CN116754234A - Automatic printing production equipment running state detection method - Google Patents
Automatic printing production equipment running state detection method Download PDFInfo
- Publication number
- CN116754234A CN116754234A CN202311034900.3A CN202311034900A CN116754234A CN 116754234 A CN116754234 A CN 116754234A CN 202311034900 A CN202311034900 A CN 202311034900A CN 116754234 A CN116754234 A CN 116754234A
- Authority
- CN
- China
- Prior art keywords
- fault
- target
- component
- vibration
- sound
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 73
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 230000001133 acceleration Effects 0.000 claims abstract description 106
- 230000005236 sound signal Effects 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 60
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 26
- 238000006243 chemical reaction Methods 0.000 claims abstract description 17
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000010606 normalization Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 abstract description 10
- 238000004458 analytical method Methods 0.000 description 18
- 230000002159 abnormal effect Effects 0.000 description 10
- 230000001419 dependent effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
Abstract
The invention relates to the technical field of data processing, in particular to a method for detecting the running state of automatic printing production equipment. The method comprises the following steps: obtaining vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the running process; modal decomposition and screening to obtain at least two target intrinsic modal components; performing numerical symbol conversion to obtain a signal component code; determining fault information entropy of each target eigenmode component; further determining a vibration fault impact factor of the vibration signal and a sound fault impact factor of the sound signal; obtaining the fault degree of each time point according to the vibration fault influence factors, the sound fault influence factors and the gear accelerations of all time points; and detecting the running state of the printing production equipment according to the fault degree of the current time point to obtain a detection result. The invention can effectively improve the detection effect of the running state of the printing production equipment.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for detecting the running state of automatic printing production equipment.
Background
The printing production equipment is a mechanical equipment for transferring image and text information onto the surface of a printing object, specifically, a printing machine, for example, because the structure of the printing machine is complex, the printing speed is high, and any weak fault of a transmission part can lead to the large-amplitude sliding of the quality of a printing product, so that the printed product has the phenomena of misprinting, missing printing and the like. Therefore, it is important to detect the operation state of the printing production equipment.
In the related art, vibration signals in the running process of the printing production equipment are decomposed and processed through an empirical mode, then the vibration signals are analyzed according to the generated intrinsic mode components, and the running state of the printing production equipment is determined according to an analysis result.
Disclosure of Invention
In order to solve the technical problem that the fault characteristics of the printing production equipment in the operation process cannot be accurately determined in the related art, so that the detection effect on the operation state is poor, the invention provides an automatic printing production equipment operation state detection method, which adopts the following technical scheme:
the invention provides a method for detecting the running state of automatic printing production equipment, which comprises the following steps:
obtaining vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the running process; respectively carrying out modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components;
performing numerical symbol conversion on the longitudinal coordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component for coding; obtaining fault information entropy of each target eigenmode component according to the signal component codes;
determining vibration fault influence factors of the vibration signals according to the frequency and fault information entropy of the vibration signals corresponding to all target eigenmode components, and determining sound fault influence factors of the sound signals according to the frequency and fault information entropy of the sound signals corresponding to all target eigenmode components; obtaining the fault degree of each time point according to the vibration fault influence factor, the sound fault influence factor and the gear acceleration of all time points;
and detecting the running state of the printing production equipment according to the fault degree of the current time point to obtain a detection result.
Further, the performing modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components respectively includes:
performing empirical mode decomposition on the vibration signal to obtain vibration eigenmode components of the vibration signal, and determining a first number of preset vibration eigenmode components as target eigenmode components of the vibration signal;
performing empirical mode decomposition on the sound signal to obtain sound eigenmode components of the sound signal, and determining a first preset second number of sound eigenmode components as target eigenmode components of the sound signal; wherein the preset first number and the preset second number are equal to or less than 4.
Further, the performing numerical symbol conversion on the ordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component code includes:
respectively calculating the mean value of the longitudinal coordinate values of each target eigenmode component at all time points to obtain a reference value of the corresponding target eigenmode component;
comparing the ordinate value of each time point of any target eigenmode component with a reference value, adjusting the ordinate value to 1 when the ordinate value is larger than the reference value of the target eigenmode component, and adjusting the ordinate value to 0 when the ordinate value is smaller than or equal to the reference value of the target eigenmode component, so as to obtain the binary code of the target eigenmode component;
dividing the binary codes according to preset lengths to obtain code segments, carrying out binary conversion on the binary codes in each code segment, converting the binary codes into decimal codes, and combining the decimal codes according to time sequence to obtain signal component codes.
Further, the obtaining the fault information entropy of each target eigenmode component according to the signal component code includes:
and calculating the information entropy of all coding values in the signal component codes corresponding to each target eigenmode component as the fault information entropy of the target eigenmode component.
Further, the determining a vibration fault influence factor of the vibration signal according to the frequency and the fault information entropy of the vibration signal corresponding to all the target eigenmode components includes:
respectively carrying out normalization processing on the frequency of each target eigen mode component in the vibration signal to obtain a vibration component weight;
calculating the product of the vibration component weight of each target eigenmode component in the vibration signal and the fault information entropy to serve as a fault influence index of the corresponding target eigenmode component;
and taking the average normalized value of fault influence indexes of all target eigenmode components in the vibration signal as a vibration fault influence factor of the vibration signal.
Further, the determining the sound fault influencing factor of the sound signal according to the frequency and fault information entropy of the sound signal corresponding to all the target eigenmode components includes:
respectively carrying out normalization processing on the frequency of each target eigen mode component in the sound signal to obtain a sound component weight;
calculating the product of the sound component weight of each target eigenmode component in the sound signal and fault information entropy to serve as a fault influence index of the corresponding target eigenmode component;
and taking the average normalized value of fault influence indexes of all target eigenmode components in the sound signal as a sound fault influence factor of the sound signal.
Further, the obtaining the fault degree of each time point according to the vibration fault influence factor, the sound fault influence factor and the gear acceleration of all time points includes:
determining maximum and minimum values of gear acceleration at all time points, and taking the average value of the absolute value of the difference between the maximum value and the preset standard acceleration and the absolute value of the difference between the minimum value and the preset standard acceleration as a first acceleration influence coefficient;
calculating the average value of the gear acceleration at all time points as an acceleration average value, and taking the absolute value of the difference between the acceleration average value and a preset standard acceleration as a second acceleration influence coefficient;
obtaining a target acceleration coefficient according to the first acceleration influence coefficient and the second acceleration influence coefficient, wherein the first acceleration influence coefficient and the target acceleration coefficient are in positive correlation, the second acceleration influence coefficient and the target acceleration coefficient are in positive correlation, and the value of the target acceleration coefficient is a normalized value;
calculating the product of the vibration fault influence factor and the sound fault influence factor as an operation fault coefficient;
and taking the normalized value of the product of the operation fault coefficient and the target acceleration coefficient as the fault degree.
Further, the detecting the operation state of the printing production equipment according to the fault degree of the current time point to obtain a detection result includes:
when the fault degree of the current time point is greater than a preset degree threshold value, determining that the detection result is in a fault running state;
and when the fault degree of the current time point is smaller than or equal to a preset degree threshold value, determining that the detection result is in a normal running state.
The invention has the following beneficial effects:
the embodiment of the invention analyzes the characteristics of complex structure and high-speed operation of the printing production equipment, and analyzes faults by acquiring vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the operation process and combining the vibration signals, the sound signals and the gear acceleration; in the analysis process, respectively carrying out modal decomposition on the vibration signal and the sound signal and determining a target intrinsic modal component, wherein the target intrinsic modal component is obtained through modal decomposition and screening, so that the background characteristic and the local noise interference can be effectively removed, and the main abnormal state characteristics of the vibration signal and the sound signal are reserved; the longitudinal coordinate values of the target eigenmode components at different time points are subjected to numerical value symbol conversion, faults are analyzed by using fault information entropy, vibration signals and sound signals on time sequences can be rapidly analyzed by combining the characteristics of high frequency, short period and irregularity of abnormal faults, timeliness of signal analysis is guaranteed, and then the current state is analyzed by combining gear acceleration at all time points to obtain fault degree, so that fault conditions in the operation process of printing production equipment can be effectively analyzed, the fault degree can accurately and objectively represent the fault conditions of bearings and gears in the operation process of the printing production equipment, and accuracy of fault feature analysis of the bearings and gears in the printing production equipment is improved; the operation state of the printing production equipment at each time point is detected through the fault degree, so that a detection result is obtained, the reliability of operation state detection can be effectively improved, and the operation state detection effect is enhanced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting the running state of an automatic printing production device according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating conversion of signal component codes according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to the specific implementation, structure, features and effects of an operation state detection method of an automatic printing production device according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
An embodiment of an operation state detection method of automatic printing production equipment comprises the following steps:
the following specifically describes a specific scheme of the running state detection method of the automatic printing production equipment provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting an operation state of an automatic printing production device according to an embodiment of the present invention is shown, where the method includes:
s101: obtaining vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the running process; and respectively carrying out modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components.
It can be understood that the invention monitors the running state of the printing production equipment mainly through the vibration, running sound and acceleration of the gear, so that a corresponding suitable vibration detection device, a sound sensor and an acceleration sensor are required to be installed on the printing production equipment, each data is acquired through a data acquisition card, and the sampling rate which is higher than twice the highest frequency of the signal is generally adopted during acquisition so as to avoid signal distortion. That is, the invention can set a fixed time period to periodically collect vibration signals, sound signals and gear accelerations at different time points, and the collection time of the invention can be adjusted according to actual detection requirements without limitation.
The printing production device may be, for example, a printer, and it is understood that when the printer fails in the printing process, the printing effect of the printed product can be directly or indirectly affected, and production accidents such as displacement, dislocation or missing printing are caused, so that the detection of the printing production device in the running process is crucial.
In the embodiment of the invention, a certain gear fixed in the printing production equipment can be specifically selected, and the running acceleration of the gear is continuously monitored to obtain the gear acceleration.
Further, in some embodiments of the present invention, performing modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components, respectively, includes: performing empirical mode decomposition on the vibration signal to obtain vibration eigenmode components of the vibration signal, and determining a first number of vibration eigenmode components preset before as target eigenmode components of the vibration signal; empirical mode decomposition is carried out on the sound signal, sound eigenmode components of the sound signal are obtained, and a first preset second number of sound eigenmode components are determined to be target eigenmode components of the sound signal; wherein the preset first number and the preset second number are less than or equal to 4.
The empirical mode decomposition (Empirical Mode Decomposition, EMD) is a time-frequency processing method of an adaptive signal, and is not described herein in detail, by decomposing a complex signal into a limited number of eigenmode components (Intrinsic Mode Function, IMF) to analyze the complex signal.
In the embodiment of the invention, the vibration signal and the sound signal can be subjected to empirical mode decomposition respectively to obtain the vibration eigenmode component of the vibration signal and the sound eigenmode component of the sound signal. It can be understood that, among the eigenmode components decomposed by the empirical mode decomposition, the earlier the corresponding component frequency is.
In the scene of the invention, as the printing production equipment can cause high vibration frequency during abnormal operation, the operation sound is harsher, namely fault information is usually contained in high-frequency parts of vibration signals and sound signals, the high-frequency parts of the signals are mainly concentrated in the first few eigenmode components, and the first few eigenmode components are usually left for characteristic extraction; the residual eigenmode components are mainly low-frequency noise interference, and the last few residual eigenmode components can be removed, so that the characteristic of an operation fault can be effectively extracted, and therefore, the method takes the preset first number of vibration eigenmode components as target eigenmode components of vibration signals, and the preset second number of sound eigenmode components as target eigenmode components of sound signals, wherein the preset first number and the preset second number are smaller than or equal to 4.
That is, the present invention may set a preset first number and a preset second number according to an actual detection requirement, and optionally, the preset first number and the preset second number are both 4, and take this value as a specific example, the first 4 vibration eigenmode components obtained by decomposing the vibration signal through an empirical mode are taken as target eigenmode components of the vibration signal, and the remaining vibration eigenmode components are taken as redundant components to be removed, and similarly, the target eigenmode components of the first 4 sound signals are obtained, and the remaining sound eigenmode components are taken as redundant components to be removed.
Of course, in other embodiments of the present invention, the preset first number and the preset second number may also be set to other values, for example, the preset first number is 2, and the preset second number is 3, which is not limited.
S102: performing numerical symbol conversion on the longitudinal coordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component for coding; and obtaining fault information entropy of each target eigenmode component according to the signal component codes.
Further, in some embodiments of the present invention, performing numerical symbol conversion on the ordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component code includes: respectively calculating the mean value of the longitudinal coordinate values of each target eigenmode component at all time points to obtain a reference value of the corresponding target eigenmode component; comparing the ordinate value of each time point of any target eigenmode component with a reference value, adjusting the ordinate value to 1 when the ordinate value is larger than the reference value of the target eigenmode component, and adjusting the ordinate value to 0 when the ordinate value is smaller than or equal to the reference value of the target eigenmode component, so as to obtain the binary code of the target eigenmode component; dividing the binary codes according to preset lengths to obtain code segments, carrying out binary conversion on the binary codes in each code segment, converting the binary codes into decimal codes, and combining the decimal codes according to time sequence to obtain signal component codes.
In the embodiment of the invention, the mean value of the ordinate value of each target eigenmode component at all time points is calculated, the mean value is used as the reference value of the corresponding target eigenmode component, the ordinate value of any target eigenmode component at any time point is compared with the reference value, the comparison process can be a difference process, namely, the difference value between the ordinate value and the reference value is calculated, when the difference value is larger than 0, namely, when the ordinate value is larger than the reference value of the target eigenmode component, the ordinate value is adjusted to be 1, and when the difference value is smaller than or equal to 0, namely, the ordinate value is smaller than or equal to the reference value of the target eigenmode component, the ordinate value is adjusted to be 0, therefore, after each target eigenmode component is processed, the time sequence binary code is obtained, and the binary code is composed of 0 and 1, wherein each value can represent that the ordinate value of the corresponding time point is larger than the mean value of the target eigenmode component, and the time sequence is not limited.
According to the embodiment of the invention, the ordinate values of the target eigenmode components of all time points are replaced in a mean value mode, so that the ordinate values of different time points are simplified while the analysis effect of the target eigenmode components is maintained, the complexity of analysis is further simplified, the timeliness of data analysis is improved while the data analysis effect is ensured, and the running state of printing production equipment can be obtained in time.
The preset length is the coding length in the coding section, and in the embodiment of the invention, the preset length can be set to be 3, namely, 3 continuous codes form one coding section, and decimal conversion is performed on the codes in the coding section to obtain the signal component codes. FIG. 2 is a schematic diagram of signal component coding conversion according to an embodiment of the present invention; in fig. 2, the code segment "010" is converted into "2" through decimal system, and of course, the present invention can also set different preset lengths according to actual requirements, which is not limited.
Further, in some embodiments of the present invention, obtaining the fault information entropy of each target eigenmode component according to the signal component coding includes: and calculating the information entropy of all coding values in the signal component codes corresponding to each target eigenmode component as the fault information entropy of the target eigenmode component.
In the embodiment of the present invention, the probability of each coding value in the signal component coding may be counted in advance, and then, according to all the coding value probabilities, the fault information entropy of the target intrinsic mode component is calculated by using an information entropy formula, where the corresponding calculation formula may specifically be, for example:
in the method, in the process of the invention,fault information entropy representing the i-th target eigenmode component, i representing the index of the target eigenmode component, M representing the total number of types of encoded values, i representing the type index of encoded values,/being the index of the type of encoded values>Representing the probability of the i-th class of encoded values, log represents a logarithmic function.
In the embodiment of the present invention, since the information entropy formula is a calculation formula well known in the art, and will not be described in detail, the complexity of each target eigen mode component can be calculated by the information entropy formula, and as the printer fault state is different, the corresponding vibration signal and each target eigen mode component in the sound signal will also show different data relationships, including both the size relationship and the data change trend, and the characteristics of such a group of data can be described by the information entropy.
In the embodiment of the invention, after the fault information entropy of each target eigenmode component is obtained, further fault analysis can be performed according to the fault information entropy.
S103: determining vibration fault influence factors of the vibration signals according to the frequency and fault information entropy of the vibration signals corresponding to all target eigenmode components, and determining sound fault influence factors of the sound signals according to the frequency and fault information entropy of the sound signals corresponding to all target eigenmode components; and obtaining the fault degree of each time point according to the vibration fault influence factor, the sound fault influence factor and the gear acceleration of all time points.
Further, in some embodiments of the present invention, determining a vibration fault impact factor of the vibration signal according to frequencies and fault information entropy of the vibration signal corresponding to all target eigenmode components includes: respectively carrying out normalization processing on the frequency of each target eigen mode component in the vibration signal to obtain a vibration component weight; calculating the product of the vibration component weight value and the fault information entropy of each target eigenmode component in the vibration signal as a fault influence index of the corresponding target eigenmode component; and taking the average normalized value of the fault influence indexes of all the target eigenmode components in the vibration signal as a vibration fault influence factor of the vibration signal.
In the embodiment of the invention, as the vibration frequency is higher, more noise characteristics in the corresponding component signals can be represented, therefore, the vibration component weight can be obtained by normalizing according to the vibration frequency, the vibration component weight can represent the weight of each vibration component, the product of the vibration component weight of each target intrinsic mode component in the vibration signal and the fault information entropy is calculated to be used as a fault influence index of the corresponding target intrinsic mode component, and then the mean normalized value of the fault influence indexes of all the target intrinsic mode components in the vibration signal is calculated to be used as the vibration fault influence factor of the vibration signal.
The larger the vibration fault influence factor is, the more high-frequency components in the corresponding vibration signals are represented, namely, the more abnormal vibration conditions are, and the more abnormal vibration states can be further represented.
Similarly, processing the sound signal to obtain a sound fault influence factor of the sound signal, and in some embodiments of the present invention, determining the sound fault influence factor of the sound signal according to frequencies and fault information entropy of the sound signal corresponding to all target eigenmode components includes: respectively carrying out normalization processing on the frequency of each target eigen mode component in the sound signal to obtain a sound component weight; calculating the product of the sound component weight value and the fault information entropy of each target eigenmode component in the sound signal as a fault influence index of the corresponding target eigenmode component; and taking the average normalized value of fault influence indexes of all target eigenmode components in the sound signal as a sound fault influence factor of the sound signal. Since the processing procedure of the sound signal is similar to that of the vibration signal, the description thereof will be omitted.
Further, in some embodiments of the present invention, obtaining the degree of failure at each time point based on the vibration failure influence factor, the sound failure influence factor, and the gear acceleration at all time points includes: determining maximum and minimum values of gear acceleration at all time points, and taking the average value of the absolute value of the difference between the maximum value and the preset standard acceleration and the absolute value of the difference between the minimum value and the preset standard acceleration as a first acceleration influence coefficient; calculating the average value of the gear acceleration at all time points as an acceleration average value, and taking the absolute value of the difference between the acceleration average value and a preset standard acceleration as a second acceleration influence coefficient; obtaining a target acceleration coefficient according to the first acceleration influence coefficient and the second acceleration influence coefficient, wherein the first acceleration influence coefficient and the target acceleration coefficient have positive correlation, the second acceleration influence coefficient and the target acceleration coefficient have positive correlation, and the value of the target acceleration coefficient is a normalized value; calculating the product of the vibration fault influence factor and the sound fault influence factor as an operation fault coefficient; and taking the normalized value of the product of the operation fault coefficient and the target acceleration coefficient as the fault degree.
The positive correlation relationship indicates that the dependent variable increases along with the increase of the independent variable, the dependent variable decreases along with the decrease of the independent variable, and the specific relationship can be multiplication relationship, addition relationship, idempotent of an exponential function and is determined by practical application; the negative correlation indicates that the dependent variable decreases with increasing independent variable, and the dependent variable increases with decreasing independent variable, which may be a subtraction relationship, a division relationship, or the like, and is determined by the actual application.
In some embodiments of the present invention, the calculation formula of the fault degree may specifically be, for example:
in the method, in the process of the invention,indicating the degree of failure at the h-th time point, h indicating the index of the time point, +.>The average value of the acceleration is represented,indicating a preset standard acceleration->Represents the maximum value of the gear acceleration at all time points, +.>Representing the minimum value of the gear acceleration at all time points, < >>Vibration failure influence factor indicating the h time point, +.>A sound malfunction influencing factor indicating the h time point,/->The normalization process is represented. In some embodiments of the invention, the normalization process may be, for example, specifically a maximum-minimum normalization process, and the normalization in the subsequent steps is allThe maximum and minimum normalization processing may be adopted, and in other embodiments of the present invention, other normalization methods may be selected according to a specific numerical range, which will not be described herein.
The preset standard acceleration is the acceleration of the gear under the standard condition, and it can be understood that the rotation speed of the gear should be kept unchanged in the normal printing process, that is, the preset standard acceleration can be specifically 0, and of course, when the machine is started, and when the machine is shut down, the corresponding preset standard acceleration can be set for different periods, so that the machine is not limited.
In the method, in the process of the invention,representing a first acceleration influence factor,/->The second acceleration influence coefficient is represented, the target acceleration coefficient is obtained according to the first acceleration influence coefficient and the second acceleration influence coefficient, as the maximum value and the minimum value of the acceleration at all time points represent extreme value conditions of gear operation at all time points, the greater the difference between the maximum value and the minimum value and the preset standard acceleration is, the more unstable the printing production equipment is in the operation process, the greater the possibility of faults is represented, the greater the difference between the acceleration mean and the preset standard acceleration is, the greater the possibility of faults is represented as the whole condition is represented, therefore, the target acceleration coefficient is calculated by calculating the score normalization values of the first acceleration influence coefficient and the second acceleration influence coefficient, and the greater the target acceleration coefficient is, the greater the fault possibility is.
In the method, in the process of the invention,the operation fault coefficient representing the h time point can represent that the more the corresponding high-frequency vibration information and high-frequency sound information are, namely the more the signals containing faults are, the greater the fault possibility is, because the vibration fault influence factor and the sound fault influence factor are larger. Thereby, the fault is obtained by calculating the normalized value of the product of the operational fault coefficient and the target acceleration coefficientThe degree, the fault degree can effectively represent the fault condition in the operation process of the printing production equipment.
S104: and detecting the running state of the printing production equipment according to the fault degree of the current time point to obtain a detection result.
Further, in some embodiments of the present invention, detecting the operation state of the printing production device according to the fault degree of the current time point to obtain a detection result includes: when the fault degree of the current time point is greater than a preset degree threshold value, determining that the detection result is in a fault running state; and when the fault degree of the current time point is smaller than or equal to a preset degree threshold value, determining that the detection result is in a normal running state.
The preset degree threshold is a threshold of a fault degree, and in the embodiment of the invention, the detection result can be determined to be in a fault running state when the fault degree of the current time point is greater than the preset degree threshold, and the detection result can be determined to be in a normal running state when the fault degree of the current time point is less than or equal to the preset degree threshold. Alternatively, the preset degree threshold may specifically be, for example, not limited thereto.
After the detection result is determined to be the fault running state, the invention can use a machine learning mode to predict and judge the fault position of the printing production equipment by combining the vibration signal, the sound signal and the acceleration of the gear corresponding to the continuous fault running state, namely, the vibration signal, the sound signal and the acceleration of the gear can be input into a pre-trained big data neural network model to output the fault position of the printing production equipment through model analysis, and carry out fault alarm and automatic correction according to the fault degree, without limitation.
The embodiment of the invention analyzes the characteristics of complex structure and high-speed operation of the printing production equipment, and analyzes faults by acquiring vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the operation process and combining the vibration signals, the sound signals and the gear acceleration; in the analysis process, respectively carrying out modal decomposition on the vibration signal and the sound signal and determining a target intrinsic modal component, wherein the target intrinsic modal component is obtained through modal decomposition and screening, so that the background characteristic and the local noise interference can be effectively removed, and the main abnormal state characteristics of the vibration signal and the sound signal are reserved; the longitudinal coordinate values of the target eigenmode components at different time points are subjected to numerical value symbol conversion, faults are analyzed by using fault information entropy, vibration signals and sound signals on time sequences can be rapidly analyzed by combining the characteristics of high frequency, short period and irregularity of abnormal faults, timeliness of signal analysis is guaranteed, and then the current state is analyzed by combining gear acceleration at all time points to obtain fault degree, so that fault conditions in the operation process of printing production equipment can be rapidly and effectively analyzed, fault conditions of bearings and gears in the operation process of the printing production equipment can be accurately and timely represented, and accuracy of fault feature analysis of the bearings and the gears in the printing production equipment is improved; the operation state of the printing production equipment at each time point is detected through the fault degree, so that a detection result is obtained, the reliability of operation state detection can be effectively improved, and the operation state detection effect is enhanced.
An embodiment of a fault degree analysis method for automatic printing production equipment comprises the following steps:
because the printing production equipment has high operation precision requirement, tiny operation faults can be more sensitively reflected in products printed by the printing production equipment, in the related art, by acquiring vibration signals of the printing production equipment, carrying out empirical mode decomposition on the vibration signals, respectively analyzing intrinsic mode functions obtained by the empirical mode decomposition at each moment, and determining the fault degree of the printing production equipment according to analysis results, in this way, the accuracy and analysis effect are not ideal when the fault degree is analyzed due to the characteristics of high frequency, short period and irregularity of signals corresponding to abnormal faults.
In order to solve the technical problem, the embodiment provides a failure degree analysis method for an automatic printing production device, which includes:
s201: obtaining vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the running process; and respectively carrying out modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components.
S202: performing numerical symbol conversion on the longitudinal coordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component for coding; and obtaining fault information entropy of each target eigenmode component according to the signal component codes.
S203: determining vibration fault influence factors of the vibration signals according to the frequency and fault information entropy of the vibration signals corresponding to all target eigenmode components, and determining sound fault influence factors of the sound signals according to the frequency and fault information entropy of the sound signals corresponding to all target eigenmode components; and obtaining the fault degree of each time point according to the vibration fault influence factor, the sound fault influence factor and the gear acceleration of all time points.
Since the specific implementation process of steps S201 to S203 is already described in detail in the above-mentioned method for detecting the running state of an automatic printing production apparatus, no detailed description is given.
In summary, the invention analyzes faults by acquiring vibration signals, sound signals and gear accelerations of the printing production equipment at different time points in the running process and combining the vibration signals, the sound signals and the gear accelerations; in the analysis process, respectively carrying out modal decomposition on the vibration signal and the sound signal and determining a target intrinsic modal component, wherein the target intrinsic modal component is obtained through modal decomposition and screening, so that the background characteristic and the local noise interference can be effectively removed, and the main abnormal state characteristics of the vibration signal and the sound signal are reserved; the longitudinal coordinate values of the target eigenmode components at different time points are subjected to numerical value symbol conversion, faults are analyzed by using fault information entropy, vibration signals and sound signals on time sequences can be rapidly analyzed by combining the characteristics of high frequency, short period and irregularity of abnormal faults, timeliness of signal analysis is guaranteed, and then the current state is analyzed by combining gear acceleration at all time points to obtain fault degrees, so that fault characteristics in the operation process of printing production equipment can be rapidly and effectively analyzed, fault conditions of bearings and gears in the operation process of the printing production equipment can be accurately and timely represented, and accuracy and timeliness of fault degree analysis of bearings and gears in the printing production equipment are improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and 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 identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A method for detecting an operating state of an automated printing production facility, the method comprising:
obtaining vibration signals, sound signals and gear acceleration of the printing production equipment at different time points in the running process; respectively carrying out modal decomposition and screening on the vibration signal and the sound signal to obtain at least two target eigenmode components;
performing numerical symbol conversion on the longitudinal coordinate values of each target eigenmode component at different time points, and converting each target eigenmode component into a signal component for coding; obtaining fault information entropy of each target eigenmode component according to the signal component codes;
determining vibration fault influence factors of the vibration signals according to the frequency and fault information entropy of the vibration signals corresponding to all target eigenmode components, and determining sound fault influence factors of the sound signals according to the frequency and fault information entropy of the sound signals corresponding to all target eigenmode components; obtaining the fault degree of each time point according to the vibration fault influence factor, the sound fault influence factor and the gear acceleration of all time points;
and detecting the running state of the printing production equipment according to the fault degree of the current time point to obtain a detection result.
2. The method for detecting the operation state of an automatic printing production device according to claim 1, wherein the performing modal decomposition and screening on the vibration signal and the sound signal respectively to obtain at least two target eigenmode components comprises:
performing empirical mode decomposition on the vibration signal to obtain vibration eigenmode components of the vibration signal, and determining a first number of preset vibration eigenmode components as target eigenmode components of the vibration signal;
performing empirical mode decomposition on the sound signal to obtain sound eigenmode components of the sound signal, and determining a first preset second number of sound eigenmode components as target eigenmode components of the sound signal; wherein the preset first number and the preset second number are equal to or less than 4.
3. The method of claim 1, wherein said performing numerical symbol conversion on the ordinate values of each of said target eigenmode components at different time points to convert each of said target eigenmode components into a signal component code comprises:
respectively calculating the mean value of the longitudinal coordinate values of each target eigenmode component at all time points to obtain a reference value of the corresponding target eigenmode component;
determining binary codes of the target eigenmode components according to the ordinate values and the reference values of each time point of each target eigenmode component;
dividing the binary codes according to preset lengths to obtain code segments, carrying out binary conversion on the binary codes in each code segment, converting the binary codes into decimal codes, and combining the decimal codes according to time sequence to obtain signal component codes.
4. The method for detecting the operation state of an automatic printing production device according to claim 1, wherein the obtaining the fault information entropy of each target eigenmode component according to the signal component code includes:
and calculating the information entropy of all coding values in the signal component codes corresponding to each target eigenmode component as the fault information entropy of the target eigenmode component.
5. The method for detecting an operation state of an automated printing production apparatus according to claim 1, wherein the determining a vibration fault impact factor of the vibration signal according to frequency and fault information entropy of the vibration signal corresponding to all target eigenmode components comprises:
respectively carrying out normalization processing on the frequency of each target eigen mode component in the vibration signal to obtain a vibration component weight;
calculating the product of the vibration component weight of each target eigenmode component in the vibration signal and the fault information entropy to serve as a fault influence index of the corresponding target eigenmode component;
and taking the average normalized value of fault influence indexes of all target eigenmode components in the vibration signal as a vibration fault influence factor of the vibration signal.
6. The method for detecting an operation state of an automated printing production apparatus according to claim 1, wherein the determining the sound fault impact factor of the sound signal according to the frequency and fault information entropy of the sound signal corresponding to all the target eigenmode components comprises:
respectively carrying out normalization processing on the frequency of each target eigen mode component in the sound signal to obtain a sound component weight;
calculating the product of the sound component weight of each target eigenmode component in the sound signal and fault information entropy to serve as a fault influence index of the corresponding target eigenmode component;
and taking the average normalized value of fault influence indexes of all target eigenmode components in the sound signal as a sound fault influence factor of the sound signal.
7. The method for detecting an operation state of an automatic printing production apparatus according to claim 1, wherein the obtaining the degree of failure at each time point based on the vibration failure influence factor, the sound failure influence factor, and the gear acceleration at all time points comprises:
determining maximum and minimum values of gear acceleration at all time points, and taking the average value of the absolute value of the difference between the maximum value and the preset standard acceleration and the absolute value of the difference between the minimum value and the preset standard acceleration as a first acceleration influence coefficient;
calculating the average value of the gear acceleration at all time points as an acceleration average value, and taking the absolute value of the difference between the acceleration average value and a preset standard acceleration as a second acceleration influence coefficient;
obtaining a target acceleration coefficient according to the first acceleration influence coefficient and the second acceleration influence coefficient, wherein the first acceleration influence coefficient and the target acceleration coefficient are in positive correlation, the second acceleration influence coefficient and the target acceleration coefficient are in positive correlation, and the value of the target acceleration coefficient is a normalized value;
calculating the product of the vibration fault influence factor and the sound fault influence factor as an operation fault coefficient;
and determining the fault degree according to the operation fault coefficient and the target acceleration coefficient.
8. The method for detecting the operation state of the automatic printing production equipment according to claim 1, wherein the detecting the operation state of the printing production equipment according to the fault degree of the current time point to obtain the detection result comprises the following steps:
when the fault degree of the current time point is greater than a preset degree threshold value, determining that the detection result is in a fault running state;
and when the fault degree of the current time point is smaller than or equal to a preset degree threshold value, determining that the detection result is in a normal running state.
9. The method for detecting an operating state of an automated printing production facility according to claim 7, wherein the determining a degree of failure from the operational failure coefficient and the target acceleration coefficient comprises:
and carrying out normalization processing on the product of the operation fault coefficient and the target acceleration coefficient to obtain the fault degree.
10. A method of detecting an operating state of an automated printing production facility according to claim 3, wherein said determining a binary code of each target eigenmode component based on the ordinate value and the reference value for each time point for said target eigenmode component comprises:
comparing the ordinate value of each time point of any target eigenmode component with a reference value, adjusting the ordinate value to 1 when the ordinate value is larger than the reference value of the target eigenmode component, adjusting the ordinate value to 0 when the ordinate value is smaller than or equal to the reference value of the target eigenmode component, and sorting all the adjusted ordinate values according to the sequence order to obtain the binary code of the target eigenmode component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034900.3A CN116754234B (en) | 2023-08-17 | 2023-08-17 | Automatic printing production equipment running state detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034900.3A CN116754234B (en) | 2023-08-17 | 2023-08-17 | Automatic printing production equipment running state detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116754234A true CN116754234A (en) | 2023-09-15 |
| CN116754234B CN116754234B (en) | 2023-11-21 |
Family
ID=87953645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311034900.3A Active CN116754234B (en) | 2023-08-17 | 2023-08-17 | Automatic printing production equipment running state detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116754234B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BE784857A (en) * | 1971-06-14 | 1972-10-02 | Krone Gmbh | ENDED PULSE SIGNAL MODULATOR INCLUDING AN AMPLITUDE CONVERTER TO ANGLED CHARACTERISTICS |
| CN201966893U (en) * | 2010-12-31 | 2011-09-07 | 苏州云芯微电子科技有限公司 | Current mirror array layout distribution structure of binary current-steering digital to analog converter |
| CN105281063A (en) * | 2014-06-09 | 2016-01-27 | 广濑电机株式会社 | Method and apparatus for reducing far-end crosstalk in electrical connectors |
| CN105910803A (en) * | 2016-04-15 | 2016-08-31 | 中北大学 | Acoustic-pressure-information-processing-based diagnosis method for feeding system fault |
| CN106528966A (en) * | 2016-10-27 | 2017-03-22 | 北京印刷学院 | Fault characteristic extraction method of high-speed press vibration signal on the basis of SVM (Support Vector Machine) |
| CN106951197A (en) * | 2017-01-19 | 2017-07-14 | 北京印刷学院 | A kind of printing equipment remote fault diagnosis method and system based on signal testing |
| CN107560851A (en) * | 2017-08-28 | 2018-01-09 | 合肥工业大学 | Rolling bearing Weak fault feature early stage extracting method |
| CN109029987A (en) * | 2018-09-10 | 2018-12-18 | 北航（天津武清）智能制造研究院有限公司 | Epicyclic gearbox gear distress detection method and system |
| CN109374299A (en) * | 2018-12-13 | 2019-02-22 | 西安理工大学 | A kind of Fault Diagnosis of Roller Bearings for printing element |
| CN111665051A (en) * | 2020-07-01 | 2020-09-15 | 天津大学 | Bearing fault diagnosis method under strong noise variable-speed condition based on energy weight method |
| WO2021056727A1 (en) * | 2019-09-27 | 2021-04-01 | 山东科技大学 | Joint noise reduction method based on variational mode decomposition and permutation entropy |
| CN113159127A (en) * | 2021-03-23 | 2021-07-23 | 浙江大胜达包装股份有限公司 | Intelligent fault diagnosis method for gravure printing machine guide roller based on improved generation countermeasure network |
| CN113553930A (en) * | 2021-07-14 | 2021-10-26 | 董跃周 | Method for diagnosing mechanical fault of on-load tap-changer of transformer |
| CN116517860A (en) * | 2023-04-19 | 2023-08-01 | 淮沪煤电有限公司丁集煤矿 | Ventilator fault early warning system based on data analysis |
-
2023
- 2023-08-17 CN CN202311034900.3A patent/CN116754234B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BE784857A (en) * | 1971-06-14 | 1972-10-02 | Krone Gmbh | ENDED PULSE SIGNAL MODULATOR INCLUDING AN AMPLITUDE CONVERTER TO ANGLED CHARACTERISTICS |
| CN201966893U (en) * | 2010-12-31 | 2011-09-07 | 苏州云芯微电子科技有限公司 | Current mirror array layout distribution structure of binary current-steering digital to analog converter |
| CN105281063A (en) * | 2014-06-09 | 2016-01-27 | 广濑电机株式会社 | Method and apparatus for reducing far-end crosstalk in electrical connectors |
| CN105910803A (en) * | 2016-04-15 | 2016-08-31 | 中北大学 | Acoustic-pressure-information-processing-based diagnosis method for feeding system fault |
| CN106528966A (en) * | 2016-10-27 | 2017-03-22 | 北京印刷学院 | Fault characteristic extraction method of high-speed press vibration signal on the basis of SVM (Support Vector Machine) |
| CN106951197A (en) * | 2017-01-19 | 2017-07-14 | 北京印刷学院 | A kind of printing equipment remote fault diagnosis method and system based on signal testing |
| CN107560851A (en) * | 2017-08-28 | 2018-01-09 | 合肥工业大学 | Rolling bearing Weak fault feature early stage extracting method |
| CN109029987A (en) * | 2018-09-10 | 2018-12-18 | 北航（天津武清）智能制造研究院有限公司 | Epicyclic gearbox gear distress detection method and system |
| CN109374299A (en) * | 2018-12-13 | 2019-02-22 | 西安理工大学 | A kind of Fault Diagnosis of Roller Bearings for printing element |
| WO2021056727A1 (en) * | 2019-09-27 | 2021-04-01 | 山东科技大学 | Joint noise reduction method based on variational mode decomposition and permutation entropy |
| CN111665051A (en) * | 2020-07-01 | 2020-09-15 | 天津大学 | Bearing fault diagnosis method under strong noise variable-speed condition based on energy weight method |
| CN113159127A (en) * | 2021-03-23 | 2021-07-23 | 浙江大胜达包装股份有限公司 | Intelligent fault diagnosis method for gravure printing machine guide roller based on improved generation countermeasure network |
| CN113553930A (en) * | 2021-07-14 | 2021-10-26 | 董跃周 | Method for diagnosing mechanical fault of on-load tap-changer of transformer |
| CN116517860A (en) * | 2023-04-19 | 2023-08-01 | 淮沪煤电有限公司丁集煤矿 | Ventilator fault early warning system based on data analysis |
Non-Patent Citations (2)
| Title |
|---|
| 焦培林: "精密数据采集系统的软件原理及在单牙轮钻头实验中的应用", 西南石油学院学报, no. 04 * |
| 王帅;向阳;王磊;: "基于集总经验模态分解和极坐标表示的瞬时转速诊断方法", 中国机械工程, no. 15 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116754234B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| CN108444708B (en) | Method for establishing rolling bearing intelligent diagnosis model based on convolutional neural network | |
| CN112232447B (en) | Construction method of complete sample set of power equipment state monitoring data | |
| CN107657250B (en) | Bearing fault detection and positioning method and detection and positioning model implementation system and method | |
| CN110427916B (en) | Fault diagnosis method under action of central frequency convergence tendency | |
| CN113158814B (en) | Bearing health state monitoring method based on convolution self-encoder | |
| CN105275833A (en) | CEEMD (Complementary Empirical Mode Decomposition)-STFT (Short-Time Fourier Transform) time-frequency information entropy and multi-SVM (Support Vector Machine) based fault diagnosis method for centrifugal pump | |
| Dou et al. | A rule-based intelligent method for fault diagnosis of rotating machinery | |
| CN114167838B (en) | Multi-scale health assessment and fault prediction method for servo system | |
| CN116701984B (en) | Automatic fault diagnosis system of numerical control machine tool based on machine learning | |
| CN110837718B (en) | Switch fault detection method and device, electronic equipment and storage medium | |
| CN116304751B (en) | Operation data processing method for overhauling motor train unit components | |
| CN116956215A (en) | Fault diagnosis method and system for transmission system | |
| CN116754234B (en) | Automatic printing production equipment running state detection method | |
| CN115034137A (en) | RVM and degradation model-based two-stage hybrid prediction method for residual life of bearing | |
| CN117076935B (en) | Digital twin-assisted mechanical fault data lightweight generation method and system | |
| CN113551927A (en) | Mechanical equipment fault early warning method and system based on vibration signals | |
| CN115705413A (en) | Method and device for determining abnormal log | |
| CN115959549A (en) | Escalator fault diagnosis method based on digital twinning | |
| CN112607555B (en) | Training method and detection method of model for elevator guide rail state detection | |
| CN114595525A (en) | Rolling bearing degradation trend prediction method based on linear regression and TCN | |
| CN113988173A (en) | Fault diagnosis method, system, equipment and storage medium based on qualitative trend analysis and five-state Bayesian network | |
| CN113205215A (en) | Knowledge-based battlefield situation prediction method | |
| CN117273547B (en) | Production equipment operation data processing method based on edge calculation | |
| CN115115037B (en) | Bearing fault probability analysis device |
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 |