CN117509067A - Mining conveyor system with detection function and operation method - Google Patents
Mining conveyor system with detection function and operation method Download PDFInfo
- Publication number
- CN117509067A CN117509067A CN202410008349.3A CN202410008349A CN117509067A CN 117509067 A CN117509067 A CN 117509067A CN 202410008349 A CN202410008349 A CN 202410008349A CN 117509067 A CN117509067 A CN 117509067A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- detection data
- ultrasonic detection
- adjusted
- tearing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 149
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000005065 mining Methods 0.000 title claims abstract description 49
- 230000007613 environmental effect Effects 0.000 claims abstract description 35
- 238000005516 engineering process Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000000926 separation method Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 25
- 230000004044 response Effects 0.000 claims description 21
- 239000000428 dust Substances 0.000 claims description 18
- 238000002592 echocardiography Methods 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000003745 diagnosis Methods 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000008439 repair process Effects 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 6
- 238000013210 evaluation model Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000009022 nonlinear effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of mining conveying detection, in particular to a mining conveyor system with a detection function and an operation method. Firstly, an ultrasonic sensor is utilized to transmit and receive ultrasonic signals, a multi-factor determination method is adopted to calculate pulse repetition frequency, an overlapping echo separation technology is introduced to obtain original ultrasonic detection data, and the original ultrasonic detection data is adjusted and calibrated by combining with environmental parameters of a mining conveyor to obtain adjusted and calibrated ultrasonic detection data; and then preprocessing the adjusted and calibrated ultrasonic detection data, extracting time domain features and frequency domain features of the preprocessed ultrasonic detection data to obtain a comprehensive feature set, optimizing the comprehensive feature set to obtain a final feature set, analyzing by using a longitudinal tearing intelligent recognition algorithm based on the final feature set, and judging whether the conveyor belt is longitudinally torn or not. The technical problems of inaccurate detection data processing and poor self-adaptability in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of mining conveying detection, in particular to a mining conveyor system with a detection function and an operation method.
Background
Conveyors are one of the key devices in the mining industry for efficiently transporting minerals and other materials. However, mining conveyor belts are often subjected to extreme operating conditions such as friction, tearing, and wear. These factors can lead to damage to the conveyor belt, affecting its performance and efficiency. Conventional mining conveyor systems often lack an effective monitoring mechanism to detect and prevent such longitudinal tears. When serious damage occurs to the conveyor belt, shutdown and production efficiency may be reduced, and even safety of workers may be threatened. Therefore, it is important to develop a mining conveyor system with an efficient longitudinal tear detection function.
There are many methods for mining conveying detection, and our invention patent application number: "CN202210225204.X", publication date: 2022.07.15, discloses a "belt longitudinal tear monitoring system and conveying equipment", the belt longitudinal tear monitoring system includes: an ultrasonic wave transmitting device, an ultrasonic wave receiving device and a reflective coating coated on the belt; the belt is annular, the reflective coating is in the inner ring surface of belt, the belt divide into upper band and lower floor's area, the upper band is used for bearing the weight of the material, ultrasonic emission device with ultrasonic receiving arrangement all is located between the upper band with the lower floor's area, ultrasonic emission device's transmitting end with ultrasonic receiving arrangement's receiving end all is towards the inner surface of upper band, ultrasonic emission device is used for transmitting the ultrasonic wave, ultrasonic receiving arrangement is used for receiving echo and converts echo acoustic pressure value into. The belt longitudinal tearing monitoring system has high monitoring precision, can monitor whether the belt is longitudinally torn in time, avoids the problem of material leakage, and ensures the exploitation of coal mines.
However, the above technology has at least the following technical problems: the technical problems of inaccurate detection data processing and poor self-adaptability are solved.
Disclosure of Invention
The invention provides a mining conveyor system with a detection function and an operation method thereof, solves the technical problems of inaccurate detection data processing and poor self-adaptability in the prior art, and realizes the technical effects of high-precision detection data processing and self-adaptive longitudinal tearing detection of a conveyor belt.
The invention relates to a mining conveyor system with a detection function and an operation method thereof, which concretely comprise the following technical scheme:
mining conveyor system with detect function, including the following part:
the system comprises an ultrasonic detection unit, an environment adaptability adjustment unit, a data analysis processing unit, an intelligent response and adjustment unit and a self-maintenance unit;
the ultrasonic detection unit utilizes the ultrasonic sensor to transmit and receive ultrasonic signals, calculates the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, introduces an overlapping echo separation technology, obtains original ultrasonic detection data, and transmits the original ultrasonic detection data to the environment adaptability adjustment unit; simultaneously, the parameters of the ultrasonic waves are adjusted by utilizing the feedback data of the intelligent response and adjustment unit;
the environment adaptability adjusting unit is used for analyzing the relation between the original ultrasonic detection data and the environment parameters, adjusting and calibrating the original ultrasonic detection data, wherein the environment parameters comprise temperature, humidity and dust concentration, obtaining the adjusted and calibrated ultrasonic detection data, and transmitting the adjusted and calibrated ultrasonic detection data to the data analysis processing unit;
the data analysis processing unit is used for analyzing the adjusted and calibrated ultrasonic detection data, identifying whether the conveyor belt is longitudinally torn or not, obtaining a diagnosis result of the conveyor belt tearing, and transmitting the diagnosis result to the intelligent response and adjustment unit;
the intelligent response and adjustment unit is used for automatically adjusting the operation parameters and emergency response signals of the mining conveyor system based on the diagnosis result of the data analysis and processing unit, including the conveying speed, obtaining the adjusted operation parameters and the emergency response signals, adjusting the operation of the conveyor according to the adjusted operation parameters, triggering a safety alarm according to the emergency response signals, and feeding back to the ultrasonic detection unit;
the self-maintenance unit monitors the performance and health status of the mining conveyor system and implements predictive maintenance and fault diagnosis using machine learning techniques.
The operation method of the mining conveyor with the detection function comprises the following steps:
s1, utilizing an ultrasonic sensor to transmit and receive ultrasonic signals, adopting a multi-factor determination method to calculate the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, introducing an overlapped echo separation technology to obtain original ultrasonic detection data, and combining the environmental parameters of a mining conveyor to adjust and calibrate the original ultrasonic detection data to obtain the adjusted and calibrated ultrasonic detection data;
s2, preprocessing the adjusted and calibrated ultrasonic detection data, extracting time domain features and frequency domain features of the preprocessed ultrasonic detection data to obtain a comprehensive feature set, optimizing the comprehensive feature set to obtain a final feature set, analyzing by using a longitudinal tearing intelligent recognition algorithm based on the final feature set, and judging whether the conveyor belt has longitudinal tearing or not;
the method is applied to the mining conveyor system with the detection function.
Preferably, in the step S1, the method specifically includes:
in the process of acquiring original ultrasonic detection data, when receiving the ultrasonic detection data, an overlapped echo separation technology is introduced to separate overlapped echoes, and the overlapped echo separation technology is specifically realized as follows: firstly, detecting whether ultrasonic echoes overlap or not by a signal analysis method, and when the ultrasonic echoes are detected to overlap, performing time-frequency analysis by utilizing short-time Fourier transform; extracting the center frequency, bandwidth, amplitude and phase of each ultrasonic echo by using an echo characteristic extraction method; finally, the overlapped ultrasonic echoes are separated and reconstructed after being absorbed by using a reconstruction formula; and finally obtaining the original ultrasonic detection data.
Preferably, in the step S1, the method further includes:
when the original ultrasonic detection data are adjusted and calibrated, an environmental impact assessment model set is constructed to analyze the impact relationship between the environmental parameters and the original ultrasonic detection data.
Preferably, in the step S1, the method further includes:
the environmental impact assessment model set comprises a temperature impact model, a humidity impact model and a dust impact model; and applying the collected environmental parameters to an environmental impact evaluation model set, estimating the actual impact of the environment on the ultrasonic detection data, and correspondingly adjusting the original ultrasonic detection data according to the temperature impact model, the humidity impact model and the dust impact model to obtain the adjusted and calibrated ultrasonic detection data.
Preferably, in the step S2, the method specifically includes:
the longitudinal tearing intelligent recognition algorithm adopts a probability-based classification method to calculate the probability that each sample belongs to a longitudinal tearing category, and the specific implementation process is as follows: firstly, carrying out self-adaptive adjustment on the characteristics by utilizing a tearing characteristic self-adaptive algorithm based on a final characteristic set to obtain the characteristics after comprehensive adjustment; then, probability estimation is carried out based on the comprehensively adjusted characteristics; further, a tearing probability optimization algorithm is introduced to optimize a probability estimation result, and a probability estimation value after adjustment and optimization is obtained; the method comprises the steps of setting a threshold value for distinguishing whether longitudinal tearing occurs, and judging that the longitudinal tearing occurs when the probability estimated value after adjustment and optimization is larger than the set threshold value; otherwise, it is determined that this is not the case.
Preferably, in the step S2, the method further includes:
and the tearing probability optimization algorithm adjusts and optimizes the probability estimation result by defining probability weights.
Preferably, in the step S2, the method further includes:
determining the position of the tear and deducing the severity of the tear and the characteristics of the tear based on the analysis result of the longitudinal tear intelligent identification algorithm; depending on the location of the tear, the severity of the tear, and the nature of the tear, repair or inspection advice is provided.
The technical scheme of the invention has the beneficial effects that:
1. according to the invention, the original ultrasonic detection data is adjusted and calibrated by combining an ultrasonic technology with environmental parameters, so that the accuracy of a detection result is improved; the introduced overlapped echo separation technology effectively separates and analyzes overlapped ultrasonic echoes, thereby improving the capability of detecting longitudinal tearing; analyzing the influence of environmental parameters on the original ultrasonic detection data by constructing an environmental influence evaluation model set to obtain more accurate ultrasonic detection data, and providing accurate data basis for longitudinal tearing detection;
2. according to the invention, the characteristic elements are dynamically adjusted through the tearing characteristic self-adaptive algorithm, so that the data is more suitable for subsequent probability estimation, and the adaptability and the robustness of the tearing characteristic self-adaptive algorithm under different environments and conditions are improved; and the probability of longitudinal tearing of the conveying belt is estimated by comprehensively considering a plurality of characteristic elements, so that the accuracy of tearing detection is improved. And the probability estimation after optimization is adjusted, so that the robustness and reliability of the result are further improved.
Drawings
FIG. 1 is a block diagram of a mining conveyor system with detection according to the present invention;
fig. 2 is a flow chart of a method of operating a mining conveyor with detection according to the present invention.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of 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 apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the mining conveyor system with a detection function and an operation method thereof provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, the mining conveyor system with detection function of the present invention is specifically applied to a mining conveyor system with belt longitudinal tear detection function, and the system comprises the following parts:
the system comprises an ultrasonic detection unit, an environment adaptability adjustment unit, a data analysis processing unit, an intelligent response and adjustment unit and a self-maintenance unit;
the ultrasonic detection unit is used for respectively transmitting and receiving ultrasonic signals by utilizing the ultrasonic sensor, calculating the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, obtaining original ultrasonic detection data, and transmitting the original ultrasonic detection data to the environment adaptability adjustment unit; simultaneously, the parameters of the ultrasonic waves are adjusted by utilizing feedback data of the intelligent response and adjustment unit so as to adapt to different detection requirements and environmental conditions, wherein the detection parameters comprise the frequency and the intensity of the ultrasonic waves;
the environment adaptability adjusting unit is used for analyzing the relation between the original ultrasonic detection data and the environment parameters, such as temperature, humidity and dust concentration, so as to obtain the ultrasonic detection data subjected to environment adjustment and calibration, and transmitting the ultrasonic detection data subjected to the adjustment and calibration to the data analysis processing unit;
and the data analysis processing unit is used for analyzing the adjusted and calibrated ultrasonic detection data, accurately identifying whether the conveyor belt is longitudinally torn, obtaining a detailed diagnosis result of the conveyor belt tearing, and transmitting the diagnosis result to the intelligent response and adjustment unit.
The intelligent response and adjustment unit is used for automatically adjusting the operation parameters of the mining conveyor system, such as the conveying speed or sending out a shutdown alarm, so as to obtain adjusted operation parameters and emergency response signals, adjusting the operation of the conveyor according to the adjusted operation parameters, triggering a safety alarm according to the emergency response signals, and feeding back to the ultrasonic detection unit to optimize the performance of the ultrasonic detection unit;
the functional description of the intelligent response and regulation unit is part of an automation and control system, belonging to conventional technical means and not described in detail here.
And the self-maintenance unit is used for monitoring the performance and the health state of the mining conveyor system, and performing predictive maintenance and fault diagnosis by using a machine learning technology so as to ensure the long-term stable operation of the system.
Machine learning techniques are used for predictive maintenance and fault diagnosis in order to address various challenges that conveyor systems may face during operation to ensure the stability and reliability of the conveyor systems. The above-described method is a common technical means for those skilled in the art, and will not be described herein.
Referring to fig. 2, the operation method of the mining conveyor with the detection function of the invention is specifically applied to the operation method of the mining conveyor with the detection function of longitudinal tearing of a belt, and the operation method comprises the following steps:
s1, utilizing an ultrasonic sensor to transmit and receive ultrasonic signals, adopting a multi-factor determination method to calculate the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, introducing an overlapped echo separation technology to obtain original ultrasonic detection data, and combining the environmental parameters of a mining conveyor to adjust and calibrate the original ultrasonic detection data to obtain the adjusted and calibrated ultrasonic detection data;
setting parameters of an ultrasonic sensor, such as pulse repetition frequency and intensity, by a professional technician according to the type and thickness of the mining conveyor belt;
firstly, calculating pulse repetition frequency of ultrasonic pulse emitted by ultrasonic sensor by utilizing multi-factor determination method, making the pulse pass through conveyer belt and be reflected back at discontinuity in its interior, and making the pulse repetition frequencyThe calculation is as follows:
，
wherein,is the speed of the conveyor belt, i.e., the distance the conveyor belt moves per second; />Is the propagation velocity of ultrasonic waves in the conveyor belt material, depending on the density and elastic modulus of the conveyor belt material; />Is the width of the conveyor belt; />Is the radius of the detection range of the ultrasonic sensor; />Is the incidence angle of the ultrasonic sensor and the plane of the conveyer belt; />Is the ultrasonic beam width;the distance of the movement of the conveyor belt is ensured before the ultrasonic sensor covers the whole detection range, so that each area is ensured to have enough time to be covered by ultrasonic wave beams; />Taking into account the propagation path and beam width spread of the ultrasonic beam during its passage through the conveyor belt, ensuring that the ultrasonic beam can effectively cover the entire width of the conveyor belt, including the effects of beam spread; calculating a proper pulse repetition frequency according to the characteristics of the conveyor belt and the technical specification of the ultrasonic sensor so as to ensure effective ultrasonic detection of the conveyor belt, wherein the pulse repetition frequency is a key parameter for ensuring that ultrasonic waves can effectively cover the whole detection range and reflect back to the ultrasonic sensor in the aspect of detecting longitudinal tearing;
and transmitting ultrasonic signals according to the pulse repetition frequency, and immediately after transmitting the ultrasonic signals, recording the exact position of each pulse through a built-in position sensor so as to ensure the comprehensive detection of the conveying belt. The position information of the pulses and the pulse repetition frequency will be used for processing the reflected ultrasonic signals;
then, the ultrasonic sensor captures the reflected signal to obtain original ultrasonic detection data; the raw ultrasonic detection data may include the intensity of the ultrasonic signal, pulse repetition frequency, reflection pattern, and positional information of the belt detected by the ultrasonic sensor.
When receiving the original ultrasonic detection data, ultrasonic echoes may overlap, so that tearing detection is difficult, and the invention introduces an overlapping echo separation technology to separate the overlapping ultrasonic echoes so as to analyze each ultrasonic echo independently:
firstly, detecting whether ultrasonic echoes overlap or not by using a signal analysis method, wherein the adopted signal analysis method is the prior art and is not described in detail herein; if the ultrasonic echo overlapping is detected, immediately performing high-resolution time-frequency analysis on the received original ultrasonic detection data by using short-time Fourier transform (STFT) to distinguish time and frequency characteristics of different ultrasonic echoes; extracting the center frequency, bandwidth, amplitude and phase of each ultrasonic echo from the STFT result by using an echo characteristic extraction method, wherein the adopted echo characteristic extraction method is the prior art and is not described in detail herein; finally, separating and reconstructing overlapped ultrasonic echoes after absorbing by using a reconstruction formula so as to analyze each ultrasonic echo independently; the ultrasonic echo signal reconstruction formula is as follows:
，
wherein,is the reconstructed ultrasonic echo signal; />The i-th ultrasonic echo amplitude reflects the intensity of the ultrasonic echo and is related to the tearing size; />Is an imaginary representation; />Is the phase of the ith ultrasonic echo, and is related to the time characteristic of the ultrasonic echo; />The arrival time of the ith ultrasonic echo is a key parameter for determining the ultrasonic echo position; />Is the time width of the ith ultrasonic echo, and determines the duration of the ultrasonic echo;is a rectangular function; />Is the number of ultrasonic echoes; t represents a continuous time for describing ultrasoundChanges in the wave echo signal over time;
finally, original ultrasonic detection data are obtained;
further, the original ultrasonic detection data are adjusted and calibrated by combining the environmental parameters of the mining conveyor, and the adjusted and calibrated ultrasonic detection data are obtained; the environmental parameters of the mining conveyor include temperature, humidity and dust concentration; the specific process is as follows:
firstly, preprocessing original ultrasonic detection data and environment parameter data, wherein the preprocessing comprises filtering and noise reduction to improve the data quality, performing model analysis on the preprocessed data to obtain the influence of the environment parameters on the original ultrasonic detection data, and adjusting and calibrating the original ultrasonic detection data according to an analysis result;
according to the known physical principles and the characteristics of the ultrasonic technology, how different environmental parameters affect the ultrasonic signal is analyzed theoretically, for example, how high humidity affects the propagation speed and attenuation of the ultrasonic signal, or how dust affects the scattering and absorption of the ultrasonic signal;
an environmental impact evaluation model set is constructed, and the impact relationship between environmental parameters and original ultrasonic detection data is analyzed, specifically:
a temperature influence model describing the influence of temperature on the propagation speed of an ultrasonic signal:
，
wherein,the propagation speed of the ultrasonic signal after the temperature influence is considered; />Is the reference temperature->The propagation speed of the ultrasonic signal; />Is the current ambient temperature; />Is a reference temperature; />Is the temperature primary coefficient; />Is a temperature quadratic coefficient for describing the nonlinear effect of temperature variation on the propagation speed of the ultrasonic signal;
humidity influence model, describing the influence of humidity on the propagation speed of ultrasonic signals:
，
wherein,the propagation speed of the ultrasonic signal is considered after the influence of humidity; />Is the current ambient humidity; />Is the reference humidity; />Is the humidity primary coefficient; />Is a humidity secondary coefficient describing the nonlinear effect of humidity variation on the propagation speed of the ultrasonic signal;
dust influence model, dust concentration can influence ultrasonic signal's intensity through the attenuation coefficient:
，
wherein,the intensity of the ultrasonic signal after the influence of dust concentration is considered; />The intensity of the ultrasonic signal when no dust exists; />Is the dust concentration; />Is the primary attenuation coefficient of dust concentration; />The secondary attenuation coefficient of the dust concentration is used for describing the nonlinear influence of the dust concentration on the intensity of an ultrasonic signal; />Is the propagation distance of the ultrasonic signal.
The collected environmental parameters are applied to the models of the environmental impact assessment model set to estimate the actual impact of the environmental parameters on the raw ultrasonic detection data, and the corresponding environmental parameter models are applied to adjust the raw ultrasonic detection data to compensate for the impact of the environmental parameters, for example, to adjust the propagation speed of the ultrasonic signal according to the current temperature and humidity, and to adjust the intensity of the ultrasonic signal according to the dust concentration.
The adjusted and calibrated ultrasonic detection data are obtained through the process.
According to the invention, the original ultrasonic detection data is adjusted and calibrated by combining an ultrasonic technology with environmental parameters, so that the accuracy of a detection result is improved; the introduced overlapped echo separation technology effectively separates and analyzes overlapped ultrasonic echoes, thereby improving the capability of detecting longitudinal tearing; the influence of environmental parameters on the original ultrasonic detection data is analyzed by constructing an environmental influence evaluation model set, so that more accurate ultrasonic detection data is obtained, and an accurate data basis is provided for longitudinal tearing detection.
S2, preprocessing the adjusted and calibrated ultrasonic detection data, extracting time domain features and frequency domain features of the preprocessed ultrasonic detection data to obtain a comprehensive feature set, optimizing the comprehensive feature set to obtain a final feature set, analyzing by using a longitudinal tearing intelligent recognition algorithm based on the final feature set, and judging whether the conveyor belt has longitudinal tearing or not;
firstly, standardizing the regulated and calibrated ultrasonic detection data, removing noise and non-target frequency components from the standardized ultrasonic detection data by using a digital filter, purifying signals, highlighting data characteristics possibly related to tearing of a conveyor belt, and obtaining preprocessed ultrasonic detection data; the use of a digital filter to remove noise and non-target frequency components is a well known technique for those skilled in the art and will not be described in detail herein; and respectively extracting the time domain features and the frequency domain features of the preprocessed ultrasonic detection data by using a measuring method and Fourier transformation, integrating the time domain features and the frequency domain features into a comprehensive feature set, optimizing the comprehensive feature set by using a feature selection algorithm, removing redundant and unimportant features, and ensuring that the final feature set has the highest efficiency and accuracy for longitudinal tearing detection. The measurement method and the feature selection algorithm adopted are all the prior art.
Further, deep analysis is carried out on the final feature set by utilizing a longitudinal tearing intelligent recognition algorithm, the longitudinal tearing intelligent recognition algorithm adopts a probability-based classification method, and the probability that each feature element belongs to a longitudinal tearing type is calculated by combining the feature data of the final feature set, so that the specific implementation process is as follows:
firstly, carrying out self-adaptive adjustment on characteristic elements by using a tearing characteristic self-adaptive algorithm based on a final characteristic set, wherein the tearing characteristic self-adaptive algorithm can adapt to the characteristics and environmental conditions of different conveying belts, and the adaptability and the flexibility of the tearing characteristic self-adaptive algorithm are improved; the tearing characteristic self-adaptive algorithm enables the data to be more suitable for subsequent probability estimation by dynamically adjusting characteristic elements, and the implementation formula is as follows:
，
wherein,is the final feature set comprising a plurality of feature elements +.>，/>Is the number of characteristic elements; />、/>、/>Is +.>The coefficient vector with the same dimension is used for adjusting the processing mode of each characteristic element; />Is a weight vector for weighting the contribution of each feature element, obtained through expert experience; />Element-by-element multiplication of the representation vector; />Is a small constant with a value range of [10 ] -20 ,10 -17 ]For ensuring the stability of the logarithmic function. The formula firstly carries out square and logarithmic transformation on each characteristic element, and highlights the nonlinear relation among the characteristic elements; then, use the weight vector +.>The importance of each transformed feature element is adjusted, and feature elements which are more important for probability estimation are emphasized; finally throughCombining the adjusted characteristic elements to form a comprehensive adjusted characteristic，/>Contains information of all feature elements before adjustment and is expressed in a way that is more suitable for probability estimation.
The tearing characteristic self-adaptive algorithm can dynamically adjust the characteristic processing mode according to the characteristics of each characteristic element and the influence on the final result, so that the accuracy of the subsequent probability estimation is improved, and the adaptability and the robustness of the tearing characteristic self-adaptive algorithm under different environments and conditions are improved;
then, probability estimation is carried out on the comprehensively adjusted characteristics, and the identification accuracy is improved;
，
wherein,the probability of longitudinal tearing of the conveyor belt is observed under the condition that all the comprehensively adjusted characteristics are observed; />Indicating that in case of a known tearing of the conveyor belt the i-th characteristic data +.>Probability of->；/>The probability of tearing of the conveyer belt is estimated according to expert experience; />The probability of the ith feature data is observed, whether tearing occurs or not is not considered, and the occurrence probability of the ith feature data under normal and abnormal conditions is reflected; />Is the total number of features; the process comprehensively considers the characteristics to evaluate the probability of longitudinal tearing of the conveyor belt, so that the accuracy of tearing detection is improved, and the health condition of the conveyor belt can be more comprehensively understood and predicted by combining the characteristics.
Further, in order to avoid instability of the feature data, a tearing probability optimization algorithm is introduced to optimize a probability estimation result; the tearing probability optimization algorithm adjusts and optimizes the probability obtained by the probability estimation by defining probability weights, so that the robustness and reliability of a final output result are ensured;
weighting of each feature：
，
Wherein,is directed to the firstiWeight adjustment parameters of individual features, +.>Is the firstiThe feature data;
further, the probability estimation is adjusted and optimized to obtain the value of the probability estimation after adjustment and optimization：
，
Through the adjustment optimization, the weight is used for adjusting the occurrence probability of each feature, so that the influence of unusual or less relevant features can be reduced, namely, errors caused by noise and abnormal values in original ultrasonic detection data are reduced, the accuracy of probability estimation is improved, the method is suitable for complex or variable environments such as the operation environment of a mining conveyor, the data quality can fluctuate due to various factors, and the actual situation can be reflected more accurately through weight adjustment, so that a more reliable diagnosis result is provided;
setting a threshold valueθFor distinguishing whether a longitudinal tear has occurred, the threshold is typically determined based on historical data and actual operating experience; if it isJudging that the longitudinal tearing occurs; otherwise, it is determined that this is not the case.
Selecting data related to the features with high tearing probability based on the analysis result, and determining the approximate position of the tear based on the data related to the features; based on the estimated probability values and the details of the relevant features, the severity of the tear and the nature of the tear can be inferred, and corresponding repair or inspection advice can be provided based on the location of the tear, the severity of the tear and the nature of the tear; the longitudinal tearing detection of the mining conveyor is realized. Details of the relevant features are: the frequency change of the preprocessed ultrasonic detection data can be related to the severity of tearing; the pre-processed ultrasonic inspection data shows different patterns or textures, such as size and shape, in the tear area to identify the tear characteristics.
According to the invention, the characteristic elements are dynamically adjusted through the tearing characteristic self-adaptive algorithm, so that the data is more suitable for subsequent probability estimation, and the adaptability and the robustness of the tearing characteristic self-adaptive algorithm under different environments and conditions are improved; and the probability of longitudinal tearing of the conveying belt is estimated by comprehensively considering a plurality of characteristic elements, so that the accuracy of tearing detection is improved. And the probability estimation after optimization is adjusted, so that the robustness and reliability of the result are further improved.
In summary, the mining conveyor system with the detection function and the operation method of the mining conveyor system with the detection function are completed.
According to the embodiment of the invention, the original ultrasonic detection data is adjusted and calibrated by combining an ultrasonic technology with environmental parameters, so that the accuracy of a detection result is improved; the introduced overlapped echo separation technology effectively separates and analyzes overlapped ultrasonic echoes, thereby improving the capability of detecting longitudinal tearing; analyzing the influence of environmental parameters on the original ultrasonic detection data by constructing an environmental influence evaluation model set to obtain more accurate ultrasonic detection data, and providing accurate data basis for longitudinal tearing detection; the embodiment of the invention also dynamically adjusts the characteristic elements through the tearing characteristic self-adaptive algorithm, so that the data is more suitable for subsequent probability estimation, and the adaptability and the robustness of the tearing characteristic self-adaptive algorithm under different environments and conditions are improved; and the probability of longitudinal tearing of the conveying belt is estimated by comprehensively considering a plurality of characteristic elements, so that the accuracy of tearing detection is improved. And the probability estimation after optimization is adjusted, so that the robustness and reliability of the result are further improved.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. Mining conveyor system with detect function, characterized by comprising the following parts:
the system comprises an ultrasonic detection unit, an environment adaptability adjustment unit, a data analysis processing unit, an intelligent response and adjustment unit and a self-maintenance unit;
the ultrasonic detection unit utilizes the ultrasonic sensor to transmit and receive ultrasonic signals, calculates the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, introduces an overlapping echo separation technology, obtains original ultrasonic detection data, and transmits the original ultrasonic detection data to the environment adaptability adjustment unit; simultaneously, the parameters of the ultrasonic waves are adjusted by utilizing the feedback data of the intelligent response and adjustment unit;
the environment adaptability adjusting unit is used for analyzing the relation between the original ultrasonic detection data and the environment parameters, adjusting and calibrating the original ultrasonic detection data, wherein the environment parameters comprise temperature, humidity and dust concentration, obtaining the adjusted and calibrated ultrasonic detection data, and transmitting the adjusted and calibrated ultrasonic detection data to the data analysis processing unit;
the data analysis processing unit is used for analyzing the adjusted and calibrated ultrasonic detection data, identifying whether the conveyor belt is longitudinally torn or not, obtaining a diagnosis result of the conveyor belt tearing, and transmitting the diagnosis result to the intelligent response and adjustment unit;
the intelligent response and adjustment unit is used for automatically adjusting the operation parameters and emergency response signals of the mining conveyor system based on the diagnosis result of the data analysis and processing unit, wherein the operation parameters comprise conveying speed, the adjusted operation parameters and the emergency response signals are obtained, the conveyor operation is adjusted according to the adjusted operation parameters, the safety alarm is triggered according to the adjusted emergency response signals, and meanwhile, the safety alarm is fed back to the ultrasonic detection unit;
the self-maintenance unit monitors the performance and health status of the mining conveyor system and implements predictive maintenance and fault diagnosis using machine learning techniques.
2. A method of operating a mining conveyor with a detection function, applied to the mining conveyor system with a detection function of claim 1, comprising the steps of:
s1, utilizing an ultrasonic sensor to transmit and receive ultrasonic signals, adopting a multi-factor determination method to calculate the pulse repetition frequency of ultrasonic pulses transmitted by the ultrasonic sensor, introducing an overlapped echo separation technology to obtain original ultrasonic detection data, and combining the environmental parameters of a mining conveyor to adjust and calibrate the original ultrasonic detection data to obtain the adjusted and calibrated ultrasonic detection data;
s2, preprocessing the adjusted and calibrated ultrasonic detection data, extracting time domain features and frequency domain features of the preprocessed ultrasonic detection data to obtain a comprehensive feature set, optimizing the comprehensive feature set to obtain a final feature set, analyzing by using a longitudinal tearing intelligent recognition algorithm based on the final feature set, and judging whether the conveyor belt is longitudinally torn or not.
3. The method for operating a mining conveyor with a detection function according to claim 2, characterized in that in step S1, it comprises in particular:
in the process of acquiring original ultrasonic detection data, when receiving the ultrasonic detection data, an overlapped echo separation technology is introduced to separate overlapped echoes, and the overlapped echo separation technology is specifically realized as follows: firstly, detecting whether ultrasonic echoes overlap or not by a signal analysis method, and when the ultrasonic echoes are detected to overlap, performing time-frequency analysis by utilizing short-time Fourier transform; extracting the center frequency, bandwidth, amplitude and phase of each ultrasonic echo by using an echo characteristic extraction method; finally, the overlapped ultrasonic echoes are separated and reconstructed after being absorbed by using a reconstruction formula; and finally obtaining the original ultrasonic detection data.
4. A method of operating a mining conveyor with detection as in claim 3 further comprising, in step S1:
when the original ultrasonic detection data are adjusted and calibrated, an environmental impact assessment model set is constructed to analyze the impact relationship between the environmental parameters and the original ultrasonic detection data.
5. The method of operating a mining conveyor with detection function according to claim 4, further comprising, in step S1:
the environmental impact assessment model set comprises a temperature impact model, a humidity impact model and a dust impact model; and applying the collected environmental parameters to an environmental impact assessment model set, estimating the actual impact of the environment on the ultrasonic detection data, and adjusting the original ultrasonic detection data according to the temperature impact model, the humidity impact model and the dust impact model to obtain the adjusted and calibrated ultrasonic detection data.
6. The method for operating a mining conveyor with a detection function according to claim 2, characterized in that in step S2, it comprises in particular:
the longitudinal tearing intelligent recognition algorithm adopts a probability-based classification method to calculate the probability that each sample belongs to a longitudinal tearing category, and the specific implementation process is as follows: firstly, carrying out self-adaptive adjustment on the characteristics by utilizing a tearing characteristic self-adaptive algorithm based on a final characteristic set to obtain the characteristics after comprehensive adjustment; then, probability estimation is carried out based on the comprehensively adjusted characteristics; further, a tearing probability optimization algorithm is introduced to optimize a probability estimation result, and a probability estimation value after adjustment and optimization is obtained; setting a threshold value for distinguishing whether longitudinal tearing occurs, and judging that longitudinal tearing occurs when the estimated probability value after adjustment and optimization is larger than the set threshold value; otherwise, it is determined that this is not the case.
7. The method of operating a mining conveyor with detection function according to claim 6, further comprising, in step S2:
and the tearing probability optimization algorithm adjusts and optimizes the probability estimation result by defining probability weights.
8. The method of operating a mining conveyor with detection function according to claim 2, characterized in that in step S2, it further comprises:
determining the position of the tear and deducing the severity of the tear and the characteristics of the tear based on the analysis result of the longitudinal tear intelligent identification algorithm; depending on the location of the tear, the severity of the tear, and the nature of the tear, repair or inspection advice is provided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410008349.3A CN117509067B (en) | 2024-01-04 | 2024-01-04 | Mining conveyor system with belt longitudinal tearing detection function and operation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410008349.3A CN117509067B (en) | 2024-01-04 | 2024-01-04 | Mining conveyor system with belt longitudinal tearing detection function and operation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117509067A true CN117509067A (en) | 2024-02-06 |
| CN117509067B CN117509067B (en) | 2024-03-22 |
Family
ID=89762972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410008349.3A Active CN117509067B (en) | 2024-01-04 | 2024-01-04 | Mining conveyor system with belt longitudinal tearing detection function and operation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117509067B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004250161A (en) * | 2003-02-19 | 2004-09-09 | Okabe Kikai Kogyo Kk | Abnormality detection device of conveyer belt |
| AU2009206205A1 (en) * | 2008-01-22 | 2009-07-30 | Barge's Belting Solution Pty Ltd | Method and apparatus for monitoring a conveyor belt |
| JP2011088724A (en) * | 2009-10-23 | 2011-05-06 | Bridgestone Corp | Vertical tear detecting device of conveyor belt |
| CN103213824A (en) * | 2013-04-26 | 2013-07-24 | 刘旭珍 | Belt anti-tear monitoring device and monitoring method |
| CN204124749U (en) * | 2014-07-26 | 2015-01-28 | 长治市同诚机械有限公司 | A kind of belt tearing detector |
| CN114751138A (en) * | 2022-03-09 | 2022-07-15 | 国家能源集团国源电力有限公司 | Belt longitudinal tearing monitoring system and conveying equipment |
| CN115180367A (en) * | 2022-08-06 | 2022-10-14 | 山西华智弘兴科技有限公司 | Belt transmission band foreign matter recognition device |
| CN115857402A (en) * | 2022-12-06 | 2023-03-28 | 中煤科工集团上海有限公司 | Intelligent control system for coal conveying of coal mine |
-
2024
- 2024-01-04 CN CN202410008349.3A patent/CN117509067B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004250161A (en) * | 2003-02-19 | 2004-09-09 | Okabe Kikai Kogyo Kk | Abnormality detection device of conveyer belt |
| AU2009206205A1 (en) * | 2008-01-22 | 2009-07-30 | Barge's Belting Solution Pty Ltd | Method and apparatus for monitoring a conveyor belt |
| JP2011088724A (en) * | 2009-10-23 | 2011-05-06 | Bridgestone Corp | Vertical tear detecting device of conveyor belt |
| CN103213824A (en) * | 2013-04-26 | 2013-07-24 | 刘旭珍 | Belt anti-tear monitoring device and monitoring method |
| CN204124749U (en) * | 2014-07-26 | 2015-01-28 | 长治市同诚机械有限公司 | A kind of belt tearing detector |
| CN114751138A (en) * | 2022-03-09 | 2022-07-15 | 国家能源集团国源电力有限公司 | Belt longitudinal tearing monitoring system and conveying equipment |
| CN115180367A (en) * | 2022-08-06 | 2022-10-14 | 山西华智弘兴科技有限公司 | Belt transmission band foreign matter recognition device |
| CN115857402A (en) * | 2022-12-06 | 2023-03-28 | 中煤科工集团上海有限公司 | Intelligent control system for coal conveying of coal mine |
Non-Patent Citations (2)
| Title |
|---|
| 李亭等: "水平井分段压裂各段产能评价技术研究进展", 《科学技术与工程》, vol. 23, no. 21, 28 July 2023 (2023-07-28), pages 8916 - 8927 * |
| 王俊青: "矿用皮带运输机故障检测方案设计", 《自动化应用》, no. 12, 25 December 2019 (2019-12-25), pages 87 - 89 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117509067B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3085937B1 (en) | System and method for detecting vehicle system faults | |
| US20200233397A1 (en) | System, method and computer-accessible medium for machine condition monitoring | |
| US4459851A (en) | Method and device for the localization and analysis of sound emissions | |
| TWI587294B (en) | Detection method of abnormal sound of apparatus and detection device | |
| JP5145417B2 (en) | Signal determination method, signal determination apparatus, program, and signal determination system | |
| Yang et al. | A novel feature representation method based on original waveforms for acoustic emission signals | |
| US10648951B2 (en) | Classification of ultrasonic indications using pattern recognition | |
| GB2394549A (en) | Determining internal pipeline condition by analysing acoustical vibrations generated by a pig passing through the pipeline | |
| CA2616900C (en) | Method for error-free checking of tubes for surface faults | |
| Nazarko et al. | Application of artificial neural networks in the damage identification of structural elements | |
| US7079959B2 (en) | High-resolution intelligent rotor machine diagnostic system and method | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| KR20090015596A (en) | Method for structural health monitoring using ultrasonic guided wave | |
| US20210149387A1 (en) | Facility failure prediction system and method for using acoustic signal of ultrasonic band | |
| CN114486259A (en) | Signal processing method of distributed optical fiber acoustic sensing system for optimizing variational modal decomposition | |
| CN117509067B (en) | Mining conveyor system with belt longitudinal tearing detection function and operation method | |
| JP2002228575A (en) | Corrosion diagnostic system for tank steel plate | |
| Quy et al. | Pipeline leak detection using acoustic emission and state estimate in feature space | |
| US11567024B2 (en) | System and method for detection of concentration of micro and nano particles in a fluid environment | |
| CN116609440B (en) | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation | |
| US20040143398A1 (en) | Method and system for monitoring vibration and/or mechanical waves in mechanical systems | |
| US20040130458A1 (en) | Wireless sensors for system monitoring and diagnostics | |
| US20240003854A1 (en) | Method for automatically identifying an acoustic source from a produced acoustic signal | |
| EP1177433A1 (en) | Roller mechanism using an array of ultrasound elements to interrogate wood properties | |
| CN1415959A (en) | Method of real time tracking bottom echo for ultrasonic crank detection gate |
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 |