Method for controlling X / Y-axis tangential precision of bottleneck station of bottle-making machine based on artificial intelligence

Abstract

The invention discloses a bottle-making machine bottleneck part station X / Y axis tangential precision control method based on artificial intelligence, and relates to the technical field of automatic control. The method comprises the following steps: constructing a machining process vibration model of a bottleneck part station by taking vibration intensity data as a first dependent variable and machining process parameters and machining material parameters as independent variables, obtaining a vibration intensity predicted value, extracting material removal rate data completed in unit time in a historical machining process, and taking the data as a quantitative characterization value of machining efficiency; the machining efficiency is used as a second dependent variable, the machining process parameters and the machining material parameters are used as independent variables, a machining efficiency evaluation model of the bottleneck part station is constructed, a machining efficiency prediction value is obtained, the minimum vibration strength and the maximum machining efficiency obtained at any moment in the machining process are used as control targets, a machining process optimization model is constructed, and the machining efficiency prediction value is obtained. And the optimal value of the parameters in the machining process is obtained, and accurate control over the X / Y-axis motion state of the bottleneck part station is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and particularly relates to a method for controlling the tangential accuracy of the X / Y axes at the bottle neck station of a bottle making machine based on artificial intelligence. Background Art

[0002] In a bottle making machine, the X / Y axes at the bottle neck station usually refer to the moving axes used for processing the bottleneck part. The X axis is usually used to control the feeding movement of processing tools (such as cutters, milling cutters, etc.) in the horizontal direction, and is mainly responsible for the radial processing of the bottle neck; the Y axis is usually used to control the movement of the processing tool in the vertical direction and is responsible for the axial processing of the bottle neck. Through the coordinated movement of the X axis and the Y axis, the processing of complex shapes of the bottle neck can be achieved, such as the taper, thread, chamfer, etc. of the bottleneck. The movement accuracy and control ability of the X axis and the Y axis also directly affect the processing quality of the bottle neck, including dimensional accuracy, shape accuracy, and surface quality, etc.

[0003] Currently, the main factors affecting the tangential accuracy of the X / Y axes at the bottle neck station of a bottle making machine include the following aspects:

[0004] 1) Mechanical system factors: Generally, both the X axis and the Y axis adopt a guide rail drive mode. The straightness, parallelism, and surface quality of the guide rail directly affect the movement accuracy of the axis. When the guide rail is worn or deformed, the tangential accuracy will decrease; transmission system error: The pitch error, backlash of the ball screw, and the accuracy of the transmission chain will all affect the tangential accuracy of the X / Y axes; bearing accuracy: The manufacturing accuracy, assembly accuracy of the bearing, and the wear during use will all have an impact on the movement accuracy of the X / Y axes.

[0005] 2) Control system factors: Numerical control system error: The software algorithm, parameter setting in the control system, and the accuracy of the feedback system will all affect the tangential accuracy; servo motor performance: The response speed, torque fluctuation of the servo motor, and the accuracy of the encoder will all have an impact on the movement accuracy of the X / Y axes.

[0006] 3) Process system factors: Process system stiffness: Insufficient stiffness of the X / Y axes may cause deformation during the processing, thereby affecting the tangential accuracy; influence of processing force: Acting forces such as cutting force and clamping force may cause deformation of the mechanical system, thereby affecting the processing accuracy.

[0007] 4) Environmental factors: Thermal deformation of mechanical components: Components such as machine tools, guide rails, and lead screws expand when heated during the processing, which may cause a decrease in the tangential accuracy of the X / Y axes; change in environmental temperature: In addition, fluctuations in the workshop environmental temperature may also cause thermal deformation of mechanical components.

[0008] 5) Other factors: Assembly and adjustment errors: The assembly accuracy, adjustment accuracy of the X / Y axes, and the installation accuracy of the tool will all affect the tangential accuracy; Tool wear: Tool wear during use will cause changes in the machining dimensions, thereby affecting the tangential accuracy of the bottle neck.

[0009] In view of the main influencing factors of the tangential accuracy of the X / Y axes at the bottle neck station of the bottle making machine, the following solutions have been proposed in the prior art: For the optimization measures of the mechanical system, the straightness and parallelism of the guide rails can be regularly checked, and the worn guide rail components can be replaced in a timely manner. Regularly detect the accuracy and wear of the ball screws and bearings in the drive system, and replace them if necessary. Optimize the structural design of the X / Y axes, increase the rigidity of mechanical components, and reduce deformation during the machining process. For the adjustment measures of the control system, the parameters of the servo motor, such as gain, resonance suppression, and load inertia, can be adjusted to improve the response speed and stability of the system. By adopting a full closed-loop control system and installing a high-precision linear grating scale to real-time feedback the position information of the axes, the tangential accuracy can be further improved. For the solutions to thermal deformation control, monitor the equipment and environmental temperatures during the machining process, and perform thermal deformation compensation through the control system to reduce the influence of temperature changes on the machining accuracy. And maintain the stability of the workshop temperature to avoid deformation of mechanical components caused by environmental temperature fluctuations. The above solutions taken for the decline in the tangential accuracy of the X / Y axes caused by mechanical system factors, control system factors, and environmental factors have achieved good application effects in the actual production process and improved the tangential accuracy of the X / Y axes to a certain extent.

[0010] However, in the prior art, for the optimization measures of the process, generally, by optimizing parameters such as cutting speed, feed rate, and cutting depth according to the machining requirements of the bottle neck, the vibration during the machining process can be reduced to improve the tangential accuracy. There is a lack of a process optimization control method that comprehensively analyzes the influencing mechanisms of multiple factors. Since the determination of machining parameters depends on various factors such as machining material properties, machining requirements, machining positions, and tool parameters, the machining parameters obtained by only analyzing a single machining requirement factor are difficult to achieve the expected accuracy control effect. Therefore, we propose an X / Y axis tangential accuracy control method for the bottle neck station of the bottle making machine based on artificial intelligence. Summary of the Invention

[0011] The main object of the present invention is to provide an X / Y axis tangential accuracy control method for the bottle neck station of the bottle making machine based on artificial intelligence, which can effectively solve the problems in the background technology.

[0012] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0013] An X / Y axis tangential accuracy control method for the bottle neck station of the bottle making machine based on artificial intelligence, comprising:

[0014] Step 1: Obtain the historical data of the processing parameters and processing material parameters at the bottle neck station.

[0015] The processing parameters include cutting speed, feed rate, and cutting depth; the processing material parameters include material hardness, material elastic modulus, and material thermal conductivity.

[0016] Step 2: Extract the vibration intensity data in the historical processing. Taking the vibration intensity data as the first dependent variable and the processing parameters and processing material parameters as independent variables, construct the processing vibration model for the bottle neck station, and use the processing vibration model to obtain the vibration intensity prediction value V vib ;

[0017] The expression of the processing vibration model is:

[0018]

[0019] In the formula, Vc is the cutting speed, with the unit of m / min; f is the feed rate, with the unit of mm / r; a p is the cutting depth, with the unit of mm; H is the hardness value of the processing material, with the unit of N / mm 2 ; E is the elastic modulus of the processing material, with the unit of GPa; k is the thermal conductivity of the processing material, with the unit of W / m·K; θ1 is the vibration correction coefficient of the cutting speed; θ2 is the vibration correction coefficient of the feed rate; θ3 is the vibration correction coefficient of the cutting depth; θ4 is the vibration correction coefficient of the material hardness; θ5 is the vibration correction coefficient of the material elastic modulus; θ6 is the vibration correction coefficient of the material thermal conductivity.

[0020] Step 3: Extract the material removal rate data completed per unit time in the historical processing as the quantitative characterization value of the processing efficiency. Taking the processing efficiency as the second dependent variable and the processing parameters and processing material parameters as independent variables, construct the processing efficiency evaluation model for the bottle neck station, and use the processing efficiency evaluation model to obtain the processing efficiency prediction value η.

[0021] The expression of the processing efficiency evaluation model is:

[0022] η = Vc·f·a p ·α(H)·γ(E)·μ(material type)

[0023] In the formula, Vc is the cutting speed, with the unit of m / min; f is the feed rate, with the unit of mm / r; a p is the cutting depth, with the unit of mm; μ(material type) is the material type correction coefficient; α(H) is the efficiency correction coefficient of the material hardness; γ(E) is the efficiency correction coefficient of the material elastic modulus;

[0024] The calculation formula for the efficiency correction coefficient α(H) of material hardness is as follows: where β is a constant coefficient; H is the hardness value of the processed material, with the unit of N / mm 2 ;

[0025] The calculation formula for the efficiency correction coefficient γ(E) of material elastic modulus is as follows: where δ is a constant coefficient; E is the elastic modulus of the processed material, with the unit of GPa;

[0026] The material type correction coefficient μ(material type) is determined according to the material type, where the material type includes glass, plastic, metal, and ceramic;

[0027] When the material type is plastic, the material type correction coefficient μ(material type) takes values in [0.75, 1];

[0028] When the material type is glass, the material type correction coefficient μ(material type) takes values in [0.5, 0.8];

[0029] When the material type is metal, the material type correction coefficient μ(material type) takes values in [0.35, 0.65];

[0030] When the material type is ceramic, the material type correction coefficient μ(material type) takes values in [0.25, 0.5].

[0031] Step Four: Taking the acquisition of the minimum vibration intensity and the maximum processing efficiency at any moment during the processing as the control objective, construct an optimization model for the processing process;

[0032] The expression of the optimization model for the processing process is as follows:

[0033]

[0034] In the formula, F is the objective function; st. is the constraint condition of the objective function; is the weight coefficient of the vibration intensity in the objective function F, is the weight coefficient of the processing efficiency in the objective function F, and is to take the minimum value of the calculation result; is the vibration intensity during the processing process under the conditions that the cutting speed is Vc, the feed rate is f, the cutting depth is a p , the hardness value of the processed material is H, the elastic modulus of the processed material is E, and the thermal conductivity of the processed material is k; During the machining process, under the conditions that the cutting speed is Vc, the feed rate is f, and the cutting depth is a p , the machining efficiency when the hardness value of the workpiece material is H, the elastic modulus of the workpiece material is E, and the thermal conductivity of the workpiece material is k; Vc min,i is the lower limit of the cutting speed of the i-th workpiece material; Vc max,i is the upper limit of the cutting speed of the i-th workpiece material; f min,i is the lower limit of the single-pass feed rate of the i-th workpiece material; f max,i is the upper limit of the single-pass feed rate of the i-th workpiece material; a pmin,i is the lower limit of the single-pass cutting depth of the i-th workpiece material; a pmax,i is the upper limit of the single-pass cutting depth of the i-th workpiece material; E i is the elastic modulus of the i-th workpiece material; E max is the maximum elastic modulus of the workpiece materials that can be machined at the bottle neck station of the bottle making machine; H i is the hardness value of the i-th workpiece material; H max is the maximum hardness value of the workpiece materials that can be machined at the bottle neck station of the bottle making machine; k i is the thermal conductivity of the i-th workpiece material; k max is the maximum thermal conductivity of the workpiece materials that can be machined at the bottle neck station of the bottle making machine.

[0035] Step Five: Use the machining process optimization model to obtain the optimal values of the machining process parameters, and control the X / Y axis movement state of the bottle neck station according to the obtained optimal values of the machining process parameters.

[0036] The present invention has the following beneficial effects

[0037] Compared with the prior art, by obtaining the historical data of the processing parameter and processing material parameter of the bottle neck station, extracting the vibration intensity data in the historical processing process, using the vibration intensity data as the first dependent variable, and using the processing parameter and processing material parameter as the independent variables, a processing process vibration model of the bottle neck station is constructed. The vibration intensity prediction value is obtained by using the processing process vibration model. The material removal rate data completed per unit time in the historical processing process is extracted as the quantitative characterization value of the processing efficiency. Using the processing efficiency as the second dependent variable and using the processing parameter and processing material parameter as the independent variables, a processing efficiency evaluation model of the bottle neck station is constructed. The processing efficiency prediction value is obtained by using the processing efficiency evaluation model. Taking obtaining the minimum vibration intensity and the maximum processing efficiency at any moment during the processing process as the control target, a processing process optimization model is constructed. The optimal value of the processing parameter is obtained by using the processing process optimization model. The X / Y axis motion state of the bottle neck station is controlled according to the obtained optimal value of the processing parameter. The technical solution of the present invention is based on artificial intelligence technology. By learning the historical processing data and constructing an optimization model according to the learning result, it can comprehensively analyze the multi-factor influence mechanism of the tangential accuracy, so as to optimize the processing parameters such as cutting speed, feed rate and cutting depth, and further reduce the vibration during the processing process, so that the processing process reaches the expected accuracy control effect. At the same time, on the basis of ensuring the processing effect, the processing efficiency is improved as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic flow chart of the method for controlling the tangential accuracy of the X / Y axis of the bottle neck station of the bottle making machine based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] The following further describes the present invention in conjunction with the specific embodiments. Among them, the drawings are only for illustrative purposes and show only schematic diagrams, not physical diagrams, and should not be construed as a limitation to the present invention. In order to better illustrate the specific embodiments of the present invention, some components in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0040] The specific implementation process of the technical solution of the present invention includes the following steps:

[0041] Step 1: Obtain the historical data of the processing parameter and processing material parameter of the bottle neck station. Among them, the processing parameters include cutting speed, feed rate and cutting depth; the processing material parameters include material hardness, material elastic modulus and material thermal conductivity.

[0042] Step 2: Extract the vibration intensity data in the historical processing process. Taking the vibration intensity data as the first dependent variable and the processing parameters and processing material parameters as independent variables, construct a processing process vibration model for the bottleneck station, and use the processing process vibration model to obtain the vibration intensity prediction value V vib ; where the expression of the processing process vibration model is:

[0043]

[0044] In the formula, Vc is the cutting speed, with the unit of m / min; f is the feed rate, with the unit of mm / r; a p is the cutting depth, with the unit of mm; H is the hardness value of the processing material, with the unit of N / mm 2 ; E is the elastic modulus of the processing material, with the unit of GPa; k is the thermal conductivity of the processing material, with the unit of W / m·K; θ1 is the vibration correction coefficient of the cutting speed; θ2 is the vibration correction coefficient of the feed rate; θ3 is the vibration correction coefficient of the cutting depth; θ4 is the vibration correction coefficient of the material hardness; θ5 is the vibration correction coefficient of the material elastic modulus; θ6 is the vibration correction coefficient of the material thermal conductivity.

[0045] It should be noted that for each correction coefficient in the processing process vibration model, specific values can be obtained by fitting historical data. Specifically, by collecting historical data, including cutting parameters, material properties, and the corresponding vibration intensity. The data can be obtained through experimental measurement or production records. Then, organize and record the collected data in the following table form, as shown in Table 1 specifically:

[0046]

[0047] Table 1 Statistical Table of Vibration Model Fitting Data

[0048] Among them, in Table 1, Vc k , f k , a pk , H k , E k and V vibk respectively represent the cutting speed, feed rate, cutting depth, hardness value of the processing material, elastic modulus of the processing material, and vibration intensity data collected in the k-th time during the same processing process.

[0049] After the data is sorted out, a data processing software, such as MATLAB software, can be used to perform fitting processing on the obtained data, so as to obtain a mathematical model describing the relationship between the vibration intensity and the cutting parameters and material properties, that is, the processing process vibration model in this solution.

[0050] Through the above steps, the vibration intensity generated during the machining process can be quantitatively calculated. Furthermore, by controlling various machining process parameters and machining material parameters, the vibration intensity can be reduced, making the machining process more stable, thereby improving the machining accuracy.

[0051] Step 3: Extract the material removal rate data completed per unit time during the historical machining process as the quantitative characterization value of the machining efficiency. Taking the machining efficiency as the second dependent variable and the machining process parameters and machining material parameters as the independent variables, construct a machining efficiency evaluation model for the bottleneck station, and use the machining efficiency evaluation model to obtain the machining efficiency prediction value η. Among them, the expression of the machining efficiency evaluation model is:

[0052] η = Vc·f·a p ·α(H)·γ(E)·μ(material type)

[0053] In the formula, Vc is the cutting speed, with the unit of m / min; f is the feed rate, with the unit of mm / r; a p is the cutting depth, with the unit of mm; μ(material type) is the material type correction coefficient; α(H) is the efficiency correction coefficient of the material hardness; γ(E) is the efficiency correction coefficient of the material elastic modulus;

[0054] It should be noted that for the machining efficiency, it is not only affected by the machining process parameters, namely the cutting speed, feed rate, and cutting depth, but also affected by factors such as the type of material being machined, material hardness, and material elastic modulus. The higher the material hardness, usually the cutting speed or feed rate needs to be reduced to avoid tool wear and vibration, so the machining efficiency is lower; materials with a higher elastic modulus usually require a higher cutting force, and the cutting depth or feed rate may need to be reduced, so the machining efficiency is lower; in addition, for different machining materials, due to their different materials, hardness, and elastic modulus, they will also affect the machining efficiency. Therefore, it is necessary to introduce the efficiency correction coefficient α(H) of the material hardness, the efficiency correction coefficient γ(E) of the material elastic modulus, and the material type correction coefficient μ(material type) for correction. Specifically:

[0055] The calculation formula for the efficiency correction coefficient α(H) of the material hardness is: Among them, β is a constant coefficient; H is the hardness value of the machining material, with the unit of N / mm 2 ;

[0056] The calculation formula for the efficiency correction coefficient γ(E) of the material elastic modulus is: Among them, δ is a constant coefficient; E is the elastic modulus of the machining material, with the unit of GPa;

[0057] The material type correction coefficient μ (material type) is determined according to the material type, where the material types include glass, plastic, metal, and ceramic; when the material type is plastic, the material type correction coefficient μ (material type) takes values in the range of [0.75, 1]; when the material type is glass, the material type correction coefficient μ (material type) takes values in the range of [0.5, 0.8]; when the material type is metal, the material type correction coefficient μ (material type) takes values in the range of [0.35, 0.65]; when the material type is ceramic, the material type correction coefficient μ (material type) takes values in the range of [0.25, 0.5].

[0058] Through the above steps, the processing efficiency in the processing process can be quantitatively evaluated, so as to improve the processing efficiency on the basis of ensuring the processing accuracy, which is more beneficial to improving the enterprise benefits.

[0059] Step 4: Taking obtaining the minimum vibration intensity and the maximum processing efficiency at any time during the processing process as the control objective, construct an optimization model for the processing process; where the expression of the optimization model for the processing process is as follows:

[0060]

[0061] In the formula, F is the objective function; st. is the constraint condition of the objective function; is the weight coefficient of the vibration intensity in the objective function F, is the weight coefficient of the processing efficiency in the objective function F, and is to take the minimum value of the calculation result; is during the processing process, when the cutting speed is Vc, and the feed rate is f, the cutting depth is a p and the vibration intensity under the condition that the hardness value of the processed material is H, the elastic modulus of the processed material is E, and the thermal conductivity of the processed material is k; is during the processing process, when the cutting speed is Vc, and the feed rate is f, the cutting depth is a p and the processing efficiency under the condition that the hardness value of the processed material is H, the elastic modulus of the processed material is E, and the thermal conductivity of the processed material is k; Vc min,i is the lower limit of the cutting speed of the i-th processed material; Vc max,i is the upper limit of the cutting speed of the i-th processed material; f min,i is the lower limit of the single-pass feed rate of the i-th processed material; f max,i is the upper limit of the single-pass feed rate of the i-th processed material; a pmin,i is the lower limit of the single-pass cutting depth of the i-th processed material; a pmax,iis the upper limit of the single - pass machining cutting depth for the i - th machining material; E i is the elastic modulus of the i - th machining material; E max is the maximum value of the elastic modulus of the machining materials that can be processed by the bottle neck station of the bottle making machine; H i is the hardness value of the i - th machining material; H max is the maximum value of the hardness values of the machining materials that can be processed by the bottle neck station of the bottle making machine; k i is the thermal conductivity of the i - th machining material; k max is the maximum value of the thermal conductivities of the machining materials that can be processed by the bottle neck station of the bottle making machine.

[0062] By constructing an optimization model for the machining process in this step, it is possible to comprehensively analyze the multi - factor influence mechanism of tangential accuracy, so as to optimize machining parameters such as cutting speed, feed rate, and cutting depth. Furthermore, the vibration during the machining process can be reduced, enabling the machining process to achieve the expected accuracy control effect. At the same time, on the basis of ensuring the machining effect, the machining efficiency can be improved as much as possible.

[0063] Step 5: Use the machining process optimization model to obtain the optimal values of the machining process parameters, and control the X / Y - axis motion state of the bottle neck station according to the obtained optimal values of the machining process parameters to obtain the optimal machining effect.

[0064] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above - mentioned embodiments. What is described in the above - mentioned embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of a bottle making machine based on artificial intelligence, characterized in that, Including: Step 1: Obtain the historical data of the processing parameter and processing material parameter at the bottle neck station; Step 2: Extract the vibration intensity data during the historical processing. Using the vibration intensity data as the first dependent variable and the processing parameter and processing material parameter as independent variables, construct the processing vibration model for the bottle neck station, and use the processing vibration model to obtain the vibration intensity prediction value V vib ; Step 3: Extract the material removal rate data completed per unit time in the historical processing as the quantitative characterization value of the processing efficiency. Taking the processing efficiency as the second dependent variable and the processing parameter and processing material parameter as the independent variables, construct the processing efficiency evaluation model of the bottle neck station, and use the processing efficiency evaluation model to obtain the processing efficiency prediction value η; Step 4: Taking obtaining the minimum vibration intensity and the maximum processing efficiency at any moment during the processing as the control target, construct the processing optimization model; Step 5: Use the processing optimization model to obtain the optimal values of the processing parameters, and control the X / Y axis movement state of the bottle neck station according to the obtained optimal values of the processing parameters.

2. The method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of a bottle making machine based on artificial intelligence according to claim 1, wherein, The processing parameters include cutting speed, feed rate, and cutting depth; the processing material parameters include material hardness, material elastic modulus, and material thermal conductivity.

3. The method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of a bottle making machine based on artificial intelligence according to claim 1, characterized in that, The expression of the processing vibration model is: Wherein, Vc is the cutting speed, with the unit of m / min; f is the feed rate, with the unit of mm / r; a p is the cutting depth, with the unit of mm; H is the hardness value of the processed material, with the unit of N / mm 2 ; E is the elastic modulus of the processed material, with the unit of GPa; k is the thermal conductivity of the processed material, with the unit of W / m·K; θ1 is the vibration correction coefficient of the cutting speed; θ2 is the vibration correction coefficient of the feed rate; θ3 is the vibration correction coefficient of the cutting depth; θ4 is the vibration correction coefficient of the material hardness; θ5 is the vibration correction coefficient of the material elastic modulus; θ6 is the vibration correction coefficient of the material thermal conductivity.

4. The method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of a bottle making machine based on artificial intelligence according to claim 1, characterized in that, The expression of the processing efficiency evaluation model is: η = Vc·f·a p ·α(H)·γ(E)·μ(material type) Where, Vc is the cutting speed in m / min; f is the feed rate in mm / r; a p is the cutting depth in mm; μ(material type) is the material type correction factor; α(H) is the efficiency correction factor for material hardness; γ(E) is the efficiency correction factor for material elastic modulus.

5. The method for controlling the X / Y axis tangential accuracy of the bottle neck station of a bottle making machine based on artificial intelligence according to claim 4, wherein The calculation formula for the efficiency correction coefficient α(H) of material hardness is as follows: where β is a constant coefficient; H is the hardness value of the processed material, with the unit of N / mm 2 ; The calculation formula for the efficiency correction coefficient γ(E) of the material elastic modulus is as follows: where δ is a constant coefficient; E is the elastic modulus of the processed material, with the unit of GPa.

6. The method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of the bottle making machine based on artificial intelligence according to claim 4, characterized in that, The material type correction coefficient μ(material type) is determined according to the material type, where the material type includes glass, plastic, metal, and ceramic.

7. The method for controlling the tangential accuracy of the X / Y axis at the bottle neck station of a bottle making machine based on artificial intelligence according to claim 1, wherein The expression of the processing optimization model is: where F is the objective function; st. is the constraint condition of the objective function; is the weight coefficient of the vibration intensity in the objective function F, is the weight coefficient of the machining efficiency in the objective function F, and is to take the minimum value of the calculation result; is the vibration intensity during the machining process when the cutting speed is Vc, the feed rate is f, the cutting depth is a p , the hardness value of the machining material is H, the elastic modulus of the machining material is E, and the thermal conductivity of the machining material is k; is the machining efficiency during the machining process when the cutting speed is Vc, the feed rate is f, the cutting depth is a p , the hardness value of the machining material is H, the elastic modulus of the machining material is E, and the thermal conductivity of the machining material is k; Vc min,i is the lower limit of the cutting speed of the i-th machining material; Vc max,i is the upper limit of the cutting speed of the i-th machining material; f min,i is the lower limit of the single - pass machining feed rate for the i - th machining material; f max,i is the upper limit of the single - pass machining feed rate for the i - th machining material; is the lower limit of the single - pass machining cutting depth for the i - th machining material; is the upper limit of the single - pass machining cutting depth for the i - th machining material; E i is the elastic modulus of the i-th processing material; E max is the maximum value of the elastic modulus of the processing materials that can be processed at the bottle neck station of the bottle making machine; H i is the hardness value of the i-th processing material; H max is the maximum value of the hardness values of the processing materials that can be processed at the bottle neck station of the bottle making machine; k i is the thermal conductivity of the i-th processing material; k max is the maximum value of the thermal conductivities of the processing materials that can be processed at the bottle neck station of the bottle making machine.

8. The method for controlling the X / Y axis tangential accuracy of the bottle neck station of a bottle making machine based on artificial intelligence according to claim 4, wherein When the material type is plastic, the material type correction coefficient μ(material type) takes [0.75, 1]; When the material type is glass, the material type correction coefficient μ(material type) takes [0.5, 0.8]; When the material type is metal, the material type correction coefficient μ(material type) takes [0.35, 0.65]; When the material type is ceramic, the material type correction coefficient μ(material type) takes [0.25, 0.5].

Images