Intelligent control machine tool machining device

Abstract

The invention discloses an intelligent control machine tool machining device which comprises a sensor module, a central control module and an action module. A strain sensor in the sensor module is used for sensing the cutting speed; the laser ranging sensor is used for sensing the cutting depth; the laser speed measurement sensor is used for sensing spindle rotating speed. An optimal regulation and control strategy is given by the eagle algorithm in the central control module based on the data measured by the sensor module and the data pre-stored by the CPU; and the CPU makes a decision based on the target function and a strategy provided by an eagle algorithm, and reasonably regulates and controls the cutting speed, the cutting depth and the rotating speed of the main shaft. A main shaft servo device, a main shaft motor and a speed reducer in the action module automatically adjust parameters of a machined object according to instructions of the central control module. Compared with the prior art, the method has the advantages of high flexibility, labor saving and the like, the adaptability of machine tool machining is improved under the condition that the cost is controlled, and economic benefits are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and more particularly to an intelligent control machine tool processing device. Background Art

[0002] Machine tools are the "mother machines" of the equipment manufacturing industry. The machine tool industry not only provides necessary production equipment for various industries, but also largely determines the production efficiency and product quality of the manufacturing industry. Therefore, the innovation and upgrading of the machine tool industry is of great significance to the development of the entire manufacturing industry. At present, many machine tools consume huge amounts of energy and have low technological levels. If parts cannot be accurately processed, it will have a great impact on industrial manufacturing.

[0003] In order to further improve the precision of parts processing and its adaptability to different types of parts processing, the method of combining intelligent machine tools with neural networks is more common in large-scale processing scenarios. The Chinese invention patent with application number 202311251189.7 discloses a processing adjustment scheme for the CNC machine tool obtained by combining a multi-neural network fusion model, which fills the gap in intelligent machine tool processing to a certain extent. However, the neural network model itself is difficult to train, requires a huge amount of data to be deployed, and has high requirements for computer resources and equipment design thresholds. When facing small and medium-sized processing scenarios, there may be a problem of resource waste. Therefore, there is also a market demand for intelligent machine tools that are suitable for small and medium-sized scenarios, and meet the requirements of reducing energy consumption, saving resources, and high adaptability. Summary of the invention

[0004] Purpose of the invention:

[0005] In order to solve the problems raised in the background technology, the present invention provides an intelligent control machine tool processing device. By using the Osprey algorithm to optimize the parameters of the machine tool processing object, the approximate optimal solution of the minimum power of the machine tool's cutting speed, cutting depth and spindle speed parameters in the current processing scenario is obtained, and combined with the modular design of the intelligent machine tool, while ensuring the processing accuracy, the cost and power consumption are further reduced, and higher economic benefits are generated in small and medium-sized processing scenarios.

[0006] Technical solution:

[0007] The present invention discloses an intelligent control machine tool processing device, which includes a sensor module, an action module, and a central control module;

[0008] The sensor module includes a rotation speed detection module, a cutting depth detection module and a rotation speed detection module, the rotation speed detection module is used to measure the cutting speed of the machine tool, the cutting depth detection module is used to measure the cutting depth and the rotation speed detection module is used to detect the spindle speed;

[0009] The action module includes a spindle servo device, which includes a cutting control module and a speed control module. The cutting control module is used to control the cutting speed and cutting depth of the machining tool head; the speed control module is used to control the spindle speed;

[0010] The central control module is equipped with the Osprey algorithm and the objective function, and is used to receive the data from the sensor module and send it to the action module for execution;

[0011] The sensor module is connected to the central control module, and the action module is connected to the central control module.

[0012] Furthermore, the rotation speed detection module includes a strain sensor; the cutting depth detection module includes a laser distance measurement sensor, and the rotation speed detection module includes a laser speed measurement sensor.

[0013] Furthermore, the action unit also includes a spindle motor. The cutting control module and the speed control module receive control instructions from the central control module, and the spindle motor supplies energy, and they work together to control the cutting speed, cutting depth and spindle speed of the machining tool head.

[0014] Furthermore, the specific operation mode of the central control module is that the Osprey algorithm in the central control module gives the optimal control strategy based on the data measured by the sensor module and the data pre-stored in the CPU; the CPU makes decisions based on the objective function and the strategy provided by the Osprey algorithm, and issues control instructions on the cutting speed, cutting depth and spindle speed.

[0015] Furthermore, the central control module uses the Osprey algorithm to give the optimal solution for different processing objects based on the cutting speed, cutting depth and spindle speed of the processing tool head. The specific optimization process is as follows:

[0016] S1 establishes and initializes the osprey population to form an initial population. A set of randomly distributed osprey position matrices are generated as follows:

[0017]

[0018] x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m

[0019] Where X is the population matrix of the osprey's location; X i is the i-th osprey; x ij is the j-th problem variable of the i-th osprey; N is the total number of osprey population members; m is the total number of problem variables; r i,jis a random number uniformly distributed between [0,1]; ub j lb j are the upper and lower bounds of the variable respectively;

[0020] S2 brings the randomly generated osprey positions into the objective function for evaluation. Each osprey represents a minimum machine tool processing power. The objective function formula is as follows:

[0021] minZ=min(P u +P m )

[0022]

[0023]

[0024]

[0025] Where Z is the machining power of the machine tool, P u is the system no-load operating power, is the minimum no-load power of the machine tool, m 1 , m 2 The spindle speed coefficient, n is the spindle speed, P m is the system material removal power, k is the correction factor, α ρ is the cutting depth, v c is the cutting speed, d is the cutter diameter, n is min is the minimum spindle speed, n max is the maximum spindle speed, η is the machine tool efficiency coefficient, P max is the maximum rated power of the machine tool, is the minimum cutting depth, is the maximum cutting depth;

[0026] S3 selects the search space and locates the most promising area. In the osprey algorithm, ospreys with better objective function values ​​are considered to have fish schools underwater. The formula for the location of the fish school for each osprey is as follows:

[0027] FP i ={X k |k∈{1,2,...,N}∧F k <F i}∪{X best}

[0028] Where FP i is the fish school position set of the i-th osprey; X best For optimal Osprey location;

[0029] The S4 osprey randomly finds the location of one of the fish and attacks it. Based on the simulated osprey moving towards the fish, the new position of the corresponding osprey is calculated using the following formula:

[0030]

[0031]

[0032] If this new position improves the value of the objective function, that is, the appropriate spindle speed n, cutting depth α are found ρ , cutting speed v c , then replace the previous position of the osprey according to the following formula:

[0033]

[0034] In the formula, is the new position of the i-th osprey in the first stage; is its j-th dimension value; F i P1 is the objective function value; SF i is the new position of the ith osprey in the first phase; SF i,j is its j-th dimension value; I i,j is a random number uniformly distributed between [1,2];

[0035] S5 updates the position of the osprey in the search space. After catching the fish, the osprey takes the fish to a suitable place. A new random position is calculated as the "position suitable for eating fish" according to the following formula:

[0036]

[0037]

[0038] If the value of the objective function is improved at this new position, a more suitable spindle speed n and cutting depth α are found. ρ , cutting speed v c , then replace the previous position of the corresponding osprey according to the following formula:

[0039]

[0040] In the formula, is the new position of the i-th osprey in the second stage; is its j-th dimension value; F i P2 is the objective function value; r is a random number uniformly distributed between [0,1]; t is the current number of iterations; T is the maximum number of iterations of the algorithm;

[0041] S6 determines whether the termination condition is met. If the termination condition is not met, return to S3; if the constraint condition is met, go to S7;

[0042] S7 outputs the best spindle speed n and cutting depth α ρ , cutting speed v c , thus obtaining the lowest machine tool processing power.

[0043] Furthermore, S1 introduces the elite chaos reverse learning strategy to increase the probability of selecting a better solution and improve the quality of the initial population individuals. The improved formula is as follows:

[0044]

[0045] In the formula, This is the individual osprey after the lens imaging is reversed; ub j and lb j are the maximum and minimum values ​​of the jth dimension in the current population respectively; k is the zoom factor of the lens.

[0046] Beneficial effects:

[0047] 1. The present invention takes the minimum machine tool processing power as the objective function, and uses the Osprey algorithm to provide the optimal solution for the cutting speed, cutting depth and spindle speed of the machining tool head to be suitable for different machining objects. It can improve the machining accuracy and efficiency of the machine tool, which is beneficial to improving the adaptability of the device, reducing energy consumption and saving resources.

[0048] 2. The present invention increases the probability of selecting a better solution by introducing an elite chaos reverse learning strategy, which is beneficial to improving the quality of individuals in the initial population and further optimizing the final processing plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a structural schematic diagram of the present invention;

[0050] Figure 2 This is a schematic diagram of the installation position of the sensor of the present invention;

[0051] Figure 3 This is a flow chart of the Osprey algorithm proposed in the present invention. DETAILED DESCRIPTION

[0052] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0053] like Figure 1-2As shown, this embodiment provides an intelligent control machine tool processing device, including a sensor module, a central control module, and an action module. The sensor module includes a speed detection module, a cutting depth detection module, and a speed detection module; the action unit includes a spindle servo device, a spindle motor, and a reducer, and the spindle servo device includes a cutting control module and a speed control module; the central control module includes an objective function, an Osprey algorithm, and a CPU.

[0054] In the sensor module, the speed detection module includes a strain sensor; the cutting depth detection module includes a laser distance sensor, and the speed detection module includes a laser speed sensor. The strain sensor is used to measure the cutting speed of the machining tool head; the laser distance sensor is used to measure the cutting depth of the machining tool head; and the laser speed sensor is used to measure the spindle speed.

[0055] The central control module is equipped with the Osprey algorithm and the objective function. The Osprey algorithm gives the optimal control strategy based on the data measured by the sensor module and the data pre-stored by the CPU; the CPU makes decisions based on the objective function and the strategy provided by the Osprey algorithm to reasonably control the cutting speed, cutting depth and spindle speed. The cutting control module and speed control module in the spindle servo device in the action module work together with the spindle motor to control the cutting speed and cutting depth of the machining tool head; the reducer controls the spindle speed.

[0056] like Figure 3 As shown, this embodiment uses the Osprey algorithm to provide the optimal solution for the cutting speed, cutting depth and spindle speed of the machining tool head to be suitable for different machining objects. The specific optimization process is as follows:

[0057] 1) Establish and initialize the osprey population to form an initial population. Generate a set of randomly distributed osprey position matrices as follows:

[0058]

[0059] x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m

[0060] Where X is the population matrix of the osprey's location; X i is the i-th osprey; x ij is the j-th problem variable of the i-th osprey; N is the total number of osprey population members; m is the total number of problem variables; r i,j is a random number uniformly distributed between [0,1]; ub j lb j are the upper and lower bounds of the variable respectively.

[0061] 2) The randomly generated osprey positions are brought into the objective function for evaluation. Each osprey represents a minimum machine tool processing power. The objective function formula is as follows:

[0062] minZ=min(P u +P m )

[0063]

[0064]

[0065]

[0066] Where Z is the machining power of the machine tool, P u is the system no-load operating power, is the minimum no-load power of the machine tool, m 1 , m 2 The spindle speed coefficient, n is the spindle speed, P m is the system material removal power, k is the correction factor, α ρ is the cutting depth, v c is the cutting speed, d is the cutter diameter, n is min is the minimum spindle speed, n max is the maximum spindle speed, η is the machine tool efficiency coefficient, P max is the maximum rated power of the machine tool, is the minimum cutting depth, is the maximum cutting depth.

[0067] 3) Select the search space and locate the most promising area. In the osprey algorithm, ospreys with better objective function values ​​are considered to have fish schools underwater. The formula for the location of the fish school for each osprey is as follows:

[0068] FP i ={X k |k∈{1,2,...,N}∧F k <F i}∪{X best}

[0069] Where FP i is the fish school position set of the i-th osprey; X best For optimal Osprey location.

[0070] 4) The osprey randomly finds the location of one of the fish and attacks it. Based on the simulation of the osprey moving towards the fish, the new position of the corresponding osprey is calculated using the following formula:

[0071]

[0072]

[0073] If this new position improves the value of the objective function, that is, the appropriate spindle speed n, cutting depth α are found ρ , cutting speed v c , then replace the previous position of the osprey according to the following formula:

[0074]

[0075] In the formula, is the new position of the i-th osprey in the first stage; is its j-th dimension value; F i P1 is the objective function value; SF i is the new position of the ith osprey in the first phase; SF i,j is its j-th dimension value; I i,j is a random number uniformly distributed between [1,2].

[0076] 5) Update the position of the osprey in the search space. After catching the fish, the osprey takes the fish to a suitable place. A new random position is calculated as the "position suitable for eating fish" according to the following formula:

[0077]

[0078]

[0079] If the value of the objective function is improved at this new position, a more suitable spindle speed n and cutting depth α are found. ρ , cutting speed v c , then replace the previous position of the corresponding osprey according to the following formula:

[0080]

[0081] In the formula, is the new position of the i-th osprey in the second stage; is its j-th dimension value; F i P2 is the objective function value; r is a random number uniformly distributed between [0,1]; t is the current number of iterations; T is the maximum number of iterations of the algorithm.

[0082] 6) Determine whether the termination condition is met. If the termination condition is not met, return to step 3); if the constraint condition is met, go to step 7).

[0083] 7) Output the optimal spindle speed n and cutting depth α ρ , cutting speed v c, thus obtaining the lowest machine tool processing power.

[0084] Furthermore, the improvement of IOOA is to improve 1) by introducing the elite chaos reverse learning strategy to increase the probability of selecting a better solution, thereby improving the quality of the initial population individuals. The improved formula is as follows:

[0085]

[0086] In the formula, This is the individual osprey after the lens imaging is reversed; ub j and lb j are the maximum and minimum values ​​of the jth dimension in the current population respectively; k is the zoom factor of the lens.

[0087] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control machine tool processing device, characterized in that: The device includes a sensor module, an action module, and a central control module; The sensor module includes a rotation speed detection module, a cutting depth detection module and a rotation speed detection module, the rotation speed detection module is used to measure the cutting speed of the machine tool, the cutting depth detection module is used to measure the cutting depth and the rotation speed detection module is used to detect the spindle speed; The action module includes a spindle servo device, which includes a cutting control module and a speed control module. The cutting control module is used to control the cutting speed and cutting depth of the machining tool head; the speed control module is used to control the spindle speed; The central control module is equipped with the Osprey algorithm and the objective function, and is used to receive the data from the sensor module and send it to the action module for execution; The sensor module is connected to the central control module, and the action module is connected to the central control module.

2. The intelligent control machine tool processing device according to claim 1, characterized in that: The rotation speed detection module includes a strain sensor; the cutting depth detection module includes a laser distance measurement sensor, and the rotation speed detection module includes a laser speed measurement sensor.

3. The intelligent control machine tool processing device according to claim 1, characterized in that: The action unit also includes a spindle motor. The cutting control module and the speed control module receive control instructions from the central control module and the spindle motor supplies energy, and they work together to control the cutting speed, cutting depth and spindle speed of the machining tool head.

4. The intelligent control machine tool processing device according to claim 1, characterized in that: The specific operation mode of the central control module is that the Osprey algorithm in the central control module gives the optimal control strategy based on the data measured by the sensor module and the data pre-stored in the CPU; the CPU makes decisions based on the objective function and the strategy provided by the Osprey algorithm, and issues control instructions on the cutting speed, cutting depth and spindle speed.

5. An intelligent control machine tool processing device according to claim 1 or 4, characterized in that: The central control module uses the Osprey algorithm to give the best solution for different processing objects based on the cutting speed, cutting depth and spindle speed of the processing tool head. The specific optimization process is as follows: S1 establishes and initializes the osprey population to form an initial population, and generates a set of randomly distributed osprey position matrices as follows: x i,j =lb j +r i,j ·(ub j -lb j ),i=1,2,...,N,j=1,2,...,m Where X is the population matrix of the osprey's location; X i is the position of the i-th osprey; x i,j is the j-th dimension of the problem variable of the i-th osprey; N is the total number of members of the osprey population; m is the total number of problem variables; r i,j is a random number uniformly distributed between [0,1]; ub j lb j are the upper and lower bounds of the variable respectively; S2 brings the randomly generated osprey positions into the objective function for evaluation. Each osprey represents a minimum machine tool processing power. The objective function formula is as follows: minZ=min(P u +P m ) Where Z is the machining power of the machine tool, P u is the system no-load operating power, is the minimum no-load power of the machine tool, m1, m2 are the speed coefficients of the spindle, n is the spindle speed, P m is the system material removal power, k is the correction factor, α ρ is the cutting depth, v c is the cutting speed, d is the cutter diameter, n is min is the minimum spindle speed, n max is the maximum spindle speed, η is the machine tool efficiency coefficient, P max is the rated maximum power of the machine tool, α ρmin is the minimum cutting depth, α ρmax is the maximum cutting depth; S3 selects the search space and locates the most promising area. In the osprey algorithm, ospreys with better objective function values ​​are considered to have fish schools underwater. The formula for the fish school location of each osprey is as follows: FP i ={X k ∣k∈{1,2,...,N}∧F k <F i }∪{X best } Where, X k is the position of the kth osprey; F k is the objective function value of the kth osprey; F i is the objective function value of the i-th osprey; FP i is the fish school position set of the i-th osprey; X best for optimal Osprey location; The S4 osprey randomly finds the position of one of the fish and attacks it. Based on the simulation of the osprey moving towards the fish, the new position of the corresponding osprey is calculated using the following formula: If this new position improves the value of the objective function, that is, the appropriate spindle speed n, cutting depth α are found ρ , cutting speed v c , then replace the previous position of the osprey according to the following formula: In the formula, is the new position of the i-th osprey in the first stage; is its j-th dimension value; F i P1 is the objective function value; SF i is the new position of the ith osprey in the first phase; SF i,j is its j-th dimension value; I i,j is a random number uniformly distributed between [1,2]; S5 updates the position of the osprey in the search space. After catching a fish, the osprey takes the fish to a suitable place and calculates a new random position as a "position suitable for eating fish" according to the following formula: If the value of the objective function is improved at this new position, a more suitable spindle speed n and cutting depth α are found. ρ , cutting speed v c , then replace the previous position of the corresponding osprey according to the following formula: In the formula, is the new position of the i-th osprey in the second stage; is its j-th dimension value; F i P2 is the objective function value; r is a random number uniformly distributed between [0,1]; t is the current number of iterations; T is the maximum number of iterations of the algorithm; S6 determines whether the termination condition is met. If the termination condition is not met, return to S3; If the constraint condition is met, go to S7; S7 outputs the best spindle speed n and cutting depth α ρ , cutting speed v c , thus obtaining the lowest machine tool processing power.

6. The intelligent control machine tool processing device according to claim 5, characterized in that: S1 introduces the elite chaos reverse learning strategy to increase the probability of selecting a better solution and improve the quality of individuals in the initial population. The improved formula is as follows: In the formula, This is the osprey individual after the lens imaging is reversed; ub j and lb j are the maximum and minimum values ​​of the jth dimension in the current population respectively; k is the zoom factor of the lens.

Images