Sampling measurement method and device in drilling machine assembly production process
By constructing a simulation measurement model and a risk assessment model, the defect risk of drilling rig components is predicted, which solves the problems of slow defect detection speed and limited resources in the existing technology, and accurately sampling and measurement are achieved, and production efficiency and yield management are improved.
Patent Information
- Application Number
- CN202311052289.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-21
- Publication Date
- 2025-02-21
AI Technical Summary
The defect detection speed in the production process of existing drilling rig components is slow, requiring additional labor and equipment costs. Due to limited testing resources, problems are easily missed, affecting yield management.
By constructing simulation measurement models and risk assessment models, the defect risks of target components are predicted and accurate sampling and measurement are achieved. The specific steps include collecting key data from the target component, inputting it into the pre-trained simulation measurement model and risk assessment model, determining the measurement predicted value and target risk assessment results, deciding whether to perform sampling measurements, and updating model parameters.
While ensuring product yield goals, it has achieved the goal of reducing product production cycles, improving production efficiency and reducing invalid measurements.
Smart Images
Figure CN119494254A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sampling and measurement, and in particular to a sampling and measurement method and device in the production process of drilling rig components. Background Art
[0002] The production process of drilling rigs requires a lot of spare parts, and the quality of spare parts directly determines the overall quality of the drilling rig. Continuously conducting defect detection of parts during the production process is an important means to improve the yield rate of drilling rigs. Only by exposing as many defects of drilling rig parts as possible and as timely as possible can the time and difficulty of solving yield problems be shortened. Otherwise, it will be very difficult to track down after the final production is completed.
[0003] Defect detection in the production process of drilling rig components is a common practice based on this concept. However, compared with production, defect detection is slow and requires additional manpower and equipment costs. In this case, it is time-consuming and labor-intensive to detect defects in all products. Therefore, sampling is generally used in the industry for defect detection. The setting of the sampling rate depends on the number of detection equipment in the factory and the judgment of the frequency of defects at the target detection site.
[0004] At present, the current sampling strategy for drilling rig parts is to use static sampling by personnel, that is, to conduct random sampling inspection on product batch numbers. However, due to limited inspection resources, such inspection methods will inevitably cause a large number of problems to be missed, which will have a relatively large impact on the yield management of drilling rig parts. Summary of the invention
[0005] In view of this, the purpose of this application is to provide a sampling and measurement method and device in the production process of drilling rig components. By constructing a simulation measurement model and a risk assessment model, the defect risk of the target component is predicted, thereby achieving accurate sampling and measurement, thereby reducing the product production cycle and improving production efficiency while ensuring that the predetermined product yield target is achieved.
[0006] The present application embodiment provides a sampling and measuring method in a drilling rig component production process, the sampling and measuring method comprising:
[0007] For each target component in the drilling rig, collect key data generated during the processing of the target component;
[0008] Inputting the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine the measurement prediction value of the target component;
[0009] The measurement prediction value of the target component and the predetermined target measurement equipment related data are input into a pre-trained risk assessment model corresponding to the target component to determine the target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether sampling measurement of the target component is required.
[0010] Optionally, when it is determined that sampling and measurement of the target component is required according to the target risk assessment result of the target component, the sampling and measurement method further includes:
[0011] Sending the target risk assessment result of the target component to the target user and obtaining the actual measurement value of the target component;
[0012] The actual measurement value of the target component is used to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component.
[0013] Optionally, a simulation measurement model corresponding to the target component is constructed by the following steps:
[0014] Acquire historical production data and actual measurement values during the processing of a sample component; wherein the sample component and the target component are of the same model or type;
[0015] Using a machine learning algorithm, model training is performed based on the historical production data and actual measurement values to obtain an initial simulation measurement model;
[0016] Determine whether the initial simulation measurement model meets the index requirements according to the preset evaluation index;
[0017] If not, continue to use the historical production data and actual measurement values to adjust and optimize the model parameters of the initial simulation measurement model until the index requirements of the preset evaluation index are met, and obtain the simulation measurement model corresponding to the target component.
[0018] Optionally, build a risk assessment model corresponding to the target component through the following steps:
[0019] Acquire measurement data of a sample component, data related to defect risk of a target measurement device, and a real risk label; the target measurement device is a device for measuring the target component;
[0020] Inputting the measurement data of the sample component and data related to the defect risk of the target measurement equipment into the initial risk assessment model to obtain a risk prediction label;
[0021] Compare the risk prediction label with the true risk label to determine the target loss function value;
[0022] Based on the target loss function value, the initial risk assessment model is iteratively trained and the model parameters of the initial risk assessment model are updated until the target loss function value converges, and the training is stopped to obtain the risk assessment model corresponding to the target component.
[0023] Optionally, the collecting of key data generated during the processing of the target component includes: collecting production data of key process steps during the processing of the target component; wherein the key process steps are pre-specified process steps that have an impact on the final product quality of the target component during the processing.
[0024] Optionally, the key data includes: component data and equipment data involved in processing the target component.
[0025] The present application also provides a sampling and measuring device in the production process of a drilling rig component, the sampling and measuring device comprising:
[0026] A collection module, for collecting key data generated during the processing of each target component in the drilling rig;
[0027] A first determination module is used to input the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component;
[0028] The second determination module is used to input the measurement prediction value of the target component and the predetermined target measurement equipment related data into a pre-trained risk assessment model corresponding to the target component to determine the target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether it is necessary to sample and measure the target component.
[0029] Optionally, the sampling and measuring device further includes an updating module, wherein the updating module is used to:
[0030] When it is determined that sampling measurement of the target component is required according to the target risk assessment result of the target component, the target risk assessment result of the target component is sent to the target user, and an actual measurement value of the target component is obtained;
[0031] The actual measurement value of the target component is used to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component.
[0032] Optionally, the sampling and measuring device further comprises a first building module, wherein the first building module is used for:
[0033] Acquire historical production data and actual measurement values during the processing of a sample component; wherein the sample component and the target component are of the same model or type;
[0034] Using a machine learning algorithm, model training is performed based on the historical production data and actual measurement values to obtain an initial simulation measurement model;
[0035] Determine whether the initial simulation measurement model meets the index requirements according to the preset evaluation index;
[0036] If not, continue to use the historical production data and actual measurement values to adjust and optimize the model parameters of the initial simulation measurement model until the index requirements of the preset evaluation index are met, and obtain the simulation measurement model corresponding to the target component.
[0037] Optionally, the sampling and measuring device further comprises a second building block, wherein the second building block is used for:
[0038] Acquire measurement data of a sample component, data related to defect risk of a target measurement device, and a real risk label; the target measurement device is a device for measuring the target component;
[0039] Inputting the measurement data of the sample component and data related to the defect risk of the target measurement equipment into the initial risk assessment model to obtain a risk prediction label;
[0040] Compare the risk prediction label with the true risk label to determine the target loss function value;
[0041] Based on the target loss function value, the initial risk assessment model is iteratively trained and the model parameters of the initial risk assessment model are updated until the target loss function value converges, and the training is stopped to obtain the risk assessment model corresponding to the target component.
[0042] Optionally, the collecting of key data generated during the processing of the target component includes: collecting production data of key process steps during the processing of the target component; wherein the key process steps are pre-specified process steps that have an impact on the final product quality of the target component during the processing.
[0043] Optionally, the key data includes: component data and equipment data involved in processing the target component.
[0044] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the sampling measurement method as described above are performed.
[0045] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the sampling and measurement method described above are executed.
[0046] A sampling measurement method and device for a drilling component production process provided in an embodiment of the present application include: for each target component in the drilling rig, collecting key data generated during the processing of the target component; inputting the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component; inputting the measurement prediction value of the target component and pre-determined target measurement equipment-related data into a pre-trained risk assessment model corresponding to the target component to determine a target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether sampling measurement of the target component is required.
[0047] In this way, through the technical solution provided by this application, by constructing a simulation measurement model and a risk assessment model, the defect risk of the target component is predicted, thereby achieving accurate sampling measurement and real-time determination of component defects, thereby reducing the product production cycle, improving production efficiency and reducing invalid measurements while ensuring that the predetermined product yield target is achieved.
[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 A flow chart of a sampling and measuring method in a drilling rig component production process provided by an embodiment of the present application;
[0051] Figure 2 One of the structural schematic diagrams of a sampling and measuring device in a drilling rig component production process provided by an embodiment of the present application;
[0052] Figure 3 A second structural schematic diagram of a sampling and measuring device in a drilling rig component production process provided by an embodiment of the present application;
[0053] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0054] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the 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 components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.
[0055] The production process of drilling rigs requires a lot of spare parts, and the quality of spare parts directly determines the overall quality of the drilling rig. Continuously conducting defect detection of parts during the production process is an important means to improve the yield rate of drilling rigs. Only by exposing as many defects of drilling rig parts as possible and as timely as possible can the time and difficulty of solving yield problems be shortened. Otherwise, it will be very difficult to track down after the final production is completed.
[0056] Defect detection in the production process of drilling rig components is a common practice based on this concept. However, compared with production, defect detection is slow and requires additional manpower and equipment costs. In this case, it is time-consuming and labor-intensive to detect defects in all products. Therefore, sampling is generally used in the industry for defect detection. The setting of the sampling rate depends on the number of detection equipment in the factory and the judgment of the frequency of defects at the target detection site.
[0057] At present, the current sampling strategy for drilling rig parts is to use static sampling by personnel, that is, to conduct random sampling inspection on product batch numbers. However, due to limited inspection resources, such inspection methods will inevitably cause a large number of problems to be missed, which will have a relatively large impact on the yield management of drilling rig parts.
[0058] Based on this, an embodiment of the present application provides a sampling and measurement method and device in the production process of drilling rig components. By constructing a simulation measurement model and a risk assessment model, the defect risk of the target component is predicted, thereby achieving accurate sampling and measurement, thereby reducing the product production cycle and improving production efficiency while ensuring that the predetermined product yield target is achieved.
[0059] See also Figure 1 , Figure 1 This is a flow chart of a sampling and measuring method in the production process of a drilling rig component provided in an embodiment of the present application. Figure 1 As shown in , the sampling measurement method provided by the embodiment of the present application includes:
[0060] S101. For each target component in the drilling rig, collect key data generated during the processing of the target component.
[0061] Here, the drilling rig includes a plurality of components, and a component may be a part, or a combination of one or several assemblies and several parts.
[0062] In one embodiment provided in the present application, the collecting of key data generated during the processing of the target component includes: collecting production data of key process steps during the processing of the target component; wherein the key process steps are pre-specified process steps that have an impact on the final product quality of the target component during the processing, and the key data include: component data and equipment data involved in the processing of the target component.
[0063] For example, the key data may include basic parameters of the component, temperature, pressure, speed, vacuum, gas flow, fault code, fault time, etc. The key data is selected based on whether it will affect the quality of the final product of the component.
[0064] When collecting key data, the key data generated during the processing of the target component can be collected in a high-frequency manner.
[0065] For example, data is collected by collecting data at each data point 10 times per second. This high-frequency data collection can restore the real-time status of the component during the processing process for subsequent data analysis and prediction.
[0066] S102: Input the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component.
[0067] Here, the simulation measurement model is used to determine a prediction model for finished product data based on production process data of the target component.
[0068] The simulation measurement model may be a model used only for measuring one component, or may be a model used for measuring all components in the drilling rig.
[0069] In one implementation provided in the present application, a simulation measurement model corresponding to the target component is constructed by the following steps:
[0070] S201. Obtain historical production data and actual measurement values during the processing of a sample component.
[0071] S202: Using a machine learning algorithm, perform model training based on the historical production data and actual measurement values to obtain an initial simulation measurement model.
[0072] S203: Determine whether the initial simulation measurement model meets the index requirement according to the preset evaluation index.
[0073] S204: If not, continue to use the historical production data and actual measurement values to adjust and optimize the model parameters of the initial simulation measurement model until the index requirements of the preset evaluation index are met, thereby obtaining a simulation measurement model corresponding to the target component.
[0074] In this embodiment, the constructed simulation measurement model is only used to measure the model of one component.
[0075] For step S201, the sample component and the target component are of the same model or type.
[0076] For example, when the target component is a drill bit of type A, the sample component is also a drill bit of type A.
[0077] The historical production data in step S201 is data that has been processed by data preprocessing and feature selection, including cleaning, denoising, missing value filling, data smoothing and other preprocessing operations to ensure the accuracy and availability of the data.
[0078] Feature selection is to extract and select features from data based on the characteristics of the technical problem to be solved and domain knowledge. These feature values are usually numerical data used to describe the characteristics and attributes of the target measurement. The data retained after feature selection is consistent with the type of key data mentioned above.
[0079] For step S203, the evaluation index may be: accuracy, precision, recall, etc. The index requirement is a preset threshold of the evaluation index.
[0080] When it is determined that the index requirement is met, the initial simulation measurement model can be directly determined as the simulation measurement model corresponding to the target component.
[0081] S103: Input the measurement prediction value of the target component and predetermined target measurement equipment related data into a pre-trained risk assessment model corresponding to the target component to determine a target risk assessment result of the target component.
[0082] Here, the target risk assessment result is used to determine whether sampling measurement of the target component is required.
[0083] The target measurement equipment related data may include non-process data, component sampling factors, component safety model output data, and risk elimination model output data, etc. The non-process data may include: recipe data, alarm data, position change data, PiRun data, retention data, etc.
[0084] Recipe data is a device recipe, device program, or process recipe. It is a file used by the device. The file contains a series of processing steps and process parameters to guide the operation of the device and implement specific process operations.
[0085] PiRun generally refers to when you are adjusting a process formula and you don’t know what changes it will bring, you will first do an experiment with a non-product and collect data to see if there is a significant impact. If not, you will then use the product to do it. This process is called PiRun.
[0086] In one embodiment provided in the present application, a risk assessment model corresponding to the target component is constructed by the following steps:
[0087] S301, obtaining measurement data of a sample component, data related to a defect risk of a target measurement device, and a real risk label.
[0088] S302: Input the measurement data of the sample component and the data related to the defect risk of the target measurement equipment into an initial risk assessment model to obtain a risk prediction label.
[0089] S303: Compare the risk prediction label with the true risk label to determine a target loss function value.
[0090] S304. Based on the target loss function value, the initial risk assessment model is iteratively trained and the model parameters of the initial risk assessment model are updated until the target loss function value converges, and the training is stopped to obtain the risk assessment model corresponding to the target component.
[0091] In this implementation, the constructed risk assessment model is only used to predict the model of one type of component of the target component.
[0092] For step S301, the target measurement device is a device for measuring the target component.
[0093] The data related to the defect risk of the target measurement equipment acquired in step S301 is data that has undergone data preprocessing and feature selection processing.
[0094] The data preprocessing includes cleaning, denoising, standardization and other preprocessing operations to ensure the quality and availability of the data, which may include processing missing values, outliers, etc.
[0095] Feature selection is the process of extracting and selecting features from data based on the characteristics of the technical problem to be solved and domain knowledge. For example, if the difference between the previous and next values of time series data is OOC (Out of Control) or OOS (Out of Spec), it is selected as the feature value.
[0096] The target loss function value in step S303 may be determined according to the risk factor, and the calculation of the risk factor may be derived from the weighted average of each characteristic value.
[0097] In another embodiment provided in the present application, when it is determined that a sampling measurement of the target component is required based on the target risk assessment result of the target component, the sampling measurement method also includes: sending the target risk assessment result of the target component to the target user, and obtaining the actual measurement value of the target component; and using the actual measurement value of the target component to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component respectively.
[0098] Here, the actual measurement value obtained is data obtained by actually measuring the target component through the target measurement device.
[0099] A sampling and measurement method for a drilling component production process provided in an embodiment of the present application includes: for each target component in the drilling rig, collecting key data generated during the processing of the target component; inputting the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component; inputting the measurement prediction value of the target component and pre-determined target measurement equipment-related data into a pre-trained risk assessment model corresponding to the target component to determine a target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether sampling measurement of the target component is required.
[0100] In this way, through the technical solution provided by this application, by constructing a simulation measurement model and a risk assessment model, the defect risk of the target component is predicted, thereby achieving accurate sampling measurement and real-time determination of component defects, thereby reducing the product production cycle, improving production efficiency and reducing invalid measurements while ensuring that the predetermined product yield target is achieved.
[0101] See also Figure 2 , Figure 3 , Figure 2 This is one of the structural schematic diagrams of a sampling and measuring device in the production process of a drilling rig component provided in an embodiment of the present application. Figure 3 This is a second structural diagram of a sampling and measuring device in the production process of a drilling rig component provided in an embodiment of the present application. Figure 2As shown in , the sampling and measuring device 200 comprises:
[0102] The collection module 210 is used to collect key data generated during the processing of each target component in the drilling rig;
[0103] A first determination module 220 is used to input the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component;
[0104] The second determination module 230 is used to input the measurement prediction value of the target component and the predetermined target measurement equipment related data into a pre-trained risk assessment model corresponding to the target component to determine the target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether it is necessary to perform sampling measurement on the target component.
[0105] Optional, such as Figure 3 As shown, the sampling and measuring device 200 further includes an updating module 240, and the updating module 240 is used to:
[0106] When it is determined that sampling measurement of the target component is required according to the target risk assessment result of the target component, the target risk assessment result of the target component is sent to the target user, and an actual measurement value of the target component is obtained;
[0107] The actual measurement value of the target component is used to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component.
[0108] Optionally, the sampling and measuring device 200 further includes a first building module 250, and the first building module 250 is used to:
[0109] Acquire historical production data and actual measurement values during the processing of a sample component; wherein the sample component and the target component are of the same model or type;
[0110] Using a machine learning algorithm, model training is performed based on the historical production data and actual measurement values to obtain an initial simulation measurement model;
[0111] Determine whether the initial simulation measurement model meets the index requirements according to the preset evaluation index;
[0112] If not, continue to use the historical production data and actual measurement values to adjust and optimize the model parameters of the initial simulation measurement model until the index requirements of the preset evaluation index are met, and obtain the simulation measurement model corresponding to the target component.
[0113] Optionally, the sampling and measuring device 200 further includes a second building module 260, and the second building module 260 is used to:
[0114] Acquire measurement data of a sample component, data related to defect risk of a target measurement device, and a real risk label; the target measurement device is a device for measuring the target component;
[0115] Inputting the measurement data of the sample component and data related to the defect risk of the target measurement equipment into the initial risk assessment model to obtain a risk prediction label;
[0116] Compare the risk prediction label with the true risk label to determine the target loss function value;
[0117] Based on the target loss function value, the initial risk assessment model is iteratively trained and the model parameters of the initial risk assessment model are updated until the target loss function value converges, and the training is stopped to obtain the risk assessment model corresponding to the target component.
[0118] Optionally, the collecting of key data generated during the processing of the target component includes: collecting production data of key process steps during the processing of the target component; wherein the key process steps are pre-specified process steps that have an impact on the final product quality of the target component during the processing.
[0119] Optionally, the key data includes: component data and equipment data involved in processing the target component.
[0120] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .
[0121] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 For the steps of the sampling and measuring method in the method embodiment shown, the specific implementation method can be found in the method embodiment, which will not be repeated here.
[0122] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1For the steps of the sampling and measuring method in the method embodiment shown, the specific implementation method can be found in the method embodiment, which will not be repeated here.
[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0124] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0128] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A sampling and measuring method in the production process of drilling rig components, characterized in that: The sampling and measuring method comprises: For each target component in the drilling rig, collect key data generated during the processing of the target component; Inputting the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine the measurement prediction value of the target component; The measurement prediction value of the target component and the predetermined target measurement equipment related data are input into a pre-trained risk assessment model corresponding to the target component to determine the target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether sampling measurement of the target component is required.
2. The sampling and measuring method according to claim 1, characterized in that: When it is determined according to the target risk assessment result of the target component that sampling measurement of the target component is required, the sampling measurement method further comprises: Sending the target risk assessment result of the target component to the target user and obtaining the actual measurement value of the target component; The actual measurement value of the target component is used to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component.
3. The sampling measurement method according to claim 1, characterized in that: Build the simulation measurement model corresponding to the target component through the following steps: Acquire historical production data and actual measurement values during the processing of a sample component; wherein the sample component and the target component are of the same model or type; Using a machine learning algorithm, model training is performed based on the historical production data and actual measurement values to obtain an initial simulation measurement model; Determine whether the initial simulation measurement model meets the index requirements according to the preset evaluation index; If not, continue to use the historical production data and actual measurement values to adjust and optimize the model parameters of the initial simulation measurement model until the index requirements of the preset evaluation index are met, and obtain the simulation measurement model corresponding to the target component.
4. The sampling measurement method according to claim 1, characterized in that: The risk assessment model corresponding to the target component is constructed through the following steps: Acquire measurement data of a sample component, data related to defect risk of a target measurement device, and a real risk label; the target measurement device is a device for measuring the target component; Inputting the measurement data of the sample component and data related to the defect risk of the target measurement equipment into the initial risk assessment model to obtain a risk prediction label; Compare the risk prediction label with the true risk label to determine the target loss function value; Based on the target loss function value, the initial risk assessment model is iteratively trained and the model parameters of the initial risk assessment model are updated until the target loss function value converges, and the training is stopped to obtain the risk assessment model corresponding to the target component.
5. The sampling and measuring method according to claim 1, characterized in that: The collecting of key data generated during the processing of the target component includes: collecting production data of key process steps during the processing of the target component; wherein the key process steps are pre-specified process steps that have an impact on the final product quality of the target component during the processing.
6. The sampling and measuring method according to claim 5, characterized in that: The key data includes: component data and equipment data involved in processing the target component.
7. A sampling and measuring device in the production process of drilling rig components, characterized in that: The sampling and measuring device comprises: A collection module, for collecting key data generated during the processing of each target component in the drilling rig; A first determination module is used to input the collected key data of the target component into a pre-trained simulation measurement model corresponding to the target component to determine a measurement prediction value of the target component; The second determination module is used to input the measurement prediction value of the target component and the predetermined target measurement equipment related data into a pre-trained risk assessment model corresponding to the target component to determine the target risk assessment result of the target component; wherein the target risk assessment result is used to determine whether it is necessary to sample and measure the target component.
8. The sampling and measuring device according to claim 7, characterized in that: The sampling and measuring device further comprises an updating module, wherein the updating module is used for: When it is determined that sampling measurement of the target component is required according to the target risk assessment result of the target component, the target risk assessment result of the target component is sent to the target user, and an actual measurement value of the target component is obtained; The actual measurement value of the target component is used to update the model parameters of the simulation measurement model and the risk assessment model corresponding to the target component.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the sampling measurement method as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the sampling and measuring method according to any one of claims 1 to 6 are executed.