processed sound signal. The method can monitor whether the anvil is broken or not in time and accurately position the broken anvil by utilizing the characteristics and advantages of the microphone array and the existing processing means aiming at the signals of the microphone array, thereby not only solving the defects of the traditional manual inspection, but also overcoming the problems of time and labor waste and large environmental interference caused by other existing monitoring methods.
Description
Technical Field
The invention relates to the field of engineering equipment monitoring, in particular to a top hammer monitoring system, method and device of a cubic press.
Background
A hinged cubic apparatus ultra-high pressure and high temperature diamond synthetic press (cubic apparatus press for short) is mainly composed of a main machine base, six identical working cylinders and pistons thereof to establish an ultra-high pressure key component. As shown in fig. 1-2, each piston end is provided with a large cushion block 10, a small cushion block 20 and a top hammer 30, and the components in six directions are basically the same and are not described herein. Among them, the anvil 30 is a key part of the cubic press for generating ultra-high pressure, and is generally made of tungsten-cobalt hard alloy. The top hammer breakage is a common production accident in the synthetic process of the artificial diamond, if the replacement is not found in time and the production is continued, not only can the domino effect be caused, but also other top hammers are broken in succession due to uneven stress, the later maintenance cost of the equipment is increased, and the hammer collapse or even blasting accidents can be caused, so that the personnel are injured. Therefore, the real-time monitoring of the working state of the cubic press and the position judgment of the broken anvil are researched, real-time online alarming, shutdown and other timely treatments are realized, and huge economic benefits and social benefits are brought to enterprises.
In the prior art, there are three main methods for monitoring the break of the anvil of the cubic press:
1) manual on-site inspection: such as manually striking the hammer or empirically catching the "snap" sound generated by the hammer breaking during operation of the press by the human ear.
2) Monitoring by using an acoustic emission sensor: for example, the acoustic emission sensor is installed in the inner cavity of a hollow signal transmission tube to capture the stress wave signal generated by the top hammer due to the fracture, and the front end opening of the signal transmission tube must be opposite to the center of the top hammer of the cubic press.
3) Monitoring by using ultrasonic waves: for example, a cavity is arranged on each cushion block of six top hammers of a cubic press, an ultrasonic transducer is arranged in the cavity, and a monitored fracture signal is converted into an electric signal for processing.
However, the prior art has the disadvantages that:
1) the manual inspection method is relatively backward in means and more subjectively dependent, the accuracy and timeliness are difficult to guarantee, the labor cost is greatly consumed, and the production efficiency is influenced.
2) The acoustic emission sensor method has strict centering requirements, the high-standard installation process causes the mode to be time-consuming and labor-consuming in actual operation, and particularly, once centering deviation occurs, the monitoring result is basically invalid.
3) In the ultrasonic monitoring process, the signal attenuation is serious, the sensitivity is low, the testing range is small, and the ultrasonic monitoring is easily influenced by the environment, for example, the vibration of the equipment can cause large errors in the ultrasonic monitoring; in particular, when a fault anvil is accurately positioned, measurement needs to be performed point by point, and the measurement is time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to provide a top hammer monitoring system, a top hammer monitoring method and a top hammer monitoring device of a cubic press, which are used for overcoming the defects and making up the defects.
The technical scheme adopted by the invention is as follows:
a cubic press top hammer monitoring system comprising: the device comprises a data processing unit, an audio signal processing unit and a microphone array arranged on a cubic press;
the microphone array is connected with the input end of the audio signal processing unit, and the data processing unit is connected with the output end of the audio signal processing unit;
the microphone array is used for acquiring sound signals emitted by a top hammer of a cubic press in real time;
the audio signal processing unit is used for processing the sound signal and sending the processed sound signal to the data processing unit;
the data processing unit is used for analyzing the state of the anvil according to the processed sound signal.
Optionally, the microphone units in the microphone array are mounted on a large pad of a piston of a cubic press.
Optionally, the number of the microphone units is three, and the three microphone units are respectively mounted on the large cushion blocks of the three movable cylinders or the three fixed cylinders.
Optionally, the three microphone units have equal distances from each other to form a regular triangular microphone array.
Optionally, the system further comprises: the device comprises a warning unit and a main control unit for controlling the operation of the cubic press;
the main control unit is connected with the data processing unit and used for controlling the stop of the cubic press and/or triggering the warning unit to output an alarm signal according to the state of the anvil sent by the data processing unit.
A monitoring method for a top hammer of a cubic press comprises the following steps:
acquiring sound signals collected by a microphone array in a working state of the cubic press in real time;
performing preliminary analysis on the sound signal to identify suspected target audio data;
and determining real top hammer fracture audio data from the suspected target audio data based on a preset pattern recognition strategy.
Optionally, the performing a preliminary analysis on the sound signal, and identifying suspected target audio data includes:
taking the sound signal in a set time period as an analysis unit, and calculating time domain and frequency domain values of the sound signal;
and analyzing whether the sound signal is suspected target audio data or not according to the relation between the time domain and frequency domain calculation results and a preset judgment threshold value.
Alternatively,
the calculating time domain and frequency domain values of the sound signal comprises:
calculating a time domain maximum value and a time domain minimum value of the sound signal in a set time period;
calculating the energy sum in a preset frequency band range of the sound signal in a set time period;
the analyzing whether the sound signal is suspected target audio data according to the relationship between the time domain and frequency domain calculation results and a preset judgment threshold comprises:
and when the time domain maximum value is larger than a preset time domain positive threshold, the time domain minimum value is smaller than a preset time domain negative threshold, and the energy sum is larger than a preset energy threshold, determining that the sound signal in the set time period is suspected target audio data.
Optionally, the determining, based on a preset pattern recognition strategy, real top hammer fracture audio data from the suspected target audio data includes:
extracting multi-dimensional features from each data frame of the suspected target audio data, wherein the multi-dimensional features consist of time domain features and/or frequency domain features;
and determining real top hammer fracture audio data according to the multi-dimensional features and a pre-constructed recognition model.
Optionally, the method further comprises:
sequentially calling one microphone unit of the microphone array as a reference array element;
and positioning the source position of the top hammer fracture audio data by using the reference array element.
A monitoring device for top hammer of cubic press comprises:
the sound acquisition module is used for acquiring sound signals acquired by the microphone array in a working state of the cubic press in real time;
the preliminary analysis module is used for carrying out preliminary analysis on the sound signal and identifying suspected target audio data;
and the pattern recognition module is used for determining real top hammer fracture audio data from the suspected target audio data based on a preset pattern recognition strategy.
Optionally, the preliminary analysis module specifically includes:
the audio analysis unit is used for calculating time domain and frequency domain values of the sound signals by taking the sound signals in a set time period as an analysis unit;
and the suspected data judging unit is used for analyzing whether the sound signal is suspected target audio data according to the relationship between the time domain and frequency domain calculation results and a preset judgment threshold value.
Alternatively,
the audio analysis unit specifically includes:
the time domain value calculating component is used for calculating the time domain maximum value and the time domain minimum value of the sound signal in a set time period;
the frequency domain value calculating component is used for calculating the energy sum in a preset frequency band range of the sound signal in a set time period;
the suspected data determining unit is specifically configured to determine that the sound signal in the set time period is suspected target audio data when the time domain maximum value is greater than a preset time domain positive threshold, the time domain minimum value is less than a preset time domain negative threshold, and the energy sum is greater than a preset energy threshold.
Optionally, the pattern recognition module specifically includes:
a multi-dimensional feature extraction unit, configured to extract a multi-dimensional feature from each data frame of the suspected target audio data, where the multi-dimensional feature is composed of a time domain feature and/or a frequency domain feature;
and the real fracture data identification unit is used for determining real top hammer fracture audio data according to the multi-dimensional features and a pre-constructed identification model.
Optionally, the apparatus further comprises:
the reference array element calling module is used for calling one microphone unit of the microphone array as a reference array element in sequence;
and the fracture sound source positioning module is used for positioning the source position of the anvil fracture audio data by utilizing the reference array element.
In conclusion, by introducing the microphone array technology, the invention realizes the real-time online monitoring of the anvil of the cubic press, not only solves the defects of the traditional manual inspection, but also solves the problems of time and labor waste and large environmental interference in other existing monitoring modes.
Furthermore, suspected data can be obtained preliminarily by analyzing the sound signals collected in real time, and real top hammer fracture audio data can be further obtained through a mode identification technology;
furthermore, the source of real anvil fracture audio data can be determined based on sound source positioning technology, so that the control equipment is stopped and the overhaul is warned. Therefore, the method analyzes the running state of the equipment by adopting a data pre-selection and mode identification mode based on the layout structure of the microphone array, and locks the position of the fault anvil by using a sound source positioning technology, thereby comprehensively realizing the real-time monitoring of the anvil state of the cubic press.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
FIG. 1 is a schematic perspective view of a cubic press;
FIG. 2 is a schematic view of the internal structure of a cubic press;
FIG. 3 is a block diagram of an embodiment of a cubic press top hammer monitoring system provided by the present invention;
FIG. 4 is a schematic diagram of an embodiment of a monitoring system for the anvil of a cubic press according to the present invention;
FIG. 5 is a block diagram of an integrated embodiment of a cubic press top hammer monitoring system provided by the present invention;
FIG. 6 is a schematic view of a monitoring system for the anvil of a cubic press according to a preferred embodiment of the present invention;
FIG. 7 is a flow chart of an embodiment of a cubic press top hammer monitoring method provided by the present invention;
FIG. 8 is a flow chart of an exemplary embodiment of a cubic press top hammer monitoring method of the present invention;
fig. 9 is a block diagram of an embodiment of a cubic press top hammer monitoring device provided by the invention.
Description of reference numerals:
1 microphone array 2 audio signal processing unit 3 data processing unit
10 big cushion block, 20 small cushion block, 30 top hammer and 101 microphone unit
4 warning unit 5 main control unit Mic1, Mic2, Mic3 microphone unit
S, X, Q, H, Z, Y anvil 100 sound collection module 200 preliminary analysis module
300 mode identification module
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
First, to facilitate understanding of the following, it should be noted that: the six directions of the cubic press can include four directions of horizontal front, back, left and right, and vertical up and down (here, horizontal, vertical, front, back, left, right, up and down are all relative position expressions for easy understanding). The cubic press generally comprises three movable cylinders (e.g. upper, front and right cylinders as shown in fig. 1) and three fixed cylinders (e.g. lower, rear and left cylinders) as well as the pressing process comprises the steps of synchronously moving the three movable cylinders toward the three fixed cylinders (e.g. upper-lower, front-rear and left-right cylinders) corresponding to the movable cylinders to apply six-direction pressure to the centrally located synthesis block, so that the matching of the three movable cylinders or the three fixed cylinders has a certain geometrical rule, that is, one cylinder in the vertical direction and two adjacent cylinders in the horizontal direction form three matched movable cylinders, and the other cylinder in the vertical direction and two adjacent cylinders in the horizontal direction form three fixed cylinders correspondingly.
Based on the structural characteristics of the cubic press, the present invention provides an embodiment of a monitoring system for the anvil of the cubic press, as shown in fig. 3, including: a data processing unit 3, an audio signal processing unit 2 and a microphone array 1 arranged in a cubic press. The electrical connection relationship may be that the microphone array 1 is connected to the input end of the audio signal processing unit 2, and the data processing unit 3 is connected to the output end of the audio signal processing unit 2. The invention provides a microphone array (instead of a single microphone) as a main means for anvil monitoring, which considers that although a single microphone can meet basic pickup requirements under the conditions of low noise, no reverberation and close distance to a sound source, in combination with the actual application scene of a single microphone product, if a large amount of noise, multipath reflection and reverberation exist in a real environment, for example, in a workshop where a plurality of jacks work, the environmental noise is relatively large, the quality of picked audio signals is easily reduced greatly, and the accuracy of determining the anvil state is seriously influenced; moreover, the signal received by the single microphone is superimposed by a plurality of sound sources and environmental noise, and the separation of the sound sources is difficult to realize, so that the sound sources cannot be positioned and separated, and the targeted fracture alarm is difficult to provide. In order to avoid these limitations of a single microphone, in this embodiment, it is considered that the microphone array is composed of a group of microphone units arranged according to a certain geometric structure, such as but not limited to a cross, a ring, a triangle, or a solid, and the like, and it can perform space-time processing on collected sound signals in different spatial directions, that is, by using the spatial filtering characteristics of the microphone array, functions such as noise suppression, reverberation removal, sound source direction finding, sound source tracking, array gain, and the like can be realized, so as to improve the subsequent audio signal processing quality, thereby improving the fracture identification accuracy under the actual application environment. The purpose of this embodiment is to combine a microphone array with a cubic apparatus press, and in implementation, a mature microphone array scheme may be selected, and it can be understood by those skilled in the art that an array formed by simply arranging a plurality of microphone units is only one audio acquisition physical interface, but in the art, when referring to a microphone array scheme, processing means matched with the physical interface is regarded as a whole, that is, the microphone array 1 and the audio signal processing unit 2 form a complete microphone hardware solution, wherein the audio signal processing unit 2 is configured with a conventional array algorithm, and the audio signal processing unit 2 will be described in detail later, which is not repeated herein; therefore, in the implementation stage, a person skilled in the art only needs to configure a microphone array scheme which is convenient for the operation of the person and meets the actual requirement according to the environment of the working site of the top press without improving a software program.
Referring to fig. 4 again, in actual operation, because the main function of the microphone array 1 is to collect the sound signal emitted by the anvil of the cubic press in real time, the microphone array 1 should be located as close to the anvil 30 as possible, and according to the actual shape, structure and size of the cubic press, in order to not affect the normal operation of the production personnel and consider the convenience of microphone array installation and routing and the factors such as on-site working conditions, it is preferable to install each microphone unit 101 in the microphone array on the large cushion block 10 of the piston of the cubic press, because the small cushion block 20 and the anvil 30 will be driven by the piston to squeeze the central material in the production process, if the microphone unit 101 makes telescopic motion along with the piston, that is, the array element is in motion state at any time, which will cause the sound source positioning accuracy of the cubic press to decrease, so it is not suggested to be installed on the moving parts of the cubic press, it can also be seen that the large block 10 is a preferred location relatively closer to the top hammer 30, and specifically, the microphone unit 101 may be mounted at an end of the large block 10 close to the top hammer, for example, on the large block 10 having a cylindrical shape, and the microphone unit 101 may be mounted on the outer periphery close to the end face of the cylindrical shape (the end face facing the top hammer). In practical operation, the microphone unit 101 may be mounted in various ways, for example, a bracket is welded or screwed on the large cushion block 10, and the microphone unit 101 may be fixedly mounted on the bracket by a ribbon, a screw, or the like; furthermore, fixed mounting means such as attaching, suction, etc. are also conceivable, provided of course that the microphone unit 101 is mounted relatively stably on the large pad 10.
It should be noted that the number of microphone units 101 may not be limited, and only six cases of sound source positions in a cubic press (i.e., the sound source distribution is known and fixed) are possible for the case of breakage of the jack hammers based on the principle that six jack hammers of a cubic press are distributed on six faces of a regular hexahedron. For example, the microphone units 101 are arranged on six (or five, four or three) big cushion blocks 10, and the distance from a broken sound source to a certain reference microphone unit 101 is obtained according to the sound source positioning algorithm of the array, so that which of six top hammers the broken sound source comes from can be uniquely determined; of course, in other embodiments, there may be other numbers of arrangements, and an embodiment of three microphone units 101 will be taken as an example hereinafter. It is also noted that for ease of illustration and from practical experience (with a minimum probability of two or more anvils breaking simultaneously in a cubic press), the present invention is exemplified by a single acoustic source, i.e., only one anvil in a cubic press is considered to break at the same time.
In the following, after the microphone unit 101 collects the sound signal emitted by the jack hammer, the sound signal is transmitted to the audio signal processing unit 2 via the signal cable for processing, where the processing may be analog-to-digital conversion, noise reduction, sampling alignment, and the like. In practice, the audio signal processing unit 2 may be a sound card with multi-channel acquisition and analog and/or digital signal processing configuration, for example, an adapter with a built-in multi-channel ADC chip and/or codec chip and/or DSP chip, etc., of course, in other embodiments, a part of digital signal processing, such as noise reduction processing, etc., may be moved to the data processing unit 3, but any configuration is conventional, and the present invention is not limited thereto.
The data processing unit 3 receives the sound signal processed by the audio signal processing unit 2 in a wired or wireless manner, and analyzes the anvil state according to the sound signal, where a specific analysis method is exemplified in a conventional manner, and after receiving a real-time sound signal collected by a current microphone array, a anvil working sound in a normal state is stored in the data processing unit 3, and the two are compared to easily find a difference, so that the working state of the anvil can be known, and a sound source position where the difference occurs can also be known by using technical characteristics of the microphone array 1. In specific implementation, the hardware of the data processing unit 3 is selected, and a server with a built-in audio analysis program can be considered, or a conventional sound comparison program is associated with the control of the whole production, and a central control lower computer or an upper computer or a field electric control cabinet for controlling the cubic press is adopted as a hardware carrier of the data processing unit 3; based on the aforementioned concept of transferring part of the digital signal processing to the data processing unit 3, accordingly, in one embodiment, the data processing unit 3 and the audio signal processing unit 2 may also be arranged in a set, for example, a PCBA formed by an embedded technology for a processor for analyzing sound data is integrated with a sound card. In addition, in order to avoid the interference of the surrounding environment or the damage to the components of the signal processing unit 2, the data processing unit 3 and the like in the production field, a centralized independent electrical box can be arranged for the units and the like, and related cables can be led out from the box wall.
Regarding the aforementioned wired or wireless connection manner, here, taking the server as an example, when the data processing unit 3 is a local server, the audio signal processing unit 2 may be wired to the local server through a data cable such as a network cable or a bus. When the data processing unit 3 is a remote server, the audio signal processing unit 2 may establish a wireless connection with the remote server through WIFI or transmission means such as 4G and 5G, and may select an existing wireless communication scheme such as IP6356S, CC1101, RTL8188 or BK 7231U. Of course, in another embodiment, if the data processing unit 3 is a local and close-distance device or terminal, it may also be considered that the audio signal processing unit 2 and the data processing unit 3 establish a wireless connection in a bluetooth manner, for example, a WCN3680 module supporting the WIFI standard and bluetooth 4.0 may be used in implementation, and the invention is not limited thereto.
Based on the above embodiments, in consideration of the safety requirements of the production site, as shown in fig. 5, in an integrated embodiment, the monitoring system provided by the present invention may further include an alarm unit 4 and a main control unit 5 for controlling the operation of the cubic press, wherein the alarm unit 4 is used to output alarm signals in the form of lights, sounds, characters, images, etc., so that the hardware with the above functions may be used as the alarm unit 4; the main control unit 5 may also be a central control lower computer or an upper computer in the production field, and is configured to receive the analysis result of the data processing unit 3, and accordingly control the operation state of the cubic press and/or trigger the warning unit 4 to output an alarm signal. For example, the data processing unit 3 reports a signal indicating that a anvil of a cubic press is broken to the main control unit 5, the main control unit 5 stops the cubic press from continuing to operate or resets the cubic press to a non-pressing state according to a conventional control program, and simultaneously triggers the display screen (the warning unit 4) to output a warning message indicating that the cubic press is stopped and which anvil needs to be repaired in a text and voice manner, where the supplementary explanation is two points. Secondly, the top hammer capable of locating a specific fault is just a sound source locating technology using a microphone array, and specific description of the technology can be referred to for the technology, and is not repeated herein; in another embodiment, the main control unit 5 may not stop the cubic press, but only trigger an audible and visual alarm device corresponding to a certain anvil of the cubic press to output an alarm signal, and an operator may manually control the main control unit 5 to stop the cubic press after the production process is finished, for example, a corresponding alarm lamp may be disposed near each cubic press, and the alarm lamp may be a multi-color colored lamp pillar (or a colored lamp strip, etc.) for indicating anvils at different positions; in another embodiment, the main control unit 5 may only control the cubic press to stop, and after the central control manager determines that the fault identification is valid by the field control platform (such as the production HMI), the central control manager triggers the warning unit 4 to output warning information to the field operator.
The anvil monitoring system provided by the invention combines the microphone array with the cubic apparatus press, utilizes the characteristics and advantages of the microphone array and the existing processing scheme aiming at the signals of the microphone array, and can timely monitor whether the anvil is broken and accurately position the broken anvil. Furthermore, based on the sound source positioning technology of the microphone array, the stop of the cubic press can be controlled after the anvil is determined to be broken, and the alarm can be given to an operator and the position of the broken anvil can be shown, so that targeted maintenance and replacement can be carried out in time. In conclusion, the mode for realizing the real-time online monitoring of the anvil of the cubic press is to simply install each microphone unit of the microphone array and configure the corresponding electric connection device, so that the defects of the traditional manual inspection are overcome, and the problems that other existing monitoring modes are time-consuming and labor-consuming to install and are greatly interfered by the environment are solved.
With respect to the aforementioned arrangement of the microphone arrays, the present invention, in conjunction with fig. 1 and fig. 2, provides a preferred embodiment that is both hardware cost saving and easy to install and can ensure accurate and effective monitoring, as shown in fig. 6, in this preferred embodiment, the number of the microphone units 101 is three, that is, a microphone array with only three array elements is selected to locate the position of the anvil where the fracture occurs, and the three microphone units 101 can be respectively installed on the large cushion block 10 of three movable cylinders (in other embodiments, three microphone units 101 can be respectively installed on three fixed cylinders). In the example of fig. 6, the three microphone units 101 are named as Mic1, Mic2 and Mic3 respectively for convenience of illustration, and the cylinders are represented by lines according to the three-dimensional structure of fig. 1, so that the internal structural relationship of the cubic press can be clearly seen. The upper-movable cylinder placing Mic1, the front-movable cylinder placing Mic2 and the right-movable cylinder placing Mic3 have two advantages that one is provided with a uniform position reference standard and is convenient to install, and particularly, the bolt head on the small cushion block 20 can be referred to during actual installation, and the microphone unit can be arranged on a vertical bisector of two bolt heads on the periphery of the small cushion block 20 corresponding to the large cushion block 10; another advantage is that the internal structure characteristics of cubic apparatus press are combined, make the microphone unit can be in relative top hammer position placed in the middle, can guarantee that three microphone unit two liang of intervals are equal after so installing, and the three constitutes regular triangle's microphone array promptly, and the array element interval is regular triangle's length of side.
The regular triangular microphone array arranged on the three large cushion blocks is a preferable scheme of the embodiment, and the function of the regular triangular microphone array is embodied in that six sound sources to be monitored are exactly positioned on the same side of the regular triangular array, and because the sound source positions are distributed on the top hammer 30, the distance from the top hammer 30 to a microphone unit and the distance between the microphone units are in the same order of magnitude and are relatively close to each other, the near-field sound source positioning technology can be adopted. Furthermore, due to the special position relationship between the regular triangle array and the six sound sources, when one of the microphone units is used as a reference, the positions of the two opposite top hammers can be located, so that the monitoring of all six top hammers can be sufficiently covered by using the three microphone units as reference microphones in sequence, and the layout structure of the microphone array can be called as a microphone regular triangle circulating area array.
The sound source localization technology of microphone array is the prior art, and only the layout characteristics of the microphone regular triangle circulating area array are briefly described here: in monitoring, when Mic1 is called as a reference microphone, because the distances from the top hammer Q and the top hammer H to Mic1 are considered to be the same from an engineering perspective, the distances from the top hammer Z and the top hammer Y to Mic1 are also considered to be the same, and only the top hammer S and the top hammer X with the distance difference are considered, the sound signals emitted by the top hammer S and the top hammer X can be positioned by only calculating the distance from a sound source to Mic1, and the distance from the top hammer S to Mic1 is recorded as dS1The distance d from top hammer X to Mic1X1. Similarly, when Mic2 is called as a reference microphone, the sound signals emitted by the top hammer Q and the top hammer H can be positioned, and the distance between the top hammer Q and Mic2 is recorded as dQ2Distance d from top hammer H to Mic2H2(ii) a Similarly, when Mic3 is called as a reference microphone, the sound signals emitted by the top hammer Z and the top hammer Y can be positioned, and the distance between the top hammer Z and Mic3 is recorded as dZ3Distance d from top hammer Y to Mic3Y3. From actual measurements dS1＝dQ2＝dY3＝L1，dX1＝dH2＝dZ3＝L2And the inherent structural characteristics necessarily satisfy L2＞L1The distance relation embodied by the structure can realize the accurate positioning of the fault anvil by a sound source positioning algorithm. Finally, it is pointed out that, in view of the defects of the prior art, the present invention aims to obtain a solution for monitoring the top hammer fracture, so that the fracture condition of the top hammer can be known by utilizing the conventional comparison analysis of the sound signals collected by the microphone array, and the above positioning technique is an additional technical effect of the microphone array, that is, not only the fault of the top hammer is monitored by the present invention, but also the position of the top hammer with the fracture condition of the body can be further identified by the technical characteristics of the microphone array. In conclusion, the invention not only solves the problems in the prior art, but also represents more remarkable technical progress.
On the basis of the above embodiment and preferred embodiment of the hardware structure layout, the present invention further provides a monitoring method of cubic press top hammer, which is different from the conventional comparison, as shown in fig. 7, and the method may include the following steps:
step S1, acquiring sound signals collected by a microphone array in a working state of the cubic press in real time;
step S2, carrying out preliminary analysis on the sound signal, and identifying suspected target audio data;
and step S3, determining real top hammer breaking audio data from the suspected target audio data based on a preset pattern recognition strategy.
Therefore, the embodiment has a design concept different from the traditional comparison mode, namely, real broken audio data is identified from real-time monitored sound data through two main steps of primary screening and fine screening by using a microphone array technology. The design consideration is that in combination with practical experience, when the cubic press is in a working state, due to the field environment (especially the scene that a plurality of presses work simultaneously), collected sound signals are often influenced by some irrelevant noises, and therefore the concept of primary screening and fine screening is adopted so as to more accurately capture real hammer-breaking audio. In combination with the foregoing, before performing the preliminary analysis, the method may further consider that the noise reduction processing technology for the microphone array is used to perform interference suppression processing on the acquired sound signals, so as to provide a more reliable data base to be analyzed for the subsequent preliminary screening and fine screening.
Because the sound signal generated by the top hammer breakage belongs to the impact signal which has obvious non-Gaussian characteristic, the time domain characteristic of the signal can reflect the overall state of the equipment and can be used for fault monitoring and trend prediction; the frequency domain characteristics of the signal can be used to determine the type, cause and location of the fault. Based on this, the collected sound signal is preliminarily analyzed in actual operation, and the time domain value and the frequency domain value of the sound signal can be used as a measurement basis, for example, the sound signal collected in a set time period is used as an analysis unit to examine the sound signalIn other words, the invention proposes that the precondition for data pre-selection satisfies a preset condition from the time domain and frequency domain angles, such as calculating the time domain maximum value (positive maximum amplitude) and the time domain minimum value (negative maximum amplitude) of the sound signal within a set time period, and the energy sum within a preset frequency band range of the sound signal within the set time period, and then requiring only when the time domain maximum value is greater than a preset time domain positive threshold T1And the time domain minimum value is smaller than a preset time domain negative threshold value T2And the energy sum is larger than a preset energy threshold value EfWhen all three conditions are satisfied, it can be determined that the sound signal in the set time period is the suspected target audio data.
The specific implementation process can be referred to as follows:
taking a set time period as a time unit of data to be analyzed, and performing preprocessing such as framing, windowing and FFT (fast Fourier transform) on a sound signal in the time unit.
It should be noted that the set time period is determined by practical application and/or a lot of experiments and experiences. Since the audio signal can be regarded as a short-time stationary signal, assuming that the sampling rate of the sound signal is 16kHz, the length of each frame is 512 points, 96ms is the length of 3 frames of the audio signal, and the length of the breaking sound signal of the hammer-top "snap" is approximately 3-5 frames, the set time period can be preset to be 160ms, that is, the length of 5 frames.
Calculating the maximum time domain value of the sound signal in the unit time and recording the maximum time domain value as maxTMinimum value minT(ii) a And the sum of the energy of the frequency domain in a preset frequency band or a plurality of frequency bands is marked as pow;
(iii) survey maxT、minTPow and T1、T2、EfIn the present embodiment, if the following conditions are satisfied: time domain-maxT＞T1，minT＜T2(ii) a Frequency domain-pow > EfThen the currently analyzed sound signal may then be determined as suspectThe audio data is labeled.
Then, based on the obtained suspected object audio data, a pattern recognition technique may be used to further classify the suspected object sound data frame into a conclusion about whether it is real top hammer fracture audio data, and a conventional pattern recognition algorithm, such as K-NN (K-Nearest Neighbor) algorithm, hmm (hidden Markov model) algorithm, gmm (gaussian Mixture model) algorithm, svm (support Vector machine) algorithm, etc., may be used.
In a preferred embodiment, a Support Vector Machine (SVM) algorithm is used as an example to classify each frame of the suspected target audio data (two types: non-top-hammer-break audio data and real-top-hammer-break audio data). The implementation process may be to extract a multi-dimensional feature from each data frame of the suspected target audio data, where the multi-dimensional feature is composed of a time domain feature and/or a frequency domain feature, and then determine the real top hammer fracture audio data according to the multi-dimensional feature and a pre-constructed recognition model.
For example, the following characteristic parameters may be extracted:
mean (1-dimensional data): it is a stable component describing the signal, also called direct current component, which is the equilibrium point position of mechanical vibration, and is the first moment statistical average of the signal.
Root mean square value (1-dimensional data): the energy used to describe the vibration signal, also called the effective value, is the statistical average of the second moment of the signal.
Peak indicator (1-dimensional data): a statistical indicator for detecting whether an impact is present in the signal. Wherein the peak value XpRefers to the unimodal maximum of the vibration waveform. For example, in the length of one frame signal, 10 numbers with the maximum absolute value are found, and the arithmetic mean of the 10 numbers is used as the peak value Xp。
Pulse index (1-dimensional data): a statistical indicator for detecting whether an impact is present in the signal.
Margin index (1-dimensional data): for detecting the wear of mechanical equipment.
Distortion index (1-dimensional data): the asymmetry of the vibration signal is reflected and is the statistical average of the third moment of the signal.
Kurtosis index (1-dimensional data): reflecting the impact characteristics in the vibration signal, is the fourth moment average of the signal. Is very sensitive to the impact characteristics in the signal, with a normal value around 3. If the value is close to 4 or exceeds 4, it indicates that there is an impact vibration in the motion state of the machine. In general, the clearance is too large, and the sliding pair surface is broken.
Pitch frequency (1-dimensional data): and calculating the pitch frequency of each frame by using the approximate partial coefficients after wavelet transformation.
Singular value decomposition (the decomposition order is selected to be 45 orders, and the first 30 singular values are taken, namely 30-dimensional data): reflecting the energy distribution of the useful signal and the noise in the signal.
All the features are extracted to form a 38-dimensional vector as an input vector of the recognition model, and the output vector is 2-dimensional, namely 10 (non-top hammer fracture) and 01 (top hammer fracture). It should be noted that, in the above example, only the pitch frequency is the frequency domain feature, and the other 37 dimensions are all the time domain features, but the number of the frequency domain features and the time domain features is not limited in other embodiments, for example, the singular value decomposition may include time domain singular value decomposition and frequency domain singular value decomposition, the above example is time domain singular value decomposition, and the other example may also employ frequency domain singular value decomposition.
On the basis of the embodiments of the above-mentioned system, method, etc., the present invention further provides a comprehensive monitoring scheme, as shown in fig. 8, which may include the following steps:
step S1, acquiring sound signals collected by a microphone array in a working state of the cubic press in real time;
step S2, carrying out preliminary analysis on the sound signal, and identifying suspected target audio data;
step S3, determining real top hammer fracture audio data from suspected target audio data based on a preset pattern recognition strategy;
step S4, determining the position of a broken fault anvil by using a sound source positioning technology of a microphone array;
and step S5, controlling the stop of the cubic press and/or warning the information of the failed anvil.
The specific sound source positioning mode can be that one microphone unit of a microphone array is called in sequence to serve as a reference array element, and the source position of the anvil fracture audio data is positioned by utilizing the reference array element.
In actual operation, the above-mentioned process can be implemented by using the existing sound source localization algorithm, such as an energy-based algorithm, a controllable beam forming algorithm, a spectrum estimation algorithm, a TDOA/TDE-based algorithm, and the like. In which the TDOA algorithm is less computationally intensive and is suitable for a single sound source in the near field, therefore, a preferred embodiment of the present invention is to calculate the sound source position information (i.e. the distance from the sound source to the reference array element) corresponding to each frame of data of the top hammer break audio data based on the TDOA algorithm. In particular, in conjunction with the embodiment of the microphone regular triangle circular area array (fig. 6) mentioned above, the following operations are performed:
first, Mic1 is called as the sound source localization subfunction of the reference microphone, and the return value of the sound source localization subfunction (i.e. the distance from the sound source to the reference array element) is L. If L is equal to L1If +/-0.1 k, the sound source comes from the top hammer S, namely the top hammer S is broken, and the sound source is switched to the fourth step; if L is equal to L2If +/-0.1 k, the sound source comes from the anvil X, namely the anvil X is broken, and the sound source is switched to the fourth step; if the situation is not the case, the sound source comes from one of the other four top hammers. Here, [ -0.1k, +0.1k]Is the error range, and k is the scale factor obtained by experiment.
Secondly, Mic2 is called as a sound source positioning sub-function of the reference microphone, and the return value of the sound source positioning sub-function (namely the distance from the sound source to the reference array element) is L. If L is equal to L1If +/-0.1 k, the sound source comes from the top hammer Q, namely the top hammer Q is broken, and the sound source is switched to the fourth step; if L is equal to L2If +/-0.1 k, the sound source comes from the anvil H, namely the anvil H breaks, and the sound source is switched to the fourth step; if not, the sound source is from one of the two remaining top hammers (Z, Y).
Thirdly, Mic3 is called as the sound source localization sub-function of the reference microphone, the return value of which (i.e. the distance of the sound source to the reference array element) is L. If L is equal to L1+ -0.1k, then sound is indicatedThe source is from the top hammer Y, namely the top hammer Y is broken, and the fourth step is executed; if L is equal to L2And +/-0.1 k, the sound source comes from the top hammer Z, namely the top hammer Z is broken, and the fourth step is executed.
And fourthly, finishing sound source positioning.
Finally, in step S5, when the monitoring result is determined, a stop command may be sent to control the cubic press to stop, and at the same time, the number of the cubic press and the number of the anvil thereof are preset, so that an alarm may be given synchronously and the number of the broken anvil is shown, so that the fault can be handled timely and effectively. The operation and warning method of the cubic press are described above and will not be described herein.
In summary, by introducing the microphone array technology, the invention realizes the real-time online monitoring of the anvil of the cubic press, not only solves the defects of the traditional manual inspection, but also overcomes the problems of time and labor waste and large environmental interference in the installation of other existing monitoring modes.
Furthermore, suspected data can be obtained preliminarily by analyzing the sound signals collected in real time, and real top hammer fracture audio data can be further obtained through a mode identification technology;
furthermore, the source of real anvil fracture audio data can be determined based on sound source positioning technology, so that the control equipment is stopped and the overhaul is warned. Therefore, the method analyzes the running state of the equipment by adopting a data pre-selection and mode identification mode based on the layout structure of the microphone array, and locks the position of the fault anvil by using a sound source positioning technology, thereby comprehensively realizing the real-time monitoring of the anvil state of the cubic press.
Corresponding to the above method embodiment and its preferred solution, the present invention further provides an embodiment of a monitoring device for top hammer of cubic press, as shown in fig. 9, including:
the sound acquisition module 100 is used for acquiring sound signals acquired by the microphone array in a working state of the cubic press in real time;
a preliminary analysis module 200, configured to perform preliminary analysis on the sound signal, and identify suspected target audio data;
and the pattern recognition module 300 is configured to determine real anvil fracture audio data from the suspected target audio data based on a preset pattern recognition strategy.
Further, the preliminary analysis module specifically includes:
the audio analysis unit is used for calculating time domain and frequency domain values of the sound signals by taking the sound signals in a set time period as an analysis unit;
and the suspected data judging unit is used for analyzing whether the sound signal is suspected target audio data according to the relationship between the time domain and frequency domain calculation results and a preset judgment threshold value.
Further, the air conditioner is provided with a fan,
the audio analysis unit specifically includes:
the time domain value calculating component is used for calculating the time domain maximum value and the time domain minimum value of the sound signal in a set time period;
the frequency domain value calculating component is used for calculating the energy sum in a preset frequency band range of the sound signal in a set time period;
the suspected data determining unit is specifically configured to determine that the sound signal in the set time period is suspected target audio data when the time domain maximum value is greater than a preset time domain positive threshold, the time domain minimum value is less than a preset time domain negative threshold, and the energy sum is greater than a preset energy threshold.
Further, the pattern recognition module specifically includes:
a multi-dimensional feature extraction unit, configured to extract a multi-dimensional feature from each data frame of the suspected target audio data, where the multi-dimensional feature is composed of a time domain feature and/or a frequency domain feature;
and the real fracture data identification unit is used for determining real top hammer fracture audio data according to the multi-dimensional features and a pre-constructed identification model.
Further, the apparatus further comprises:
the reference array element calling module is used for calling one microphone unit of the microphone array as a reference array element in sequence;
and the fracture sound source positioning module is used for positioning the source position of the anvil fracture audio data by utilizing the reference array element.
Finally, it should be emphasized that while the above-described embodiments of the apparatus and preferred embodiments have been described in the context of their operation and technical principles, it will be appreciated that the various component embodiments of the apparatus may also be implemented in hardware, or as software modules running on one or more processors, or as a combination thereof. The modules or units or components in the device embodiments may be combined into one module or unit or component, or may be divided into a plurality of sub-modules or sub-units or sub-components to be implemented.
In addition, the embodiments in the present specification are all described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, they are described in a relatively simple manner, and reference may be made to some descriptions of method embodiments for relevant points. The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The structure, features and effects of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the above embodiments are merely preferred embodiments of the present invention, and it should be understood that technical features related to the above embodiments and preferred modes thereof can be reasonably combined and configured into various equivalent schemes by those skilled in the art without departing from and changing the design idea and technical effects of the present invention; therefore, the invention is not limited to the embodiments shown in the drawings, and all the modifications and equivalent embodiments that can be made according to the idea of the invention are within the scope of the invention as long as they are not beyond the spirit of the description and the drawings.
Claims (13)
1. A monitoring system for top hammer of cubic press is characterized by comprising: the device comprises a data processing unit, an audio signal processing unit and a microphone array arranged on a cubic press;
the microphone array is connected with the input end of the audio signal processing unit, and the data processing unit is connected with the output end of the audio signal processing unit;
the microphone array is provided with three microphone units, and the three microphone units are arranged on a large cushion block of a piston of the cubic press and form a regular triangular microphone array so as to be used for acquiring sound signals emitted by a top hammer of the cubic press in real time;
the audio signal processing unit is used for processing the sound signal and sending the processed sound signal to the data processing unit;
the data processing unit is used for analyzing the state of the anvil according to the processed sound signal.
2. The cubic press top hammer monitoring system as set forth in claim 1, wherein three said microphone units are mounted on said large blocks of three movable cylinders or three fixed cylinders, respectively.
3. The cubic press top hammer monitoring system as set forth in any one of claims 1-2, further comprising: the device comprises a warning unit and a main control unit for controlling the operation of the cubic press;
the main control unit is connected with the data processing unit and used for controlling the stop of the cubic press and/or triggering the warning unit to output an alarm signal according to the state of the anvil sent by the data processing unit.
4. A monitoring method for top hammer of cubic press is characterized by comprising the following steps:
acquiring sound signals collected by a microphone array in a working state of the cubic press in real time; the microphone array is provided with three microphone units, and the three microphone units are arranged on a large cushion block of a piston of the cubic press and form a regular triangular microphone array;
performing preliminary analysis on the sound signal to identify suspected target audio data;
and determining real top hammer fracture audio data from the suspected target audio data based on a preset pattern recognition strategy.
5. The method as claimed in claim 4, wherein said preliminary analysis of the acoustic signal to identify suspected target audio data comprises:
taking the sound signal in a set time period as an analysis unit, and calculating time domain and frequency domain values of the sound signal;
and analyzing whether the sound signal is suspected target audio data or not according to the relation between the time domain and frequency domain calculation results and a preset judgment threshold value.
6. The cubic press top hammer monitoring method as set forth in claim 5,
the calculating time domain and frequency domain values of the sound signal comprises:
calculating a time domain maximum value and a time domain minimum value of the sound signal in a set time period;
calculating the energy sum in a preset frequency band range of the sound signal in a set time period;
the analyzing whether the sound signal is suspected target audio data according to the relationship between the time domain and frequency domain calculation results and a preset judgment threshold comprises:
and when the time domain maximum value is larger than a preset time domain positive threshold, the time domain minimum value is smaller than a preset time domain negative threshold, and the energy sum is larger than a preset energy threshold, determining that the sound signal in the set time period is suspected target audio data.
7. The method as claimed in claim 4, wherein said determining real anvil fracture audio data from the suspected target audio data based on a predetermined pattern recognition strategy comprises:
extracting multi-dimensional features from each data frame of the suspected target audio data, wherein the multi-dimensional features consist of time domain features and/or frequency domain features;
and determining real top hammer fracture audio data according to the multi-dimensional features and a pre-constructed recognition model.
8. The cubic press top hammer monitoring method as set forth in any one of claims 4 to 7, further comprising:
sequentially calling one microphone unit of the microphone array as a reference array element;
and positioning the source position of the top hammer fracture audio data by using the reference array element.
9. The utility model provides a cubic press top hammer monitoring devices which characterized in that includes:
the sound acquisition module is used for acquiring sound signals acquired by the microphone array in a working state of the cubic press in real time; the microphone array is provided with three microphone units, and the three microphone units are arranged on a large cushion block of a piston of the cubic press and form a regular triangular microphone array;
the preliminary analysis module is used for carrying out preliminary analysis on the sound signal and identifying suspected target audio data;
and the pattern recognition module is used for determining real top hammer fracture audio data from the suspected target audio data based on a preset pattern recognition strategy.
10. The cubic press top hammer monitoring device as set forth in claim 9, wherein said preliminary analysis module comprises:
the audio analysis unit is used for calculating time domain and frequency domain values of the sound signals by taking the sound signals in a set time period as an analysis unit;
and the suspected data judging unit is used for analyzing whether the sound signal is suspected target audio data according to the relationship between the time domain and frequency domain calculation results and a preset judgment threshold value.
11. The cubic press top hammer monitoring device as set forth in claim 10,
the audio analysis unit specifically includes:
the time domain value calculating component is used for calculating the time domain maximum value and the time domain minimum value of the sound signal in a set time period;
the frequency domain value calculating component is used for calculating the energy sum in a preset frequency band range of the sound signal in a set time period;
the suspected data determining unit is specifically configured to determine that the sound signal in the set time period is suspected target audio data when the time domain maximum value is greater than a preset time domain positive threshold, the time domain minimum value is less than a preset time domain negative threshold, and the energy sum is greater than a preset energy threshold.
12. The cubic press top hammer monitoring device as recited in claim 9, wherein said pattern recognition module comprises:
a multi-dimensional feature extraction unit, configured to extract a multi-dimensional feature from each data frame of the suspected target audio data, where the multi-dimensional feature is composed of a time domain feature and/or a frequency domain feature;
and the real fracture data identification unit is used for determining real top hammer fracture audio data according to the multi-dimensional features and a pre-constructed identification model.
13. The cubic press top hammer monitoring device as set forth in any one of claims 9 to 12, further comprising:
the reference array element calling module is used for calling one microphone unit of the microphone array as a reference array element in sequence;
and the fracture sound source positioning module is used for positioning the source position of the anvil fracture audio data by utilizing the reference array element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910470900.5A CN110201606B (en) | 2019-05-31 | 2019-05-31 | System, method and device for monitoring top hammer of cubic press |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910470900.5A CN110201606B (en) | 2019-05-31 | 2019-05-31 | System, method and device for monitoring top hammer of cubic press |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110201606A CN110201606A (en) | 2019-09-06 |
| CN110201606B true CN110201606B (en) | 2022-02-18 |
Family
ID=67790026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910470900.5A Active CN110201606B (en) | 2019-05-31 | 2019-05-31 | System, method and device for monitoring top hammer of cubic press |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110201606B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110987402B (en) * | 2019-12-20 | 2022-01-11 | 中国科学技术大学 | Ball mill working state detection method based on sound energy |
| CN115060575A (en) * | 2022-06-29 | 2022-09-16 | 中国工程物理研究院核物理与化学研究所 | High-pressure ultrasonic device of cubic apparatus press |
| CN120369829B (en) * | 2025-06-30 | 2025-09-16 | 太原科技大学 | Monitoring method and system for hexahedral top press |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4072353A (en) * | 1976-08-27 | 1978-02-07 | The Curators Of The University Of Missouri | Thrust-impact rock-splitter |
| US4175106A (en) * | 1977-09-14 | 1979-11-20 | Masonite Corporation | Post press molding of man-made boards to produce contoured furniture parts |
| CN2243081Y (en) * | 1995-05-19 | 1996-12-18 | 王林 | Device for monitoring break of knock-out harmmer of diamond press |
| CN201921672U (en) * | 2010-12-27 | 2011-08-10 | 桂林市恒鑫科技有限公司 | Breakage alarm for anvil of artificial diamond press |
| CN203196604U (en) * | 2012-12-27 | 2013-09-18 | 郑州人造金刚石及制品工程技术研究中心有限公司 | Top hammer early-warning device of cubic press |
| CN103674538A (en) * | 2013-12-18 | 2014-03-26 | 北京航天测控技术有限公司 | Multi-fault mode identification method and device of swashplate of helicopter |
| CN106770675A (en) * | 2016-12-06 | 2017-05-31 | 郑州轻工业学院 | Diamond press top hammer crackle online test method based on acoustic emission signal |
| CN206500125U (en) * | 2017-02-28 | 2017-09-19 | 洛阳启明超硬材料有限公司 | A kind of large-scale mute cubic hydraulic press |
-
2019
- 2019-05-31 CN CN201910470900.5A patent/CN110201606B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4072353A (en) * | 1976-08-27 | 1978-02-07 | The Curators Of The University Of Missouri | Thrust-impact rock-splitter |
| US4175106A (en) * | 1977-09-14 | 1979-11-20 | Masonite Corporation | Post press molding of man-made boards to produce contoured furniture parts |
| CN2243081Y (en) * | 1995-05-19 | 1996-12-18 | 王林 | Device for monitoring break of knock-out harmmer of diamond press |
| CN201921672U (en) * | 2010-12-27 | 2011-08-10 | 桂林市恒鑫科技有限公司 | Breakage alarm for anvil of artificial diamond press |
| CN203196604U (en) * | 2012-12-27 | 2013-09-18 | 郑州人造金刚石及制品工程技术研究中心有限公司 | Top hammer early-warning device of cubic press |
| CN103674538A (en) * | 2013-12-18 | 2014-03-26 | 北京航天测控技术有限公司 | Multi-fault mode identification method and device of swashplate of helicopter |
| CN106770675A (en) * | 2016-12-06 | 2017-05-31 | 郑州轻工业学院 | Diamond press top hammer crackle online test method based on acoustic emission signal |
| CN206500125U (en) * | 2017-02-28 | 2017-09-19 | 洛阳启明超硬材料有限公司 | A kind of large-scale mute cubic hydraulic press |
Non-Patent Citations (1)
| Title |
|---|
| 六面顶压机顶锤破裂的在线无损检测研究;刘栋;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;中国优秀硕士学位论文全文数据库工程科技Ⅰ辑;20160115(第01期);第B015-100页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110201606A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110201606B (en) | System, method and device for monitoring top hammer of cubic press | |
| CN106066254B (en) | The detection in real time of factory's failure based on Internet of Things and positioning system and method | |
| CN203490359U (en) | Portable transformer station noise imaging positioning detecting device | |
| CN110208022A (en) | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning | |
| CN114414963A (en) | Acoustic imaging positioning system and method for intelligent monitoring of substation domain faults | |
| JP6527187B2 (en) | Learning model construction device, anomaly detection device, anomaly detection system and server | |
| CN111354366A (en) | Abnormal sound detection method and abnormal sound detection device | |
| CN108594795A (en) | A kind of EMU sound fault diagnosis system and diagnostic method | |
| CN108760034A (en) | A kind of transformer vibration noise source positioning system and method | |
| CN103336266A (en) | Portable transformer substation noise imaging positioning detection device | |
| CN104049037A (en) | Fault early warning system | |
| CN116776279A (en) | Multi-modal data collaborative abnormal target detection method for flash explosion early warning of transmission lines | |
| CN109019349A (en) | fault detection method, detector, computer storage medium and crane | |
| CN103920424B (en) | Man-made diamond pressing machine splits hammer real-time monitoring device and method and splits hammer determination methods | |
| CN103344943A (en) | Ultrasonic image positioning detecting device of transformer substation | |
| CN105897483A (en) | Airplane fault real time monitoring and positioning system and method based on internet of things | |
| CN116213498B (en) | Mold wear monitoring and positioning device and method based on multichannel acoustic emission | |
| CN112371995A (en) | Selective laser melting 3D printing crack detection method and device and storage medium | |
| CN109351831B (en) | Five metals stamping workpiece forming process | |
| CN111292510A (en) | Recognition early warning method for urban cable damaged by external force | |
| CN106482912B (en) | A kind of vacuum equipment leak detection and localization method | |
| CN115031830A (en) | A nondestructive testing device and method of acoustic wave optical imaging for power equipment diagnosis | |
| CN112173912B (en) | Elevator brake wheel wear degree monitoring system | |
| CN210729456U (en) | Top hammer monitoring system of cubic apparatus press | |
| CN208147865U (en) | A kind of sound recognition system applied to robot used for intelligent substation patrol |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220507 Address after: 450045 building 4, Henan information security industry demonstration park, No. 115, Baorui Road, Zhengzhou City, Henan Province Patentee after: Henan Xunfei Artificial Intelligence Technology Co.,Ltd. Address before: 471000 Building 1, science and Technology Park, Luoyang National University, No. 1, Longyu Road, Jianxi District, Luoyang City, Henan Province Patentee before: LUOYANG VOICE CLOUD INNOVATION INSTITUTE |