A method and system for bore positioning of a hydraulic manifold block

Abstract

The application provides a hole positioning machining method and system for a hydraulic manifold, and relates to the technical field of hole positioning machining. The method comprises the following steps: obtaining a hydraulic manifold design drawing and machine tool shaft numbers; generating multiple sets of hole drilling sequence schemes; determining multiple adjustment hole drilling schemes representing segmented drilling based on machining process data of an initial hole drilling scheme representing segmented drilling; determining a target hole drilling scheme representing segmented drilling based on machining process data of the multiple adjustment hole drilling schemes representing segmented drilling; determining target hole drilling schemes of multiple segmented drillings based on the target hole drilling scheme representing segmented drilling; and machining the multiple segmented drillings based on the target hole drilling schemes of the multiple segmented drillings. The method can quickly and accurately determine an optimal machining scheme of the hydraulic manifold.

Description

Technical Field

[0001] This invention relates to the field of hole positioning and machining technology, and specifically to a hole positioning and machining method and system for hydraulic integrated blocks. Background Technology

[0002] As a core component of hydraulic systems, the machining quality of the channels in hydraulic manifolds directly affects the operational accuracy, reliability, and service life of the entire hydraulic system. The structure of hydraulic manifolds is becoming increasingly complex, with a greater number of channels, larger differences in diameter, and denser spatial layouts. They often utilize difficult-to-machine materials such as high-strength alloys, placing stringent demands on the precision control, efficiency improvement, and process stability of channel machining. In traditional machining processes, the planning of hydraulic manifold channel machining relies heavily on manual experience or simple programmed logic, which is prone to problems such as channel deformation and tool interference due to limitations in experience. The setting of machining parameters often uses fixed templates, making it difficult to adapt to the differentiated requirements of different channel depths and material hardness, often resulting in excessive heat accumulation leading to out-of-tolerance hole wall accuracy or excessive tool wear. Furthermore, for multi-axis machine tools, traditional methods struggle to balance machining efficiency and process safety in optimizing hole combinations and arranging machining sequences, easily leading to excessively long machining cycles or insufficient quality stability. Simultaneously, with the increasing demand for personalized design of hydraulic manifolds, the small-batch, multi-variety production model significantly increases the requirements for the flexibility of machining solutions. Traditional methods relying on manual adjustments are not only slow in response time, but also struggle to achieve globally optimal planning in complex channel layouts, resulting in poor consistency in processing quality and a high scrap rate, thus hindering the improvement of the overall performance of the hydraulic system.

[0003] Therefore, how to quickly and accurately determine the optimal processing scheme for hydraulic integrated blocks is an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem this invention addresses is how to quickly and accurately determine the optimal processing scheme for hydraulic integrated blocks.

[0005] According to a first aspect, the present invention provides a method for machining the positioning of holes in a hydraulic integrated block, comprising: acquiring a hydraulic integrated block design drawing and a number of machine tool axes; generating multiple drilling sequence schemes using a generation model based on the hydraulic integrated block design drawing and the number of machine tool axes; determining a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes; acquiring machining process data of the initial drilling scheme representing the segmented drilling; determining multiple adjusted drilling schemes representing the segmented drilling based on the machining process data of the initial drilling scheme representing the segmented drilling; determining a target drilling scheme representing the segmented drilling based on the machining process data of the multiple adjusted drilling schemes representing the segmented drilling; determining target drilling schemes for multiple segmented drilling based on the target drilling scheme representing the segmented drilling; and machining the multiple segmented drilling based on the target drilling schemes for the multiple segmented drilling.

[0006] In one possible implementation, determining multiple adjusted drilling schemes representing segmented drilling based on the processing data of the initial drilling scheme representing segmented drilling includes: determining drilling adjustment information for the start segment, drilling adjustment information for the end segment, and the number of drilling segments for the middle segment based on the processing data of the initial drilling scheme representing segmented drilling; and determining multiple adjusted drilling schemes representing segmented drilling based on the drilling adjustment information for the start segment, the drilling adjustment information for the end segment, and the number of drilling segments for the middle segment.

[0007] In one possible implementation, determining the target drilling scheme for multiple segmented boreholes based on the target drilling scheme representing segmented boreholes includes: constructing multiple nodes and multiple edges, wherein the multiple nodes include a center node representing segmented boreholes and multiple segmented borehole nodes, the node features of the node representing segmented boreholes are the target drilling scheme representing segmented boreholes and the segmented borehole information, the node features of each segmented borehole node are the segmented borehole information, the center node representing segmented boreholes establishes edges with the multiple segmented borehole nodes respectively, and the features of the edges represent the degree of difference between the representative segmented borehole information and the segmented borehole information; and processing the multiple nodes and multiple edges based on a graph neural network to obtain the target drilling scheme for multiple segmented boreholes.

[0008] In one possible implementation, the generative model is a generative adversarial network.

[0009] According to a second aspect, the present invention provides a hole positioning and machining system for a hydraulic integrated block, comprising: an acquisition module for acquiring a hydraulic integrated block design drawing and a number of machine tool axes; a generation module for generating multiple drilling sequence schemes based on the hydraulic integrated block design drawing and the number of machine tool axes using a generation model; a scheme determination module for determining a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes; and a data acquisition module for acquiring the initial drilling scheme representing the segmented drilling. The system includes: a drilling process data module; an adjustment scheme determination module for determining multiple adjustment drilling schemes representing segmented drilling based on the initial drilling process data representing segmented drilling; a target determination module for determining a target drilling scheme representing segmented drilling based on the multiple adjustment drilling schemes representing segmented drilling; a segmentation scheme determination module for determining target drilling schemes for multiple segmented drilling based on the target drilling scheme representing segmented drilling; and a processing execution module for processing multiple segmented drilling based on the target drilling schemes for multiple segmented drilling.

[0010] In one possible implementation, the adjustment scheme determination module is further configured to: determine drilling adjustment information for the starting segment, drilling adjustment information for the ending segment, and the number of drilling segments for the intermediate segment based on the processing data of the initial drilling scheme representing segmented drilling; and determine multiple adjustment drilling schemes representing segmented drilling based on the drilling adjustment information for the starting segment, the drilling adjustment information for the ending segment, and the number of drilling segments for the intermediate segment.

[0011] In one possible implementation, the segmentation scheme determination module is further configured to: construct multiple nodes and multiple edges, wherein the multiple nodes include a representative segmented drilling center node and multiple segmented drilling nodes, the node features of the representative segmented drilling node are the target drilling scheme representing the segmented drilling and the segmented drilling information, the node features of each segmented drilling node are the segmented drilling information, the representative segmented drilling center node establishes edges with the multiple segmented drilling nodes respectively, and the features of the edges represent the difference between the representative segmented drilling information and the segmented drilling information; and process the multiple nodes and multiple edges based on a graph neural network to obtain the target drilling scheme for multiple segmented drilling.

[0012] In one possible implementation, the generative model is a generative adversarial network.

[0013] According to a third aspect, embodiments of the present invention provide an electronic device, including: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method including: acquiring a hydraulic integrated block design drawing and a number of machine tool axes; generating multiple drilling sequence schemes using a generative model based on the hydraulic integrated block design drawing and the number of machine tool axes; determining a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes; acquiring machining process data of the initial drilling scheme representing the segmented drilling; determining multiple adjusted drilling schemes representing the segmented drilling based on the machining process data of the initial drilling scheme representing the segmented drilling; determining a target drilling scheme representing the segmented drilling based on the machining process data of the multiple adjusted drilling schemes representing the segmented drilling; determining a target drilling scheme for the multiple segmented drilling based on the target drilling scheme representing the segmented drilling; and machining the multiple segmented drillings based on the target drilling scheme for the multiple segmented drilling.

[0014] According to a fourth aspect, this embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the aforementioned method for machining the positioning of holes in a hydraulic integrated block. The method includes: acquiring a hydraulic integrated block design drawing and a number of machine tool axes; generating multiple drilling sequence schemes using a generation model based on the hydraulic integrated block design drawing and the number of machine tool axes; determining a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes; acquiring machining process data of the initial drilling scheme representing the segmented drilling; determining multiple adjusted drilling schemes representing the segmented drilling based on the machining process data of the initial drilling scheme representing the segmented drilling; determining a target drilling scheme representing the segmented drilling based on the machining process data of the multiple adjusted drilling schemes representing the segmented drilling; determining target drilling schemes for multiple segmented drilling based on the target drilling scheme representing the segmented drilling; and machining the multiple segmented drilling based on the target drilling schemes for the multiple segmented drilling.

[0015] This invention provides a method and system for machining the positioning of holes in a hydraulic integrated block. The method includes: acquiring a hydraulic integrated block design drawing and the number of machine tool axes; generating multiple drilling sequence schemes using a generation model based on the hydraulic integrated block design drawing and the number of machine tool axes; determining a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes; acquiring machining process data of the initial drilling scheme representing the segmented drilling; determining multiple adjusted drilling schemes representing the segmented drilling based on the machining process data of the initial drilling scheme representing the segmented drilling; determining a target drilling scheme representing the segmented drilling based on the machining process data of the multiple adjusted drilling schemes representing the segmented drilling; determining target drilling schemes for multiple segmented drilling based on the target drilling scheme representing the segmented drilling; and machining multiple segmented drilling based on the target drilling schemes for multiple segmented drilling. This method can quickly and accurately determine the optimal machining scheme for the hydraulic integrated block. Attached Figure Description

[0016] Figure 1 A flowchart illustrating a method for locating and machining channels in a hydraulic integrated block, provided as an embodiment of the present invention;

[0017] Figure 2 This is a schematic diagram of a hydraulic integrated block according to an embodiment of the present invention;

[0018] Figure 3 This is a flowchart illustrating a process for determining multiple adjusted drilling schemes representing segmented drilling, provided by an embodiment of the present invention.

[0019] Figure 4 A flowchart illustrating a target drilling scheme for determining multiple segmented boreholes, provided by an embodiment of the present invention;

[0020] Figure 5 This is a schematic diagram of a hole positioning and machining system for hydraulic integrated blocks provided in an embodiment of the present invention. Detailed Implementation

[0021] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0022] In this embodiment of the invention, the following are provided: Figure 1 The method shown is a method for positioning and machining channels for hydraulic integrated blocks, the method comprising steps S1 to S8:

[0023] Step S1: Obtain the hydraulic integrated block design drawing and the number of machine tool axes.

[0024] A hydraulic manifold is a block-shaped component that integrates valves, channels, and interfaces in a hydraulic system. It connects different hydraulic components through pre-set internal oil passages, thereby achieving hydraulic oil distribution and control and simplifying system piping connections. Hydraulic manifolds improve the compactness and reliability of hydraulic systems. Figure 2 This is a schematic diagram of a hydraulic integrated block according to an embodiment of the present invention.

[0025] A hydraulic manifold design drawing is a digital 3D model generated by engineers using computer-aided design (CAD) to guide the manufacturing of the hydraulic manifold. Hydraulic manifold design drawings can be stored in standardized data formats (STEP, IGES, or parametric CAD files). The design drawing includes the geometric parameters, functional constraints, material properties, and manufacturing specifications of the hydraulic manifold.

[0026] Geometric parameters include the spatial location, diameter, depth, tilt angle, and spacing between adjacent channels.

[0027] Functional constraints include the connection logic between channels, the direction of hydraulic oil flow, and pressure level requirements.

[0028] Material properties include the material type of the integrated block body and the surface of the channels, as well as the heat treatment process requirements.

[0029] The processing specifications include process details such as surface roughness, tolerance range, and chamfering of orifices.

[0030] The number of machine tool axes is the number of motion axes that a machining center possesses, obtained from the machine tool configuration file. The number of axes determines the machine tool's degrees of freedom of movement and spatial positioning capabilities during machining. For example, if a machine tool has 2 axes (such as XY axes), it can precisely position and machine holes in a plane, and can machine two holes simultaneously. If it has 5 axes (such as XYZAB axes), it can achieve simultaneous machining of multiple holes in complex three-dimensional space, and can machine five holes simultaneously.

[0031] Step S2: Based on the hydraulic integrated block design drawing and the number of machine tool axes, generate multiple drilling sequence schemes using a generation model.

[0032] In some embodiments, the generative model is a generative adversarial network. The input to the generative model is the hydraulic integrated block design drawing and the number of machine tool axes, and the output of the generative model is multiple drilling sequence schemes.

[0033] Generative Adversarial Networks (GANs) consist of two networks: a generator and a discriminator. The generator produces fake data that conforms to a certain distribution, while the discriminator is responsible for distinguishing between the fake data generated by the generator and real data. Through adversarial training between the generator and the discriminator, the generator can continuously optimize its generation capabilities, eventually producing outputs that closely approximate the distribution of real data.

[0034] Multiple drilling sequence schemes are generated from a generative model to guide the machining sequence of holes in the hydraulic integrated block. Each drilling sequence scheme includes the machining order of each hole, the hole position combination based on the number of machine tool axes, and the timing arrangement.

[0035] Determining a drilling sequence can reduce the risk of hole deformation or tool interference, and provides multiple options from different weighting perspectives, such as prioritizing minimizing tool interference or shortening machining time. When machining materials such as high-strength alloys, machining small holes before large holes may cause stress redistribution, leading to deformation of the previously machined small holes or damage to the hole walls. Incorrect machining sequences can also cause tool interference with machined surfaces. In complex three-dimensional structures, improper machining sequences can make certain areas inaccessible, increasing machining difficulty and potentially causing irreparable damage.

[0036] The hydraulic integrated block design drawing includes spatial parameters such as the location, size, and material properties of the channels. These parameters define physical constraints such as the hole spacing and depth. The number of machine tool axes provides information on the parallel capability of the number of holes that the machine tool can process simultaneously. The number of machine tool axes can be mapped to the hole position combination rules in the sequence scheme through a generative adversarial network to ensure that the drilling sequence scheme meets the actual processing conditions.

[0037] Generative Adversarial Networks (GANs) possess powerful generation and optimization capabilities. Through an adversarial mechanism between the generator and discriminator, GANs can extract the layout features of hole distribution from hydraulic integrated block design drawings and, combined with constraints such as machine tool axis limitations, generate diverse drilling sequence schemes. These schemes are then continuously filtered and optimized. The generator can learn the hole relationships in the design drawings, such as the order of adjacent holes, to generate diverse drilling sequence schemes. The discriminator, on the other hand, can evaluate the feasibility of drilling sequence schemes based on physical constraint rules and a process knowledge base (stress distribution empirical model), thereby selecting multiple differentiated and feasible drilling sequence schemes.

[0038] Step S3: Based on the hydraulic integrated block design drawing, the multiple drilling sequence schemes, determine the target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and the initial drilling scheme representing the segmented drilling.

[0039] In some embodiments, a deep neural network model can be used to determine a target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and an initial drilling scheme representing the segmented drilling based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes. The input to the deep neural network model is the hydraulic integrated block design drawing and the multiple drilling sequence schemes, and the output of the deep neural network model is the target drilling sequence scheme, multiple segmented drilling information, representative segmented drilling information, and the initial drilling scheme representing the segmented drilling.

[0040] In some embodiments, determining the target drilling sequence scheme based on the hydraulic integrated block design drawing, the multiple drilling sequence schemes, multiple segmented drilling information, representative segmented drilling information, and the initial drilling scheme representing the segmented drilling includes steps S31 to S33:

[0041] Step S31: Based on the hydraulic integrated block design drawing and the multiple drilling sequence schemes, determine the feasibility score of the initial drilling sequence and mark the segmented processing requirements.

[0042] In some embodiments, a deep neural network can be used to determine the feasibility score of the initial drilling sequence and the segmented processing requirement label.

[0043] A deep neural network (DNN) is a neural network model consisting of multiple hidden layers. A DNN receives data through its input layer, which then performs nonlinear transformations and feature extraction on the data through neurons in the hidden layers, finally outputting the result through its output layer. DNNs can process high-dimensional data and can capture complex patterns by optimizing weights through backpropagation.

[0044] The feasibility score for the initial drilling sequence is a comprehensive evaluation of multiple drilling sequence schemes using a deep neural network. The score includes the tool interference risk index, estimated processing time, and stress distribution differences.

[0045] The segmented machining requirement markers are determined by a deep neural network to indicate the operations that need to be performed in stages during the hole machining process. The markers include suggestions on the number of segments for deep holes, cooling interval requirements for high-stress areas, and suggestions for adjusting complex hole paths.

[0046] The hydraulic integrated block design drawing provides the geometric parameters, material properties, and processing specifications of the channels. This information serves as the direct basis for layout constraints and segmented processing requirements. Multiple drilling sequence schemes encompass logical combinations of different processing sequences. These schemes are compared using a deep neural network to assess quantifiable tool interference risks, processing time differences, and stress distribution characteristics, thereby generating an initial feasibility score. By combining the physical constraints of the design drawing with the technological logic of the drilling schemes, the deep neural network can extract key features such as channel spacing thresholds and stress concentration area markers, thus deriving scoring indicators and segmented processing recommendations.

[0047] Deep neural networks can extract geometric parameters such as spatial location, diameter, depth, and tilt angle of channels from hydraulic integrated block design drawings, as well as attribute features such as material hardness and machining accuracy. They can also identify spatial relationships between channels through convolutional layers. Deep neural networks can perform temporal feature analysis on multiple drilling sequence schemes, then capture the sequential logic of channel machining in each scheme through recurrent layers. Simultaneously, by combining the material stress characteristics and hole distribution in the hydraulic integrated block design drawings, they can quantitatively calculate the tool interference risk index, machining time estimate, and stress distribution differences for each scheme, forming an initial drilling sequence feasibility score. For features such as deep channels and high-hardness material areas in the hydraulic integrated block design drawings, deep neural networks can combine the impact of the machining sequence in the drilling schemes on heat dissipation and stress, outputting segmented machining requirement labels through fully connected layers.

[0048] Step S32: Based on the initial drilling sequence feasibility score, the segmented processing requirement marking to determine the priority adjustment rules, the process parameter adaptation range, multiple segmented drilling information, representative segmented drilling information, and multiple preliminary target drilling sequence schemes.

[0049] In some embodiments, a deep neural network can be used to determine priority adjustment rules, process parameter adaptation range, multiple segmented drilling information, representative segmented drilling information, and multiple initial target drilling sequence schemes.

[0050] The priority adjustment rule is a dynamic adjustment criterion generated by a deep neural network to optimize the order of hole processing. The priority adjustment rule clearly defines the criteria for determining the priority of hole processing in different scenarios.

[0051] The process parameter adaptation range is a reasonable range of process parameters for each channel machining process, defined by the output of a deep neural network. This range specifies the upper and lower limits of machining control parameters for different channel characteristics such as depth, material hardness, and tilt angle. For example, for deep channels greater than 200mm, the machining speed adaptation range is 500-700 r / min, and the cooling interval adaptation range is 30-60 seconds. For high-hardness materials with a hardness greater than 30HRC, the feed rate adaptation range is 0.08-0.12 mm / rev.

[0052] Segmented drilling information is segmented machining information for the channels on the hydraulic integrated block, output by a deep neural network. Each segmented drilling information includes the number of segmented machining operations for each channel, the segment length for each segment, the machining speed for each segment, and the cooling interval between segments.

[0053] By determining the segmented drilling information, it is possible to adapt to the heat dissipation differences and processing difficulties at different depths of the channel, so as to avoid heat accumulation, channel deformation or tool wear caused by continuous processing. At the same time, it can ensure processing accuracy and efficiency, thereby ensuring that the channel processing process is stable and controllable.

[0054] As an example, the segmented drilling information for one of the channels A includes: Channel A has a total length of 250mm and is divided into 4 segments. The first segment has a machining length of 60mm, a machining speed of 800r / min, and a cooling interval of 30 seconds after machining; the second segment has a machining length of 70mm, a machining speed of 700r / min, and a cooling interval of 45 seconds after machining; the third segment has a machining length of 50mm, a machining speed reduced to 600r / min, and a cooling interval of 60 seconds after machining; the fourth segment has a machining length of 70mm, a machining speed maintained at 600r / min, and a cooling interval of 75 seconds after machining.

[0055] Representative segmented drilling information is the segmented machining information of a representative hole selected from multiple segmented drilling information. This representative segmented drilling information can reflect the common characteristics of other segmented drilling.

[0056] The multiple initial target drilling sequence schemes are a set of candidate processing sequence plans generated by screening the feasibility scores of the initial drilling sequence through a deep neural network and optimizing them by combining priority adjustment rules.

[0057] Deep neural networks, through nonlinear transformations across multiple hidden layers, can deeply integrate the feasibility score of the initial drilling sequence and the segmented processing requirement markings. The model can combine the deep hole segmentation suggestions in the segmented processing requirement markings with the hole depth in the layout constraints, thereby mapping the deep hole processing speed range within the process parameter adaptation range. Simultaneously, by ranking the feasibility scores and verifying their matching with the constraints, the model can filter out multiple initial target drilling sequence schemes that meet the requirements, and can generate representative segmented drilling information based on the similarity of hole features through clustering.

[0058] Step S33: Based on the priority adjustment rules, the process parameter adaptation range, the multiple preliminary target drilling sequence schemes, the representative segment drilling information, determine the target drilling sequence scheme and the initial drilling scheme for the representative segment drilling.

[0059] In some embodiments, a deep neural network can be used to determine the target drilling sequence scheme and the initial drilling scheme representing segmented drilling.

[0060] The target drilling sequence scheme is the optimal hole machining sequence plan determined from multiple drilling sequence schemes using a deep neural network. The target drilling sequence scheme includes the final determined machining order of each hole, the hole position combination based on the number of machine tool axes, and the timing arrangement.

[0061] The target drilling sequence scheme can minimize the risk of hole deformation and tool interference.

[0062] The initial drilling plan, representing segmented drilling, is the initial machining plan for segmented drilling output from the model, determined by the initial plan. The initial drilling plan for segmented drilling includes the segmented machining sequence representing the borehole, the toolpath, and specific machining parameters.

[0063] The segmented processing sequence representing the channel refers to the logical rules for the segments representing the channel, including the start position, end position, and number of segments for each segment.

[0064] Tool path refers to the specified movement trajectory of the cutting tool when machining representative segments of a hole. Tool path includes the specific forms of the feed, retraction, and cutting paths. For example, a helical feed path might be used in the first segment, a stepped cutting path in the second segment, and a straight feed / retraction path in the third segment.

[0065] The specific machining parameters include the machining control parameters for each segment, such as rotational speed (r / min), feed rate (mm / rev), and cooling interval time (seconds).

[0066] Deep neural networks can combine the priority adjustment rule of prioritizing large-diameter channels with the temporal logic of multiple initial target drilling sequence schemes, and then use weight optimization to select the target drilling sequence scheme that satisfies the minimum interference risk and the shortest processing time. At the same time, deep neural networks can map the segmented features representing segmented drilling information with the constraint boundary of the process parameter adaptation range, refine the segmented processing sequence, tool path and specific processing parameters representing the channel, and form the initial drilling scheme representing segmented drilling.

[0067] Step S4: Obtain the processing data of the initial drilling scheme representing segmented drilling.

[0068] The machining process data for the initial drilling plan representing segmented drilling is acquired through a sensor system integrated into the machining equipment. This data records the entire process of segmented drilling from the start of machining to the cooling of each segment during the execution of the initial drilling plan. The machining process data includes dynamic monitoring data of the segmented drilling, machining quality indicators, and records of abnormal events.

[0069] The dynamic monitoring data for machining includes changes in the surface temperature of the channel, the amplitude of tool vibration, and the state of cutting chips.

[0070] Processing quality indicators include hole wall surface roughness and hole diameter deviation.

[0071] The abnormal event log includes timestamps and locations of events such as tool wear, as well as records of machining interruptions caused by chip blockage.

[0072] Step S5: Based on the processing data of the initial drilling scheme representing segmented drilling, determine multiple adjusted drilling schemes representing segmented drilling.

[0073] In some embodiments, Figure 3 This is a flowchart illustrating a method for determining multiple adjusted drilling schemes representing segmented drilling, as provided in an embodiment of the present invention. The determination of these schemes includes steps S51-S52:

[0074] Step S51: Based on the processing data of the initial drilling scheme representing segmented drilling, determine the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment.

[0075] In some embodiments, a segmentation information determination model can be used to determine the drilling adjustment information for the start segment, the drilling adjustment information for the end segment, and the number of drilling segments in the middle segment. The segmentation information determination model is a Transformer model. The input to the model is the processing data of the initial drilling scheme representing segmented drilling, and the output is the drilling adjustment information for the start segment, the drilling adjustment information for the end segment, and the number of drilling segments in the middle segment.

[0076] The Transformer model is a neural network architecture based on a self-attention mechanism. It consists of an encoder and a decoder structure. The Transformer model can process sequential data through multi-head self-attention and capture long-range dependencies. The encoder maps the input sequence to hidden representations, and the decoder generates the output sequence. The Transformer model excels at handling variable-length sequences and can optimize feature extraction within a global context.

[0077] The initial drilling adjustment information is determined by segment information from the model output, specifying the process parameters that need to be modified in the initial machining stage of the initial drilling scheme representing segmented drilling. This initial drilling adjustment information includes parameter change commands such as the initial segment machining length correction value, speed adjustment amount, and cooling time correction value. For example, if the initial segment speed in the initial scheme is too high, causing an abnormal temperature rise, an adjustment command to reduce the speed is generated.

[0078] The drilling adjustment information for the final segment is determined by the segment information, which outputs the model to specify the process parameters that need to be modified during the final machining stage of the initial drilling plan representing the segmented drilling. This final segment drilling adjustment information includes parameter change commands such as the final segment machining length correction value, rotational speed adjustment amount, and cooling time correction value. For example, if the final segment temperature is detected to be too high, an adjustment command to increase the cooling interval is generated.

[0079] The number of drilling segments in the intermediate section is determined by segmentation information, which is the adjustment value of the number of segments output by the model for the representative segmented drilling in the intermediate processing stage.

[0080] The number of drilling segments in the middle section can be used to optimize heat distribution and stress control during deep hole machining. For example, the original plan is to process in 4 segments, but if the temperature in the middle section rises too quickly, the number of segments is increased to 5 to improve heat dissipation.

[0081] The processing data of the initial drilling scheme representing segmented drilling provides dynamic monitoring information and quality indicators during segmented processing. This data can be analyzed by the Transformer model to identify processing characteristics at each stage and pinpoint parameters requiring adjustment. The Transformer model can use a self-attention mechanism to parse time-series features in the processing data; for example, it can identify the correlation between rapid temperature rise and excessive rotational speed in the initial stage, thereby generating suggestions for adjusting the rotational speed. In the middle stage, the Transformer model can analyze the matching degree between the number of segments and material heat dissipation to dynamically optimize the number of segments. Furthermore, in the final stage, it can combine the relationship between cooling time and the quality of the hole end to adjust the cooling time. The Transformer model can capture the dependencies between stages through global attention, generating optimization and adjustment information covering the entire segmented process.

[0082] Step S52: Based on the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment, determine multiple adjustment drilling schemes representing segmented drilling.

[0083] In some embodiments, an adjustment scheme determination model can be used to determine multiple adjustment drilling schemes representing segmented drilling. The adjustment scheme determination model is a deep neural network, and its inputs are drilling adjustment information for the start segment, drilling adjustment information for the end segment, and the number of drilling segments in the middle segment. The output of the adjustment scheme determination model is multiple adjustment drilling schemes representing segmented drilling.

[0084] The multiple adjusted drilling schemes representing segmented drilling are a set of improved machining schemes for representative segmented drilling generated by the adjusted scheme determination model. Each adjusted drilling scheme includes a segmented machining sequence representing the hole, tool paths, and differentiated configurations of specific machining parameters.

[0085] Multiple adjustable drilling schemes representing segmented drilling can be weighted from perspectives such as prioritizing shorter processing time or prioritizing quality, to provide multiple options to adapt to processing needs.

[0086] The drilling adjustment information for the initial stage provides correction values ​​for process parameters during the initial machining phase, such as rotation speed adjustment and cooling time correction values. This can be used to optimize the thermal stress distribution and tool wear risk in the initial stage. The drilling adjustment information for the final stage provides correction values ​​for process parameters during the finishing machining phase, such as rotation speed adjustment and cooling time correction values. This can be used to reduce residual stress and improve the machining quality at the end of the hole. The drilling segment count for the intermediate stage provides adjustment values ​​for the number of segments in the intermediate machining phase. This can be used to balance heat distribution and stress control in deep hole machining, such as increasing the number of segments to improve heat dissipation.

[0087] Deep neural networks can process the drilling adjustment information of the initial and final segments, as well as the number of drilling segments in the middle segment, through multi-layer nonlinear transformations. The model can extract key information such as the rotational speed adjustment range and cooling time correction value from the initial and final segment adjustment information, and analyze the matching degree between the number of segments in the middle segment and material heat dissipation. The model can dynamically allocate weights based on design requirements, such as reducing the number of segments but increasing the rotational speed in efficiency-priority scenarios, and increasing the number of segments and extending the cooling time in quality-priority scenarios. Subsequently, the model can predict the optimal combination of each adjustment parameter through regression layers and generate multiple differentiated solutions by combining process knowledge bases (such as stress distribution empirical models). For example, if too few segments in the middle segment lead to excessively high temperatures in a certain solution, the model will increase the number of segments and adjust the cooling time to balance processing efficiency and quality.

[0088] Step S6: Determine the target drilling scheme representing the segmented drilling based on the processing data of multiple adjusted drilling schemes representing segmented drilling.

[0089] In some embodiments, a target scheme determination model can be used to determine a target drilling scheme representing segmented drilling. The target scheme determination model is a deep neural network, the input of which is processing data of multiple adjusted drilling schemes representing segmented drilling, and the output of which is the target drilling scheme representing the segmented drilling.

[0090] The target drilling plan, representing segmented drilling, is the optimal machining plan selected from multiple adjusted drilling plans. The target drilling plan for segmented drilling includes the segmented machining sequence representing the borehole, the toolpath, and specific machining parameters.

[0091] The machining process data of multiple adjustable drilling schemes representing segmented drilling provides dynamic monitoring information such as temperature changes and tool vibration after the adjustment drilling schemes are executed, as well as quality indicators such as surface roughness and dimensional deviations. Deep neural networks can analyze the actual performance of each adjustable drilling scheme using this machining process data. The deep neural network first extracts features from the machining process data of multiple adjustable drilling schemes, and then quantifies the performance indicators of each scheme (machining efficiency, quality pass rate, tool wear rate). The deep neural network fuses these indicators through multi-layer nonlinear transformations and constructs a comprehensive evaluation model to score each adjustment scheme. The deep neural network can prioritize schemes with stable machining processes, meeting quality standards, and high efficiency as representative target drilling schemes for segmented drilling.

[0092] Step S7: Determine multiple target drilling schemes for segmented drilling based on the target drilling scheme representing segmented drilling.

[0093] In some embodiments, Figure 4 This is a flowchart illustrating a target drilling scheme for determining multiple segmented boreholes, provided by an embodiment of the present invention. The determination of the target drilling scheme for multiple segmented boreholes includes steps S71-S72:

[0094] Step S71: Construct multiple nodes and multiple edges. The multiple nodes include a node representing the segmented drilling center and multiple segmented drilling nodes. The node characteristics of the node representing the segmented drilling are the target drilling scheme and the segmented drilling information. The node characteristics of each segmented drilling node are the segmented drilling information. The node representing the segmented drilling center establishes edges with the multiple segmented drilling nodes respectively. The edge characteristics represent the degree of difference between the node representing the segmented drilling information and the segmented drilling information.

[0095] The system comprises multiple nodes, including a central node representing the segmented borehole and multiple segmented borehole nodes. The central node represents the target drilling scheme and segmented borehole information. Each segmented borehole node represents its corresponding segmented borehole information. The central node establishes multiple edges with each of the segmented borehole nodes, with the edge characteristics indicating the degree of difference between the central node's information and the information of each individual segmented borehole.

[0096] In some embodiments, a deep neural network can be used to determine the degree of difference between the segmented borehole information and the segmented borehole information. The degree of difference includes the difference in borehole depth, material properties, and processing difficulty.

[0097] By constructing multiple nodes and edges, a structured relationship can be established between the optimal processing experience representing segmented drilling and the specific processing requirements of other segmented drilling. The target drilling scheme and segmented drilling information carried by the central node representing the segmented drilling serve as a validated optimization benchmark, providing a reference for other segmented drilling. The characteristics of multiple segmented drilling nodes clearly present the unique processing conditions of each hole, and the characteristics of the edges, by quantifying the differences between the two, accurately pinpoint the adjustment direction of different holes in processing parameter adaptation. Through this node-edge relationship structure, the common patterns of the benchmark scheme and the individual requirements of each hole can be systematically integrated, providing structured data support for exploring the dependencies between the central node and other nodes.

[0098] Step S72: Based on the graph neural network, process multiple nodes and multiple edges to obtain a target drilling scheme with multiple segmented drilling.

[0099] Graph Neural Networks (GNNs) are deep learning models capable of processing nodes and edges. GNNs update node features through a message-passing mechanism and allow each node to aggregate feature information from its neighboring nodes. By stacking multiple layers and fusing local and global topological information, the dependencies between the central node and other nodes can be uncovered.

[0100] In a structure with multiple nodes and edges, the central node representing segmented drilling carries the optimized and validated target drilling scheme and segmented drilling information. This information includes the confirmed effective segmented machining logic, toolpaths, and specific process parameters, serving as the benchmark for guiding the machining of other holes. The characteristics of multiple segmented drilling nodes are their respective segmented drilling information, clearly presenting the differences in geometric parameters (such as depth and diameter), material properties, and machining requirements of different holes. The characteristics of the edges between nodes represent the degree of difference between the representative segmented drilling information and the individual segmented drilling information. This difference reflects the differences in machining difficulty, heat dissipation requirements, and stress control among different holes, such as the difference in the number of segmentations required for deep holes versus shallow holes, and the difference in rotational speed adjustment requirements between high-strength alloys and ordinary materials. By processing the structure with multiple nodes and edges using a graph neural network, multiple target drilling schemes for segmented drilling can be generated. This helps ensure that the machining scheme for each hole both draws on the optimization experience of the representative hole and adapts to its own characteristics. Graph neural networks can use message passing mechanisms to propagate the optimal features representing the center node of segmented drilling to each segmented drilling node. Each node aggregates the feature information of its neighboring nodes and fuses the difference features to generate a processing scheme that takes into account both common patterns and individual needs, ensuring that all channels achieve the optimal balance in processing accuracy, efficiency and stability.

[0101] Step S8: Process the multiple segmented holes based on the target drilling scheme of the multiple segmented holes.

[0102] Once a target drilling scheme for multiple segmented drillings is determined, the multiple segmented drillings in the hydraulic integrated block are processed based on the target drilling scheme for multiple segmented drillings.

[0103] Based on the same inventive concept Figure 5 This is a schematic diagram of a hole positioning and machining system for a hydraulic integrated block provided by an embodiment of the present invention. The hole positioning and machining system for the hydraulic integrated block includes:

[0104] Module 81 is used to acquire the hydraulic integrated block design drawing and the number of machine tool axes;

[0105] The generation module 82 is used to generate multiple drilling sequence schemes based on the hydraulic integrated block design drawing and the number of machine tool axes using the generation model;

[0106] The scheme determination module 83 is used to determine the target drilling sequence scheme, multiple segment drilling information, representative segment drilling information, and representative segment drilling initial drilling scheme based on the hydraulic integrated block design drawing, the multiple drilling sequence schemes, multiple segment drilling information, representative segment drilling information, and representative segment drilling initial drilling scheme based on the hydraulic integrated block design drawing, the multiple drilling sequence schemes, multiple segment drilling information, representative segment drilling information, and representative segment drilling initial drilling scheme.

[0107] The data acquisition module 84 is used to acquire processing data representing the initial drilling scheme of segmented drilling;

[0108] The adjustment scheme determination module 85 is used to determine multiple adjustment drilling schemes representing segmented drilling based on the processing data of the initial drilling scheme representing segmented drilling.

[0109] The target determination module 86 is used to determine the target drilling scheme representing the segmented drilling based on the processing data of multiple adjusted drilling schemes representing segmented drilling.

[0110] The segmented drilling scheme determination module 87 is used to determine the target drilling scheme for multiple segmented boreholes based on the target drilling scheme representing the segmented boreholes.

[0111] The processing execution module 88 is used to process multiple segmented holes based on the target drilling scheme of the multiple segmented holes.

[0112] It should be noted that, in order to simplify the descriptions disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments of this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0113] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for machining channel positioning in hydraulic integrated blocks, characterized in that, include: Obtain the design drawings of the hydraulic integrated block and the number of machine tool axes; Based on the hydraulic integrated block design drawing and the number of machine tool axes, multiple drilling sequence schemes are generated using a generative model. Based on the hydraulic integrated block design drawing, the target drilling sequence scheme is determined by the multiple drilling sequence schemes, multiple segmented drilling information, representative segmented drilling information, and the initial drilling scheme representing the segmented drilling. Obtain the processing data of the initial drilling scheme representing segmented drilling; Based on the processing data of the initial drilling scheme representing segmented drilling, multiple adjusted drilling schemes representing segmented drilling are determined. The target drilling scheme representing segmented drilling is determined based on the machining process data of multiple adjusted drilling schemes representing segmented drilling. Based on the target drilling scheme representing segmented drilling, multiple target drilling schemes for segmented drilling are determined. The multiple segmented holes are processed based on the target drilling scheme.

2. The method for machining channel positioning for hydraulic integrated blocks as described in claim 1, characterized in that, The determination of multiple adjusted drilling schemes representing segmented drilling based on the processing data of the initial drilling scheme representing segmented drilling includes: Based on the processing data of the initial drilling scheme representing segmented drilling, determine the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment. Based on the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment, multiple adjustment drilling schemes representing segmented drilling are determined.

3. The method for machining channel positioning for hydraulic integrated blocks as described in claim 1, characterized in that, The determination of multiple target drilling schemes for segmented drilling based on the target drilling scheme representing segmented drilling includes: Construct multiple nodes and multiple edges. The multiple nodes include a node representing the center of the segmented drilling and multiple segmented drilling nodes. The node characteristics of the node representing the segmented drilling are the target drilling scheme and the segmented drilling information. The node characteristics of each segmented drilling node are the segmented drilling information. The node representing the center of the segmented drilling establishes edges with the multiple segmented drilling nodes. The edge characteristics represent the degree of difference between the node representing the segmented drilling information and the segmented drilling information. The target drilling scheme with multiple segmented drilling is obtained by processing multiple nodes and multiple edges based on graph neural networks.

4. The method for machining channel positioning for hydraulic integrated blocks as described in claim 1, characterized in that, The generative model is a generative adversarial network.

5. A hole positioning and machining system for hydraulic integrated blocks, characterized in that, include: The acquisition module is used to acquire hydraulic integrated block design drawings and machine tool axis counts; The generation module is used to generate multiple drilling sequence schemes based on the hydraulic integrated block design drawing and the number of machine tool axes using the generation model; The scheme determination module is used to determine the target drilling sequence scheme, multiple segment drilling information, representative segment drilling information, and representative segment drilling initial drilling scheme based on the hydraulic integrated block design drawing, the multiple drilling sequence schemes, multiple segment drilling information, representative segment drilling information, and representative segment drilling initial drilling scheme. The data acquisition module is used to acquire processing data representing the initial drilling scheme of segmented drilling; The adjustment scheme determination module is used to determine multiple adjustment drilling schemes representing segmented drilling based on the processing data of the initial drilling scheme representing segmented drilling. The target determination module is used to determine the target drilling scheme representing the segmented drilling based on the processing data of multiple adjusted drilling schemes representing segmented drilling. The segmented drilling scheme determination module is used to determine the target drilling scheme for multiple segmented boreholes based on the target drilling scheme representing the segmented boreholes. The processing execution module is used to process multiple segmented holes based on the target drilling scheme of the multiple segmented holes.

6. The hole positioning and machining system for hydraulic integrated blocks as described in claim 5, characterized in that, The adjustment scheme determination module is also used for: Based on the processing data of the initial drilling scheme representing segmented drilling, determine the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment. Based on the drilling adjustment information of the starting segment, the drilling adjustment information of the ending segment, and the number of drilling segments in the middle segment, multiple adjustment drilling schemes representing segmented drilling are determined.

7. The hole positioning and machining system for hydraulic integrated blocks as described in claim 5, characterized in that, The segmentation scheme determination module is also used for: Construct multiple nodes and multiple edges. The multiple nodes include a node representing the center of the segmented drilling and multiple segmented drilling nodes. The node characteristics of the node representing the segmented drilling are the target drilling scheme and the segmented drilling information. The node characteristics of each segmented drilling node are the segmented drilling information. The node representing the center of the segmented drilling establishes edges with the multiple segmented drilling nodes. The edge characteristics represent the degree of difference between the node representing the segmented drilling information and the segmented drilling information. The target drilling scheme with multiple segmented drilling is obtained by processing multiple nodes and multiple edges based on graph neural networks.

8. The hole positioning and machining system for hydraulic integrated blocks as described in claim 5, characterized in that, The generative model is a generative adversarial network.

9. An electronic device, characterized in that, include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the hole positioning machining method for a hydraulic integrated block as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the hole positioning machining method for hydraulic integrated blocks as described in any one of claims 1 to 4.

Images