CN118081873B - Special-shaped sponge cutting method and control system - Google Patents
Special-shaped sponge cutting method and control system Download PDFInfo
- Publication number
- CN118081873B CN118081873B CN202410524095.0A CN202410524095A CN118081873B CN 118081873 B CN118081873 B CN 118081873B CN 202410524095 A CN202410524095 A CN 202410524095A CN 118081873 B CN118081873 B CN 118081873B
- Authority
- CN
- China
- Prior art keywords
- value
- generation amount
- debris
- chip
- amount
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005520 cutting process Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 70
- 238000004519 manufacturing process Methods 0.000 claims description 59
- 238000009499 grossing Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 3
- 229920000742 Cotton Polymers 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a special-shaped sponge cutting method and a control system, which relate to the technical field of sponge cutting, and the technical key points of the scheme are as follows: calculating to obtain a predicted value of the chip generation amount at the next moment through a smooth value and a trend value of the actual chip generation amount at the moment t and the chip generation amount at the last moment, calculating to obtain a chip generation amount fluctuation value through the average value of the actual chip generation amount observation value and the actual chip generation amount observation value at different moments in a time window, calculating to obtain a chip generation amount error value through the difference value between the predicted value of the chip generation amount and the actual chip generation amount observation value under a marked time sequence, calculating to obtain a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal is present in the special-shaped sponge cutting equipment.
Description
Technical Field
The invention relates to the technical field of sponge cutting, in particular to a special-shaped sponge cutting method and a control system.
Background
The special-shaped sponge generally refers to sponge products with irregular shapes or special designs, and along with the continuous progress of industrial technology and the increasing intensity of market competition, the special-shaped sponge cutting technology has become an indispensable part in modern industrial production, and the optimization of a special-shaped sponge cutting method and the intellectualization of a control system have important significance for improving the production efficiency, reducing the cost and improving the product quality.
In the Chinese application of the application publication No. CN116277267A, a control method of an intelligent cutting assembly line is disclosed, wherein the circular vertical cutter assembly line comprises a deviation rectifying platform, a slicing machine, a cotton sucking machine, a first lifting table, a circular vertical cutter special-shaped cutting machine, a second lifting table and a control system, and the control method comprises the following steps of: preparing work; slicing and layering processing: cutting the bottom skin, rectifying the deviation of the sponge, slicing and layering; transferring the sponge sheet; performing special-shaped cutting processing; the control system tracks orders in real time.
In the chinese application of the application publication No. CN114654523a, a control system of a novel sponge slicer is disclosed, the sponge slicer includes a gantry, a conveyor belt, a knife rest, a knife belt and a press roller, wherein, the gantry spans across two sides of the width direction of the conveyor belt, the knife belt is installed on the gantry by the knife rest, the press roller is movably installed on the knife rest, the control system includes a programmable controller, a cotton photoelectric device on a platform, a press roller photoelectric device, a knife rest servo, a platform servo, a press roller lifting servo, a press roller rotating servo and a touch display screen.
In combination with the above invention, the prior art has the following disadvantages:
In the special-shaped sponge cutting process, due to the actions of various potential factors, such as equipment abrasion, material property change, improper operation and the like, cutting abnormality can be possibly caused, the reasons for the abnormality are complex and diversified, a great challenge is brought to the monitoring process, the abnormal signals are often difficult to comprehensively and accurately capture in the prior art, and the accuracy and the efficiency of abnormality monitoring are limited;
in the monitoring process of special-shaped sponge cutting, some abnormal reasons may be relatively hidden and not easily observed, and the sponge chip quantity is used as an important index in the cutting process, so that the running condition of equipment can be intuitively reflected, the key factor is often ignored in the prior art, and the chip quantity information is not fully utilized to reveal the potential abnormal reasons, so that a monitoring blind area is formed.
Disclosure of Invention
(One) solving the technical problems
In order to overcome the defects of the prior art, the invention provides a special-shaped sponge cutting method and a control system, wherein a predicted value of the generation amount of chips at the next moment is calculated and obtained through a smooth value and a trend value of the generation amount of chips at the moment, the generation amount fluctuation value of chips is calculated and obtained through the average value of the generation amount of chips at different moments in a time window and the generation amount of chips at the moment, the generation amount error value of chips is calculated and obtained through the difference value between the predicted value of the generation amount of chips and the generation amount of chips at the time sequence of marks, the generation amount error value of chips is calculated and obtained by combining the generation amount fluctuation value of chips and the generation amount error value of chips, the generation amount error value of chips is compared with an abnormal threshold value, and whether the special-shaped sponge cutting equipment has abnormality is judged, so that the problem in the background technology is solved.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: a special-shaped sponge cutting method comprises the following steps:
Calculating to obtain the smooth value and the trend value of the chip generation amount at the moment t through the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last moment, and further calculating to obtain the predicted value of the chip generation amount at the moment next;
Calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
Initializing a time window and moving, calculating to obtain a chip generation quantity fluctuation value through the average value of actual chip generation quantity observation values and actual chip generation quantity observation values at different moments in the time window, and marking a time sequence in the current time window when the chip generation quantity fluctuation value is larger than a fluctuation threshold value;
calculating to obtain a chip generation amount error value through the difference value between the predicted value of the chip generation amount and the actual chip generation amount observed value under the marked time sequence, calculating to obtain a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
Further, an initial smooth value and a trend value are set, and the smooth value and the trend value of the chip generation amount at the moment t are obtained through calculation through the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last, and the calculation formula is as follows:
Wherein, Smooth value representing the amount of debris generated at time t,/>A smooth value representing the generation amount of the chips at the previous moment, alpha represents a smooth coefficient, and the value range of alpha is [0,1 ]/>Representing the observed value of the actual debris generation amount at the time t/>Trend value representing debris generation amount at time t,/>And the trend value of the chip generation amount at the last moment is represented, beta represents a trend smoothing coefficient, and the value range of beta is [0,1].
Further, the generation amount of the scraps at the next moment is predicted by the smooth value and the trend value of the generation amount of the scraps at the moment t, and the predicted value of the generation amount of the scraps at the next moment is obtained by calculation, wherein the calculation formula is as follows:
Wherein, Predicted value representing the amount of chips produced at the next time,/>Smooth value representing the amount of debris generated at time t,/>Trend value indicating the amount of chips generated at time t.
Further, calculating a predicted value of the generated debris amount to obtain a continuous time series, comparing the predicted value of the generated debris amount with a corresponding observed value of the generated actual debris amount, calculating an error value of the generated debris amount, evaluating the predicted result of the generated debris amount, and the calculation formula is as follows:
where Ev represents the chip production amount error value, Predicted value representing the amount of generated debris,/>An observation value indicating the actual amount of generated debris, i indicating a time series of marks,/>N is a positive integer;
When the debris production error value is greater than the error threshold, the smoothing coefficient and the trend smoothing coefficient are optimized and adjusted until the debris production error value is less than the error threshold.
Further, by means of the observed value of the actual debris generation amount and the average value of the observed value of the actual debris generation amount at different moments in the time window, the fluctuation condition of the change of the debris generation amount at different moments is analyzed, the fluctuation value of the debris generation amount is calculated and obtained, and the calculation formula is as follows:
Where Fd represents a debris generation amount fluctuation value, Representing an observation of the actual amount of debris produced at time k, k representing the identity of time,/>K is a positive integer,/>Representing the average of the actual chip production observations.
Further, the time window is moved forward by one time unit until the entire time sequence is traversed, the debris production amount fluctuation value is compared with the fluctuation threshold value, and when the debris production amount fluctuation value is greater than the fluctuation threshold value, the time sequence within the current time window is marked.
Further, by comparing the difference between the predicted value of the chip production amount and the observed value of the actual chip production amount, the chip production amount error value is calculated and obtained, and the calculation formula is as follows:
where Ev represents the chip production amount error value, Predicted value representing the amount of generated debris,/>Representing an actual chip production observation, j representing the identity of the marked time series,/>M is a positive integer.
Further, the debris generation amount fluctuation value and the debris generation amount error value are combined, and after linear normalization processing, the debris generation amount abnormal value is calculated and obtained, and the calculation formula is as follows:
Where Dp represents an abnormal value of the chip production amount, ev represents an error value of the chip production amount, fd represents a fluctuation value of the chip production amount, 、/>Representing the weight coefficient,/>，/>。
Further, an abnormal threshold value is preset, the abnormal value of the debris generation amount is compared with the abnormal threshold value, and whether abnormal conditions exist in the special-shaped sponge cutting equipment or not is judged, specifically:
When the abnormal value of the debris generation amount is less than or equal to the abnormal threshold value, no processing is required; when the abnormal value of the debris generation amount is larger than the abnormal threshold value, sending out early warning, and checking and maintaining the special-shaped sponge cutting equipment in time.
A special-shaped sponge cutting control system comprises a debris generation amount monitoring module, a debris generation amount prediction module, a debris generation amount analysis module and an abnormality judgment module; wherein,
The debris generation amount monitoring module is used for collecting the debris amount data generated in the special-shaped sponge cutting process in real time and transmitting the data to other modules in the control system, including a debris generation amount prediction module and a debris generation amount analysis module;
The debris generation amount prediction module calculates and obtains a smooth value and a trend value of the debris generation amount at the moment t through a smooth value and a trend value of the actual debris generation amount at the moment t and the debris generation amount at the moment last moment, and further calculates and obtains a predicted value of the debris generation amount at the moment next;
the adjustment and optimization module is used for calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
the debris generation amount analysis module calculates and obtains a debris generation amount fluctuation value through the average value of the actual debris generation amount observation values and the actual debris generation amount observation values at different moments in the time window, and marks the time sequence in the current time window when the debris generation amount fluctuation value is larger than a fluctuation threshold value;
the abnormal judgment module is used for calculating and obtaining a chip generation amount error value through a difference value between a predicted value of the chip generation amount and an actual chip generation amount observed value under the marked time sequence, calculating and obtaining a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
(III) beneficial effects
The invention provides a special-shaped sponge cutting method and a control system, which have the following beneficial effects:
(1) By combining the observed value at the current moment and the smooth value at the last moment, the actual change of the chip production amount is reflected more accurately, the continuity and the correlation of the time sequence are considered, the predicted result is more practical, the introduced trend value can clearly represent the increasing or decreasing trend of the chip production amount, the trend value is crucial to predicting the future change of the chip production amount, and particularly, when the production environment or the process condition is changed, the trend value can better reflect the influence of the changes on the chip production amount.
(2) The method has the advantages that the accuracy of prediction is improved by continuously optimizing and adjusting the smoothing coefficient and the trend smoothing coefficient, the change trend of the debris generation amount in a future period of time can be known more accurately, so that a more reasonable decision is made, the model can be better adapted to the change of actual data by dynamically adjusting the model parameters, the stability and the reliability of the model are improved, and good prediction performance can be kept under different environments and scenes.
(3) The fluctuation value reflects the change degree of the observed value of the debris generation amount in the time window, when the fluctuation value exceeds the preset threshold value, the change in the time window exceeds the normal range, and the time sequence segments with obvious change characteristics can be rapidly positioned by comparing the fluctuation value with the threshold value.
(4) The running state of the equipment is more comprehensively evaluated by comprehensively considering the fluctuation value and the error value of the chip production quantity, the fluctuation value reflects the variation degree of the chip production quantity, the error value measures the deviation between the actual value and the expected value, the fluctuation value and the error value are combined, the abnormal phenomenon can be more accurately identified, the possibility of false alarm and false omission is reduced, the abnormality of the chip production quantity is often closely related to the cutting quality, the generation of unqualified products can be reduced by timely finding and processing the abnormality, the overall quality of the products is improved, and the market competitiveness of enterprises is enhanced.
Drawings
FIG. 1 is a schematic diagram showing steps of a method for cutting a special-shaped sponge according to the present invention;
FIG. 2 is a schematic flow chart of the method for cutting the special-shaped sponge according to the invention;
fig. 3 is a schematic structural diagram of the special-shaped sponge cutting control system of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Referring to fig. 1-2, the invention provides a method for cutting a special-shaped sponge, which comprises the following steps:
Step one: calculating to obtain the smooth value and the trend value of the chip generation amount at the moment t through the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last moment, and further calculating to obtain the predicted value of the chip generation amount at the moment next;
the first step comprises the following steps:
step 101: when the special-shaped sponge is cut, the amount of scraps generated in the cutting process of the special-shaped sponge is monitored in real time, and the monitored data are summarized to construct a scraps generation amount data set;
Step 102: setting an initial smooth value and a trend value, and calculating to obtain the smooth value and the trend value of the chip generation amount at the moment t by using the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last moment, wherein the calculation formula is as follows:
Wherein, Smooth value representing the amount of debris generated at time t,/>A smooth value representing the generation amount of the chips at the previous moment, alpha represents a smooth coefficient, and the value range of alpha is [0,1 ]/>Representing the observed value of the actual debris generation amount at the time t/>Trend value representing debris generation amount at time t,/>A trend value representing the generation amount of the scraps at the last moment, wherein beta represents a trend smoothing coefficient, and the value range of beta is [0,1];
The initial smoothed value and trend value may be set to the first observed value or other reasonable estimate;
Step 103: and predicting the debris generation amount at the next moment by using the smoothed value and the trend value of the debris generation amount at the moment t, and calculating to obtain the predicted value of the debris generation amount at the next moment, wherein the calculation formula is as follows:
Wherein, Predicted value representing the amount of chips produced at the next time,/>Smooth value representing the amount of debris generated at time t,/>A trend value representing the amount of debris generated at time t;
Step 104: the above steps are repeated, the smoothed value and the trend value of the debris generation amount are updated using the new actual debris generation amount observation value, and the debris generation amount at the next timing is predicted.
It should be noted that, the selection of the smoothing coefficient α and the trend smoothing coefficient β is critical to the prediction result, the larger α value may make the prediction value more sensitive to the recent observation value, the smaller α value may make the prediction value smoother, the fitting degree of the prediction result and the actual data may be observed through testing different α values, the best α value is selected, the main function of the trend smoothing coefficient β is to control the weight of the trend term in the prediction, and the value of β, similar to the smoothing coefficient α, may also affect the sensitivity degree of the prediction value to the recent trend change.
In use, the contents of steps 101 to 102 are combined:
By combining the observed value at the current moment and the smooth value at the last moment, the actual change of the chip production amount is reflected more accurately, the continuity and the correlation of the time sequence are considered, the predicted result is more practical, the introduced trend value can clearly represent the increasing or decreasing trend of the chip production amount, the trend value is crucial to predicting the future change of the chip production amount, and particularly, when the production environment or the process condition is changed, the trend value can better reflect the influence of the changes on the chip production amount.
Step two: calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
the second step comprises the following steps:
Step 201: calculating and obtaining a predicted value of the debris generation amount of the continuous time sequence, comparing the predicted value of the debris generation amount with a corresponding observed value of the actual debris generation amount, calculating and obtaining an error value of the debris generation amount, evaluating a predicted result of the debris generation amount, and calculating the error value of the debris generation amount according to the following formula:
where Ev represents the chip production amount error value, Predicted value representing the amount of generated debris,/>An observation value indicating the actual amount of generated debris, i indicating a time series of marks,/>N is a positive integer;
Step 202: and presetting an error threshold, and optimizing and adjusting the smoothing coefficient and the trend smoothing coefficient when the error value of the debris generation amount is larger than the error threshold until the error value of the debris generation amount is smaller than the error threshold.
It should be noted that, when the smoothing coefficient and the trend smoothing coefficient are adjusted, a grid search and cross verification method is adopted to set a series of possible coefficient values, then the model performance under different coefficient combinations is evaluated through cross verification, finally, the coefficient combination with the smallest prediction error is selected as the optimal parameter, and in addition, the dynamic adjustment strategy of the parameter is considered, that is, the smoothing coefficient is dynamically updated according to the input of new data so as to better adapt to the change of the data.
In use, the contents of steps 201 to 202 are combined:
the accuracy of prediction can be remarkably improved by continuously optimizing and adjusting the smoothing coefficient and the trend smoothing coefficient, the change trend of the debris generation amount in a period of time in the future can be more accurately known, so that a more reasonable decision is made, the model can be better adapted to the change of actual data by dynamically adjusting the model parameters, the stability and the reliability of the model can be improved, and good prediction performance can be kept under different environments and scenes.
Step three: initializing a time window and moving, calculating to obtain a chip generation quantity fluctuation value through the average value of actual chip generation quantity observation values and actual chip generation quantity observation values at different moments in the time window, and marking a time sequence in the current time window when the chip generation quantity fluctuation value is larger than a fluctuation threshold value;
the third step comprises the following steps:
Step 301: when the special-shaped sponge is cut, acquiring an actual chip generation amount observation value under a continuous time sequence, initializing an empty time window, determining the size of the time window, extracting data in the time window from the starting point of the time sequence, and setting the size of the time window to be 30 minutes;
Step 302: analyzing the variation fluctuation condition of the chip production quantity at different moments through the actual chip production quantity observation value and the average value of the actual chip production quantity observation value at different moments in a time window, and calculating to obtain the chip production quantity fluctuation value, wherein the calculation formula is as follows:
Where Fd represents a debris generation amount fluctuation value, Representing an observation of the actual amount of debris produced at time k, k representing the identity of time,/>K is a positive integer,/>A mean value representing an observed value of an actual debris generation amount;
Step 303: moving the time window forward by one time unit, wherein the time unit can be set to be 5 minutes, repeating the steps until the whole time sequence is traversed, presetting a fluctuation threshold value, comparing the debris generation quantity fluctuation value with the fluctuation threshold value, and marking the time sequence in the current time window when the debris generation quantity fluctuation value is larger than the fluctuation threshold value.
It should be noted that the size of the time window should be selected to capture the variation characteristics of the actual debris generation while avoiding being too smooth or too sensitive, and in practice, the optimal time window size may be determined by trial and error or optimization based on statistical methods, for example, different time window sizes may be tried, and the variation and stability of the analysis result may be compared, and in addition, the performance of the model under the different time window sizes may be evaluated by using a cross-validation technique or the like.
In use, the contents of steps 301 to 303 are combined:
The fluctuation value reflects the degree of change in the observed value of the debris generation amount in the time window, and when the fluctuation value exceeds the preset threshold value, the change in the time window exceeds the normal range and is possibly caused by a special event or factor, so that the time sequence segments with significant change characteristics can be rapidly positioned by comparison with the threshold value.
Step four: calculating to obtain a chip generation amount error value through the difference value between the predicted value of the chip generation amount and the actual chip generation amount observed value under the marked time sequence, calculating to obtain a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
The fourth step comprises the following steps:
Step 401: obtaining a predicted value of the debris generation amount and an actual debris generation amount observed value under the marked time sequence, and calculating to obtain a debris generation amount error value by comparing the difference between the predicted value of the debris generation amount and the actual debris generation amount observed value, wherein the calculation formula is as follows:
where Ev represents the chip production amount error value, Predicted value representing the amount of generated debris,/>Representing an actual chip production observation, j representing the identity of the marked time series,/>M is a positive integer;
It should be noted that, the predicted value of the generated debris amount at this time is the predicted value after being optimized and adjusted, so when the error value of the generated debris amount fluctuates greatly, it is explained that the observed value of the actual generated debris amount at this time is likely to have a problem, and further analysis is needed;
step 402: combining the debris generation quantity fluctuation value and the debris generation quantity error value, and calculating to obtain a debris generation quantity abnormal value after linear normalization processing, wherein the calculation formula is as follows:
Where Dp represents an abnormal value of the chip production amount, ev represents an error value of the chip production amount, fd represents a fluctuation value of the chip production amount, 、/>Representing the weight coefficient,/>，/>；
Step 403: presetting an abnormal threshold, comparing the abnormal value of the chip generation amount with the abnormal threshold, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment or not, wherein the abnormal conditions are as follows:
When the abnormal value of the scrap generation amount is smaller than or equal to the abnormal threshold value, the abnormal value indicates that the abnormal sponge cutting equipment is normal, and no treatment is needed;
When the abnormal value of the debris generation amount is larger than the abnormal threshold value, abnormal occurrence of the special-shaped sponge cutting equipment is indicated, early warning is sent out, and the special-shaped sponge cutting equipment is checked and maintained in time.
In use, the contents of steps 401 to 403 are combined:
The running state of the equipment is more comprehensively evaluated by comprehensively considering the fluctuation value and the error value of the chip production quantity, the fluctuation value reflects the variation degree of the chip production quantity, the error value measures the deviation between the actual value and the expected value, the fluctuation value and the error value are combined, the abnormal phenomenon can be more accurately identified, the possibility of false alarm and false omission is reduced, the abnormality of the chip production quantity is often closely related to the cutting quality, the generation of unqualified products can be reduced by timely finding and processing the abnormality, the overall quality of the products is improved, and the market competitiveness of enterprises is enhanced.
Referring to fig. 3, the invention further provides a special-shaped sponge cutting control system, which comprises a debris generation amount monitoring module, a debris generation amount prediction module, a debris generation amount analysis module and an abnormality judgment module; wherein,
The debris generation amount monitoring module is used for collecting the debris amount data generated in the special-shaped sponge cutting process in real time and transmitting the data to other modules in the control system, including a debris generation amount prediction module and a debris generation amount analysis module;
The debris generation amount prediction module calculates and obtains a smooth value and a trend value of the debris generation amount at the moment t through a smooth value and a trend value of the actual debris generation amount at the moment t and the debris generation amount at the moment last moment, and further calculates and obtains a predicted value of the debris generation amount at the moment next;
the adjustment and optimization module is used for calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
the debris generation amount analysis module calculates and obtains a debris generation amount fluctuation value through the average value of the actual debris generation amount observation values and the actual debris generation amount observation values at different moments in the time window, and marks the time sequence in the current time window when the debris generation amount fluctuation value is larger than a fluctuation threshold value;
the abnormal judgment module is used for calculating and obtaining a chip generation amount error value through a difference value between a predicted value of the chip generation amount and an actual chip generation amount observed value under the marked time sequence, calculating and obtaining a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
In the application, the related formulas are all the numerical calculation after dimensionality removal, and the formulas are one formulas for acquiring a large amount of data and performing software simulation to obtain the latest real situation, and coefficients in the formulas are set by a person skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (10)
1. The special-shaped sponge cutting method is characterized by comprising the following steps of:
Calculating to obtain the smooth value and the trend value of the chip generation amount at the moment t through the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last moment, and further calculating to obtain the predicted value of the chip generation amount at the moment next;
Calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
Initializing a time window and moving, calculating to obtain a chip generation quantity fluctuation value through the average value of actual chip generation quantity observation values and actual chip generation quantity observation values at different moments in the time window, and marking a time sequence in the current time window when the chip generation quantity fluctuation value is larger than a fluctuation threshold value;
calculating to obtain a chip generation amount error value through the difference value between the predicted value of the chip generation amount and the actual chip generation amount observed value under the marked time sequence, calculating to obtain a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
2. A method for cutting a shaped sponge according to claim 1, wherein,
Setting an initial smooth value and a trend value, and calculating to obtain the smooth value and the trend value of the chip generation amount at the moment t by using the observed value of the actual chip generation amount at the moment t and the smooth value and the trend value of the chip generation amount at the moment last moment, wherein the calculation formula is as follows:
Wherein/> A smoothed value representing the amount of debris generated at time t,A smooth value representing the generation amount of the chips at the previous moment, alpha represents a smooth coefficient, and the value range of alpha is [0,1 ]/>Representing the observed value of the actual debris generation amount at the time t/>Trend value representing debris generation amount at time t,/>And the trend value of the chip generation amount at the last moment is represented, beta represents a trend smoothing coefficient, and the value range of beta is [0,1].
3. A method for cutting a shaped sponge according to claim 2, wherein,
And predicting the debris generation amount at the next moment by using the smoothed value and the trend value of the debris generation amount at the moment t, and calculating to obtain the predicted value of the debris generation amount at the next moment, wherein the calculation formula is as follows:
Wherein/> Predicted value representing the amount of chips produced at the next time,/>Smooth value representing the amount of debris generated at time t,/>Trend value indicating the amount of chips generated at time t.
4. A method for cutting a shaped sponge according to claim 1, wherein,
Calculating and obtaining a predicted value of the debris generation amount of the continuous time sequence, comparing the predicted value of the debris generation amount with a corresponding observed value of the actual debris generation amount, calculating and obtaining an error value of the debris generation amount, evaluating a predicted result of the debris generation amount, and calculating the error value of the debris generation amount according to the following formula:
Where Ev represents the chip production level error value,/> A predicted value indicating the amount of generated debris,An observation value indicating the actual amount of generated debris, i indicating a time series of marks,/>N is a positive integer;
When the debris production error value is greater than the error threshold, the smoothing coefficient and the trend smoothing coefficient are optimized and adjusted until the debris production error value is less than the error threshold.
5. A method for cutting a shaped sponge according to claim 1, wherein,
Analyzing the variation fluctuation condition of the chip production quantity at different moments through the actual chip production quantity observation value and the average value of the actual chip production quantity observation value at different moments in a time window, and calculating to obtain the chip production quantity fluctuation value, wherein the calculation formula is as follows:
Wherein Fd represents a debris generation amount fluctuation value,/> Representing an observation of the actual amount of debris produced at time k, k representing the identity of time,/>K is a positive integer,/>Representing the average of the actual chip production observations.
6. A method for cutting a shaped sponge according to claim 5, wherein,
The time window is moved forward by one time unit until the entire time sequence is traversed, the debris production amount fluctuation value is compared with a fluctuation threshold value, and when the debris production amount fluctuation value is greater than the fluctuation threshold value, the time sequence within the current time window is marked.
7. A method for cutting a shaped sponge according to claim 1, wherein,
By comparing the difference between the predicted value of the chip production amount and the observed value of the actual chip production amount, the chip production amount error value is calculated and obtained, and the calculation formula is as follows:
Where Ev represents the chip production level error value,/> Predicted value representing the amount of generated debris,/>Representing an actual chip production observation, j representing the identity of the marked time series,/>M is a positive integer.
8. A method for cutting a shaped sponge according to claim 7, wherein,
Combining the debris generation quantity fluctuation value and the debris generation quantity error value, and calculating to obtain a debris generation quantity abnormal value after linear normalization processing, wherein the calculation formula is as follows:
Wherein Dp represents an abnormal value of the chip production amount, ev represents an error value of the chip production amount, fd represents a fluctuation value of the chip production amount,/> 、/>Representing the weight coefficient,/>，/>。
9. A method for cutting a shaped sponge according to claim 8, wherein,
Comparing the abnormal value of the scrap generation amount with an abnormal threshold value, judging whether abnormal conditions exist in the special-shaped sponge cutting equipment, and specifically: when the abnormal value of the debris generation amount is less than or equal to the abnormal threshold value, no processing is required; when the abnormal value of the debris generation amount is larger than the abnormal threshold value, sending out early warning, and checking and maintaining the special-shaped sponge cutting equipment in time.
10. A shaped sponge cutting control system for implementing the method of any one of claims 1 to 9, comprising:
The debris generation amount monitoring module is used for collecting the debris amount data generated in the special-shaped sponge cutting process in real time and transmitting the data to the debris generation amount prediction module and the debris generation amount analysis module;
The debris generation amount prediction module calculates and obtains a smooth value and a trend value of the debris generation amount at the moment t through a smooth value and a trend value of the actual debris generation amount at the moment t and the debris generation amount at the moment last moment, and further calculates and obtains a predicted value of the debris generation amount at the moment next;
the adjustment and optimization module is used for calculating and obtaining a predicted value of the chip generation amount of the continuous time sequence, comparing the predicted value of the chip generation amount with a corresponding actual chip generation amount observed value, calculating and obtaining a chip generation amount error value, and optimizing and adjusting when the chip generation amount error value is larger than an error threshold value;
the debris generation amount analysis module calculates and obtains a debris generation amount fluctuation value through the average value of the actual debris generation amount observation values and the actual debris generation amount observation values at different moments in the time window, and marks the time sequence in the current time window when the debris generation amount fluctuation value is larger than a fluctuation threshold value;
the abnormal judgment module is used for calculating and obtaining a chip generation amount error value through a difference value between a predicted value of the chip generation amount and an actual chip generation amount observed value under the marked time sequence, calculating and obtaining a chip generation amount abnormal value by combining the chip generation amount fluctuation value and the chip generation amount error value, comparing the chip generation amount abnormal value with an abnormal threshold value, and judging whether abnormal conditions exist in the special-shaped sponge cutting equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524095.0A CN118081873B (en) | 2024-04-29 | 2024-04-29 | Special-shaped sponge cutting method and control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524095.0A CN118081873B (en) | 2024-04-29 | 2024-04-29 | Special-shaped sponge cutting method and control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118081873A CN118081873A (en) | 2024-05-28 |
| CN118081873B true CN118081873B (en) | 2024-06-21 |
Family
ID=91145972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410524095.0A Active CN118081873B (en) | 2024-04-29 | 2024-04-29 | Special-shaped sponge cutting method and control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118081873B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107363645A (en) * | 2017-08-21 | 2017-11-21 | 温州大学 | Milling machine process tool abrasion Forecasting Methodology based on power detection |
| CN114211561A (en) * | 2021-10-27 | 2022-03-22 | 南通禾弘电子科技有限公司 | Chip difference amount center compensation type circuit board perforating machine |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10139311B2 (en) * | 2014-09-26 | 2018-11-27 | Palo Alto Research Center Incorporated | Computer-implemented method and system for machine tool damage assessment, prediction, and planning in manufacturing shop floor |
| CN117435718A (en) * | 2023-10-30 | 2024-01-23 | 深圳市云初信息科技有限公司 | Science and technology information recommendation method and system |
-
2024
- 2024-04-29 CN CN202410524095.0A patent/CN118081873B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107363645A (en) * | 2017-08-21 | 2017-11-21 | 温州大学 | Milling machine process tool abrasion Forecasting Methodology based on power detection |
| CN114211561A (en) * | 2021-10-27 | 2022-03-22 | 南通禾弘电子科技有限公司 | Chip difference amount center compensation type circuit board perforating machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118081873A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112527788B (en) | Method and device for detecting and cleaning abnormal value of transformer monitoring data | |
| CA2634328C (en) | Method and system for trend detection and analysis | |
| CN107146004B (en) | A kind of slag milling system health status identifying system and method based on data mining | |
| US9378183B2 (en) | Monitoring diagnostic device and monitoring diagnostic method | |
| CN101470426B (en) | Fault detection method and system | |
| CN109524139A (en) | A kind of real-time device performance monitoring method based on equipment working condition variation | |
| CN110362608B (en) | Rain flow counting method and local anomaly factor-based energy consumption anomaly detection method | |
| WO2006019448A1 (en) | Parametric injection molding system and method | |
| CN110995153B (en) | Abnormal data detection method and device for photovoltaic power station and electronic equipment | |
| CN117290802B (en) | Host power supply operation monitoring method based on data processing | |
| CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
| CN116050678A (en) | Die-casting product processing test system and method based on cloud computing | |
| CN110208028B (en) | Online fault detection method and system for concrete production equipment based on dust concentration | |
| CN118081873B (en) | Special-shaped sponge cutting method and control system | |
| US11676055B2 (en) | System for detecting data drift in machine-learning process monitoring | |
| CN113552853B (en) | Alarm management method and device for multiple working conditions of chemical system | |
| US11609836B2 (en) | Operation method and operation device of failure detection and classification model | |
| CN116341993B (en) | State monitoring method and system for polystyrene production process | |
| CN117078118B (en) | Intelligent detection system for quality of workpiece produced by numerical control machine tool | |
| CN118122785B (en) | Intelligent monitoring system for wire rod rolling production and manufacturing | |
| CN116993734B (en) | Battery heat insulation cotton cutting quality prediction system based on visual imaging analysis | |
| EP4068179A1 (en) | Analysis apparatus, analysis method, and program | |
| CN118294145A (en) | Bearing fault prediction method and system | |
| CN117359393A (en) | Multi-signal cutter abrasion monitoring and controlling system in numerical control machining process | |
| CN118410271A (en) | Industrial big data analysis method based on multi-source heterogeneous data management |
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 |