A data monitoring method and system for PPS masterbatch processing

Abstract

The present invention relates to the field of data processing technology, and specifically to a data monitoring method and system for a PPS masterbatch processing process, the method comprising: obtaining a spectrum of a polyphenylene sulfide PPS masterbatch; based on the spectrum, determining the overall purity of the PPS masterbatch during the preparation process; based on the overall purity, determining the corresponding purity authenticity; based on the purity authenticity, determining the purity abnormality score of the PPS masterbatch during the preparation process; based on the purity abnormality score, performing data monitoring on the preparation process of the PPS masterbatch. The method can accurately determine the purity abnormality score of the PPS masterbatch during the preparation process by analyzing PPS masterbatches with different purity authenticity, thereby performing data monitoring on the preparation process of the PPS masterbatch through the purity abnormality score, and can improve the accuracy of monitoring the PPS masterbatch processing process.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data monitoring method and system for a PPS masterbatch processing process in the technical field of data processing. Background Art

[0002] As an engineering plastic, the performance and use of polyphenylene sulfide (PPS) masterbatch are directly affected by the purity of the masterbatch during the preparation process. High-purity masterbatch can ensure that the final product has stable physical and chemical properties, such as mechanical strength, heat resistance, chemical corrosion resistance, etc., so it is very important to monitor the purity of PPS masterbatch in each production process.

[0003] Generally, infrared spectroscopy is used to perform spectral analysis to detect the purity of each prepared PPS masterbatch, and then the concentration data of all preparation processes are used as the characteristic value of the isolated forest to calculate the anomaly score to determine the purity of the abnormal preparation process. However, many PPS masterbatches can be prepared in each preparation process, and the purity of these masterbatches is different; some have high purity and some have low purity. Therefore, the purity of the PPS masterbatch obtained above is not necessarily true, and if it is untrue data, the anomaly score obtained by the isolated forest algorithm to monitor the preparation process may also have a large error, resulting in low monitoring accuracy of the PPS masterbatch processing. Summary of the invention

[0004] In order to solve the technical problem of low monitoring accuracy of the PPS masterbatch processing in the prior art, the object of the present invention is to provide a data monitoring method and system for the PPS masterbatch processing. The technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a data monitoring method for a PPS masterbatch processing process, the method comprising:

[0006] Obtain the spectrum of polyphenylene sulfide PPS masterbatch;

[0007] Based on the spectrogram, determining the overall purity of the PPS masterbatch during the preparation process;

[0008] Based on the overall purity, determining the corresponding purity authenticity;

[0009] Based on the purity authenticity, determining the purity abnormality score of the PPS masterbatch during the preparation process;

[0010] Based on the purity abnormality score, data monitoring is performed on the preparation process of the PPS masterbatch.

[0011] In a second aspect, a data monitoring system for a PPS masterbatch processing process is provided, the system comprising:

[0012] An acquisition module, used for acquiring a spectrum of polyphenylene sulfide PPS masterbatch;

[0013] A first determination module is used to determine the overall purity of the PPS masterbatch during the preparation process based on the spectrum;

[0014] A second determination module, configured to determine the corresponding purity authenticity based on the overall purity;

[0015] A third determination module is used to determine the purity abnormality score of the PPS masterbatch during the preparation process based on the purity authenticity;

[0016] A monitoring module is used to perform data monitoring on the preparation process of the PPS masterbatch based on the purity abnormality score.

[0017] According to a third aspect, a computer program product is provided. The computer program product includes: a computer program code. When the computer program code is executed on a computer, the computer executes the method according to the first aspect.

[0018] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed on a computer, the computer executes the method according to the first aspect.

[0019] The present invention has the following beneficial effects: after obtaining the spectrum of the polyphenylene sulfide PPS masterbatch, the overall purity of the PPS masterbatch in the preparation process is determined based on the spectrum, so that the overall purity of the PPS masterbatch in the preparation process can be accurately calculated through spectral analysis. Afterwards, the corresponding purity authenticity is determined through the overall purity, and the purity abnormality score of the PPS masterbatch in the preparation process is determined based on the purity authenticity; in this way, by analyzing PPS masterbatches with different purity authenticity, the purity abnormality score of the PPS masterbatch in the preparation process can be accurately determined, so that the preparation process of the PPS masterbatch is monitored by data through the purity abnormality score, which can improve the accuracy of monitoring the processing of the PPS masterbatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a schematic diagram of a process flow of implementing a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0022] Figure 2 It is another implementation flow diagram of a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0023] Figure 3 It is a schematic diagram of an application scenario of a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0024] Figure 4 It is another implementation flow diagram of a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0025] Figure 5 It is another implementation flow diagram of a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0026] Figure 6 It is a curve schematic diagram of the purity of PPS masterbatch in a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0027] Figure 7 It is a schematic diagram of the composition structure of a data monitoring system for a PPS masterbatch processing process provided by an embodiment of the present invention;

[0028] Figure 8 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a data monitoring method for a PPS masterbatch processing process proposed by the present invention, its specific implementation, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0030] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0031] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0032] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0033] The following is a detailed description of a data monitoring method for a PPS masterbatch processing process provided by the present invention in conjunction with the accompanying drawings.

[0034] See also Figure 1 , which shows a flow chart of a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention. The method can be implemented by the following steps:

[0035] 101. Collect the spectrum of each PPS masterbatch after air-cooled pelletizing.

[0036] Here, a collection plan is designed first, and then the spectrum of each PPS masterbatch after air-cooled pelletizing is collected according to the collection plan.

[0037] 102. According to the spectrum, determine the initial purity of each PPS masterbatch.

[0038] 103, determine the authenticity of the initial purity of each PPS masterbatch.

[0039] 104, determine the overall purity and authenticity of PPS masterbatch in each preparation process.

[0040] 105, an isolation forest is constructed according to the overall purity of PPS masterbatches in all preparation processes, and a binary tree path is obtained.

[0041] 106, assign weights to all binary tree paths according to their authenticity.

[0042] 107, determine the purity anomaly score for each preparation process.

[0043] 108. Monitor the preparation process according to the purity abnormality score of the PPS masterbatch of each preparation process.

[0044] In the embodiment of the present invention, feature analysis is first performed to obtain the true purity of the PPS masterbatch in each preparation process through these PPS masterbatches with different authenticity in each preparation process, and the authenticity of this purity is obtained; finally, the path weight of each binary tree of the isolated forest is corrected by authenticity to correct the abnormal score, so as to improve the accuracy of monitoring the PPS masterbatch processing process.

[0045] The embodiment of the present invention provides a data monitoring method and system for a PPS masterbatch processing process. Figure 2 The steps shown achieve:

[0046] 201, obtain the spectrum of PPS masterbatch.

[0047] Here, a collection plan is first formulated, and the initial PPS masterbatch is air-cooled and pelletized according to the collection plan to obtain multiple PPS masterbatches; then the multiple PPS masterbatches are subjected to infrared spectroscopy to obtain spectra of multiple PPS masterbatches. In some possible implementations, the collection plan includes: in the process of preparing PPS masterbatches, the PPS masterbatch is extruded through a screw extruder, and then air-cooled and pelletized to obtain PPS masterbatches. Afterwards, for each PPS masterbatch obtained by air-cooling and pelletizing, an infrared spectra of the masterbatch can be obtained by an infrared spectrometer, and the infrared spectra are as follows: Figure 3 As shown in the waveform 31 in FIG. 1 , the horizontal axis represents the wave number (wavenumber) and the vertical axis represents the transmittance (transmittance).

[0048] 202. Determine the overall purity of the PPS masterbatch during the preparation process based on the spectrum.

[0049] Here, since the spectrum includes multiple wavelengths, the probability of each wavelength being the center of the overall distribution is calculated. Then, the suspected absorption peak and the wavelength of the absorption peak, i.e., the candidate absorption peak wavelength, are determined through the probability of each wavelength being the center of the overall distribution; so that the initial purity of each PPS masterbatch in the preparation process can be calculated through the candidate absorption peak wavelength, and the overall purity can be calculated through the initial purity combined with the purity authenticity.

[0050] In some possible implementations, the center of the normal distribution obtained by the spectrum is first compared with the center of the normal distribution of the standard PPS masterbatch to determine the purity of all PPS masterbatches prepared each time; then the purity authenticity is determined by the temporal purity variation characteristics of the wind-cut cold pellets; next, the overall purity and authenticity of each preparation process are determined by obtaining the authenticity of all PPS masterbatches in each preparation process; finally, the purity anomaly score of each preparation process is determined by assigning a binary tree path weight to the isolated forest based on the authenticity of each preparation process. The above step 202 can be performed by Figure 4 The steps shown achieve:

[0051] 401, in the spectrum diagram, determine the probability that any wavelength is the center of a normal distribution.

[0052] Here, because the components of PPS masterbatch are all normally distributed or close to normally distributed in the infrared spectrum, the infrared spectrum of standard PPS masterbatch is the superposition of a series of normal distribution curves. As for the absorption peak, it must be located at the symmetric center of the normal distribution curve, so first determine the probability that any wavelength v in the PPS masterbatch spectrum is the normal center, as shown in formula (1):

[0053] (1);

[0054] in, Represents a screening process (" "Wavelength screening" can be understood as wavelength screening based on photon energy, selecting a specific wavelength range based on the energy characteristics of the photon. However, in practical applications, screening can be performed directly based on the wavelength range). , It means that the first-order derivative of the corresponding point on the wavelength v is 0 and the second-order derivative is negative (convex function), f represents the maximum and minimum normalized function, represents the difference between the wavelength v and the wavelengths obtained after screening on the left and right sides, represents the probability that wavelength v is the center of the normal distribution. Respectively The first wavelength on the left and the first wavelength on the right obtained by screening.

[0055] The spectrum of PPS masterbatch can be regarded as the superposition of some normal distributions. For the center of the normal distribution, the local maximum convex point must be used first. However, some small oscillations may also be the local maximum convex points, and the local maximum convex point of the center of the normal distribution is at a certain distance from other normal distribution centers. Therefore, based on the local maximum convex point, the above formula is constructed to eliminate the influence of some small oscillations.

[0056] 402 : Determine a candidate absorption peak wavelength among the multiple wavelengths in the spectrum based on the probability.

[0057] Here, in the spectrum graph, the wavelength whose probability is greater than the preset probability threshold is determined; and the wavelength whose probability is greater than the preset probability threshold is determined as the candidate absorption peak wavelength. The preset probability threshold may be a custom threshold, for example, the preset probability threshold is 0.7. If the probability of any wavelength being the center of the normal distribution is greater than 0.7, the wavelength is determined to be the center of the normal distribution of the suspected PPS masterbatch spectrum graph, and the wavelength is determined to be a candidate absorption peak wavelength. In this way, by judging whether the probability of any wavelength being the center of the normal distribution is greater than the preset probability threshold, the candidate absorption peak wavelength with a higher probability can be quickly and accurately analyzed from the multiple wavelengths in the spectrum graph.

[0058] In some possible implementations, the preset probability threshold is set to 0.7. If the probability that any wavelength is the center of the normal distribution is greater than 0.7, then the wavelength is suspected to be the center of the normal distribution of the PPS masterbatch spectrum. Assuming that The wavelength is the normal distribution center of the suspected PPS masterbatch spectrum, that is is the candidate absorption peak wavelength.

[0059] 403 , determining the initial purity of any PPS masterbatch during the preparation process based on the candidate absorption peak wavelength and the preset standard substance catalog.

[0060] Here, the overall distribution curve and the spectrum fitting mixing curve are drawn through the candidate absorption peak wavelength and the center of the normal distribution to which the candidate absorption peak wavelength belongs, so as to accurately calculate the initial purity of any PPS masterbatch in the preparation process in combination with the constituent molecules of the PPS masterbatch.

[0061] In some possible implementations, the above step 403 can be performed by Figure 5 The steps shown achieve:

[0062] 501 . For any of the PPS masterbatches, based on the candidate absorption peak wavelength corresponding to the any of the PPS masterbatches, determine a normal distribution curve formed by taking the candidate absorption peak wavelength as the center of the normal distribution.

[0063] Here, the wavelength of the candidate absorption peak must contain the center of the normal distribution. If the wavelength i is the center of the normal distribution, the expression of the normal distribution curve is shown in formula (2):

[0064] (2);

[0065] in, represents the normal distribution curve formed by the wavelength i as the center of the normal distribution, Indicates wavelength. It means that the standard deviation of the center of a normal distribution is assumed to be i wavelength. Indicates that wavelength i is the mean of the center of a normal distribution, set To be greater than 1600 (because the absorption peaks of all PPS masterbatch components are greater than 1600). exp() represents an exponential function with the natural constant e as the base.

[0066] 502. Determine a spectral fitting mixing curve corresponding to any one of the PPS masterbatches based on the normal distribution curve and the candidate absorption peak wavelength.

[0067] Here, the spectral fitting mixing curve of the PPS masterbatch obtained by all candidate absorption peak wavelengths is shown in formula (3):

[0068] (3);

[0069] in, It represents the spectrum fitting mixed curve of PPS masterbatch obtained by all candidate absorption peak wavelengths. m means that the sample has a total of m wavelengths as candidate absorption peak wavelengths. Represents the coefficient before the normal distribution curve (if it tends to 0, it proves that there is no curve superposition with this point as the center of the normal distribution), It represents the normal distribution curve obtained by taking k wavelengths as the center of the normal distribution.

[0070] Since the PPS masterbatch spectrum can be regarded as the superposition of some normal distribution curves, and the wavelength of the candidate absorption peak must include the center of the normal distribution curve, the Gaussian curves of all candidate absorption peaks are accumulated (if the candidate absorption peak is the Gaussian center, H tends to 1, otherwise it tends to 0), and a mixed Gaussian curve with unknown parameters can be obtained.

[0071] 503, performing fitting estimation on the spectrum fitting mixing curve of any of the PPS master batches to obtain target parameters.

[0072] Here, the least square method can be used to perform optimal fitting estimation to obtain the optimal unknown parameters in the mixed Gaussian curve, that is, the target parameters. The target parameters may include: coefficients of the mixed Gaussian curve, that is, coefficients of the normal distribution curve, that is, the mean and standard deviation of the normal distribution curve, etc.

[0073] 504, determining the constituent molecules of the PPS masterbatch in a preset standard substance catalog.

[0074] Here, the preset standard substance catalogue can be a standard substance catalogue, including: all constituent molecules of the standard PPS masterbatch, so the constituent molecules of the PPS masterbatch can be found in the preset standard substance catalogue. The constituent molecules of the PPS masterbatch include: how many constituent molecules are there in the PPS masterbatch, the absorption peak wavelength corresponding to each constituent molecule, and the absorption peak value (that is, the data sequence is obtained). ,in, They represent the absorption peak wavelengths corresponding to the constituent molecules, Indicates the absorption peak wavelength corresponding to the nth constituent molecule. They represent the absorption peak values ​​corresponding to the constituent molecules, represents the peak absorption value corresponding to the nth constituent molecule).

[0075] 505 , determining the initial purity of any one of the PPS masterbatches during the preparation process based on the constituent molecules and the target parameters.

[0076] Here, after obtaining the constituent molecules of the PPS masterbatch, we can get the number of constituent molecules in the PPS masterbatch, the absorption peak wavelength corresponding to each constituent molecule, and the absorption peak value; and combine the absorption peak wavelength corresponding to each constituent molecule with the absorption peak value to calculate the initial purity of each PPS masterbatch during the preparation process.

[0077] In some possible implementations, the above step 505 may be implemented by the following steps 551 to 553 (not shown):

[0078] 551. Determine the absorption peak wavelength corresponding to the constituent molecule in the preset standard substance catalog.

[0079] 552, determine the difference between the candidate absorption peak wavelength and the intermediate absorption peak wavelength.

[0080] Here, the difference is obtained by subtracting the candidate absorption peak wavelength from the intermediate absorption peak wavelength.

[0081] 553, based on the difference, the preset standard substance catalog and the target parameter, determine the initial purity of any one of the PPS masterbatches during the preparation process.

[0082] Here, the initial purity of the i-th PPS masterbatch during the preparation process is shown in formula (4):

[0083] (4);

[0084] in, C represents the initial purity of the i-th PPS masterbatch during the preparation process, and m represents the wavelengths corresponding to a total of m candidate absorption peaks. Indicates that the wavelength corresponding to the kth candidate absorption peak is used as the target parameter of the normal distribution curve constructed by the normal distribution center. min indicates the selection of the minimum function. represents the wavelength corresponding to the kth candidate absorption peak as the highest value corresponding to the center of the normal distribution, and Not 0. Assume that k wavelength is the standard deviation of the center of a normal distribution, Represents the catalog of standard substances, the peak value of the absorption peak corresponding to the i-th constituent molecule of the standard PPS masterbatch, represents the kth wavelength corresponding to the candidate absorption peak, It represents the catalog of standard substances and the absorption peak wavelength corresponding to the i-th constituent molecule of the standard PPS masterbatch.

[0085] The above least squares method has obtained the optimal unknown parameters of all suspected normal distribution centers. The larger the value, the greater the probability that it belongs to the center of the normal distribution, and the closer it is to a wavelength and absorbance in the standard substance catalog, so each candidate absorption peak is On the basis of (which can constitute the basis of normal distribution), In this way, by adjusting the difference between the candidate absorption peak wavelength and the intermediate absorption peak wavelength through the target parameter, the initial purity of each PPS masterbatch during the preparation process can be accurately calculated, thereby facilitating the subsequent calculation of the overall purity of the PPS masterbatch to improve the accuracy of the calculation of the overall purity.

[0086] 404 , determining the overall purity based on the initial purity of the plurality of PPS masterbatches during the preparation process and the corresponding purity authenticity.

[0087] Here, by combining the initial purity of each PPS masterbatch with the corresponding purity authenticity, the overall purity of the PPS masterbatch can be accurately calculated.

[0088] In some possible implementations, the above step 404 may be implemented by the following steps 441 to 443 (not shown):

[0089] 441, determine the overall authenticity based on the authenticity corresponding to the initial purity of the plurality of PPS masterbatches during the preparation process.

[0090] Here, the purity change relationship is determined in the time sequence of the preparation process through the initial purity of the PPS masterbatch during the preparation process, and based on the purity change relationship and the initial purity of any masterbatch, the corresponding authenticity of the initial purity of any masterbatch is determined. In some possible implementations, for the air-cooled pelletizing process of the PPS masterbatch processing, since the air-cooled pelletizing is carried out in a hot cutting hood, a fan is used to blow air into the hot cutting hood for cooling to ensure the quality of the pellets during the pelletizing process (in this process, due to the high temperature in the early stage, some materials may not be completely evenly distributed, resulting in lower purity of the masterbatch). As the cooling time increases, the material gradually cools and solidifies, impurities and uneven substances are eliminated, and the purity of the masterbatch gradually increases. Therefore, the initial purity of the PPS masterbatch in each preparation process is as follows: Figure 6 As shown in curve 61 in , the abscissa represents time and the ordinate represents initial purity.

[0091] Among them, the relationship between the purity change of each preparation process of PPS masterbatch over time , as shown in formula (5):

[0092] (5);

[0093] Among them, combined with the value in curve 61, the purity of PPS masterbatch at all time sequences obtained in each preparation process is substituted into the function , and the function is fitted by the least square method to obtain the optimal parameters a, b, c; e represents the natural constant. The authenticity of the initial purity of the hth PPS masterbatch obtained in each preparation process is determined by the purity change relationship of the air-cooled pelletizing process, as shown in formula (6):

[0094] (6);

[0095] in, It indicates the authenticity of the initial purity of the hth PPS masterbatch obtained in each preparation process. exp indicates an exponential function with the natural constant e as the base. Indicates the actual purity of the hth PPS masterbatch, It means that the time when the hth PPS masterbatch is located is substituted into the above function The initial purity obtained. Because the purity change over time after air-cooling pelletizing conforms to the function model obtained above, the smaller the error with the function model, the higher the authenticity of the PPS masterbatch purity.

[0096] 442, determining the proportion of the authenticity corresponding to the initial purity of any PPS masterbatch in the preparation process in the total authenticity.

[0097] Here, the authenticity corresponding to the initial purity of multiple PPS masterbatches during the preparation process is first summed to obtain the total authenticity. The authenticity corresponding to the initial purity of any PPS masterbatch during the preparation process is divided by the total authenticity to obtain the proportion of the authenticity corresponding to the initial purity of any PPS masterbatch during the preparation process in the total authenticity.

[0098] 443, combining the initial purity of any one of the PPS masterbatches during the preparation process with the proportion to obtain the overall purity.

[0099] Here, the initial purity of any PPS masterbatch in the preparation process is multiplied by the proportion, and the overall purity is obtained by the multiplication result. The overall purity of the PPS masterbatch in each preparation process is shown in formula (7):

[0100] (7);

[0101] in, Indicates the overall purity of the PPS masterbatch in the preparation process, w means that a total of w PPS masterbatches are obtained, Indicates the authenticity of the hth masterbatch, Represents the purity of the hth masterbatch. Generally speaking, the overall purity of PPS masterbatch is the average purity of all masterbatches in the preparation process. However, interference from impurities and the like during the detection process may result in the purity of some masterbatches being untrue. Therefore, authenticity has a better contribution to its overall purity, and the above formula can be constructed. In this way, by analyzing the probability of each wavelength as the center of the normal distribution, suspected absorption peaks, i.e., candidate absorption peaks, are screened out, and the wavelength of the candidate absorption peak is determined; and by combining the initial purity of any PPS masterbatch in the preparation process with the corresponding purity authenticity, the overall purity of the PPS masterbatch can be analyzed quickly and accurately.

[0102] 203. Based on the overall purity, determine the corresponding purity authenticity.

[0103] Here, the proportion is adjusted by using the authenticity corresponding to the initial purity of any PPS masterbatch in the preparation process to obtain an adjusted proportion; for example, the authenticity corresponding to the initial purity of any PPS masterbatch in the preparation process is multiplied by the proportion to obtain the adjusted proportion. Then, based on the adjusted proportions corresponding to multiple PPS masterbatches combined with the overall purity, the purity authenticity corresponding to the overall purity is determined. For example, the purity authenticity of the PPS masterbatch in each preparation process is as shown in formula (8):

[0104] (8);

[0105] in, Indicates the purity authenticity of the PPS masterbatch in the preparation process; Indicates the overall purity of the PPS masterbatch in the preparation process; w means there are a total of w PPS masterbatches, In this way, the purity authenticity corresponding to the overall purity can be accurately calculated by combining the initial purity of any PPS masterbatch in the preparation process with the authenticity corresponding to the initial purity of any PPS masterbatch in the preparation process.

[0106] 204. Based on the purity authenticity, determine a purity abnormality score of the PPS masterbatch during the preparation process.

[0107] Here, after obtaining the purity authenticity, the purity anomaly score of the PPS masterbatch during the preparation process is calculated by introducing an isolation forest and constructing a binary tree. In some possible implementations, the above step 204 can be implemented by the following steps 241 to 243 (not shown in the figure):

[0108] 241. In the isolated forest, a binary tree of the preparation process of the PPS masterbatch is constructed.

[0109] Here, in the isolation forest, a binary tree is constructed for the PPS masterbatch in each preparation process. After determining the overall purity of the PPS masterbatch in each preparation process, the overall purity of each preparation process is used as a characteristic value to construct an isolation forest to obtain abnormal preparation processes (there are few abnormal preparation processes, and the purity is greatly different from that of the normal preparation process, so the isolation forest algorithm can be used). The isolation tree can easily isolate the abnormal impure preparation process to the leaf node, while the purity of the normal preparation process usually requires more splits to be isolated. Therefore, the overall purity of the abnormal preparation process often appears on the path of the isolation tree earlier than the overall purity of the normal preparation process. The anomaly score is determined by calculating the average path length of each sample in multiple isolation trees. The sample with a shorter path is likely to be an outlier. Generally, the path length of the purity of the A preparation process on the Lth tree is the number of paths from the root node to the leaf node, and the path length is how much, but the authenticity of this preparation process is questionable, so the path weight should be assigned according to the relative weight of the real and reliable preparation process becomes longer, and the path weight of the unreal preparation process becomes shorter, so that the real abnormal preparation process can be better separated.

[0110] 242. Determine a current binary tree path value of each tree based on the purity authenticity and the binary tree.

[0111] Here, the current binary tree path value of the Ath preparation process in the Lth tree is as shown in formula (9):

[0112] (9);

[0113] in, Indicates the current binary tree path value of the Lth tree in the Ath preparation process, Indicates the authenticity of the PPS masterbatch in the Ath preparation process, It represents the historical binary tree path value of the Lth tree in the original Ath preparation process in the isolation forest. Generally, the current binary tree path length of the Lth tree is the number of paths from the root node to the leaf node, and the path length is how much. Therefore, the anomaly score formula can be obtained again through the corrected path length.

[0114] 243, based on the current binary tree path value of each binary tree, determine the purity abnormality score of the PPS masterbatch during the preparation process.

[0115] Here, the current binary tree path value of each binary tree is obtained in the above steps, indicating that the purity of each preparation process has been corrected in all the binary trees of the isolation forest. Therefore, the purity anomaly score of the A-th preparation process can be directly calculated by all the binary trees. , as shown in formula (10):

[0116] (10);

[0117] in, Represents the mean value of the binary tree path value in the A-th preparation process. Represents the average of the path lengths among all binary trees in the isolation forest. Represents the average path length of a binary tree.

[0118] 205 , based on the purity abnormality score, perform data monitoring on the preparation process of the PPS masterbatch.

[0119] Here, the authenticity of the purity in each preparation process is used to assign a weight to each binary tree path in the isolated forest, and then the final PPS purity anomaly score in each PPS masterbatch processing and preparation process is obtained. After that, according to the anomaly score of each processing and preparation process, a threshold is set (for example, the threshold is set to 0.5) to determine whether there is an anomaly. If the purity anomaly score exceeds this threshold, it can be considered that there is an anomaly in the PPS masterbatch processing process. For the detected anomalies, corresponding measures can be taken to handle and adjust them to ensure product quality and the stability of the processing process.

[0120] In the embodiment of the present invention, after obtaining the spectrum of the PPS masterbatch, the overall purity of the PPS masterbatch during the preparation process is determined through the spectrum; in this way, the overall purity of the PPS masterbatch during the preparation process can be accurately calculated through spectral analysis. Afterwards, the corresponding purity authenticity is determined through the overall purity, and based on the purity authenticity, the purity abnormality score of the PPS masterbatch during the preparation process is determined; in this way, by analyzing PPS masterbatches with different purity authenticity, the purity abnormality score of the PPS masterbatch during the preparation process can be accurately determined, so that the data monitoring of the preparation process of the PPS masterbatch can be carried out through the purity abnormality score, which can improve the accuracy of monitoring the processing of the PPS masterbatch.

[0121] The embodiment of the present invention provides a data monitoring system for a PPS masterbatch processing process. Figure 7 As shown, the system 700 includes: an acquisition module 701, which is used to acquire a spectrum of polyphenylene sulfide PPS masterbatch; a first determination module 702, which is used to determine the overall purity of the PPS masterbatch during the preparation process based on the spectrum; a second determination module 703, which is used to determine the corresponding purity authenticity based on the overall purity; a third determination module 704, which is used to determine the purity anomaly score of the PPS masterbatch during the preparation process based on the purity authenticity; and a monitoring module 705, which is used to perform data monitoring on the preparation process of the PPS masterbatch based on the purity anomaly score.

[0122] In some possible implementations, the first determination module 702 is further used to determine the probability of any wavelength in the spectrum being the center of a normal distribution; determine a candidate absorption peak wavelength among multiple wavelengths in the spectrum based on the probability; determine the initial purity of any PPS masterbatch in the preparation process based on the candidate absorption peak wavelength and a preset standard substance catalog; determine the overall purity based on the initial purity of multiple PPS masterbatches in the preparation process and the corresponding purity authenticity.

[0123] In some possible implementations, the first determination module 702 is further used to determine, in the spectrum graph, a wavelength whose probability is greater than a preset probability threshold; and determine the wavelength whose probability is greater than the preset probability threshold as the candidate absorption peak wavelength.

[0124] In some possible implementations, the first determination module 702 is also used to determine, for any PPS masterbatch, based on the candidate absorption peak wavelength corresponding to the any PPS masterbatch, a normal distribution curve formed by the candidate absorption peak wavelength as the center of the normal distribution; determine the spectral fitting mixing curve corresponding to the any PPS masterbatch based on the normal distribution curve and the candidate absorption peak wavelength; perform fitting estimation on the spectral fitting mixing curve for the any PPS masterbatch to obtain target parameters; determine the constituent molecules of the PPS masterbatch in a preset standard substance catalog; and determine the initial purity of the any PPS masterbatch during the preparation process based on the constituent molecules and the target parameters.

[0125] In some possible implementations, the first determination module 702 is further used to determine the absorption peak wavelength corresponding to the constituent molecule in the preset standard substance catalog; determine the difference between the candidate absorption peak wavelength and the absorption peak wavelength corresponding to the constituent molecule; and determine the initial purity of any PPS masterbatch in the preparation process based on the difference, the preset standard substance catalog and the target parameter.

[0126] In some possible implementations, the first determination module 702 is further used to determine the total authenticity based on the authenticity corresponding to the initial purity of the multiple PPS masterbatches during the preparation process; determine the proportion of the authenticity corresponding to the initial purity of any PPS masterbatch during the preparation process in the total authenticity; and merge the initial purity of any PPS masterbatch during the preparation process with the proportion to obtain the overall purity.

[0127] In some possible implementations, the first determination module 702 is further used to determine the purity change relationship in the time sequence of the preparation process based on the initial purity of the PPS masterbatch during the preparation process; and to determine the authenticity corresponding to the initial purity of any masterbatch based on the purity change relationship and the initial purity of any masterbatch.

[0128] In some possible implementations, the first determination module 702 is further used to adjust the proportion using the authenticity corresponding to the initial purity of any PPS masterbatch during the preparation process to obtain an adjusted proportion; and determine the purity authenticity corresponding to the overall purity based on the adjusted proportions corresponding to multiple PPS masterbatches and the overall purity.

[0129] In some possible implementations, the third determination module 704 is also used to construct a binary tree of the preparation process of the PPS masterbatch in the isolation forest; determine the current binary tree path value of each binary tree based on the purity authenticity and the binary tree; and determine the purity anomaly score of the PPS masterbatch in the preparation process based on the current binary tree path value of each binary tree.

[0130] Optionally, the transmission medium may be a wired link (such as but not limited to coaxial cable, optical fiber and digital subscriber line (DSL), etc.) or a wireless link (such as but not limited to wireless Fidelity (WIFI), Bluetooth and mobile device network, etc.). It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the method embodiments provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0131] Figure 8 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 8 As shown, the computer device 800 includes: a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and running on the processor 802, wherein when the processor 802 executes the computer program 803, the computer device can execute any one of the data monitoring methods for the PPS masterbatch processing process described above.

[0132] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to perform a data monitoring method for a PPS masterbatch processing process provided by an embodiment of the present invention. This embodiment can divide the functional modules of the device according to the above method example. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module, and the above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic, which is only a logical function division, and there may be other division methods in actual implementation. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0133] It should be understood that the device provided in this embodiment is used to perform the above-mentioned data monitoring method for the processing of PPS masterbatch, so the same effect as the above-mentioned implementation method can be achieved. In the case of an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to the device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic boxes, modules and circuits described in conjunction with the disclosure of the present invention. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module can be a memory.

[0134] In addition, the device provided in the embodiment of the present invention may be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a data monitoring method for a PPS masterbatch processing process provided in the above embodiment. This embodiment also provides a computer-readable storage medium, in which a computer program code is stored, and when the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a data monitoring method for a PPS masterbatch processing process provided in the above embodiment.

[0135] The present embodiment also provides a computer program product, when the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement a data monitoring method for a PPS masterbatch processing process provided by the above embodiment. Among them, the device, computer-readable storage medium, computer program product or chip provided in the present embodiment are all used to execute the corresponding method provided above, so the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here. Through the description of the above implementation mode, the technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiment described above is only schematic, for example, the division of modules or units is only a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0136] It should be noted that the sequence of the above-mentioned embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. The above content is only a specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A data monitoring method for PPS masterbatch processing, characterized in that: The method comprises: Obtain the spectrum of polyphenylene sulfide PPS masterbatch; Based on the spectrogram, determining the overall purity of the PPS masterbatch during the preparation process; Based on the overall purity, determining the corresponding purity authenticity; Based on the purity authenticity, determining the purity abnormality score of the PPS masterbatch during the preparation process; Based on the purity abnormality score, data monitoring is performed on the preparation process of the PPS masterbatch; Determining the overall purity of the PPS masterbatch during the preparation process based on the spectrum includes: In the spectrum, determining the probability of any wavelength being the center of a normal distribution; determining, among the plurality of wavelengths in the spectrum, a candidate absorption peak wavelength based on the probability; Determine the initial purity of any PPS masterbatch during the preparation process based on the candidate absorption peak wavelength and the preset standard substance catalog; Determining the overall purity based on the initial purity of multiple PPS masterbatches during the preparation process and the corresponding purity authenticity; The determining of the overall purity based on the initial purity of the plurality of PPS masterbatches during the preparation process and the corresponding purity authenticity comprises: Determining the overall authenticity based on the authenticity corresponding to the initial purity of the plurality of PPS masterbatches during the preparation process; Determine the proportion of the authenticity corresponding to the initial purity of any PPS masterbatch during the preparation process in the total authenticity; The initial purity of any one of the PPS masterbatches during the preparation process is combined with the proportion to obtain the overall purity; Determining the purity abnormality score of the PPS masterbatch during the preparation process based on the purity authenticity includes: In the isolated forest, a binary tree of the preparation process of the PPS masterbatch is constructed; Determining a current binary tree path value of each binary tree based on the purity authenticity and the binary tree; Based on the current binary tree path value of each binary tree, the purity abnormality score of the PPS masterbatch during the preparation process is determined.

2. A data monitoring method for PPS masterbatch processing according to claim 1, characterized in that: The step of determining a candidate absorption peak wavelength among the plurality of wavelengths in the spectrum diagram based on the probability comprises: In the spectrum graph, determining a wavelength whose probability is greater than a preset probability threshold; The wavelength whose probability is greater than a preset probability threshold is determined as the candidate absorption peak wavelength.

3. A data monitoring method for PPS masterbatch processing according to claim 1, characterized in that: The method of determining the initial purity of any PPS masterbatch during the preparation process based on the candidate absorption peak wavelength and the preset standard substance catalogue includes: For any of the PPS masterbatches, based on the candidate absorption peak wavelength corresponding to the any of the PPS masterbatches, determining a normal distribution curve formed by the candidate absorption peak wavelength as the center of the normal distribution; Based on the normal distribution curve and the candidate absorption peak wavelength, determining a spectral fitting mixing curve corresponding to any one of the PPS masterbatches; Fitting and estimating the spectrum fitting mixing curve of any of the PPS masterbatches to obtain target parameters; Determine the constituent molecules of the PPS masterbatch in the preset standard substance catalog; Based on the constituent molecules and the target parameters, the initial purity of any one of the PPS masterbatches during the preparation process is determined.

4. A data monitoring method for PPS masterbatch processing according to claim 3, characterized in that: The step of determining the initial purity of any one of the PPS masterbatches during the preparation process based on the constituent molecules comprises: Determining the absorption peak wavelength corresponding to the constituent molecule in the preset standard substance catalog; Determining the difference between the candidate absorption peak wavelength and the absorption peak wavelength corresponding to the constituent molecule; Based on the difference, the preset standard substance catalog and the target parameter, the initial purity of any one of the PPS masterbatches during the preparation process is determined.

5. A data monitoring method for PPS masterbatch processing according to claim 1, characterized in that: The method further comprises: Based on the initial purity of the PPS masterbatch during the preparation process, determining the purity change relationship in the time sequence of the preparation process; Based on the purity variation relationship and the initial purity of any masterbatch, the authenticity corresponding to the initial purity of any masterbatch is determined.

6. A data monitoring method for PPS masterbatch processing according to claim 1, characterized in that: The determining of the corresponding purity authenticity based on the overall purity includes: The proportion is adjusted by using the authenticity corresponding to the initial purity of any one of the PPS masterbatches during the preparation process to obtain an adjusted proportion; Based on the adjusted proportions corresponding to the plurality of PPS masterbatches and the overall purity, the purity authenticity corresponding to the overall purity is determined.

7. A data monitoring system for PPS masterbatch processing, used in the data monitoring method according to claim 1, characterized in that: The system comprises: An acquisition module, used for acquiring a spectrum of polyphenylene sulfide PPS masterbatch; A first determination module is used to determine the overall purity of the PPS masterbatch during the preparation process based on the spectrum; A second determination module, configured to determine the corresponding purity authenticity based on the overall purity; A third determination module is used to determine the purity abnormality score of the PPS masterbatch during the preparation process based on the purity authenticity; A monitoring module is used to perform data monitoring on the preparation process of the PPS masterbatch based on the purity abnormality score.

Images