A method and system for automatic online detection of PET production equipment

By establishing a safety distance prediction model based on feedforward neural network, automatic online detection of PET production equipment is realized, the problem of unreasonable self-testing methods of production data is solved, the detection efficiency and accuracy are improved, and the safety of the production process is ensured. .

CN114091779BActive Publication Date: 2024-11-26YANGZHOU SANXING PLASTIC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111437731.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-30
Publication Date
2024-11-26
Estimated Expiration
2041-11-30

AI Technical Summary

Technical Problem

The self-inspection method of PET production equipment is unreasonable, resulting in a low pass rate of detection results. The existing slice detection technology is cumbersome and inefficient, and has not been widely promoted.

Method used

Using automatic online detection method, by obtaining the historical opening size data set, extrusion speed data set and safe distance data set of PET production equipment, the feedforward neural network is trained, and a safe distance prediction model is established to detect and judge whether the safe distance is in real time. Safe and provide reminder information.

Benefits of technology

Automatic detection based on production historical data is realized, detection efficiency and accuracy are improved, the problem of unreasonable self-inspection methods of production data is solved, and the reliability of the detection results of PET production equipment and the safety of the production process are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114091779B_ABST
    Figure CN114091779B_ABST
Patent Text Reader

Abstract

The present invention discloses an automatic online detection method for PET production equipment, the method comprising: obtaining a first historical opening size data set of a die-forming flat model of the PET production equipment; obtaining a historical extrusion speed data set of the PET material in the die-forming flat model; obtaining a historical safety distance data set; obtaining a safety distance prediction model; obtaining a first opening size of the die-forming flat model of the PET production equipment; obtaining a first extrusion speed of the PET material in the die-forming flat model; obtaining a first predicted safety distance; obtaining an actual safety distance; obtaining a first judgment result; and determining whether to obtain a first reminder message. The technical problem of an unreasonable self-checking method for production data of PET production equipment is solved, and the technical effect of automatically detecting the production data of PET production equipment based on production history data and obtaining a judgment result is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for automatic online detection of PET production equipment. Background Art

[0002] PET polyethylene terephthalate, commonly known as polyester resin, is the most important variety of thermoplastic polyester. During the processing of PET materials, the parameters of PET production equipment are set based on the PET finished product standards. After the settings are completed, the PET finished products are tested using automatic detection technology. The automatic detection technology relies on the PET finished product standards to determine relevant indicators. The PET finished products may be interfered by environmental factors during product processing, resulting in certain differences between the PET finished products and the PET finished product standards. The test results have a low pass rate. Alternatively, slice detection technology is used for detection and optimization of relevant parameters. However, the slice detection technology has a cumbersome operation process and low efficiency, and may not be widely promoted and used.

[0003] The present application solves the technical problem that the production data self-checking method of PET production equipment is unreasonable. Summary of the invention

[0004] The embodiment of the present application solves the technical problem of unreasonable self-inspection of production data of PET production equipment by providing an automatic online detection method and system for PET production equipment, and achieves the technical effect of automatically detecting the production data of PET production equipment based on production history data and obtaining judgment results.

[0005] In view of the above problems, an embodiment of the present application provides an automatic online detection method and system for PET production equipment.

[0006] In a first aspect, an embodiment of the present application provides an automatic online detection method for PET production equipment, wherein the method is applied to an automatic online detection device for PET production equipment.

[0007] On the other hand, an embodiment of the present application provides an automatic online detection system for PET production equipment, wherein the system includes: a first acquisition unit, the first acquisition unit is used to obtain a first historical opening size data set of a mouth die forming flat model of the PET production equipment; a second acquisition unit, the second acquisition unit is used to obtain a historical extrusion speed data set of the PET material in the mouth die forming flat model; a third acquisition unit, the third acquisition unit is used to obtain a historical safety distance data set; a fourth acquisition unit, the fourth acquisition unit is used to train a feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; a fifth acquisition unit, the fifth acquisition unit is used to obtain a historical safety distance prediction model. The fifth obtaining unit is used to obtain the first opening size of the die molding flat model of the PET production equipment; the sixth obtaining unit, the sixth obtaining unit is used to obtain the first extrusion speed of the PET material in the die molding flat model; the seventh obtaining unit, the seventh obtaining unit is used to input the first opening size and the first extrusion speed into the safety distance prediction model to obtain the first predicted safety distance; the eighth obtaining unit, the eighth obtaining unit is used to obtain the actual safety distance; the ninth obtaining unit, the ninth obtaining unit is used to judge whether the actual safety distance is safe according to the first predicted safety distance, and obtain a first judgment result; the first determining unit, the first determining unit is used to determine whether to obtain the first reminder information according to the first judgment result.

[0008] In a third aspect, an embodiment of the present application provides an automatic online detection system for PET production equipment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods described in the first aspect are implemented.

[0009] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0010] By adopting the method of obtaining the first historical opening size data set of the die-forming flat model of the PET production equipment; obtaining the historical extrusion speed data set of the PET material in the die-forming flat model; obtaining the historical safety distance data set; training the feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; obtaining the first opening size of the die-forming flat model of the PET production equipment; obtaining the first extrusion speed of the PET material in the die-forming flat model; inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain the first predicted safety distance; obtaining the actual safety distance; judging whether the actual safety distance is safe according to the first predicted safety distance to obtain the first judgment result; and determining whether to obtain the first reminder information according to the first judgment result, the technical problem of unreasonable self-checking method of production data of PET production equipment is solved, and the technical effect of automatically detecting the production data of PET production equipment based on production history data and obtaining the judgment result is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of a process of an automatic online detection method for PET production equipment according to an embodiment of the present application;

[0013] Figure 2 A schematic diagram of a flow chart of obtaining a safety distance prediction model for an automatic online detection method for PET production equipment according to an embodiment of the present application;

[0014] Figure 3 A schematic diagram of a flow chart of obtaining second reminder information in an automatic online detection method for PET production equipment according to an embodiment of the present application;

[0015] Figure 4 A schematic diagram of a process for obtaining third reminder information in an automatic online detection method for PET production equipment according to an embodiment of the present application;

[0016] Figure 5 A schematic diagram of a process for obtaining a first judgment result of an automatic online detection method for PET production equipment according to an embodiment of the present application;

[0017] Figure 6 This is a structural schematic diagram of an automatic online detection system for PET production equipment according to an embodiment of the present application;

[0018] Figure 7 It is a schematic diagram of the structure of an exemplary electronic device according to an embodiment of the present application.

[0019] Explanation of the figure marks: first obtaining unit 11, second obtaining unit 12, third obtaining unit 13, fourth obtaining unit 14, fifth obtaining unit 15, sixth obtaining unit 16, seventh obtaining unit 17, eighth obtaining unit 18, ninth obtaining unit 19, first determining unit 20, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. DETAILED DESCRIPTION

[0020] The embodiment of the present application solves the technical problem of unreasonable self-inspection of production data of PET production equipment by providing an automatic online detection method and system for PET production equipment, and achieves the technical effect of automatically detecting the production data of PET production equipment based on production history data and obtaining judgment results.

[0021] Application Overview

[0022] Relying on PET finished product standards or slice detection technology to inspect PET production equipment, the detection results are not satisfactory, and it is impossible to optimize the relevant data in a targeted manner. The automatic detection technology analysis data does not consider the impact of the environment or other related factors on the processing process.

[0023] There is a technical problem in the prior art that the production data self-checking method of PET production equipment is unreasonable.

[0024] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0025] An embodiment of the present application provides an automatic online detection method for PET production equipment, wherein the method includes obtaining a first historical opening size data set of a die-forming flat model of the PET production equipment; obtaining a historical extrusion speed data set of the PET material in the die-forming flat model; obtaining a historical safety distance data set; training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; obtaining a first opening size of the die-forming flat model of the PET production equipment; obtaining a first extrusion speed of the PET material in the die-forming flat model; inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance; obtaining an actual safety distance; judging whether the actual safety distance is safe according to the first predicted safety distance to obtain a first judgment result; and determining whether a first reminder message is obtained according to the first judgment result.

[0026] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0027] Embodiment 1

[0028] like Figure 1 As shown, an embodiment of the present application provides an automatic online detection method for PET production equipment, wherein the method is applied to an automatic online detection device for PET production equipment, and the method includes:

[0029] S100: Obtaining a first historical opening size data set of a die forming flat model of the PET production equipment;

[0030] Specifically, the PET production equipment is an automated PET processing product production equipment, and the PET production equipment can be a vacuum molding box, a cutting machine, a PET mold or other equipment used for automated PET processing product production. This application mainly analyzes the equipment from the detection perspective, and the equipment that affects the detection results will be studied in depth. The mouth die forming flat model is a plastic tube forming mold after normalizing the blank. The first historical opening size data set is a data record of the mouth die forming flat model of the PET production equipment during the production and processing process. The first historical opening size data acquisition method can be a related record statistical table. The first historical opening size data acquisition method is not fixed and depends specifically on the PET production equipment.

[0031] S200: Obtaining a historical extrusion speed data set of the PET material in the die forming flat model;

[0032] Specifically, the historical extrusion speed data set is obtained during the production and processing of the PET material in the die-forming flat model of the PET production equipment. The historical extrusion speed data acquisition method can be based on relevant data conversion or the statistical result of the data acquisition module. The acquisition method of the historical extrusion speed data is not fixed and depends on the PET production equipment. To further illustrate, if there is a PET water supply pipe production line, during the water pipe production process, the historical extrusion speed of the PET material will affect the wall thickness of the water pipe product. In the uniform situation of the die-forming flat model of the PET production equipment, within a certain range, the higher the PET material extrusion speed, the thicker the wall; the lower the PET material extrusion speed, the thinner the wall. Reasonable extrusion speed can ensure the accuracy of the amount of PET material while ensuring the quality of the water pipe and reduce the loss of PET material. Therefore, the historical extrusion speed data can affect the detection data of the PET production equipment to a certain extent.

[0033] S300: Obtain historical safety distance dataset;

[0034] Specifically, the historical safety distance data is the safety distance data of the PET products formed during the production and processing of products formed by PET materials due to the thermoplasticity of PET materials. A simple example is used to illustrate that the most common PET material is spun into polyester fiber, i.e., terylene, which is used in the textile industry. During the process of processing into silk, the safety distance needs to be collected. The historical safety distance can be obtained by statistically analyzing the safety distance displayed by the integrated digital display module of the PET production equipment. The historical safety distance is not fixed and depends on the PET production equipment. The historical safety distance data set is formed by a large amount of collection of the safety distance.

[0035] S400: training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set, and the historical extrusion speed data set to obtain a safety distance prediction model;

[0036] Specifically, the feedforward neural network is the simplest neural network, and each neuron is arranged in layers. Each neuron is only connected to the neurons in the previous layer. The output of the previous layer is received and output to the next layer. There is no feedback between the layers. The feedforward neural network is a type of artificial neural network and a common model in machine learning artificial intelligence systems. The historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set are input into the feedforward neural network, and the feedforward neural network is trained with a large amount of training data. Each set of input data includes safety distance, opening size data and extrusion speed data. After the training, the feedforward neural network is converted into a safety distance prediction model, which can perform safety distance prediction. It is specially explained that the input data of the feedforward neural network only means that the data is added to the feedforward neural network for model training, and does not represent the data at the input and output ends of the feedforward neural network.

[0037] To further specify, the data in the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set need to be input correspondingly during the input process, that is, each group of input data includes corresponding groups in the safety distance, opening size data and extrusion speed data. During the production and processing of the die forming flat model of the PET production equipment, the historical data records of the same indicators will have certain changes. The opening size data and extrusion speed data at the same historical moment are input to obtain the safety distance corresponding to the same historical moment. Simply put, there is a certain conversion relationship between the safety distance, opening size data and extrusion speed data at the same historical moment, and training the feedforward neural network is to extract the conversion relationship therein. The conversion relationship is finally saved in the safety distance prediction model obtained, thereby ensuring the rationality of the input data of the feedforward neural network, providing a basis for the accuracy and reliability of the safety distance prediction, and providing data support for the acquisition of the safety distance prediction model.

[0038] S500: Obtaining a first opening size of a die-forming flat model of the PET production equipment;

[0039] Specifically, the first opening size of the mouth die molding flat model of the PET production equipment is the opening size of the mouth die molding flat model of the PET production equipment at the current stage. The opening size can be obtained through the digital display position data of the PET production equipment, or by using monitoring equipment for video image analysis. During the analysis process, attention should be paid to the scale between the image and the actual situation. The method for obtaining the first opening size is not fixed, and it depends specifically on the PET production equipment. The first opening size of the mouth die molding flat model of the PET production equipment is obtained to provide data support for subsequent data analysis.

[0040] S600: obtaining a first extrusion speed of the PET material in the die-forming flat model;

[0041] Specifically, the first extrusion speed of the PET material in the die-forming flat model is the extrusion speed of the PET material in the die-forming flat model at the current stage. The method for obtaining the first extrusion speed is not fixed, and it depends specifically on the PET production equipment. It can be obtained using a sensor at the material extrusion port of the die-forming flat model. If the PET production equipment has relevant data, the data can also be converted to obtain the first extrusion speed. To put it simply, the machine sets the extrusion amount and extrusion time of the PET material, and limits the PET material to uniform extrusion. The extrusion speed of the PET material can be converted using the ratio of the extrusion amount of the PET material to the extrusion time of the PET material.

[0042] S700: inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance;

[0043] Specifically, the safety distance prediction model inputs the first opening size and the first extrusion speed, and the obtained data is the first safety distance prediction data, that is, the first predicted safety distance is obtained. The safety distance prediction model is a mathematical model. There is a conversion relationship between the first opening size and the first extrusion speed and the first predicted safety distance. Conversion calculation is performed in the safety distance prediction model to obtain the first predicted safety distance, providing support for data comparison and analysis processing between the actual safety distance and the first predicted safety distance.

[0044] S800: Get the actual safety distance;

[0045] Specifically, the actual safety distance is obtained by collecting data on the safety distance of the PET production equipment under the conditions corresponding to the first opening size and the first extrusion speed. The actual safety distance is the PET product processing process. The PET production equipment has a module for real-time measurement of the safety distance. The real-time displayed data corresponding to the safety distance measurement module is the actual safety distance. The method for obtaining the actual safety distance is not fixed and depends specifically on the PET production equipment.

[0046] S900: judging whether the actual safety distance is safe according to the first predicted safety distance, and obtaining a first judgment result;

[0047] S1000: Determine whether to obtain first reminder information according to the first judgment result.

[0048] Specifically, the first predicted safety distance is not equal to the actual safety distance. During the production of PET products, the PET production equipment may have a certain difference between the first predicted safety distance and the actual safety distance due to certain faults, unreasonable parameter modification or other reasons. The first judgment result is the result of analyzing and comparing the difference. The first judgment result determines whether the actual safety distance is safe, and the judgment result may be safe or unsafe. The first reminder information is used to remind of the abnormality of the judgment result when the first judgment result determines that the actual safety distance is unsafe. The first judgment result is obtained by analysis and the first reminder information is used for reminder, that is, automatic reminder for the detection result of the PET production equipment, to provide support for ensuring the normal operation of the PET production equipment, and to reduce the waste of production costs caused by abnormal operation of the PET production equipment.

[0049] Furthermore, the step S300 of obtaining the historical safety distance data set includes:

[0050] S310: Obtain historical safety distance data;

[0051] S320: Filter and obtain safety distance data corresponding to the first historical opening size data set and the historical extrusion speed data set from the historical safety distance data to obtain the historical safety distance data set.

[0052] Specifically, the safety distance data corresponding to the first historical opening size data set and the historical extrusion speed data set are screened from the historical safety distance data, and the corresponding opening size data set and the historical extrusion speed data set at the same historical stage and the same data collection frequency, and the corresponding safety distance data set at the same historical stage and the same data collection frequency is the historical safety distance data set. The correlation between the first historical opening size data set, the historical extrusion speed data set and the historical safety distance data and the rationality of the data are guaranteed, providing data support for the reliability of subsequent data analysis.

[0053] Further, such as Figure 2 As shown, the feedforward neural network is trained according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model, and step S400 includes:

[0054] S410: Using the historical safety distance data set as ideal output data of the feedforward neural network;

[0055] S420: Using the first historical opening size data set and the historical extrusion speed data set as input data of the feedforward neural network;

[0056] S430: Using a back propagation algorithm to train the feedforward neural network to a stable state, to obtain the safety distance prediction model.

[0057] Specifically, the feedforward neural network is an artificial neural network, and the back propagation algorithm is the most commonly used and most effective algorithm for training artificial neural networks at this stage. In order to ensure that the feedforward neural network can output the historical safety distance data set after inputting the first historical opening size data set and the historical extrusion speed data set, that is, the ideal output data set of the feedforward neural network is the historical safety distance data set, the feedforward neural network is trained using the back propagation algorithm. After the first historical opening size data set and the historical extrusion speed data set are input, the output is determined to be the historical safety distance data set, that is, the training of the feedforward neural network is completed. The training completion model is different from the feedforward neural network and is the safety distance prediction model. Simply put, the safety distance prediction model and the feedforward neural network have the same structure but are different. The difference mainly lies in the corresponding conversion relationship between input and output in the safety distance prediction model.

[0058] To further specify, the specific steps of the back propagation algorithm include: inputting the training set data into the input layer of the feedforward neural network, passing through the hidden layer, and finally reaching the output layer and outputting the result, which is the forward propagation process of the feedforward neural network; since there is an error between the output result of the feedforward neural network and the actual result, the error between the estimated value and the actual value is first calculated, and the error is backpropagated from the output layer to the hidden layer until it propagates to the input layer; in the process of back propagation, the values ​​of various parameters are adjusted according to the error; the above process is continuously iterated until convergence, thereby ensuring the accuracy and rationality of the safety distance prediction model, providing a model basis for data conversion, and further ensuring the reliability of the output data of the safety distance prediction model.

[0059] Further, such as Figure 3 As shown, the embodiment of the present application includes:

[0060] S1100: Obtaining the expected production thickness of the PET material;

[0061] S1200: collecting the actual thickness of the PET material by measuring;

[0062] S1300: Determine the relationship between the actual thickness and the expected production thickness;

[0063] S1400: If the actual thickness is greater than the expected production thickness, obtain second reminder information, where the second reminder information is used to remind that the actual thickness is greater than the expected production thickness.

[0064] Specifically, the expected production thickness of the PET material is obtained at the initial stage of product production based on product demand and the industry standard of the product. The expected production thickness includes the standard production thickness of the PET product and the threshold limit of the production thickness. The actual thickness of the PET material is collected by measurement. The collection method is mainly specifically limited according to the required accuracy of the PET product, such as using an electronic micrometer or other related measuring equipment to measure and judge the relationship between the actual thickness and the expected production thickness. There are three possible results. In particular, it is explained that the actual production thickness is affected by the extrusion speed of the PET material and the opening size of the die molding flat model of the PET production equipment. If the actual thickness is less than the expected production thickness, the threshold value of the production thickness is used. The value is limited. Exceeding the threshold value will cause the actual safety distance to be greater than the first predicted safety distance, and then the first judgment result is obtained. The first judgment result is judged to be unsafe. Not exceeding the threshold value indicates that the product is within the allowable error range, that is, it meets the expected production thickness requirement. If the actual thickness is equal to the expected production thickness, that is, it meets the expected production thickness requirement. If the actual thickness is greater than the expected production thickness, a second reminder message is obtained. The second reminder message is used to remind that the actual thickness is greater than the expected production thickness. The thickness of the finished PET product is further analyzed, which provides a data basis for further optimizing the setting data, provides an explanation for judging the detection results through the actual safety distance, and provides an explanation for the rationality of the detection and judgment process.

[0065] Further, such as Figure 4 As shown, if the actual thickness is greater than the expected production thickness, after obtaining the second reminder information, step S1400 includes:

[0066] S1410: Obtaining a thickness difference according to the expected production thickness and the actual thickness;

[0067] S1420: Calculating a first relationship between the thickness difference and the pressure according to a linear regression function;

[0068] S1430: Obtaining first pressure information according to the thickness difference and the first relationship;

[0069] S1440: Obtain third reminder information according to the first pressure information, where the third reminder information is used to remind to add a pressure roller according to the first pressure information.

[0070] To further specify, based on the expected production thickness and the actual thickness, a thickness difference is obtained, the thickness difference being the thickness difference obtained by subtracting the expected production thickness from the actual thickness, and a first relationship between the thickness difference and pressure is calculated based on a linear regression function, and a functional relationship exists between the thickness difference and pressure, and the functional relationship can be approximately converted using a straight line, and the specific calculation method is not repeated here, and first pressure information is obtained based on the thickness difference and the first relationship, and the first pressure information is the pressure value corresponding to the thickness difference, and third reminder information is obtained based on the first pressure information, and the third reminder information is used to remind to add a pressure roller according to the first pressure information, and the pressure roller is a general term for an axial machine part for applying pressure, and adding a pressure roller can reduce the actual production thickness, and the production thickness can be intelligently adjusted, which provides further refinement for the integrity of the automatic online detection scheme of the PET production equipment and ensures the comprehensiveness of the reminder information corresponding to the monitoring scheme.

[0071] Further, the step S100 of obtaining a first historical opening size data set of a die forming flat model of the PET production equipment includes:

[0072] S110: Obtaining a predetermined opening threshold of a die forming flat model of the PET production equipment;

[0073] S120: Obtain a historical opening size data set of a die forming flat model of the PET production equipment;

[0074] S130: Filtering the historical opening size data set according to the predetermined opening threshold to obtain the first historical opening size data set.

[0075] Specifically, a predetermined opening threshold of the die-forming flat model of the PET production equipment is obtained, wherein the threshold is limited for the PET production equipment to process the PET product and is specifically set according to the characteristics of the PET product, and a historical opening size data set of the die-forming flat model of the PET production equipment is obtained, wherein the historical opening size data set is a data set obtained by indiscriminately counting the opening size data of the processing process, and the historical opening size data set is filtered according to the predetermined opening threshold, and data that meets the predetermined opening threshold is counted to obtain the first historical opening size data set, thereby ensuring the reliability of the opening size data and ensuring that the opening size of the die-forming flat model of the PET production equipment at the time corresponding to the first historical opening size data set meets the set requirements, thereby providing a data basis for further data analysis.

[0076] Further, such as Figure 5As shown, judging whether the actual safety distance is safe according to the first predicted safety distance to obtain a first judgment result, step S900 further includes:

[0077] S910: Obtain a predetermined distance threshold;

[0078] S920: Determine whether the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold;

[0079] S930: If the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold, determine that the first judgment result is that the actual safety distance is safe;

[0080] S940: If the difference between the first predicted safety distance and the actual safety distance is not within the predetermined distance threshold, determine that the first judgment result is that the actual safety distance is unsafe.

[0081] Specifically, a predetermined distance threshold is obtained, and the predetermined threshold is the distance limit formed by the maximum and minimum values ​​of the difference between the first predicted safety distance and the historical safety distance data set, and it is determined whether the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold. According to the judgment standard, if the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold, the first judgment result is determined to be that the actual safety distance is safe; if the difference between the first predicted safety distance and the actual safety distance is not within the predetermined distance threshold, the first judgment result is determined to be that the actual safety distance is unsafe. The first judgment result judgment standard allows a certain range of errors, taking into account that the actual production process is affected by various factors, while ensuring that the PET products produced by the PET production equipment meet the product requirements, the qualified rate of the products is guaranteed, and data support is provided for the rationality of the first judgment result. The first judgment result is the automatic detection result, which further ensures the reliability of the automatic detection result.

[0082] In summary, the automatic online detection method and system for PET production equipment provided in the embodiments of the present application have the following technical effects:

[0083] By adopting the method of obtaining the first historical opening size data set of the die forming flat model of the PET production equipment; obtaining the historical extrusion speed data set of the PET material in the die forming flat model; obtaining the historical safety distance data set; training the feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; obtaining the first opening size of the die forming flat model of the PET production equipment; obtaining the first extrusion speed of the PET material in the die forming flat model; inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance; obtaining the actual safety distance; judging whether the actual safety distance is safe according to the first predicted safety distance to obtain a first judgment result; and determining whether to obtain the first reminder information according to the first judgment result. The embodiment of the present application solves the technical problem of unreasonable self-checking mode of production data of PET production equipment by providing an automatic online detection method and system for PET production equipment, and achieves the technical effect of automatically detecting the production data of PET production equipment based on production history data and obtaining judgment results. 2. The historical safety distance data set is used as the ideal output data of the feedforward neural network; the first historical opening size data set and the historical extrusion speed data set are used as the input data of the feedforward neural network; the feedforward neural network is trained to a stable state using the back propagation algorithm to obtain the safety distance prediction model. The accuracy and rationality of the safety distance prediction model are guaranteed, a model basis is provided for data conversion, and the reliability of the output data of the safety distance prediction model is further guaranteed.

[0084] 3. Due to the adoption of obtaining the expected production thickness of the PET material; collecting the actual thickness of the PET material by measurement; judging the size relationship between the actual thickness and the expected production thickness; if the actual thickness is greater than the expected production thickness, obtaining a second reminder message, the second reminder message is used to remind that the actual thickness is greater than the expected production thickness. Further analysis of the thickness of the finished PET product provides a data basis for further optimizing the setting data, provides an explanation for determining the detection result through the actual safety distance, and provides an explanation for the rationality of the detection and determination process.

[0085] 4. The method adopts the method of obtaining the thickness difference according to the expected production thickness and the actual thickness; calculating the first relationship between the thickness difference and the pressure according to the linear regression function; obtaining the first pressure information according to the thickness difference and the first relationship; obtaining the third reminder information according to the first pressure information, and the third reminder information is used to remind to add a pressure roller according to the first pressure information. Adding a pressure roller can reduce the actual production thickness and intelligently adjust the production thickness, which provides further refinement for the integrity of the automatic online detection scheme of the PET production equipment and ensures the comprehensiveness of the reminder information corresponding to the monitoring scheme.

[0086] 5. By adopting the method of obtaining a predetermined opening threshold of the die-forming flat model of the PET production equipment; obtaining a historical opening size data set of the die-forming flat model of the PET production equipment; and filtering the historical opening size data set according to the predetermined opening threshold to obtain the first historical opening size data set, the reliability of the opening size data is ensured, and the opening size of the die-forming flat model of the PET production equipment at the time corresponding to the first historical opening size data set meets the setting requirements, providing a data basis for further data analysis.

[0087] 6. Due to the adoption of obtaining a predetermined distance threshold; judging whether the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold; if the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold, determining the first judgment result to be that the actual safety distance is safe; if the difference between the first predicted safety distance and the actual safety distance is not within the predetermined distance threshold, determining the first judgment result to be that the actual safety distance is unsafe. The first judgment result determination standard allows a certain range of error, considering that the actual production process is affected by various factors, while ensuring that the PET products produced by the PET production equipment meet the product requirements, ensuring the product qualification rate, providing data support for the rationality of the first judgment result, the first judgment result is the automatic detection result, further ensuring the reliability of the automatic detection result.

[0088] Embodiment 2

[0089] Based on the same inventive concept as the automatic online detection method for PET production equipment in the aforementioned embodiment, Figure 6 As shown, the embodiment of the present application provides an automatic online detection system for PET production equipment, wherein the system includes:

[0090] A first obtaining unit 11, the first obtaining unit 11 is used to obtain a first historical opening size data set of a die forming flat model of the PET production equipment;

[0091] A second obtaining unit 12, the second obtaining unit 12 is used to obtain a historical extrusion speed data set of the PET material in the die forming flat model;

[0092] A third obtaining unit 13, wherein the fourth obtaining unit 13 is used to obtain a historical safety distance data set;

[0093] A fourth obtaining unit 14, the fourth obtaining unit 14 is used to train a feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model;

[0094] A fifth obtaining unit 15, the fifth obtaining unit 15 is used to obtain a first opening size of a die forming flat model of the PET production equipment;

[0095] A sixth obtaining unit 16, the sixth obtaining unit 16 is used to obtain a first extrusion speed of the PET material in the die-forming flat model;

[0096] a seventh obtaining unit 17, wherein the seventh obtaining unit 17 is used to input the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance;

[0097] An eighth obtaining unit 18, wherein the eighth obtaining unit 18 is used to obtain an actual safety distance;

[0098] a ninth obtaining unit 19, wherein the ninth obtaining unit 19 is configured to determine whether the actual safety distance is safe according to the first predicted safety distance, and obtain a first determination result;

[0099] The first determining unit 20 is used to determine whether to obtain first reminder information according to the first judgment result.

[0100] Furthermore, the system comprises:

[0101] a tenth obtaining unit, the tenth obtaining unit being used to obtain historical safety distance data;

[0102] An eleventh obtaining unit is used to filter and obtain safety distance data corresponding to the first historical opening size data set and the historical extrusion speed data set from the historical safety distance data, so as to obtain the historical safety distance data set.

[0103] Furthermore, the system comprises:

[0104] a second determining unit, the second determining unit being configured to use the historical safety distance data set as ideal output data of the feedforward neural network;

[0105] a first input unit, the first input unit being used to use the first historical opening size data set and the historical extrusion speed data set as input data of the feedforward neural network;

[0106] The first execution unit is used to train the feedforward neural network to a stable state by using a back propagation algorithm to obtain the safety distance prediction model.

[0107] Furthermore, the system comprises:

[0108] a twelfth obtaining unit, the twelfth obtaining unit being used to obtain an expected production thickness of the PET material;

[0109] A first collecting unit, the first collecting unit is used to collect the actual thickness of the PET material by measurement;

[0110] A first judgment unit, the first judgment unit is used to judge the size relationship between the actual thickness and the expected production thickness;

[0111] A thirteenth obtaining unit, the thirteenth obtaining unit is used to obtain second reminder information if the actual thickness is greater than the expected production thickness, and the second reminder information is used to remind that the actual thickness is greater than the expected production thickness.

[0112] Furthermore, the system comprises:

[0113] a fourteenth obtaining unit, the fourteenth obtaining unit being used to obtain a thickness difference according to the expected production thickness and the actual thickness;

[0114] a first calculation unit, the first calculation unit being configured to calculate a first relationship between the thickness difference and the pressure according to a linear regression function;

[0115] a fifteenth obtaining unit, the fifteenth obtaining unit being configured to obtain first pressure information according to the thickness difference and the first relationship;

[0116] A sixteenth obtaining unit, wherein the sixteenth obtaining unit is used to obtain third reminder information according to the first pressure information, wherein the third reminder information is used to remind to increase the pressure roller according to the first pressure information.

[0117] Furthermore, the system comprises:

[0118] A seventeenth obtaining unit, the seventeenth obtaining unit is used to obtain a predetermined opening threshold value of the die forming flat model of the PET production equipment;

[0119] An eighteenth obtaining unit, the eighteenth obtaining unit is used to obtain a historical opening size data set of a mouth die forming flat model of the PET production equipment;

[0120] A nineteenth obtaining unit is used to filter the historical opening size data set according to the predetermined opening threshold to obtain the first historical opening size data set.

[0121] Furthermore, the system comprises:

[0122] a twentieth obtaining unit, the twentieth obtaining unit being used to obtain a predetermined distance threshold;

[0123] a second judgment unit, the second judgment unit being used to judge whether the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold;

[0124] a third determining unit, configured to determine that the first judgment result is that the actual safety distance is safe if the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold;

[0125] A fourth determining unit, wherein the fourth determining unit is configured to determine that the first judgment result is that the actual safety distance is unsafe if the difference between the first predicted safety distance and the actual safety distance is not within the predetermined distance threshold.

[0126] Exemplary Electronic Devices

[0127] Reference below Figure 7 To describe the electronic device of the embodiment of the present application,

[0128] Based on the same inventive concept as the automatic online detection method for PET production equipment in the aforementioned embodiment, an embodiment of the present application also provides an automatic online detection system for PET production equipment, including: a processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system executes any one of the methods described in the first aspect.

[0129] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0130] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0131] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.

[0132] The memory 301 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus architecture 304. The memory may also be integrated with the processor.

[0133] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing an automatic online detection method for PET production equipment provided in the above embodiment of the present application.

[0134] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0135] An embodiment of the present application provides an automatic online detection method for PET production equipment, wherein the method is applied to an automatic online detection device for PET production equipment, and the method includes: obtaining a first historical opening size data set of a die-forming flat model of the PET production equipment; obtaining a historical extrusion speed data set of the PET material in the die-forming flat model; obtaining a historical safety distance data set; training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; obtaining a first opening size of the die-forming flat model of the PET production equipment; obtaining a first extrusion speed of the PET material in the die-forming flat model; inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance; obtaining an actual safety distance; judging whether the actual safety distance is safe according to the first predicted safety distance to obtain a first judgment result; and determining whether a first reminder message is obtained according to the first judgment result.

[0136] Those skilled in the art will appreciate that the various digital numbers such as the first and second involved in the present application are only for the convenience of description, and are not used to limit the scope of the embodiments of the present application, nor do they represent the order of precedence. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0137] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0138] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or the design of any combination of the above functions. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any traditional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration to implement.

[0139] The steps of the method or algorithm described in the embodiments of the present application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a terminal. Optionally, the processor and the storage medium can also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0140] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. An automatic online detection method for PET production equipment, characterized in that: The method is applied to an automatic online detection device for PET production equipment, and the method comprises: Obtain a first historical opening size data set of a die forming flat model of the PET production equipment; Obtaining a historical extrusion speed data set of the PET material in the die forming flat model; Obtain historical safety distance datasets; Training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set, and the historical extrusion speed data set to obtain a safety distance prediction model; Obtaining a first opening size of a die-forming flat model of the PET production equipment; Obtaining a first extrusion speed of the PET material in the die-forming flat model; Inputting the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance; Get the actual safety distance; Determine whether the actual safety distance is safe according to the first predicted safety distance, and obtain a first determination result; Determining whether to obtain first reminder information according to the first judgment result; The obtaining of the historical safety distance data set includes: Obtain historical safety distance data; Filtering and obtaining safety distance data corresponding to the first historical opening size data set and the historical extrusion speed data set from the historical safety distance data to obtain the historical safety distance data set; The step of training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set, and the historical extrusion speed data set to obtain a safety distance prediction model includes: Using the historical safety distance data set as the ideal output data of the feedforward neural network; Using the first historical opening size data set and the historical extrusion speed data set as input data of the feedforward neural network; The feedforward neural network is trained to a stable state using a back-propagation algorithm to obtain the safety distance prediction model.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining the expected production thickness of the PET material; Collecting the actual thickness of the PET material by measuring; Determining the relationship between the actual thickness and the expected production thickness; If the actual thickness is greater than the expected production thickness, second reminder information is obtained, where the second reminder information is used to remind that the actual thickness is greater than the expected production thickness.

3. The method according to claim 2, characterized in that If the actual thickness is greater than the expected production thickness, after obtaining the second reminder information, the method further includes: Obtaining a thickness difference according to the expected production thickness and the actual thickness; Calculating a first relationship between the thickness difference and the pressure according to a linear regression function; obtaining first pressure information according to the thickness difference and the first relationship; According to the first pressure information, third reminder information is obtained, and the third reminder information is used to remind to increase the pressure roller according to the first pressure information.

4. The method according to claim 1, characterized in that The step of obtaining a first historical opening size data set of a die forming flat model of the PET production equipment comprises: Obtaining a predetermined opening threshold of a die-forming flat model of the PET production equipment; Obtain a historical opening size data set of a die forming flat model of the PET production equipment; The historical opening size data set is filtered according to the predetermined opening threshold to obtain the first historical opening size data set.

5. The method according to claim 1, characterized in that The step of judging whether the actual safety distance is safe according to the first predicted safety distance to obtain a first judgment result includes: obtaining a predetermined distance threshold; Determining whether the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold; If the difference between the first predicted safety distance and the actual safety distance is within the predetermined distance threshold, determining that the first judgment result is that the actual safety distance is safe; If the difference between the first predicted safety distance and the actual safety distance is not within the predetermined distance threshold, it is determined that the first judgment result is that the actual safety distance is unsafe.

6. An automatic online detection system for PET production equipment, characterized in that: The system comprises: A first obtaining unit, the first obtaining unit is used to obtain a first historical opening size data set of a die forming flat model of the PET production equipment; A second obtaining unit, the second obtaining unit is used to obtain a historical extrusion speed data set of the PET material in the die forming flat model; A third obtaining unit, the third obtaining unit is used to obtain a historical safety distance data set; a fourth obtaining unit, the fourth obtaining unit being used to train a feedforward neural network according to the historical safety distance data set, the first historical opening size data set and the historical extrusion speed data set to obtain a safety distance prediction model; A fifth obtaining unit, the fifth obtaining unit is used to obtain a first opening size of a die-forming flat model of the PET production equipment; A sixth obtaining unit, the sixth obtaining unit is used to obtain a first extrusion speed of the PET material in the die-forming flat model; a seventh obtaining unit, the seventh obtaining unit being configured to input the first opening size and the first extrusion speed into the safety distance prediction model to obtain a first predicted safety distance; An eighth obtaining unit, wherein the eighth obtaining unit is used to obtain an actual safety distance; a ninth obtaining unit, the ninth obtaining unit being configured to determine whether the actual safety distance is safe according to the first predicted safety distance, and obtain a first determination result; a first determining unit, the first determining unit being used to determine whether to obtain first reminder information according to the first judgment result; The obtaining of the historical safety distance data set includes: Obtain historical safety distance data; Filtering and obtaining safety distance data corresponding to the first historical opening size data set and the historical extrusion speed data set from the historical safety distance data to obtain the historical safety distance data set; The step of training a feedforward neural network according to the historical safety distance data set, the first historical opening size data set, and the historical extrusion speed data set to obtain a safety distance prediction model includes: Using the historical safety distance data set as the ideal output data of the feedforward neural network; Using the first historical opening size data set and the historical extrusion speed data set as input data of the feedforward neural network; The feedforward neural network is trained to a stable state using a back-propagation algorithm to obtain the safety distance prediction model.

7. A device for automatic online detection of PET production equipment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 5 are implemented.