Protective clothing production data processing method and system

Abstract

The invention relates to the technical field of data processing, in particular to a protective clothing production data processing method and system, and the method comprises the steps: obtaining a temperature sequence and a pressure sequence in a protective clothing sterilization process; presetting the local range of the temperature, and calculating the noise influence degree of the temperature; correcting the noise influence degree by using the correlation between the temperature and the pressure collected at the sampling time corresponding to the local range; the method comprises the following steps: marking temperatures meeting a preset screening condition in a temperature sequence, presetting a sliding window, filtering all marked temperatures by using an SG filter, and in the filtering process, filtering by taking an interval between a current marked temperature and a next marked temperature as a sliding step length of a current sliding window to obtain a denoised temperature sequence. According to the invention, the denoising efficiency and denoising effect of the temperature sequence in the sterilization process of the protective clothing can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a protective clothing production data processing method and system. Background Art

[0002] Protective clothing is a key piece of equipment that protects workers from harmful substances, and strict quality control is required during the production process. By processing production data, we can ensure that the data is accurate and consistent, effectively monitor each link, promptly detect and correct problems, and ensure product quality. Sterilization equipment is crucial in the production of protective clothing, and the temperature during the sterilization process helps optimize the sterilization procedure and improve efficiency. However, due to various factors, the temperature may be interfered by noise, resulting in inaccurate data, which in turn affects the sterilization time and effect. Therefore, it is crucial to denoise the temperature during the sterilization process. It should be noted that the sterilization process is usually carried out in a confined space, and there is a close relationship between temperature and pressure: when the temperature rises, the pressure in the space increases, and vice versa. Therefore, in the process of temperature denoising, the relationship between temperature and pressure can be combined to ensure the accuracy of the denoising results.

[0003] The SG (Savitzky-Golay) filter is an algorithm commonly used in signal processing and data smoothing. The core idea is to smooth the noise and retain the trend or pattern of the signal by fitting a polynomial to the local area of ​​the data. Since the temperature in the sterilization process is crucial, every slight change can reflect the stability and efficiency of the sterilization process. Therefore, compared with other filtering algorithms, the SG (Savitzky-Golay) filter is more suitable for denoising the temperature in the sterilization process.

[0004] In the related art, a method and device for denoising sea clutter based on MEEMD and SG filtering is disclosed in a patent application document with publication number CN113378485A. The method comprises: firstly, using the CEEMD part in MEEMD to perform empirical mode decomposition on sea clutter. Then, using the permutation entropy in MEEMD to calculate the randomness of each order of empirical mode components, determining two thresholds, eliminating those greater than the maximum threshold, screening the empirical mode components within the threshold range, and identifying them as noise-dominated components. Finally, using SG filtering to filter the screened empirical mode components.

[0005] However, when the above scheme uses the SG filter to filter data, it is necessary to process the data one by one, and the processed data contains noise and normal data, which is inefficient. Moreover, when filtering normal data, due to the presence of noise, the sliding window may contain noise, thereby affecting the denoising effect. Summary of the invention

[0006] In order to solve the problem of low efficiency and accuracy when using SG filter for data denoising, the present invention provides a protective clothing production data processing method and system.

[0007] According to a first aspect of the present invention, a method for processing protective clothing production data is provided, comprising: Obtain the temperature sequence and pressure sequence during the sterilization process of protective clothing; Taking any temperature in the temperature sequence as the center, presetting the local range of the temperature, and calculating the noise impact degree of the temperature, the noise impact degree represents the difference between the deviation of the temperature and the average temperature in the local range, and the difference between the deviation of the remaining temperatures in the local range and the average temperature; The correlation between the temperature in the local range and the pressure at the corresponding sampling moment in the pressure sequence is used to correct the noise impact, and the correction value is negatively correlated with the correlation. Mark the temperatures that meet the preset screening conditions in the temperature sequence, and filter all marked temperatures using the SG filter based on the preset sliding window. During the filtering process, the interval between the current marked temperature and the next marked temperature is used as the sliding step of the current sliding window for filtering to obtain the denoised temperature sequence; The number of marked temperatures is positively correlated with the average value of the corrected noise influence degree in the temperature sequence, and the corrected noise influence degree of the marked temperatures is greater than the corrected noise influence degree of the unmarked temperatures.

[0008] The present invention can accurately measure the degree to which each temperature in the temperature sequence is affected by noise, mark the temperature that is most affected by noise, and denoise it. The consumption of computing resources is reduced, and the situation that normal temperature is incorrectly filtered due to the presence of noise is avoided, thereby ensuring the accuracy of the temperature sequence after denoising; and the sliding step size of the sliding window can be adaptively adjusted during the filtering process, thereby improving the filtering efficiency.

[0009] Preferably, the noise impact degree satisfies the following relationship: ; In the formula, The temperature series The degree of noise influence of each temperature; The temperature series The value of a temperature; The temperature series The average temperature within a local area; For this local area The value of a temperature; is the amount of data in the local area; The sign for the absolute value.

[0010] The present invention utilizes the local outlier characteristic of noise to ensure the accuracy of the calculated noise influence degree.

[0011] Preferably, the noise impact degree is corrected, including: Calculate the Pearson correlation coefficient between the temperature in the local range and the pressure at the corresponding sampling time in the pressure series to obtain the correlation; The correction value of the noise performance level satisfies the following relationship: ; In the formula, The temperature series The correction value of the noise influence degree of each temperature; The temperature series The degree of noise influence of each temperature; The temperature series The Pearson correlation coefficient between the temperature in the local range of a temperature and the pressure at the corresponding sampling moment in the pressure series; The natural constant An exponential function with base ; is the normalization function.

[0012] The present invention can avoid misjudging normal data changes as changes caused by noise, thereby accurately measuring the influence of noise on each temperature in the temperature sequence.

[0013] Preferably, the method for obtaining the number of marked temperatures includes: A quantity threshold is preset, the average value of the correction value of the noise influence degree of all temperatures in the temperature sequence is calculated, and percentile is calculated, the product of the percentile result and the quantity threshold is calculated, and the product is rounded to an integer value as the number of temperatures marked in the temperature sequence.

[0014] The present invention combines the overall noise level of the temperature sequence to determine the number of marked temperatures, thereby reducing the waste of computing resources.

[0015] Preferably, a method for obtaining temperatures in a temperature sequence that meet a preset screening condition includes: According to the correction value of the noise influence degree of the temperature, the temperature sequence is sorted from large to small to obtain an ordered temperature sequence; Starting from the first data in the ordered temperature sequence, data are selected in sequence until the number of selected data is the same as the number of marked temperatures, thereby obtaining the temperatures in the temperature sequence that meet the preset screening conditions.

[0016] The present invention can filter the temperature which is greatly affected by noise in a targeted manner, thereby avoiding the normal temperature from being wrongly filtered due to the existence of noise, and ensuring the accuracy of the filtering result.

[0017] Preferably, when the length of the sliding window is an odd number, all marked temperatures are filtered using an SG filter, including: When filtering the current marked temperature, a polynomial fitting is performed on the temperature in the current sliding window using the least square method to obtain a fitting value of the temperature in the current sliding window; The current marked temperature is replaced by the fitted value of the temperature at the center position in the current sliding window to filter the current marked temperature.

[0018] Preferably, when the length of the sliding window is an even number, all marked temperatures are filtered using an SG filter, including: The fitting value of the temperature in the current sliding window is obtained, and the current marked temperature is replaced by the average of the fitting values ​​of the two adjacent temperatures closest to the center position in the current sliding window to filter the current marked temperature.

[0019] According to a second aspect of the present invention, a protective clothing production data processing system is provided. The system includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the steps of the first aspect of the present invention.

[0020] The present invention has the following effects: The present invention can specifically denoise the temperatures in the temperature sequence that are greatly affected by noise, reduce the amount of calculation when filtering the temperature sequence, and ensure the accuracy of the filtering result; and when filtering each marked temperature, the sliding step size of the sliding window can be adaptively adjusted, thereby improving the filtering efficiency, so that the denoised temperature sequence in the sterilization process of protective clothing can be obtained quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. 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 The present invention is a flowchart of a method for processing protective clothing production data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Reference Figure 1 , a protective clothing production data processing method, including steps S1 to S4, specifically as follows: S1: Obtain the temperature sequence and pressure sequence during the sterilization process of protective clothing.

[0025] Specifically, the temperature and pressure during the sterilization process of the protective clothing can be collected using a temperature sensor and a pressure sensor, respectively, and the collection frequency can be set to 1 Hz to obtain a temperature sequence and a pressure sequence. The present invention does not specifically limit the frequency of data collection.

[0026] It should be noted that the sterilization process of protective clothing is usually carried out in a confined space. In this environment, there is a positive correlation between temperature and pressure: as the temperature rises, the pressure in the space will also increase accordingly. This is because the saturated vapor pressure of steam is closely related to temperature. The higher the temperature, the stronger the tendency of liquid water molecules to transform into gas, which leads to an increase in pressure in the space. Conversely, when the temperature decreases, the vaporization tendency of steam molecules weakens, and the pressure in the space also decreases. In view of the close relationship between temperature and pressure in the sterilization process of protective clothing, the relationship between temperature and pressure can better reflect the temperature change characteristics. Therefore, the present invention collects the pressure during the sterilization process of protective clothing to provide a data basis for the subsequent analysis of the temperature change characteristics.

[0027] S2: Taking any temperature in the temperature sequence as the center, preset the local range of the temperature, and calculate the noise impact degree of the temperature. The noise impact degree represents the deviation between the temperature and the average temperature in the local range, and the difference between the deviation between the remaining temperatures in the local range and the average temperature.

[0028] It should be noted that, since the temperature sensor will be affected by the ambient noise during the sterilization process of protective clothing, noise will be present in the collected temperature sequence, and the noise usually appears as local outliers. Therefore, the present invention uses this feature to measure the influence of noise on each temperature in the temperature sequence.

[0029] The local range refers to any temperature in the temperature sequence as the center, including The data segment of each temperature is It should be noted that when the length of the data segment on either side of any temperature in the temperature sequence is less than When , the data segment on this side is discarded, and the temperature and the data segment on the other side that meet the conditions are used as the local range of the temperature, where The floor symbol.

[0030] Specifically, the noise influence degree of any temperature in the temperature sequence satisfies the following relationship: ; In the formula, The temperature series The degree of noise influence of each temperature; The temperature series The value of a temperature; The temperature series The average temperature within a local area; For this local area The value of a temperature; is the amount of data in the local area; The sign for the absolute value.

[0031] in, Reflects the The deviation of a temperature from the average temperature in the local area of ​​that temperature; It reflects the overall deviation of the residual temperature in the local range from the average temperature in the local range; if the difference between the two is large, it means that the If the local outlier of a temperature is large, the temperature is more affected by noise, and the corresponding noise influence on the temperature is larger.

[0032] In another embodiment, the deviation of any temperature from the average temperature in the local range of the temperature can be expressed by a ratio, and the deviation of the remaining temperatures in the corresponding local range from the average value can also be expressed by a ratio. This embodiment does not specifically limit the way of expressing the deviation.

[0033] In another embodiment, the difference between the deviation of any temperature and the average temperature in the local range of the temperature and the deviation of the remaining temperatures in the local range and the average temperature can also be determined by a difference calculation formula instead of a ratio calculation formula.

[0034] S3: Use the correlation between the temperature in the local range and the pressure at the corresponding sampling time in the pressure sequence to correct the degree of noise influence, and the correction value is negatively correlated with the correlation.

[0035] It should be noted that during the sterilization process of protective clothing, its temperature will also be affected by human factors, resulting in a sudden change in temperature. This change is a normal data change, but the method of calculating the noise influence degree in step S2 may detect the normal data change as noise, so it is necessary to correct the noise influence degree calculated in step S2. In the sterilization process of protective clothing, there is a close positive correlation between temperature and pressure. Therefore, this feature of the present invention corrects the noise influence degree.

[0036] In an exemplary embodiment of the present invention, the determination of the corrected noise impact degree may be achieved by the following steps: Calculate the Pearson correlation coefficient between the temperature in the local range and the pressure at the corresponding sampling time in the pressure series to obtain the correlation; The correction value of the noise performance level satisfies the following relationship: ; In the formula, The temperature series The correction value of the noise influence degree of each temperature; The temperature series The degree of noise influence of each temperature; The temperature series The Pearson correlation coefficient between the temperature in the local range of a temperature and the pressure at the corresponding sampling moment in the pressure series; The natural constant An exponential function with base ; is the normalization function.

[0037] in, The larger the The greater the correlation between the temperature in the local range of a temperature and the pressure at the corresponding sampling moment in the pressure sequence, the less likely the temperature is affected by noise. Therefore, it is necessary to correct the degree of noise influence on the temperature downward to accurately assess the influence of noise on the temperature. It should be noted that the calculation method of the Pearson correlation coefficient between different data is a prior art and is not described in detail in this embodiment.

[0038] In another embodiment, the correlation between the temperature and pressure in the corresponding time period may be calculated in other ways, such as not determining it by the Pearson correlation coefficient, but by the Spearman rank correlation coefficient, the Kendall rank correlation coefficient, etc.

[0039] S4: Mark the temperatures that meet the preset filtering conditions in the temperature sequence, and filter all marked temperatures using the SG filter based on the preset sliding window. During the filtering process, the interval between the current marked temperature and the next marked temperature is used as the sliding step size of the current sliding window for filtering to obtain the denoised temperature sequence.

[0040] It should be noted that the temperatures collected during the sterilization process of protective clothing are not all noise. Therefore, when directly using the traditional SG (Savitzky-Golay) filter for denoising, it is usually necessary to fit each temperature, that is, to gradually fit the temperature sequence through a sliding window (step size of 1) to remove the noise. The amount of calculation is large, and there may be a waste of computing resources. In addition, when the traditional SG filter filters the data around the noise, because the sliding window contains normal data and noise, the normal data is affected and deviations occur, thereby generating a filter wave phenomenon, which in turn affects the denoising effect. Therefore, the present invention improves the traditional SG filter, that is, by adaptively adjusting the sliding step size, the data is denoised in a targeted manner to improve the denoising effect while improving the processing efficiency.

[0041] Among them, when the temperatures that meet the preset screening conditions are marked in the temperature sequence, the number of marked temperatures is positively correlated with the average value of the corrected noise influence degree in the temperature sequence, and the corrected noise influence degree of the marked temperature is greater than the corrected noise influence degree of the unmarked temperature.

[0042] In an exemplary embodiment of the present invention, the determination of the number of marked temperatures may be achieved by the following steps: A quantity threshold is preset, the average value of the correction value of the noise influence degree of all temperatures in the temperature sequence is calculated, and percentile is calculated, the product of the percentile result and the quantity threshold is calculated, and the product is rounded to an integer value as the number of temperatures marked in the temperature sequence.

[0043] Specifically, the number of temperatures marked in the temperature sequence satisfies the following relationship: ; In the formula, is the number of temperatures marked in the temperature series; is a preset quantity threshold. In this embodiment ; It is the average value of the correction value of the noise influence degree of all temperatures in the temperature series; is the percentage symbol; The floor symbol.

[0044] in, The larger the value, the more noise there is in the temperature series, and more temperatures can be marked for filtering; on the contrary, The smaller it is, the less noise there is in the temperature series, and fewer temperatures can be marked for filtering, thus saving computing resources.

[0045] In an exemplary embodiment of the present invention, the following steps may be used to determine the temperature in the temperature sequence that satisfies the preset screening condition: According to the correction value of the degree of noise influence of temperature, the temperature sequence is sorted from large to small to obtain an ordered temperature sequence; starting from the first data in the ordered temperature sequence, data are selected in sequence until the number of selected data is the same as the number of marked temperatures, to obtain the temperature in the temperature sequence that meets the preset screening conditions.

[0046] Among them, the preset screening condition is that the corrected noise impact level is at a high level.

[0047] For example, the first As a reference data segment, if any temperature is within the reference data segment, it means that the corrected noise impact of the temperature is at a high level and meets the screening conditions; otherwise, it is determined that the corrected noise impact of the temperature is at a low level and does not meet the screening conditions. In this way, all temperatures in the temperature sequence that meet the preset screening conditions can be screened. Among them, is the number of temperatures marked in the temperature series.

[0048] Optionally, by screening and marking the temperatures in the temperature sequence that meet the preset screening conditions, the temperatures in the temperature sequence that are greatly affected by noise can be identified, so that data denoising can be performed in a targeted manner to avoid the situation where normal temperatures are incorrectly filtered due to the presence of noise, thereby ensuring the accuracy of the denoising results.

[0049] Furthermore, after all the marked temperatures in the temperature sequence are determined, a sliding window may be preset and the first marked temperature may be filtered using an SG filter.

[0050] In an exemplary embodiment of the present invention, if the length of the sliding window is an odd number, filtering of any marked temperature can be achieved by the following steps: When filtering the current marked temperature, the least squares method is used to perform polynomial fitting on the temperature in the current sliding window to obtain the fitting value of the temperature in the current sliding window; the fitting value of the temperature at the center position in the current sliding window is used to replace the current marked temperature to filter the current marked temperature.

[0051] It should be noted that when using the SG filter to filter data, the length of the selected sliding window is generally an odd number. When filtering data based on a sliding window with an odd length, the fitted value of the data at the center of the sliding window is often used to replace the filtered data, thereby ensuring the accuracy of the filtering result.

[0052] Optionally, the length of the sliding window selected in this embodiment is ,in ; and when the least squares fitting is used to perform polynomial fitting on the temperature in the current sliding window, the order of the polynomial used is 2. Of course, a sliding window of appropriate length and polynomial order may also be selected according to specific circumstances, and this embodiment does not specifically limit this. It should be noted that the process of performing polynomial fitting using the least squares method is a prior art, and this embodiment will not be described in detail herein.

[0053] In another exemplary embodiment of the present invention, when the length of the sliding window is an even number, filtering of any marked temperature can be achieved by the following steps: The fitting value of the temperature in the current sliding window is obtained, and the current marked temperature is replaced by the average of the fitting values ​​of the two adjacent temperatures closest to the center position in the current sliding window to filter the current marked temperature.

[0054] For example, when the length of the sliding window is , then use the current sliding window, The temperature and The average of the fitted values ​​of the temperatures is used to replace the filtered marked temperature at the current moment.

[0055] Furthermore, after the first marked temperature is filtered using the SG filter, the interval between the marked temperature and the next marked temperature is used as the sliding step of the sliding window, so that the next marked temperature is filtered using the sliding window after sliding, and so on, until all marked temperatures are filtered to obtain a denoised temperature sequence. Thus, the temperature sequence can be filtered by adaptively adjusting the sliding step, thereby improving the filtering efficiency.

[0056] Optionally, after determining the denoised temperature sequence in the sterilization process of protective clothing, in-depth analysis and mining can be carried out in combination with other relevant data in the production process of protective clothing, so as to obtain more accurate and targeted optimization measures and improvement plans to improve the efficiency of the protective clothing production process, optimize equipment configuration, and improve equipment maintenance efficiency.

[0057] The present invention also provides a protective clothing production data processing system, the system includes a memory and a processor, and a computer program is stored in the memory, the computer program integrates the function of a protective clothing production data processing method, when the computer program is executed, a protective clothing production data processing method can be used to improve the denoising efficiency and denoising effect of the temperature sequence in the sterilization process of protective clothing.

[0058] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0059] 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. A method for processing protective clothing production data, characterized in that: include: Obtain the temperature sequence and pressure sequence during the sterilization process of protective clothing; Taking any temperature in the temperature sequence as the center, presetting a local range of the temperature, and calculating the noise influence degree of the temperature, wherein the noise influence degree represents the difference between the deviation of the temperature and the average temperature in the local range, and the difference between the deviation of the remaining temperatures in the local range and the average temperature; The noise influence degree is corrected by using the Pearson correlation coefficient between the temperature in the local range and the pressure at the corresponding sampling moment in the pressure sequence; Correction value: ; In the formula, The temperature series The correction value of the noise influence degree of each temperature; The temperature series The degree of noise influence of each temperature; The temperature series The Pearson correlation coefficient between the temperature in the local range of a temperature and the pressure at the corresponding sampling moment in the pressure series; The natural constant An exponential function with base ; is the normalization function; Mark the temperatures in the temperature sequence that meet the preset screening conditions, and filter all marked temperatures using the SG filter based on the preset sliding window. During the filtering process, the interval between the current marked temperature and the next marked temperature is used as the sliding step of the current sliding window for filtering to obtain a denoised temperature sequence; The number of marked temperatures is positively correlated with the average value of the corrected noise influence degree in the temperature sequence, and the corrected noise influence degree of the marked temperatures is greater than the corrected noise influence degree of the unmarked temperatures.

2. A protective clothing production data processing method according to claim 1, characterized in that: The noise impact degree satisfies the following relationship: ； In the formula, The temperature series The degree of noise influence of each temperature; The temperature series The value of a temperature; The temperature series The average temperature within a local area; For this local area The value of a temperature; is the amount of data in the local area; The sign for the absolute value.

3. A protective clothing production data processing method according to claim 1, characterized in that: The method for obtaining the number of marked temperatures includes: A quantity threshold is preset, an average value of the correction value of the noise influence degree of all temperatures in the temperature sequence is calculated and percentileized, a product of the percentile result and the quantity threshold is calculated, and a value after rounding the product is taken as the number of temperatures marked in the temperature sequence.

4. A protective clothing production data processing method according to claim 3, characterized in that: The method for obtaining the temperature that meets the preset screening condition in the temperature sequence includes: According to the correction value of the noise influence degree of the temperature, the temperature sequence is sorted from large to small to obtain an ordered temperature sequence; Starting from the first data in the ordered temperature sequence, data are selected in sequence until the number of the selected data is the same as the number of the marked temperatures, thereby obtaining the temperatures in the temperature sequence that meet the preset screening conditions.

5. A protective clothing production data processing method according to claim 1, characterized in that: When the length of the sliding window is an odd number, the filtering of all marked temperatures using the SG filter includes: When filtering the current marked temperature, a polynomial fitting is performed on the temperature in the current sliding window using the least square method to obtain a fitting value of the temperature in the current sliding window; The current marked temperature is replaced by the fitted value of the temperature at the center position in the current sliding window to filter the current marked temperature.

6. A protective clothing production data processing method according to claim 5, characterized in that: When the length of the sliding window is an even number, the filtering of all marked temperatures using the SG filter includes: The fitting value of the temperature in the current sliding window is obtained, and the current marked temperature is replaced by the average of the fitting values ​​of the two adjacent temperatures closest to the center position in the current sliding window to filter the current marked temperature.

7. A protective clothing production data processing system, characterized in that: The protective clothing production data processing system comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

Images