Boring depth prediction method and device

Abstract

The invention relates to the field of machine detection, in particular to a boring depth prediction method and device. The method comprises the steps of obtaining machine tool operation parameters when a machine tool machines a to-be-tested bore hole; and inputting machine tool operation parameters to the prediction model to obtain a first boring depth. Wherein the prediction model represents the corresponding relation between the operation state of the machine tool and the boring depth when the machine tool machines a boring hole of the same type as the to-be-tested boring hole. The first boring depth is the processing depth of the to-be-tested boring hole. According to the scheme, the boring depth is automatically detected in real time, and the detection efficiency in the machining process is greatly improved.

Description

Technical Field

[0001] This application relates to the field of machine inspection, and in particular to a method and apparatus for predicting boring depth. Background Technology

[0002] Currently, in the boring process, existing technologies still rely on manual measurement and subjective judgment, which has significant limitations: on the one hand, manual measurement is prone to errors, and the judgment results are uncertain due to the influence of personnel experience; on the other hand, in the face of mass production scenarios, the current approach mostly adopts a sampling and post-production inspection mode, which makes it difficult to detect quality problems such as excessive boring depth in a timely manner, easily leading to the production of batches of defective products, resulting in cost waste and efficiency loss. Therefore, how to achieve accurate prediction of boring depth has become a problem worthy of discussion. Summary of the Invention

[0003] This application provides a method for real-time and automated detection of boring depth, which significantly improves the detection efficiency of the machining process.

[0004] In a first aspect, this application provides a method for predicting boring depth, the method comprising: Obtain the machine tool operating parameters when machining the bore to be tested; Input the machine tool operating parameters into the prediction model to obtain the first boring depth. The prediction model represents the correspondence between the machine tool's operating state and the boring depth when the machine tool processes a boring of the same type as the boring to be tested. The first boring depth is the processing depth of the boring to be tested.

[0005] In the above method, the machining depth of the bore to be tested is predicted by a predictive model, enabling real-time and automated detection of the bore depth, significantly improving the detection efficiency of the machining process. Compared with the prior art that relies on manual experience to judge the bore depth, this application determines the bore depth based on the correspondence between the machine tool's operating status and the bore depth, resulting in more accurate and stable predictions, reducing the impact of human error on machining quality; it can also provide data support for subsequent machining quality inspection, improving the overall quality stability of the boring process.

[0006] Optionally, the above prediction model is obtained in the following way: Obtain historical machine tool operating parameters, including the temperature at at least one location of the machine tool when machining a single reference boring hole during the historical time period, and the power output of the machine tool when machining a single reference boring hole. The reference boring hole and the boring hole to be tested belong to the same type. A neural network model is used to train the training sample set until the verification sample set meets the preset evaluation criteria to obtain the prediction model. The training sample set is a subset of the historical machine tool operating parameters, and the verification sample set is a subset of the historical machine tool operating parameters. The training sample set and the verification sample set are different.

[0007] In the above method, historical temperature and power data of similar boring holes are selected as training samples to ensure that the patterns learned by the model match the boring holes to be tested, thereby improving the relevance and accuracy of the model's predictions. The training method using both training and validation sample sets effectively avoids model overfitting. By selecting easily collected machine tool operating parameters such as temperature and power as input features, there is no need to install additional complex detection equipment, reducing the implementation cost and difficulty of the solution.

[0008] Optionally, the above-mentioned acquisition of machine tool operating parameters during the machining of the bore to be tested specifically includes: Obtain initial machine tool operating parameters, including the continuous temperature at at least one position of the machine tool when the machine tool is machining at least one reference boring hole within a preset time period, and the power output of the machine tool when machining at least one reference boring hole; The initial machine tool operating parameters are determined based on the machining time of a single boring hole. The machine tool operating parameters include the temperature at at least one position of the machine tool when machining the boring hole to be tested, and the power output of the machine tool when machining the boring hole to be tested.

[0009] In the above method, by dividing the continuously acquired batch data into independent data units of a single boring dimension, interference between different boring processing data can be eliminated, ensuring that the data input to the model corresponds one-to-one with the processing of a single boring hole. This allows the model to accurately learn the parameter variation patterns within a single boring processing cycle, further improving the accuracy of depth prediction.

[0010] Optionally, before the above-mentioned input of machine tool operating parameters to the prediction model to obtain the first boring depth, the method further includes: The target prediction model is determined based on the label of the bore to be tested. The label is used to mark the correspondence between the bore type and the prediction model. Different types of bores correspond to different prediction models. The target prediction model is the prediction model corresponding to the type of bore to be tested. The machine tool operating parameters are input into the prediction model to obtain the first boring depth, specifically including: Input the machine tool operating parameters into the target prediction model to obtain the first boring depth.

[0011] In the above method, by establishing the correspondence between boring hole type and prediction model, different types of boring holes can be predicted using dedicated models, thereby improving the accuracy and adaptability of model prediction.

[0012] Optionally, after inputting the machine tool operating parameters into the prediction model to obtain the first boring depth, the method further includes: If the depth of the first boring hole meets the alarm rules, an alarm is issued.

[0013] In the above method, by realizing real-time early warning of processing quality, technicians can be promptly reminded to intervene and avoid the generation of batches of defective products, thereby realizing the quality monitoring of boring and improving the quality of boring processing.

[0014] Optionally, the above neural network model is a gated recurrent unit (GRU).

[0015] Compared to traditional recurrent neural networks, GRU can ensure the stability of model training, reduce the error in predicting bore depth, and improve the accuracy of prediction.

[0016] Secondly, embodiments of this application provide a boring depth prediction device, the device comprising: The transceiver module is used to acquire machine tool operating parameters when the machine tool is machining the bore to be tested; The processing module is used to input machine tool operating parameters into the prediction model to obtain the first boring depth. The prediction model represents the correspondence between the machine tool's operating state and the boring depth when the machine tool processes a boring of the same type as the boring to be tested. The first boring depth is the processing depth of the boring to be tested.

[0017] Thirdly, embodiments of this application also provide a computer device, including: Memory, used to store program instructions; A processor is used to call program instructions stored in memory and execute the methods described in any of the first aspects above according to the obtained program.

[0018] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the methods described in any of the first aspects.

[0019] Fifthly, embodiments of this application also provide a computer program product, which includes an executable program that is executed by a processor using the methods described in any of the first aspects. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a boring depth prediction method provided in an embodiment of this application; Figure 2A schematic diagram of a boring hole to be tested, provided for an embodiment of this application; Figure 3 This application provides a schematic diagram showing the location of a temperature sensor arranged inside a machine tool according to an embodiment of the present application; Figure 4 A schematic diagram illustrating the model prediction accuracy provided in an embodiment of this application; Figure 5 A schematic diagram illustrating another model prediction accuracy provided in an embodiment of this application; Figure 6 A schematic diagram illustrating another model prediction accuracy provided in an embodiment of this application; Figure 7 A schematic diagram illustrating another model prediction accuracy provided in an embodiment of this application; Figure 8 A schematic diagram of a boring depth prediction structure provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The application scenarios described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. Those skilled in the art will understand that with the emergence of new application scenarios, the technical solutions provided in this application are also applicable to similar technical problems. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0024] The boring depth prediction method and related hardware provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 An exemplary flowchart of a boring depth prediction method provided in an embodiment of this application is shown. This process can be executed by a terminal or a server. The following description uses the terminal executing the boring depth prediction method as an example. Figure 1 As shown, the process specifically includes: Step S101: Obtain the machine tool operating parameters when machining the boring hole to be tested.

[0026] In one optional embodiment, the terminal can acquire the initial machine tool operating parameters when the machine tool is machining the bore to be tested. For example, the terminal can acquire the continuous temperature at at least one location of the machine tool during a preset time period when the machine tool is machining at least one bore to be tested, and the power output by the machine tool when machining at least one bore to be tested, thus constituting the initial machine tool operating parameters. The machine tool location for which temperature needs to be measured can be a location where the machine tool generates heat, and / or a location where the machine tool dissipates heat. The machine tool location for which temperature needs to be measured includes at least one or more of the following: spindle front bearing, spindle housing flange, intermediate rotating shaft bearing end cover, power input shaft bearing end cover, spindle motor housing, column temperature, and cutting fluid inlet. For example, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of a boring bar to be tested. The boring bar to be tested can be used to machine guide holes with a reamer. It can also be used to machine seat ring holes with a double-edged boring bar. For example... Figure 3 As shown in the figure, this application embodiment provides a schematic diagram of the location of a temperature sensor arranged inside a machine tool. Figure 3 The temperature sensors are positioned at locations where heat is generated and dissipated on the machine tool, specifically including: Position T1: Front spindle bearing; Position T2: Front spindle bearing; Position T3: Spindle housing flange; Position T4: Intermediate rotating shaft bearing end cover; Position T5: Power input shaft bearing end cover; Position T6: Spindle motor housing; Position T7: Column temperature; Position T8: Cutting fluid inlet. It can be understood that all temperature points can collect data within the same time period. For example, the temperature sensor's sampling frequency can be 10Hz. Or, for example, the temperature sensor's sampling frequency can be 20Hz.

[0027] After acquiring the initial machine tool operating parameters, the terminal can divide these parameters based on the machining time of a single boring hole, thus obtaining the machine tool operating parameters. These parameters include the temperature at at least one location on the machine tool during the machining of the tested boring hole, and the power output during machining. For example, the terminal acquires initial machine tool operating parameters that include real-time temperature data for the spindle front bearing, spindle housing flange, intermediate rotating shaft bearing end cover, power input shaft bearing end, spindle motor housing, column, and cutting fluid inlet during the continuous machining of 18 boring holes, as well as real-time spindle output power data, with a data acquisition frequency of 1Hz. Assuming the machining time for a single boring hole is 60 seconds, the terminal divides the continuously acquired initial operating parameters into 60-second time units, obtaining a set of independent machine tool operating parameters for each boring hole. Taking the third boring hole as an example, the machine tool operating parameters may include the following: spindle front bearing temperature: 42.3℃; spindle housing flange temperature: 32.5℃; intermediate rotating shaft bearing end cover temperature: 32.5℃; power input shaft bearing end cover temperature: 32.5℃; spindle motor housing temperature: 32.5℃; column temperature: 32.5℃; and cutting fluid inlet temperature: 32.5℃. The machine tool outputs 10KW when machining the boring hole to be tested.

[0028] Optionally, after acquiring the machine tool's operating parameters, the terminal can preprocess these parameters. For example, it can compare the temperature data at at least one location on the machine tool with the ambient temperature, subtract the ambient temperature from each temperature data point to obtain preprocessed temperature data. For instance, the preprocessed temperature data could be 0.1°C, 0.5°C, 1.3°C, 3.1°C, -1.6°C, or -2.3°C. By using the result of subtracting the ambient temperature from each temperature data point as input to the prediction model, the model input can be optimized, improving its robustness and ensuring that the model's prediction accuracy does not significantly degrade when the ambient temperature changes.

[0029] Step S102: Input the machine tool operating parameters into the prediction model to obtain the first boring depth.

[0030] The prediction model represents the relationship between the machine tool's operating state and the boring depth when the machine tool processes a boring hole of the same type as the boring hole to be tested. The first boring depth is the processing depth of the boring hole to be tested.

[0031] The following explains how to obtain the prediction model: The terminal can acquire initial historical machine tool operating parameters for a preset time period. These parameters include the continuous temperature at at least one position of the machine tool during the machining of at least one reference bore, and the power output during the machining of that reference bore. The reference bore and the bore to be tested are of the same type. For example, historical machine tool operating parameters may include: spindle front bearing temperature: 45.3℃; spindle housing flange temperature: 32.8℃; intermediate rotating shaft bearing end cover temperature: 32.8℃; power input shaft bearing end cover temperature: 32.5℃; spindle motor housing temperature: 33.5℃; column temperature: 33.5℃; and position T8: cutting fluid inlet temperature: 32.6℃.

[0032] After acquiring the initial historical machine tool operating parameters, the terminal can divide these parameters based on the machining time for a single boring operation. These initial historical machine tool operating parameters are then standardized to obtain the final historical machine tool operating parameters. For example, suppose the machining time for a single boring operation is 10 minutes, and the initial historical machine tool operating parameters contain data from within one hour. The terminal can then divide the initial historical machine tool operating parameters according to the 10-minute machining time for a single boring operation. The ambient temperature is then subtracted from each temperature data point in the divided initial historical machine tool operating parameters to obtain standardized temperature data. For example, the standardized temperature data may include temperatures of 0.1°C, 0.5°C, 1.3°C, 3.1°C, -1.6°C, and -2.3°C.

[0033] After acquiring the initial historical machine tool operating parameters, the terminal can divide the initial historical machine tool operating parameters based on the machining time of a single boring operation, thus obtaining the historical machine tool operating parameters. These historical machine tool operating parameters include the temperature at at least one location of the machine tool during the machining of a single reference boring operation within a preset time period, as well as the power output of the machine tool during the machining of that single reference boring operation. For example, assuming the machining time for a single boring operation is 10 minutes, and the initial historical machine tool operating parameters contain data from within one hour, the terminal can divide the initial historical machine tool operating parameters based on a machining time of 2 minutes for a single boring operation, thus obtaining the historical machine tool operating parameters.

[0034] After obtaining the historical machine tool operating parameters, the terminal can further split these parameters (e.g., by random splitting, splitting according to a preset ratio, etc.) to obtain a training sample set and a validation sample set. The training sample set is a subset of the historical machine tool operating parameters, and the validation sample set is a subset of the historical machine tool operating parameters; the training sample set and the validation sample set are different.

[0035] After acquiring the training sample set and the validation sample set, the terminal can use a neural network model to train the training sample set until the validation sample set meets the preset evaluation criteria, thus obtaining the prediction model. For example, the preset evaluation criteria is that the error between the preset size and the actual size is less than an error threshold. As shown in Table 1, experimental verification shows that the GRU model has the smallest error compared to other models. Therefore, this application can use a neural network model to train the training sample set until the validation sample set meets the preset evaluation criteria, thus obtaining the prediction model.

[0036]

[0037] In some embodiments, because the dimensional fluctuations of some boring holes are small and not on the same order of magnitude as the reference size, directly predicting the size can easily mask the details of the fluctuations due to the magnitude of the reference size, resulting in low accuracy. In this case, the model's output can be set to the error size between the predicted size and the reference size, focusing on the key fluctuation parts, allowing the model to learn more accurate deviation patterns and making the output more realistic. For example, if the reference size for the boring hole is 100mm, and the depth fluctuation is only ±0.02mm, directly predicting a size of around 100mm will easily overlook the small fluctuations, resulting in a large prediction error. By changing the prediction to the error size between the hole and the 100mm reference size, the prediction model can focus on learning the fluctuation patterns within the ±0.02mm range, and the prediction results will more closely match actual machining deviations. Figure 4 , Figure 5 As shown, the higher the overlap between the two lines, the closer the predicted value is to the true value, and the better the model's prediction effect. The greater the deviation between the two lines, the greater the prediction error, and the worse the model performance. Experiments have verified that after adjusting the prediction model to output the error size between the predicted size and the reference size, the accuracy of the prediction model is significantly improved. Optionally, after adjusting the prediction model to output the error size between the predicted size and the reference size, the terminal can also monitor the quality of the bore to be tested based on whether the error size meets the alarm rules. For example, the alarm rule can be to compare the error size with an error threshold. If the absolute value of the error size is greater than the error threshold, the terminal can issue an alarm. Here, the error threshold is a value within the machining tolerance range of the bore to be tested. Optionally, after adjusting the prediction model to output the error size between the predicted size and the reference size, the terminal can also determine the first boring depth corresponding to the bore to be tested based on the error size and the reference size. For example, if the reference dimension for boring is 100mm and the tolerance dimension is -0.02mm, then the first boring depth is the sum of the reference dimension and the tolerance dimension, i.e., 100 - 0.02 = 99.98mm. As another example, if the reference dimension for boring is 100mm and the tolerance dimension is +0.03mm, then the first boring depth is the sum of the reference dimension and the tolerance dimension, i.e., 100 + 0.03 = 100.03mm.

[0038] In other embodiments, to address the problem that traditional models, when processing size prediction tasks, produce outputs with low variability and fail to reflect the true fluctuation characteristics of samples, this application addresses this issue by resetting the loss function. This applies additional loss penalties to the conservative prediction actions of the prediction model for samples with large size fluctuations. For example, a weighted loss function is designed to apply higher loss weights to samples with fluctuations exceeding a threshold. Figure 6 , Figure 7 As shown in the figure, experimental verification shows that the higher the overlap between the two lines, the closer the predicted value is to the true value, and the better the model's prediction performance. The greater the deviation between the two lines, the larger the prediction error and the worse the model performance. The prediction model with the improved loss function breaks through the limitation of predicting samples with large error sizes. It no longer tends to output conservative prediction values ​​close to the mean or a fixed interval, but can accurately fit the true fluctuation pattern of the sample. Compared with the traditional model, the prediction model with the improved loss function significantly reduces the prediction error and greatly improves the fit between the predicted value and the true value.

[0039] In practical implementation, since the prediction model requires significant computing power during the prediction process, and the electronic equipment deployed on the production site (including machine tools, industrial controllers, etc.) may be unable to run the prediction model due to limitations in hardware computing performance, a cloud-edge architecture control system can be set up to implement the method provided in this application embodiment. Electronic equipment located on the production site acts as the edge side, collecting machine tool operating parameters, preprocessing the data (e.g., subtracting ambient temperature from temperature data), and then reporting it to the cloud, where the prediction model is deployed. In this way, terminal preprocessing of data can solve data transmission redundancy, improve data quality, and enhance the response efficiency of the prediction model in the subsequent cloud server.

[0040] Optionally, the initial machine tool operating parameters may also include machining status data. This machining status data includes at least one or more of the following: part number, cycle start signal, cutting signal, spindle speed signal, and Z-coordinate. The Z-coordinate is the coordinate in the Z direction of the machine tool coordinate system. For example, part number: P20240518-003 (unique identifier for the machined part), cycle start signal: 1 (1 indicates start, 0 indicates stop, providing real-time feedback on whether machining has started), cutting signal: 1 (1 indicates cutting in progress, 0 indicates no cutting, determining whether the tool is in contact with the workpiece), spindle speed signal: 3000 rpm (real-time speed data, reflecting cutting efficiency), Z-coordinate: -15.2 mm (spindle axial position, reflecting machining depth). If the predictive model is deployed in the cloud, the terminal can bind a unique machining object through the part number, ensuring a one-to-one correspondence between data and parts and avoiding confusion. Combining the cycle start signal and cutting signal, it determines whether the current machining is in a normal state. If an abnormal situation occurs where "cycle start = 1, but cutting signal = 0", the terminal can immediately trigger an alarm, indicating a machining abnormality.

[0041] Optionally, since a single spindle machining system can accommodate multiple different types of boring holes, the boring depth requirements vary for different part numbers. For example, the required depth for the intake seat ring hole is 8.65±0.09mm; the required depth for the exhaust seat ring hole is 8.5±0.09mm. To improve the prediction accuracy of the prediction model, a single prediction model is trained and predicted only for the same type of boring hole. To differentiate prediction models for different types of boring holes, the terminal can use labels to mark the prediction model corresponding to the type of boring hole. Before inputting the test data set into the prediction model to obtain the first boring depth, the terminal can also determine the target prediction model based on the label of the boring hole to be tested. The target prediction model is the prediction model corresponding to the type of boring hole to be tested. The machine tool operating parameters are then input into the target prediction model to obtain the first boring depth.

[0042] Optionally, after obtaining the first boring depth, the terminal can determine whether the first boring depth meets the alarm rules. If the first boring depth meets the alarm rules, an alarm is issued. For example, the alarm rules compare the first boring depth with a first threshold and a second threshold respectively. If the first boring depth is less than the first threshold, or greater than the second threshold, the terminal can issue an alarm. For example, an SMS reminder can be sent to the technician. Another example is that the terminal can control a red light to illuminate and remind the technician. Optionally, the terminal can also control the machine tool to stop processing.

[0043] It is understood that the first threshold and the second threshold are values ​​within the tolerance range of the boring process to be tested. The aforementioned first threshold and second threshold are preset by those skilled in the art and can be changed. For example, the intake manifold hole depth requirement is 8.65 ± 0.09 mm. If the first threshold and the second threshold are taken as 80% of the tolerance, then for a tolerance of 0.09 mm, the value is 0.072 mm. Therefore, the first threshold is 8.65 - 0.072 = 8.578 mm, and the second threshold is 8.65 + 0.072 = 8.722 mm. As another example, if the threshold is taken as 90% of the tolerance, assuming a tolerance of 0.09 mm, the threshold is set to 0.081 mm. Therefore, the first threshold is 8.65 - 0.081 = 8.569 mm, and the second threshold is 8.65 + 0.081 = 8.731 mm.

[0044] Based on the same technological concept Figure 8 An exemplary schematic diagram of a boring depth prediction device provided in an embodiment of this application is shown, illustrating the process that the device can perform.

[0045] like Figure 8 As shown, the device specifically includes: The transceiver module 801 is used to acquire the machine tool operating parameters when the machine tool is machining the boring hole to be tested; The processing module 802 is used to input machine tool operating parameters into the prediction model to obtain the first boring depth. The prediction model represents the correspondence between the machine tool's operating state and the boring depth when the machine tool processes a boring of the same type as the boring to be tested. The first boring depth is the processing depth of the boring to be tested.

[0046] Optionally, the above prediction model is obtained in the following way: The transceiver module 801 is also used to: acquire historical machine tool operating parameters, including the temperature at at least one position of the machine tool when the machine tool is machining a single reference boring hole during a historical time period, and the power output of the machine tool when machining a single reference boring hole, wherein the reference boring hole and the boring hole to be tested belong to the same type; The processing module 802 is also used to: train the training sample set with a neural network model until the verification sample set meets the preset evaluation criteria to obtain a prediction model, wherein the training sample set is a subset of the historical machine tool operating parameters, the verification sample set is a subset of the historical machine tool operating parameters, and the training sample set and the verification sample set are different.

[0047] Optionally, the transceiver module 801 is specifically used to obtain the machine tool operating parameters when machining the bore to be tested, as described above. Obtain initial machine tool operating parameters, including the continuous temperature at at least one position of the machine tool when the machine tool is machining at least one reference boring hole within a preset time period, and the power output of the machine tool when machining at least one reference boring hole; The processing module 802 is specifically used to: divide the initial machine tool operating parameters based on the processing time of machining a single boring hole, and obtain the machine tool operating parameters, which include the temperature at at least one position of the machine tool when machining the boring hole to be tested, and the power output by the machine tool when machining the boring hole to be tested.

[0048] Optionally, before the above-mentioned input machine tool operating parameters are fed into the prediction model to obtain the first boring depth, the processing module 802 is also used for: The target prediction model is determined based on the label of the bore to be tested. The label is used to mark the correspondence between the bore type and the prediction model. Different types of bores correspond to different prediction models. The target prediction model is the prediction model corresponding to the type of bore to be tested. The machine tool operating parameters are input into the prediction model to obtain the first boring depth, specifically including: Input the machine tool operating parameters into the target prediction model to obtain the first boring depth.

[0049] Optionally, after the above-mentioned input machine tool operating parameters are fed into the prediction model to obtain the first boring depth, the processing module 802 is further used for: If the depth of the first boring hole meets the alarm rules, an alarm is issued.

[0050] Optionally, the above neural network model is a gated recurrent unit (GRU).

[0051] Based on the same technical concept, embodiments of this application also provide an electronic device. Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0052] At least one processor 901 and a memory 902 connected to at least one processor 901. In this embodiment, the specific connection medium between the processor 901 and the memory 902 is not limited. Figure 9 The example shown is the connection between processor 901 and memory 902 via bus 900. Bus 900 is... Figure 9 The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. The Bus 900 can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 9 The term is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, the processor 901 can also be called a controller; there is no restriction on the name.

[0053] In this embodiment, the memory 902 stores instructions executable by at least one processor 901. By executing the instructions stored in the memory 902, the at least one processor 901 can execute the method for determining the obstacle avoidance mechanism of a self-developed UAV, as described above. The processor 901 can implement... Figure 8 The functions of each module in the device shown.

[0054] The processor 901 is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 902 and calling data stored in memory 902, the processor can perform various functions and process data, thereby monitoring the device as a whole.

[0055] In one possible design, processor 901 may include one or more processing units. Processor 901 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, driver interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 901. In some embodiments, processor 901 and memory 902 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0056] The processor 901 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method for determining an obstacle avoidance mechanism for a self-developed UAV disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0057] Memory 902, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 902 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 902 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 902 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0058] By designing and programming the processor 901, the code corresponding to the method for determining the obstacle avoidance mechanism of a self-developed UAV described in the aforementioned embodiments can be embedded into the chip, thereby enabling the chip to execute the code during runtime. Figure 2 The illustrated embodiment presents a method for determining an obstacle avoidance mechanism for a self-developed UAV model. How to design and program the processor 901 is a technique well-known to those skilled in the art and will not be described further here.

[0059] It should be noted that the electronic device provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0060] This application also provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute a method for determining an obstacle avoidance mechanism for a self-developed UAV as described in the above embodiments.

[0061] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the function specified in one or more boxes.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0065] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for predicting boring depth, characterized in that, The method includes: Obtain the machine tool operating parameters when machining the bore to be tested; The machine tool operating parameters are input into the prediction model to obtain the first boring depth. The prediction model represents the correspondence between the machine tool's operating state and the boring depth when the machine tool processes a boring hole of the same type as the boring hole to be tested. The first boring depth is the processing depth of the boring hole to be tested.

2. The method according to claim 1, characterized in that, The prediction model was obtained in the following way: Obtain historical machine tool operating parameters, including the temperature at at least one position of the machine tool when the machine tool was machining a single reference boring hole during a historical time period, and the power output of the machine tool when machining the single reference boring hole, wherein the reference boring hole and the boring hole to be tested belong to the same type; A neural network model is used to train the training sample set until the verification sample set meets the preset evaluation criteria to obtain the prediction model. The training sample set is a subset of the historical machine tool operating parameters, and the verification sample set is a subset of the historical machine tool operating parameters. The training sample set and the verification sample set are different.

3. The method according to claim 1, characterized in that, The acquisition of machine tool operating parameters during the machining of the bore to be tested specifically includes: Obtain initial machine tool operating parameters, which include the continuous temperature at at least one position of the machine tool when the machine tool is machining at least one reference boring hole within a preset time period, and the power output by the machine tool when machining the at least one reference boring hole; The initial machine tool operating parameters are determined based on the processing time of machining a single boring hole, and the machine tool operating parameters are obtained. The machine tool operating parameters include the temperature at at least one position of the machine tool when machining the boring hole to be tested, and the power output by the machine tool when machining the boring hole to be tested.

4. The method according to claim 1, characterized in that, Before inputting the machine tool operating parameters into the prediction model to obtain the first boring depth, the method further includes: The target prediction model is determined based on the label of the bore to be tested. The label is used to mark the correspondence between the bore type and the prediction model. Different types of bores correspond to different prediction models. The target prediction model is the prediction model corresponding to the type of the bore to be tested. The step of inputting the machine tool operating parameters into the prediction model to obtain the first boring depth specifically includes: The first boring depth is obtained by inputting the machine tool operating parameters into the target prediction model.

5. The method according to any one of claims 1 to 4, characterized in that, After inputting the machine tool operating parameters into the prediction model to obtain the first boring depth, the method further includes: If the depth of the first boring hole meets the alarm rules, an alarm is issued.

6. The method according to claim 2, characterized in that, The neural network model is a gated recurrent unit (GRU).

7. A boring depth prediction device, characterized in that, The device includes: The transceiver module is used to acquire machine tool operating parameters when the machine tool is machining the bore to be tested; The processing module is used to input the machine tool operating parameters into the prediction model to obtain the first boring depth, wherein the prediction model represents the correspondence between the machine tool's operating state and the boring depth when the machine tool processes a boring hole of the same type as the boring hole to be tested, and the first boring depth is the processing depth of the boring hole to be tested.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for causing the computer to perform the method of any one of claims 1-6.

10. A computer program product, characterized in that, When the computer program product is invoked by a computer, it causes the computer to perform the method as described in any one of claims 1-6.

Images