A stone carving task management and control system based on the Internet of Things

Abstract

The present invention discloses a stone carving task management and control system based on the Internet of Things, which involves task management and control technology and is used to improve the problems of abnormal tool vibration and carving trajectory deviation that are prone to occur during the carving process. By detecting internal cracks and bubbles before rough carving of the stone, the crack volume and bubble volume are obtained, and the material defect value is generated; at the same time, the use time of the rough carving tool is collected, the tool vibration is monitored and processed, and the tool wear is evaluated to generate a wear assessment result. The material defect value and the tool wear assessment are combined to analyze the hidden danger characteristics of rough carving and improve the processing quality and stability. The fine carving time is obtained, and the hidden danger characteristics are combined to determine whether to add a secondary fine carving task; if added, the secondary fine carving feedback data is collected and its effect is evaluated. This method effectively improves the carving quality and processing efficiency, reduces waste loss, and enhances the level of intelligent processing.

Description

Technical Field

[0001] The present invention relates to the technical field of task management and control, and more specifically, to a stone carving task management and control system based on the Internet of Things. Background Art

[0002] Traditional stone carving typically employs a two-stage process strategy of rough carving and fine carving to improve efficiency and quality. The rough carving stage primarily removes the rough outline of the original stone, while the fine carving stage is used to restore details and surface treatment. However, in practice, natural defects in the stone (such as cracks and bubbles) often create unforeseen damage risks during the carving process. This is especially true during the rough carving stage, where failure to accurately identify structural defects within the stone can easily lead to material breakage or carving failure.

[0003] Currently, rough carving tools experience significant wear under high-intensity operations, and the degree of tool wear directly affects the surface quality and equipment stability of the carving. Existing technologies often rely on manual experience to assess tool life, lacking real-time monitoring and intelligent analysis of tool vibration. This can lead to problems such as abnormal tool vibration and engraving trajectory deviation during the carving process. Therefore, a stone carving task management and control system based on the Internet of Things (IoT) was proposed. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a stone carving task management and control system based on the Internet of Things, which solves the problems raised in the above-mentioned background technology through the collaborative operation of multi-source data collection, state assessment modeling and intelligent task scheduling modules.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An Internet of Things-based stone carving task management and control system, including a defect detection module, a rough carving wear module, a hidden danger analysis module, and a secondary fine carving module;

[0007] The defect detection module is used to detect internal cracks and bubbles in the carving stone before rough carving, obtain the crack volume and bubble volume of the carving stone and generate the material defect value of the carving stone;

[0008] The rough carving wear module is used to collect the tool usage time of the rough carving tool, monitor the tool engraving vibration of the rough carving tool and process it, evaluate the tool wear of the rough carving tool based on the tool usage time and generate a wear assessment result;

[0009] The hidden danger analysis module is used to analyze the hidden danger characteristics of the rough carving by comprehensively considering the material defect value of the carving stone and the wear assessment results of the rough carving tool. It also obtains the duration of the fine carving and decides whether to add a secondary fine carving task based on the hidden danger characteristics of the rough carving.

[0010] The secondary fine carving module is used to collect feedback data after the secondary fine carving of the carved stone when a secondary fine carving task is added, and evaluate the effect of the secondary fine carving task based on the feedback data.

[0011] In a preferred embodiment, the crack volume and the bubble volume are respectively the sum of all crack volumes and the sum of bubble volumes inside the carving stone;

[0012] The material defect value of the carving stone is generated by using a neural network algorithm according to the crack volume and bubble volume of the carving stone.

[0013] In a preferred embodiment, when a neural network algorithm is used to generate the material defect value of the engraving stone, the calculation is performed using the neural network algorithm formula: , where w is the influencing factor adjustment parameter, which is used to adjust the crack volume of the carved stone so that it reaches the same dimension as the bubble volume, l is the crack volume of the carved stone, q is the bubble volume of the carved stone, a is the material defect value of the carved stone, and f is the neural network function relationship between l and q and a respectively.

[0014] In a preferred embodiment, when the stone material being carved enters the rough carving stage, information about the rough carving tool currently being used to carve the stone material is called, including the tool usage time of the rough carving tool. During the rough carving process of the stone material, the carving vibration of the rough carving tool is monitored in real time and compared with a preset vibration threshold.

[0015] If the tool engraving vibration of the rough engraving tool exceeds a preset vibration threshold, it is determined that the rough engraving tool has an abnormal vibration phenomenon and the engraving vibration value thereof is used as the tool engraving vibration abnormality value of the rough engraving tool;

[0016] After the rough carving stage is completed, the average value of the tool engraving vibration anomaly of the rough carving tool in the rough carving stage is calculated. The logarithmic normalization algorithm is used to standardize the average value of the tool engraving vibration anomaly of the rough carving tool and the tool usage time, and then the maximum value is selected as the wear assessment result b of the rough carving tool.

[0017] In a preferred embodiment, the material defect value of the carving stone and the wear assessment result of the rough carving tool are standardized and substituted into the logistic regression formula to calculate the hidden danger characteristics of the rough carving. The specific formula is expressed as follows:

[0018] ;

[0019] Where L is the result of logistic regression calculation, that is, the hidden danger characteristics of the rough carving, e is the natural base, and y is the linear combination term of the logistic regression model. The specific setting of y is:

[0020] ;

[0021] Where, is the bias term, is the material defect value of the carving stone, This is the wear evaluation result of the rough engraving tool. as well as are the regression coefficients of the material defect value of the engraving stone and the wear evaluation results of the rough engraving tool;

[0022] After the first round of fine carving is completed, the duration of the fine carving is obtained.

[0023] In a preferred embodiment, the system timestamp is recorded at the start and end of fine carving respectively, and the difference between the fine carving end timestamp and the fine carving start timestamp is calculated to obtain the fine carving duration of the current time;

[0024] Substitute the time of fine carving and the hidden danger characteristics of rough carving into the principal component discriminant analysis model to obtain the added fine carving coefficient. The implementation steps are as follows:

[0025] A1: Standardize the hidden danger characteristics of the original input variables, namely, the fine carving time and the rough carving time;

[0026] A2: Construct a sample matrix and perform principal component analysis;

[0027] A3: Linear discriminant analysis is performed to obtain the additional carving coefficient.

[0028] In a preferred embodiment, the added fine carving coefficient is compared with a preset fine carving threshold. If the added fine carving coefficient is greater than or equal to the fine carving threshold, a secondary fine carving task needs to be added. If the added fine carving coefficient is less than the fine carving threshold, no fine carving needs to be added.

[0029] A secondary fine carving task is added based on the judgment result. When the secondary fine carving task is added, feedback data is collected after the carving stone is finely carved for the second time.

[0030] In a preferred embodiment, the feedback data includes the amount of cutting waste and surface finish;

[0031] The total amount of waste generated by cutting during the processing is monitored in real time by a weighing sensor installed on the engraving equipment. The difference in waste data between the start and end of cutting is recorded to obtain the amount of cutting waste.

[0032] A non-contact surface roughness measuring instrument is used to sample the surface of the stone after carving to obtain surface height data. The surface roughness is calculated and the surface finish is obtained using the inverse form of the surface roughness.

[0033] In a preferred embodiment, the amount of cutting waste and surface finish are standardized and substituted into a polynomial model to obtain a secondary fine carving evaluation coefficient.

[0034] In a preferred embodiment, the secondary fine carving evaluation coefficient is compared with a preset fine carving evaluation threshold. If the secondary fine carving evaluation coefficient is greater than or equal to the fine carving evaluation threshold, the secondary fine carving effect is evaluated as efficient. If the secondary fine carving evaluation coefficient is less than the fine carving evaluation threshold, the secondary fine carving effect is evaluated as inefficient.

[0035] The technical effects and advantages of the stone carving task management and control system based on the Internet of Things of the present invention are as follows:

[0036] The present invention detects internal cracks and bubbles in the carving stone before rough carving, obtains the crack volume and bubble volume of the stone and generates a material defect value of the carving stone, collects the tool usage time of the rough carving tool, monitors the tool carving vibration of the rough carving tool at that time and processes it, evaluates the tool wear of the rough carving tool to generate a wear evaluation result, comprehensively analyzes the hidden danger characteristics of the rough carving at that time by combining the material defect value of the carving stone and the wear evaluation result of the rough carving tool, improves the processing quality and stability, obtains the fine carving time at that time and selects whether to add a secondary fine carving task based on the hidden danger characteristics of the rough carving at that time, and when adding the secondary fine carving task, collects feedback data after the secondary fine carving, and evaluates the effect of the secondary fine carving task based on the feedback data, thereby improving the carving efficiency of the stone carving task. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of the stone carving task management and control system based on the Internet of Things in the present invention.

[0038] Figure 2 This is a schematic diagram of a stone carving task management and control system based on the Internet of Things in the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] The present invention detects internal cracks and bubbles in the carving stone before rough carving, obtains the crack volume and bubble volume of the stone and generates a material defect value of the carving stone, collects the tool usage time of the rough carving tool, monitors the tool carving vibration of the rough carving tool and processes it, evaluates the tool wear of the rough carving tool to generate a wear evaluation result, analyzes the hidden danger characteristics of the rough carving by comprehensively considering the material defect value of the carving stone and the wear evaluation result of the rough carving tool, obtains the fine carving time and selects whether to add a secondary fine carving task based on the hidden danger characteristics of the rough carving, and when adding the secondary fine carving task, collects feedback data after the secondary fine carving, and evaluates the effect of the secondary fine carving task based on the feedback data, thereby improving the carving efficiency of the stone carving task.

[0041] Example 1, a stone carving task management and control system based on the Internet of Things, such as Figure 1 and Figure 2 As shown, it includes a defect detection module, a rough carving wear module, a hidden danger analysis module and a secondary fine carving module, and the electrical signals between each module are connected;

[0042] The functions of each module are as follows:

[0043] The defect detection module is used to detect internal cracks and bubbles in the carving stone before rough carving, obtain the crack volume and bubble volume of the carving stone and generate the material defect value of the carving stone;

[0044] The rough carving wear module is used to collect the tool usage time of the rough carving tool, monitor the tool engraving vibration of the rough carving tool and process it, evaluate the tool wear of the rough carving tool based on the tool usage time and generate a wear assessment result;

[0045] The hidden danger analysis module is used to analyze the hidden danger characteristics of the rough carving by comprehensively considering the material defect value of the carving stone and the wear assessment results of the rough carving tool. It also obtains the duration of the fine carving and decides whether to add a secondary fine carving task based on the hidden danger characteristics of the rough carving.

[0046] The secondary fine carving module is used to collect feedback data after the secondary fine carving of the carved stone when a secondary fine carving task is added, and evaluate the effect of the secondary fine carving task based on the feedback data.

[0047] The specific implementation is as follows:

[0048] There are multiple task stages in the stone carving process, namely the design stage, material preparation stage, carving stage, quality inspection stage, etc. Among them, the carving stage is divided into rough carving stage and fine carving stage;

[0049] The rough carving stage is the initial carving of the stone to carve out the general outline. The fine carving stage is to carry out fine carving based on the general outline of the stone obtained by rough carving according to the design drawings generated in the design stage. However, the state of different stones and the wear of carving tools will affect the final quality of the stone carving.

[0050] The defect detection module is used to detect internal cracks and bubbles in the carving stone before rough carving. The ultrasonic detector is used to detect the internal cracks and bubbles in the carving stone and generate the crack volume and bubble volume of the carving stone.

[0051] It should be explained that the crack volume and bubble volume are the sum of the volumes of all cracks and bubbles inside the carved stone respectively.

[0052] The material defect value of the carved stone is generated using a neural network algorithm based on the crack volume and bubble volume of the carved stone: , where w is the influencing factor adjustment parameter, which is used to adjust the crack volume of the carved stone so that it reaches the same dimension as the bubble volume, l is the crack volume of the carved stone, q is the bubble volume of the carved stone, a is the material defect value of the carved stone, and f is the neural network function relationship between l, q and a.

[0053] The larger the crack volume and bubble volume of the carved stone, the greater the material defect value of the carved stone, and the more secondary fine carving is needed.

[0054] It should be noted that the above-mentioned neural network function relationship f must satisfy the fact that the crack volume and bubble volume are positively correlated with the material defect value. Since the crack volume and bubble volume of the carved stone are both non-negative numbers, the above-mentioned neural network function relationship can be set to take a square operation, etc., which will not be elaborated here.

[0055] When the stone material enters the rough carving stage, the rough carving tool information currently used for carving the stone material is called, including the tool usage time of the rough carving tool. During the rough carving process of the stone material, the rough carving tool is monitored throughout the whole process, and the carving vibration of the rough carving tool is monitored in real time and compared with the preset vibration threshold;

[0056] If the tool engraving vibration of the rough engraving tool exceeds a preset vibration threshold, it is determined that the rough engraving tool has an abnormal vibration phenomenon and the engraving vibration value thereof is used as the tool engraving vibration abnormality value of the rough engraving tool;

[0057] After the rough carving stage is completed, the average value of the rough carving tool's engraving vibration abnormality during the rough carving stage is calculated, and the tool wear of the rough carving tool is evaluated based on the tool usage time of the rough carving tool. The specific steps are as follows:

[0058] The logarithmic normalization algorithm is used to normalize the average value of the tool engraving vibration abnormality of the rough engraving tool and the tool usage time: ,in The average value of the tool engraving vibration abnormality of the rough engraving tool or the tool usage time, The average value of the tool engraving vibration abnormal value of the rough engraving tool or the normalized result of the tool usage time; the maximum value among the average value of the tool engraving vibration abnormal value of the rough engraving tool and the normalized result of the tool usage time is selected as the wear assessment result b of the rough engraving tool.

[0059] The engraving tool is processed through a round of rough engraving and a round of fine engraving. Before the rough engraving, the material defect value of the engraving stone is analyzed. After the rough engraving, the wear assessment results of the rough engraving tool are analyzed. After a round of fine engraving, it is analyzed whether the current tool needs to add a second round of fine engraving tasks.

[0060] Standardize the material defect values of the engraving stone and the wear assessment results of the rough engraving tool. All input variables will be converted to the same range to ensure that each input contributes to the model in a balanced manner.

[0061] It should be noted that the standardization methods include but are not limited to standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function. The application methods of standardization are not described in detail here.

[0062] Substituting the material defect value of the carving stone and the wear assessment results of the rough carving tool into the logistic regression formula, the hidden danger characteristics of the rough carving are calculated. The specific formula is expressed as follows:

[0063] ;

[0064] Where L is the result of logistic regression calculation, that is, the hidden danger characteristics of the rough carving, e is the natural base, and y is the linear combination term of the logistic regression model. The specific setting of y is:

[0065] ;

[0066] Where, is the bias term, is the material defect value of the carving stone, This is the wear evaluation result of the rough engraving tool. as well as are the regression coefficients of the material defect value of the engraving stone and the wear evaluation results of the rough engraving tool;

[0067] After the first round of fine carving is completed, the duration of the fine carving is obtained;

[0068] The fine carving duration refers to the time it takes for the engraving tool to start and complete the fine carving process during the first round of fine carving after the rough carving and hidden danger feature analysis of the current stone is completed. The acquisition logic is to record the system timestamps at the start and end of fine carving, and calculate the difference between the fine carving end timestamp and the fine carving start timestamp to obtain the fine carving duration.

[0069] Substitute the duration of fine carving and the hidden danger characteristics of rough carving into the principal component discriminant analysis model to obtain the coefficient of additional fine carving;

[0070] The content of standardization has been described above and will not be repeated here.

[0071] It should be noted that the principal component discriminant analysis model combines principal component analysis (PCA) and linear discriminant analysis (LDA): after standardizing multiple input variables, compressing and reducing the dimensionality while retaining the maximum variance feature, improving model stability, and making a linear separable judgment on "whether to add secondary carving" in a low-dimensional space. It can also handle "positive and negative correlation" combination variables;

[0072] The implementation steps are:

[0073] A1: Standardize the hidden danger characteristics of the original input variables, namely, the fine carving time and the rough carving time;

[0074] A2: Construct a sample matrix and perform principal component analysis;

[0075] Specifically, let the standardized sample vector be:

[0076] ;

[0077] Compute the covariance matrix:

[0078] ;

[0079] Where, is the covariance matrix, is the sample size, is the sample data matrix, is the transpose of the sample data matrix;

[0080] Perform eigendecomposition on the covariance matrix and extract the principal components:

[0081] ;

[0082] Where, is the covariance matrix, It is an orthogonal matrix of the eigenvector matrix, containing all the unit eigenvectors of the covariance matrix (one per column), that is, the principal axis direction, reflecting the main direction of change of the original variable. is the inverse matrix of the eigenvector matrix, representing the transformation that converts the eigenspace back to the original space;

[0083] Take the front principal components, and obtain the compressed representation Z;

[0084] It should be noted that the selection of principal components is based on analyzing the size (contribution rate) of the eigenvalues and selecting the principal components with a cumulative contribution rate of more than 80% to ensure the representativeness and integrity of the data after dimensionality reduction. Furthermore, the principal component Z after dimensionality reduction can be used as an input variable to further construct a linear discriminant analysis (LDA) model or other classification algorithms to accurately determine whether to add a secondary fine carving task. This will not be elaborated here.

[0085] A3: Linear Discriminant Analysis;

[0086] Use the training samples (known whether to add fine carving) to establish a linear discriminant function:

[0087] ;

[0088] Where, is a weight vector, reflecting the influence of each variable on “adding fine carving”, is the principal component vector after dimensionality reduction, obtained by the previous step principal component analysis (PCA), is a bias term used to adjust the translation position of the classification function. It controls the position of the discrimination boundary in the classification space. To add the carving coefficient;

[0089] Furthermore, in LDA, the weight vector The calculation method is:

[0090] ;

[0091] Where, 、 They represent the principal component means of the samples of the “need to add fine carving” category and the “no need to add fine carving” category, is the intra-class scatter matrix, which reflects the variance of the data in each category;

[0092] Among them, this calculation method can obtain a stable and repeatable weight vector through training samples, which will not be described in detail here;

[0093] Compare the added fine carving coefficient with the preset fine carving threshold. If the added fine carving coefficient is greater than or equal to the fine carving threshold, a secondary fine carving task needs to be added. If the added fine carving coefficient is less than the fine carving threshold, no fine carving is required.

[0094] It should be noted that the fine carving threshold was obtained by our experimenters through statistical analysis and experience tuning based on historical experimental data and actual process requirements, and will not be elaborated here;

[0095] Add a secondary fine carving task based on the judgment result. When adding a secondary fine carving task, collect feedback data after the secondary fine carving of the carving stone;

[0096] Among them, the feedback data includes the amount of cutting waste and surface finish;

[0097] Cutting waste refers to the volume or weight of waste materials generated during the secondary fine carving process, which is used to reflect the processing efficiency and material utilization rate. Its acquisition logic is to use the weighing sensor installed on the engraving equipment to monitor the total amount of cutting waste generated during the processing in real time, record the difference between the waste data at the beginning and end of cutting, and obtain the cutting waste amount;

[0098] Surface finish refers to the smoothness of the surface of the carved stone after processing. It is quantified using roughness parameters to reflect the processing quality. Its acquisition logic is to use a non-contact surface roughness measuring instrument to sample the surface of the stone after carving, obtain surface height data, and calculate the surface roughness. The surface finish is obtained by taking the inverse form of the surface roughness.

[0099] The amount of cutting waste and surface finish are standardized and substituted into the polynomial model to obtain the secondary carving evaluation coefficient;

[0100] The standardization process has been described in the above content and will not be repeated here;

[0101] The polynomial regression calculation formula is as follows:

[0102] ;

[0103] Where, is the secondary carving evaluation coefficient, is the amount of cutting waste, For surface finish, is a constant term, and are the weights of cutting waste amount and surface finish respectively. The specific weight values are obtained by the experimenters based on the sample fitting goodness of fit and the principle of minimizing the sum of squared errors, so they will not be elaborated here.

[0104] The secondary fine carving evaluation coefficient is compared with the preset fine carving evaluation threshold. If the secondary fine carving evaluation coefficient is greater than or equal to the fine carving evaluation threshold, the secondary fine carving effect is evaluated as efficient. If the secondary fine carving evaluation coefficient is less than the fine carving evaluation threshold, the secondary fine carving effect is evaluated as inefficient.

[0105] Among them, the precision carving evaluation threshold was determined by the experimenters based on historical processing data and process standards through statistical analysis and experience tuning methods, and will not be elaborated here.

[0106] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0107] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0108] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0109] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0110] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A stone carving task management and control system based on the Internet of Things, characterized in that: Including defect detection module, rough carving wear module, hidden danger analysis module and secondary fine carving module; The defect detection module is used to detect internal cracks and bubbles in the carving stone before rough carving, obtain the internal crack volume and bubble volume of the carving stone, and generate the material defect value of the carving stone; The rough carving wear module is used to collect the tool usage time of the rough carving tool, monitor the tool engraving vibration of the rough carving tool and process it, evaluate the tool wear of the rough carving tool based on the tool usage time and generate a wear assessment result; The hidden danger analysis module is used to analyze the hidden danger characteristics of the rough carving by comprehensively considering the material defect value of the carving stone and the wear assessment results of the rough carving tool. It also obtains the duration of the fine carving and decides whether to add a secondary fine carving task based on the hidden danger characteristics of the rough carving. The secondary fine carving module is used to collect feedback data after the secondary fine carving of the carved stone when a secondary fine carving task is added, and evaluate the effect of the secondary fine carving task based on the feedback data.

2. The stone carving task management and control system based on the Internet of Things according to claim 1 is characterized in that: The crack volume and bubble volume are the sum of all crack volumes and bubble volumes inside the carved stone respectively; The material defect value of the carving stone is generated by using a neural network algorithm according to the crack volume and bubble volume of the carving stone.

3. The stone carving task management and control system based on the Internet of Things according to claim 1 is characterized in that: When using a neural network algorithm to generate material defect values for carved stone, the neural network algorithm formula is used for calculation: , where w is the influencing factor adjustment parameter, which is used to adjust the crack volume of the carving stone so that it reaches the same dimension as the bubble volume, l is the crack volume of the carving stone, q is the bubble volume of the carving stone, a is the material defect value of the carving stone, and f is the neural network function.

4. The stone carving task management and control system based on the Internet of Things according to claim 1 is characterized in that: When the stone material enters the rough carving stage, the rough carving tool information currently used for carving the stone material is called, including the tool usage time of the rough carving tool. During the rough carving process of the stone material, the tool carving vibration of the rough carving tool is monitored in real time and compared with the preset vibration threshold; If the tool engraving vibration of the rough engraving tool exceeds a preset vibration threshold, it is determined that the rough engraving tool has an abnormal vibration phenomenon and the engraving vibration value thereof is used as the tool engraving vibration abnormality value of the rough engraving tool; After the rough carving stage is completed, the average value of the tool engraving vibration anomaly of the rough carving tool in the rough carving stage is calculated. The logarithmic normalization algorithm is used to standardize the average value of the tool engraving vibration anomaly of the rough carving tool and the tool usage time, and then the maximum value is selected as the wear assessment result b of the rough carving tool.

5. The stone carving task management and control system based on the Internet of Things according to claim 4 is characterized in that: The material defect values of the carving stone and the wear assessment results of the rough carving tools were standardized and substituted into the logistic regression formula to calculate the hidden danger characteristics of the rough carving. The specific formula is expressed as follows: ; Where L is the result of logistic regression calculation, that is, the hidden danger characteristics of the rough carving, e is the natural base, and y is the linear combination term of the logistic regression model. The specific setting of y is: ; Where, is the bias term, is the material defect value of the carving stone, This is the wear evaluation result of the rough engraving tool. as well as are the regression coefficients of the material defect value of the engraving stone and the wear evaluation results of the rough engraving tool; After the first round of fine carving is completed, the duration of the fine carving is obtained.

6. The stone carving task management and control system based on the Internet of Things according to claim 5 is characterized in that: Record the system timestamps at the start and end of fine carving respectively, calculate the difference between the fine carving end timestamp and the fine carving start timestamp to get the fine carving duration of that time; Substitute the time of fine carving and the hidden danger characteristics of rough carving into the principal component discriminant analysis model to obtain the added fine carving coefficient. The implementation steps are as follows: A1: Standardize the hidden danger characteristics of the original input variables, namely, the fine carving time and the rough carving time; A2: Construct a sample matrix and perform principal component analysis; A3: Linear discriminant analysis is performed to obtain the additional carving coefficient.

7. The stone carving task management and control system based on the Internet of Things according to claim 6 is characterized in that: Compare the added fine carving coefficient with the preset fine carving threshold. If the added fine carving coefficient is greater than or equal to the fine carving threshold, a secondary fine carving task needs to be added. If the added fine carving coefficient is less than the fine carving threshold, no fine carving is required. A secondary fine carving task is added based on the judgment result. When the secondary fine carving task is added, feedback data is collected after the carving stone is finely carved for the second time.

8. The stone carving task management and control system based on the Internet of Things according to claim 7 is characterized in that: Feedback data includes cutting waste volume and surface finish; The total amount of waste generated by cutting during the processing is monitored in real time by a weighing sensor installed on the engraving equipment. The difference in waste data between the start and end of cutting is recorded to obtain the amount of cutting waste. A non-contact surface roughness measuring instrument is used to sample the surface of the stone after carving to obtain surface height data. The surface roughness is calculated and the surface finish is obtained using the inverse form of the surface roughness.

9. The stone carving task management and control system based on the Internet of Things according to claim 8, characterized in that: The amount of cutting waste and surface finish are standardized and substituted into the polynomial model to obtain the secondary fine carving evaluation coefficient.

10. The stone carving task management and control system based on the Internet of Things according to claim 9, characterized in that: The secondary fine carving evaluation coefficient is compared with the preset fine carving evaluation threshold. If the secondary fine carving evaluation coefficient is greater than or equal to the fine carving evaluation threshold, the secondary fine carving effect is evaluated as efficient. If the secondary fine carving evaluation coefficient is less than the fine carving evaluation threshold, the secondary fine carving effect is evaluated as inefficient.

Images