A process status detection method for a hand-painted nano-coated canvas preparation process

Abstract

The present invention relates to the field of data processing technology, and more specifically, the present invention relates to a process status detection method for a hand-painted nano-coated canvas preparation process, the method comprising: obtaining humidity data at different positions during the canvas drying process, denoising the humidity data using an improved IDR algorithm, and when the denoised humidity data at all positions are lower than a preset humidity threshold for a continuous preset time, it is determined that the drying process is completed. Among them, the process of obtaining denoised humidity data in the improved IDR algorithm is: obtaining a difference sequence of the humidity data sequence at any position within the sampling period and the noise performance of the corresponding data point in the comparison sequence, and executing the IDR algorithm based on the difference sequence to iteratively update the data process until the preset convergence condition is met, and the denoised humidity data sequence at the position is obtained. The present invention can improve the accuracy of canvas process status detection.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology. More specifically, the present invention relates to a process state detection method for a hand-painted nano-coated canvas preparation process. Background Art

[0002] Hand-painted nano-coated canvas is a painting carrier that uses grey cloth as the base material, is coated with one or more layers of coating on one side, and is supported by a frame on the other side. In the preparation process of canvas, drying is a crucial link. Accurate judgment of the drying state has an important impact on ensuring the quality of the coating and improving the performance of the canvas.

[0003] In the related art, a method for determining the drying time of textiles based on multivariate nonlinear regression is disclosed in a patent application document with publication number CN113722908A. The method includes: conducting experiments on textiles with different humidity and different materials in a dryer at different drying temperatures to obtain the corresponding drying time, obtaining textile drying time data, and constructing a textile drying time prediction model. When it is judged that the prediction result of the prediction model is correct, the humidity, material and drying temperature of the textile are input into the optimized multivariate nonlinear regression prediction model to obtain the predicted drying time of the textile.

[0004] However, when constructing a textile drying time prediction model in the above scheme, a large number of experiments are required to construct sample data, which is inefficient and does not take into account the influence of noise data in the acquired data. The training of the model may be affected to a certain extent, resulting in the inability to make accurate predictions based on the trained model, affecting the accurate prediction of the textile drying time and making it impossible to accurately detect the drying state of the textile. Summary of the invention

[0005] In order to solve the problem of inaccurate detection of the drying status of items, the present invention proposes a process status detection method for a hand-painted nano-coated canvas preparation process. The method comprises:

[0006] Get humidity data at different positions during the canvas drying process;

[0007] The humidity data is denoised using the improved IDR algorithm. When the denoised humidity data at all locations is lower than the preset humidity threshold for a continuous preset period of time, the drying process is completed.

[0008] The improved IDR algorithm is used to denoise the humidity data as follows: obtain the difference sequence between the humidity data sequence at any position in the sampling period and the noise performance of the corresponding data point in the comparison sequence, and perform the IDR algorithm iterative data update process based on the difference sequence until the preset convergence condition is met to obtain the denoised humidity data sequence at the position; the comparison sequence is a sequence composed of the average values ​​of the adjacent data points of each data point in the humidity data sequence;

[0009] The process of obtaining noise performance is as follows: calculate the average fitting error between the humidity data at any location and the humidity data at the surrounding locations at any sampling time, as well as the difference between the humidity data and the humidity data at the surrounding locations, preset the local range of the humidity data, obtain the range of the data within the local range, and use the range to correct the product of the average fitting error and the difference to obtain the noise performance of the humidity data. The noise performance is positively correlated with the range.

[0010] The present invention uses an improved IDR algorithm to obtain denoised humidity data at different positions of the canvas, which can remove the noise data of the humidity data at each position while retaining the data characteristics of the humidity data at each position, so that the drying state of the canvas can be accurately judged based on the denoised humidity data.

[0011] Preferably, the product of the average fitting error and the difference is taken as the noise performance before correction, and the noise performance before correction satisfies the following relationship:

[0012] ;

[0013] In the formula, For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The value of humidity data at each location; For the At the sampling time The average value of humidity data of eight neighboring locations of a location; For the At the sampling time The average fitting error of humidity data at one location and eight neighboring locations.

[0014] The present invention integrates a variety of data and can preliminarily evaluate the possibility that the humidity data at each location at each sampling time is noise data.

[0015] Preferably, the method for obtaining the average fitting error includes:

[0016] Obtain a set of humidity data of any position and eight neighboring positions at any sampling time, fit the set, and obtain the fitting value of each data point in the set;

[0017] Calculate the average difference between the value of each data point in the set and the fitted value of the corresponding data point to obtain the average fitting error of the data points in the set.

[0018] The present invention can determine the distribution law of humidity data at each position and surrounding positions at each sampling time by calculating the average fitting error, so as to determine the reason for the difference between the humidity data at the corresponding position and the humidity data at the surrounding positions in combination with the distribution law.

[0019] Preferably, the noise performance satisfies the following relationship:

[0020] ;

[0021] In the formula, For the At the sampling time Noise performance of humidity data at each location; For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The local range of humidity data for each location; is the hyperbolic tangent function.

[0022] The present invention limits the range of noise expression to 0-1, which can reduce the amount of calculation and the difficulty of calculation.

[0023] Preferably, the range is a comprehensive range, and a method for obtaining the comprehensive range includes:

[0024] Obtain the maximum and minimum values ​​of the data in the local range of any data point in the humidity data sequence at any position within the sampling period, calculate the difference between the maximum and minimum values, and obtain the range of the data in the local range of the data point;

[0025] The ratio of the range of the data within the local range of the data point to the number of data within the local range of the data point is taken as the comprehensive range of the data within the local range of the data point.

[0026] The present invention can eliminate the influence of inconsistent number of data points in a local range on evaluating the change of local data of corresponding data points.

[0027] Preferably, the process of iteratively updating data by executing the IDR algorithm based on the difference sequence includes:

[0028] Obtain the ordinal number of the maximum value in the difference sequence, and use the data point corresponding to the ordinal number in the comparison sequence to replace the data point of the corresponding ordinal number in the humidity data sequence at any position to obtain the interpolated data sequence;

[0029] The average value of the adjacent data points of each data point in the interpolated data sequence is calculated to obtain a new comparison sequence, and the difference in the noise performance of the corresponding data points in the interpolated data sequence and the new comparison sequence is calculated to obtain a new difference sequence. The replacement process is repeated to iteratively update the data that meets the replacement conditions in the humidity data sequence at any position.

[0030] Preferably, the method for obtaining the denoised humidity data sequence includes:

[0031] Get the preset difference threshold;

[0032] When the maximum value of the new difference sequence obtained after any replacement is completed is less than the difference threshold, the replacement process is stopped, and the interpolation data sequence obtained after any replacement is completed is used as the denoised humidity data sequence at any position.

[0033] Preferably, the method for obtaining humidity data includes:

[0034] Installing a plurality of humidity sensors around the canvas at a preset interval, wherein the installation positions of the humidity sensors include a horizontal position and a vertical position;

[0035] The readings of each humidity sensor during the canvas drying process are obtained to obtain humidity data at different positions during the canvas drying process.

[0036] The present invention has the following effects:

[0037] 1. The present invention is based on the difference sequence of the humidity data sequence at any position in the sampling period and the noise performance of the corresponding data point in the comparison sequence, and executes the process of iteratively updating data using the IDR algorithm. This can improve the judgment conditions for updating data in the IDR algorithm and avoid replacing the real humidity data, thereby ensuring the accuracy of the denoised humidity data.

[0038] 2. The present invention calculates the average fitting error of the humidity data at each position and the surrounding positions, evaluates the distribution pattern of the humidity data at the corresponding position and the surrounding positions, can effectively distinguish the reasons for the difference between the humidity data at each position and the humidity data at the surrounding positions, and further corrects the data using the range of the data in the local range, thereby ensuring the accuracy of the determined noise performance.

[0039] 3. The present invention can accurately judge the state of the drying process based on the denoised humidity data at each position of the canvas, thereby ensuring the drying effect of the canvas. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] 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:

[0041] Figure 1 It is a schematic flow chart of the steps of a method for detecting the process status of a hand-painted nano-coated canvas preparation process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] Reference Figure 1 , a process state detection method for a hand-painted nano-coated canvas preparation process, comprising steps S1 to S3, specifically as follows:

[0045] S1: Obtain humidity data at different positions during the canvas drying process.

[0046] In an exemplary embodiment of the present invention, the determination of humidity data at different positions during the canvas drying process can be achieved by the following steps:

[0047] A plurality of humidity sensors are installed around the canvas at preset intervals, wherein the installation positions of the humidity sensors include horizontal positions and vertical positions; readings of each humidity sensor during the canvas drying process are obtained to obtain humidity data at different positions during the canvas drying process.

[0048] Specifically, a suitable spacing distance can be set according to the collection range of the selected humidity sensor. In this embodiment, the spacing distance is set to 10 cm, and multiple humidity sensors are evenly arranged with a spacing distance of 10 cm in the horizontal direction and the vertical direction around the canvas, so that the collection range of the humidity sensor can cover the entire canvas; then, at a certain collection frequency, such as 1 Hz, the readings of all humidity sensors during the canvas drying process are obtained to obtain a humidity data sequence at each position during the canvas drying process. This embodiment does not specifically limit the spacing distance and the collection frequency.

[0049] S2: Use the improved IDR algorithm to denoise the humidity data.

[0050] It should be noted that the iterative interpolation for data reconstruction algorithm (IDR) is a filtering smoothing algorithm based on small window movement, which gradually improves the estimated value of the data through iteration, so as to approach the true value. The process of iteratively updating the data of the algorithm is as follows: for a humidity data sequence S, first, the comparison sequence SC of the humidity data sequence S is calculated, and the comparison sequence SC is composed of the average value of the adjacent data points of each data point in the humidity data sequence S; then, the error between the values ​​of the corresponding data points of the humidity data sequence S and the comparison sequence SC is calculated to obtain the difference sequence, determine the location of the maximum value of the difference sequence, and use the data points at the corresponding positions in the comparison sequence SC to replace the data points at the corresponding positions in the humidity data sequence S, so as to obtain the interpolation sequence SN, and based on the interpolation sequence SN, calculate the new comparison sequence and the new difference sequence, and iteratively replace the qualified data points until the convergence condition is reached, and obtain the denoised humidity data sequence of the humidity data sequence S.

[0051] It should be further explained that, since there is humidity data with similar changes to the noise data during the canvas drying process, if the traditional IDR algorithm is used to remove the noise data in the humidity data, the real humidity data similar to the noise data may be replaced, so that the obtained denoised humidity data sequence cannot reflect the change characteristics of the real humidity data sequence, resulting in the loss of detail information. Therefore, the present invention improves the judgment conditions when the algorithm updates the data, that is, based on the difference in the noise performance of the humidity data sequence and the corresponding data points in the corresponding sequence, the data points that meet the replacement conditions are determined; it can accurately distinguish between noise data and real humidity data, avoid the real humidity data from being replaced, and thus avoid the loss of detail information. Among them, the present invention only improves the judgment conditions when the algorithm updates the data, and does not improve other processes, such as the replacement process of the iterative update of the algorithm, and the determination method of the comparison sequence.

[0052] Specifically, the improved IDR algorithm is used to obtain the denoised humidity data at different locations, including the following steps:

[0053] Step 1: Calculate the noise performance of each data point in the humidity data sequence at any location within the sampling period;

[0054] Specifically, the process of obtaining noise performance includes:

[0055] (1) Calculate the average fitting error between the humidity data at any location and the humidity data at the surrounding locations at any sampling time, as well as the difference between the humidity data and the humidity data at the surrounding locations, and take the product of the average fitting error and the difference as the noise performance of the humidity data before correction;

[0056] It should be noted that during the canvas drying process, the electrical equipment around the canvas will cause noise in the collected humidity data sequence, making the humidity data at this position significantly different from the humidity data at the surrounding positions. Therefore, the difference between the humidity data at any position and the humidity data at the surrounding positions at the same sampling time can be used to determine whether the humidity data at this position at the sampling time is noise data; at the same time, due to the influence of the gravity of the canvas, there will be obvious differences between the humidity data at a certain position and the surrounding positions, but the mutation of the noise data will cause the distribution law of the humidity data at the surrounding positions to be poor, and the difference caused by gravity will not change the distribution law of the humidity data at the surrounding positions. Therefore, the present invention combines this feature to calculate the noise performance before correction, and can measure the possibility that the humidity data at any position at any sampling time is noise data.

[0057] It should be further explained that the better the distribution regularity of the data, the easier it is to fit and the smaller the corresponding fitting error. Therefore, the present invention uses this feature to measure the distribution regularity of the humidity data at any location and the surrounding locations at any sampling moment by calculating the average fitting error between the humidity data at any location and the surrounding locations at the sampling moment.

[0058] In an exemplary embodiment of the present invention, the determination of the average fitting error between the humidity data at any location at any sampling time and the humidity data at surrounding locations can be achieved by the following steps:

[0059] Get a set of humidity data at any location and eight neighborhood locations at any sampling time, fit the set, and get the fitting value of each data point in the set; calculate the average difference between the value of each data point in the set and the fitting value of the corresponding data point, and get the average fitting error of the data points in the set.

[0060] It should be noted that any position refers to the area where a humidity sensor collects humidity data, and the eight-neighborhood position of the position refers to the data area collected by eight adjacent humidity sensors surrounding the humidity sensor. It should be noted that the number of eight-neighborhood positions of any position is at most 8.

[0061] Optionally, the least square method can be used to fit the set of humidity data of any position and the eight neighboring positions at any sampling time, or a polynomial fitting method can be used to fit, so as to obtain the fitting value of each data point in the set. This embodiment does not specifically limit the fitting method used.

[0062] Furthermore, after determining the average fitting error between the humidity data at any location at any sampling time and the humidity data at the surrounding locations, the noise performance of the humidity data before correction can be calculated by combining the difference between the humidity data and the humidity data at the eight neighboring locations. Specifically, the noise performance of the humidity data at any location at any sampling time before correction satisfies the following relationship:

[0063] ;

[0064] In the formula, For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The value of humidity data at each location; For the At the sampling time The average value of humidity data of eight neighboring locations of a location; For the At the sampling time The average fitting error of humidity data at one location and eight neighboring locations.

[0065] in, Reflects the At the sampling time The difference between the humidity data at a location and the humidity data at the eight neighboring locations of that location, the larger the value is, the greater the possibility that the humidity data is noise data.

[0066] Optionally, when the average fitting error of the humidity data at any position and the eight neighboring positions at any sampling moment is large, it means that the distribution pattern of the humidity data at this position and the surrounding positions at this sampling moment is poor. If the difference between the humidity data at this position and the humidity data at the surrounding positions at this sampling moment is large, then the difference is likely to be caused by noise data, indicating that the humidity data at this position at this sampling moment is likely to be noise data.

[0067] (2) Preset the local range of the humidity data, obtain the range of the data in the local range, and use the range to correct the product of the average fitting error and the difference to obtain the noise performance of the humidity data. The noise performance is positively correlated with the range.

[0068] The local range refers to a data segment that surrounds a preset number of data points, such as 11 data points, with a certain data point as the center and formed around the data point in the humidity data sequence collected from any position during the sampling period.

[0069] Optionally, when the preset number is 11, if the number of single-side data of any data point in the humidity data sequence is less than 5, the data on that side is discarded, and the data segment consisting of the data point and the 5 data points on the other side is used as the local range of the data point.

[0070] In an exemplary embodiment of the present invention, the range of data in a local range is a comprehensive range, and the comprehensive range can be determined by the following steps:

[0071] The maximum and minimum values ​​of the data in the local range of any data point in the humidity data sequence at any position in the sampling period are obtained, and the difference between the maximum and minimum values ​​is calculated to obtain the range of the data in the local range of the data point; the ratio of the range of the data in the local range of the data point to the number of data in the local range of the data point is used as the comprehensive range of the data in the local range of the data point.

[0072] Optionally, since the amount of data contained in the local range of each humidity data may be different, the ratio of the range of the data in the local range to the number in the local range can be used to reduce the impact of the amount of data in the local range, thereby accurately evaluating the change of the data in the local range.

[0073] Furthermore, after the comprehensive range of the humidity data at any location at any sampling time is determined, the noise performance of the humidity data before correction can be corrected to obtain the noise performance of the humidity data.

[0074] Specifically, the noise performance of humidity data at any location at any sampling time satisfies the following relationship:

[0075] ;

[0076] In the formula, For the At the sampling time Noise performance of humidity data at each location; For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The range of the humidity data in the local area of ​​each location, in this embodiment, the range is a comprehensive range; is a hyperbolic tangent function, which is used to normalize the product of the noise performance before correction and the range.

[0077] in, It reflects the span of data values ​​within the local range of the humidity data. The larger the value, the more drastic the data change within the local range, and the corresponding humidity data is more likely to be noise data.

[0078] It should be noted that the existence of noise data may cause drastic changes in the data in the local range, and the comprehensive range can explain the changes in the data in the local range. Therefore, based on this feature, the present invention uses the comprehensive range to correct the noise performance before the humidity data is corrected, which can improve the accuracy of the determined noise performance.

[0079] In another embodiment, the noise performance before correction may also be corrected in other ways, such as correcting by a summation formula instead of a product calculation formula.

[0080] Step 2: Obtain the difference sequence between the humidity data sequence at the location and the noise performance of the corresponding data point in the comparison sequence; perform the IDR algorithm iterative data update process based on the difference sequence until the preset convergence condition is met to obtain the denoised humidity data sequence at the location.

[0081] The comparison sequence is a sequence composed of the average values ​​of adjacent data points of each data point in the humidity data sequence at any position within the sampling period; the difference sequence is a sequence composed of the difference in noise performance between the humidity data sequence and the corresponding data point in the comparison sequence. It should be noted that the difference can be the absolute value of the difference in noise performance of the corresponding data point, or the square difference of the noise performance of the corresponding data point, as long as it can reflect the difference in noise performance between the humidity data sequence and the corresponding data point in the corresponding sequence.

[0082] In an exemplary embodiment of the present invention, the iterative update of the humidity data sequence at any location within the sampling period can be achieved by the following steps:

[0083] (1) Obtain the ordinal number of the maximum value in the difference sequence, and use the data point corresponding to the ordinal number in the comparison sequence to replace the data point with the corresponding ordinal number in the humidity data sequence at any position to obtain the interpolated data sequence;

[0084] For example, when the humidity data sequence at any position in the sampling period is compared with the comparison sequence, the ordinal number of the maximum value of the difference sequence of the noise performance of the corresponding data point is When the first data point, replace the first data point in the humidity data sequence data points to obtain the interpolated data sequence.

[0085] (2) Calculate the average value of the adjacent data points of each data point in the interpolated data sequence to obtain a new comparison sequence, and calculate the difference in the noise performance of the corresponding data points in the interpolated data sequence and the new comparison sequence to obtain a new difference sequence. Repeat the replacement process to iteratively update the data that meets the replacement conditions in the humidity data sequence at any position.

[0086] Optionally, by iteratively updating the data in the humidity data sequence that meets the replacement condition, data points in the humidity data sequence that are more likely to be noise data can be removed, so that when the process of iteratively updating the data meets the preset convergence condition, the replacement process is stopped to obtain a denoised data sequence.

[0087] In an exemplary embodiment of the present invention, the determination of the denoised data sequence at any position can be achieved by the following steps:

[0088] A preset difference threshold is obtained; when the maximum value of the new difference sequence obtained after any replacement is completed is less than the difference threshold, the replacement process is stopped, and the interpolated data sequence obtained after any replacement is completed is used as the denoised humidity data sequence at any position.

[0089] Optionally, the difference threshold can be set to 0.1. When the minimum value of the difference sequence obtained after any replacement is less than 0.1, it means that the process of iteratively updating the data meets the preset convergence condition. In this case, the replacement process is stopped and the interpolated data sequence obtained after the replacement is completed is used as the denoised humidity data sequence at the corresponding position.

[0090] S3: When the denoised humidity data of all positions are lower than the preset humidity threshold for a continuous preset time period, the drying process is completed.

[0091] Optionally, step S2 can be used to denoise the humidity data at any position during the canvas drying process, and then the denoised humidity data at each position can be used to determine the drying state of the canvas. For example, during the canvas drying process, if the denoised humidity data at each position is lower than a humidity threshold, such as 50%RH, within a preset time period, such as 1 minute, it is determined that the canvas has reached a stable drying state, and the drying process can be stopped to complete the drying process.

[0092] Optionally, the denoised humidity data at each location may be used to analyze the humidity change trend of the canvas over time, thereby providing a data basis for analyzing the hygroscopicity, moisture permeability and other properties of the canvas.

[0093] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0094] 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 process status detection method for a hand-painted nano-coated canvas preparation process, characterized in that: include: Get humidity data at different positions during the canvas drying process; The humidity data is denoised using an improved IDR algorithm, and when the denoised humidity data at all locations is lower than a preset humidity threshold for a continuous preset period of time, the drying process is completed; The improved IDR algorithm is used to denoise the humidity data as follows: obtaining a difference sequence between the humidity data sequence at any position in the sampling period and the noise performance of the corresponding data point in the comparison sequence, and performing an IDR algorithm iterative data update process based on the difference sequence until the preset convergence condition is met to obtain the denoised humidity data sequence at the position; the comparison sequence is a sequence composed of the average values ​​of adjacent data points of each data point in the humidity data sequence; The process of obtaining the noise performance is as follows: calculating the average fitting error between the humidity data at any location and the humidity data at the surrounding locations at any sampling time, as well as the difference between the humidity data and the humidity data at the surrounding locations, presetting the local range of the humidity data, obtaining the range of the data within the local range, and using the range to correct the product of the average fitting error and the difference to obtain the noise performance of the humidity data, wherein the noise performance is positively correlated with the range.

2. The process status detection method of a hand-painted nano-coated canvas preparation process according to claim 1 is characterized in that: The product of the average fitting error and the difference is taken as the noise performance before correction, and the noise performance before correction satisfies the following relationship: ； In the formula, For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The value of humidity data at each location; For the At the sampling time The average value of humidity data of eight neighboring locations of a location; For the At the sampling time The average fitting error of humidity data at one location and eight neighboring locations.

3. The process status detection method of a hand-painted nano-coated canvas preparation process according to claim 2 is characterized in that: The method for obtaining the average fitting error comprises: Obtain a set of humidity data of any position and eight neighboring positions at any sampling time, fit the set, and obtain a fitting value of each data point in the set; The average difference between the value of each data point in the set and the fitting value of the corresponding data point is calculated to obtain the average fitting error of the data points in the set.

4. The process status detection method of a hand-painted nano-coated canvas preparation process according to claim 2 is characterized in that: The noise performance satisfies the following relationship: ； In the formula, For the At the sampling time Noise performance of humidity data at each location; For the At the sampling time The noise performance of humidity data at each location before correction; For the At the sampling time The local range of humidity data for each location; is the hyperbolic tangent function.

5. The process status detection method of a hand-painted nano-coated canvas preparation process according to claim 4 is characterized in that: The range is a comprehensive range, and the method for obtaining the comprehensive range includes: Obtain the maximum and minimum values ​​of the data in the local range of any data point in the humidity data sequence at any position within the sampling period, calculate the difference between the maximum and the minimum, and obtain the range of the data in the local range of the data point; The ratio of the range of the data within the local range of the data point to the number of data within the local range of the data point is taken as the comprehensive range of the data within the local range of the data point.

6. The process status detection method of a hand-painted nano-coated canvas preparation process according to claim 1 is characterized in that: The process of executing the IDR algorithm iteratively updating data based on the difference sequence includes: Obtaining the ordinal number of the maximum value in the difference sequence, and using the data point corresponding to the ordinal number in the comparison sequence to replace the data point of the corresponding ordinal number in the humidity data sequence at any position, to obtain an interpolated data sequence; The average value of adjacent data points of each data point in the interpolated data sequence is calculated to obtain a new comparison sequence, and the difference in noise performance between the interpolated data sequence and the corresponding data points in the new comparison sequence is calculated to obtain a new difference sequence, and the replacement process is repeated to iteratively update the data that meets the replacement conditions in the humidity data sequence at any position.

7. The process status detection method for a hand-painted nano-coated canvas preparation process according to claim 6 is characterized in that: The method for obtaining the denoised humidity data sequence comprises: Get the preset difference threshold; When the maximum value of the new difference sequence obtained after any replacement is completed is less than the difference threshold, the replacement process is stopped, and the interpolation data sequence obtained after any replacement is completed is used as the denoised humidity data sequence at any position.

8. The process status detection method for a hand-painted nano-coated canvas preparation process according to claim 1 is characterized in that: The method for obtaining humidity data comprises: Installing a plurality of humidity sensors around the canvas at a preset interval, wherein the installation positions of the humidity sensors include a horizontal position and a vertical position; The readings of the humidity sensors during the canvas drying process are obtained to obtain humidity data at different positions during the canvas drying process.

Images