Crosshead bushing inlaying processing method, system and equipment and medium
By employing collaborative computing rules and liquid nitrogen cooling technology, efficient and precise inlay processing of crosshead bushings has been achieved, solving the problems of high cost, low precision, and insufficient adaptability, and meeting diverse needs.
Patent Information
- Application Number
- CN202511805356.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-03
- Publication Date
- 2026-01-09
- Estimated Expiration
- 2045-12-03
AI Technical Summary
Existing technologies for crosshead bushing inlay processing suffer from high costs, low processing accuracy, and insufficient adaptability, especially when faced with new materials, non-standard sizes, and special working conditions.
By adopting collaborative calculation rules, combined with the standard shrinkage calculation mode and machine learning calculation mode, the shrinkage of the bushing under liquid nitrogen cooling conditions is determined. The inner and outer cylindrical surfaces of the bushing are precision machined in one go, and the bushing is installed into the crosshead under liquid nitrogen cooling conditions to form a stable interference fit.
It has achieved a reduction of processing cycle by more than 50%, reduced logistics and spare parts inventory costs, improved processing accuracy and adaptability, adapted to new materials and special working conditions, and expanded the scope of application of the technology.
Smart Images

Figure CN121289952A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of processing, and particularly relates to a crosshead bushing embedding processing method, system, device and medium. BACKGROUND
[0002] As core power equipment in the fields of petrochemical industry, oil and gas exploitation, etc., the crosshead bushing is a key vulnerable component in the transmission mechanism of the piston compressor, directly affecting the operation stability and service life of the compressor. The crosshead bushing needs to be precisely matched with the crosshead body and the crosshead pin, and the embedding processing quality of the crosshead bushing directly determines the assembly accuracy and smoothness of the three, which is one of the core links of the compressor manufacturing and maintenance.
[0003] At present, the mainstream crosshead bushing embedding processing in the industry adopts a "three-step method" process, and the specific process is as follows: first, the outer cylindrical surface of the crosshead bushing is precisely processed or ground to meet the interference fit size requirement with the crosshead hole; then, the bushing is fixed and assembled into the crosshead hole through cold assembly or press assembly; finally, the inner cylindrical surface of the bushing needs to be precisely processed or ground again to ensure that it forms a gap fit with the crosshead pin in accordance with the design standard.
[0004] However, the traditional process has many outstanding problems in actual application:
[0005] Firstly, the cost loss is significant. Since the crosshead body needs to be clamped and processed twice, and some compressor plants lack high-precision processing equipment, the crosshead body needs to be returned to the factory or outsourced for processing, which generates high logistics costs, spare parts storage costs and outsourcing processing fees, especially for large compressors (such as 1600KW oil field booster compressors), the processing cycle in the factory is as long as several weeks, which seriously affects the equipment operation efficiency;
[0006] Secondly, the processing precision is difficult to guarantee. Positioning deviation is easy to occur in the two clamping processes, and the system error of the processing equipment is added, which leads to poor consistency of the fit clearance between the bushing inner hole and the crosshead pin. It is necessary to rely on workers with high grinding technology to perform on-site manual grinding to meet the requirement of more than 85% of the fitting area. This not only further increases the labor cost, but also is affected by the difference in the skill level of workers, making it difficult to stably control the processing quality;
[0007] Thirdly, the process adaptability is insufficient. When facing new materials (such as high-strength alloy, wear-resistant copper alloy), non-standard size customization or special working conditions such as high temperature and high pressure, the traditional three-step method cannot dynamically adjust the parameters, which is easy to cause problems such as tight fit, looseness or early wear, and is difficult to meet the diversified application requirements. SUMMARY
[0008] The application aims to provide a crosshead bushing inlay processing method, system, device and medium to solve the problems of high cost, low processing precision and insufficient adaptability in the prior art.
[0009] To achieve the above-mentioned purpose, the application adopts the following technical solutions:
[0010] In a first aspect, the application provides a crosshead bushing inlay processing method, which comprises:
[0011] Obtaining the design size and interference range of the crosshead and the bushing;
[0012] Determining the bushing shrinkage under the condition of liquid nitrogen cooling based on a cooperative calculation rule composed of a preset shrinkage standard calculation mode and a machine learning calculation mode;
[0013] Determining the outer diameter processing size range and the inner diameter processing size range of the bushing according to the bushing shrinkage and the interference range;
[0014] Generating a processing control instruction based on the outer diameter processing size range and the inner diameter processing size range of the bushing, sending the processing control instruction to a processing unit, and grinding the bushing when the processing unit responds to the processing control instruction;
[0015] After the grinding processing, generating an assembly instruction, sending the assembly instruction to an assembly unit, and cooling the bushing under the condition of liquid nitrogen cooling and assembling the cooled bushing into the crosshead when the assembly unit responds to the assembly instruction.
[0016] Preferably, the cooperative calculation rule is:
[0017] Calling the shrinkage standard calculation mode to determine the shrinkage standard value;
[0018] Obtaining the material and processing condition of the crosshead and the bushing, determining the processing scene of the bushing through a preset rule, and the processing scene is a standard scene, a transition scene or a complex scene;
[0019] When the processing scene is the standard scene, the shrinkage standard value is directly used as the bushing shrinkage;
[0020] When the processing scene is the transition scene, the machine learning calculation mode is called to predict the correction coefficient of the shrinkage; the shrinkage standard value is corrected according to the correction coefficient of the shrinkage to obtain the corrected shrinkage, and the corrected shrinkage is used as the bushing shrinkage;
[0021] When the processing scene is the complex scene, the machine learning calculation mode is called to predict the predicted value of the shrinkage; the predicted value of the shrinkage and the shrinkage standard value are weighted and fused based on a preset weighting coefficient to obtain the fused shrinkage, and the fused shrinkage is used as the bushing shrinkage.
[0022] Preferably, the standard calculation method for shrinkage is as follows:
[0023] Obtain the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead, and the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the bushing;
[0024] The first coefficient is determined based on the bushing's Poisson's ratio, nominal outer diameter, and nominal inner diameter;
[0025] The second coefficient is determined based on the Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead;
[0026] Select an initial value from the interference range as the selection value, and determine the interference pressure based on the selection value, the second coefficient, the first coefficient, the elastic modulus of the crosshead, the elastic modulus of the bushing, and the nominal outer diameter.
[0027] The standard value of shrinkage is determined based on the interference fit pressure, the elastic modulus of the bushing, the nominal outer diameter, and the nominal inner diameter.
[0028] Preferably, the initial value is the middle or maximum value within the interference range.
[0029] Preferably, the method further includes:
[0030] Record actual processing data under standard scenarios and determine processing deviations;
[0031] Record the trend of processing deviation. Based on the trend of processing deviation, determine the correction coefficient of the selected value to correct the selected value and obtain the corrected selected value. The corrected selected value is within the interference range.
[0032] Preferably, when the processing scenario is a transitional scenario, the machine learning calculation mode adopts a gradient boosting tree correction model; when the processing scenario is a complex scenario, the machine learning calculation mode adopts a neural network adaptation model.
[0033] Preferably, the processing conditions include: processing temperature and processing pressure, and the preset rules are:
[0034] Establish reference standards for processing temperature, processing pressure, and the material and design dimensions of bushings and crossheads;
[0035] When the processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead all meet the reference standards, the processing scenario is the standard scenario.
[0036] When any parameter in the processing temperature, processing pressure, or the material and design dimensions of the bushing and crosshead deviate from the reference standard, the processing scenario is a transitional scenario.
[0037] When two or more parameters, such as processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead, deviate from the reference standard, or when the processing scenario is complex.
[0038] Secondly, the present invention provides a crosshead bushing inlay processing system for implementing the above-mentioned crosshead bushing inlay processing method, the system comprising:
[0039] The data acquisition module is used to obtain the design dimensions and interference range of the crosshead and bushing;
[0040] The first calculation module is used to determine the bushing shrinkage under liquid nitrogen cooling conditions based on the collaborative calculation rules consisting of a preset shrinkage standard calculation mode and a machine learning calculation mode.
[0041] The second calculation module is used to determine the range of outer diameter machining dimensions and inner diameter machining dimensions of the bushing based on the bushing shrinkage and interference range.
[0042] The first instruction generation module is used to generate machining control instructions based on the outer diameter machining size range and the inner diameter machining size range of the bushing, and send the machining control instructions to the machining unit. The machining unit performs grinding machining on the bushing when responding to the machining control instructions.
[0043] The second instruction generation module is used to generate assembly instructions after grinding and send the assembly instructions to the assembly unit. When responding to the assembly instructions, the assembly unit cools the bushing under liquid nitrogen cooling conditions and inserts the cooled bushing into the crosshead.
[0044] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described crosshead bushing inlay machining method.
[0045] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described crosshead bushing inlay machining method.
[0046] The beneficial effects of this invention are:
[0047] 1. This invention accurately calculates the bushing shrinkage under liquid nitrogen cooling conditions through collaborative calculation rules. Based on this shrinkage, it determines the outer and inner diameter machining ranges for the bushing. The machining unit can then perform a one-time precision machining of the inner and outer cylindrical surfaces of the bushing according to these ranges. After cooling under liquid nitrogen, the bushing is then inserted into the crosshead. Once the bushing returns to room temperature, it forms a stable interference fit with the crosshead. Therefore, this invention utilizes the calculated outer and inner diameter machining ranges... Based on the processing size range, a two-step process of "one-time precision machining of the inner and outer cylindrical surfaces of the bushing + liquid nitrogen cold mounting" can be adopted, eliminating the cumbersome steps of secondary clamping, return to the factory or outsourcing processing, shortening the processing cycle by more than 50%. Especially for large compressors (such as 1600KW-level oilfield booster equipment), it can avoid long-distance transportation of the crosshead body, reducing logistics costs; and there is no need to purchase a complete crosshead assembly with bushing, only the bushing needs to be machined separately for on-site replacement, reducing spare parts inventory costs; at the same time, it avoids equipment damage and labor input for secondary processing, further reducing processing costs.
[0048] 2. The present invention adopts a collaborative calculation rule consisting of a preset standard shrinkage calculation mode and a machine learning calculation mode, which has strong adaptability and can flexibly adapt to new materials, non-standard size customization and special working conditions such as high temperature and high pressure, breaking through the application limitations of traditional processes and expanding the scope of application of the technology. Attached Figure Description
[0049] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:
[0050] Figure 1 This is a flowchart of a crosshead bushing inlay processing method provided in one embodiment of the present invention;
[0051] Figure 2 This is a block diagram of a crosshead bushing inlay processing system provided in one embodiment of the present invention;
[0052] Figure 3 This is a schematic diagram of parameters in a standard scenario provided by one embodiment of the present invention. Detailed Implementation
[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.
[0054] Example 1
[0055] Figure 1 This is a flowchart of a crosshead bushing inlay processing method according to one embodiment of the present invention. The application scenario of this processing method includes: a server, a controller, a processing unit, and an assembly unit. The controller is communicatively connected to the server, and both the processing unit and the assembly unit are electrically connected to the controller. The processing unit is used to perform precision machining and grinding of the bushing using a machine tool. The assembly unit is used to insert the bushing into the hole of the crosshead in an ultra-low temperature liquid nitrogen environment. The processing unit and the assembly unit are conventional equipment in the art, and their specific structures are not described in detail in this embodiment. The crosshead bushing inlay processing method of this embodiment runs on the controller, such as... Figure 1 As shown, the method includes steps S10 to S50.
[0056] Step S10: Obtain the design dimensions and interference range of the crosshead and bushing.
[0057] In this embodiment, a design database is pre-built on the server. Referring to the design manual for piston compressors, the design dimensions and interference fit range of the crosshead and bushing are entered into the design database for storage. Secondly, the design database also stores data such as the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead and bushing. When these data are needed, the design dimensions such as the inner and outer diameters of the bushing can be obtained by on-site input, and the interference fit range can be obtained by sending a query request to the server.
[0058] Step S20: Based on the collaborative calculation rules consisting of the preset shrinkage standard calculation mode and the machine learning calculation mode, determine the bushing shrinkage under liquid nitrogen cooling conditions.
[0059] In this embodiment, the collaborative computing rule is:
[0060] Step A1: Call the standard shrinkage calculation mode to determine the standard shrinkage value; the standard shrinkage calculation mode in this embodiment is as follows:
[0061] First, obtain the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead, and the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the bushing; determine the second coefficient based on the Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead, and determine the first coefficient based on the Poisson's ratio, nominal outer diameter, and nominal inner diameter of the bushing.
[0062] The expression for calculating the first coefficient is as follows:
[0063] (1);
[0064] In equation (1), C1 is the first coefficient, d1 is the nominal outer diameter of the bushing, d2 is the nominal inner diameter of the bushing, and v1 is the Poisson's ratio of the bushing.
[0065] The expression for calculating the second coefficient is as follows:
[0066] (2);
[0067] In equation (2), C2 is the second coefficient, d3 is the nominal outer diameter of the crosshead, d4 is the nominal inner diameter of the crosshead, v2 is the Poisson's ratio of the crosshead, and the nominal inner diameter d4 of the crosshead is the same as the nominal outer diameter d1 of the bushing.
[0068] Then, an initial value is selected from the interference range as the selection value. Based on the selection value, the second coefficient, the first coefficient, the elastic modulus of the crosshead, the elastic modulus of the bushing, and the nominal outer diameter, the interference pressure is determined.
[0069] Therefore, the expression for calculating the interference pressure in this embodiment is:
[0070] (3);
[0071] In equation (3), P is the interference pressure, E1 is the elastic modulus of the bushing, E2 is the elastic modulus of the crosshead, and ΔD is an initial value selected from the interference range. In this embodiment, the initial value is the middle or maximum value in the interference range.
[0072] Finally, the standard value of shrinkage is determined based on the interference fit pressure, the elastic modulus of the bushing, the nominal outer diameter, and the nominal inner diameter.
[0073] Therefore, the calculation expression for the standard value of shrinkage in this embodiment is:
[0074] (4);
[0075] In equation (4), △S is the standard value of shrinkage.
[0076] Step A2: Obtain the material and processing conditions of the crosshead and bushing, and determine the processing scenario of the bushing by preset rules. The processing scenario is a standard scenario, a transitional scenario, or a complex scenario.
[0077] The processing conditions in this embodiment mainly include two parameters: processing temperature and processing pressure. The preset rules for this embodiment are as follows:
[0078] Establish reference standards for processing temperature, processing pressure, and the materials and design dimensions of bushings and crossheads. For example, the reference standards could be: bushing material ZCuPbSn10 (lead bronze alloy), crosshead material QT600-3 (pearlitic ductile iron), crosshead outer diameter 145mm, crosshead inner diameter 98mm, crosshead outer diameter 98mm, crosshead inner diameter 86mm, processing temperature 10~50℃, and processing pressure at atmospheric pressure.
[0079] When any one of the parameters—processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead—deviates from the reference standard, the processing scenario is a transitional scenario; when any one of the parameters—processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead—deviates from the reference standard, the processing scenario is a complex scenario.
[0080] Step A3: When the processing scenario is a standard scenario, the standard shrinkage value is directly used as the bushing shrinkage value.
[0081] Therefore, in standard scenarios, the bushing shrinkage can be directly calculated using the standard shrinkage calculation mode, reducing calculation time and ensuring batch processing efficiency. This embodiment uses parameters under standard scenarios as an example, such as... Figure 3 As shown.
[0082] Will Figure 3 Substituting the parameters of the standard scenario into formulas (1) and (2), the first coefficient can be calculated as 7.369275362; the second coefficient is 7.369275362; then according to formula (3), the interference pressure can be calculated as 5.9240767 MPa; finally, according to formula (4), the standard value of shrinkage can be calculated as 0.066 mm; it should be noted that the above calculation results are approximate values after retaining a certain number of decimal places.
[0083] As a further optimization of this embodiment, since △D in formula (3) is an initial value selected within the interference range, and the size of this initial value will affect the accuracy of the final shrinkage standard value, in order to improve the calculation accuracy of the shrinkage standard calculation mode, the selected value is dynamically adjusted during the processing; specifically as follows: record the actual processing data under the standard scenario and determine the processing deviation; record the changing trend of the processing deviation, and determine the correction coefficient of the selected value according to the changing trend of the processing deviation (if the changing trend of the processing deviation is that the processing deviation is gradually increasing, then the subsequent correction operation is performed), so as to correct the selected value and obtain the corrected selected value, which is within the interference range.
[0084] In this embodiment, when employing a dynamic adjustment strategy, the initial selection value is preferably the middle value within the interference range. When the corrected selection value is less than the minimum value within the interference range, the minimum value within the interference range is directly used. Similarly, when the corrected selection value is greater than the maximum value within the interference range, the maximum value within the interference range is directly used. If the processing deviation continues to increase when selecting either the maximum or minimum value within the interference range, an alarm signal is generated to trigger a fault alarm, enabling fault diagnosis and troubleshooting of the processing unit.
[0085] Step A4: When the processing scenario is a transitional scenario, call the machine learning calculation mode to predict the correction coefficient of shrinkage; correct the standard value of shrinkage according to the correction coefficient of shrinkage to obtain the corrected shrinkage, and use the corrected shrinkage as the bushing shrinkage.
[0086] In this embodiment, when the processing scenario is a transitional scenario, the machine learning calculation mode adopts the Gradient Boosting Tree (GBRT) correction model. The GBRT in this embodiment iteratively trains a weak classifier (decision tree), focusing on optimizing the error of the previous model. It can accurately capture the nonlinear relationship between the standard shrinkage value and the deviation of a single variable (a parameter deviating from the reference standard) (e.g., the correction law of the gap fit amount for every 10°C increase in temperature), and the correction result is more consistent with the actual processing error. Furthermore, the decision tree structure of GBRT can clearly present the mapping path of "input variable (e.g., temperature) → correction coefficient," and can directly output the explicit basis of "due to high temperature: 80°C, correction coefficient: 1.05," maintaining consistency with the "traceability" of the standard shrinkage calculation mode, facilitating manual review and process compliance verification. Secondly, the single variable deviation data in the transitional scenario is easy to collect (e.g., processing errors at different temperatures), allowing for the training of a high-precision correction model without massive amounts of data. The training speed is also fast, enabling rapid adaptation to the correction needs of different single variables (temperature, pressure, minor material adjustments).
[0087] Step A5: When the processing scenario is a complex scenario, call the machine learning calculation mode to predict the predicted amount of shrinkage; based on the preset weighting coefficient, the predicted amount of shrinkage and the standard value of shrinkage are weighted and fused to obtain the fused shrinkage amount, and the fused shrinkage amount is used as the bushing shrinkage amount.
[0088] In this embodiment, when the processing scenario is complex, the machine learning computing mode acquires an neural network (ANN) adaptation model; the neural network (ANN) adaptation model of this embodiment has the following advantages:
[0089] In complex scenarios, multiple variables such as material, size, and working conditions are coupled with each other (e.g., the elastic modulus of a new material and the wall thickness of a non-standard size jointly affect the shrinkage). The multi-layer neural network structure of ANN can automatically learn the complex nonlinear relationships between multiple variables and achieve accurate mapping of "multiple inputs → multiple outputs" without the need for manual pre-setting of coupling rules.
[0090] When faced with unknown scenarios such as new materials (without historical processing data) and non-standard sizes (without formulas for direct calculation), ANN can learn from data on similar materials and similar size ratios to transfer and adapt processing parameters to new scenarios. Furthermore, in complex scenarios, some parameters may be missing (such as some mechanical properties of new materials not being fully tested). ANN can automatically make up for the impact of missing data through the distributed storage and computation of network nodes.
[0091] Therefore, the collaborative calculation rules composed of the preset shrinkage standard calculation mode and the machine learning calculation mode adopted in this embodiment have strong adaptability and can flexibly adapt to new materials, non-standard size customization and special working conditions such as high temperature and high pressure, breaking through the application limitations of traditional processes and expanding the scope of application of the technology.
[0092] Step S30: Determine the range of outer diameter machining dimensions and inner diameter machining dimensions of the bushing based on the bushing shrinkage and interference range.
[0093] In this embodiment, the minimum value of the outer diameter machining dimension range of the bushing is:
[0094] d 1min =d1+△D min (5);
[0095] In equation (5), d 1min △D is the minimum value of the range of machined outer diameter dimensions for the bushing. min It is the minimum value within the range of interference.
[0096] In this embodiment, the maximum value of the outer diameter machining dimension range of the bushing is:
[0097] d 1max =d1+△Dmax (6);
[0098] In equation (6), d 1max △D represents the maximum value of the range of machined outer diameter dimensions for the bushing. max It is the maximum value within the range of interference.
[0099] In this embodiment, the minimum value of the inner diameter machining dimension range of the bushing is:
[0100] d 2min =d2+△S(7;
[0101] In equation (7), d 2min This is the minimum value within the range of machined inner diameter dimensions for the bushing.
[0102] In this embodiment, the maximum value of the inner diameter machining dimension range of the bushing is:
[0103] d 2max =d2+k△S(8;
[0104] In equation (8), d 2max The value represents the maximum value within the machining range of the bushing's inner diameter, and k is a proportionality coefficient, with the value being... .
[0105] Step S40: Based on the outer diameter machining range and inner diameter machining range of the bushing, generate machining control instructions and send the machining control instructions to the machining unit. The machining unit performs grinding machining on the bushing in response to the machining control instructions.
[0106] Step S50: After grinding, an assembly instruction is generated and sent to the assembly unit. When responding to the assembly instruction, the assembly unit cools the bushing under liquid nitrogen cooling conditions and inserts the cooled bushing into the crosshead. Therefore, by using ultra-low temperature liquid nitrogen to cool the bushing (to avoid deformation of the bushing's inner hole), the shrunken bushing is inserted into the hole of the crosshead body. After returning to normal temperature, the dimension of the inner cylindrical surface of the crosshead bushing directly reaches the mating clearance of the crosshead pin.
[0107] This embodiment can accurately calculate the bushing shrinkage under liquid nitrogen cooling conditions through collaborative calculation rules. Then, based on the bushing shrinkage, the outer diameter machining size range and inner diameter machining size range of the bushing are determined. The machining unit can then finish the inner and outer cylindrical surfaces of the bushing in one operation according to the outer diameter machining size range and the inner diameter machining size range. Then, under liquid nitrogen cooling conditions, the bushing is cooled and the cooled bushing is inserted into the crosshead. When the bushing returns to room temperature, it can form a stable interference fit with the crosshead.
[0108] Furthermore, based on the calculated range of outer and inner diameter machining dimensions, this embodiment can adopt a two-step process of "one-time precision machining of the inner and outer cylindrical surfaces of the bushing + liquid nitrogen cold mounting," eliminating the cumbersome steps of secondary clamping, return to the factory, or outsourcing machining, shortening the machining cycle by more than 50%. Especially for large compressors (such as 1600KW-level oilfield booster equipment), it can avoid long-distance transportation of the crosshead body, reducing logistics costs; and there is no need to purchase a complete crosshead assembly with bushing, only the bushing needs to be machined separately for on-site replacement, reducing spare parts inventory costs; at the same time, it avoids equipment damage and labor input for secondary machining, further reducing machining costs.
[0109] As a further optimization of this embodiment, a benchmark library and an algorithm training library are built on the server of this embodiment; the data in the algorithm training library is used to train the Gradient Boosting Tree (GBRT) and the Neural Network (ANN) to obtain the Gradient Boosting Tree (GBRT) correction model and the Neural Network (ANN) adaptation model.
[0110] The steps for constructing the benchmark library and the algorithm training library are as follows:
[0111] 1. Collect basic parameter data, calculation data, actual processing data, and error data.
[0112] The basic parameter data includes: material parameters (elastic modulus, Poisson's ratio) of crosshead, bushing, and crosshead pin, structural dimensions (inner and outer diameters of bushing, bore diameter of crosshead body), and operating parameters (temperature, pressure).
[0113] The calculation data includes: the bushing shrinkage amount and bushing machining dimensions (outer diameter machining dimension range and inner diameter machining dimension range) calculated using formulas (1) to (4).
[0114] The actual machining data includes: machine tool machining parameters (feed speed, depth of cut, spindle speed), machining process data (tool wear, machining time), and quality inspection data (actual dimensional deviation, roundness, surface defects).
[0115] Among them, the error data includes the deviation between the results of formulas (1) to (4) and the actual processing results.
[0116] 2. Data cleaning and standardization: The collected basic parameter data, calculation data, actual processing data, and error data are processed for missing values, outlier removal, and data standardization.
[0117] 3. Build a benchmark library: Store data of "input parameters - formula calculation results - actual processing feedback" under standard scenarios, classified by "material combination + size specification" (such as QT600-3 / ZCuPbSn10 material, φ98 / φ86mm size). Each data entry includes basic parameters, core parameters of formula calculation (interference, shrinkage, processing size), and the pass rate and error value of actual processing.
[0118] 4. Construct an algorithm training library: Integrate full data of standard and non-standard scenarios (complex working conditions, new materials, non-standard sizes), and label them according to "scenario type" (standard scenario, transitional scenario, complex scenario). Each data entry includes basic parameters, formula calculation results, actual processing results, and error data, which are used for training, verification, and iteration of GBRT and ANN to ensure that the algorithm can cover different application scenarios.
[0119] Example 2
[0120] Figure 2 This is a block diagram of a crosshead bushing inlay processing system provided in one embodiment of the present invention. Figure 2 As shown, this embodiment provides a crosshead bushing inlay machining system for implementing the crosshead bushing inlay machining method in Embodiment 1. The system includes:
[0121] The data acquisition module is used to obtain the design dimensions and interference range of the crosshead and bushing;
[0122] The first calculation module is used to determine the bushing shrinkage under liquid nitrogen cooling conditions based on the collaborative calculation rules consisting of a preset shrinkage standard calculation mode and a machine learning calculation mode.
[0123] The second calculation module is used to determine the range of outer diameter machining dimensions and inner diameter machining dimensions of the bushing based on the bushing shrinkage and interference range.
[0124] The first instruction generation module is used to generate machining control instructions based on the outer diameter machining size range and the inner diameter machining size range of the bushing, and send the machining control instructions to the machining unit. The machining unit performs grinding machining on the bushing when responding to the machining control instructions.
[0125] The second instruction generation module is used to generate assembly instructions after grinding and send the assembly instructions to the assembly unit. When responding to the assembly instructions, the assembly unit cools the bushing under liquid nitrogen cooling conditions and inserts the cooled bushing into the crosshead.
[0126] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the crosshead bushing inlay machining method in Embodiment 1.
[0127] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the crosshead bushing inlay machining method in Embodiment 1.
[0128] This embodiment can accurately calculate the bushing shrinkage under liquid nitrogen cooling conditions through collaborative calculation rules. Then, based on the bushing shrinkage, the outer diameter machining size range and inner diameter machining size range of the bushing are determined. The machining unit can then perform precision machining on the inner and outer cylindrical surfaces of the bushing in one operation according to the outer diameter machining size range and the inner diameter machining size range. Then, under liquid nitrogen cooling conditions, the bushing is cooled and the cooled bushing is inserted into the crosshead. When the bushing returns to room temperature, it can form a stable interference fit with the crosshead.
[0129] 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.
[0130] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will 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 system that specifies functions in one or more boxes.
[0131] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for inlaying crosshead bushings, characterized in that, The method includes: Obtain the design dimensions and interference range for the crosshead and bushing; Based on the collaborative calculation rules consisting of the preset shrinkage standard calculation mode and the machine learning calculation mode, the bushing shrinkage under liquid nitrogen cooling conditions is determined. Determine the range of outer diameter machining dimensions and inner diameter machining dimensions of the bushing based on the bushing shrinkage and interference range; Based on the outer diameter machining range and inner diameter machining range of the bushing, machining control instructions are generated and sent to the machining unit. The machining unit performs grinding machining on the bushing in response to the machining control instructions. After grinding, an assembly instruction is generated and sent to the assembly unit. When responding to the assembly instruction, the assembly unit cools the bushing under liquid nitrogen cooling conditions and inserts the cooled bushing into the crosshead.
2. The crosshead bushing inlay processing method according to claim 1, characterized in that, The collaborative computing rules are as follows: Call the standard shrinkage calculation mode to determine the standard shrinkage value; The material and processing conditions of the crosshead and bushing are obtained, and the processing scenario of the bushing is determined by preset rules. The processing scenario is a standard scenario, a transitional scenario, or a complex scenario. When the processing scenario is a standard scenario, the standard shrinkage value is directly used as the bushing shrinkage value; When the processing scenario is a transitional scenario, the machine learning calculation mode is invoked to predict the correction coefficient of shrinkage; the standard value of shrinkage is corrected according to the correction coefficient of shrinkage to obtain the corrected shrinkage, and the corrected shrinkage is used as the bushing shrinkage. When the processing scenario is complex, the machine learning calculation mode is invoked to predict the shrinkage amount; the predicted shrinkage amount and the standard shrinkage amount are weighted and fused based on the preset weighting coefficient to obtain the fused shrinkage amount, which is used as the bushing shrinkage amount.
3. The crosshead bushing inlay processing method according to claim 2, characterized in that, The standard calculation method for shrinkage is as follows: Obtain the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead, and the elastic modulus, Poisson's ratio, nominal outer diameter, and nominal inner diameter of the bushing; The first coefficient is determined based on the bushing's Poisson's ratio, nominal outer diameter, and nominal inner diameter; The second coefficient is determined based on the Poisson's ratio, nominal outer diameter, and nominal inner diameter of the crosshead; Select an initial value from the interference range as the selection value, and determine the interference pressure based on the selection value, the second coefficient, the first coefficient, the elastic modulus of the crosshead, the elastic modulus of the bushing, and the nominal outer diameter. The standard value of shrinkage is determined based on the interference fit pressure, the elastic modulus of the bushing, the nominal outer diameter, and the nominal inner diameter.
4. The crosshead bushing inlay processing method according to claim 3, characterized in that, The initial value is the middle or maximum value within the range of interference.
5. The crosshead bushing inlay processing method according to claim 3, characterized in that, The method further includes: Record actual processing data under standard scenarios and determine processing deviations; Record the trend of processing deviation. Based on the trend of processing deviation, determine the correction coefficient of the selected value to correct the selected value and obtain the corrected selected value. The corrected selected value is within the interference range.
6. The method for inlaying the crosshead bushing according to claim 2, characterized in that, When the processing scenario is a transitional scenario, the machine learning computing mode adopts a gradient boosting tree correction model; when the processing scenario is a complex scenario, the machine learning computing mode adopts a neural network adaptation model.
7. The method for inlaying crosshead bushings according to claim 2, characterized in that, The processing conditions include: processing temperature and processing pressure, and the preset rules are: Establish reference standards for processing temperature, processing pressure, and the material and design dimensions of bushings and crossheads; When the processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead all meet the reference standards, the processing scenario is the standard scenario. When any parameter in the processing temperature, processing pressure, or the material and design dimensions of the bushing and crosshead deviate from the reference standard, the processing scenario is a transitional scenario. When two or more parameters, such as processing temperature, processing pressure, and the material and design dimensions of the bushing and crosshead, deviate from the reference standard, or when the processing scenario is complex.
8. A crosshead bushing inlay machining system for implementing the crosshead bushing inlay machining method according to any one of claims 1-7, characterized in that, The system includes: The data acquisition module is used to obtain the design dimensions and interference range of the crosshead and bushing; The first calculation module is used to determine the bushing shrinkage under liquid nitrogen cooling conditions based on the collaborative calculation rules consisting of a preset shrinkage standard calculation mode and a machine learning calculation mode. The second calculation module is used to determine the range of outer diameter machining dimensions and inner diameter machining dimensions of the bushing based on the bushing shrinkage and interference range. The first instruction generation module is used to generate machining control instructions based on the outer diameter machining size range and the inner diameter machining size range of the bushing, and send the machining control instructions to the machining unit. The machining unit performs grinding machining on the bushing when responding to the machining control instructions. The second instruction generation module is used to generate assembly instructions after grinding and send the assembly instructions to the assembly unit. When responding to the assembly instructions, the assembly unit cools the bushing under liquid nitrogen cooling conditions and inserts the cooled bushing into the crosshead.
9. 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 crosshead bushing inlay machining method according to any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the crosshead bushing inlay machining method as described in any one of claims 1-7.
Citation Information
Patent Citations
Interference fit freezing method applied to main rollers
CN102211266A
Cylindrical pin assembling method based on interference magnitude control
CN112378305A
Welded bushing for double-screw pump and manufacturing process thereof
CN113757109A
Method for calculating interference magnitude of outer circle of water-lubricated bearing batten
CN117634069A
Mounting process for large-interference-magnitude metal sealing ring of ultrahigh-pressure container
CN120306954A