Deep Learning-Based Steel Shot Production Data Analysis System and Method

Abstract

The present application discloses a steel shot production data analysis system and method based on deep learning, belonging to the field of deep learning. The present application constructs a fault cause search model, imports the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes, and feeds back the found fault causes to the management end in real time. The present application comprehensively analyzes the shape and defect production characteristics of steel shots, thereby accurately obtaining the production quality of steel shots, and then quickly and accurately discovers the fault causes during the operation process based on the production quality characteristics of steel shots, the operation data of equipment, and historical data, improving the accuracy and efficiency of fault cause discovery.

Description

Technical Field

[0001] This application belongs to the field of deep learning, specifically a steel shot production data analysis system and method based on deep learning. Background Art

[0002] Steel shot is a metal material widely used in fields such as metal surface treatment, casting, steel structures, and metal rust removal. The production process of steel shot usually includes multiple links such as raw material preparation, melting, casting, crushing, and screening. The main raw materials of steel shot are scrap iron or pig iron. After the production of steel shot, quality inspection of the produced steel shot is required. The quality inspection includes multiple aspects such as appearance inspection, dimension measurement, and chemical composition analysis to ensure that the quality of the steel shot meets the standard requirements. The production of steel shot requires strict control of the process parameters and quality standards of each link to ensure that the produced steel shot meets the use requirements and has good performance;

[0003] When analyzing steel shot production data in the prior art, it is impossible to comprehensively analyze the shape and defect production characteristics of steel shot, and thus it is impossible to accurately obtain the production quality of steel shot, resulting in inaccurate discovery of the cause of failures during operation based on the production quality characteristics of steel shot, the operation data of equipment, and historical data. Most of the prior art has the above problems;

[0004] To solve the problems raised in this background art, this application designs a steel shot production data analysis system and method based on deep learning. Summary of the Invention

[0005] In view of the deficiencies of the prior art, this application proposes a steel shot production data analysis system and method based on deep learning.

[0006] To achieve the above object, this application provides the following technical solutions: In the first aspect, this application provides a steel shot production data analysis method based on deep learning, which includes the following specific steps:

[0007] S1. Obtain steel shot production data and operation data during the operation of production equipment;

[0008] S2. Import the obtained steel shot production data into a steel shot production evaluation model for steel shot production evaluation;

[0009] S3. Determine whether to search for faulty equipment based on the steel shot production evaluation result. If the determination is yes, then perform S4; if the determination is no, then end;

[0010] S4. Construct a fault cause search model, and import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for the cause of the fault;

[0011] S5. Real-time feedback the found cause of the fault to the management terminal.

[0012] As a preferred technical solution of the steel shot production data analysis method based on deep learning, the specific content of obtaining the steel shot production data and the operation data during the operation of the production equipment is as follows:

[0013] S11. Obtain the production data corresponding to the steel shot production process. Among them, the steel shot production data includes the steel shot surface defect data and the steel shot production shape data. Among them, the steel shot surface defect data includes the pit area and pit depth data on the steel shot surface, and the steel shot production shape data includes the image data and diameter data of each parallel section of the steel shot. The method for obtaining the roundness data and diameter data of the corresponding parallel sections is to obtain the three-dimensional image of the steel shot, cut the steel shot image with a plurality of parallel planes at the same distance, obtain the images of all the cut surfaces as parallel sections, and obtain the roundness data and diameter data of the corresponding parallel sections;

[0014] S12. Obtain the operation data of the production equipment during the steel shot production process. Among them, the production equipment operation data includes the operation equipment voltage, current, temperature, and operation pressure data;

[0015] S13. Store the obtained production data of the steel shot production process and the operation data of the production equipment corresponding to the steel shot production process in the storage component.

[0016] As a preferred technical solution of the steel shot production data analysis method based on deep learning, the evaluation of steel shot production by importing the obtained steel shot production data into the steel shot production evaluation model includes the following specific steps:

[0017] S21. Obtain the production data of the production processes of several steel shot samples, and import the obtained steel shot production shape data into the shape outlier calculation formula to calculate the shape outlier. Among them, the shape outlier calculation formula is: , where n is the number of steel shot samples, mi is the number of parallel sections, and Lij is the shortest distance from the jth parallel section to the center of the sphere;

[0018] S22. Obtain the steel shot surface defect data, and import the steel shot surface defect data into the defect outlier calculation formula to calculate the defect outlier. Among them, the defect outlier calculation formula is: , where Di is the number of pits on the ith steel shot sample, V is the volume of the standard steel shot, dci is the depth of the cth pit on the ith steel shot sample, and sci is the area of the cth pit on the ith steel shot sample;

[0019] S23. Substitute the obtained shape outlier and defect outlier into the steel shot production outlier calculation formula to calculate the steel shot production outlier. Among them, the steel shot production outlier calculation formula is: , where b is the proportion of defective anomalies; in this formula, the steel shot anomalies are accurately analyzed through shape anomalies and defective anomalies.

[0020] As a preferred technical solution of the steel shot production data analysis method based on deep learning, the judgment of whether to search for faulty equipment based on the steel shot production evaluation results includes the following specific steps:

[0021] Compare the obtained steel shot production anomaly value with the set steel shot production anomaly threshold. If the obtained steel shot production anomaly value is greater than or equal to the set steel shot production anomaly threshold, it is necessary to search for faulty equipment. If the obtained steel shot production anomaly value is less than the set steel shot production anomaly threshold, it is not necessary to search for faulty equipment.

[0022] As a preferred technical solution of the steel shot production data analysis method based on deep learning, the construction of the fault cause search model and the import of the obtained steel shot production evaluation data and equipment operation data into the fault cause search model for fault cause search include the following specific contents:

[0023] S41. Extract historical equipment operation data, shape anomaly values of historical production products, defective anomaly value data of historical production products, and searched fault cause data, and construct a deep learning neural network model with historical equipment operation data, shape anomaly values of historical production products, and defective anomaly value data of historical production products as inputs and fault cause data as outputs;

[0024] S42. Set the parameter training set and parameter test set according to the ratio of 9:1 for the extracted historical equipment operation data, shape anomaly values of historical production products, defective anomaly value data of historical production products, and searched fault cause data; input 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum fault cause search accuracy as the deep learning neural network model;

[0025] S43. Import the calculated shape anomaly value, defective anomaly value, and equipment operation data into the deep learning neural network model to output the corresponding fault cause data.

[0026] In the second aspect, the present application provides a steel shot production data analysis system based on deep learning, which is implemented based on the above-mentioned steel shot production data analysis method based on deep learning, and specifically includes a data acquisition module, a steel shot production evaluation module, a judgment module, a fault cause search module, and a cause feedback module;

[0027] Among them, the data acquisition module is used to acquire steel shot production data and operation data during the operation of production equipment;

[0028] The steel shot production evaluation module is used to obtain steel shot production data and import it into the steel shot production evaluation model for steel shot production evaluation;

[0029] The judgment module is used to judge whether to search for faulty equipment based on the steel shot production evaluation result;

[0030] The fault cause search module is used to construct a fault cause search model, and import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes;

[0031] The cause feedback module is used to feedback the found fault causes to the management end in real time;

[0032] It may further include a control module, which is used to control the operation of the data acquisition module, the steel shot production evaluation module, the judgment module, the fault cause search module and the cause feedback module.

[0033] In a third aspect, the present application provides an electronic device, including: a processor and a memory, wherein a computer program callable by the processor is stored in the memory;

[0034] The processor executes the above-mentioned steel shot production data analysis method based on deep learning by calling the computer program stored in the memory.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which when run on a computer, cause the computer to execute the above-mentioned steel shot production data analysis method based on deep learning.

[0036] Compared with the prior art, the beneficial effects of the present application are:

[0037] The present application obtains steel shot production data and operation data during the operation of production equipment, obtains steel shot production data and imports it into the steel shot production evaluation model for steel shot production evaluation, judges whether to search for faulty equipment based on the steel shot production evaluation result, constructs a fault cause search model, imports the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes, and feedbacks the found fault causes to the management end in real time. The present application comprehensively analyzes the shape and defect production characteristics of steel shots, and then accurately obtains the production quality of steel shots. Then, based on the production quality characteristics of steel shots, the operation data of equipment and historical data, it quickly and accurately discovers the fault causes during the operation process, improving the accuracy and efficiency of fault cause discovery. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments read in conjunction with the accompanying drawings;

[0039] Figure 1 This is a schematic diagram of the overall process of the steel shot production data analysis method based on deep learning of the present application;

[0040] Figure 2 This is a schematic diagram of step S2 of the steel shot production data analysis method based on deep learning of the present application;

[0041] Figure 3 This is a schematic diagram of step S4 of the steel shot production data analysis method based on deep learning of the present application;

[0042] Figure 4 This is a schematic diagram of the overall framework of the steel shot production data analysis system based on deep learning of the present application;

[0043] Figure 5 This is a schematic diagram of obtaining a three-dimensional view of parallel sections of the present application;

[0044] Figure 6 This is a schematic diagram of the parallel plane cutting process of the present application. Detailed Embodiments

[0045] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present application and its application or use.

[0046] Embodiment 1. To solve the technical problems proposed in the background art, the present application provides a preferred embodiment: as Figure 1 - Figure 3 shown, the steel shot production data analysis method based on deep learning includes the following specific steps:

[0047] S1. Obtain steel shot production data and operation data during the operation of production equipment;

[0048] In one specific embodiment, the specific content of obtaining steel shot production data and operation data during the operation of production equipment is:

[0049] S11. Obtain production data corresponding to the steel shot production process. Among them, the steel shot production data includes steel shot surface defect data and steel shot production shape data. Among them, the steel shot surface defect data includes the pit area and pit depth data on the steel shot surface, and the steel shot production shape data includes the image data and diameter data of each parallel section of the steel shot, as Figure 5 andFigure 6 As shown Figure 5 This is a schematic diagram for obtaining a three-dimensional view of the parallel cross-sections of the present application Figure 6 This is a schematic diagram of the cutting process of the parallel planes of the present application. The method for obtaining the roundness data and diameter data of each corresponding parallel cross-section is as follows: Obtain a three-dimensional image of the steel shot, cut the steel shot image with several parallel planes at the same distance, obtain the images of all the cut surfaces as parallel cross-sections, and obtain the roundness data and diameter data of each corresponding parallel cross-section

[0050] The production data of the steel shot can be obtained from the three-dimensional image of the steel shot. The three-dimensional image of the steel shot can be obtained using a three-dimensional scanner: A three-dimensional scanner is a device that can quickly obtain the surface shape and geometric data of an object. By placing the steel shot on the platform of the scanner, the three-dimensional point cloud data of the steel shot can be obtained, and then a three-dimensional image can be generated

[0051] S12. Obtain the operation data of the production equipment during the production process of the steel shot. Among them, the operation data of the production equipment includes the voltage, current, temperature, and operation pressure data of the operating equipment

[0052] S13. Store the production data of the steel shot production process and the operation data of the production equipment corresponding to the steel shot production process in the storage component

[0053] S2. Obtain the production data of the steel shot and import it into the steel shot production evaluation model for steel shot production evaluation

[0054] In one specific embodiment, obtaining the production data of the steel shot and importing it into the steel shot production evaluation model for steel shot production evaluation includes the following specific steps

[0055] S21. Obtain the production data of the production processes of several steel shot samples, and import the obtained production shape data of the steel shot into the shape outlier calculation formula to calculate the shape outlier value. Among them, the shape outlier calculation formula is , where n is the number of steel shot samples, mi is the number of parallel cross-sections, Lij is the shortest distance from the jth parallel cross-section to the center of the sphere. Here, it should be noted that the center of the sphere here is the center of the steel shot, a is the shape outlier proportion coefficient, S() is the area of the image in the parentheses, Tij is the image of the jth parallel cross-section of the ith steel shot sample, Tijm is the image of the jth parallel cross-section of the standard steel shot is the intersection of the images is the union of the images, xij is the average diameter of the jth parallel cross-section of the ith steel shot sample, xijm is the average diameter of the jth parallel cross-section of the standard steel shot. Here, it should be noted that since there may be accidental factors for a steel shot, so multiple steel shot samples are selected here, and the number of parallel cross-sections is selected to be greater than or equal to 5. In the formula where the upper formula is the area of the intersection image of the j-th parallel section of the i-th steel shot sample and the j-th parallel section of the standard steel shot, and the lower formula is the area of the union image of the j-th parallel section of the i-th steel shot sample and the j-th parallel section of the standard steel shot, that is, the similarity of the two image regions. Since the formula output is an abnormal value of the shape, it is inversely proportional to the similarity of the two image regions. Therefore, ; and for is the difference value of the diameters. Therefore, this formula analyzes the abnormality of the parallel section through the abnormality of the image and the abnormality of the diameter. For parallel sections at different positions, it is certain that the section closest to the center of the steel shot is the largest and the most important. Therefore, is used, that is, the reciprocal of the distance to the center of the steel shot is used for importance weighting. The meaning of adding 1 to the distance here is to prevent the numerator from being 0;

[0056] S22. Obtain the steel shot surface defect data, and import the steel shot surface defect data into the defect outlier calculation formula to calculate the defect outlier. Among them, the defect outlier calculation formula is: , where Di is the number of pits on the i-th steel shot sample, V is the volume of the standard steel shot, dci is the depth of the c-th pit on the i-th steel shot sample, and sci is the area of the c-th pit on the i-th steel shot sample;

[0057] S23. Substitute the obtained shape outlier and defect outlier into the steel shot production outlier calculation formula to calculate the steel shot production outlier. Among them, the steel shot production outlier calculation formula is: , where b is the proportion of defect outliers; in this formula, the steel shot abnormality is accurately analyzed through the shape abnormality and the defect abnormality;

[0058] S3. Determine whether to search for faulty equipment based on the steel shot production evaluation result. If the judgment is yes, then perform S4. If the judgment is no, then end;

[0059] In one specific embodiment, compare the obtained steel shot production outlier with the set steel shot production outlier threshold. If the obtained steel shot production outlier is greater than or equal to the set steel shot production outlier threshold, then it is necessary to search for faulty equipment. If the obtained steel shot production outlier is less than the set steel shot production outlier threshold, then it is not necessary to search for faulty equipment;

[0060] Here, it is necessary to specifically explain the value-taking methods of the shape anomaly proportion coefficient, the defect anomaly proportion, and the steel shot production anomaly threshold: Obtain 5000 groups of steel shot production data, import them into the steel shot production anomaly value calculation formula to calculate the steel shot production anomaly value, perform equipment maintenance to check if there is a failure, import the failure judgment result and the calculated steel shot production anomaly value into the fitting software, and output the value-taking of the shape anomaly proportion coefficient, the defect anomaly proportion, and the steel shot production anomaly threshold that meet the maximum failure judgment accuracy rate;

[0061] S4. Construct a fault cause search model, and import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes;

[0062] In one specific embodiment, constructing a fault cause search model and importing the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes includes the following specific contents:

[0063] S41. Extract historical equipment operation data, shape anomaly values of historical production products, defect anomaly value data of historical production products, and searched fault cause data, and construct a deep learning neural network model with equipment operation data, shape anomaly values of production products, and defect anomaly value data of production products as inputs and fault cause data as outputs;

[0064] S42. Set the parameter training set and parameter test set according to the ratio of 9:1 for the extracted historical equipment operation data, shape anomaly values of historical production products, defect anomaly value data of historical production products, and searched fault cause data; Input 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; Use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum fault cause search accuracy rate as the deep learning neural network model. Among them, the output strategy formula of the s-th neuron in the M-th layer of the deep learning neural network model is: , where is the output of the s-th neuron in the M-th layer, is the connection weight between the c-th neuron in the (M - 1)-th layer and the s-th neuron in the M-th layer, represents the input of the c-th neuron in the (M - 1)-th layer, represents the bias of the linear relationship between the c-th neuron in the (M - 1)-th layer and the s-th neuron in the M-th layer, Sig() represents the Sigmoid activation function, and w is the number of neurons in the (M - 1)-th layer; Here, it should be noted that in this neural network, the three inputs of the input layer are: equipment operation data, shape anomaly values of production products, and defect anomaly value data of production products, and the output of the output layer is the searched fault cause;

[0065] S43. Import the calculated shape outliers, defect outliers, and equipment operation data into the deep learning neural network model to output the corresponding fault cause data;

[0066] S5. Real-time feedback the found fault cause to the management terminal, and the management terminal selects appropriate maintenance personnel to perform fault maintenance according to the found fault cause.

[0067] The advantages of this embodiment over the prior art are as follows: Obtain the steel shot production data and the operation data during the operation of the production equipment, import the steel shot production data into the steel shot production evaluation model for steel shot production evaluation, judge whether to search for faulty equipment through the steel shot production evaluation results, construct a fault cause search model, import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes, and real-time feedback the found fault cause to the management terminal. This application comprehensively analyzes the shape and defect production characteristics of steel shots, thereby accurately obtaining the production quality of steel shots, and then quickly and accurately discovers the fault causes during the operation process based on the production quality characteristics of steel shots, the operation data of the equipment, and historical data, improving the accuracy and efficiency of fault cause discovery.

[0068] Embodiment 2. As Figure 4 shown, the steel shot production data analysis system based on deep learning is implemented based on the above-mentioned steel shot production data analysis method based on deep learning, and specifically includes a data acquisition module, a steel shot production evaluation module, a judgment module, a fault cause search module, and a cause feedback module; among them, the data acquisition module is used to obtain the steel shot production data and the operation data during the operation of the production equipment; the steel shot production evaluation module is used to import the steel shot production data into the steel shot production evaluation model for steel shot production evaluation; the judgment module is used to judge whether to search for faulty equipment through the steel shot production evaluation results; the fault cause search module is used to construct a fault cause search model, and import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes; the cause feedback module is used to real-time feedback the found fault cause to the management terminal; it may also include a control module, and the control module is used to control the operation of the data acquisition module, the steel shot production evaluation module, the judgment module, the fault cause search module, and the cause feedback module;

[0069] For the steps of each parameter and each unit module in the above-mentioned steel shot production data analysis system based on the present application to implement the corresponding functions, reference can be made to the parameters and steps in the embodiments of the steel shot production data analysis method based on deep learning in the above text, and details are not described here.

[0070] Embodiment 3. This embodiment provides an electronic device, including: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory;

[0071] The processor executes the above-mentioned method for analyzing steel shot production data based on deep learning by calling the computer program stored in the memory.

[0072] This electronic device may have relatively large differences due to different configurations or performances, and can include one or more processors and one or more memories. Among them, at least one computer program is stored in the memory, and this computer program is loaded and executed by the processor to implement the method for analyzing steel shot production data based on deep learning provided by the above-mentioned method embodiments. This electronic device can also include other components for implementing device functions. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment will not be elaborated here.

[0073] Embodiment 4. This embodiment proposes a computer-readable storage medium, on which a rewritable computer program is stored;

[0074] When the computer program runs on a computer device, it causes the computer device to execute the above-mentioned method for analyzing steel shot production data based on deep learning.

[0075] For example, the computer-readable storage medium can be a read-only memory, a random access memory, a compact disc read-only memory, magnetic tape, a floppy disk, and an optical data storage device, etc.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more collections of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0077] The term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus.

[0078] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions applied in the present application.

Claims

1. A method for analyzing steel shot production data based on deep learning, characterized in that, It includes the following specific steps: S1. Obtain the production data of steel shots and the operation data during the operation of production equipment; S2. Obtain the production data of steel shots and import it into the steel shot production evaluation model for steel shot production evaluation; It includes the following specific steps: S21. Obtain the production data of the production processes of several steel shot samples, and import the obtained production shape data of the steel shot into the shape outlier calculation formula to calculate the shape outlier value. The shape outlier calculation formula is as follows: , where n is the number of steel shot samples, mi is the number of parallel sections, Lij is the shortest distance from the j-th parallel section to the center of the sphere, a is the shape outlier proportion coefficient, S() is the area of the image in the parentheses, Tij is the image of the j-th parallel section of the i-th steel shot sample, Tijm is the image of the j-th parallel section of the standard steel shot, is the intersection of the images, is the union of the images, xij is the average diameter of the j-th parallel section of the i-th steel shot sample, and xijm is the average diameter of the j-th parallel section of the standard steel shot; S22. Obtain the surface defect data of the steel shot, and import the surface defect data of the steel shot into the defect outlier calculation formula to calculate the defect outlier. Among them, the defect outlier calculation formula is: , where Di is the number of pits on the i-th steel shot sample, V is the volume of the standard steel shot, dci is the depth of the c-th pit on the i-th steel shot sample, and sci is the area of the c-th pit on the i-th steel shot sample; S23. Obtain the calculated shape outliers and defect outliers, substitute them into the steel shot production outlier calculation formula to calculate the steel shot production outliers. The steel shot production outlier calculation formula is as follows: , where b is the proportion of defect outliers; S3. Determine whether to search for faulty equipment based on the steel shot production evaluation result. If the judgment is yes, proceed to S4; if the judgment is no, end; S4. Construct a fault cause search model, and import the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes; S5. Real-time feedback the found fault causes to the management terminal.

2. The method for analyzing steel shot production data based on deep learning according to claim 1, wherein The specific content of obtaining the production data of steel shots and the operation data during the operation of production equipment is as follows: S11. Obtain the production data corresponding to the steel shot production process. Among them, the steel shot production data includes the surface defect data of steel shots and the production shape data of steel shots. Among them, the surface defect data of steel shots includes the pit area and pit depth data on the surface of steel shots, and the production shape data of steel shots includes the image data and diameter data of each parallel section of steel shots; S12. Obtain the operation data of production equipment corresponding to the steel shot production process. Among them, the operation data of production equipment includes the voltage, current, temperature and operation pressure data of the operation equipment; S13. Store the obtained production data of the steel shot production process and the operation data of production equipment corresponding to the steel shot production process in the storage component.

3. The data analysis method for steel shot production based on deep learning according to claim 2, wherein The determination of whether to search for faulty equipment based on the steel shot production evaluation result includes the following specific steps: Compare the obtained steel shot production outlier with the set steel shot production outlier threshold. If the obtained steel shot production outlier is greater than or equal to the set steel shot production outlier threshold, it is necessary to search for faulty equipment; if the obtained steel shot production outlier is less than the set steel shot production outlier threshold, it is not necessary to search for faulty equipment.

4. The method for analyzing steel shot production data based on deep learning according to claim 3, characterized in that, The construction of the fault cause search model and the import of the obtained steel shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes include the following specific content: S41. Extract the historical equipment operation data, the shape outlier of historical production products, the defect outlier data of historical production products and the found fault cause data, and construct a deep learning neural network model with the historical equipment operation data, the shape outlier of historical production products and the defect outlier data of historical production products as the input and the fault cause data as the output; S42. Set the parameter training set and parameter test set according to the ratio of 9:1 for the extracted historical equipment operation data, the shape outlier of historical production products, the defect outlier data of historical production products and the found fault cause data; input 90% of the parameter training set into the deep learning neural network model for training to obtain the initial deep learning neural network model; use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum fault cause search accuracy as the deep learning neural network model; S43. Import the calculated shape outliers, defect outliers, and equipment operation data into the deep learning neural network model to output the corresponding fault cause data.

5. A steel shot production data analysis system based on deep learning, which is implemented based on the steel shot production data analysis method based on deep learning according to any one of claims 1-4, characterized in that, Specifically, it includes a data acquisition module, a shot production evaluation module, a judgment module, a fault cause search module, and a cause feedback module. Among them, the data acquisition module is used to acquire shot production data and operation data during the operation of the production equipment. The shot production evaluation module is used to import the shot production data into the shot production evaluation model for shot production evaluation. The judgment module is used to judge whether to search for faulty equipment based on the shot production evaluation results. The fault cause search module is used to build a fault cause search model, and import the obtained shot production evaluation data and equipment operation data into the fault cause search model to search for fault causes. The cause feedback module is used to timely feedback the found fault causes to the management terminal.

6. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor. It is characterized in that the processor executes the deep learning-based shot production data analysis method according to any one of claims 1-4 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that, Stores instructions that, when run on a computer, cause the computer to execute the deep learning-based shot production data analysis method according to any one of claims 1-4.

Images