Production data processing method and system based on data medium station

Abstract

The invention relates to the technical field of workpiece production data processing, in particular to a production data processing method and system based on a data medium table, and the method comprises the steps: installing r * c pressure sensors in a die to collect the pressure data of a plurality of positions in the die; performing first curve fitting on pressure data acquired by the pressure sensor in a local range to obtain a first curve, calculating simulated pressure data by adopting an interpolation method, and performing second curve fitting in the local range to obtain a second curve; calculating the original noise expression degree according to the pressure data collected by the same pressure sensor, and calculating the corrected noise expression degree according to the pressure data collected by the adjacent sensors at the same moment and the original noise expression degree; and according to the modified noise expression degree, screening to obtain the pressure data to be filtered and filtering the pressure data to be filtered. The technical problem that in the prior art, when a die is used for workpiece production, the data processing efficiency is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of workpiece production data processing, and to a production data processing method and system based on a data middle platform. Background Art

[0002] In the process of using molds to produce workpieces, it is necessary to detect a variety of data to ensure the quality and performance of the workpiece. Among them, the size and stability of the pressure in the mold are directly related to the molding accuracy and quality of the workpiece.

[0003] During the production process, due to the influence of various factors, the pressure data may contain noise. The noise data will affect the judgment of the pressure value, thereby affecting the precise control of the production process and the accuracy of subsequent data analysis. For example, in terms of mold design optimization, production process adjustment, etc., accurate pressure data can provide a more accurate reference. Therefore, it is necessary to denoise the pressure data in the production process.

[0004] In the prior art, when denoising a pressure data sequence through a denoising algorithm, each data in the sequence is usually denoised in turn. For example, the patent application document with application publication number CN117113000A is entitled "A method for evaluating landslide susceptibility based on multivariate time series data", which includes: step 1, data collection and storage; step 2, data preprocessing: processing missing data values ​​and data outliers, and performing Kalman filtering.

[0005] However, using the above method to process and filter all pressure data will result in low data processing efficiency. Summary of the invention

[0006] In order to solve the technical problem of low data processing efficiency when using molds to produce workpieces, the present invention proposes a production data processing method and system based on a data middle platform. To this end, the present invention provides solutions in the following aspects.

[0007] In a first aspect of the implementation manner of the present invention, a production data processing method based on a data middle platform is provided, including: installing r×c pressure sensors in a mold to collect pressure data at multiple positions in the mold, where r represents the number of rows and c represents the number of columns; performing a first curve fitting on the pressure data collected by the pressure sensor in a local range to obtain a first curve, using an interpolation method to calculate simulated pressure data, and performing a second curve fitting on the local range to obtain a second curve, wherein the local range represents a data range consisting of n data before and after the pressure data in the pressure data collected by the pressure sensor centered at the pressure data; calculating the degree of original noise performance. ,in, It represents the original noise performance of the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment. represents the first curve corresponding to the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment, A second curve representing the pressure data collected by the pressure sensor in the rth row and the cth column at the i-th moment; calculating a corrected noise performance degree, wherein the corrected noise performance degree is proportional to the original noise performance degree and is also proportional to the difference between the pressures collected by the pressure sensor corresponding to the pressure data and the adjacent pressure sensor at the same moment; and filtering the pressure data to be filtered according to the size of the corrected noise performance degree.

[0008] Firstly, by installing a plurality of pressure sensors (r×c) in the mold, the present invention can monitor pressure data at different positions and obtain more comprehensive pressure distribution information in the mold; secondly, performing noise analysis on the pressure data of each sensor at each moment can help understand the reliability of the data, and by comparing with the pressure data of adjacent pressure sensors, the noise can be corrected more accurately; finally, the pressure to be filtered is screened and filtered based on the degree of corrected noise performance. By removing unnecessary filtered pressure data, the complexity of filtering calculation can be reduced, thereby greatly improving data processing efficiency.

[0009] Optionally, after collecting the pressure data at multiple positions in the mold, the method further includes: completing missing parts and performing abnormal correction processing on the pressure data.

[0010] During the production process, the pressure sensor may cause missing or abnormal data due to failure, signal interference or other reasons. Therefore, completing missing data and correcting abnormalities of the pressure data can improve the quality of the pressure data.

[0011] Optionally, the method for obtaining the first curve is: using a least squares method to perform first curve fitting on the pressure collected by the pressure sensor in a local range.

[0012] Optionally, the modified noise performance level , specifically: ,in, represents the original noise performance of the pressure data at the i-th moment collected by the pressure sensor at the r-th row and the c-th column, It represents the number of pressure sensors adjacent to the pressure sensor in the rth row and cth column. represents the pressure data collected by the pressure sensor in the rth row and the cth column at the i-th moment, Represents the pressure data collected by the pressure sensor in the jth row and the kth column at the i-th moment.

[0013] By comparing the data with the adjacent sensors and combining it with the original noise performance level, a more comprehensive and accurate corrected noise performance level can be obtained.

[0014] Optionally, the method of obtaining the pressure to be filtered by screening according to the magnitude of the corrected noise performance degree includes: sorting the pressure data collected by each pressure sensor from large to small according to the corresponding corrected noise performance degree, and screening the first T% of the pressure data as the pressure to be filtered.

[0015] Filtering only the pressure data with severe noise can greatly save computing resources and improve data processing efficiency.

[0016] Optionally, the filtering according to the magnitude of the corrected noise performance degree to obtain the pressure to be filtered includes: sorting the pressure data collected by each pressure sensor from large to small according to the corresponding corrected noise performance degree, and filtering the pressure data greater than a threshold value p as the pressure to be filtered, wherein the threshold value p= ,in, Indicates the performance level of the reference corrected noise corresponding to the pressure sensor. represents the hyperbolic tangent function, Indicates the mean value of the corrected noise performance corresponding to the pressure data collected by the pressure sensor.

[0017] The data range collected by the pressure sensor at each position is not necessarily the same, and the noise may also be different. By adaptively adjusting the corrected noise performance threshold of the pressure sensor at each position, the pressure to be filtered can be screened out more accurately.

[0018] Optionally, the filtering according to the magnitude of the modified noise performance degree to obtain the pressure data to be filtered and filtering it includes: filtering the pressure data to be filtered by adopting Gaussian filtering or non-local mean filtering.

[0019] In a second aspect of an embodiment of the present invention, a production data processing system based on a data middle platform is provided, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a production data processing method based on a data middle platform as described in any one of the first aspect of an embodiment of the present invention is implemented.

[0020] The beneficial effects of the present invention are as follows: first, by installing multiple pressure sensors (r×c) in the mold, the present invention can monitor pressure data at different positions and obtain more comprehensive pressure distribution information in the mold; second, performing noise analysis on the pressure data of each sensor at each moment can help understand the reliability of the data, and by comparing with the mean absolute error of adjacent sensor data, the noise can be corrected more accurately; finally, based on the degree of corrected noise performance, the pressure to be filtered is screened and filtered. By removing unnecessary filtered pressure data, the complexity of the filtering calculation can be reduced, greatly improving the data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 This is a flow chart of a production data processing method based on a data middle platform provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a mold provided by an embodiment of the present invention and equipped with 3×5 pressure sensors; Figure 3 It is a block diagram of a production data processing system based on a data middle platform provided in an embodiment of the present invention.

[0022] Figure numerals: 1. mold; 2. pressure sensor. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a flow chart of a production data processing method based on a data middle station provided by an embodiment of the present invention. Figure 1 The specific instructions are as follows: S101. Install r×c pressure sensors in the mold to collect pressure data at multiple positions in the mold, where r represents the number of rows and c represents the number of columns.

[0026] When producing workpieces, the pressure conditions at different locations in the mold used are also different, and a single sensor may not accurately reflect the pressure conditions of the entire mold. The pressure sensors are evenly distributed inside the mold to form a grid of r rows and c columns. This layout allows pressure data to be collected at different locations of the mold, providing comprehensive pressure monitoring.

[0027] During the production process, the pressure sensor may cause missing or abnormal data due to failure, signal interference or other reasons. Therefore, in some embodiments, it is also necessary to perform missing completion and abnormal correction processing on the pressure data collected by each pressure sensor to improve the quality of the pressure data. Generally, interpolation, mean or median filling methods can be used to fill missing values. For abnormal data, statistical methods can be used to screen out abnormal pressure data, such as Z-score detection method, and then missing completion processing can be performed on it. It should be noted that the above-mentioned missing completion and abnormal correction methods are all well-known technologies and will not be repeated here.

[0028] S102, performing a first curve fitting on the pressure data collected by the pressure sensor in a local range to obtain a first curve, using an interpolation method to calculate simulated pressure data, and performing a second curve fitting on the local range to obtain a second curve, wherein the local range represents a data range consisting of n data before and after the pressure data as the center in the pressure data collected by the pressure sensor.

[0029] For example, for the pressure sensor in row j and column k, the pressure data collected at time i is , assuming n=3, then according to The pressure data collected at the three moments before and after the first curve are fitted to obtain the first curve; then the , calculate the simulated pressure data at the i-th moment using the interpolation method based on the pressure data at multiple moments before and after , then according to The pressure data collected at the three moments before and after the second curve fitting is used to obtain the second curve. For the pressure data at the edge, its local range can be discarded accordingly. For example, in the above example, if If there is only one pressure data at the previous moment, then The pressure data of the previous moment, the pressure data of the next three moments and Perform a first curve fitting to obtain a first curve.

[0030] In some embodiments, the method for obtaining the first curve is: using the least square method to fit the first curve to the pressure collected by the pressure sensor in a local range. Correspondingly, the least square method can also be used to fit the second curve, which will not be described in detail here.

[0031] S103: Calculate the original noise performance level.

[0032] The original noise performance ,in, It represents the original noise performance of the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment. represents the first curve corresponding to the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment, represents the second curve corresponding to the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment. Characterizes the area enclosed by the first curve and the second curve in the local range. In order to avoid the area difference between the pressure data points at the edge and other data points being too large, a coefficient is set in front , in order to find the average value. In addition, for the pressure data points at the edge, the integral range can be discarded accordingly. For example, if n=3 and there is only one pressure data before the pressure data, the integral range is x=1 to x=5, and the coefficient Then 5-1=4.

[0033] S104: Calculate and correct the noise performance level.

[0034] The modified noise performance level is proportional to the original noise performance level and the mean absolute error of the pressure collected by the pressure sensor corresponding to the pressure data and the adjacent pressure sensors at the same time.

[0035] In some embodiments, the modified noise performance level , specifically: ,in, represents the original noise performance of the pressure data at the i-th moment collected by the pressure sensor at the r-th row and the c-th column, It represents the number of pressure sensors adjacent to the pressure sensor in the rth row and cth column. represents the pressure data collected by the pressure sensor in the rth row and the cth column at the i-th moment, Represents the pressure data collected by the pressure sensor in the jth row and the kth column at the i-th moment.

[0036] like Figure 2 The figure shows a schematic diagram of a mold provided by an embodiment of the present invention with 3×5 pressure sensors installed. If the corrected noise performance of the pressure sensor 2 in the 2nd row and the 3rd column at the i-th moment is to be calculated, it can be seen from the figure that the adjacent pressure sensors 2 are the 1st row and the 2nd column, the 1st row and the 3rd column, the 1st row and the 4th column, the 2nd row and the 2nd column, the 2nd row and the 4th column, the 3rd row and the 2nd column, the 3rd row and the 3rd column, and the 3rd row and the 4th column, a total of 8, so =8, It is the sum of the absolute values ​​of the differences between the pressure data collected by the pressure sensor 2 in the 2nd row and the 3rd column at the i-th moment and the pressure data collected by the adjacent eight pressure sensors 2 at the i-th moment.

[0037] S105, filtering the pressure data to be filtered according to the magnitude of the corrected noise performance and filtering the pressure data.

[0038] In some embodiments, the filtering according to the magnitude of the corrected noise performance degree to obtain the pressure to be filtered includes: sorting the pressure data collected by each pressure sensor 2 from large to small according to the corresponding corrected noise performance degree, and filtering the first T% of the pressure data as the pressure to be filtered.

[0039] For example, T=10 is preset, and for the pressure sensor 2 in the second row and third column, the pressure data collected by the pressure sensor 2 are screened, and the pressure data with the corrected noise performance in the top 10% is used as the pressure to be filtered.

[0040] In addition, since the pressure ranges at different positions in some molds 1 are different, a threshold value of the degree of corrected noise performance can also be set, and the pressure data collected by each pressure sensor 2 is sorted from large to small according to the corresponding degree of corrected noise performance, and the pressure data greater than the threshold value p is selected as the pressure to be filtered, and the threshold value p= ,in, Indicates the performance level of the reference correction noise corresponding to the pressure sensor 2, represents the hyperbolic tangent function, It represents the average value of the corrected noise performance level corresponding to the pressure data collected by the pressure sensor 2. For pressure sensors 2 at different positions or molds 1 in different working modes, the baseline corrected noise performance level corresponding to the pressure sensor 2 can be preset. , and then calculate the mean value of the corrected noise performance corresponding to the pressure data collected by the pressure sensor 2 , thereby obtaining the modified noise performance threshold value p corresponding to the pressure sensor 2. By adaptively adjusting the modified noise performance threshold value of the pressure sensor 2 at each position, the pressure to be filtered can be screened more accurately.

[0041] After obtaining the pressure to be filtered, it needs to be filtered. Generally, Gaussian filtering or non-local mean filtering can be used to filter the pressure data to be filtered. It should be noted that Gaussian filtering or non-local mean filtering belongs to the well-known technology and will not be described in detail here.

[0042] A production data processing method based on a data middle platform provided by an embodiment of the present invention can monitor pressure data at different positions by installing multiple pressure sensors 2 (r×c) in a mold, so as to obtain more comprehensive pressure distribution information in the mold 1; performing noise analysis on the pressure data of each sensor at each moment can help understand the reliability of the data, and by comparing with the pressure data of adjacent pressure sensors 2, the noise can be corrected more accurately; finally, the pressure to be filtered is selected and filtered based on the degree of corrected noise performance, and by removing unnecessary filtered pressure data, the complexity of filtering calculation can be reduced, thereby greatly improving data processing efficiency.

[0043] The present invention also provides a production data processing system based on a data middle station. Figure 3 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a production data processing method based on a data middle station described in the present invention is implemented.

[0044] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0045] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0046] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0047] Additionally, the articles "a," "an," and "an" as used in this disclosure are generally understood to mean "one or more," unless specified otherwise or clear from context to be directed to a singular form.

[0048] Where "including," "having," "having," "having," or variations thereof are used in the detailed description, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0049] In some of the processes described in the specification of the present invention and the above-mentioned drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed or executed in parallel in the order in which they appear in this article, and the sequence numbers of the operations, such as S1, S2, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that if descriptions such as "first", "second", "A1", "B1" appear in this article, then their role is to distinguish different messages, devices, modules, etc., does not represent the order of precedence, does not have any technical meaning, and does not limit "A1", "B1", "first" and "second" to be different types.

[0050] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. The production data processing method based on the data middle station is characterized by: include: Install r×c pressure sensors in the mold to collect pressure data at multiple locations in the mold, where r represents the number of rows and c represents the number of columns; Performing a first curve fitting on the pressure data collected by the pressure sensor in a local range to obtain a first curve, using an interpolation method to calculate simulated pressure data, and performing a second curve fitting on the local range to obtain a second curve, wherein the local range represents a data range consisting of n data before and after the pressure data as the center in the pressure data collected by the pressure sensor; Calculate the original noise representation ,in, It represents the original noise performance of the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment. represents the first curve corresponding to the pressure data collected by the pressure sensor at the rth row and the cth column at the i-th moment, The second curve represents the pressure data collected by the pressure sensor at the rth row and the cth column at the ith moment; Calculating a modified noise performance degree, wherein the modified noise performance degree is proportional to the original noise performance degree and is also proportional to the difference between the pressures collected by the pressure sensor corresponding to the pressure data and the adjacent pressure sensor at the same time; The pressure data to be filtered is obtained according to the magnitude of the corrected noise performance and filtered.

2. The production data processing method based on the data middle station according to claim 1 is characterized in that: After collecting the pressure data of multiple positions in the mold, the method further includes: performing missing completion and abnormal correction processing on the pressure data.

3. The production data processing method based on the data middle station according to claim 1 is characterized in that: The method for obtaining the first curve is: using the least square method to perform first curve fitting on the pressure collected by the pressure sensor in a local range.

4. The production data processing method based on the data middle station according to claim 1 is characterized in that: The modified noise performance level , specifically: ,in, represents the original noise performance of the pressure data at the i-th moment collected by the pressure sensor at the r-th row and the c-th column, It represents the number of pressure sensors adjacent to the pressure sensor in the rth row and cth column. represents the pressure data collected by the pressure sensor in the rth row and the cth column at the i-th moment, Represents the pressure data collected by the pressure sensor in the jth row and the kth column at the i-th moment.

5. The production data processing method based on the data middle station according to claim 1 is characterized in that: The step of selecting the pressure to be filtered according to the degree of the modified noise performance comprises: The pressure data collected by each pressure sensor are sorted from large to small according to the corresponding corrected noise performance level, and the first T% of the pressure data are selected as the pressure to be filtered.

6. The production data processing method based on the data middle station according to claim 1 is characterized in that: The step of selecting the pressure to be filtered according to the degree of the modified noise performance comprises: The pressure data collected by each pressure sensor are sorted from large to small according to the corresponding corrected noise performance, and the pressure data greater than the threshold p is selected as the pressure to be filtered, where the threshold p= ,in, Indicates the performance level of the reference corrected noise corresponding to the pressure sensor. represents the hyperbolic tangent function, Indicates the mean value of the corrected noise performance corresponding to the pressure data collected by the pressure sensor.

7. The production data processing method based on the data middle station according to claim 1 is characterized in that: The pressure data to be filtered is obtained according to the magnitude of the modified noise performance and filtered, including: filtering the pressure data to be filtered by Gaussian filtering or non-local mean filtering.

8. A production data processing system based on a data middle station, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the production data processing method based on the data middle platform according to any one of claims 1 to 7 is implemented.

Images