Data Analysis Method for Surface Treatment Process of Steel Parts

Abstract

The present application discloses a data analysis method for the surface treatment process of steel parts, which is used to analyze the process data of steel parts treated by phosphating process, and the method includes: taking a process step of the phosphating process as a treatment step; obtaining the image data and temperature data of the surface of the steel part after the process step before the treatment step as the image data and temperature data to be analyzed; based on artificial intelligence technology, determining the step process parameter configuration and process treatment method of the treatment step according to the image data and temperature data to be analyzed. This provides data support for ensuring the quality stability of steel parts after phosphating treatment.

Description

Technical Field

[0001] The invention relates to the technical field of phosphating step treatment, and in particular to a data analysis method for the surface treatment process of a steel product. Background Art

[0002] The phosphating process is a process in which a phosphate chemical conversion film is formed by chemical and electrochemical reactions. The phosphate conversion film formed is called a phosphating film. At present, each process step of the phosphating process is controlled by the operator and relies on the operator's experience, resulting in unstable quality of the products output by the phosphating process. Summary of the invention

[0003] Based on this, it is necessary to address the technical problem of unstable quality of products output by the phosphating process in the prior art and propose a data analysis method for the surface treatment process of steel parts.

[0004] The present application provides a data analysis method for the surface treatment process of a steel part, the method is used to analyze the process data of a steel part phosphating by a phosphating process, the various process steps of the phosphating process sequentially include: a degreasing step, a first water washing step, a pickling step, a second water washing step, a third water washing step, a surface conditioning step, a phosphating step, a fourth water washing step, a hot water washing step, a drying step and an oil sealing step, the method includes:

[0005] Using a process step of the phosphating process as a treatment step;

[0006] Acquiring image data and temperature data of the surface of the steel workpiece after being processed in the process step preceding the processing step as image data to be analyzed and temperature data to be analyzed;

[0007] Based on artificial intelligence technology, according to the image data to be analyzed and the temperature data to be analyzed, the process parameter configuration and the process processing method of the processing step are determined, wherein the process processing method is one of full processing, local processing first and then full processing, and full processing first and then local processing.

[0008] The data analysis method of the surface treatment process of steel parts of the present application is used to analyze the process data of steel parts phosphating by phosphating process. The process steps of the phosphating process include: degreasing step, first water washing step, pickling step, second water washing step, third water washing step, surface adjustment step, phosphating step, fourth water washing step, hot water washing step, drying step and oil sealing step. The method uses a process step of the phosphating process as a processing step to obtain image data and temperature data of the surface of the steel part after the previous process step of the processing step as image data to be analyzed and temperature data to be analyzed. Based on artificial intelligence technology, the process parameter configuration and process treatment method of the processing step are determined according to the image data to be analyzed and the temperature data to be analyzed, so as to realize automatic and dynamic determination of the process parameter configuration and process treatment method of the process step based on the image data and temperature data of the surface of the steel part, which is conducive to improving the accuracy of each process step, and further provides data support for ensuring the quality stability of the steel parts after phosphating. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0010] in:

[0011] Figure 1 A flow chart of a data analysis method for a surface treatment process of a steel workpiece in one embodiment;

[0012] Figure 2 Another flow chart of a data analysis method for a surface treatment process of a steel workpiece in one embodiment. DETAILED DESCRIPTION

[0013] 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 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.

[0014] See also Figure 1 As shown, Figure 1A flow chart of a data analysis method for the surface treatment process of a steel part provided in an embodiment of the present invention, wherein the method is used to analyze process data of a steel part that is phosphated using a phosphating process, wherein the various process steps of the phosphating process include, in sequence: a degreasing step, a first water washing step, a pickling step, a second water washing step, a third water washing step, a surface conditioning step, a phosphating step, a fourth water washing step, a hot water washing step, a drying step, and an oil sealing step.

[0015] The degreasing step is to remove oil from the surface of the steel parts.

[0016] The first water washing step is to wash the surface of the steel workpiece with water.

[0017] The pickling step is to pickle the surface of the steel workpiece.

[0018] The second water washing step is to wash the surface of the steel workpiece with water.

[0019] The third water washing step is to wash the surface of the steel workpiece with water.

[0020] The surface conditioning step is to condition the surface of the steel parts. Surface conditioning is to treat the metal surface that needs phosphating with a special solution before phosphating. The surface conditioning changes the microscopic state of the metal surface to accelerate phosphating and promote the formation of a fine, uniform and dense phosphating salt film during the phosphating process.

[0021] The phosphating step is to phosphate the surface of the steel parts.

[0022] The fourth water washing step is to wash the surface of the steel part with water.

[0023] The hot water washing step is to wash the surface of the steel parts with hot water.

[0024] The drying step is to dry the surface of the steel workpiece.

[0025] The oil sealing step is to perform oil sealing on the surface of the steel parts. The oil sealing is used to seal the surface of the steel parts with grease.

[0026] The method comprises:

[0027] S1: using a process step of the phosphating process as a treatment step;

[0028] Specifically, any one of all the process steps of the phosphating process is used as a treatment step, or any one of some of the process steps of the phosphating process is used as a treatment step.

[0029] S2: acquiring image data and temperature data of the surface of the steel workpiece after being processed in the process step before the processing step as image data to be analyzed and temperature data to be analyzed;

[0030] The image data is a collection of images obtained by photographing the surface of the steel product using any one of an industrial camera, a laser line scan camera, and a microscope. That is, the image data includes data of at least one image.

[0031] The temperature data is data on the surface temperature of the steel workpiece.

[0032] For example, if the treatment step is the phosphating step of the phosphating process, then the process step before the treatment step is the surface conditioning step of the phosphating process.

[0033] Specifically, the image data and temperature data of the surface of the steel workpiece after being processed in the previous process step of the processing step input by the user can be obtained, the image data and temperature data of the surface of the steel workpiece after being processed in the previous process step of the processing step can be obtained from a preset storage space, and the image data and temperature data of the surface of the steel workpiece after being processed in the previous process step of the processing step can be obtained from a third-party application.

[0034] The image data of the surface of the steel workpiece after being processed in the process step before the processing step is used as the image data to be analyzed, and the temperature data of the steel workpiece after being processed in the process step before the processing step is used as the temperature data to be analyzed.

[0035] S3: Based on artificial intelligence technology, according to the image data to be analyzed and the temperature data to be analyzed, determine the process parameter configuration and process processing method of the processing step, wherein the process processing method is one of full processing, local processing first and then full processing, and full processing first and then local processing.

[0036] Specifically, based on one or more prediction models trained by artificial intelligence, the specific value or specific range of the parameter configuration of the processing step is predicted according to the image data to be analyzed and the temperature data to be analyzed, and the predicted data is used as the step process parameter configuration of the processing step, so as to determine the step process parameter configuration and process treatment method of the steel workpiece that are more suitable for the image data to be analyzed and the temperature data to be analyzed. By executing the processing step on the steel workpiece based on the step process parameter configuration and process treatment method, it is helpful to ensure the effect of the processing step.

[0037] Among them, based on the prediction model trained by artificial intelligence, the processing method of the processing step is predicted according to the image data to be analyzed and the temperature data to be analyzed, and the predicted data is used as the process processing method.

[0038] The process treatment method is one of full treatment, partial treatment first and full treatment, and full treatment first and partial treatment, so as to facilitate accurate treatment. Full treatment means directly performing the process step treatment on the full area of ​​the area to be treated of the steel workpiece. Partial treatment first and full treatment means first performing the process step treatment on a partial area of ​​the area to be treated of the steel workpiece, so that the state of the area to be treated of the entire steel workpiece is consistent, and then performing the process step treatment on the full area of ​​the area to be treated of the steel workpiece. Full treatment first and partial treatment means first performing the process step treatment on the full area of ​​the area to be treated of the steel workpiece, and then performing the process step on a partial area of ​​the area to be treated of the steel workpiece, so that the state of the area to be treated of the entire steel workpiece is consistent. The area to be treated is the area that needs to be treated by the process step.

[0039] It is understandable that a computer device may be used to perform steps S1 to S3.

[0040] Optionally, the operator performs process processing based on the processing step on the steel workpiece according to the process parameter configuration and process processing method of the processing step.

[0041] Optionally, according to the process parameter configuration and process treatment method of the processing step, the phosphating treatment equipment is controlled to perform process treatment based on the processing step on the steel parts.

[0042] This embodiment realizes the automatic and dynamic determination of the process parameter configuration and process treatment method of the process steps based on the surface image data and temperature data of the steel workpiece, which is conducive to improving the accuracy of each process step, and further provides data support for ensuring the quality stability of the steel workpiece after phosphating treatment, thereby making this application intelligent and advanced.

[0043] In one embodiment, the step of determining the process parameter configuration and process processing method of the processing step based on the image data to be analyzed and the temperature data to be analyzed based on artificial intelligence technology includes:

[0044] S31: inputting the image data to be analyzed and the temperature data to be analyzed into a preset first model to perform classification prediction of a processing method to obtain a first vector;

[0045] Treatment methods include treating the whole first, treating the part first and then the whole, and treating the whole and then the part.

[0046] Specifically, the image data to be analyzed and the temperature data to be analyzed are spliced ​​and input into a preset first model for classification prediction of the processing method, and the predicted vector is used as the first vector.

[0047] The preset first model is a pre-trained multi-classification model. The model structure and model training method of the preset first model can be selected from the existing technology and will not be described in detail here.

[0048] S32: taking the classification category corresponding to the element with the largest value in the first vector as the process processing method of the processing step;

[0049] Specifically, the classification category (that is, the processing method) corresponding to the element with the largest value in the first vector is used as the process processing method of the processing step.

[0050] S33: inputting the processing step, the process method of the processing step, the image data to be analyzed and the temperature data to be analyzed into a preset second model for classification prediction of parameter configuration to obtain a second vector;

[0051] Specifically, the processing steps, the process methods of the processing steps, the image data to be analyzed and the temperature data to be analyzed are spliced ​​and input into a preset second model for classification prediction of parameter configuration, and the predicted vector is used as the second vector.

[0052] The preset second model is a pre-trained multi-classification model. The model structure and model training method of the preset second model can be selected from the prior art and will not be described in detail here.

[0053] S34: Using the classification category corresponding to the element with the largest value in the second vector as the step process parameter configuration of the processing step.

[0054] Specifically, the classification category corresponding to the element with the largest value in the second vector is parameter configuration, and the parameter configuration is used as the step process parameter configuration of the processing step.

[0055] In this embodiment, the image data to be analyzed and the temperature data to be analyzed are input into a preset first model for classification prediction of the processing method, and the accuracy of the determined process processing method is improved through the model; the processing steps, the process processing methods of the processing steps, the image data to be analyzed and the temperature data to be analyzed are input into a preset second model for classification prediction of parameter configuration, and multiple factors of the processing steps, the process processing methods of the processing steps, the image data to be analyzed and the temperature data to be analyzed are comprehensively considered, and prediction is performed through the model, thereby improving the accuracy of the determined process processing method; this embodiment provides a basis for ensuring the quality stability of steel parts after phosphating treatment.

[0056] In one embodiment, before the degreasing step of the phosphating process, the method further comprises:

[0057] S011: performing pollutant detection on the surface of the steel part to obtain a pollutant detection result;

[0058] Specifically, the surface of the steel product is tested for pollutants using chemical analyzers, sensors and other testing equipment, and the test data is used as the pollutant test result.

[0059] S012: Based on the pollutant detection result, the surface of the steel part is subjected to a decontamination treatment, and the steel part after the decontamination treatment is used for the degreasing step of the phosphating process.

[0060] Specifically, a decontamination treatment method is determined according to the pollutant detection result, and the surface of the steel part is decontaminated by manual and / or equipment using the determined decontamination treatment method. The steel part after the decontamination treatment does not contain pollutants. Therefore, the steel part after the decontamination treatment is used for the degreasing step of the phosphating process.

[0061] In this embodiment, based on the pollutant detection results, the surface of the steel parts is decontaminated. The steel parts after the decontamination treatment are used in the degreasing step of the phosphating process, thereby avoiding the influence of pollutants on the phosphating treatment of the steel parts using the phosphating process, and further providing data support for ensuring the quality stability of the steel parts after the phosphating treatment.

[0062] In one embodiment, the step of performing a decontamination treatment on the surface of the steel part based on the pollutant detection result, and using the steel part after the decontamination treatment for the degreasing step of the phosphating process comprises:

[0063] S0121: Based on the pollutant detection result, performing a decontamination treatment on the surface of the steel part;

[0064] Specifically, a decontamination treatment method is determined according to the pollutant detection result, and the determined decontamination treatment method is used to perform decontamination treatment on the surface of the steel part.

[0065] S0122: Acquire image data of the surface of the steel product after decontamination treatment as first data;

[0066] Specifically, the image data of the surface of the steel workpiece after the decontamination treatment can be obtained by the user, the image data of the surface of the steel workpiece after the decontamination treatment can be obtained from a preset storage space, and the image data of the surface of the steel workpiece after the decontamination treatment can be obtained from a third-party application.

[0067] It can be understood that the first data is also image data of the surface of the steel workpiece after the decontamination treatment and before the degreasing step of the phosphating process.

[0068] S0123: Based on artificial intelligence technology, according to the first data, performing an appearance qualification analysis on the surface of the steel product after the decontamination treatment to obtain a first analysis result;

[0069] Specifically, the first data is input into a first appearance analysis model corresponding to the steel product to perform classification prediction of qualified appearance, and the classification category corresponding to the element with the largest value in the predicted vector is taken as the first analysis result.

[0070] The first appearance analysis model corresponding to the steel product is a binary classification model. The model structure and model training method of the first appearance analysis model corresponding to the steel product can be selected from the prior art and will not be described in detail here.

[0071] S0124: The steel product with the qualified first analysis result is used in the degreasing step of the phosphating process.

[0072] Specifically, the steel product with a qualified first analysis result is used in the degreasing step of the phosphating process, so that the steel product with a qualified appearance enters the phosphating process.

[0073] It is understandable that the steel product with an unqualified first analysis result cannot enter the phosphating process and therefore cannot be used in the degreasing step of the phosphating process.

[0074] This embodiment is based on artificial intelligence technology. According to the first data, the surface of the steel part after the decontamination treatment is analyzed for appearance qualification, and the accuracy of the analysis is improved by artificial intelligence technology; the steel part with the first analysis result as qualified is used in the degreasing step of the phosphating process, so that the steel part with qualified appearance enters the phosphating process, thereby improving the quality of the product output by the phosphating process.

[0075] In one embodiment, before the oil sealing step of the phosphating process, the method further comprises:

[0076] S41: acquiring image data of the surface of the steel product after the drying step of the phosphating process as second data;

[0077] Specifically, the image data of the surface of the steel workpiece after the drying step of the phosphating process input by the user can be obtained, the image data of the surface of the steel workpiece after the drying step of the phosphating process can be obtained from a preset storage space, and the image data of the surface of the steel workpiece after the drying step of the phosphating process can be obtained from a third-party application.

[0078] It can be understood that the second data is also image data of the surface of the steel workpiece after the drying step of the phosphating process and before the oil sealing step of the phosphating process.

[0079] S42: Based on artificial intelligence technology, according to the second data, performing an appearance qualification analysis on the surface of the steel product after the drying step of the phosphating process to obtain a second analysis result;

[0080] Specifically, the second data is input into a second appearance analysis model corresponding to the steel product to perform classification prediction of qualified appearance, and the classification category corresponding to the element with the largest value in the predicted vector is taken as the second analysis result.

[0081] The second appearance analysis model corresponding to the steel product is a binary classification model. The model structure and model training method of the second appearance analysis model corresponding to the steel product can be selected from the prior art and will not be described in detail here.

[0082] S43: The steel product that is qualified by the second analysis result is used in the oil sealing step of the phosphating process.

[0083] Specifically, the steel parts with qualified first analysis results are used in the degreasing step of the phosphating process, so that the steel parts with qualified appearance enter the oil sealing step.

[0084] It is understandable that the phosphating film of the steel part whose first analysis result is unqualified does not meet the requirements and therefore cannot be used in the oil sealing step of the phosphating process.

[0085] This embodiment is based on artificial intelligence technology. According to the second data, the surface of the steel part after the drying step of the phosphating process is analyzed for appearance qualification, and the accuracy of the analysis is improved by artificial intelligence technology; the steel part with qualified results of the second analysis is used in the oil sealing step of the phosphating process, so that the steel part with qualified appearance enters the oil sealing step of the phosphating process, thereby improving the quality of the product output by the phosphating process.

[0086] The phosphate film must be continuous, uniform, and finely crystallized. The phosphate film should have a consistent color, moderate grain size, strong adhesion, and no loose film, severe dust, scratches, white spots, fingerprints, rust spots, etc. The color of the phosphate film should be light gray to dark gray.

[0087] In one embodiment, the step of performing an appearance qualification analysis on the surface of the steel part after the drying step of the phosphating process based on the artificial intelligence technology and the second data to obtain the second analysis result comprises:

[0088] S421: Acquire image data of the surface of the steel workpiece used in the degreasing step of the phosphating process as third data;

[0089] Specifically, the image data of the surface of the steel workpiece used in the degreasing step of the phosphating process can be obtained by the user, the image data of the surface of the steel workpiece used in the degreasing step of the phosphating process can be obtained from a preset storage space, and the image data of the surface of the steel workpiece used in the degreasing step of the phosphating process can be obtained from a third-party application.

[0090] It can be understood that the third data is also image data of the surface of the steel workpiece before the phosphating process.

[0091] S422: inputting the second data and the third data into a preset uniformity analysis model to perform uniformity prediction of phosphating to obtain a third vector;

[0092] The uniformity of phosphating refers to the uniformity of the thickness of the phosphating film on steel parts.

[0093] Specifically, the second data and the third data are input into a preset uniformity analysis model to predict the uniformity of phosphating, and the predicted vector is used as the third vector. The third data represents the surface data of the steel workpiece entering the phosphating process, and the second data represents the surface data of the steel workpiece after the drying step and before the oil sealing step. The uniformity of phosphating is predicted by comparing the second data and the third data, thereby improving the accuracy of the prediction.

[0094] Optionally, the preset uniformity analysis model is a binary classification model. The model structure and model training method of the preset uniformity analysis model can be selected from the existing technology and will not be described in detail here.

[0095] S423: Determine a uniformity analysis result according to the third vector;

[0096] Specifically, the classification category corresponding to the element with the largest value in the third vector is used as the uniformity analysis result.

[0097] The uniformity analysis result is either qualified or unqualified.

[0098] S424: inputting the second data and the third data into a preset minimum thickness analysis model to predict the minimum thickness of phosphating to obtain a fourth vector;

[0099] Specifically, the second data and the third data are spliced ​​and input into a preset minimum thickness analysis model to predict the minimum thickness of phosphating, and the predicted vector is used as the fourth vector.

[0100] Optionally, the preset minimum thickness analysis model is a multi-classification model. The model structure and model training method of the preset minimum thickness analysis model can be selected from the prior art and will not be described in detail here.

[0101] S425: Determine minimum thickness data according to the fourth vector;

[0102] Specifically, the classification category corresponding to the element with the largest value in the fourth vector (that is, the thickness value of the phosphate film of the steel product) is used as the minimum thickness data.

[0103] S426: inputting the second data and the third data into a preset maximum thickness analysis model to predict the maximum thickness of phosphating to obtain a fifth vector;

[0104] Specifically, the second data and the third data are spliced ​​and input into a preset maximum thickness analysis model to predict the maximum thickness of phosphating, and the predicted vector is used as the fifth vector.

[0105] Optionally, the preset maximum thickness analysis model is a multi-classification model. The model structure and model training method of the preset maximum thickness analysis model can be selected from the prior art and will not be described in detail here.

[0106] S427: Determine maximum thickness data according to the fifth vector;

[0107] Specifically, the classification category corresponding to the element with the largest value in the fifth vector (that is, the thickness value of the phosphate film of the steel product) is used as the maximum thickness data.

[0108] S428: Determine actual color data of the steel product according to the second data;

[0109] Specifically, the second data is input into a preset color detection model to perform color data detection, and the maximum color data and the minimum color data obtained by the detection are used as the actual color data of the steel workpiece.

[0110] Optionally, the preset color detection model is a multi-classification model. The model structure and model training method of the preset color detection model can be selected from the existing technology and will not be described in detail here.

[0111] Each element of the prediction vector output by the preset color detection model corresponds to a classification category, which expresses the corresponding relationship between the prediction type and the prediction value, and the prediction type is maximum or minimum.

[0112] S429: If the minimum thickness data and the maximum thickness data are both within the preset phosphating thickness range, and the uniformity analysis result is qualified, and the actual color data is within the preset color data range, the second analysis result is determined to be qualified;

[0113] Specifically, the minimum thickness data and the maximum thickness data are both within the preset phosphating thickness range, which means that the thickness value of the phosphating film of the steel part meets the requirements; the minimum thickness data and the maximum thickness data are both within the preset phosphating thickness range, and the uniformity analysis result is qualified, and the actual color data is within the preset color data range, which means that the thickness value of the phosphating film meets the requirements, and the uniformity of the thickness of the phosphating film of the steel part meets the requirements, and the color of the phosphating film of the steel part meets the color requirements of the phosphating film, and the phosphating film at this time meets the phosphating film requirements corresponding to the steel part, and therefore, the second analysis result is determined to be qualified.

[0114] Optionally, the preset phosphating thickness range is 10um to 25um.

[0115] S4210: If any one of the minimum thickness data and the maximum thickness data is outside the preset phosphating thickness range, or the uniformity analysis result is unqualified, the second analysis result is determined to be unqualified.

[0116] Specifically, if any one of the minimum thickness data and the maximum thickness data is outside the preset phosphating thickness range, or the uniformity analysis result is unqualified, or the actual color data is outside the preset color data range, it means that the thickness value of the phosphating film does not meet the requirements, or the thickness uniformity of the phosphating film of the steel part does not meet the requirements, or the color of the phosphating film of the steel part does not meet the color requirements of the phosphating film. At this time, the phosphating film of the steel part does not meet the phosphating film requirements corresponding to the steel part.

[0117] This embodiment predicts the uniformity of phosphating, the maximum thickness, the minimum thickness, and the color data by using the surface data of the steel parts entering the phosphating process and the surface data of the steel parts after the drying step and before the oil sealing step, thereby improving the accuracy of the prediction and thus improving the accuracy of the determined second analysis result.

[0118] In one embodiment, the steel part is a part used in oil production, and a surface of the steel part is provided with threads.

[0119] Optionally, the part for oil extraction is a bolt, and a surface of the bolt is provided with threads.

[0120] This embodiment analyzes the data of steel parts processing for parts used in oil extraction scenarios, and the quality stability of the phosphating treatment is beneficial to prolonging the service life of the equipment or facilities used for oil extraction of the steel parts.

[0121] In one embodiment, the various process steps of the phosphating process include, in sequence: a degreasing step, a first water washing step, a pickling step, a second water washing step, a third water washing step, a surface conditioning step, a phosphating step, a fourth water washing step, a hot water washing step, a drying step, and an oil sealing step;

[0122] The standard process parameter configuration of the degreasing step of the phosphating process includes: a cleaning agent parameter, a first temperature parameter and a first duration parameter, wherein the cleaning agent parameters include: a cleaning agent ratio of 5%, a total alkalinity range of 38pt to 45pt, a free alkalinity range of 24pt to 32pt, a pH range of 12 to 14, a first temperature parameter range of 55°C to 60°C, and a first duration parameter range of 15min to 20min;

[0123] The standard process parameter configuration of the first water washing step of the phosphating process includes: a first water washing method and a first water washing parameter, wherein the first water washing method is overflow, and the first water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min;

[0124] The standard process parameter configuration of the pickling step of the phosphating process includes: hydrochloric acid pickling, a ratio of 5% of pickling additive and a second time parameter;

[0125] The standard process parameter configuration of the second water washing step of the phosphating process includes: a second water washing method and a second water washing parameter, the second water washing method is overflow, the second water washing parameter is: the pH value ranges from 6 to 8, the temperature is room temperature, and the treatment time ranges from 1 min to 3 min;

[0126] The standard process parameter configuration of the third water washing step of the phosphating process includes: a third water washing method and a third water washing parameter, wherein the third water washing method is overflow, and the third water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min;

[0127] The standard process parameter configuration of the surface conditioning step of the phosphating process includes: the ratio of the surface conditioning agent is 6‰, the pH value range is 8.5-9, the temperature is room temperature, and the treatment time range is 0.5min-1min;

[0128] The standard process parameter configuration of the phosphating step of the phosphating process includes: a phosphating solution for oilfield casing, a phosphating solution ratio of 14%, a total acidity range of 50pt to 70pt, a free acidity range of 8pt to 13pt, a temperature range of 90°C to 98°C, and a time range of 15 to 20min;

[0129] The standard process parameter configuration of the fourth water washing step of the phosphating process includes: a fourth water washing method and a fourth water washing parameter, wherein the fourth water washing method is overflow, and the fourth water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min;

[0130] The standard process parameter configuration of the hot water washing step of the phosphating process includes: a fifth water washing method and a fifth water washing parameter, wherein the fifth water washing method is overflow, and the fifth water washing parameter is: a pH value range of 6 to 8, a temperature range of 80°C to 90°C, and a treatment time range of 1min to 3min;

[0131] The standard process parameter configuration of the drying step of the phosphating process includes: drying time;

[0132] The standard process parameter configuration of the oil sealing step of the phosphating process includes: dehydrated anti-rust oil, a temperature range of room temperature to 120° C., and a treatment time range of 1 min to 2 min.

[0133] It is understandable that the standard process parameter configuration of the oil sealing step of the phosphating process includes a range. For parameters (e.g., time) with a range in the standard process parameter configuration of the processing step, the values ​​in the step process parameter configuration of the processing step determined by the present application are specific values ​​and sub-ranges of the range in the standard process parameter configuration of the processing step. For example, the range of the processing time in the standard process parameter configuration of the oil sealing step of the phosphating process is 1min to 2min, and the time of the step process parameter configuration of the processing step determined by the present application is 1.5min. For another example, the range of the processing time in the standard process parameter configuration of the oil sealing step of the phosphating process is 1min to 2min, and the time of the step process parameter configuration of the processing step determined by the present application is 1.5min to 2min.

[0134] In this embodiment, pt is a unit.

[0135] In one embodiment, one or more of the third water washing step of the phosphating process, the fourth water washing step of the phosphating process and the hot water washing step of the phosphating process are rinsed with distilled water.

[0136] In the third water washing step of the phosphating process described in this embodiment, the fourth water washing step of the phosphating process and one or more of the hot water washing steps of the phosphating process are rinsed with distilled water, thereby improving the rinsing effect and further providing data support for ensuring the quality stability of steel parts after phosphating treatment.

[0137] In one embodiment, the drying step of the phosphating process is a process step of drying in a vacuum environment or a dust-free environment.

[0138] The drying step of the phosphating process described in this embodiment is a process step in which the drying is performed in a vacuum environment or a dust-free environment, which is beneficial to improving the cleanliness of the surface of the steel parts after the drying step, and is beneficial to ensuring the effect of the oil sealing step, and further provides data support for ensuring the quality stability of the steel parts after the phosphating treatment.

[0139] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0140] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0141] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A data analysis method for the surface treatment process of a steel product, characterized in that: The method is used to analyze process data of a steel product subjected to phosphating treatment using a phosphating process, and the method comprises: Using a process step of the phosphating process as a treatment step; Acquire image data and temperature data of the surface of the steel workpiece after being processed in the process step before the processing step as image data to be analyzed and temperature data to be analyzed; Based on artificial intelligence technology, according to the image data to be analyzed and the temperature data to be analyzed, the process parameter configuration and the process processing method of the processing step are determined, wherein the process processing method is one of full processing, partial processing first and then full processing, and full processing first and then partial processing; The step of determining the process parameter configuration and process processing method of the processing step based on the image data to be analyzed and the temperature data to be analyzed based on artificial intelligence technology includes: Inputting the image data to be analyzed and the temperature data to be analyzed into a preset first model for classification prediction of a processing method to obtain a first vector; Using the classification category corresponding to the element with the largest value in the first vector as the process processing method of the processing step; Input the processing step, the process method of the processing step, the image data to be analyzed, and the temperature data to be analyzed into a preset second model for classification prediction of parameter configuration to obtain a second vector; The classification category corresponding to the element with the largest value in the second vector is used as the step process parameter configuration of the processing step.

2. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: Before the degreasing step of the phosphating process, the method further comprises: Conducting pollutant detection on the surface of the steel product to obtain a pollutant detection result; Based on the pollutant detection result, the surface of the steel part is subjected to a decontamination treatment, and the steel part after the decontamination treatment is used for the degreasing step of the phosphating process.

3. The data analysis method for the surface treatment process of steel parts according to claim 2, characterized in that: The step of performing a decontamination treatment on the surface of the steel part based on the pollutant detection result, and using the steel part after the decontamination treatment for the degreasing step of the phosphating process comprises: Based on the pollutant detection result, performing a decontamination treatment on the surface of the steel part; Acquiring image data of the surface of the steel product after decontamination treatment as first data; Based on artificial intelligence technology, according to the first data, an appearance qualification analysis is performed on the surface of the steel product after the decontamination treatment to obtain a first analysis result; The steel product with a qualified first analysis result is used in the degreasing step of the phosphating process.

4. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: Before the oil sealing step of the phosphating process, the method further comprises: Acquiring image data of the surface of the steel product after the drying step of the phosphating process as second data; Based on artificial intelligence technology, according to the second data, an appearance qualification analysis is performed on the surface of the steel product after the drying step of the phosphating process to obtain a second analysis result; The steel product with a qualified second analysis result is used in the oil sealing step of the phosphating process.

5. The data analysis method for the surface treatment process of steel parts according to claim 4, characterized in that: The step of performing an appearance qualification analysis on the surface of the steel product after the drying step of the phosphating process based on the artificial intelligence technology and the second data to obtain a second analysis result comprises: acquiring image data of the surface of the steel workpiece used in the degreasing step of the phosphating process as third data; Inputting the second data and the third data into a preset uniformity analysis model to predict the uniformity of phosphating to obtain a third vector; Determining a uniformity analysis result according to the third vector; Inputting the second data and the third data into a preset minimum thickness analysis model to predict the minimum thickness of phosphating to obtain a fourth vector; Determining minimum thickness data according to the fourth vector; Inputting the second data and the third data into a preset maximum thickness analysis model to predict the maximum thickness of phosphating to obtain a fifth vector; Determining maximum thickness data according to the fifth vector; Determining actual color data of the steel workpiece according to the second data; If the minimum thickness data and the maximum thickness data are both within the preset phosphating thickness range, and the uniformity analysis result is qualified, and the actual color data is within the preset color data range, the second analysis result is determined to be qualified; If any one of the minimum thickness data and the maximum thickness data is outside the preset phosphating thickness range, or the uniformity analysis result is unqualified, or the actual color data is outside the preset color data range, the second analysis result is determined to be unqualified.

6. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: The steel part is used in oil extraction, and a thread is arranged on the surface of the steel part.

7. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: The various process steps of the phosphating process include: a degreasing step, a first water washing step, a pickling step, a second water washing step, a third water washing step, a surface conditioning step, a phosphating step, a fourth water washing step, a hot water washing step, a drying step and an oil sealing step; The standard process parameter configuration of the degreasing step of the phosphating process includes: a cleaning agent parameter, a first temperature parameter and a first duration parameter, wherein the cleaning agent parameters include: a cleaning agent ratio of 5%, a total alkalinity range of 38pt to 45pt, a free alkalinity range of 24pt to 32pt, a pH range of 12 to 14, a first temperature parameter range of 55°C to 60°C, and a first duration parameter range of 15min to 20min; The standard process parameter configuration of the first water washing step of the phosphating process includes: a first water washing method and a first water washing parameter, wherein the first water washing method is overflow, and the first water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min; The standard process parameter configuration of the pickling step of the phosphating process includes: hydrochloric acid pickling, a ratio of 5% of pickling additive and a second time parameter; The standard process parameter configuration of the second water washing step of the phosphating process includes: a second water washing method and a second water washing parameter, the second water washing method is overflow, the second water washing parameter is: the pH value ranges from 6 to 8, the temperature is room temperature, and the treatment time ranges from 1 min to 3 min; The standard process parameter configuration of the third water washing step of the phosphating process includes: a third water washing method and a third water washing parameter, wherein the third water washing method is overflow, and the third water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min; The standard process parameter configuration of the surface conditioning step of the phosphating process includes: the ratio of the surface conditioning agent is 6‰, the pH value range is 8.5-9, the temperature is room temperature, and the treatment time range is 0.5min-1min; The standard process parameter configuration of the phosphating step of the phosphating process includes: a phosphating solution for oilfield casing, a phosphating solution ratio of 14%, a total acidity range of 50pt to 70pt, a free acidity range of 8pt to 13pt, a temperature range of 90°C to 98°C, and a time range of 15 to 20min; The standard process parameter configuration of the fourth water washing step of the phosphating process includes: a fourth water washing method and a fourth water washing parameter, wherein the fourth water washing method is overflow, and the fourth water washing parameter is: a pH value range of 6 to 8, a temperature of room temperature, and a treatment time range of 1 min to 3 min; The standard process parameter configuration of the hot water washing step of the phosphating process includes: a fifth water washing method and a fifth water washing parameter, wherein the fifth water washing method is overflow, and the fifth water washing parameter is: a pH value range of 6 to 8, a temperature range of 80°C to 90°C, and a treatment time range of 1min to 3min; The standard process parameter configuration of the drying step of the phosphating process includes: drying time; The standard process parameter configuration of the oil sealing step of the phosphating process includes: dehydrated anti-rust oil, a temperature range of room temperature to 120° C., and a treatment time range of 1 min to 2 min.

8. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: One or more of the third water washing step of the phosphating process, the fourth water washing step of the phosphating process and the hot water washing step of the phosphating process are rinsed with distilled water.

9. The data analysis method for the surface treatment process of steel parts according to claim 1, characterized in that: The drying step of the phosphating process is a process step of drying in a vacuum environment or a dust-free environment.

Images