Analysis method of tin stripping water reuse performance based on dynamic data evaluation

Abstract

The present invention relates to a tin stripping water reuse performance analysis method based on dynamic data evaluation, and belongs to the technical field of tin stripping water reuse analysis. The present invention constructs real-time dynamic data based on time series based on normal pre-processed dynamic data information, thereby constructing a tin stripping water performance evaluation tracking model based on the real-time dynamic data based on the time series, and tracks the performance data of the tin stripping water through the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water, and finally performs reuse analysis based on the real-time performance data of the tin stripping water, obtains the reuse analysis results, and generates relevant recommendation information based on the reuse analysis results. The present invention can timely discover tin stripping water with abnormal performance by performing performance analysis on the real-time dynamic data of the tin stripping water, and can timely perform reuse analysis on the tin stripping water, thereby maintaining the normal stripping effect of electronic components.

Description

Technical Field

[0001] The present invention relates to the technical field of tin stripping water reuse analysis, and in particular to a tin stripping water reuse performance analysis method based on dynamic data evaluation. Background Art

[0002] Tin stripping water, also known as tin stripping liquid, is one of the main chemical materials used in the production of printed circuit boards. It is used to remove tin plating, tin-lead alloy plating and tin soldering points. Especially for electronic components, the removal of tin / lead-tin alloy layer on the copper surface during the manufacturing process of circuit boards can be carried out by immersion or mechanical spraying. Secondly, it is suitable for the removal of tin / lead-tin alloy layer on the copper surface. It has no damage to the copper substrate and nickel substrate, and can remove copper rust to make the copper substrate bright as new, and has no corrosion to the base resin, plastic and ink characters. However, in the process of use, tin stripping water is often reused. In the process of reuse, the infiltration of other impurities or the generation of chemical reactions will cause the stripping performance of tin stripping water to decrease. If the performance of the tin stripping water of the corresponding equipment is not discovered in time, the stripping effect of the tin plating, tin-lead alloy plating and tin soldering points of the components will be poor, and then defective products will be produced. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation, comprising:

[0006] The real-time dynamic data information of the tin stripping water is collected by a sensor, and the pre-processed dynamic data information of the tin stripping water is obtained within a preset time by pre-processing the real-time dynamic data information of the tin stripping water;

[0007] By performing cluster analysis on the pre-processed dynamic data information within the preset time, abnormal pre-processed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal pre-processed dynamic data information;

[0008] Constructing a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, tracking the performance data of the tin stripping water through the tin stripping water performance evaluation tracking model, and obtaining the real-time performance data of the tin stripping water;

[0009] A reuse analysis is performed based on the real-time performance data of the tin stripping water, a reuse analysis result is obtained, and relevant recommendation information is generated according to the reuse analysis result.

[0010] Furthermore, in this method, real-time dynamic data information of the tin stripping water is collected by a sensor, and the real-time dynamic data information of the tin stripping water is preprocessed to obtain the preprocessed dynamic data information within a preset time, specifically:

[0011] Set the real-time dynamic data sampling density, the real-time data sampling volume and the sampling amplitude coefficient, and collect the real-time dynamic data information of the tin stripping water through the sensor based on the real-time dynamic data sampling density, the real-time data sampling volume and the sampling amplitude coefficient;

[0012] A variational mode decomposition method is introduced, a real-time dynamic data denoising time is set, and the real-time dynamic data information of the tin stripping water is denoised based on the real-time dynamic data denoising time by using the variational mode decomposition method to obtain a noise value of each real-time dynamic data;

[0013] Setting a noise threshold evaluation index, and determining whether the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, if the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, discarding the corresponding real-time dynamic data;

[0014] If the noise value of the real-time dynamic data is not greater than the noise threshold evaluation index, the corresponding real-time dynamic data is used as preprocessed data, and a timestamp is constructed. Based on the timestamp and the preprocessed data, the preprocessed dynamic data information within a preset time is constructed.

[0015] Furthermore, in this method, by performing cluster analysis on the preprocessed dynamic data information within the preset time, abnormal preprocessed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal preprocessed dynamic data information, specifically:

[0016] Introducing a fuzzy clustering algorithm, and setting the number of cluster centers, constructing sample data based on the dynamic data information preprocessed within the preset time, performing cluster analysis on the sample data based on the number of cluster centers, and obtaining a clustered sample data set;

[0017] Calculate the Jaccard similarity coefficient between the clustered sample data sets, take the sample data sets whose Jaccard similarity coefficient is lower than the Jaccard similarity coefficient threshold as abnormal pre-processed dynamic data information, and remove the abnormal pre-processed dynamic data information;

[0018] The sample data set whose Jaccard similarity coefficient is not less than the Jaccard similarity coefficient threshold is taken as normal pre-processed dynamic data information, and real-time dynamic data based on time series is constructed based on the normal pre-processed dynamic data information.

[0019] Furthermore, in this method, a tin stripping water performance evaluation tracking model is constructed according to the real-time dynamic data, specifically:

[0020] Constructing a tin stripping water performance evaluation tracking model based on a recurrent neural network, constructing a learning sample according to the real-time dynamic data based on the time series, and keeping the data of the input neurons of the recurrent neural network consistent with the dimension of the learning sample;

[0021] The input learning sample data is passed to the units in the hidden layer, and all neurons in the last layer of the hidden layer are weighted summed, and the summed value of the hidden layer output is divided by the output neuron to obtain the probability value of the output state;

[0022] The probability values ​​of the output states are sorted to obtain a sorting result, and a dynamic data state with the largest probability value of the output state is obtained through the sorting result, and the dynamic data state with the largest probability value of the output state is used as the output result;

[0023] After continuous training, the prediction accuracy of the output results is statistically analyzed. When the prediction accuracy is greater than the prediction accuracy threshold, the model parameters of the tin stripping water performance evaluation tracking model are saved, and the tin stripping water performance evaluation tracking model is output.

[0024] Furthermore, in this method, the performance data of the tin stripping water is tracked by the tin stripping water performance evaluation tracking model to obtain real-time performance data of the tin stripping water, specifically:

[0025] Acquire dynamic characteristic data within a preset time, and input the dynamic characteristic data within the preset time into the tin stripping water performance evaluation tracking model for identification and prediction;

[0026] Through identification and prediction, real-time performance data of the tin stripping water is obtained, and the real-time performance data of the tin stripping water is output.

[0027] Furthermore, in the present method, a reuse analysis is performed based on the real-time performance data of the tin stripping water to obtain a reuse analysis result, which specifically includes:

[0028] Setting a performance data evaluation index threshold of the tin stripping water, and determining whether the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water;

[0029] When the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with normal performance data;

[0030] When the real-time performance data of the tin stripping water is not greater than the performance data evaluation index threshold of the tin stripping water, it is marked as tin stripping water with abnormal performance data;

[0031] A reuse analysis result is generated according to the tin stripping water of the normal performance data and the tin stripping water of the abnormal performance data, and the reuse analysis result is output.

[0032] Furthermore, in this method, generating relevant recommendation information according to the reuse analysis result specifically includes:

[0033] When the reuse analysis result is tin stripping water with normal performance data, obtaining a utilization device of the tin stripping water with normal performance data, and obtaining the tin stripping water performance data information required in the target area;

[0034] Introducing a genetic algorithm, setting a genetic algebra based on the genetic algorithm, initializing a required equipment combination according to the required tin stripping water performance data information in the target area, and obtaining performance data of each used equipment in the required equipment combination;

[0035] Determine whether the performance data of each device in the required device combination is greater than the tin stripping water performance data information required in the target area. If so, output the required device combination and generate relevant recommendation information.

[0036] When the performance data of each device in the required equipment combination is not all greater than the tin stripping water performance data information required in the target area, the required equipment combination is readjusted until all are greater than the tin stripping water performance data information required in the target area.

[0037] A second aspect of the present invention provides a tin stripping water reuse performance analysis system based on dynamic data evaluation, the system comprising a memory and a processor, the memory comprising a tin stripping water reuse performance analysis method program based on dynamic data evaluation, and when the tin stripping water reuse performance analysis method program based on dynamic data evaluation is executed by the processor, any step of the tin stripping water reuse performance analysis method based on dynamic data evaluation is implemented.

[0038] A third aspect of the present invention provides a terminal device, including:

[0039] The data noise processing module is responsible for collecting the real-time dynamic data information of the tin stripping water through the sensor, and preprocessing the real-time dynamic data information of the tin stripping water to obtain the preprocessed dynamic data information within a preset time;

[0040] The data clustering analysis module is responsible for performing clustering analysis on the pre-processed dynamic data information within the preset time, eliminating abnormal pre-processed dynamic data information, and constructing real-time dynamic data based on time series based on normal pre-processed dynamic data information;

[0041] A performance data tracking module is loaded to build a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, and the performance data of the tin stripping water is tracked through the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water;

[0042] The recommendation module is responsible for performing a reuse analysis based on the real-time performance data of the tin stripping water, obtaining the reuse analysis results, and generating relevant recommendation information according to the reuse analysis results.

[0043] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a method program for analyzing the performance of tin stripping water reuse based on dynamic data evaluation. When the method program for analyzing the performance of tin stripping water reuse based on dynamic data evaluation is executed by a processor, any step of the method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation is implemented.

[0044] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0045] The present invention collects real-time dynamic data information of tin stripping water through a sensor, and pre-processes the real-time dynamic data information of tin stripping water to obtain the pre-processed dynamic data information within a preset time, and then clusters the pre-processed dynamic data information within the preset time to eliminate abnormal pre-processed dynamic data information, and constructs real-time dynamic data based on time series based on normal pre-processed dynamic data information, thereby constructing a tin stripping water performance evaluation tracking model based on the real-time dynamic data based on time series, tracking the performance data of tin stripping water through the tin stripping water performance evaluation tracking model, obtaining real-time performance data of tin stripping water, and finally performing reuse analysis based on the real-time performance data of tin stripping water, obtaining reuse analysis results, and generating relevant recommendation information based on the reuse analysis results. The present invention can timely discover tin stripping water with abnormal performance by performing performance analysis on the real-time dynamic data of tin stripping water, and can timely reuse and analyze the tin stripping water, thereby maintaining the normal removal effect of electronic components. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0047] Figure 1 The overall flow chart of the tin stripping water reuse performance analysis method based on dynamic data evaluation is shown;

[0048] Figure 2 A partial method flow chart of a method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation is shown;

[0049] Figure 3 The system block diagram of the tin stripping water reuse performance analysis system based on dynamic data evaluation is shown;

[0050] Figure 4 A device schematic diagram of a terminal device is shown. DETAILED DESCRIPTION

[0051] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0053] like Figure 1 As shown, the first aspect of the present invention provides a method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation, comprising:

[0054] S102: collecting real-time dynamic data information of the tin stripping water through a sensor, and preprocessing the real-time dynamic data information of the tin stripping water to obtain the preprocessed dynamic data information within a preset time;

[0055] S104: performing cluster analysis on the pre-processed dynamic data information within a preset time, eliminating abnormal pre-processed dynamic data information, and constructing real-time dynamic data based on time series based on normal pre-processed dynamic data information;

[0056] S106: constructing a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, tracking the performance data of the tin stripping water through the tin stripping water performance evaluation tracking model, and obtaining the real-time performance data of the tin stripping water;

[0057] S108: Perform reuse analysis based on the real-time performance data of the tin stripping water, obtain the reuse analysis results, and generate relevant recommendation information based on the reuse analysis results.

[0058] It should be noted that the present invention can timely discover tin stripping water with abnormal performance by analyzing the real-time dynamic data of tin stripping water, and can timely analyze the reuse of tin stripping water, so as to maintain the normal stripping effect of electronic components. Among them, the real-time dynamic data includes the concentration data information and concentration type information of the main components in the tin stripping water, such as hydrofluoric acid, fluoride salt (ammonium bifluoride), peroxide concentration data, and nitric acid, ferric nitrate, corrosion inhibitor, surfactant, nitrogen oxide inhibitor, complexing agent concentration data, etc.

[0059] Furthermore, in this method, the real-time dynamic data information of the tin stripping water is collected by a sensor, and the real-time dynamic data information of the tin stripping water is preprocessed to obtain the preprocessed dynamic data information within a preset time, specifically:

[0060] Set the real-time dynamic data sampling density, real-time data sampling volume and sampling amplitude coefficient, and collect the real-time dynamic data information of the tin stripping water through the sensor based on the real-time dynamic data sampling density, real-time data sampling volume and sampling amplitude coefficient;

[0061] The variational mode decomposition method is introduced, the real-time dynamic data denoising time is set, and the real-time dynamic data information of the tin stripping water is denoised based on the real-time dynamic data denoising time by the variational mode decomposition method to obtain the noise value of each real-time dynamic data;

[0062] A noise threshold evaluation index is set, and it is determined whether the noise value of the real-time dynamic data is greater than the noise threshold evaluation index. If the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, the corresponding real-time dynamic data is eliminated;

[0063] If the noise value of the real-time dynamic data is not greater than the noise threshold evaluation index, the corresponding real-time dynamic data is used as the preprocessed data, and a timestamp is constructed. Based on the timestamp and the preprocessed data, the preprocessed dynamic data information within the preset time is constructed.

[0064] It should be noted that since the sensor collects continuous data and the data is interfered by noise, the variational mode decomposition method is used to perform noise analysis on each data through the sensor according to the real-time dynamic data sampling density, real-time data sampling volume and sampling amplitude coefficient, so as to obtain the real-time dynamic data noise value not greater than the noise threshold evaluation index as the preprocessed data, thereby improving the evaluation accuracy of the dynamic data.

[0065] Furthermore, in this method, by performing cluster analysis on the pre-processed dynamic data information within a preset time, abnormal pre-processed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal pre-processed dynamic data information, specifically:

[0066] Introduce a fuzzy clustering algorithm, set the number of cluster centers, construct sample data based on dynamic data information preprocessed within a preset time, perform cluster analysis on the sample data based on the number of cluster centers, and obtain a clustered sample data set;

[0067] Calculate the Jaccard similarity coefficient between the clustered sample data sets, take the sample data sets whose Jaccard similarity coefficient is lower than the Jaccard similarity coefficient threshold as abnormal pre-processed dynamic data information, and remove the abnormal pre-processed dynamic data information;

[0068] The sample data set whose Jaccard similarity coefficient is not less than the Jaccard similarity coefficient threshold is taken as normal pre-processed dynamic data information, and real-time dynamic data based on time series is constructed based on the normal pre-processed dynamic data information.

[0069] It should be noted that fuzzy clustering algorithms include k-means fuzzy clustering algorithm, FCM fuzzy clustering algorithm, etc. In the process of sensor data collection, due to the interference of other data in a time series, the sample data set whose Jaccard similarity coefficient is lower than the Jaccard similarity coefficient threshold is regarded as abnormal pre-processed dynamic data information, thereby eliminating sample data with occasional abnormalities.

[0070] Furthermore, in this method, a tin stripping water performance evaluation tracking model is constructed based on real-time dynamic data, specifically:

[0071] A tin stripping water performance evaluation and tracking model is built based on a recurrent neural network. Learning samples are built based on real-time dynamic data based on time series. The data of the input neurons of the recurrent neural network are kept consistent with the dimension of the learning samples.

[0072] The input learning sample data is passed to the units in the hidden layer, and all neurons in the last layer of the hidden layer are weighted summed, and the summed value of the hidden layer output is divided by the output neuron to obtain the probability value of the output state;

[0073] By sorting the probability values ​​of the output states, a sorting result is obtained, and the dynamic data state with the largest probability value of the output state is obtained through the sorting result, and the dynamic data state with the largest probability value of the output state is used as the output result;

[0074] After continuous training, the prediction accuracy of the output results is statistically analyzed. When the prediction accuracy is greater than the prediction accuracy threshold, the model parameters of the tin stripping water performance evaluation tracking model are saved, and the tin stripping water performance evaluation tracking model is output.

[0075] It should be noted that the recurrent neural network is a machine learning model based on a neural network, which is usually composed of an input layer, a hidden layer, and an output layer. It is mainly used to solve regression problems, that is, predicting continuous output values ​​based on input data. The number of neurons in the input layer is consistent with the dimension of the input vector in the learning sample. The neurons are distributed units, and all input variables are passed to the units in the hidden layer. The number of neurons in the hidden layer is set to the number of learning samples to ensure that the model has sufficient learning ability for the data samples. According to the dimension of the data set, a standard sample data is generated every 5 minutes, and the screening data can generate 25,000 samples, so the number of neurons in the hidden layer is set to 25,000. This method can track the performance of the tin stripping water through machine learning technology and Internet of Things technology, and timely detect the abnormality of the tin stripping water.

[0076] Furthermore, in this method, the performance data of the tin stripping water is tracked by the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water, specifically:

[0077] Acquire dynamic characteristic data within a preset time, and input the dynamic characteristic data within the preset time into a tin stripping water performance evaluation tracking model for identification and prediction;

[0078] Through identification and prediction, real-time performance data of the tin stripping water is obtained and output.

[0079] Furthermore, in the present method, a reuse analysis is performed based on the real-time performance data of the tin stripping water to obtain the reuse analysis results, which specifically include:

[0080] Set the performance data evaluation index threshold of the tin stripping water, and determine whether the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water;

[0081] When the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with normal performance data;

[0082] When the real-time performance data of the tin stripping water is not greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with abnormal performance data;

[0083] A reuse analysis result is generated based on the tin stripping water with normal performance data and the tin stripping water with abnormal performance data, and the reuse analysis result is output.

[0084] It should be noted that the performance data of tin stripping water is mainly the stripping performance, and the stripping performance is related to the concentration of chemical components in the tin stripping water. Therefore, the performance data evaluation index threshold of the tin stripping water is mainly the concentration evaluation index threshold of each chemical component concentration.

[0085] like Figure 2 As shown, further, in this method, relevant recommendation information is generated according to the reuse analysis results, specifically including:

[0086] S202: When the analysis result of the reuse of the tin stripping water is normal performance data, the utilization equipment of the tin stripping water with normal performance data is obtained, and the tin stripping water performance data information required in the target area is obtained;

[0087] S204: introducing a genetic algorithm, setting a genetic algebra based on the genetic algorithm, initializing the required equipment combination according to the required tin stripping water performance data information in the target area, and obtaining the performance data of each used equipment in the required equipment combination;

[0088] S206: Determine whether the performance data of each device in the required device combination is greater than the tin stripping water performance data information required in the target area. If so, output the required device combination and generate relevant recommendation information;

[0089] S208: When the performance data of each device in the required equipment combination is not all greater than the tin stripping water performance data information required in the target area, the required equipment combination is readjusted until all are greater than the tin stripping water performance data information required in the target area.

[0090] It should be noted that this method can recommend the optimal equipment working combination according to the tin stripping water performance data information required in the target area, so that all equipment meets the tin stripping water performance requirements in the target area.

[0091] In addition, the method further comprises:

[0092] The historical degradation characteristic change data of tin stripping water performance under various working environment characteristics are obtained through big data, the working environment characteristics are used as the first node, the tin stripping water performance degradation characteristic data is used as the second node, and a tin stripping water performance degradation characteristic prediction model is constructed based on a deep neural network;

[0093] Constructing a directed description relationship, connecting the first node and the second node based on the directed description relationship, constructing a topological structure graph, obtaining a plurality of topological structure graphs, and constructing topological structure graph feature data based on a time series based on the topological structure graphs;

[0094] Inputting the time series-based topological structure graph feature data into the tin stripping water performance degradation feature prediction model for training, and obtaining a trained tin stripping water performance degradation feature prediction model;

[0095] Obtaining working environment characteristics of a target area and tin stripping water performance characteristic data at a current timestamp, and inputting the working environment characteristics of the target area and the tin stripping water performance characteristic data at a current timestamp into the trained tin stripping water performance degradation characteristic prediction model for prediction;

[0096] Through prediction, the tin stripping water performance characteristic data of the tin stripping water in the target area within the preset time is obtained, and the required equipment combination is updated according to the tin stripping water performance characteristic data of the tin stripping water in the target area within the preset time, until the tin stripping water performance characteristic data of the required equipment combination within the preset time are all greater than the tin stripping water performance data information required in the target area.

[0097] It should be noted that in different working environments (temperature, particulate matter content, etc.), due to the presence of particulate matter in the air, the particulate matter will react with the chemical substances in the tin stripping water, thereby causing the performance of the tin stripping water to degrade. This method can predict the performance characteristic data of the tin stripping water in the target area within a preset time, thereby updating the required equipment combination and improving the rationality of work allocation.

[0098] In addition, the method further comprises:

[0099] After genetic iteration through genetic algebra, when the tin stripping water performance characteristic data of the required equipment combination within the preset time is not all greater than the tin stripping water performance data information required in the target area, the environmental characteristic data in the target area is obtained;

[0100] Initializing working parameters of an environment control device, and adjusting environmental characteristic data in the target area based on the working parameters of the environment control device to obtain real-time environmental characteristic data;

[0101] Predicting the performance characteristic data of the tin stripping water in the target area within a preset time under the real-time environmental characteristic data;

[0102] If the tin stripping water performance characteristic data of the tin stripping water in the target area is lower than the preset tin stripping water performance threshold within the preset time under the real-time environmental characteristic data, the working parameters of the environmental control equipment are adjusted until they are no lower than the preset tin stripping water performance threshold.

[0103] It should be noted that the environmental control equipment can be fans, air conditioners, exhaust fans, dehumidifiers, air purifiers and other environmental control equipment. The working parameters include data such as the fan speed and exhaust volume. Through this method, the environmental data can be adjusted until it is no less than the preset tin stripping water performance threshold, so that the tin stripping water working environment meets the predetermined requirements.

[0104] like Figure 3As shown, the second aspect of the present invention provides a tin stripping water reuse performance analysis system 4 based on dynamic data evaluation, the system includes a memory 31 and a processor 32, the memory 31 includes a tin stripping water reuse performance analysis method program based on dynamic data evaluation, when the tin stripping water reuse performance analysis method program based on dynamic data evaluation is executed by the processor 32, any step of the tin stripping water reuse performance analysis method based on dynamic data evaluation is implemented.

[0105] like Figure 4 As shown, the third aspect of the present invention provides a terminal device, including:

[0106] The data noise processing module 10 is responsible for collecting the real-time dynamic data information of the tin stripping water through the sensor, and preprocessing the real-time dynamic data information of the tin stripping water to obtain the preprocessed dynamic data information within a preset time;

[0107] The data clustering analysis module 20 is responsible for performing clustering analysis on the pre-processed dynamic data information within a preset time, removing abnormal pre-processed dynamic data information, and constructing real-time dynamic data based on time series based on normal pre-processed dynamic data information;

[0108] The performance data tracking module 30 is loaded to build a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, and the performance data of the tin stripping water is tracked through the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water;

[0109] The recommendation module 40 is responsible for performing a reuse analysis based on the real-time performance data of the tin stripping water, obtaining the reuse analysis results, and generating relevant recommendation information according to the reuse analysis results.

[0110] Furthermore, in this device, the real-time dynamic data information of the tin stripping water is collected by the sensor, and the real-time dynamic data information of the tin stripping water is preprocessed to obtain the preprocessed dynamic data information within a preset time, specifically:

[0111] Set the real-time dynamic data sampling density, real-time data sampling volume and sampling amplitude coefficient, and collect the real-time dynamic data information of the tin stripping water through the sensor based on the real-time dynamic data sampling density, real-time data sampling volume and sampling amplitude coefficient;

[0112] The variational mode decomposition method is introduced, the real-time dynamic data denoising time is set, and the real-time dynamic data information of the tin stripping water is denoised based on the real-time dynamic data denoising time by the variational mode decomposition method to obtain the noise value of each real-time dynamic data;

[0113] A noise threshold evaluation index is set, and it is determined whether the noise value of the real-time dynamic data is greater than the noise threshold evaluation index. If the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, the corresponding real-time dynamic data is eliminated;

[0114] If the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, the corresponding real-time dynamic data is used as the preprocessed data, and a timestamp is constructed. Based on the timestamp and the preprocessed data, the preprocessed dynamic data information within the preset time is constructed.

[0115] Furthermore, in this device, by performing cluster analysis on the pre-processed dynamic data information within a preset time, abnormal pre-processed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal pre-processed dynamic data information, specifically:

[0116] Introduce a fuzzy clustering algorithm, set the number of cluster centers, construct sample data based on dynamic data information preprocessed within a preset time, perform cluster analysis on the sample data based on the number of cluster centers, and obtain a clustered sample data set;

[0117] Calculate the Jaccard similarity coefficient between the clustered sample data sets, take the sample data sets whose Jaccard similarity coefficient is lower than the Jaccard similarity coefficient threshold as abnormal pre-processed dynamic data information, and remove the abnormal pre-processed dynamic data information;

[0118] The sample data set whose Jaccard similarity coefficient is not less than the Jaccard similarity coefficient threshold is taken as normal pre-processed dynamic data information, and real-time dynamic data based on time series is constructed based on the normal pre-processed dynamic data information.

[0119] Furthermore, in this device, a tin stripping water performance evaluation tracking model is constructed based on real-time dynamic data, specifically:

[0120] A tin stripping water performance evaluation and tracking model is built based on a recurrent neural network. Learning samples are built based on real-time dynamic data based on time series. The data of the input neurons of the recurrent neural network are kept consistent with the dimension of the learning samples.

[0121] The input learning convenience data is passed to the units in the hidden layer, and all neurons in the last layer of the hidden layer are weighted summed, and the summed value of the hidden layer output is divided by the output neuron to obtain the probability value of the output state;

[0122] By sorting the probability values ​​of the output states, a sorting result is obtained, and the dynamic data state with the largest probability value of the output state is obtained through the sorting result, and the dynamic data state with the largest probability value of the output state is used as the output result;

[0123] After continuous training, the prediction accuracy of the output results is statistically analyzed. When the prediction accuracy is greater than the prediction accuracy threshold, the model parameters of the tin stripping water performance evaluation tracking model are saved, and the tin stripping water performance evaluation tracking model is output.

[0124] Furthermore, in this device, the performance data of the tin stripping water is tracked by the tin stripping water performance evaluation tracking model to obtain real-time performance data of the tin stripping water, specifically:

[0125] Acquire dynamic characteristic data within a preset time, and input the dynamic characteristic data within the preset time into a tin stripping water performance evaluation tracking model for identification and prediction;

[0126] Through identification and prediction, real-time performance data of the tin stripping water is obtained and output.

[0127] Furthermore, in this device, a reuse analysis is performed based on the real-time performance data of the tin stripping water to obtain the reuse analysis results, which specifically include:

[0128] Set the performance data evaluation index threshold of the tin stripping water, and determine whether the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water;

[0129] When the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with normal performance data;

[0130] When the real-time performance data of the tin stripping water is not greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with abnormal performance data;

[0131] A reuse analysis result is generated based on the tin stripping water with normal performance data and the tin stripping water with abnormal performance data, and the reuse analysis result is output.

[0132] Furthermore, in this device, relevant recommendation information is generated according to the reuse analysis result, specifically including:

[0133] When the analysis result of the reuse of the tin stripping water is normal performance data, the utilization equipment of the tin stripping water with normal performance data is obtained, and the tin stripping water performance data information required in the target area is obtained;

[0134] Introduce a genetic algorithm, set a genetic algebra based on the genetic algorithm, initialize the required equipment combination according to the required tin stripping water performance data information in the target area, and obtain the performance data of each used equipment in the required equipment combination;

[0135] Determine whether the performance data of each device in the required equipment combination is greater than the tin stripping water performance data information required in the target area. If so, output the required equipment combination and generate relevant recommendation information;

[0136] When the performance data of each device in the required equipment combination is not all greater than the tin stripping water performance data information required in the target area, the required equipment combination is readjusted until it is all greater than the tin stripping water performance data information required in the target area.

[0137] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a method program for analyzing the performance of tin stripping water reuse based on dynamic data evaluation. When the method program for analyzing the performance of tin stripping water reuse based on dynamic data evaluation is executed by a processor, any step of the method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation is implemented.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0139] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0140] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0141] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0142] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, disks or optical disks.

[0143] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation, characterized in that: include: The real-time dynamic data information of the tin stripping water is collected by a sensor, and the pre-processed dynamic data information of the tin stripping water is obtained within a preset time by pre-processing the real-time dynamic data information of the tin stripping water; By performing cluster analysis on the pre-processed dynamic data information within the preset time, abnormal pre-processed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal pre-processed dynamic data information; Constructing a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, tracking the performance data of the tin stripping water through the tin stripping water performance evaluation tracking model, and obtaining the real-time performance data of the tin stripping water; Performing a reuse analysis based on the real-time performance data of the tin stripping water, obtaining a reuse analysis result, and generating relevant recommendation information according to the reuse analysis result; A tin stripping water performance evaluation and tracking model is constructed based on the real-time dynamic data, specifically: Constructing a tin stripping water performance evaluation tracking model based on a recurrent neural network, constructing a learning sample according to the real-time dynamic data based on the time series, and keeping the data of the input neurons of the recurrent neural network consistent with the dimension of the learning sample; The input learning sample data is passed to the units in the hidden layer, and all neurons in the last layer of the hidden layer are weighted summed, and the summed value of the hidden layer output is divided by the output neuron to obtain the probability value of the output state; The probability values ​​of the output states are sorted to obtain a sorting result, and a dynamic data state with the largest probability value of the output state is obtained through the sorting result, and the dynamic data state with the largest probability value of the output state is used as the output result; After continuous training, the prediction accuracy of the output results is statistically calculated. When the prediction accuracy is greater than the prediction accuracy threshold, the model parameters of the tin stripping water performance evaluation tracking model are saved, and the tin stripping water performance evaluation tracking model is output; Generate relevant recommendation information according to the reuse analysis result, specifically including: When the reuse analysis result is tin stripping water with normal performance data, obtaining a utilization device of the tin stripping water with normal performance data, and obtaining the tin stripping water performance data information required in the target area; Introducing a genetic algorithm, setting a genetic algebra based on the genetic algorithm, initializing a required equipment combination according to the required tin stripping water performance data information in the target area, and obtaining performance data of each used equipment in the required equipment combination; Determine whether the performance data of each device in the required device combination is greater than the tin stripping water performance data information required in the target area. If so, output the required device combination and generate relevant recommendation information. When the performance data of each device in the required equipment combination is not all greater than the tin stripping water performance data information required in the target area, the required equipment combination is readjusted until all are greater than the tin stripping water performance data information required in the target area.

2. The tin stripping water reuse performance analysis method based on dynamic data evaluation according to claim 1, characterized in that: The real-time dynamic data information of the tin stripping water is collected by the sensor, and the real-time dynamic data information of the tin stripping water is preprocessed to obtain the dynamic data information after preprocessing within a preset time, specifically: Set the real-time dynamic data sampling density, the real-time data sampling volume and the sampling amplitude coefficient, and collect the real-time dynamic data information of the tin stripping water through the sensor based on the real-time dynamic data sampling density, the real-time data sampling volume and the sampling amplitude coefficient; A variational mode decomposition method is introduced, a real-time dynamic data denoising time is set, and the real-time dynamic data information of the tin stripping water is denoised based on the real-time dynamic data denoising time by using the variational mode decomposition method to obtain a noise value of each real-time dynamic data; Setting a noise threshold evaluation index, and determining whether the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, if the noise value of the real-time dynamic data is greater than the noise threshold evaluation index, discarding the corresponding real-time dynamic data; If the noise value of the real-time dynamic data is not greater than the noise threshold evaluation index, the corresponding real-time dynamic data is used as preprocessed data, and a timestamp is constructed. Based on the timestamp and the preprocessed data, the preprocessed dynamic data information within a preset time is constructed.

3. The tin stripping water reuse performance analysis method based on dynamic data evaluation according to claim 1, characterized in that: By performing cluster analysis on the pre-processed dynamic data information within the preset time, abnormal pre-processed dynamic data information is eliminated, and real-time dynamic data based on time series is constructed based on normal pre-processed dynamic data information, specifically: Introducing a fuzzy clustering algorithm, and setting the number of cluster centers, constructing sample data based on the dynamic data information preprocessed within the preset time, performing cluster analysis on the sample data based on the number of cluster centers, and obtaining a clustered sample data set; Calculate the Jaccard similarity coefficient between the clustered sample data sets, take the sample data sets whose Jaccard similarity coefficient is lower than the Jaccard similarity coefficient threshold as abnormal pre-processed dynamic data information, and remove the abnormal pre-processed dynamic data information; The sample data set whose Jaccard similarity coefficient is not less than the Jaccard similarity coefficient threshold is taken as normal pre-processed dynamic data information, and real-time dynamic data based on time series is constructed based on the normal pre-processed dynamic data information.

4. The method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation according to claim 1, characterized in that: The performance data of the tin stripping water is tracked by the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water, specifically: Acquire dynamic characteristic data within a preset time, and input the dynamic characteristic data within the preset time into the tin stripping water performance evaluation tracking model for identification and prediction; Through identification and prediction, real-time performance data of the tin stripping water is obtained, and the real-time performance data of the tin stripping water is output.

5. The method for analyzing the performance of tin stripping water reuse based on dynamic data evaluation according to claim 1, characterized in that: Based on the real-time performance data of the tin stripping water, a reuse analysis is performed to obtain a reuse analysis result, specifically including: Setting a performance data evaluation index threshold of the tin stripping water, and determining whether the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water; When the real-time performance data of the tin stripping water is greater than the performance data evaluation index threshold of the tin stripping water, it is marked as the tin stripping water with normal performance data; When the real-time performance data of the tin stripping water is not greater than the performance data evaluation index threshold of the tin stripping water, it is marked as tin stripping water with abnormal performance data; A reuse analysis result is generated according to the tin stripping water of the normal performance data and the tin stripping water of the abnormal performance data, and the reuse analysis result is output.

6. The tin stripping water reuse performance analysis system based on dynamic data evaluation is characterized by: The system includes a memory and a processor, wherein the memory includes a tin stripping water reuse performance analysis method program based on dynamic data evaluation, and when the tin stripping water reuse performance analysis method program based on dynamic data evaluation is executed by the processor, the steps of the tin stripping water reuse performance analysis method based on dynamic data evaluation as described in any one of claims 1 to 5 are implemented.

7. A terminal device, characterized in that: include: The data noise processing module is responsible for collecting the real-time dynamic data information of the tin stripping water through the sensor, and preprocessing the real-time dynamic data information of the tin stripping water to obtain the preprocessed dynamic data information within a preset time; The data clustering analysis module is responsible for performing clustering analysis on the pre-processed dynamic data information within the preset time, eliminating abnormal pre-processed dynamic data information, and constructing real-time dynamic data based on time series based on normal pre-processed dynamic data information; A performance data tracking module is loaded to build a tin stripping water performance evaluation tracking model according to the real-time dynamic data based on the time series, and the performance data of the tin stripping water is tracked through the tin stripping water performance evaluation tracking model to obtain the real-time performance data of the tin stripping water; A recommendation module is responsible for performing a reuse analysis based on the real-time performance data of the tin stripping water, obtaining a reuse analysis result, and generating relevant recommendation information according to the reuse analysis result; A tin stripping water performance evaluation and tracking model is constructed based on the real-time dynamic data, specifically: Constructing a tin stripping water performance evaluation tracking model based on a recurrent neural network, constructing a learning sample according to the real-time dynamic data based on the time series, and keeping the data of the input neurons of the recurrent neural network consistent with the dimension of the learning sample; The input learning sample data is passed to the units in the hidden layer, and all neurons in the last layer of the hidden layer are weighted summed, and the summed value of the hidden layer output is divided by the output neuron to obtain the probability value of the output state; The probability values ​​of the output states are sorted to obtain a sorting result, and a dynamic data state with the largest probability value of the output state is obtained through the sorting result, and the dynamic data state with the largest probability value of the output state is used as the output result; After continuous training, the prediction accuracy of the output results is statistically calculated. When the prediction accuracy is greater than the prediction accuracy threshold, the model parameters of the tin stripping water performance evaluation tracking model are saved, and the tin stripping water performance evaluation tracking model is output; Generate relevant recommendation information according to the reuse analysis result, specifically including: When the reuse analysis result is tin stripping water with normal performance data, obtaining a utilization device of the tin stripping water with normal performance data, and obtaining the tin stripping water performance data information required in the target area; Introducing a genetic algorithm, setting a genetic algebra based on the genetic algorithm, initializing a required equipment combination according to the required tin stripping water performance data information in the target area, and obtaining performance data of each used equipment in the required equipment combination; Determine whether the performance data of each device in the required device combination is greater than the tin stripping water performance data information required in the target area. If so, output the required device combination and generate relevant recommendation information. When the performance data of each device in the required equipment combination is not all greater than the tin stripping water performance data information required in the target area, the required equipment combination is readjusted until all are greater than the tin stripping water performance data information required in the target area.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a tin stripping water reuse performance analysis method program based on dynamic data evaluation. When the tin stripping water reuse performance analysis method program based on dynamic data evaluation is executed by a processor, the steps of the tin stripping water reuse performance analysis method based on dynamic data evaluation described in any one of claims 1 to 5 are implemented.

Images