A robot face cover sorting system based on ISWO algorithm trajectory planning

Abstract

The application provides a robot face lining sorting system based on ISWO algorithm trajectory planning, which comprises a face lining sorting work station and a robot for automatic feeding and discharging; the face lining sorting work station comprises a device main body, a stamping die, a feeding trolley, an outer frame, a lead screw, a micro DC motor, a back baffle, a sliding block, a mounting plate and a proximity switch; a time optimization method of the sorting system is as follows: introducing an elite pool strategy and a spiral search strategy into hunting and nest building stages, and reciprocally improving the original strategy of population reduction stage, enhancing the SWO algorithm of robot feeding and discharging, so as to jump out of a local optimal capacity and improve the convergence speed and precision of the algorithm; under the condition of constraining the joint speed and acceleration of the robot, the ISWO algorithm is adopted to perform time optimal planning on the sorting trajectory based on a 4-3-4 hybrid polynomial interpolation function; the application can construct a face lining feeding and discharging work station of an ABB1200 robot, and the ISWO algorithm is also adopted for the robot to perform optimal time planning on the feeding and discharging trajectory.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of mechanical automation and robot trajectory planning, and in particular to a robot face lining sorting system based on ISWO algorithm trajectory planning. BACKGROUND

[0002] In a traditional shoe material face lining hot pressing process, workers need to manually put prepared sheet face lining raw materials into a hot pressing mold, and then manually take out the face lining after hot pressing. This process has many problems. First, there is a safety hazard. The temperature of the hot pressing mold is as high as 190 degrees Celsius. There is a serious risk of burns and other safety hazards in the process of manually putting or taking out the face lining. Second, the manual feeding and discharging efficiency is low, which affects the income of the enterprise. Third, the labor intensity is large. Manual operation of the hot pressing process is time-consuming and labor-intensive, which increases the labor intensity of the workers. In order to solve the above problems, the application provides a robot face lining sorting system based on ISWO algorithm trajectory planning, which is used to solve the problems of low efficiency of traditional manual feeding and discharging, high labor intensity of workers, and harm to the health of workers, and at the same time improves the production efficiency of the enterprise, and achieves the purpose of reducing the cost and increasing the benefit of the enterprise. SUMMARY

[0003] The application provides a robot face lining sorting system based on ISWO algorithm trajectory planning, which can construct a face lining feeding and discharging workstation of an ABB1200 robot, and at the same time, the ISWO algorithm is used to plan the feeding and discharging trajectory of the robot, so that the technical problems in the prior art are solved.

[0004] The application adopts the following technical scheme.

[0005] A robot face lining sorting system based on ISWO algorithm trajectory planning, the sorting system comprises a face lining sorting work station and a robot for automatic feeding and discharging of shoe material face lining hot pressing and stabilizing operation; the face lining sorting work station comprises a device main body, a stamping die, a feeding trolley, an outer frame, a lead screw, a micro DC motor, a back baffle, a sliding block, a mounting plate and a proximity switch; the sorting system optimizes the time of the robot trajectory based on the ISWO algorithm, and the method is as follows: the original SWO algorithm of the robot feeding and discharging is enhanced by introducing the elite pool strategy and the spiral search strategy into the hunting and nest building stage, and reciprocally improving the original strategy of the population reduction stage, so as to jump out of the local optimal ability and improve the convergence speed and precision of the algorithm, and the ISWO algorithm is used to plan the time optimization of the sorting trajectory based on the 4-3-4 mixed polynomial interpolation function under the condition of constraining the joint speed and acceleration of the robot.

[0006] The mechanical structure of the face lining sorting work station comprises a device main body (1), a punching die (2), a feeding trolley (9), an outer frame (10), a lead screw (14), a micro DC motor (16), a back baffle (19), a sliding block (22), a mounting plate (23), and a proximity switch (24);

[0007] The punching die (2) is N and installed side by side inside the device main body (1), a supporting steel frame (3) is installed on one side of the device main body (1), a moving device (4) is installed on the supporting steel frame (3), a robot (5) is installed at the bottom of the moving device (4), and an end effector (6) is installed on the flange plate of the robot (5);

[0008] An upper feeding machine (7) and a lower feeding machine (8) are respectively installed on one side of the device main body (1), and the feeding trolley (9) is placed on one side of the upper feeding machine (7);

[0009] The upper feeding machine and the lower feeding machine each comprise a lifting platform for placing materials, and the lifting platform is driven to lift by a micro DC motor;

[0010] The upper feeding machine is used to transfer the face lining materials sent by the feeding trolley to the upper feeding position of the robot, and after the materials at the punching die are processed by the robot, the processed materials are sent to the lower feeding machine by the robot;

[0011] The proximity switch (24) comprises two proximity switches arranged at the mounting plate (23) and used for collecting upper limit signals and lower limit signals of lifting actions of the lifting platform (12), and a proximity switch arranged at the lifting platform (12) and used for detecting whether there is a face lining on the lifting platform (12);

[0012] Two ends of one side of the mounting plate (23) are provided with guide rails (21) of the lifting platform, the guide rails (21) are arranged in pairs, the two guide rails (21) are arranged in parallel with each other, and the guide rails (21) are slidably connected to both ends of the sliding block (22) of the lifting platform;

[0013] The lead screw (14), the bearing seat, the guide rail (21), and the sliding block (22) are installed on the mounting plate (23), the micro DC motor (16) is fixed in the motor support (17) of the mounting plate, a shaft coupling (15) is sleeved on the output end of the micro DC motor (16), one end of the shaft coupling (15) is connected to the bottom of the lead screw (14), and the lead screw (14) is threadedly connected to the sliding block (22).

[0014] The outer frame (10) is provided with a fixed foot (11) at the bottom, which is used to prevent interference when the feeding trolley (9) is attached to the material machine;

[0015] The aluminum profile of the material machine side baffle (18) installed on both sides of the outer frame (10) can adjust the distance of the material machine side baffle (18) through the loose angle aluminum and the outer connecting plate, which is used to limit the movement and rotation of the face cover of different sizes;

[0016] The slider (22) and the lifting platform (12) are connected by the heightening block (13); the rear baffle (19) is supported by the support frame (20) installed on the mounting plate (23), which is used to prevent the face cover from being pressed and bent.

[0017] The feeding trolley (9) comprises a feeding trolley outer frame (25); the feeding trolley outer frame (25) is internally provided with feeding trolley guide blocks (26), and the feeding trolley guide blocks (26) are provided with feeding trolley shovels (27) therebetween, and the feeding trolley shovels (27) are provided with feeding trolley pushing plates (28) on one side;

[0018] The feeding trolley pushing plate (28) is welded with a trolley handle (29) at one end, the feeding trolley outer frame (25) is provided with a caster mounting plate (30) at the bottom, and the caster mounting plate (30) is provided with a flat-top universal caster (31) at the bottom;

[0019] The number of the stamping die (2) is six.

[0020] The working method of the robot face cover sorting system comprises the following steps:

[0021] Step S1, the face cover material neatly stacked in a tray is placed on the feeding trolley shovel (27), the feeding trolley outer frame (25) is pushed to advance the material machine, the feeding trolley (9) is aligned and closely contacted with the material machine (7) through the guide block, the T-shaped bolt embedded in the feeding trolley outer frame (25) clamps the feeding trolley shovel (27), the pin connected with the shovel on the feeding trolley pushing plate (28) is pulled out to make the pushing plate and the shovel slide, at this time, the lower limit position of the tray of the material machine (7) is slightly lower than the height of the feeding trolley shovel (27), then the feeding trolley pushing plate (28) is pushed to push the face cover on the feeding trolley shovel (27) into the tray of the material machine (7), and the feeding action of the material machine (7) is completed;

[0022] Step S2, the robot (5) with the end effector (6) moves along the feeding and discharging machines in the parallel direction through the moving device (4), moves to the top of the material machine (7) after feeding, then the robot (5) reaches the face cover to be picked up with the end effector (6), the air needle on the end effector (6) picks up the face cover on the material machine (7), the material machine (7) rises by one face cover height, since the face cover has different thicknesses on the left and right sides, the face cover is stacked alternately by 180 degrees, and when the direction is unified, the end effector (6) is rotated by 180 degrees and placed in the mold, and the feeding action is completed.

[0023] Step S3, the robot (5) with the end effector (6) will take the face liner to the unloader (8), then the unloader (8) will descend one face liner height, and so on, until the face liner on the feeder (7) is stabilized and taken to the unloader (8) by the robot (5), the feeder trolley outer frame (25) can be pushed forward to the unloader (8), the feeder trolley (9) is aligned and closely attached to the unloader (8) through the guide block, the T-shaped bolt stuck in the feeder trolley shovel plate (28) is pushed, the pin connected to the shovel plate is inserted into the push plate to fix the push plate on the shovel plate, then the feeder trolley push plate (28) is pushed to shovel the face liner on the unloader tray into the feeder trolley shovel plate, and the feeder trolley (9) is returned to complete the unloading operation of the unloader (8).

[0024] The robot is a picking robot, which performs automatic feeding and unloading operation of shoe material face liner hot pressing and stabilizing operation by a mechanical arm, the mechanical arm is a six-axis serial mechanical arm, and the method for time optimization of the robot trajectory based on the ISWO algorithm includes the following steps.

[0025] Step one, taking the six-axis serial mechanical arm as the research object, the D-H table and joint parameter detail drawing of the robot mechanical arm are established;

[0026] Step two, according to the actual requirements of the robot, an interpolation function, a trajectory path point, an objective function and a constraint condition are established;

[0027] Step three, the SWO is improved and the ISWO algorithm is used to optimize the robot trajectory curve, and the time optimal trajectory curve of the robot is obtained.

[0028] In step two, the picking robot adopts 4-3-4 hybrid polynomial interpolation for trajectory planning design, and the interpolation function established is as follows:

[0029]

[0030] Wherein, S δ1 , S δ2 , S δ3 respectively represent the angular displacement of the δth joint of the robot in the 1st, 2nd and 3rd trajectory planning, t1, t2, t3 respectively represent the time of the δth joint of the robot in the 1st, 2nd and 3rd trajectory planning, and a represents the polynomial coefficient in the 4-3-4 interpolation function.

[0031] In step two, when the robot is trajectory planned by 4-3-4 polynomial interpolation method, four points need to be calibrated in space, and the trajectory path point diagram is as shown in Figure 13

[0032] Let S δ0 , S δ1 , S δ2 , S​δ3 respectively represent the start point, two path points and the end point of the δth joint of the picking robot; the velocity and acceleration of the start point and the end point are continuous, then the interpolation point S δ0 and S δ3 have the same velocity and acceleration; through these conditions, the following relational expression can be constructed: δ1 δ2

[0033] S δ = A·a (Formula 2);

[0034]

[0035]

[0036] a = [a 14 a 13 a 12 a 11 a 10 a 23 a 22 a 21 a 20 a 34 a 33 a 32 a 31 a 30 ] (Formula 5)

[0037] In Formula 2, S δ represents the position of the δth joint of the picking robot, S δ is expanded as Formula 3; A is a conversion matrix obtained according to the constraint condition, which is only related to time t, and is expanded as Formula 4; a represents the polynomial coefficient in the 4-3-4 interpolation function, which is expanded as Formula 5; the polynomial coefficient in the 4-3-4 interpolation function is solved according to the above formulas, so as to obtain the motion trajectory of each joint of the picking robot in the three interpolation sections.

[0038] In Step 2, the optimization objective function and the constraint condition of the picking robot are as follows:

[0039] f δ (t) = min (t1 + t2 + t3) (Formula 6)

[0040]

[0041] In the formula, t1, t2 and t3 represent the time of each joint after optimization in each interpolation section, and respectively represent the velocity and acceleration of the δth joint of the picking robot, and ​​​respectively represent the maximum velocity and maximum acceleration of the picking robot's δ joint.

[0042] In step three, the improved content of SWO algorithm includes: by introducing the elite pool strategy to the nest-building stage of SWO algorithm, the phenomenon of nest point aggregation is solved, and the ability of the algorithm to jump out of local optimum is improved, as shown in the following formula:

[0043]

[0044]

[0045] In the formula, are the first three optimal individuals, is randomly composed of the best three individuals; in the search process, the optimal individuals in the nest-building stage formula and the random individuals will be replaced by a random selection from the elite pool, and the diversity of candidate solutions in the elite pool makes the algorithm update more flexible, enhancing the algorithm's ability to jump out of local optimum.

[0046] In step three, the improved content of SWO algorithm includes: introducing spiral search strategy to the following and nest-building behavior of SWO algorithm, gradually reducing the search range by changing the value of b with the increase of iteration number, improving the convergence speed of the algorithm, and the specific formula is as follows:

[0047] Beta=e bl *cos(2πl)(formula 13)

[0048]

[0049] Formula 14 represents the mathematical expression of the following and escaping behavior of the hunting stage of the spider bee algorithm, and formula 15 represents the mathematical model of its nest-building behavior; γ is the Levy-generated number, is a binary vector, and formula 12 and formula 13 represent the change function in the spiral search strategy, which can effectively make the operator concentrate in the high probability area of the solution, thereby reducing the number of iterations and speeding up the finding of the optimal solution;

[0050] In step three, the improved content of SWO algorithm includes: in the original SWO algorithm population reduction and memory storage stage, an improved reciprocating population reduction strategy is introduced, and the specific formula is as follows:

[0051]

[0052] In the formula, N max and N min are the maximum population size and the minimum population size, t and t max are the current iteration number and the maximum iteration number, % is the remainder operator, and Cy represents the number of reciprocating cycles;

[0053] Step three interpolates each segment of the picking robot trajectory separately to plan a time-optimal trajectory;

[0054] Step three includes the following steps:

[0055] Step 1: initialize the basic parameters of the ISWO algorithm, population size 6N, maximum iteration number t max , the trade-off probability between hunting and mating behavior Tr=0.3, the crossover probability Cr=0.2, the time upper limit ub(2,2,2) s and the time lower limit lb(0,0,0) s of the 4-3-4 interpolation target function;

[0056] Step 2: Calculate the fitness value of the spider wasp according to formula 6 and the 3-segment trajectory running time t1, t2, t3 of each joint of the robot arm is substituted into formula (6) to judge whether the speed and acceleration constraints are met, the optimal individual of the spider wasp is updated and saved;

[0057] Step 3: The algorithm enters the iteration process, if the random number rand generated between [0,1] is less than TR, then enter the hunting or nesting stage; wherein the following processes such as following, escaping and nesting stage in the hunting stage are updated according to formula 14, formula 15;

[0058] Step 4: If the random number r is greater than Tr, the female and male spider wasps mate to produce offspring, and mating behavior is performed;

[0059] Step 5: Add memory storage, change the population size according to the reciprocal population reduction strategy of formula 16, and improve the optimization accuracy;

[0060] Step 6: Calculate the fitness value of the updated spider wasp position, compare the fitness values that meet the speed and acceleration constraints with the optimal values of the previously saved spider wasp individuals, and update the optimal values of the current spider wasp individuals and save them;

[0061] Step 7: Determine whether the maximum iteration number is reached, if yes, stop iteration, and output the optimal fitness value of the spider wasp and the 3-segment trajectory running time of each joint of the robot arm, otherwise return to step 3.

[0062] The robot arm is an ABB series IRB1200 six-axis serial robot of ABB1200 robot, and the method of sorting system based on ISWO algorithm for time optimization of robot trajectory can be simulated and verified in matlab, and the feasibility of reducing the running time before and after trajectory optimization by this algorithm can be confirmed.

[0063] This invention provides a robotic upper lining sorting system based on ISWO algorithm trajectory planning, which has the following beneficial effects: A robotic workstation model for loading and unloading shoe upper linings is constructed using mechanical automation technology. This workstation enables automated production of shoe upper linings through hot pressing and stabilization, greatly reducing safety hazards and workload for workers, and lowering labor costs for enterprises. Simultaneously, to further improve the workstation robot's picking cycle time, an improved spider-bee algorithm is introduced to perform time-optimal trajectory planning for the fixed motion trajectory of the picking robot at the workstation. This effectively solves problems such as long robot trajectory running time and large fluctuations, improving robot efficiency, reducing redundant time, and increasing the enterprise's upper lining production capacity. Based on the constructed robotic workstation model for loading and unloading shoe upper linings, this invention uses the ISWO algorithm to perform time-optimal trajectory planning for the picking robot's motion trajectory. This time-optimal trajectory planning can improve the picking efficiency of the workstation robot, thereby increasing the benefits for shoe manufacturing enterprises. Attached Figure Description

[0064] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0065] Appendix Figure 1 This is a schematic diagram of the overall structure of the picking robot workstation;

[0066] Appendix Figure 2 This is a schematic diagram of the overall structure of the feeding vehicle;

[0067] Appendix Figure 3 This is a schematic diagram of the internal structure of the feeding vehicle;

[0068] Appendix Figure 4 This is a partial schematic diagram of the internal structure of the feeding vehicle;

[0069] Appendix Figure 5 This is an enlarged schematic diagram of the feeding cart structure.

[0070] Appendix Figure 6 This is a schematic diagram of the ISWO algorithm flow.

[0071] Appendix Figure 7 Detailed schematic diagram of the parameters of the robotic arm joints;

[0072] Appendix Figure 8 A schematic diagram of the approximate trajectory of a robotic arm loading material on-site;

[0073] Appendix Figure 9 A schematic diagram of the realistic motion trajectory of a robotic arm;

[0074] Appendix Figure 10 This is a schematic diagram of the dynamic parameters of the unoptimized robotic arm's speed and acceleration.

[0075] Appendix Figure 11Dynamic parameter diagram of the speed and acceleration of the mechanical arm optimized by SWO;

[0076] Attached Figure 12 Dynamic parameter diagram of the speed and acceleration of the mechanical arm optimized by ISWO;

[0077] Attached Figure 13 Trajectory path point diagram of four points in space calibration in step two

[0078] In the figure, 1, device main body; 2, stamping die; 3, support steel frame; 4, moving device; 5, robot; 6, end effector; 7, feeding machine; 8, discharging machine; 9, feeding trolley; 10, outer frame; 11, fixed footrest; 12, lifting platform; 13, heightening block; 14, lead screw; 15, coupling; 16, miniature DC motor; 17, motor support; 18, material machine side baffle; 19, rear baffle; 20, support frame; 21, guide rail; 22, sliding block; 23, mounting plate; 24, proximity switch; 25, trolley outer frame; 26, feeding trolley guide block; 27, feeding trolley shovel plate; 28, feeding trolley pushing plate; 29, trolley handle; 30, caster mounting plate; 31, flat-top universal caster. DETAILED DESCRIPTION

[0079] As shown in the figure, a robot face lining sorting system based on ISWO algorithm trajectory planning, the sorting system includes a face lining sorting work station, a robot for shoe material face lining hot pressing stable operation of automatic feeding and discharging; the face lining sorting work station includes a device main body, a stamping die, a feeding trolley, an outer frame, a lead screw, a miniature DC motor, a rear baffle, a sliding block, a mounting plate and a proximity switch; the sorting system optimizes the time of the robot trajectory based on the ISWO algorithm, the method is: by introducing the elite pool strategy, the spiral search strategy to the hunting and nest building stage, and reciprocating improvement to the original strategy of population reduction stage, enhancing the original SWO algorithm of the robot feeding and discharging, to jump out of the local optimal ability and improve the convergence speed and accuracy of the algorithm, and under the condition of constraining the joint speed and acceleration of the robot, using the ISWO algorithm to optimize the time of the sorting trajectory based on the 4-3-4 mixed polynomial interpolation function.

[0080] The mechanical structure of the face lining sorting work station includes a device main body 1, a stamping die 2, a feeding trolley 9, an outer frame 10, a lead screw 14, a miniature DC motor 16, a rear baffle 19, a sliding block 22, a mounting plate 23 and a proximity switch 24;

[0081] The stamping die 2 has N and is installed side by side in the device main body 1, one side of the device main body 1 is provided with a support steel frame 3, the support steel frame 3 is provided with a moving device 4, the moving device 4 is provided with a robot 5 at the bottom, and the robot 5 is provided with an end effector 6 on the flange plate;

[0082] The device body 1 side is respectively installed with the upper feeder 7 and the lower feeder 8, the feeder car 9 is placed in the upper feeder 7 side;

[0083] The upper feeder and the lower feeder all include a lifting platform for placing materials, and the lifting platform is driven to lift by a micro DC motor;

[0084] The upper feeder is used to transfer the face lining material sent by the feeder car to the upper feeding position of the robot, and after the material at the stamping die is processed by the robot, the processed material is sent to the lower feeder by the robot;

[0085] The proximity switch 24 includes two proximity switches arranged on the mounting plate 23 for collecting the upper limit signal and the lower limit signal of the lifting platform 12 lifting action respectively, and also includes a proximity switch arranged on the lifting platform 12 for detecting whether there is a face lining on the lifting platform 12;

[0086] The mounting plate 23 side two ends are installed with the guide rail 21 of the lifting platform, the guide rail 21 is arranged in pairs, the two guide rails 21 are arranged in parallel with each other, and the guide rail 21 is slidably connected with the sliding block 22 of the lifting platform at both ends;

[0087] The lead screw 14, bearing seat, guide rail 21 and sliding block 22 are installed on the mounting plate 23, the micro DC motor 16 is fixed in the motor support 17 inside the mounting plate, the micro DC motor 16 is sleeved with a shaft coupling 15 outside the output end, the shaft coupling 15 is connected with one end of the bottom of the lead screw 14, and the lead screw 14 is threadedly connected with the sliding block 22.

[0088] The outer frame 10 bottom is installed with a fixed foot 11 for preventing interference when the feeder car 9 is attached to the material machine;

[0089] The aluminum profile of the material machine side baffle 18 installed on both sides of the outer frame 10 can adjust the distance of the material machine side baffle 18 through the tight angle aluminum and the outer connecting plate, for limiting the movement and rotation of face lining of different sizes;

[0090] The sliding block 22 and the lifting platform 12 are connected by a heightening block 13; the back baffle 19 is supported by a support frame 20 installed on the mounting plate 23, for preventing being pressed and bent by the face lining.

[0091] The feeder car 9 includes a feeder car outer frame 25; the feeder car outer frame 25 is internally provided with feeder car guide blocks 26, feeder car shovel plates 27 are arranged between the feeder car guide blocks 26, and feeder car pushing plates 28 are installed on one side of the feeder car shovel plates 27;

[0092] The push plate 28 of the feeding trolley is welded with a trolley handle 29 at one end, and the bottom of the outer frame 25 of the feeding trolley is installed with a caster mounting plate 30, and the bottom of the caster mounting plate 30 is installed with a flat-top universal caster 31.

[0093] The number of the stamping die 2 is six.

[0094] The working method of the robot face lining sorting system comprises the following steps:

[0095] Step S1, the face lining material stacked in a tray is placed on the shovel plate 27 of the feeding trolley, the trolley outer frame 25 is pushed to move forward to the feeding machine, the feeding trolley 9 is aligned and closely contacted with the feeding machine 7 through the guide block, the T-shaped bolt embedded in the trolley outer frame 25 is clamped to the feeding trolley shovel plate 27, the pin connected with the shovel plate on the feeding trolley push plate 28 is pulled out to make the push plate and the shovel plate slide, at this time, the lower limit position of the tray of the feeding machine 7 is slightly lower than the height of the feeding trolley shovel plate 27, then the feeding trolley push plate 28 is pushed to push the face lining on the feeding trolley shovel plate 27 into the tray of the feeding machine 7, and the feeding action to the feeding machine 7 is completed.

[0096] Step S2, the robot 5 with the end effector 6 moves along the feeding and discharging machine in the parallel direction through the moving device 4, and moves to the position directly above the feeding machine 7 after feeding, then the robot 5 carries the end effector 6 to the face lining to be picked up, the air needle on the end effector 6 picks up the face lining on the feeding machine 7, the feeding machine 7 rises by one face lining height, since the face lining has different thicknesses on the left and right sides, the face lining is stacked in 180 degrees alternately, and the end effector 6 rotates by 180 degrees to place the face lining into the mold, and the feeding action is completed.

[0097] Step S3, after the robot body stabilizes the face lining, the robot 5 carries the end effector 6 to take the face lining to the discharging machine 8, then the discharging machine 8 descends by one face lining height, and the feeding trolley outer frame 25 is pushed to move forward to the discharging machine 8, the feeding trolley 9 is aligned and closely contacted with the discharging machine 8 through the guide block, the T-shaped bolt clamped to the feeding trolley shovel plate 28 is pulled out, the pin connected with the shovel plate on the feeding trolley push plate is inserted to fix the push plate on the shovel plate, then the feeding trolley push plate 28 is pushed to shovel the face lining on the discharging machine tray into the feeding trolley shovel plate, and the feeding trolley 9 returns to the original position, and the discharging action to the discharging machine 8 is completed.

[0098] The robot is a sorting robot, which performs automatic feeding and discharging operation of shoe material face lining hot pressing and stabilizing operation by a mechanical arm, the mechanical arm is a six-axis serial mechanical arm, and the method for time optimization of the robot trajectory based on the ISWO algorithm comprises the following steps.

[0099] Step one, taking six-axis serial robot arm as the research object, the D-H table and joint parameter detail drawing of the robot arm are established;

[0100] Step two, according to the actual requirements of the robot, the interpolation function, trajectory path point, objective function and constraint condition are established;

[0101] Step three, the SWO is improved and the ISWO algorithm is used to optimize the robot trajectory curve, and the time optimal trajectory curve of the robot is obtained.

[0102] In step two, the picking robot adopts 4-3-4 hybrid polynomial interpolation for trajectory planning design, and the interpolation function established is as follows:

[0103]

[0104] Wherein, S δ1 , S δ2 , S δ3 respectively represent the angular displacement of the δ joint of the robot in the first, second and third trajectory planning, t1, t2, t3 respectively represent the time of the δ joint of the robot in the first, second and third trajectory planning, and a represents the polynomial coefficient in the 4-3-4 interpolation function;

[0105] In step two, when the robot is trajectory planned by 4-3-4 polynomial interpolation method, four points need to be calibrated in space, and the trajectory path point diagram is as shown in Figure 13

[0106] Let S δ0 , S δ1 , S δ2 , S δ3 respectively represent the start point, two path points and end point of the δ joint of the picking robot; The speed and acceleration of the start point and the end point are continuous, then the interpolation points S δ0 and S δ3 have speed and acceleration of 0, S δ1 and S δ2 have equal speed and acceleration; Through these conditions, the following relationship can be constructed:

[0107] S δ = A·a (formula 2);

[0108] Wherein

[0109]

[0110] a = [a 14 a 13 a 12 a 11 a 10 ​a 23 a 22 a 21 a 20 a 34 a 33 a 32 a 31 a 30 ](Formula 5)

[0111] In Formula 2, S δ denotes the position of the δth joint of the picking robot, S δ The expansion formula is as shown in Formula 3; A is a conversion matrix obtained according to the constraint condition, and is only related to time t, and the expansion formula is as shown in Formula 4; a denotes the polynomial coefficient in the 4-3-4 interpolation function, and the expansion formula is as shown in Formula 5; the polynomial coefficient in the 4-3-4 interpolation function is solved according to the above formula, so as to obtain the motion trajectory of each joint of the picking robot in the three interpolation sections.

[0112] In Step 2, the optimization objective function and the constraint condition of the picking robot are as follows:

[0113] f δ (t)=min(t1+t2+t3) (Formula 6)

[0114]

[0115] In the formula, t1, t2, and t3 denote the time of each joint after optimization in each interpolation section, and denote the velocity and acceleration of the δth joint of the picking robot, respectively, and denote the maximum velocity and maximum acceleration of the δth joint of the picking robot, respectively.

[0116] In Step 3, the improvement content of the SWO algorithm includes: introducing the elite pool strategy to the nest building stage of the SWO algorithm to solve the phenomenon of nest point aggregation, and improving the ability of the algorithm to jump out of the local optimum, and the formula is as follows:

[0117]

[0118]

[0119] In the formula, are the first three optimal individuals, is randomly composed of the best three individuals; in the search process, the optimal individual in the nest building stage formula and the random individual will be replaced by a random selection from the elite pool, and the diversity of the candidate solutions in the elite pool makes the algorithm update more flexible, and enhances the ability of the algorithm to jump out of the local optimum.

[0120] The improvement of the SWO algorithm in step three includes: introducing the spiral search strategy into the following and nest-building behavior of the SWO algorithm, gradually reducing the search range by changing the value of b with the increase of the iteration number, and improving the convergence speed of the algorithm, and the specific formula is as follows:

[0121] Beta=e bl *cos(2pi l) (formula 13)

[0122]

[0123] Formula 14 represents the mathematical expression of the following and escaping behavior of the hunting stage of the spider wasp algorithm, and formula 15 represents the mathematical model of its nest-building behavior; gamma is the Levy generated number, is a binary vector, and formula 12 and formula 13 represent the change function in the spiral search strategy, which can effectively make the operator concentrate in the high probability area of the solution, thereby reducing the iteration number and speeding up the finding of the optimal solution;

[0124] The improvement of the SWO algorithm in step three includes: introducing an improved reciprocating population reduction strategy in the population reduction and memory storage stage of the original SWO algorithm, and the specific formula is as follows:

[0125]

[0126] In the formula, N max and N min are the maximum population number and the minimum population number, t and t max are the current iteration number and the maximum iteration number, % is the remainder operator, and Cy represents the number of reciprocating cycles;

[0127] Step three separately performs time-optimal trajectory planning for each segment of the trajectory of the picking robot;

[0128] Step three includes the following steps: step ①: initializing the basic parameters of the ISWO algorithm, the population number 6N, the maximum iteration number t max , the balance probability Tr between hunting and mating behavior is 0.3, the crossover probability Cr is 0.2, and the time upper limit ub(2,2,2) s and the time lower limit lb(0,0,0) s of the 4-3-4 interpolation target function;

[0129] Step ②: calculate the fitness value of the spider wasp according to formula 6 and substitute the running time t1, t2, t3 of the 3 segments of the trajectory of each joint of the mechanical arm into formula (6) to judge whether the speed and acceleration constraints are met, compare the fitness values that meet the speed and acceleration constraints, update the optimal individual of the spider wasp and save it;

[0130] Step 3: The algorithm enters the iteration process, and if the random number rand generated between [0, 1] is less than Tr, the hunting or nesting stage is entered; wherein the following-up, escaping and nesting stage of the hunting stage are updated according to formula 14 and formula 15 to update the position of the spider bee;

[0131] Step 4: If the random number r is greater than Tr, the female and male spider bees mate to produce offspring, and the mating behavior is performed;

[0132] Step 5: Memory storage is added, the population number is changed according to the reciprocal population reduction strategy of formula 16, and the optimization precision is improved;

[0133] Step 6: The fitness value of the updated position of the spider bee is calculated, the optimal value of the fitness value meeting the speed and acceleration constraints is compared with the optimal value of the previously saved spider bee individual, and the optimal value obtained by the comparison is updated as the optimal value of the current spider bee individual and is saved;

[0134] Step 7: It is judged whether the maximum iteration number is reached, if yes, the iteration is stopped, and the optimal fitness value of the spider bee and the 3-stage trajectory running time of each joint of the robot are output, otherwise, the step 3 is returned.

[0135] The robot is an ABB series IRB1200 six-axis serial robot of ABB1200 robot, and the method of the sorting system based on the ISWO algorithm for time optimization of the robot trajectory can be simulated and verified in matlab, and the feasibility of the time reduction of the robot before and after the trajectory optimization by the algorithm can be confirmed.

[0136] Example 1

[0137] Please refer to Figures 1-5A kind of robot face lining sorting system based on ISWO algorithm trajectory planning, robot workstation model includes: device body 1, punch die 2, feeding car 9, outer frame 10, screw rod 14, micro DC motor 16, back baffle 19, sliding block 22, mounting plate 23 and proximity switch 24, punch die 2 has six, six punch die 2 are installed in device body 1 inside side by side, device body 1 side is equipped with support steel frame 3, support steel frame 3 is installed with moving device 4, moving device 4 bottom is equipped with robot 5, robot 5 flange plate is equipped with end effector 6, device body 1 side is equipped with feeding machine 7 and discharging machine 8 respectively, feeding car 9 is placed in feeding machine 7 side, by neatly into the face lining of dish is placed on the feeding car shovel plate 27, push feeding car push material plate 28 can be face lining on the feeding car shovel plate 57 is topped into the tray of feeding machine 7, completes the feeding action of feeding machine 7, robot 5 carries end effector 6 and moves accurately along the side by side direction of feeding and discharging machine by moving device, air needle on end effector 6 picks up the face lining on feeding machine 7, completes the feeding action, waits for the body to complete the face lining pressure stabilization, robot 5 carries end effector and takes face lining to discharging machine 8, discharging machine 8 drops a face lining height, worker pushes material car outer frame 25 and advances towards discharging machine, push feeding car push material plate 28 can shovel face lining on the tray of discharging machine 8 into the feeding car shovel plate 27, feeding car 9 is returned again, and the unloading action of discharging machine 8 is completed, the workstation can realize the partial automation of shoe material face lining hot-pressing stability, greatly reduces the security risk and workload of worker when working, and reduces the labor cost of enterprise.

[0138] Example 2:

[0139] Proximity switch 24 is provided with three, two proximity switches 24 are provided on mounting plate 23, and the upper limit and lower limit signals of lifting platform 12 are collected by the two proximity switches 24 respectively; proximity switch 24 is provided on lifting platform 12, and whether there is face lining on lifting platform 12 is detected.

[0140] Example 3:

[0141] The aluminum profile of material machine side baffle 18 installed on the two sides of outer frame 10 can adjust the distance of material machine side baffle 18 through loose angle aluminum and outer connecting plate, for limiting the movement and rotation of face lining of different sizes, the aluminum profile of side baffle installed on the outer frame of feeding machine, discharging machine and feeding car can adjust the distance of side baffle through loose angle aluminum and outer connecting plate, so that the face lining of different sizes has only one degree of freedom of movement.

[0142] Example 4:

[0143] Two guide rails 21 are installed on both ends of one side of the mounting plate 23, the two guide rails 21 are arranged in parallel with each other, and the guide rails 21 are slidably connected with both ends of the sliding block 22, the sliding block 22 is connected with the lifting platform 12 by the heightening block 13; the backstop 19 is supported by the support frame 20 installed on the mounting plate 23, which is used to prevent the face lining from being pressed and bent, the lead screw 14, the bearing seat, the guide rail 21 and the sliding block 22 are installed on the mounting plate 23, the micro DC motor 16 is installed inside the motor support 17, the micro DC motor 16 is sleeved with the shaft coupling 15 outside the output end, the shaft coupling 15 is connected with one end of the bottom of the lead screw 14, and the lead screw 14 is threadedly connected with the sliding block 22; the fixed foot stand 11 is installed at the bottom of the outer frame 10, which is used to prevent interference when the feeding trolley 9 is attached to the material sticking machine.

[0144] Example 5:

[0145] The feeding trolley 9 comprises a feeding trolley outer frame 25, a feeding trolley guide block 26, a feeding trolley shovel plate 27, a feeding trolley pushing plate 28, a trolley handle 29, a caster mounting plate 30 and a flat top universal caster 31. The feeding trolley guide block 26 is arranged inside the feeding trolley outer frame 25, and the feeding trolley shovel plate 27 is arranged between the feeding trolley guide blocks 26. The feeding trolley shovel plate 27 is provided with the feeding trolley pushing plate 28 on one side, and the feeding trolley pushing plate 28 is provided with the trolley handle 29 welded on one end. The feeding trolley outer frame 25 is provided with the caster mounting plate 30 at the bottom, and the caster mounting plate 30 is provided with the flat top universal caster 31 at the bottom. There are four lengthwise countersunk grooves on the upper and lower surfaces of the feeding trolley shovel plate. The feeding trolley shovel plate is bolted together with the four screws welded on the feeding trolley outer frame through the countersunk grooves, which limits the five degrees of freedom of the feeding trolley shovel plate, so that the feeding trolley shovel plate can only slide along one axis on the feeding trolley outer frame. The feeding trolley pushing plate and the rear of the feeding trolley shovel plate are both provided with round holes, and their relative displacement can be limited by inserting and pulling out the pin.

[0146] Working principle: the face lining neatly stacked in a tray is placed on the shovel plate 27 of the feeding trolley, the worker pushes the outer frame 25 of the trolley forward to the upper feeder, the upper guide block of the feeding trolley 9 is aligned with the upper feeder 7 and closely attached, the T-shaped bolt embedded in the outer frame 25 of the trolley is clamped to the shovel plate 27 of the feeding trolley, the pin connected with the shovel plate on the feeding trolley push plate 28 is pulled out so that the push plate and the shovel plate can slide, since the lower limit position of the tray of the upper feeder 7 is slightly lower than the height of the shovel plate 27 of the feeding trolley, the face lining on the shovel plate 27 of the feeding trolley can be pushed into the tray of the upper feeder 7 by pushing the feeding trolley push plate 28, and the feeding action to the upper feeder 7 is completed. The robot 5 carries the end effector 6 to move accurately along the upper and lower feeders in the side-by-side direction through the moving device 4, moves to the upper side of the upper feeder 7 after feeding, then the robot 5 carries the end effector 6 to reach the face lining to be picked up through teaching, the air needle on the end effector 6 picks up the face lining on the upper feeder 7, the upper feeder 7 rises by one face lining height, since the face lining has different thicknesses on the left and right sides and is alternately stacked by 180 degrees when stacked, in order to stabilize the direction, the end effector 6 can be rotated by 180 degrees and placed in the mold, the feeding action is completed, after the face lining is stabilized and completed, the robot 5 carries the end effector 6 to take the face lining to the lower feeder 8, the lower feeder 8 is lowered by one face lining height, and the process is repeated, after the face lining on the upper feeder 7 is stabilized and all are taken to the lower feeder 8 by the robot 5, the worker pushes the outer frame 25 of the feeding trolley forward to the lower feeder 8, the upper guide block of the feeding trolley 9 is aligned with the lower feeder 8 and closely attached, the T-shaped bolt clamping the shovel plate 28 of the feeding trolley is pulled out, the pin connected with the shovel plate on the feeding trolley push plate is inserted again so that the push plate is fixed on the shovel plate, the face lining on the tray of the lower feeder can be shoveled into the shovel plate of the feeding trolley by pushing the feeding trolley push plate 28, and the feeding trolley 9 is returned, the unloading action to the lower feeder 8 is completed. The working station can realize partial automation of shoe material face lining hot pressing and stabilization, greatly reduce the safety hidden danger and workload of workers, and reduce the labor cost of enterprises.

[0147] The mechanical design part of the example is marked as: 1, device main body; 2, stamping die; 3, support steel frame; 4, moving device; 5, robot; 6, end effector; 7, upper feeder; 8, lower feeder; 9, feeding trolley; 10, outer frame; 11, fixed foot base; 12, lifting platform; 13, heightening block; 14, lead screw; 15, shaft coupling; 16, micro DC motor; 17, motor support; 18, feeder side edge baffle; 19, rear baffle; 20, support frame; 21, guide rail; 22, sliding block; 23, mounting plate; 24, proximity switch; 25, trolley outer frame; 26, feeding trolley guide block; 27, feeding trolley shovel plate; 28, feeding trolley push plate; 29, trolley handle; 30, caster mounting plate; 31, flat top universal caster.

[0148] Example 6:

[0149] As Figure 6As shown, the SWO (spider bee algorithm) is improved, and the improved SWO algorithm and 4-3-4 hybrid polynomial interpolation function are used for time optimal planning of the picking trajectory of the robot under the condition of constraining the robot joint speed and acceleration, including the following steps:

[0150] 1) Establish the D-H table of ABB1200 robot;

[0151] 2) According to the actual requirements of the robot, establish the interpolation function, trajectory path point, objective function and constraint condition;

[0152] 3) Improve the SWO algorithm and use the ISWO algorithm to optimize the robot trajectory curve to obtain the time optimal trajectory curve of the robot.

[0153] The specific implementation process is as follows: based on the construction of the shoe material surface lining unloading robot workstation model, the ISWO algorithm is used to plan the time optimal trajectory of the picking robot motion trajectory.

[0154] Further, the robot D-H table established in step 1) is as follows:

[0155] Table 1

[0156]

[0157] Further, the parameter detail diagram of the mechanical arm joint in step 1) is as shown in the accompanying drawings: Figure 7 As shown:

[0158] Further, step 2) includes the following steps:

[0159] First, the picking robot uses 4-3-4 hybrid polynomial interpolation for trajectory planning design, and the interpolation function is established as shown below:

[0160]

[0161] In the above formula: S δ1 , S δ2 , S δ3 Each represents the angular displacement of the δth joint of the robot in the 1st, 2nd and 3rd trajectory planning, t1, t2 and t3 each represent the time of the δth joint of the robot in the 1st, 2nd and 3rd trajectory planning, and a represents the polynomial coefficient in the 4-3-4 interpolation function.

[0162] Secondly, when the robot is trajectory planned by 4-3-4 polynomial interpolation method, 4 points need to be calibrated in space, S δ0 , S δ1 , S δ2 , S δ3respectively represent the start point, two path points and the end point of the δth joint segment of the picking robot. The velocity and acceleration of the start point and the end point are continuous, and the following relationship can be constructed through these conditions:

[0163] S δ = A · a (2)

[0164] wherein

[0165]

[0166] a = [a 14 a 13 a 12 a 11 a 10 a 23 a 22 a 21 a 20 a 34 a 33 a 32 a 31 a 30 ](5)

[0167] S δ in formula (2) represents the position of the δth joint of the picking robot, S δ The expansion formula is as formula (3); A is a conversion matrix obtained according to the constraint condition, which is only related to time t, and the expansion formula is formula (4); a represents the polynomial coefficient in the 4-3-4 interpolation function, and the expansion formula is formula (5); according to the above formula, the polynomial coefficient in the 4-3-4 interpolation function can be solved, so as to obtain the motion trajectory of each joint of the picking robot in the three interpolation segments. Further, the optimization objective function and the constraint condition of the picking robot in step 2) are as follows:

[0168] f δ (t) = min (t1 + t2 + t3) (6)

[0169]

[0170] t1, t2, t3 in the formula represent the time of each joint after optimization in each interpolation segment, and respectively represent the velocity and acceleration of the δth joint of the picking robot, and respectively represent the maximum velocity and maximum acceleration of the δth joint of the picking robot. Further, the improvement content of the SWO algorithm in step 2) includes:

[0171] (a). A strategy of elite pool is introduced into the nest-building stage of SWO algorithm to solve the phenomenon of nest point aggregation and improve the ability of the algorithm to jump out of local optimum. The formula is as follows:

[0172]

[0173] wherein are the first three optimal individuals, is randomly composed of the best three individuals. In the search process, the optimal individuals and the random individuals in the nest-building stage formula will be replaced by a random selection from the elite pool. The diversity of candidate solutions in the elite pool makes the algorithm update more flexible and enhances the ability of the algorithm to jump out of local optimum.

[0174] (b). The spiral search strategy is introduced into the following and nest-building behavior of SWO algorithm. The search range is gradually reduced by changing the value of b with the increase of iteration number, which improves the convergence speed of the algorithm. The specific formula is as follows:

[0175]

[0176] Beta=e bl *cos(2πl)(13)

[0177]

[0178]

[0179] Equation (14) represents the mathematical expression of the following and escape behavior of the hunting stage of the spider bee algorithm, and equation (15) represents the mathematical model of its nest-building behavior; γ is the Levy generated number, is a binary vector, and equations (12) and (13) represent the change function in the spiral search strategy, which can effectively make the operator concentrate in the high probability area of the solution, thereby reducing the iteration number and speeding up the finding of the optimal solution.

[0180] (c). In the population reduction and memory storage stage of the original SWO algorithm, an improved reciprocating population reduction strategy is introduced. The specific formula is as follows:

[0181]

[0182] wherein N max and N min are the maximum population number and the minimum population number, t and t max are the current iteration number and the maximum iteration number, % is the remainder operator, and Cy represents the number of reciprocating cycles.

[0183] Further, step 3) separately plans a time-optimal trajectory for each interpolated trajectory of the picking robot.

[0184] Further, the step 3) comprises the following steps:

[0185] 1: initialize the basic parameters of the ISWO algorithm, population size 6N, maximum iteration number t max , the balance probability between hunting and mating behavior Tr=0.3, the crossover probability Cr=0.2, the time upper limit ub(2,2,2) s and the time lower limit lb(0,0,0) s of the 4-3-4 interpolation target function.

[0186] 2: calculate the fitness value of the spider wasp according to formula (6) and the 3-section trajectory running time t1, t2, t3 of each joint of the mechanical arm is substituted into formula (6) to judge whether the speed and acceleration constraints are met, the fitness values meeting the speed and acceleration constraint conditions are compared, the optimal individual of the spider wasp is updated and saved.

[0187] 3: the algorithm enters the iteration process, if the random number r generated between [0,1] is less than TR, then enter the hunting or nesting stage. Wherein, the following processes such as following, escaping and nesting stage in the hunting stage are updated according to formula (14), (15).

[0188] 4: if the random number r is greater than TR, the female and male spider wasps mate to produce offspring, and mating behavior is performed.

[0189] 5: add memory storage, change the population size according to the reciprocal population reduction strategy of formula (16), and improve the optimization accuracy.

[0190] 6: calculate the fitness value of the updated spider wasp position, compare the fitness values meeting the speed and acceleration constraint conditions with the optimal value of the previously saved spider wasp individual, and update the optimal value of the current spider wasp individual to the optimal value of the current spider wasp individual and save it.

[0191] 7: judge whether the maximum iteration number is reached, if yes, stop iteration, and output the optimal fitness value of the spider wasp and the 3-section trajectory running time of each joint of the mechanical arm, otherwise return to step 3.

[0192] Example 7:

[0193] In order to further illustrate the accuracy and reliability of the method of the application, the improved spider wasp algorithm time optimal trajectory planning of the sorting robot is carried out by Matlab software. In this simulation, there are 30 spider wasp individuals for each joint, the balance probability between hunting and mating TR=0.3, the uniform crossover operator Cr=0.2 for male and female spider wasps, and the maximum iteration number t max= 1000, the number of reciprocating cycles Cy = 2. According to the ABB1200 robot official data, the maximum angular velocity allowed by the picking robot 1-6 joints is: 288° / s, 240° / s, 300° / s, 400° / s, 405° / s, 600° / s, and the maximum acceleration is 2400° / s 2 , considering that there are 32.7N clamp loads, the maximum acceleration is set to 270 / s 2 , the angular velocity and angular acceleration of the initial point and the terminal point are both 0, and the maximum iteration number t max = 1000. Table 2 is the four path points of the picking robot trajectory, Figure 8 is the approximate trajectory graph of the on-site operation scene of the mechanical arm feeding, Figure 9 is the real motion trajectory graph of the mechanical arm simulation. Figure 10 The dynamic parameter graph of the unoptimized mechanical arm velocity and acceleration is given, and the maximum velocity and acceleration of the six joints of the unoptimized mechanical arm are: 56.1° / s, 30.4° / s, -44.2° / s, -23.8° / s, -49.2° / s, 28.0° / s, 43.8° / s 2 , -26.7° / s 2 , -52.4° / s 2 , -39.8° / s 2 , -60.5° / s 2 , 55.0° / s 2 . Comparing Table 7 with the upper limit of the mechanical arm motion, the velocity and acceleration of each joint of the unoptimized mechanical arm are relatively conservative, and the performance of the mechanical arm is not fully utilized. Figure 11 The dynamic parameter graph of the mechanical arm velocity and acceleration optimized by SWO is given, and the longitudinal axis can be observed to intuitively analyze that the velocity and acceleration of each joint of the mechanical arm after the SWO algorithm optimization have been significantly improved within the constraint range, for example, the maximum velocity of joint 1 is improved from 56.1° / s to 105.8° / s, and the maximum acceleration is improved from 43.8° / s 2 to 167.8° / s 2 , and the effect of other joints is also obviously improved, the velocity curve of each joint is smooth, the acceleration curve is continuous, the running time is reduced from 6s to 3.88s, which is shortened by nearly 35% of the time. Figure 11The dynamic parameter diagram of the optimized mechanical arm speed and acceleration of ISWO. Table 3 is the comparison of the calculation results of the three algorithms. It can be seen that the motion trajectory of the mechanical arm optimized by the ISWO algorithm is smooth, the speed curve and the acceleration curve of each joint are still continuous, the speed and acceleration of each joint are basically further improved, and the running time is further reduced to 3.28s, which is 35% of SWO, and the time of ISWO is shortened by 45%. Therefore, it can be shown that the time optimal trajectory planning method of the mechanical arm based on the ISWO algorithm proposed in the paper can shorten the operation time of the mechanical arm while ensuring smooth execution of the action.

[0194] Table 2

[0195]

[0196] Table 3

[0197]

[0198] The example proposes a robot face lining sorting system based on ISWO algorithm trajectory planning, relating to the fields of robot technology and mechanical automation. The face lining feeding and discharging workstation model of the ABB1200 robot is first constructed, including the device main body, the stamping die, the feeding car, the outer frame, the screw rod, the micro DC motor, the back baffle, the sliding block, the mounting plate and the proximity switch. Then the spider bee algorithm (SWO) is improved, the elite pool strategy and the spiral search strategy are introduced into the hunting and nesting stages, and the original strategy of the population reduction stage is reciprocally improved, the ability of the original SWO algorithm to jump out of the local optimum is enhanced, and the convergence speed and accuracy of the algorithm are improved. Then the time optimal planning of the improved algorithm (ISWO) is carried out on the basis of the 4-3-4 hybrid polynomial interpolation function of the sorting trajectory, and finally the simulation in matlab verifies the feasibility of the time optimization of the picking trajectory. The application not only realizes the automatic feeding and discharging of the shoe material face lining hot pressing stable type, but also further improves the robot feeding and discharging beat, greatly reduces the safety hidden danger of workers during work, improves the production efficiency, and has certain practical value for shoemaking enterprises.

[0199] The foregoing merely illustrates the principles of the application and application of its leading features. This application is not limited to the illustrative embodiments shown and described herein. Rather, this application is capable of operating within a further range of conditions and environments than those specifically described herein, and further modifications can be made without departing from the spirit or scope of the application. Accordingly, the description is to be construed as illustrative only and not restrictive of the broad disclosure or application of the application. The specification and drawings are, accordingly, to be regarded simply as illustrative and with the scope of the application being measured by the appended claims, and not with the specification. No admission is made that any reference constitutes prior art. It is my intent, therefore, to be limited only as appears in the following claims.

[0200] Furthermore, it should be understood that although the description above relates to embodiments, not every embodiment contains only one independent technical solution, and the description above is only for the sake of clarity, and those skilled in the art should understand the description as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that those skilled in the art can understand.

Claims

1. A robot face mask sorting system based on ISWO algorithm trajectory planning, characterized in that: The sorting system includes a face lining sorting work station and a robot for automatic feeding and discharging for shoe material face lining hot pressing and stabilizing operation; the face lining sorting work station includes a device main body, a stamping die, a feeding trolley, an outer frame, a lead screw, a micro DC motor, a back baffle, a sliding block, a mounting plate and a proximity switch; the sorting system performs time optimization on the robot trajectory based on the ISWO algorithm, and the method is as follows: the original SWO algorithm for robot feeding and discharging is enhanced by introducing the elite pool strategy and the spiral search strategy into the hunting and nest building stages, and reciprocally improving the original strategy for the population reduction stage, so as to jump out of the local optimal capacity and improve the convergence speed and precision of the algorithm, and the ISWO algorithm is used to perform time optimal planning on the feeding trajectory based on the 4-3-4 mixed polynomial interpolation function under the condition of constraining the joint speed and acceleration of the robot; The mechanical structure of the face lining sorting work station includes a device main body (1), a stamping die (2), a feeding trolley (9), an outer frame (10), a lead screw (14), a micro DC motor (16), a back baffle (19), a sliding block (22), a mounting plate (23) and a proximity switch (24); The stamping die (2) is N in number and is installed side by side inside the device main body (1), one side of the device main body (1) is provided with a supporting steel frame (3), the supporting steel frame (3) is provided with a moving device (4), the bottom of the moving device (4) is provided with a robot (5), and the flange plate of the robot (5) is provided with an end effector (6); One side of the device main body (1) is provided with a feeding machine (7) and a discharging machine (8), respectively, and the feeding trolley (9) is placed on one side of the feeding machine (7); The feeding machine and the discharging machine each include a lifting table for placing materials, and the lifting table is driven to lift by the micro DC motor; The feeding machine is used for transferring the face lining materials sent by the feeding trolley to the feeding position of the robot, and after the materials at the stamping die are processed by the robot, the processed materials are sent to the discharging machine by the robot; The proximity switch (24) includes two proximity switches arranged at the mounting plate (23) and used for collecting the upper limit position signal and the lower limit position signal of the lifting action of the lifting table (12), and also includes a proximity switch arranged at the lifting table (12) and used for detecting whether there is face lining on the lifting table (12); One side of the mounting plate (23) is provided with guide rails (21) at both ends of the lifting table, the guide rails (21) are arranged in pairs and are arranged in parallel with each other, and the guide rails (21) are slidably connected to both ends of the sliding block (22) of the lifting table; The lead screw (14), the bearing seat, the guide rail (21) and the sliding block (22) are installed on the mounting plate (23), the micro DC motor (16) is fixed in the motor support (17) of the mounting plate, a coupling (15) is sleeved on the output end of the micro DC motor (16), one end of the coupling (15) is connected to the bottom of the lead screw (14), and the lead screw (14) is threadedly connected to the sliding block (22).

2. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 1, wherein: The outer frame (10) is provided with a fixed foot base (11) at the bottom, which is used for preventing interference when the feeding trolley (9) is attached to the material machine. The aluminum profile of the material machine side baffle (18) installed on both sides of the outer frame (10) can adjust the distance of the material machine side baffle (18) through the loose angle aluminum and the outer connecting plate, which is used to limit the movement and rotation of the different size face lining; The slider (22) and the lifting platform (12) are connected by the raised block (13); the rear baffle (19) is supported by the support frame (20) installed on the mounting plate (23), which is used to prevent the face lining from being extruded and bent; The feeding trolley (9) comprises a trolley outer frame (25); the trolley outer frame (25) is internally provided with feeding trolley guide blocks (26), and feeding trolley shovel plates (27) are arranged between the feeding trolley guide blocks (26), and feeding trolley pushing plates (28) are installed on one side of the feeding trolley shovel plates (27); The feeding trolley pushing plate (28) is welded with a trolley handle (29) at one end, the trolley outer frame (25) is installed with a caster mounting plate (30) at the bottom, and the caster mounting plate (30) is installed with a flat top universal caster (31) at the bottom.

3. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 2, characterized in that: The working method of the robot face lining sorting system comprises the following steps: Step S1, the face lining material neatly arranged in a tray is placed on the feeding trolley shovel plate (27), the trolley outer frame (25) is pushed to advance the material machine, the feeding trolley (9) is aligned and closely contacted with the guide block on the material machine (7), the T-shaped bolt embedded in the trolley outer frame (25) is clamped on the feeding trolley shovel plate (27), the pin connected with the shovel plate on the feeding trolley pushing plate (28) is pulled out to make the pushing plate and the shovel plate can slide, at this time, the lower limit position of the tray of the material machine (7) is slightly lower than the height of the feeding trolley shovel plate (27), then the feeding trolley pushing plate (28) is pushed to push the face lining on the feeding trolley shovel plate into the tray of the material machine 7, and the feeding action of the material machine 7 is completed; Step S2, the robot (5) with the end effector (6) moves along the feeding and discharging machine in parallel direction through the moving device (4), moves to the top of the material machine (7) which has finished feeding, then the robot (5) with the end effector (6) reaches the face lining to be picked up, the air needle on the end effector (6) picks up the face lining on the material machine (7), the material machine (7) rises by one face lining height, because the face lining has different thicknesses on the left and right sides, the face lining is stacked alternately by 180 degrees, and when the direction is unified, the end effector (6) is rotated by 180 degrees and placed in the mold, and the feeding action is completed; Step S3, the standby body will face the liner pressure stabilization is completed, the robot (5) carrying end effector (6) will face the liner to the feeder (8), and then the feeder (8) is lowered by one face liner height, so reciprocating, wait for the feeder (7) on the face liner stable type complete and all are taken to the feeder (8) by the robot (5), can promote the material car outer frame (25) to the feeder (8) forward, through the feeding car (9) on the guide block and the feeder (8) alignment and close, dial the T-shaped bolt stuck shovel plate (27) of the feeding car, and then insert the pin connected with the shovel plate on the feeding car push plate to make the push plate fixed on the shovel plate, then push the feeding car push plate (28) shovel the face liner on the feeder tray into the feeding car shovel plate, the feeding car (9) is returned, the unloading action of the feeder (8) is completed.

4. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 1, characterized in that: The robot is a picking robot, which performs automatic feeding and discharging operation of shoe material face liner hot pressing and stabilizing operation by mechanical arm, the mechanical arm is a six-axis serial mechanical arm, and the time optimization method of the robot trajectory based on the ISWO algorithm of the sorting system comprises the following steps. Step one, taking the six-axis serial mechanical arm as the research object, the D-H table and joint parameter detail drawing of the robot mechanical arm are established; Step two, according to the actual requirements of the robot, an interpolation function, a trajectory path point, an objective function and a constraint condition are established; Step three, the SWO is improved and the ISWO algorithm is used to optimize the robot trajectory curve, and the time optimal trajectory curve of the robot is obtained.

5. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 4, characterized in that: In step two, the picking robot adopts 4-3-4 hybrid polynomial interpolation for trajectory planning design, and the interpolation function established is as follows: wherein S δ1 , S δ2 , S δ3 each represents the angular displacement of the δth joint of the robot in the 1st, 2nd, 3rd trajectory planning, t1, t2, t3 each represents the time of the δth joint of the robot in the 1st, 2nd, 3rd trajectory planning, and a represents the polynomial coefficient inside the 4-3-4 interpolation function. In step two, 4-3-4 polynomial interpolation method is used to plan the trajectory of the robot, which needs to calibrate 4 points in space. In the trajectory path points, S δ0 , S δ1 , S δ2 , S δ3 respectively represent the start point, two path points and the end point of each section of the δ joint of the picking robot. The velocity and acceleration of the start point and the end point are continuous, so the velocity and acceleration of the interpolation points S δ0 and S δ3 are 0, and the velocity and acceleration of S δ1 and S δ2 are equal. Through these conditions, the following relationship can be constructed: S δ = A a (Equation 2); wherein a = [a 14 a 13 a 12 a 11 a 10 a 23 a 22 a 21 a 20 a 34 a 33 a 32 a 31 a 30 ] (Equation 5) In formula 2, S δ represents the position of the δ joint of the picking robot, S δ The expansion formula is as shown in formula 3; A is a conversion matrix obtained according to a constraint condition, is only related to time t, the expansion formula is as shown in formula 4; a represents polynomial coefficients in the 4-3-4 interpolation function, the expansion formula is as shown in formula 5; the polynomial coefficients in the 4-3-4 interpolation function are solved according to the above formula, so that the motion trajectories of each joint of the picking robot in the three interpolation sections are obtained.

6. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 5, characterized in that: In step two, the optimization objective function and the constraint condition of the picking robot are as follows: f δ (t) = min(t1+ t2+ t3) (Equation 6) t1, t2, t3 in the formula represent the time after optimization of each joint in each interpolation, where respectively represent the velocity and acceleration of the δth joint of the picking robot, and respectively represent the maximum velocity and maximum acceleration of the δth joint of the picking robot.

7. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 6, characterized in that: In step three, the improvement content of the SWO algorithm includes: by introducing the elite pool strategy to the nest building stage of the SWO algorithm, the phenomenon of nest point aggregation is solved, and the ability of the algorithm to jump out of the local optimum is improved, and the formula is as follows: wherein The first three best individuals, The best three individuals are randomly composed; in the search process, the best individual in the nest stage formula and the random individual will be replaced by a random selection from the elite pool. The diversity of candidate solutions in the elite pool makes the algorithm update more flexible and enhances the ability of the algorithm to jump out of the local optimum.

8. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 7, characterized in that: In step three, the improvement content of the SWO algorithm includes: introducing the spiral search strategy to the following and nest building behavior of the SWO algorithm, gradually reducing the search range through the b value changing with the increase of iteration times, and improving the convergence speed of the algorithm, and the specific formula is as follows: Beta = e bl * cos(2πl) (Equation 13) Equation 14 represents the mathematical expression of the follow and escape behavior in the hunting stage of the spider mason algorithm, and equation 15 represents the mathematical model of the nest building behavior; γ is a Levy-generated number, is a binary vector, and equations 12 and 13 represent the change function in the spiral search strategy, which can effectively make the operators concentrate in the high-probability area of the solution, thereby reducing the number of iterations and accelerating the finding of the optimal solution; In step three, the improvement content of the SWO algorithm includes: in the population reduction and memory storage stage of the original SWO algorithm, an improved reciprocating population reduction strategy is introduced, and the specific formula is as follows: In the formula, N max and N min are the maximum population number and the minimum population number, t and t max are the current iteration number and the maximum iteration number, % is the remainder operator, and Cy represents the number of reciprocating cycles. In step three, the time optimal trajectory planning is separately carried out for each segment of the picking robot trajectory; Step three includes the following steps: Step 1: initialization of the basic parameters of ISWO algorithm, population size 6N, maximum iteration number t max , the trade-off probability between hunting and mating behavior Tr=0.3, the crossover probability Cr=0.2, the upper time limit of the 4-3-4 interpolation objective function ub(2,2,2) s and the lower time limit lb(0,0,0) s; Step 2: Calculate the fitness value f of the spider wasp according to formula 6 δ (t), and the 3-segment trajectory running time t1, t2, t3 of each joint of the mechanical arm is substituted into formula (6) to determine whether the speed and acceleration constraints are met. The fitness values that meet the speed and acceleration constraints are compared, the optimal individual of the spider wasp is updated and saved. Step ③: the algorithm enters the iteration process, if the random number rand generated between [0, 1] is less than Tr, the hunting or nest building stage is entered; wherein, the following, escaping and nest building stages are updated according to formula 14, formula 15; Step ④: if the random number r is greater than Tr, the offspring is generated by mating the female and male wasps, and mating behavior is performed; Step ⑤: memory storage is added, the population number is changed according to the reciprocating population reduction strategy of formula 16, and the optimization precision is improved; Step ⑤: memory storage is added, the population number is changed according to the reciprocating population reduction strategy of formula 16, and the optimization precision is improved; Step ⑥: the updated spider bee position fitness value calculation, to meet the speed and acceleration constraints of the optimal value of the fitness value and the previous saved spider bee individual comparison, and the optimal value of the comparison update is the optimal value of the current spider bee individual and save;Step ⑦: whether to reach the maximum number of iterations, if satisfied, stop iteration, while outputting the optimal fitness value of the spider bee and the 3 segment trajectory running time of each joint of the robot, otherwise return to step ③.

9. The robot face mask sorting system based on ISWO algorithm trajectory planning according to claim 7, characterized in that: The mechanical arm is an ABB series IRB1200 six-axis serial mechanical arm of ABB1200 robot, and the method that the sorting system optimizes the robot trajectory based on the ISWO algorithm can be simulated and verified in matlab, and the feasibility of reducing the running time before and after the trajectory optimization by the algorithm can be confirmed.

Images