Stainless steel pipe processing control method and device based on defect detection

Abstract

The present invention discloses a stainless steel pipe processing control method and device based on defect detection, which relates to the field of intelligent control technology. The method includes: connecting a stainless steel pipe processing control system to obtain N processing nodes; establishing N data detection blocks, obtaining processing detection data sets, and generating a historical processing detection sample library; performing defect identification on the historical processing detection sample library, and obtaining N processing defect memory libraries corresponding to N processing nodes; establishing N probability density functions; obtaining N real-time processing rates, performing defect probability calculation on the N real-time processing rates, and outputting N defect probabilities; the stainless steel pipe processing control system receives N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes. The method solves the technical problem of defects in steel pipes due to changes in processing rate in the prior art, and achieves the technical effect of improving processing quality by intelligently controlling the processing rate of abnormal processing nodes.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a stainless steel pipe processing control method and device based on defect detection. Background Art

[0002] In the field of stainless steel pipe production and processing, with the intensification of market competition and the continuous improvement of customer requirements for product quality, the balance between processing efficiency and product quality has become the focus of the industry. In the traditional processing process, in order to pursue higher production efficiency, the processing rate is often increased. However, this speed increase is often accompanied by an increase in steel pipe defects, such as cracks, burrs, and increased surface roughness. These defects not only affect the appearance quality of the steel pipe, but may also have a serious impact on its performance and life. Therefore, how to effectively control and reduce the defects of steel pipes while ensuring processing efficiency has become a technical problem that the industry needs to solve urgently. Summary of the invention

[0003] The embodiments of the present application provide a stainless steel pipe processing control method and device based on defect detection, which solves the technical problem in the prior art that defects occur in steel pipes due to changes in processing rate.

[0004] In view of the above problems, the embodiments of the present application provide a stainless steel pipe processing control method and device based on defect detection.

[0005] A first aspect of an embodiment of the present application provides a stainless steel pipe processing control method based on defect detection, the method comprising:

[0006] Connect to the stainless steel pipe processing control system to obtain N processing nodes; establish N data detection blocks according to the N processing nodes, obtain the corresponding processing detection data sets at each processing rate according to the N data detection blocks, and generate a historical processing detection sample library; perform defect identification on the historical processing detection sample library to obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate; establish N probability density functions according to the N processing defect memory libraries; obtain N real-time processing rates, calculate the defect probability of the N real-time processing rates with the N probability density functions, and output N defect probabilities; the stainless steel pipe processing control system receives the N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes.

[0007] A second aspect of the embodiment of the present application provides a stainless steel pipe processing control device based on defect detection, the device comprising:

[0008] A node acquisition module, the node acquisition module is used to connect to the stainless steel pipe processing control system to obtain N processing nodes; a sample library generation module, the sample library generation module is used to establish N data detection blocks according to the N processing nodes, obtain the corresponding processing detection data sets at each processing rate according to the N data detection blocks, and generate a historical processing detection sample library; a defect recognition module, the defect recognition module is used to perform defect recognition on the historical processing detection sample library, and obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate; a function establishment module, the function establishment module is used to establish N probability density functions according to the N processing defect memory libraries; a calculation module, the calculation module is used to obtain N real-time processing rates, calculate the defect probability of the N real-time processing rates with the N probability density functions, and output N defect probabilities; a control module, the control module is used for the stainless steel pipe processing control system to receive the N defect probabilities, generate an early warning signal, and control the processing rate of abnormal processing nodes.

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

[0010] First, connect the stainless steel pipe processing control system to obtain N processing nodes. Then, establish N data detection blocks according to the N processing nodes, obtain the corresponding processing detection data sets at each processing rate according to the N data detection blocks, and generate a historical processing detection sample library. Then, perform defect identification on the historical processing detection sample library, and obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate. Then, establish N probability density functions based on the N processing defect memory libraries. Further, obtain N real-time processing rates, calculate the defect probability of the N real-time processing rates with the N probability density functions, and output N defect probabilities. Finally, the stainless steel pipe processing control system receives N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes. The technical problem of defects in steel pipes caused by changes in processing rate in the prior art is solved, and the technical effect of improving processing quality is achieved by intelligently controlling the processing rate of abnormal processing nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a stainless steel pipe processing control method based on defect detection provided in an embodiment of the present application;

[0013] Figure 2 A schematic structural diagram of a stainless steel pipe processing control device based on defect detection provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: node acquisition module 11 , sample library generation module 12 , defect identification module 13 , function establishment module 14 , calculation module 15 , control module 16 . DETAILED DESCRIPTION

[0015] The embodiments of the present application solve the technical problem in the prior art that defects occur in steel pipes due to changes in processing rate by providing a stainless steel pipe processing control method and device based on defect detection.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the embodiment of the present application provides a stainless steel pipe processing control method based on defect detection, wherein the method includes:

[0020] Connect to the stainless steel pipe processing control system and obtain N processing nodes.

[0021] The stainless steel pipe processing control system is used to control the processing of stainless steel pipes. By connecting the stainless steel processing control system, N processing nodes are obtained. The processing nodes represent different stages or links in the processing process, including material cutting, forming, welding, grinding, heat treatment and other links. Each node corresponds to specific processing operations and process parameters. Each node directly affects the quality and performance of the final product.

[0022] N data detection blocks are established according to the N processing nodes, and processing detection data sets corresponding to each processing rate are obtained according to the N data detection blocks to generate a historical processing detection sample library.

[0023] N data detection blocks are established based on N processing nodes. The data detection block is a specific data collection and analysis area set up for each processing node, which is used to monitor and record the operating status and processing parameters of each node in real time. Each data detection block will be equipped with corresponding sensors and detection equipment to capture key data in the processing process, such as processing rate, temperature, pressure, vibration, etc. As the processing continues, the corresponding processing detection data sets at each processing rate are obtained from the N data detection blocks. The processing detection data sets record the operating conditions and processing effects of each processing node at different processing rates. With the continuous accumulation of processing detection data sets, a historical processing detection sample library is generated to provide data support for defect identification.

[0024] Defect identification is performed on the historical processing detection sample library to obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate.

[0025] After establishing a historical processing inspection sample library containing rich processing data, defects are identified on these data to identify defects that may occur at different processing nodes at different processing rates. The processing defect features (such as cracks, burrs, deformation, etc.) of N processing nodes are obtained from the historical processing inspection sample library to form a corresponding processing defect memory library. Each processing defect memory library is for a specific processing node and contains various defect features that may occur at the node at different processing rates.

[0026] Furthermore, the method further comprises: obtaining N processing defect memory banks corresponding to the N processing nodes;

[0027] Analyze the processing sequence of the N processing nodes, and mark the N processing defect memory banks in sequence; establish a similarity analysis network, call the similarity analysis network to perform similarity identification on the first processing defect memory bank and the second processing defect memory bank, and output a primary similar defect feature; the similarity analysis network performs similarity identification with the third processing defect memory bank based on the primary similar defect feature, and outputs a secondary similar defect feature, and so on, until an N-1 similar defect feature is output; and use the N-1 similar defect feature as a feature element for constructing a processing defect memory bank.

[0028] N processing nodes correspond to N processing defect memories. The processing sequence directly affects the working relationship between each node and the potential defect transmission mechanism. By analyzing the processing sequence of N processing nodes, the N processing defect memories can be identified according to the processing sequence to ensure that the processing defect memories accurately correspond to the corresponding processing nodes. Based on the historical processing defect data, a deep learning model is trained to identify the potential connections and similarities between different processing defect memories. After training, the model is set as a similarity analysis network to capture similar defect features of different processing nodes. The similarity analysis network is called to perform similarity identification on the first processing defect memory and the second processing defect memory, and a similar defect feature is output. The similar defect feature represents the common or similar defect mode in the two memories. The similar defect feature is used as input, and the similarity analysis network is called to perform similarity identification with the third processing defect memory, and a secondary similar defect feature is output, and so on, until the N-1 similar defect features are output, and the N-1 similar defect features are used as the feature elements for constructing the processing defect memory. This iterative process is actually building a hierarchy of defect features. Similar defect features at each layer are obtained based on the similarity recognition of the previous layer and the next processing defect memory library. In this way, the transmission rules and potential correlations of defects between different processing nodes can be gradually obtained.

[0029] According to the N processing defect memory banks, N probability density functions are established.

[0030] Defect feature data corresponding to different processing rates are extracted from N processing defect memory banks, and a suitable probability density function model is selected, such as Gaussian distribution, Poisson distribution, exponential distribution, etc., to establish N probability density functions.

[0031] Furthermore, according to the N processing defect memory banks, N probability density functions are established, and the method includes:

[0032] Analyze the defect variation relationship at each processing rate in the N processing defect memory libraries; identify the probability distribution type according to the defect variation relationship to obtain N initialization probability distributions; and train the N initialization probability distributions respectively with the N processing defect memory libraries to generate the N probability density functions.

[0033] Preferably, defect feature data at different processing rates, including the number, type and severity of defects, are extracted from N processing defect memory banks, and statistical analysis and visualization tools (such as scatter plots, line graphs or box plots) are used to show the changing trend of defects at various processing rates, that is, the defect change relationship; according to the distribution of defect data at different processing rates, by comparing common probability distributions (such as normal distribution, Poisson distribution, exponential distribution, etc.), the probability distribution type that best matches the defect data is identified. If the data shows that the defect rate shows the characteristics of a normal distribution as the rate changes, the normal distribution is used. If the probability of a defect decreases exponentially with an increase in the processing rate, the exponential distribution can be used. If the distribution of the defect rate data is skewed, especially when the long tail phenomenon is significant, the log-normal distribution may be more appropriate; according to the determined probability distribution type, a corresponding probability distribution is initialized for each processing defect memory bank, and the corresponding initialized probability distribution is trained using the data in each processing defect memory bank. Through multiple iterations and optimizations, N trained probability density functions can be obtained, each function corresponding to a specific processing defect memory bank.

[0034] Obtain N real-time processing rates, calculate defect probabilities for the N real-time processing rates using the N probability density functions, and output N defect probabilities.

[0035] Obtain N real-time processing rates, and use N probability density functions to calculate the defect probabilities for the N real-time processing rates. That is to say, for each real-time processing rate, find the corresponding probability density function, use the real-time processing rate as an input value, substitute it into the corresponding probability density function, calculate the probability that the defect probability exceeds a preset threshold at a given real-time processing rate, and obtain N defect probabilities.

[0036] Furthermore, the defect probabilities of the N real-time processing rates are calculated using the N probability density functions, and N defect probabilities are output, the method comprising:

[0037] A preset defect probability threshold is set; the preset defect probability threshold is converted to output a preset processing rate; the N real-time processing rates are input into the N probability density functions, and the integral falling within a range greater than the preset processing rate is calculated to obtain the output N defect probabilities.

[0038] Preferably, a preset defect probability threshold is set to determine whether the processing rate may lead to an excessively high defect rate; the processing rate range of the preset defect probability threshold is found through the probability density function, that is, for each probability density function, its corresponding cumulative distribution function is found, and the preset defect probability threshold is used to find the corresponding processing rate value, i.e., the preset processing rate, on the cumulative distribution function; the N real-time processing rates are respectively input into the corresponding N probability density functions, and the integral value of the probability density function is calculated when the real-time processing rate is greater than the preset processing rate, thereby obtaining the defect probability of the N processing nodes exceeding the preset processing rate at their respective real-time processing rates.

[0039] Furthermore, if the probability density function of the processing node obeys the normal distribution, the integral expression for calculating the defect probability according to the real-time processing rate is as follows:

[0040] ;in, represents the probability of defect occurrence at the real-time processing rate v, represents the preset defect probability threshold, represents the cumulative distribution function (CDF) of the normal distribution, represents the preset processing rate corresponding to the preset defect probability threshold, represents the mean defect probability corresponding to the processing rate in the normal distribution, Indicates the degree of variation of defect probability corresponding to the processing rate in the normal distribution.

[0041] If the probability density function of the processing node obeys the normal distribution, the integral expression for calculating the defect probability according to the real-time processing rate is: ;in, represents the probability of defect occurrence at the real-time processing rate v, represents the preset defect probability threshold, represents the cumulative distribution function (CDF) of the normal distribution, represents the preset processing rate corresponding to the preset defect probability threshold, represents the mean defect probability corresponding to the processing rate in the normal distribution, that is, the center point of the normal distribution, Indicates the degree of variation (standard deviation) of the defect probability corresponding to the processing rate in the normal distribution. Use the CDF of the normal distribution to calculate the probability of defect occurrence at the real-time processing rate .

[0042] The stainless steel pipe processing control system receives the N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes.

[0043] After receiving N defect probabilities, the stainless steel pipe processing control system can set a threshold for the defect probability based on historical data and quality control requirements. When the predicted defect probability exceeds this threshold, an early warning is triggered, an early warning signal is generated, and the control system reduces the processing rate.

[0044] Furthermore, after the stainless steel pipe processing control system receives the N defect probabilities and identifies abnormal processing nodes greater than a preset threshold, the method further includes:

[0045] Obtain an associated processing node of the abnormal processing node based on the N processing nodes, wherein the associated processing node is a node having a processing rate association with the abnormal processing node; determine an adjusted processing rate of the abnormal processing node according to the preset threshold; and synchronously adjust the processing rate of the associated processing node according to the adjusted processing rate.

[0046] When the stainless steel pipe processing control system receives the defect probability of N processing nodes, the system will immediately analyze the defect probability of each node, set a preset threshold of defect probability based on historical data, quality requirements and production standards, and compare the defect probability of each processing node with the preset threshold. When the defect probability of a node exceeds the preset threshold, the node is identified as an abnormal processing node. Once the abnormal processing node is identified, it is necessary to further determine other nodes with processing rate correlation with the abnormal node, that is, associated processing nodes. These associated processing nodes are nodes adjacent to the abnormal node on the production line. According to the preset threshold and the actual situation of the abnormal processing node, a suitable adjustment processing rate is determined to ensure that the adjusted rate can meet the production requirements and ensure product quality. After determining the adjustment processing rate of the abnormal processing node, the associated processing nodes with processing rate correlation with the node will be synchronously adjusted. The purpose of synchronous adjustment is to ensure that the processing rate of the entire production line can be coordinated and consistent, so as to avoid affecting the operating efficiency and quality of the entire production line due to the rate change of a certain node.

[0047] Furthermore, the method of synchronously adjusting the processing rate of the associated processing nodes according to the adjusted processing rate includes:

[0048] Obtain the production efficiency impact index corresponding to the associated processing node; establish an objective function to minimize the production efficiency impact index and of the associated processing node, and generate a synchronization adjustment strategy, wherein the synchronization adjustment expression of each associated processing node is as follows: ; represents the processing rate of associated node j after adjustment, shows the processing rate of associated node j after adjustment, It represents the influence coefficient of the processing rate adjustment of abnormal node i and the processing rate of associated node j. It is used to quantify the change in the rate of associated node j when the rate of abnormal node i changes. represents the processing rate of abnormal node i after adjustment, represents the processing rate of abnormal node i before adjustment; and the associated processing nodes are adjusted according to the synchronous adjustment strategy.

[0049] Preferably, production efficiency influencing indicators of associated processing nodes are obtained from historical data, including but not limited to production cycle, equipment utilization, energy consumption, defective rate, etc.; an objective function is established with the goal of minimizing the sum of production efficiency influencing indicators of associated processing nodes, so as to find a set of processing rate adjustment values ​​to minimize the production efficiency impact of the entire production line; a synchronization adjustment strategy is generated based on the objective function and the production efficiency influencing indicators of associated processing nodes, and the synchronization adjustment expression of each associated processing node is as follows ; represents the processing rate of associated node j after adjustment, shows the processing rate of associated node j after adjustment, It represents the influence coefficient of the processing rate adjustment of abnormal node i and the processing rate of associated node j, which is used to quantify the change in the rate of associated node j when the rate of abnormal node i changes. is positive, the processing rate of i increases, and the processing rate of j also increases. is negative, the processing rate of i increases, and the processing rate of j decreases. represents the processing rate of abnormal node i after adjustment, represents the processing rate of abnormal node i before adjustment; generates a synchronous adjustment strategy based on the synchronous adjustment expression, and adjusts the associated processing nodes according to the synchronous adjustment strategy.

[0050] In summary, the embodiments of the present application have at least the following technical effects:

[0051] First, connect the stainless steel pipe processing control system to obtain N processing nodes. Then, establish N data detection blocks according to the N processing nodes, obtain the corresponding processing detection data sets at each processing rate according to the N data detection blocks, and generate a historical processing detection sample library. Then, perform defect identification on the historical processing detection sample library, and obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate. Then, establish N probability density functions based on the N processing defect memory libraries. Further, obtain N real-time processing rates, calculate the defect probability of the N real-time processing rates with the N probability density functions, and output N defect probabilities. Finally, the stainless steel pipe processing control system receives N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes. The technical problem of defects in steel pipes caused by changes in processing rate in the prior art is solved, and the technical effect of improving processing quality is achieved by intelligently controlling the processing rate of abnormal processing nodes.

[0052] Embodiment 2

[0053] Based on the same inventive concept as the stainless steel pipe processing control method based on defect detection in the aforementioned embodiment, Figure 2 As shown, the present application provides a stainless steel pipe processing control device based on defect detection, and the device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0054] A node acquisition module 11, the node acquisition module 11 is used to connect to the stainless steel pipe processing control system and acquire N processing nodes; a sample library generation module 12, the sample library generation module 12 is used to establish N data detection blocks according to the N processing nodes, acquire the corresponding processing detection data sets at each processing rate according to the N data detection blocks, and generate a historical processing detection sample library; a defect recognition module 13, the defect recognition module 13 is used to perform defect recognition on the historical processing detection sample library, and acquire N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate; a function establishment module 14, the function establishment module 14 is used to establish N probability density functions according to the N processing defect memory libraries; a calculation module 15, the calculation module 15 is used to acquire N real-time processing rates, calculate the defect probability of the N real-time processing rates with the N probability density functions, and output N defect probabilities; a control module 16, the control module 16 is used for the stainless steel pipe processing control system to receive the N defect probabilities, generate an early warning signal, and control the processing rate of abnormal processing nodes.

[0055] Furthermore, the control module 16 is used to execute the following method:

[0056] Obtain an associated processing node of the abnormal processing node based on the N processing nodes, wherein the associated processing node is a node having a processing rate association with the abnormal processing node; determine an adjusted processing rate of the abnormal processing node according to the preset threshold; and synchronously adjust the processing rate of the associated processing node according to the adjusted processing rate.

[0057] Furthermore, the control module 16 is used to execute the following method:

[0058] Obtain the production efficiency impact index corresponding to the associated processing node; establish an objective function to minimize the production efficiency impact index and of the associated processing node, and generate a synchronization adjustment strategy, wherein the synchronization adjustment expression of each associated processing node is as follows: ; represents the processing rate of associated node j after adjustment, shows the processing rate of associated node j after adjustment, It represents the influence coefficient of the processing rate adjustment of abnormal node i and the processing rate of associated node j. It is used to quantify the change in the rate of associated node j when the rate of abnormal node i changes. represents the processing rate of abnormal node i after adjustment, represents the processing rate of abnormal node i before adjustment; and the associated processing nodes are adjusted according to the synchronous adjustment strategy.

[0059] Furthermore, the function establishment module 14 is used to execute the following method:

[0060] Analyze the defect variation relationship at each processing rate in the N processing defect memory libraries; identify the probability distribution type according to the defect variation relationship to obtain N initialization probability distributions; and train the N initialization probability distributions respectively with the N processing defect memory libraries to generate the N probability density functions.

[0061] Furthermore, the calculation module 15 is used to execute the following method:

[0062] A preset defect probability threshold is set; the preset defect probability threshold is converted to output a preset processing rate; the N real-time processing rates are input into the N probability density functions, and the integral falling within a range greater than the preset processing rate is calculated to obtain the output N defect probabilities.

[0063] Furthermore, the calculation module 15 is used to execute the following method:

[0064] If the probability density function of the processing node obeys the normal distribution, the integral expression for calculating the defect probability according to the real-time processing rate is as follows: ;in, represents the probability of defect occurrence at the real-time processing rate v, represents the preset defect probability threshold, represents the cumulative distribution function (CDF) of the normal distribution, represents the preset processing rate corresponding to the preset defect probability threshold, represents the mean defect probability corresponding to the processing rate in the normal distribution, Indicates the degree of variation of defect probability corresponding to the processing rate in the normal distribution.

[0065] Furthermore, the defect identification module 13 is used to perform the following method:

[0066] Analyze the processing sequence of the N processing nodes, and mark the N processing defect memory banks in sequence; establish a similarity analysis network, call the similarity analysis network to perform similarity identification on the first processing defect memory bank and the second processing defect memory bank, and output a primary similar defect feature; the similarity analysis network performs similarity identification with the third processing defect memory bank based on the primary similar defect feature, and outputs a secondary similar defect feature, and so on, until an N-1 similar defect feature is output; and use the N-1 similar defect feature as a feature element for constructing a processing defect memory bank.

[0067] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0069] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover 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 present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A stainless steel pipe processing control method based on defect detection, characterized in that: The method comprises: Connect to the stainless steel pipe processing control system and obtain N processing nodes; Establishing N data detection blocks according to the N processing nodes, acquiring processing detection data sets corresponding to each processing rate according to the N data detection blocks, and generating a historical processing detection sample library; Perform defect recognition on the historical processing detection sample library to obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate; Establishing N probability density functions according to the N processing defect memory banks; Obtaining N real-time processing rates, calculating defect probabilities for the N real-time processing rates using the N probability density functions, and outputting N defect probabilities; The stainless steel pipe processing control system receives the N defect probabilities and generates an early warning signal for controlling the processing rate of abnormal processing nodes; Wherein, according to the N processing defect memory banks, N probability density functions are established, and the method includes: Analyzing defect variation relationships at various processing rates in the N processing defect memory banks; Identify the probability distribution type according to the defect change relationship, and obtain N initialization probability distributions; Using the N processing defect memory banks to train the N initialization probability distributions respectively, to generate the N probability density functions; The method of calculating the defect probability of the N real-time processing rates using the N probability density functions and outputting N defect probabilities includes: Set preset defect probability thresholds; Converting the preset defect probability threshold and outputting a preset processing rate; Input the N real-time processing rates into the N probability density functions, calculate the integral that falls within the range greater than the preset processing rate, and output N defect probabilities; Among them, if the probability density function of the processing node obeys the normal distribution, the integral expression for calculating the defect probability according to the real-time processing rate is as follows: ； in, Indicates the real-time processing rate The probability of defect occurrence under represents the preset defect probability threshold, represents the cumulative distribution function (CDF) of the normal distribution, represents the preset processing rate corresponding to the preset defect probability threshold, represents the mean defect probability corresponding to the processing rate in the normal distribution, Indicates the degree of variation of defect probability corresponding to the processing rate in the normal distribution; Wherein, obtaining N processing defect memory libraries corresponding to the N processing nodes, the method further comprises: Analyzing the processing sequence of the N processing nodes, and marking the N processing defect memory banks in sequence; Establishing a similarity analysis network, calling the similarity analysis network to perform similarity recognition on the first processing defect memory library and the second processing defect memory library, and outputting a similar defect feature; The similarity analysis network performs similarity recognition based on the first similar defect feature and the third processing defect memory library, outputs a second similar defect feature, and so on, until an N-1th similar defect feature is output; The N-1 times similar defect features are used as characteristic elements for constructing a processing defect memory library.

2. The stainless steel pipe processing control method based on defect detection according to claim 1, characterized in that: After the stainless steel pipe processing control system receives the N defect probabilities and identifies abnormal processing nodes greater than a preset threshold, the method further includes: Acquire an associated processing node of the abnormal processing node based on the N processing nodes, wherein the associated processing node is a node having a processing rate association with the abnormal processing node; Determining an adjusted processing rate of the abnormal processing node according to the preset threshold; The processing rates of the associated processing nodes are synchronously adjusted according to the adjusted processing rate.

3. The stainless steel pipe processing control method based on defect detection according to claim 2, characterized in that: According to the adjusted processing rate, the processing rate of the associated processing node is synchronously adjusted, and the method includes: Obtaining a production efficiency impact index corresponding to the associated processing node; In order to minimize the production efficiency impact index and of the associated processing nodes, an objective function is established to generate a synchronization adjustment strategy, wherein the synchronization adjustment expression of each associated processing node is as follows: ； Represents an associated node At the adjusted processing rate, Show associated nodes At the adjusted processing rate, Indicates abnormal nodes Processing rate adjustment and associated nodes The processing rate influence coefficient is used to quantify the influence of abnormal nodes. When the rate changes, adjust the associated nodes accordingly The rate of change, Indicates abnormal nodes At the adjusted processing rate, Indicates abnormal nodes Processing rate before adjustment; The associated processing nodes are adjusted according to the synchronization adjustment strategy.

4. A stainless steel pipe processing control device based on defect detection, characterized in that: The device is used to implement the stainless steel pipe processing control method based on defect detection according to any one of claims 1 to 3, and comprises: A node acquisition module, the node acquisition module is used to connect to the stainless steel pipe processing control system to obtain N processing nodes; A sample library generation module, the sample library generation module is used to establish N data detection blocks according to the N processing nodes, obtain corresponding processing detection data sets under each processing rate according to the N data detection blocks, and generate a historical processing detection sample library; A defect recognition module, the defect recognition module is used to perform defect recognition on the historical processing detection sample library, and obtain N processing defect memory libraries corresponding to the N processing nodes, wherein each processing defect memory library includes processing defect features corresponding to each processing rate; A function establishment module, the function establishment module is used to establish N probability density functions according to the N processing defect memory banks; A calculation module, the calculation module is used to obtain N real-time processing rates, calculate the defect probabilities of the N real-time processing rates using the N probability density functions, and output N defect probabilities; A control module is used in the stainless steel pipe processing control system to receive the N defect probabilities and generate an early warning signal for controlling the processing rate of abnormal processing nodes.

Images