Acquisition method and acquisition system for free forging process data

Abstract

The invention relates to the technical field of free forging processes, and provides a free forging process data collection method and system, and the method comprises the steps: controlling a collection terminal to collect the data of a free forging process according to the collection levels and collection frequencies of different data of a forging production workshop; controlling data acquired by the acquisition terminal to be transmitted to a data processing system according to the transmission priority; the data processing system is controlled to carry out temperature compensation and size compensation on blank data in the data, and then all the data are processed; and performing partition storage on the processed data. According to the invention, the acquisition frequency and transmission priority of the data can be automatically adjusted according to the importance degree of the data, the load of a transmission line is greatly reduced, temperature compensation and size compensation are carried out on the blank data when the blank is shielded, and the accuracy of forging data is greatly improved, so that the process parameters can be optimized, the product quality is improved, and the production cost is reduced. And measures can be taken in time when abnormity occurs.

Description

Technical Field

[0001] The invention relates to the technical field of free forging process, and in particular to a method and system for collecting free forging process data. Background Art

[0002] The free forging process is a manufacturing process that deforms metal billets into the desired shape by hammering or pressure. During forging, the correct selection of forging ratio, reasonable heating temperature and holding time, reasonable initial forging temperature and final forging temperature, reasonable deformation amount and deformation speed directly affect the shape, dimensional accuracy of the metal billet and the performance of the final product.

[0003] Forging is a complex forming process. The forging production process data can reflect the status of forging production in real time and is an important asset of the production workshop. Adjusting process parameters according to forging data has a great impact on improving product quality and reducing costs.

[0004] At present, many forging plants still rely on manual data recording and empirical judgment to adjust process parameters in the free forging process. This method is not only inefficient, but also has problems such as inaccurate data recording, delayed response time, and inability to fully monitor key parameters, which in turn affects product quality and production efficiency. In addition, since some forging data in the free forging process, such as billet temperature and size, have a crucial impact on the quality of the finished product, and the billet is easily blocked during the production process, such as by a manipulator or a fixed column, the temperature and size collected by the acquisition terminal will have deviations. At this time, directly using the temperature and size collected by the acquisition terminal to adjust the process parameters will have a negative impact on the quality of the finished product and affect the accuracy and efficiency of the free forging process. Summary of the invention

[0005] In order to improve the accuracy and efficiency of the free forging process, the first object of the present invention is to provide a method for collecting free forging process data.

[0006] The second object of the present invention is to provide a system for collecting free forging process data.

[0007] The technical solution adopted by the present invention is as follows:

[0008] The first aspect of the embodiment of the present invention proposes a method for collecting free forging process data, including the following steps: controlling the collection terminal to collect forging data of the free forging process according to the collection level and collection frequency of different data in the forging production workshop, the forging data including: environmental data, industrial heat treatment furnace data, fast forging unit data and billet data; controlling the data collected by the collection terminal to be transmitted to the data processing system according to the transmission priority; controlling the data processing system to perform temperature compensation and size compensation on the billet data in the data, and then performing data cleaning, data fusion, data noise reduction and normalization on all data; and saving the processed data in partitions.

[0009] The above-mentioned free forging process data collection method of the present invention may also have the following additional technical features:

[0010] According to an embodiment of the present invention, the above-mentioned method for collecting free forging process data further includes: controlling the data processing system to track the ingot head direction of the billet in real time according to the billet data collected by the collection terminal.

[0011] According to one embodiment of the present invention, the data processing system is controlled to track the direction of the billet head of the billet in real time according to the billet data collected by the collection terminal, specifically comprising: using the ORB (Oriented FAST and RotatedBRIEF, an algorithm for detecting and describing image feature points) algorithm to extract the inflection points on the edge of the billet from the real-time grayscale image of the billet data, taking the inflection points as feature points, and connecting each feature point to obtain the edge of the billet; using the FLANN (Fast Library for Approximate Nearest Neighbors, an open source library for approximate nearest neighbor search) search library to match the feature points in two adjacent frames of images according to the BRIEF descriptor to obtain matched feature point pairs; calculating the coordinate change of the feature point pair when the billet enters the camera field of view, and deducing the translation direction of the billet when entering the camera field of view according to the coordinate change, and taking the translation direction as the initial direction of the billet; calculating the coordinate change of the feature point pair in real time, and tracking the change of the initial direction of the billet in real time according to the coordinate change and the initial direction of the billet.

[0012] According to one embodiment of the present invention, the collection terminal is controlled to collect forging data of the free forging process according to the collection level and collection frequency of different data in the forging production workshop, specifically including: dividing the collection mode into normal operation mode, rest mode and abnormal mode according to the working status of the equipment and the collection terminal; dividing the collection level of different data according to the collection mode; obtaining the collection frequency of different data according to the collection level; and controlling the collection terminal to collect the forging data of the free forging process according to the collection frequency.

[0013] According to one embodiment of the present invention, the data collected by the collection terminal is controlled to be transmitted to the data processing system according to the transmission priority, specifically including: establishing a communication connection between the collection terminal and the transfer station, concentrating the data collected by each collection terminal to the corresponding transfer station, the transfer station converts the data into binary format, and adds a timestamp to each data frame; encrypting the data frame using an AES (Advanced Encryption Standard, symmetric encryption algorithm) key, and generating a hash-based message verification code for each encrypted data frame based on a hash algorithm and a key pair; establishing a communication connection between the data processing system and the transfer station, using the user datagram protocol to periodically synchronize the network time protocol of all devices, and encrypting the data frame based on the message verification code and transmitting it to the data processing system, wherein the higher the transmission priority of the data frame, the more bandwidth is allocated for transmission.

[0014] According to one embodiment of the present invention, the data processing system is controlled to perform size compensation on the blank data in the data, specifically comprising: using the ORB algorithm to extract the inflection point on the edge of the blank from the real-time grayscale image of the blank data, taking the inflection point as a feature point, connecting each feature point to obtain the edge of the blank, and inferring the blocked area according to the edge of the blank; when the blank is in a deformed state, extracting the unblocked feature points on the edge of the blank where the edge of the blocked area is located, using the least squares method to fit the curve equation of the edge of the blocked area, and reconstructing the fitted curve back to In the grayscale image of the blank; when the blank is in a non-deformed state, the historical grayscale image data of the blank is traversed to determine whether there are feature points in the obscured area. If there are feature points, the feature points of the obscured area are inferred according to the feature points of the unobstructed area in the historical grayscale image data, and the feature points of the obscured area are connected with the two feature points closest to the obscured area, the edge of the obscured area is fitted, and reconstructed back to the grayscale image of the blank; if there are no feature points, the two feature points closest to the obscured area are connected, the edge of the obscured area is fitted, and reconstructed back to the grayscale image of the blank.

[0015] According to one embodiment of the present invention, the data processing system is controlled to perform temperature compensation on the blank data in the data, specifically comprising: using the ORB algorithm to extract the inflection point on the edge of the blank from the real-time grayscale image of the blank of the blank data, taking the inflection point as the feature point, connecting each feature point to obtain the edge of the blank, and inferring the obscured area according to the edge of the blank; when the blank is in a deformed state, the temperature T of the obscured area is inferred according to the interpolation model and the heat conduction model; when the blank is not in a deformed state, the historical temperature data T0 of the obscured area is searched, and the temperature T of the obscured area is calculated in combination with the cooling rate of the temperature of other areas of the blank; according to the temperature T of the obscured area, the data processing system is controlled to perform temperature compensation on the blank data in the data.

[0016] According to one embodiment of the present invention, the interpolation model is obtained according to the following formula: Among them, T is the temperature of the blocked area, T1, T2, T3, and T4 are the temperatures of the four new feature points that appear in the image when the robot blocks the blank, α is the first interpolation weight, and β is the second interpolation weight.

[0017] According to one embodiment of the present invention, the processed data is partitioned and saved, specifically including: using TaosDB database to store data, designing different storage structures for the processed data according to importance, losslessly storing important data and less important data and performing redundant backup, packaging and compressing ordinary data, storing it, and deleting it periodically.

[0018] An embodiment of the second aspect of the present invention proposes a free forging process data collection system, including: an acquisition module, which is used to control the acquisition terminal to collect forging data of the free forging process according to the collection level and collection frequency of different data in the forging production workshop, and the forging data includes: environmental data, industrial heat treatment furnace data and billet data; a transmission module, which is used to control the data collected by the acquisition terminal to be transmitted to a data processing system according to the transmission priority; a processing module, which is used to control the data processing system to perform temperature compensation and size compensation on the billet data in the data, and then perform data cleaning, data fusion, data noise reduction and normalization on all data; a saving module, which is used to partition and save the processed data.

[0019] Beneficial effects of the present invention:

[0020] The present invention can collect, transmit and store forging data in real time, realize real-time monitoring and feedback of multiple key data, and automatically adjust the data collection frequency and transmission priority according to the importance of the data, which greatly reduces the load of the transmission line and improves the data transmission efficiency and accuracy. It also performs temperature compensation and size compensation on the billet data when the billet is blocked, which greatly improves the accuracy of the forging data. The present invention can also track the direction of the ingot head in real time, thereby not only optimizing the process parameters and improving the product quality, but also taking timely measures when abnormalities occur to ensure the stability and safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a method for collecting free forging process data according to one embodiment of the present invention;

[0022] Figure 2 is a flow chart of size compensation according to one embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of an obstructed area when a blank is deformed according to a specific example of the present invention;

[0024] Figure 4 is a temperature compensation flow chart according to one embodiment of the present invention;

[0025] Figure 5 4 is a block diagram of a system for collecting free forging process data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Figure 1 FIG. 1 is a flow chart of a method for collecting free forging process data according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0028] S1, according to the different data collection levels and collection frequencies of the forging production workshop, the collection terminal is controlled to collect the forging data of the free forging process. The forging data includes: environmental data, industrial heat treatment furnace data and billet data, etc.

[0029] Furthermore, according to the collection level and collection frequency of different data in the forging production workshop, the collection terminal is controlled to collect the forging data of the free forging process, specifically including: dividing the collection mode into normal operation mode, rest mode and abnormal mode according to the working status of the equipment and the collection terminal; dividing the collection level of different data according to the collection mode; obtaining the collection frequency of different data according to the collection level; controlling the collection terminal to collect the forging data of the free forging process according to the collection frequency.

[0030] Specifically, forging data includes: environmental data, industrial heat treatment furnace data, fast forging unit data and billet data, among which environmental data can include temperature data, humidity data and wind speed data that are not affected by any on-site factors and can intuitively reflect the on-site environment of the production workshop; industrial heat treatment furnace data includes the temperature of all temperature zones of the industrial heat treatment furnace, the movement state of the furnace door, and the billet information in the furnace; fast forging unit data includes the pressure and movement data of the fast forging unit; billet data includes the highest temperature, lowest temperature, average temperature and image of the billet. After collecting different data of the forging production workshop, the data are concentrated at the physical space level, and data synchronization is achieved to ensure the consistency of the time of all collected data.

[0031] According to the working status of the equipment and the acquisition terminal, the data acquisition mode of the forging production workshop is divided into normal operation mode, rest mode and abnormal mode. The normal operation mode is a data acquisition mode for the equipment behavior during normal operation of forging production. The rest mode is a data acquisition mode for the equipment behavior during routine inspections when the forging production is not yet executed. The abnormal mode is a data acquisition mode for equipment or acquisition terminals that have failed. According to the acquisition mode, the data acquisition level is divided into three levels from high to low: A1, A2, and A3. Three acquisition frequencies η1, η2, and η3 are assigned to the three levels of data from high to low. Generally speaking, in the rest mode, that is, when the equipment is resting, the data acquisition level involved in the resting equipment is uniformly specified as A3. In the normal operation mode, the data acquisition level is uniformly specified as A2. When the equipment or acquisition terminal fails, the data level of the faulty equipment or acquisition terminal is temporarily upgraded to A1.

[0032] For example, when the high-temperature pressure sensor in the heat treatment furnace does not detect a pressure signal, the data of the heat treatment furnace is set to level A3. Once a pressure signal is detected, all data of the heat treatment furnace are upgraded to level A2. When the pressure signal is detected and the furnace door is detected to be open, the furnace temperature data is upgraded to level A1. When the furnace temperature data level is upgraded to level A1, the fast forging unit and the billet data acquisition terminal enter the preparatory working state, and the data level is upgraded from level A3 to level A2. When temperature information appears in the thermal imager and a grayscale image of the forging appears in the camera, the temperature data and image data of the billet are upgraded to level A1. When the clamping force signal of the manipulator is detected, all data of the fast forging unit are upgraded to level A1 until the temperature information is lost in the thermal imager and the grayscale image of the forging is lost in the camera, at which time the level of the fast forging unit data and the billet data is reduced to level A3.

[0033] S2, controlling the data collected by the collection terminal to be transmitted to the data processing system according to the transmission priority.

[0034] According to one embodiment of the present invention, the data collected by the collection terminal is transmitted to the data processing system according to the transmission priority control, which specifically includes: establishing a communication connection between the collection terminal and the transfer station, concentrating the data collected by each collection terminal to the corresponding transfer station, the transfer station converts the data into binary format, and adds a timestamp to each data frame; encrypting the data frame with an AES key, and generating a hash-based message verification code for each encrypted data frame based on a hash algorithm and a key pair; establishing a communication connection between the data processing system and the transfer station, using the user datagram protocol to periodically synchronize the network time protocol of all devices, and encrypting the data frame based on the message verification code and transmitting it to the data processing system, wherein the higher the transmission priority of the data frame, the more bandwidth is allocated for the transmission.

[0035] Specifically, a transfer station is set up for each data collection terminal, a communication connection is established between the collection terminal and the transfer station, and the data in each collection terminal is concentrated to the corresponding transfer station. The transfer station converts the serial data of the device into a standard binary format, adds a timestamp to each data frame, and encrypts the data frame using the AES key. Based on the hash algorithm and the key, a hash-based message authentication code HMAC is generated for each encrypted data frame and sent to the data processing system. The data processing system uses the same AES key to decrypt the data, extracts the data content part and the HMAC part from the entire decrypted data frame, and uses the same hash algorithm and key to calculate the data content to obtain an HMAC, and compares this HMAC with the received HMAC to see if they are consistent. If they are consistent, the data processing system receives the transmitted data, thereby improving the security of data transmission. The processing system also uses the user datagram protocol to periodically synchronize the network time protocol of all devices to ensure the consistency of all data time. During the data transmission between the data processing system and the transfer station, the higher the transmission priority of the data frame, the more bandwidth is allocated for transmission. The transmission priority of different data frames is set in advance according to the importance of the data, process status and abnormal conditions. For example, fault data is set as the highest priority and is transmitted first. In this way, it can ensure that important data is transmitted first.

[0036] In addition, a real-time monitoring and self-diagnosis system can be embedded to track data transmission status in real time, including acquisition frequency, transmission rate, packet loss rate, delay, etc. When data transmission abnormality is detected, the acquisition frequency and transmission priority of the faulty line data are upgraded to determine the source of the fault. The acquisition terminal alarm displays the fault information, and the system follows up on the progress of fault repair in real time. When the fault is resolved, the faulty line returns to normal acquisition status.

[0037] As a result, timely measures can be taken when abnormalities occur, thus ensuring the stability and safety of the production process.

[0038] S3, after controlling the data processing system to perform temperature compensation and size compensation on the blank data in the data, all the data are cleaned, fused, denoised and normalized.

[0039] The following describes how to perform temperature compensation and size compensation on the blank data in the data in conjunction with specific embodiments.

[0040] According to one embodiment of the present invention, Figure 2 As shown, the control data processing system performs size compensation on the blank data in the data, specifically including:

[0041] S301, using the ORB algorithm, extracting the inflection points on the edge of the blank from the real-time grayscale image of the blank data, taking the inflection points as feature points, connecting each feature point to obtain the edge of the blank, and inferring the blocked area based on the edge of the blank.

[0042] Specifically, Figure 3 As shown in the figure, the ORB (Oriented FAST and Rotated BRIEF) algorithm is used to extract the inflection points on the edge of the blank from the real-time grayscale image of each frame of the blank obtained by the camera. These inflection points are regarded as feature points on the edge, and each feature point is connected to obtain the edge of the blank. The blocked area can be inferred based on the edge of the blank ( Figure 3 For each feature point, the grayscale gradient G of the surrounding pixels in the horizontal and vertical directions is calculated. x and G y , through the formula The main direction of each feature point is obtained, which is used to ensure that the descriptors of these feature points can be correctly matched when the blank is rotated. The BRIEF descriptor is used to describe the local area around each feature point. Finally, the ORB algorithm outputs the coordinates, direction and descriptor of each feature point.

[0043] S302, when the blank is in a deformed state, extract unobstructed feature points on the edge of the blank where the edge of the obstructed area is located, use the least squares method to fit the curve equation of the edge of the obstructed area, and reconstruct the fitted curve back into the blank grayscale image.

[0044] Specifically, it is possible to determine whether the blank is in a deformed state based on the pressure data of the forging press unit. If there is pressure, the blank is in a deformed state. Figure 3 As shown in the figure, when the blank 1 is deformed between the upper anvil 3 and the lower anvil 4, part of the right edge will be blocked by the robot 2, and the image information of the forging here will be lost in the image. Since the deformation of the blocked part is relatively smooth and basically conforms to the quadratic curve equation, the four feature points p1, p2, P3, and P4 on the blocked edge are extracted and the formula is used to calculate the right edge. The values ​​of the first fitting coefficient, the second fitting coefficient and the third fitting coefficient a, b, c are obtained by fitting, so as to obtain the curve equation of the edge of the blocked area, and the fitted curve can be reconstructed back into the grayscale image of the blank.

[0045] S303, when the blank is in a non-deformed state, traverse the historical grayscale image data of the blank to determine whether there are feature points in the blocked area.

[0046] S304, if there are feature points, the feature points of the obscured area are inferred based on the feature points of the unobstructed area in the historical grayscale image data, the feature points of the obscured area are connected with the two feature points closest to the obscured area, the edge of the obscured area is fitted, and reconstructed back into the grayscale image of the blank.

[0047] S305: If there is no feature point, two feature points closest to the occluded area are connected to fit the edge of the occluded area and reconstruct it back into the grayscale image of the blank.

[0048] Therefore, the size compensation of the blocked area of ​​the blank data can greatly improve the subsequent three-dimensional reconstruction effect of the blank.

[0049] In one embodiment of the present invention, Figure 4 As shown, the control data processing system performs temperature compensation on the blank data in the data, specifically including:

[0050] S306, using the ORB algorithm, extracting the inflection points on the edge of the blank from the real-time grayscale image of the blank data, taking the inflection points as feature points, connecting each feature point to obtain the edge of the blank, and calculating the blocked area based on the edge of the blank.

[0051] S307, when the blank is in a deformed state, the temperature T of the shielded area is calculated according to the interpolation model and the heat conduction model.

[0052] The historical temperature data may be temperature data of the first 75-100 frames of the current blank grayscale image.

[0053] Furthermore, in one embodiment of the present invention, the heat conduction model can be obtained according to the following formula: Where T is the temperature of the shaded area, t is the time, ε is the thermal diffusion coefficient, is the spatial variation of temperature.

[0054] The interpolation model can be obtained according to the following formula:

[0055] Among them, T is the temperature of the blocked area, T1, T2, T3, and T4 are the temperatures of the four new feature points that appear in the image when the robot blocks the blank, α is the first interpolation weight, and β is the second interpolation weight.

[0056] The temperature T of the shaded area can be inferred by combining the interpolation model and the heat conduction model.

[0057] S308, when the blank is not in a deformed state, find the historical temperature data T0 of the shielded area, and calculate the temperature T of the shielded area in combination with the cooling rate of the temperature of other areas of the blank.

[0058] Specifically, if the blank is blocked, when the blank is in a deformed state, but the robot has no clamping signal, the temperature T of the blocked area is calculated by finding the historical temperature data T0 of the blocked area and combining the cooling rate of the temperature of other areas; when the robot detects that there is a clamping signal, the temperature of the blocked area is derived according to the interpolation model; when the blank is blocked in a non-deformed state, the temperature of the blocked area is calculated by finding the historical temperature data T0 of the blocked area and combining the cooling rate of the temperature of other areas. Finally, according to the temperature T of the blocked area, the data processing system is controlled to perform temperature compensation on the blank data in the data.

[0059] Therefore, by performing size compensation and temperature compensation on the billet data, the accuracy of the forging data is greatly improved.

[0060] After the size compensation and temperature compensation of the blank data, all the data are cleaned to remove the erroneous values, missing values, and duplicate data in the data to ensure the validity and accuracy of the data. Then, the cleaned data is fused by matching the timestamp and IP address of the data to integrate the relevant data from different data sources to improve the integrity and consistency of the data. At the same time, high-frequency noise is removed through noise reduction processing to retain valid signals to ensure the quality of the data. The data is normalized to unify data of different dimensions into the same range for subsequent analysis. At the same time, the data is discretized and converted into a format suitable for storage and processing to ensure the standardization and simplicity of the data, unify the units of the data, and unify the data output by different data acquisition modules into standard units to ensure data consistency.

[0061] S4, partition and save the processed data.

[0062] In one embodiment of the present invention, the processed data is partitioned and saved, specifically including: using TaosDB database to store data, designing different storage structures for the processed data according to importance, losslessly storing important data and less important data and performing redundant backup, packaging and compressing ordinary data, storing it, and deleting it periodically.

[0063] Specifically, TaosDB database is used to store data, and different storage structures are designed for the processed data according to their importance. Important data and less important data are losslessly stored and redundantly backed up. Ordinary data is packaged and compressed before storage and periodically deleted to save storage space.

[0064] Since the ingot head direction of the billet has an important influence on the subsequent microstructure analysis, distinguishing the ingot head and ingot tail of the billet is very helpful for optimizing the process parameters. Therefore, it is also very necessary to mark the ingot head direction of the billet in the real-time grayscale image of the billet.

[0065] According to an embodiment of the present invention, the above-mentioned method for collecting free forging process data may further include: controlling the data processing system to track the ingot head direction of the billet in real time according to the billet data collected by the collection terminal.

[0066] Furthermore, in one embodiment of the present invention, the data processing system is controlled to track the direction of the billet head of the billet in real time according to the billet data collected by the collection terminal, specifically including: using the ORB algorithm to extract the inflection point on the edge of the billet from the real-time grayscale image of the billet data, taking the inflection point as the feature point, and connecting each feature point to obtain the edge of the billet; using the FLANN search library to match the feature points in two adjacent frames of the image according to the BRIEF descriptor to obtain a matched feature point pair; calculating the coordinate change of the feature point pair when the billet enters the camera's field of view, and deducing the translation direction of the billet when entering the camera's field of view according to the coordinate change, and taking the translation direction as the initial direction of the billet; calculating the coordinate change of the feature point pair in real time, and tracking the change of the initial direction of the billet in real time according to the coordinate change and the initial direction of the billet.

[0067] Specifically, the FLANN search library is used to match the feature point pairs in two adjacent frames according to the BRIEF descriptor. After the matched feature point pairs are obtained, the coordinate changes of the feature points between the two adjacent frames are calculated. The formula Δx = x n+1 -x n and Δy=y n+1 -y n Calculate the horizontal displacement Δx and vertical displacement Δy of the feature point, x n is the x-axis coordinate of the feature point in the nth frame image, x n+1 is the x-axis coordinate of the feature point in the (n+1)th frame image, and y n is the y-axis coordinate of the feature point in the nth frame image, y n+1 is the y-axis coordinate of the feature point in the (n+1)th frame image; through the formula Δθ=θ n+1 -θ n Calculate the rotational motion direction difference Δθ,θ of the feature point along the z-axis n is the rotation angle of the feature point along the z-axis in the nth frame image, θ n+1 is the rotation angle of the feature point along the z-axis in the (n+1)th frame image; Calculate the displacement Δry of the feature point along the y-axis when the blank rotates along the x-axis, where θr is the rotation angle θ of the robot r , Δy r is the length of the side of the blank perpendicular to the x-axis.

[0068] When the blank enters the camera's field of view for the first time, the feature points are in a state of translational motion for a period of time. Therefore, the translational motion between the feature point pairs can be inferred by calculating the coordinate changes of the feature point pairs, generally by calculating the horizontal displacement Δx of the feature points. An initial vector is specified. This initial vector The direction is the translation direction of the billet, that is, the direction of the billet ingot head. The initial vector The direction will change in real time with the overall rotation of the blank. The coordinate changes of the feature point pairs can be calculated in real time, and the initial direction of the ingot head can be tracked in real time based on the coordinate changes and the initial direction of the ingot head. changes.

[0069] In an embodiment of the present invention, the acquisition terminal provides a RESTful API (Representational State Transfer Application Programming Interface) data interface to ensure that the data can be read in real time by the digital twin system, numerical simulation system, machine learning system, etc. on the terminal.

[0070] In summary, the free forging process data collection method according to the embodiment of the present invention can collect, transmit and store forging data in real time, realize real-time monitoring and feedback of multiple key data, and automatically adjust the data collection frequency and transmission priority according to the importance of the data, which greatly reduces the load of the transmission line and improves the data transmission efficiency and accuracy. It also performs temperature compensation and size compensation on the billet data when the billet is blocked, which greatly improves the accuracy of the forging data. The present invention can also track the direction of the ingot head in real time. Therefore, it can not only optimize the process parameters and improve the product quality, but also take timely measures when abnormalities occur to ensure the stability and safety of the production process.

[0071] Corresponding to the above-mentioned free forging process data collection method, the present invention also proposes a free forging process data collection system. Since the system embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the system embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0072] Figure 5 is a block diagram of a system for collecting free forging process data according to an embodiment of the present invention. Figure 5As shown, the system includes: a collection module 100, a transmission module 200, a processing module 300 and a storage module 400.

[0073] Among them, the acquisition module 100 is used to control the acquisition terminal to collect forging data of the free forging process according to the acquisition level and acquisition frequency of different data in the forging production workshop. The forging data includes: environmental data, industrial heat treatment furnace data and billet data; the transmission module 200 is used to control the data collected by the acquisition terminal to be transmitted to the data processing system according to the transmission priority; the processing module 300 is used to control the data processing system to perform temperature compensation and size compensation on the billet data in the data, and then perform data cleaning, data fusion, data noise reduction and normalization on all data; the storage module 400 is used to partition and save the processed data.

[0074] In one embodiment of the present invention, the processing module 300 is specifically used to: use the ORB algorithm to extract the inflection point on the edge of the blank from the real-time grayscale image of the blank data, use the inflection point as the feature point, connect each feature point to obtain the edge of the blank, and infer the blocked area according to the edge of the blank; when the blank is in a deformed state, extract the unblocked feature points on the edge of the blank where the edge of the blocked area is located, use the least squares method to fit the curve equation of the edge of the blocked area, and reconstruct the fitted curve back into the grayscale image of the blank; When it is in a non-deformed state, the historical grayscale image data of the blank is traversed to determine whether there are feature points in the occluded area. If there are feature points, the feature points of the occluded area are inferred based on the feature points of the unoccluded area in the historical grayscale image data, and the feature points of the occluded area are connected with the two feature points closest to the occluded area, the edge of the occluded area is fitted, and reconstructed back to the grayscale image of the blank; if there are no feature points, the two feature points closest to the occluded area are connected, the edge of the occluded area is fitted, and reconstructed back to the grayscale image of the blank.

[0075] In one embodiment of the present invention, the processing module 300 is specifically used to: use the ORB algorithm to extract the inflection point on the edge of the billet from the real-time grayscale image of the billet data, use the inflection point as the feature point, connect each feature point to obtain the edge of the billet, and infer the obscured area based on the edge of the billet; when the billet is in a deformed state, infer the temperature T of the obscured area based on the interpolation model and the heat conduction model; when the billet is not in a deformed state, find the historical temperature data T0 of the obscured area, and calculate the temperature T of the obscured area in combination with the cooling rate of the temperature of other areas of the billet; and control the data processing system to perform temperature compensation on the billet data in the data based on the temperature T of the obscured area.

[0076] According to the free forging process data collection system of the embodiment of the present invention, it is possible to collect, transmit and store forging data in real time, realize real-time monitoring and feedback of multiple key data, and automatically adjust the data collection frequency and transmission priority according to the importance of the data, thereby greatly reducing the load of the transmission line, improving the data transmission efficiency and accuracy, and performing temperature compensation and size compensation on the billet data when the billet is obscured, thereby greatly improving the accuracy of the forging data. Therefore, it is possible not only to optimize process parameters and improve product quality, but also to take timely measures when abnormalities occur to ensure the stability and safety of the production process.

[0077] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0078] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, the technical personnel in this field can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and associate different embodiments or examples and features of different embodiments or examples described in this specification without mutual contradiction.

[0079] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0080] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0081] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0082] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0084] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

[0085] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for collecting free forging process data, characterized in that: The following steps are involved: According to the collection level and collection frequency of different data in the forging production workshop, the collection terminal is controlled to collect data of the free forging process, and the forging data includes: environmental data, industrial heat treatment furnace data, fast forging unit data and billet data; Controlling the data collected by the collection terminal to be transmitted to the data processing system according to the transmission priority; After controlling the data processing system to perform temperature compensation and size compensation on the blank data in the data, all the data are cleaned, fused, denoised and normalized; The processed data is saved in partitions.

2. The method for collecting free forging process data according to claim 1, characterized in that: Also includes: The data processing system is controlled to track the ingot head direction of the billet in real time according to the billet data collected by the collection terminal.

3. The method for collecting free forging process data according to claim 2, characterized in that: Controlling the data processing system to track the ingot head direction of the billet in real time according to the billet data collected by the collection terminal, specifically includes: The ORB algorithm is used to extract the inflection points on the edge of the blank from the real-time grayscale image of the blank data, and the inflection points are used as feature points. Each feature point is connected to obtain the edge of the blank; Use the FLANN search library to match the feature points in two adjacent frames according to the BRIEF descriptor to obtain the matched feature point pairs; Calculate the coordinate change of the feature point pair when the blank enters the camera field of view, and infer the translation direction of the blank when it enters the camera field of view according to the coordinate change, and use the translation direction as the initial direction of the ingot head; The coordinate changes of the feature point pairs are calculated in real time, and the changes of the initial direction of the spindle head are tracked in real time based on the coordinate changes and the initial direction of the spindle head.

4. The method for collecting free forging process data according to claim 1, characterized in that: According to the different data collection levels and collection frequencies of the forging production workshop, the collection terminal is controlled to collect data of the free forging process, including: The acquisition mode is divided into normal operation mode, rest mode and abnormal mode according to the working status of the equipment and the acquisition terminal; Dividing the collection levels of different data according to the collection mode; Acquiring the collection frequency of different data according to the collection level; The acquisition terminal is controlled according to the acquisition frequency to acquire forging data of the free forging process.

5. The method for collecting free forging process data according to claim 1, characterized in that: Controlling the data collected by the collection terminal to be transmitted to the data processing system according to the transmission priority specifically includes: Establishing a communication connection between the collection terminal and the transfer station, centralizing the data collected by each collection terminal to the corresponding transfer station, the transfer station converts the data into binary format and adds a time stamp to each data frame; The data frame is encrypted using the AES key, and a hash-based message authentication code is generated for each encrypted data frame based on the hash algorithm and the key; A communication connection is established between the data processing system and the transfer station, and the network time protocol of all devices is periodically synchronized using the user datagram protocol. The data frame is encrypted and transmitted to the data processing system based on the message verification code, wherein the higher the transmission priority of the data frame, the more bandwidth is allocated for transmission.

6. The method for collecting free forging process data according to claim 1, characterized in that: Controlling the data processing system to perform size compensation on the blank data in the data specifically includes: The ORB algorithm is used to extract the inflection points on the edge of the blank from the real-time grayscale image of the blank data, and the inflection points are used as feature points. Each feature point is connected to obtain the edge of the blank, and the blocked area is deduced according to the edge of the blank. When the blank is in a deformed state, unobstructed feature points on the edge of the blank where the edge of the obstructed area is located are extracted, and the curve equation of the edge of the obstructed area is obtained by fitting using the least squares method, and the fitted curve is reconstructed back into the blank grayscale image; When the blank is in a non-deformed state, the historical grayscale image data of the blank is traversed to determine whether there are feature points in the obscured area. If there are feature points, the feature points of the obscured area are inferred based on the feature points of the unobstructed area in the historical grayscale image data, and the feature points of the obscured area are connected with the two feature points closest to the obscured area, the edge of the obscured area is fitted, and reconstructed back to the grayscale image of the blank; if there are no feature points, the two feature points closest to the obscured area are connected, the edge of the obscured area is fitted, and reconstructed back to the grayscale image of the blank.

7. The method for collecting free forging process data according to claim 1, characterized in that: Controlling the data processing system to perform temperature compensation on the blank data in the data specifically includes: The ORB algorithm is used to extract the inflection points on the edge of the blank from the real-time grayscale image of the blank data, and the inflection points are used as feature points. Each feature point is connected to obtain the edge of the blank, and the blocked area is deduced according to the edge of the blank. When the blank is in a deformed state, the temperature T of the blocked area is calculated based on the interpolation model and the heat conduction model; When the blank is not in a deformed state, the historical temperature data T0 of the blocked area is found, and the temperature T of the blocked area is calculated in combination with the cooling rate of the temperature of other areas of the blank; The data processing system is controlled according to the temperature T of the shielded area to perform temperature compensation on the blank data in the data.

8. The method for collecting free forging process data according to claim 7, characterized in that: The interpolation model is obtained according to the following formula: Among them, T is the temperature of the blocked area, T1, T2, T3, and T4 are the temperatures of the four new feature points that appear in the image when the robot blocks the blank, α is the first interpolation weight, and β is the second interpolation weight.

9. The method for collecting free forging process data according to claim 1, characterized in that: The processed data is partitioned and saved, including: TaosDB database is used to store data. Different storage structures are designed for processed data according to their importance. Important and less important data are stored losslessly and backed up redundantly. Ordinary data is packaged and compressed before storage and periodically deleted.

10. A free forging process data collection system, characterized in that: include: A collection module, which is used to control the collection terminal to collect forging data of the free forging process according to the collection level and collection frequency of different data in the forging production workshop, and the forging data includes: environmental data, industrial heat treatment furnace data and billet data; A transmission module, the transmission module is used to control the data collected by the collection terminal to be transmitted to the data processing system according to the transmission priority; A processing module, the processing module is used to control the data processing system to perform temperature compensation and size compensation on the blank data in the data, and then perform data cleaning, data fusion, data noise reduction and normalization on all the data; A storage module is used to store the processed data in partitions.

Images