TW202432299A - Tool remaining life prediction method based on current information and system thereof - Google Patents

Abstract

A tool remaining life prediction method based on current information is configured to predict a remaining life of a tool and includes performing a data obtaining step, a data normalizing step, a data dividing step and a model training and verifying step. The data obtaining step includes obtaining a plurality of tool processing data from a memory. The tool processing data include a current increase rate. The data normalizing step includes normalizing the tool processing data to generate a plurality of normalized tool processing data. The data dividing step includes dividing the normalized tool processing data into a training data set and a verifying data set. The model training and verifying step includes training a first and a second tool remaining life models by using all and a portion of the training data set, and verifying the first and the second tool remaining life models by using the verifying data set to generate a first and a second accuracies, and comparing the first and the second accuracies. Therefore, the tool remaining life prediction method based on current information of the present disclosure can determine an appropriate scenario model to predict the remaining life of the tool at optimum efficiency.

Description

Tool remaining life prediction method and system based on current information

The present invention relates to a method and system for predicting the remaining life of a tool, and in particular to a method and system for predicting the remaining life of a tool based on current information.

The machinery industry lays the foundation for the vigorous development of the entire society and now maintains a complete and strong supply chain of machine tools and precision machinery parts. However, with the increase in people's wages and education levels, most people will think twice about the factory environment and the day and night shift system. For many manufacturers engaged in mechanical processing, they are currently facing the dilemma of rising operating costs and labor shortages. Therefore, the implementation of Industry 4.0 smart manufacturing has reduced the number of employees in the factory. The man-free factory is the overall trend of the current machinery industry, and monitoring the wear of tools to estimate processing quality and processing abnormalities is an extremely important part of smart manufacturing. If the man-free factory ignores the processing quality, it is very easy to produce a large number of waste or refurbished parts, resulting in unnecessary waste of time and cost, which has a considerable negative impact on the company's operations. In summary, tool wear monitoring can bring three major benefits. The first benefit is the improvement of workpiece processing quality, the second benefit is the improvement of processing efficiency, and the third benefit is the reduction of operating costs.

Tool wear is closely related to the quality of workpiece processing, because increased tool wear will cause a significant increase in cutting resistance, resulting in a corresponding increase in the size variation range of the workpiece after processing and the surface roughness of the processed surface, which ultimately affects the processing quality. Today's processing processes often use at least multiple tools (tools for different purposes) for processing, and when the tool is severely worn, the risk of rough processing tools for material removal will increase significantly. When the rough processing tool breaks, its processing reserve will be much larger than before the tool breaks, causing the subsequent processing tools to break or splinter due to too large a reserve. Severe wear or breakage of finishing tools will cause risks such as poor machining accuracy. Therefore, severe wear or breakage of tools will have a significant impact on machine utilization, and technicians need to stop production, change tools, set tools, and repair workpieces. The current control method for tool wear is mainly based on the long-standing experience of technicians. In order to reduce risks and unexpected situations in processing, technicians often use past experience as an indicator to set a fixed number of workpieces for processing and then uniformly change tools. Or in the process of handing over to colleagues in the next shift, it is difficult to clearly explain the use of tools in a quantitative way, resulting in the next shift personnel replacing new tools before starting processing. The above situation will also invisibly waste many usable tools. It can be seen that there is currently a lack of a tool remaining life prediction method and system based on current information that requires only a small amount of data training, is low-cost, cost-effective, and has a certain degree of accuracy, so relevant researchers are looking for a solution.

Therefore, the purpose of the present invention is to provide a method and system for predicting the remaining life of a tool based on current information, which can predict the remaining life model of a tool under different materials and different situations by training the current increase factor and a generalized regression neural network (GRNN). A cost-effective situational model can be trained using a small amount of data, and the remaining life of the tool can be accurately predicted, thereby solving the problem that the known model establishment rules require a large amount of experimental data, the prediction must be based on the rule of human experience, and the cost is too high.

According to an embodiment of the method of the present invention, a tool remaining life prediction method based on current information is provided, which is used to predict a remaining life of a tool and includes the following steps: a data acquisition step, a data normalization step, a data segmentation step, and a situation model training and verification step. The data acquisition step includes driving a computing processor to obtain a plurality of tool processing data from a memory, and these tool processing data include a current increase factor. The current increase factor is a ratio of a real-time load current to an initial load current of a new tool. The data normalization step includes driving the computing processor to normalize the tool processing data to generate a plurality of normalized tool processing data so that the size scales of the normalized tool processing data are the same. The data segmentation step includes driving the computing processor to segment the normalized tool processing data into a training data set and a verification data set. The scenario model training and verification step includes driving a computing processor to use all of the training data set and a portion of the training data set to train a first tool remaining life model and a second tool remaining life model, and using the verification data set to verify the trained first tool remaining life model and the second tool remaining life model to generate a first accuracy and a second accuracy, and comparing the first accuracy and the second accuracy to determine whether to use the second tool remaining life model to predict the remaining life of the tool.

Thus, the tool remaining life prediction method based on current information of the present invention can predict the remaining life model of the tool under different materials and different scenarios through the current increase multiplier and GRNN training, so that a cost-effective scenario model can be trained using a small amount of data and the remaining life of the tool can be accurately predicted.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned tool processing data further includes a tool usage time, a current processing current slope trend, a processing cutting width and at least a processing material hardness. The current increase rate is used to determine the end point of the remaining life.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plurality of materials. The second training verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein the part of the training data set is all data of one of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plurality of materials. The second training and verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein the part of the training data set is a part of the data of one of these materials mixed with all the data of the rest of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plurality of materials. The second training and verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein part of the training data set is the mid- and late-stage data of one of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

According to an implementation method of the structural aspect of the present invention, a tool remaining life prediction system based on current information is provided, which is used to predict a remaining life of a tool, and includes a memory and an operation processor. The memory stores a plurality of tool processing data, and these tool processing data include a current increase factor, and the current increase factor is a ratio of a real-time load current to an initial load current of a new tool. The operation processor is electrically connected to the memory and receives these tool processing data. The operation processor is configured to implement an operation including the following steps: a data normalization step, a data segmentation step, and a situation model training and verification step. The data normalization step includes normalizing the tool processing data to generate a plurality of normalized tool processing data so that the size scales among the normalized tool processing data are the same. The data segmentation step includes segmenting the normalized tool processing data into a training data set and a verification data set. The scenario model training and verification step includes using all of the training data set and a portion of the training data set to train a first tool remaining life model and a second tool remaining life model, and using the verification data set to verify the trained first tool remaining life model and the second tool remaining life model to generate a first accuracy and a second accuracy, and comparing the first accuracy and the second accuracy to determine whether to use the second tool remaining life model to predict the remaining life of the tool.

Thus, the tool remaining life prediction system based on current information of the present invention can predict the remaining life model of the tool under different materials and different scenarios through the current increase multiplier and GRNN training, so that a cost-effective scenario model can be trained using a small amount of data and the remaining life of the tool can be accurately predicted.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned tool processing data further includes a tool usage time, a current processing current slope trend, a processing cutting width and at least a processing material hardness. The current increase rate is used to determine the end point of the remaining life.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plurality of materials. The second training verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein the part of the training data set is all data of one of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plurality of materials. The second training and verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein the part of the training data set is a part of the data of one of these materials mixed with all the data of the rest of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned scenario model training and verification step further includes a first training and verification step, a second training and verification step, and an accuracy comparison step. The first training and verification step includes driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set is all data of the plural materials. The second training and verification step includes driving the computing processor to train the second tool remaining life model using part of the training data set, and using the verification data set to verify the trained second tool remaining life model to generate a second accuracy, wherein part of the training data set is the mid- and late-stage data of one of these materials. The accuracy comparison step includes driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. The number of the at least one processing material hardness is plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other.

The following will describe several embodiments of the present invention with reference to the drawings. For the sake of clarity, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present invention. That is to say, in some embodiments of the present invention, these practical details are not necessary. In addition, in order to simplify the drawings, some commonly used structures and components will be shown in the drawings in a simple schematic manner; and repeated components may be represented by the same number.

In addition, in this article, when a certain component (or unit or module, etc.) is "connected" to another component, it may refer to that the component is directly connected to the other component, or it may refer to that the component is indirectly connected to the other component, that is, there are other components between the component and the other component. When it is clearly stated that a certain component is "directly connected" to another component, it means that there are no other components between the component and the other component. The terms first, second, third, etc. are only used to describe different components, and there is no restriction on the components themselves. Therefore, the first component can also be renamed as the second component. Moreover, the combination of components/units/circuits in this article is not a generally known, conventional or known combination in this field. Whether the components/units/circuits themselves are known cannot be used to determine whether their combination relationship is easy to be completed by ordinary knowledgeable people in the technical field.

Please refer to FIG. 1 and FIG. 2 together, wherein FIG. 1 is a schematic diagram of the process of the tool remaining life prediction method 100 based on current information of the first embodiment of the present invention; and FIG. 2 is a schematic diagram of the tool remaining life prediction system 200 based on current information of the second embodiment of the present invention. As shown in the figure, the tool remaining life prediction method 100 based on current information is applied to the tool remaining life prediction system 200 based on current information, and is used to predict the remaining life of the tool. The current information includes the current increase factor 122.

In FIG. 1 , the tool remaining life prediction method 100 based on current information includes the following steps: data acquisition step S2, data normalization step S4, data segmentation step S6, and scenario model training and verification step S8. Referring to FIG. 2 , the data acquisition step S2 includes driving the computing processor 220 to acquire a plurality of tool processing data 120 from the memory 210. These tool processing data 120 include a current increase factor 122, which is the ratio of the real-time load current to the initial load current of the new tool. The data normalization step S4 includes driving the computing processor 220 to normalize the tool processing data 120 to generate a plurality of normalized tool processing data 140, so that the size scales of the normalized tool processing data 140 are the same. The data segmentation step S6 includes driving the computing processor 220 to segment the normalized tool processing data 140 into a training data set 162 and a verification data set 164. The scenario model training and verification step S8 includes driving the computing processor 220 to train the first tool remaining life model and the second tool remaining life model using all of the training data set 162 and a portion of the training data set 162, and verifying the trained first tool remaining life model and the second tool remaining life model using the verification data set 164 to generate a first accuracy and a second accuracy, and comparing the first accuracy and the second accuracy to determine whether to use the second tool remaining life model to predict the remaining life of the tool. The scenario model training and verification step S8 includes a first scenario S82, a second scenario S84, and a third scenario S86.

In FIG. 2 , the tool remaining life prediction system 200 based on current information includes a memory 210 and an operation processor 220. The operation processor 220 is electrically connected to the memory 210. Referring to FIG. 1 , the memory 210 stores the tool processing data 120. The operation processor 220 receives the tool processing data 120 and is configured to implement a data normalization step S4, a data segmentation step S6, and a scenario model training and verification step S8. Thus, the tool remaining life prediction method 100 based on current information and the tool remaining life prediction system 200 based on current information of the present invention can predict the remaining life model of the tool under different materials and different situations through the current increase factor 122 and the generalized regression neural network (GRNN), so that a cost-effective situational model can be trained using a small amount of data and the remaining life of the tool can be accurately predicted.

In the aforementioned embodiment, the tool processing data 120 may further include the tool usage time, the current slope trend of the current processing at the current time, the processing cutting width and at least one processing material hardness. These data are parameters that affect the remaining life and are also the input of the model, and the output of the model is the corresponding actual remaining life. Furthermore, when the current increase multiplier 122 is greater than or equal to the critical life threshold multiplier, the tool is judged to have reached the critical life, that is, the remaining life of the tool is 0; in other words, the current increase multiplier 122 is used to judge the end point of the remaining life. The critical life threshold multiplier can be greater than 1.3 and less than 1.5, and the preferred one is 1.4. In the data segmentation step S6, the normalized tool processing data 140 can be evenly segmented into 80% of the data as the training data set 162 and 20% of the data as the verification data set 164 within the entire data range, but the present invention is not limited thereto. In addition, the memory 210 can be a random access memory (RAM) or other type of dynamic storage device that can store information and instructions for the computing processor 220 to execute, but the present invention is not limited thereto. The computing processor 220 can be a processor, a microprocessor, a central processing unit (CPU), a computer, a mobile device processor, a cloud processor, or other electronic computing processor, but the present invention is not limited thereto.

Please refer to Figures 1 to 3 together, wherein Figure 3 is a schematic diagram showing the process of applying the scenario model training and verification step S8 of Figure 1 to the first scenario S82. When the application scenario is the first scenario S82 (sufficient data volume), the scenario model training and verification step S8 includes a first training and verification step S822, a second training and verification step S824, and an accuracy comparison step S826.

The first training verification step S822 includes driving the computing processor 220 to use the entire training data set 162 to train the first tool remaining life model, and using the verification data set 164 to verify the trained first tool remaining life model to generate a first accuracy, wherein the entire training data set 162 is the entire data of the multiple materials. Specifically, the first training verification step S822 includes steps S822a, S822b, and S822c, wherein step S822a uses the entire data to train the three-material benchmark model, that is, uses the entire training data set 162 to train the first tool remaining life model. Step S822b uses the K-equal cross validation method to find the best smoothing parameters of the model, that is, the K-equal cross validation method is used to adjust the model smoothing parameters to minimize the prediction error. Step S822c uses the prediction accuracy of the validation data as a comparison benchmark, that is, the validation data set 164 is used to validate the first tool remaining life model after training to generate the first accuracy.

The second training verification step S824 includes driving the computing processor 220 to train the second tool remaining life model using part of the training data set 162, and verifying the trained second tool remaining life model using the verification data set 164 to generate a second accuracy, wherein the part of the training data set 162 is all data of one of these materials. Specifically, the second training verification step S824 includes steps S824a, S824b, and S824c, wherein step S824a is to train a model for predicting the remaining life under a specific material, that is, to train the second tool remaining life model using part of the training data set 162. Step S824b is the same as step S822b and will not be described again. Step S824c is to use the validation data to predict the accuracy, that is, to use the validation data set 164 to validate the trained second tool remaining life model to generate a second accuracy.

The accuracy comparison step S826 compares the prediction accuracy of the training model using two methods (i.e., the first training verification step S822 and the second training verification step S824); in other words, the accuracy comparison step S826 includes driving the computing processor 220 to compare the first accuracy and the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result.

In one embodiment, the K-equal cross validation method may be a 10-equal cross validation method. The accuracy may be the root mean square error (RMSE), the mean absolute percentage error (MAPE), or a combination thereof. The number of processing material hardnesses may be plural, and these processing material hardnesses correspond to these materials respectively, and these processing material hardnesses are different from each other. The processing material hardnesses may include HRC20, HRC45, and HRC55 (i.e., three materials), and the corresponding data may be obtained through repeated experiments, but the present invention is not limited to the above. In addition, in the accuracy comparison step S826, when the accuracy comparison result is that the difference between the first accuracy and the second accuracy is less than or equal to the preset difference, the second tool remaining life model is used to predict the remaining life of the tool.

Please refer to Figures 1 to 4 together, wherein Figure 4 is a schematic diagram showing the process of applying the scenario model training and verification step S8 of Figure 1 to the second scenario S84. When the application scenario is the second scenario S84 (small target data volume and large related data volume), the scenario model training and verification step S8 includes a first training and verification step S842, a second training and verification step S844, and an accuracy comparison step S846.

The first training verification step S842 includes steps S842a, S842b, and S842c. The first training verification step S842 is the same as the first training verification step S822 in FIG. 3 and will not be described again. The second training verification step S844 includes driving the computing processor 220 to use part of the training data set 162 to train the second tool remaining life model, and using the verification data set 164 to verify the trained second tool remaining life model to generate a second accuracy. Specifically, the second training verification step S844 includes steps S844a, S844b, and S844c, wherein step S844a is to reduce the target data amount and mix the related data to train the model, that is, to use part of the training data set 162 to train the second tool remaining life model, wherein part of the training data set 162 is a part of the data of one of these materials (target data) mixed with all the data of the rest of these materials (related data). Step S844b is the same as step S842b. Step S844c is to use the verification data to predict the accuracy, that is, to use the verification data set 164 to verify the trained second tool remaining life model to generate the second accuracy.

The accuracy comparison step S846 is to compare how much target data is needed for its accuracy to be close to the reference model; in other words, the accuracy comparison step S846 includes driving the computing processor 220 to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result. In one embodiment, the "part" of one of these materials (target data) is 75%, 50% or 25% of the total, and the accuracy of these three target data is compared to select the second tool remaining life model whose accuracy comparison result meets the requirements (such as greater than or equal to the preset accuracy threshold value) and is trained with the least amount of target data.

Please refer to Figures 1 to 5 together, wherein Figure 5 is a schematic diagram showing the process of applying the scenario model training and verification step S8 of Figure 1 to the third scenario S86. When the application scenario is the third scenario S86 (the model focuses on predicting the mid- and late-stage tool life), the scenario model training and verification step S8 includes a first training and verification step S862, a second training and verification step S864, and an accuracy comparison step S866.

The first training verification step S862 includes steps S862a, S862b, and S862c. The first training verification step S862 is the same as the first training verification step S822 in FIG. 3 and will not be described again. The second training verification step S864 includes driving the computing processor 220 to use part of the training data set 162 to train the second tool remaining life model, and using the verification data set 164 to verify the trained second tool remaining life model to generate a second accuracy. Specifically, the second training verification step S864 includes steps S864a, S864b, and S864c, wherein step S864a is a full data training model for the mid- and late-stage tool life, that is, using part of the training data set 162 to train the second tool remaining life model, wherein part of the training data set 162 is mid- and late-stage data of these materials. The above-mentioned mid- and late-stage data may be data with a tool remaining life of less than 50%, but the present invention is not limited thereto. Step S864b is the same as step S862b. Step S864c is to use the verification data to predict the accuracy, that is, to use the verification data set 164 to verify the trained second tool remaining life model to generate the second accuracy. This can eliminate the inaccurate factors in the model prediction in the early and middle stages of tool life, which can increase the accuracy of the model and reduce the amount of training data.

From the above implementation, it can be seen that the present invention has the following advantages: First, the remaining life of the tool can be accurately predicted by the current increase rate. Second, the GRNN is used to train the remaining life model of the tool under different materials and different scenarios, so that a cost-effective scenario model can be trained with a small amount of data, and the remaining life of the tool can be accurately predicted, thereby solving the problem that the known model establishment rules require a large amount of experimental data, the prediction must be based on the rules of human experience, and the cost is too high.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the scope of the attached patent application.

100: Tool remaining life prediction method based on current information 120: Tool processing data 122: Current increase factor 140: Normalized tool processing data 162: Training data set 164: Verification data set 200: Tool remaining life prediction system based on current information 210: Memory 220: Computation processor S2: Data acquisition step S4: Data normalization step S6: Data segmentation step S8: Scenario model training verification step S82: First scenario S822, S842, S862: First training verification step S822a, S822b, S822c, S824a, S824b, S824c, S842a, S842b, S842c, S844a, S844b, S844c, S862a, S862b, S862c, S864a, S864b, S864c: Steps S824, S844, S864: Second training verification step S826, S846, S866: Accuracy comparison step S84: Second scenario S86: Third scenario

FIG. 1 is a flow chart showing a method for predicting the remaining life of a tool based on current information according to the first embodiment of the present invention; FIG. 2 is a flow chart showing a system for predicting the remaining life of a tool based on current information according to the second embodiment of the present invention; FIG. 3 is a flow chart showing the application of the scenario model training and verification step of FIG. 1 to the first scenario; FIG. 4 is a flow chart showing the application of the scenario model training and verification step of FIG. 1 to the second scenario; and FIG. 5 is a flow chart showing the application of the scenario model training and verification step of FIG. 1 to the third scenario.

100: Tool remaining life prediction method based on current information

120: Tool processing data

122: Current increase factor

140: Normalized tool processing data

162: Training data set

164: Verification data set

S2: Data acquisition step

S4: Data normalization step

S6: Data segmentation step

S8: Situation model training verification step

S82: First Situation

S84: Second Situation

S86: The third scenario

Claims (10)

A tool residual life prediction method based on current information is used to predict a residual life of a tool. The tool residual life prediction method based on current information includes the following steps: A data acquisition step, including driving a computing processor to acquire a plurality of tool processing data from a memory, wherein the tool processing data includes a current increase factor, and the current increase factor is a ratio of a real-time load current to an initial load current of a new tool; A data normalization step, including driving the computing processor to normalize the tool processing data to generate a plurality of normalized tool processing data, so that the size scale between the normalized tool processing data is the same; A data segmentation step, including driving the computing processor to segment the normalized tool processing data into a training data set and a verification data set; and a scenario model training verification step, including driving the computing processor to use the entire training data set and a portion of the training data set to train a first tool remaining life model and a second tool remaining life model, and use the verification data set to verify the trained first tool remaining life model and the second tool remaining life model to generate a first accuracy and a second accuracy, and compare the first accuracy and the second accuracy to determine whether to use the second tool remaining life model to predict the remaining life of the tool. A tool remaining life prediction method based on current information as described in claim 1, wherein the tool processing data further includes a tool usage time, a current processing current slope trend, a processing cutting width and at least a processing material hardness, and the current increase multiplier is used to determine the end point of the remaining life. The tool remaining life prediction method based on current information as described in claim 2, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, comprising driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is all data of one of the materials; and An accuracy comparison step, comprising driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other. The tool remaining life prediction method based on current information as described in claim 2, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, including driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is a portion of data of one of the materials mixed with all data of the rest of the materials; and An accuracy comparison step, including driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other. The tool remaining life prediction method based on current information as described in claim 2, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, including driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is the mid- and late-stage data of one of the materials; and An accuracy comparison step, including driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other. A tool residual life prediction system based on current information is used to predict a residual life of a tool. The tool residual life prediction system based on current information includes: A memory storing a plurality of tool processing data, wherein the tool processing data includes a current increase factor, wherein the current increase factor is a ratio of a real-time load current to an initial load current of a new tool; and A computing processor electrically connected to the memory and receiving the tool processing data, wherein the computing processor is configured to implement an operation including the following steps: A data normalization step including normalizing the tool processing data to generate a plurality of normalized tool processing data so that the size scale between the normalized tool processing data is the same; A data segmentation step, comprising segmenting the normalized tool processing data into a training data set and a verification data set; and A scenario model training verification step, comprising using the entire training data set and a portion of the training data set to train a first tool remaining life model and a second tool remaining life model, and using the verification data set to verify the trained first tool remaining life model and the second tool remaining life model to generate a first accuracy and a second accuracy, and comparing the first accuracy and the second accuracy to determine whether to use the second tool remaining life model to predict the remaining life of the tool. A tool remaining life prediction system based on current information as described in claim 6, wherein the tool processing data further includes a tool usage time, a current time processing current slope trend, a processing cutting width and at least a processing material hardness, and the current increase multiplier is used to determine the end point of the remaining life. The tool remaining life prediction system based on current information as described in claim 7, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, comprising driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is all data of one of the materials; and An accuracy comparison step, comprising driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other. The tool remaining life prediction system based on current information as described in claim 7, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, including driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is a portion of data of one of the materials mixed with all data of the rest of the materials; and An accuracy comparison step, including driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other. The tool remaining life prediction system based on current information as described in claim 7, wherein the scenario model training and verification step further comprises: A first training and verification step, comprising driving the computing processor to use all of the training data set to train the first tool remaining life model, and using the verification data set to verify the trained first tool remaining life model to generate the first accuracy, wherein all of the training data set is all data of a plurality of materials; A second training verification step, including driving the computing processor to use the portion of the training data set to train the second tool remaining life model, and using the verification data set to verify the trained second tool remaining life model to generate the second accuracy, wherein the portion of the training data set is the mid- and late-stage data of one of the materials; and An accuracy comparison step, including driving the computing processor to compare the first accuracy with the second accuracy to generate an accuracy comparison result, and determining whether to use the second tool remaining life model to predict the remaining life of the tool based on the accuracy comparison result; Among them, the number of the at least one processing material hardness is plural, the processing material hardnesses correspond to the materials respectively, and the processing material hardnesses are different from each other.

Images