Industrial big data platform based on block chain

Abstract

The invention discloses an industrial big data platform based on a block chain, which comprises a data collection module, an intelligent detection module and an intelligent control module, and is characterized in that the data collection module is used for collecting visual images of forged parts, operation state data of equipment and comprehensive information of materials for forging; the intelligent detection module is used for detecting running state data of equipment and analyzing defects of a forging part, and the intelligent control module is used for analyzing comprehensive information data of raw materials for forging, analyzing whether a current mold can machine the raw materials or not, and adjusting the heating temperature and time of the equipment and the forging mold according to analysis results. The data collection module, the intelligent detection module and the intelligent control module are electrically connected with one another, and the data collection module comprises a material comprehensive information input module, a visual module and a sensor module.

Description

Technical Field

[0001] The present invention relates to the field of mechanical processing technology, and in particular to an industrial big data platform based on blockchain. Background Art

[0002] At present, in the automated forging production of hot die forging presses, in order to ensure the quality of forged products, the products forged by hot die forging presses are generally inspected. Most of them are manually scanned after the forgings are cooled and the data is entered into the system for further inspection. However, due to certain differences in raw materials, the existing technology cannot determine whether the mold is suitable according to the material of the raw materials, nor can it adjust the heating time and temperature according to the material of the raw materials. Manual adjustment is still required, which seriously affects the efficiency of the equipment. Moreover, since some defects of forgings show similarities under certain conditions, some defects within the allowable range may be identified as quality defects, resulting in the existing technology being unable to accurately identify the defects of forgings and prone to misjudgment. Therefore, it is very necessary to design an industrial big data platform based on blockchain to improve equipment operation efficiency and the accuracy of defect judgment. Summary of the invention

[0003] The purpose of the present invention is to provide an industrial big data platform based on blockchain to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: an industrial big data platform based on blockchain, comprising a data collection module, an intelligent detection module and an intelligent control module, characterized in that: the data collection module is used to collect visual images of forgings, operating status data of equipment and comprehensive information of materials used for forging, the intelligent detection module is used to detect the operating status data of the equipment and analyze the defects of forgings, the intelligent control module is used to analyze the comprehensive information data of raw materials used for forging, analyze whether the current mold can process the raw materials, and adjust the heating temperature, time and forging mold of the equipment according to the analysis results, and the data collection module, the intelligent detection module and the intelligent control module are electrically connected to each other;

[0005] The equipment detection module includes a temperature detection submodule, a load detection submodule and a mold detection submodule. The temperature detection submodule is used to detect the temperature of the equipment in operation, the load detection submodule is used to detect the forging pressure of the equipment, and the mold detection submodule is used to detect whether the mold is suitable for the current material.

[0006] The forging detection module includes a feature extraction submodule, a feature comparison submodule and a defect detection submodule. The feature extraction submodule is used to extract the surface features of the forgings. The feature comparison submodule is used to adopt different detection methods for different forging features. The defect detection submodule is used to distinguish the defects of the forgings using different detection methods when the forging features are the same.

[0007] According to the above technical solution, the data collection module includes a material comprehensive information input module, a visual module and a sensor module. The material comprehensive information input module is used to enter the comprehensive information of the material into the system, the visual module is used to capture the visual image of the forging, and the sensor module is used to collect the operating status data of the hot die forging press in real time.

[0008] According to the above technical solution, the intelligent detection module includes an equipment detection module, and the equipment detection module is used to detect the temperature and pressure load of the equipment in the operating state.

[0009] According to the above technical solution, the intelligent detection module also includes a forging detection module, and the forging detection module is used to extract the characteristics of the forging and analyze the defects of the forging using different methods according to the characteristics.

[0010] According to the above technical solution, the intelligent control module includes a material detection module and an equipment adjustment module. The material detection module is used to detect the material of the material and adjust the heating temperature of the equipment according to the material of the material. The equipment adjustment module is used to adjust the working mode of the equipment according to the detection results of the equipment.

[0011] According to the above technical solution, the operation method of the industrial big data platform mainly includes the following steps:

[0012] Step S1: The comprehensive information of the raw materials to be processed is input into the system through the material comprehensive information input module, the visual image of the forged parts processed by the equipment and the visual image of the equipment surroundings are collected through the visual module, and the infrared thermal data and pressure load data of the equipment under the operation state are collected in real time through the sensor module;

[0013] Step S2: When the equipment is processing forgings, the system starts the equipment detection module, starts to analyze the temperature and pressure load of the equipment in the running state and whether the mold is suitable, and adjusts the equipment according to the analysis results;

[0014] Step S3: when detecting the quality of the forged part, start the forged part detection module, start to analyze the characteristics of the forged part, adopt the corresponding detection strategy to detect according to the characteristics of the forged part, and judge whether the forged part has quality defects according to the detection results;

[0015] Step S4: When forging a new forging, the system detects the material quality and adjusts the mold of the equipment according to the result of the mold detection.

[0016] According to the above technical solution, step S2 further includes the following steps:

[0017] Step S21: Obtain infrared thermal data of the material, set the infrared thermal data collection cycle of the equipment, periodically obtain infrared data of the equipment in operation, identify the temperature of the equipment bearing, calculate the difference C between the equipment temperature in the current cycle and the equipment temperature collected in the most recent cycle, when the difference |C| is less than the threshold value set by the system, the system continues to detect the equipment temperature, when the difference |C| is greater than the threshold value set by the system, the abnormal temperature part of the equipment is marked, the working time of the equipment and the load rate under the working state are retrieved, if the load rate of the equipment is greater than the threshold value and the working time of the equipment is also greater than the threshold value, the current equipment is marked as an overloaded equipment, and the material input is reduced, otherwise the equipment is marked as a fault;

[0018] Step S22: retrieve comprehensive information data of the material to be processed, identify the code of the material to be processed, search the database according to the code of the material to be processed, obtain the hardness K of the material to be processed, search the processing history database according to the code of the material to be processed, and give the influence coefficient α of the hardness of the material to be processed on the tensile length of the material;

[0019] Step S23: Get the model of the mold, anchor the mold depression, measure the depth H of the most concave part of the mold, set the measurement interval, measure the width of the most concave part of the mold according to the set interval, calculate the width difference of the most concave part of the mold under adjacent intervals, if the width difference is less than the threshold set by the system, it means that the slope of the mold depression is steep, measure the inflection angle of the most concave part of the mold, call the corresponding stretching length influence coefficient η in the database according to the inflection angle, and calculate the length that the current material can be forged and stretched in the mold through the formula Where, L 1 Indicates the length of the material before processing, L 2 Indicates the length of the material after forging, λ indicates the influence coefficient of the pressure applied by the press on the forging length of the material, μ indicates the influence coefficient of the material's resilience on the stretching length, otherwise the current mold is marked as an available mold. If the length of the material after forging L 2 If the difference between the depth H of the most concave part of the mold and the depth H of the most concave part of the mold is less than the threshold, the current mold is marked as a usable mold, otherwise the current mold is marked as an unusable mold.

[0020] According to the above technical solution, step S3 further includes the following steps:

[0021] Step S31: retrieve the visual image of the forged part after processing, scan the features of the forged part, classify the forged part according to the features of the forged part, scan the contour feature nodes of the forged part, connect the contour feature nodes of the forged part to build the contour feature model of the forged part, set the detection accuracy to 0.1mm, overlap and compare the constructed contour model of the forged part with the forged part model in the database, mark the part that cannot be overlapped, identify the area of ​​the marked part, if the area of ​​the marked part is greater than the threshold set by the system, then mark the forged part as a marginal defective product, otherwise mark the forged part as a qualified product, by classifying the forged part according to the features extracted from the forged part, and adopting the corresponding detection strategy for the classified forged part, the corresponding detection strategy can be used more accurately, and the efficiency and accuracy of the detection can be further improved;

[0022] Step S32: grayscale the visual image of the forging, scan and identify the color values ​​of the pixels on the surface of the forging in the visual image, calculate the difference in color values ​​between adjacent pixels, and if the difference in color value between adjacent pixels is less than a threshold, mark the pixel; otherwise, the system continues to detect, identify the marks in the pixels, connect the pixels with the same marks and adjacent to each other, identify the graphic features formed by the connection of the pixels, and compare the image features. If the similarity between the image features is greater than the threshold set by the system, mark the current forging as a coarse-grained ring defective product; otherwise, the system continues to detect the remaining forgings and identify the marks in the forgings. If both edge defect marks and coarse-grained ring defect marks appear in the forging, the forging is marked as a coarse-grained ring defective product; otherwise, the defects of the forging are described according to the initial marks in the forging.

[0023] According to the above technical solution, the step S31 further includes the following steps:

[0024] Step S311: When the defect feature of the forging is a surface feature, the color value E of the pixel point on the surface of the forging part after grayscale processing is identified, and the color value difference Q between the pixel point and its upper, lower, left and right adjacent pixels is calculated in turn, and the color value of the pixel point is added to the color value difference, that is, the color value of the pixel point is G=E+Q, where G represents a new color value, and four new pictures are constructed using the new color value G respectively, and the four new pictures are overlapped and fused, and the feature nodes of the new pictures are scanned and identified, and the identified feature nodes are connected to construct a feature model, and the pixel point position of the feature model is anchored in the new picture, and the database image is searched according to the anchored pixel point position. If there is no corresponding feature point in the database image, the current forging part is marked as a scratch defective product, otherwise the system continues to detect;

[0025] Step S312: When a scratch defect mark is identified in the forged part, the color value of the pixel point of the visual image of the forged part is identified, the brightness of the visual image of the forged part is adjusted, the color value of the pixel point after the processing is scanned and identified, the difference between the color value of the pixel point before and after the processing is calculated, and the discrete coefficient of the difference of the color value of the pixel point is calculated by the formula Where i = 1, 2, 3...n, P represents the discrete coefficient of the pixel color value difference, M represents the difference between the pixel color values ​​before and after processing, It represents the average value of the difference between the color values ​​of the pixels before and after processing. If the discrete coefficient of the color value difference of the pixel is greater than the system threshold, it means that the surface of the current forging is oily and the current forging is marked as a qualified product. Otherwise, the current forging is marked as a scratch defective product.

[0026] According to the above technical solution, in step S4, infrared thermal data of the material is obtained, the temperature of the material is identified, and the temperature of the material is compared with a historical database. If the temperature of the material is less than a first threshold or greater than a second threshold, the material is marked as an unusable material, otherwise it is marked as an available material, and the mold detection results and material detection results are retrieved. The mold used by the equipment is adjusted according to the mold detection results, and the heating temperature and heating time of the equipment are adjusted according to the material detection results.

[0027] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by judging whether the material temperature meets the processing requirements, can avoid equipment failure caused by insufficient material temperature, thereby reducing the frequency of equipment failures and maintenance time, and greatly improving the operating efficiency of the equipment; by judging whether the current mold can process the current material, it can avoid unqualified processed materials, resulting in waste of energy, and even damage to the equipment, leading to equipment downtime, and greatly improving the operating efficiency of the equipment; by conducting secondary inspection of forgings with similar defect characteristics, it can avoid misjudgment caused by similar defect characteristics of forgings, and greatly improve the accuracy of forging defect detection; by adopting different detection methods, it can avoid system misjudgment caused by the same defect characteristics, thereby reducing the influence of the same defect characteristics on the accuracy of the detection results, and greatly improving the detection accuracy of forging defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0029] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] See also Figure 1 , the present invention provides a technical solution: an industrial big data platform based on blockchain, comprising a data collection module, an intelligent detection module and an intelligent control module, characterized in that: the data collection module is used to collect visual images of forgings, operating status data of equipment and comprehensive information of materials used for forging, the intelligent detection module is used to detect the operating status data of the equipment and analyze the defects of forgings, the intelligent control module is used to analyze the comprehensive information data of raw materials used for forging, analyze whether the current mold can process the raw materials, and adjust the heating temperature, time and forging mold of the equipment according to the analysis results, and the data collection module, the intelligent detection module and the intelligent control module are electrically connected to each other;

[0032] The equipment detection module includes a temperature detection submodule, a load detection submodule and a mold detection submodule. The temperature detection submodule is used to detect the temperature of the equipment in operation, the load detection submodule is used to detect the forging pressure of the equipment, and the mold detection submodule is used to detect whether the mold is suitable for the current material.

[0033] The forging detection module includes a feature extraction submodule, a feature comparison submodule and a defect detection submodule. The feature extraction submodule is used to extract the surface features of the forgings. The feature comparison submodule is used to adopt different detection methods for different forging features. The defect detection submodule is used to distinguish the defects of the forgings using different detection methods when the forging features are the same.

[0034] The data collection module includes a material comprehensive information input module, a vision module and a sensor module. The material comprehensive information input module is used to input the comprehensive information of the material into the system, the vision module is used to capture the visual image of the forging, and the sensor module is used to collect the operating status data of the hot die forging press in real time.

[0035] The intelligent detection module includes an equipment detection module, which is used to detect the temperature and pressure load of the equipment in the running state.

[0036] The intelligent detection module also includes a forging detection module, which is used to extract the characteristics of the forging and analyze the defects of the forging using different methods according to the characteristics.

[0037] The intelligent control module includes a material detection module and an equipment adjustment module. The material detection module is used to detect the material of the material and adjust the heating temperature of the equipment according to the material of the material. The equipment adjustment module is used to adjust the working mode of the equipment according to the detection result of the equipment.

[0038] The operation method of the industrial big data platform mainly includes the following steps:

[0039] Step S1: The comprehensive information of the raw materials to be processed is input into the system through the material comprehensive information input module, the visual image of the forged parts processed by the equipment and the visual image of the equipment surroundings are collected through the visual module, and the infrared thermal data and pressure load data of the equipment under the operation state are collected in real time through the sensor module;

[0040] Step S2: When the equipment is processing forgings, the system starts the equipment detection module, starts to analyze the temperature and pressure load of the equipment in the running state and whether the mold is suitable, and adjusts the equipment according to the analysis results;

[0041] Step S3: when detecting the quality of the forged part, start the forged part detection module, start to analyze the characteristics of the forged part, adopt the corresponding detection strategy to detect according to the characteristics of the forged part, and judge whether the forged part has quality defects according to the detection results;

[0042] Step S4: When forging a new forging, the system detects the material quality and adjusts the mold of the equipment according to the result of the mold detection.

[0043] Step S2 further comprises the following steps:

[0044] Step S21: Obtain infrared thermal data of the material, set the infrared thermal data collection cycle of the equipment, periodically obtain infrared data of the equipment in operation, identify the temperature of the equipment bearing, calculate the difference C between the equipment temperature in the current cycle and the equipment temperature collected in the most recent cycle, when the difference |C| is less than the threshold value set by the system, it means that the equipment temperature has changed little, and the system continues to detect the equipment temperature. When the difference |C| is greater than the threshold value set by the system, it means that the equipment temperature has changed greatly, and the abnormal temperature of the equipment is marked. The working time of the equipment and the load rate under the working state are retrieved. If the load rate of the equipment is greater than the threshold and the working time of the equipment is also greater than the threshold, the current equipment is marked as an overloaded equipment, and the material input is reduced. Otherwise, the equipment is marked as faulty. By judging whether the material temperature meets the processing requirements, it is possible to avoid equipment failure due to insufficient material temperature, thereby reducing the frequency of equipment failures and maintenance time, and greatly improving the operation efficiency of the equipment.

[0045] Step S22: retrieve comprehensive information data of the material to be processed, identify the code of the material to be processed, search the database according to the code of the material to be processed, obtain the hardness K of the material to be processed, search the processing history database according to the code of the material to be processed, and give the influence coefficient α of the hardness of the material to be processed on the tensile length of the material;

[0046] Step S23: Get the model of the mold, anchor the mold depression, measure the depth H of the most concave part of the mold, set the measurement interval, measure the width of the most concave part of the mold according to the set interval, calculate the width difference of the most concave part of the mold under adjacent intervals, if the width difference is less than the threshold set by the system, it means that the slope of the mold depression is steep, measure the inflection angle of the most concave part of the mold, call the corresponding stretching length influence coefficient η in the database according to the inflection angle, and calculate the length that the current material can be forged and stretched in the mold through the formula Where, L 1 Indicates the length of the material before processing, L 2 Indicates the length of the material after forging, λ indicates the influence coefficient of the pressure applied by the press on the forging length of the material, μ indicates the influence coefficient of the material's resilience on the stretching length, otherwise the current mold is marked as an available mold. If the length of the material after forging L 2 If the difference between the depth H of the most concave part of the mold and the depth H of the most concave part of the mold is less than the threshold, the current mold is marked as a usable mold, otherwise it is marked as an unusable mold. By judging whether the current mold can process the current material, it is possible to avoid unqualified processed materials, resulting in energy waste, and even equipment damage, leading to equipment downtime, thereby greatly improving the operating efficiency of the equipment.

[0047] Step S3 further comprises the following steps:

[0048] Step S31: retrieve the visual image of the forged part after processing, scan the features of the forged part, classify the forged part according to the features of the forged part, scan the contour feature nodes of the forged part, connect the contour feature nodes of the forged part to build the contour feature model of the forged part, set the detection accuracy to 0.1mm, overlap and compare the constructed contour model of the forged part with the forged part model in the database, mark the part that cannot be overlapped, identify the area of ​​the marked part, if the area of ​​the marked part is greater than the threshold set by the system, it means that the forged part has an edge defect, and the forged part is marked as an edge defective product, otherwise the forged part is marked as a qualified product, by classifying the forged part according to the features extracted from the forged part, and adopting the corresponding detection strategy for the classified forged part, the corresponding detection strategy can be used more accurately, and the efficiency and accuracy of the detection can be further improved;

[0049] Step S32: grayscale the visual image of the forging, scan and identify the color values ​​of the pixels on the surface of the forging in the visual image, calculate the difference in color values ​​between adjacent pixels, and if the difference in color value between adjacent pixels is less than a threshold, mark the pixel; otherwise, the system continues to detect, identify the mark in the pixel, connect the pixels with the same mark and adjacent to each other, identify the graphic features formed by the connection of the pixels, and compare the image features. If the similarity between the image features is greater than the threshold set by the system, it means that a coarse-grained ring defect occurs in the forging, and the current forging is marked as a coarse-grained ring defective product. Otherwise, the system continues to detect the remaining forgings and identify the marks in the forging. If both edge defect marks and coarse-grained ring defect marks appear in the forging, the forging is marked as a coarse-grained ring defective product. Otherwise, the defect of the forging is described according to the initial mark in the forging. By performing secondary detection on forgings with similar defect features, misjudgment caused by similar defect features of the forgings can be avoided, thereby greatly improving the accuracy of defect detection of forgings.

[0050] Step S31 further includes the following steps:

[0051] Step S311: When the defect feature of the forging is a surface feature, the color value E of the pixel point on the surface of the forging part after grayscale processing is identified, and the color value difference Q between the pixel point and its upper, lower, left and right adjacent pixels is calculated in turn, and the color value of the pixel point is added to the color value difference, that is, the color value of the pixel point is G=E+Q, where G represents a new color value, and four new pictures are constructed using the new color value G respectively, and the four new pictures are overlapped and fused, and the feature nodes of the new pictures are scanned and identified, and the identified feature nodes are connected to construct a feature model, and the pixel point position of the feature model is anchored in the new picture, and the database image is searched according to the anchored pixel point position. If there is no corresponding feature point in the database image, the current forging part is marked as a scratch defective product, otherwise the system continues to detect;

[0052] Step S312: When a scratch defect mark is identified in the forged part, the color value of the pixel point of the visual image of the forged part is identified, the brightness of the visual image of the forged part is adjusted, the color value of the pixel point after the processing is scanned and identified, the difference between the color value of the pixel point before and after the processing is calculated, and the discrete coefficient of the difference of the color value of the pixel point is calculated by the formula Where i = 1, 2, 3...n, P represents the discrete coefficient of the pixel color value difference, M represents the difference between the pixel color values ​​before and after processing, It represents the average value of the difference between the color values ​​of the pixels before and after processing. If the discrete coefficient of the color value difference of the pixel is greater than the system threshold, it means that the surface of the current forging is oily and the current forging is marked as a qualified product. Otherwise, the current forging is marked as a scratch defective product. By adopting different detection methods, it is possible to avoid system misjudgment caused by the same defect features, thereby reducing the influence of the same defect features on the accuracy of the detection results, and greatly improving the detection accuracy of forging defects.

[0053] In step S4, infrared thermal data of the material is obtained, the temperature of the material is identified, and the temperature of the material is compared with a historical database. If the temperature of the material is less than a first threshold or greater than a second threshold, the material is marked as an unusable material, otherwise it is marked as an usable material, and the mold inspection results and material inspection results are retrieved. The mold used by the equipment is adjusted according to the mold inspection results, and the heating temperature and heating time of the equipment are adjusted according to the material inspection results.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0055] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An industrial big data platform based on blockchain, including a data collection module, an intelligent detection module and an intelligent control module, characterized in that: The data collection module is used to collect visual images of forgings, equipment operation status data and comprehensive information of materials used for forging, the intelligent detection module is used to detect equipment operation status data and analyze defects of forgings, the intelligent control module is used to analyze comprehensive information data of raw materials used for forging, analyze whether the current mold can process the raw materials, and adjust the heating temperature, time and forging mold of the equipment according to the analysis results, and the data collection module, the intelligent detection module and the intelligent control module are electrically connected to each other; The equipment detection module includes a temperature detection submodule, a load detection submodule and a mold detection submodule. The temperature detection submodule is used to detect the temperature of the equipment in operation, the load detection submodule is used to detect the forging pressure of the equipment, and the mold detection submodule is used to detect whether the mold is suitable for the current material. The forging detection module includes a feature extraction submodule, a feature comparison submodule and a defect detection submodule. The feature extraction submodule is used to extract the surface features of the forgings. The feature comparison submodule is used to adopt different detection methods for different forging features. The defect detection submodule is used to distinguish the defects of the forgings using different detection methods when the forging features are the same.

2. The blockchain-based industrial big data platform according to claim 1, characterized in that: The data collection module includes a material comprehensive information input module, a visual module and a sensor module. The material comprehensive information input module is used to input the comprehensive information of the material into the system, the visual module is used to capture the visual image of the forging, and the sensor module is used to collect the operating status data of the hot die forging press in real time.

3. The industrial big data platform based on blockchain according to claim 2 is characterized in that: The intelligent detection module includes an equipment detection module, and the equipment detection module is used to detect the temperature and pressure load of the equipment in the running state.

4. The blockchain-based industrial big data platform according to claim 3 is characterized by: The intelligent detection module also includes a forging detection module, which is used to extract the characteristics of the forging and analyze the defects of the forging using different methods according to the characteristics.

5. The blockchain-based industrial big data platform according to claim 4 is characterized in that: The intelligent control module includes a material detection module and an equipment adjustment module. The material detection module is used to detect the material of the material and adjust the heating temperature of the equipment according to the material of the material. The equipment adjustment module is used to adjust the working mode of the equipment according to the detection result of the equipment.

6. The industrial big data platform based on blockchain according to claim 5 is characterized in that: The operation method of the industrial big data platform mainly includes the following steps: Step S1: The comprehensive information of the raw materials to be processed is input into the system through the material comprehensive information input module, the visual image of the forged parts processed by the equipment and the visual image of the equipment surroundings are collected through the visual module, and the infrared thermal data and pressure load data of the equipment under the operation state are collected in real time through the sensor module; Step S2: When the equipment is processing forgings, the system starts the equipment detection module, starts to analyze the temperature and pressure load of the equipment in the running state and whether the mold is suitable, and adjusts the equipment according to the analysis results; Step S3: when detecting the quality of the forged part, start the forged part detection module, start to analyze the characteristics of the forged part, adopt the corresponding detection strategy to detect according to the characteristics of the forged part, and judge whether the forged part has quality defects according to the detection results; Step S4: When forging a new forging, the system detects the material quality and adjusts the mold of the equipment according to the result of the mold detection.

7. The blockchain-based industrial big data platform according to claim 6 is characterized in that: The step S2 further comprises the following steps: Step S21: Obtain infrared thermal data of the material, set the infrared thermal data collection cycle of the equipment, periodically obtain infrared data of the equipment in operation, identify the temperature of the equipment bearing, calculate the difference C between the equipment temperature in the current cycle and the equipment temperature collected in the most recent cycle, when the difference |C| is less than the threshold value set by the system, the system continues to detect the equipment temperature, when the difference |C| is greater than the threshold value set by the system, the abnormal temperature part of the equipment is marked, the working time of the equipment and the load rate under the working state are retrieved, if the load rate of the equipment is greater than the threshold value and the working time of the equipment is also greater than the threshold value, the current equipment is marked as an overloaded equipment, and the material input is reduced, otherwise the equipment is marked as a fault; Step S22: retrieve comprehensive information data of the material to be processed, identify the code of the material to be processed, search the database according to the code of the material to be processed, obtain the hardness K of the material to be processed, search the processing history database according to the code of the material to be processed, and give the influence coefficient α of the hardness of the material to be processed on the tensile length of the material; Step S23: Get the model of the mold, anchor the mold depression, measure the depth H of the most concave part of the mold, set the measurement interval, measure the width of the most concave part of the mold according to the set interval, calculate the width difference of the most concave part of the mold under adjacent intervals, if the width difference is less than the threshold set by the system, it means that the slope of the mold depression is steep, measure the inflection angle of the most concave part of the mold, call the corresponding stretching length influence coefficient η in the database according to the inflection angle, and calculate the length that the current material can be forged and stretched in the mold through the formula Wherein, L1 represents the length of the material before processing, L2 represents the length of the material after forging, λ represents the influence coefficient of the pressure applied by the press on the forging length of the material, μ represents the influence coefficient of the material's resilience on the tensile length, otherwise the current mold is marked as a usable mold. If the difference between the length L2 of the material after forging and the depth H of the most concave part of the mold is less than the threshold value, the current mold is marked as a usable mold, otherwise the current mold is marked as an unusable mold.

8. The blockchain-based industrial big data platform according to claim 7 is characterized by: The step S3 further comprises the following steps: Step S31: retrieve the visual image of the forged part after processing, scan the features of the forged part, classify the forged part according to the features of the forged part, scan the contour feature nodes of the forged part, connect the contour feature nodes of the forged part to build the contour feature model of the forged part, set the detection accuracy to 0.1mm, overlap and compare the constructed contour model of the forged part with the forged part model in the database, mark the part that cannot be overlapped, identify the area of ​​the marked part, if the area of ​​the marked part is greater than the threshold set by the system, then mark the forged part as a marginal defective product, otherwise mark the forged part as a qualified product, by classifying the forged part according to the features extracted from the forged part, and adopting the corresponding detection strategy for the classified forged part, the corresponding detection strategy can be used more accurately, and the efficiency and accuracy of the detection can be further improved; Step S32: grayscale the visual image of the forging, scan and identify the color values ​​of the pixels on the surface of the forging in the visual image, calculate the difference in color values ​​between adjacent pixels, and if the difference in color value between adjacent pixels is less than a threshold, mark the pixel; otherwise, the system continues to detect, identify the marks in the pixels, connect the pixels with the same marks and adjacent to each other, identify the graphic features formed by the connection of the pixels, and compare the image features. If the similarity between the image features is greater than the threshold set by the system, mark the current forging as a coarse-grained ring defective product; otherwise, the system continues to detect the remaining forgings and identify the marks in the forgings. If both edge defect marks and coarse-grained ring defect marks appear in the forging, the forging is marked as a coarse-grained ring defective product; otherwise, the defects of the forging are described according to the initial marks in the forging.

9. The blockchain-based industrial big data platform according to claim 8, characterized in that: The step S31 further comprises the following steps: Step S311: When the defect feature of the forging is a surface feature, the color value E of the pixel point on the surface of the forging part after grayscale processing is identified, and the color value difference Q between the pixel point and its upper, lower, left and right adjacent pixels is calculated in turn, and the color value of the pixel point is added to the color value difference, that is, the color value of the pixel point is G=E+Q, where G represents a new color value, and four new pictures are constructed using the new color value G respectively, and the four new pictures are overlapped and fused, and the feature nodes of the new pictures are scanned and identified, and the identified feature nodes are connected to construct a feature model, and the pixel point position of the feature model is anchored in the new picture, and the database image is searched according to the anchored pixel point position. If there is no corresponding feature point in the database image, the current forging part is marked as a scratch defective product, otherwise the system continues to detect; Step S312: When a scratch defect mark is identified in the forged part, the color value of the pixel point of the visual image of the forged part is identified, the brightness of the visual image of the forged part is adjusted, the color value of the pixel point after the processing is scanned and identified, the difference between the color value of the pixel point before and after the processing is calculated, and the discrete coefficient of the difference of the color value of the pixel point is calculated by the formula Where i = 1, 2, 3...n, P represents the discrete coefficient of the pixel color value difference, M represents the difference between the pixel color values ​​before and after processing, It represents the average value of the difference between the color values ​​of the pixels before and after processing. If the discrete coefficient of the color value difference of the pixel is greater than the system threshold, it means that the surface of the current forging is oily and the current forging is marked as a qualified product. Otherwise, the current forging is marked as a scratch defective product.

10. The blockchain-based industrial big data platform according to claim 9, characterized in that: In the step S4, infrared thermal data of the material is obtained, the temperature of the material is identified, and the temperature of the material is compared with a historical database. If the temperature of the material is less than a first threshold or greater than a second threshold, the material is marked as an unusable material, otherwise it is marked as an usable material, and the mold detection results and material detection results are retrieved. The mold used by the equipment is adjusted according to the mold detection results, and the heating temperature and heating time of the equipment are adjusted according to the material detection results.

Images