Disclosure of Invention
The invention aims to provide a method and a device for generating flame path tracks through self-learning of line heating plates, which are used for learning and obtaining the deformation quantity actually generated by each flame path by analyzing the deformation quantity of a processed outer plate of a ship body during first processing, and carrying out accurate flame path track planning on the processed outer plate according to the actual deformation quantity of the flame path.
In order to solve the technical problem, the invention provides a line-fire bent plate flame path track self-learning generation method, which comprises the following steps:
calculating and obtaining an initial target angular deformation change curve corresponding to the processed outer plate; the initial target angular deformation change curve is a normal vector included angle change curve corresponding to grid curves of the same row or the same column of the initial curved surface of the processed outer plate and the target curved surface;
acquiring a primary processing flame path track of the processed outer plate according to the initial target angular deformation change curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, performing primary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to acquire a target angular deformation change curve corresponding to the processed outer plate after the current processing;
acquiring a learning correction model of the flame path processing position and the actual deformation under preset processing parameters according to the target angular deformation change curves before and after the current processing; when the current processing is primary processing, the target angular deformation change curve before the current processing is an initial target angular deformation change curve;
acquiring a secondarily planned flame path track according to the learning correction model and the target angular deformation change curve after the current processing, performing secondary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to acquire the target angular deformation change curve after the current processing; the secondarily planned flame path track consists of points, wherein the target angular deformation change curve after the current processing is equal to the actual deformation accumulated value;
judging whether the maximum value in the target angular deformation change curve after the current processing is smaller than a first threshold value or not; and if not, executing the step of obtaining a learning correction model of the flame path processing position and the actual deformation under the preset processing parameters according to the target angular deformation change curves before and after the current processing.
Optionally, the obtaining, by calculation, an initial target angular deformation change curve corresponding to the processed outer plate includes:
carrying out gridding reconstruction on the initial curved surface and the target curved surface of the processed outer plate to obtain a grid curve formed by grid point data of the same line or the same column in the initial curved surface and the target curved surface;
carrying out polynomial piecewise fitting on the grid curves to obtain a parameter equation corresponding to each grid curve;
calculating a partial derivative of the parameter equation to obtain a normal vector of each point on each grid curve;
calculating an included angle between the normal vector of each point of each grid curve and the reference normal vector by taking the normal vector at the starting point of each grid curve as a reference, and acquiring a normal vector included angle change curve corresponding to each grid curve;
and acquiring a target angular deformation change curve corresponding to the initial curved surface according to the normal vector included angle change curves corresponding to the grid curves of the same row or the same column of the initial curved surface and the target curved surface.
Optionally, the method includes obtaining a first processing flame path track of the processed outer plate according to the initial target angular deformation variation curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, performing first processing on the processed outer plate according to preset processing parameters by using the processing device, and calculating to obtain the target angular deformation variation curve corresponding to the processed outer plate after this processing, and includes:
acquiring the maximum angular deformation of the single flame channel corresponding to the thickness of the outer plate to be processed according to the technological parameters of line heating;
connecting points which are on the target angular deformation change curve and are the same integral multiple of the maximum angular deformation to obtain a primary processing flame path track corresponding to the processing outer plate;
according to the track of the primary processing flame path, locally heating the processed outer plate by using a processing device according to preset processing parameters; the processing device keeps preset processing parameters unchanged in the local heating process, wherein the preset processing parameters comprise gas-oxygen flow, moving speed of a fire gun and distance between a fire gun nozzle and a processed outer plate;
and calculating and obtaining a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
Optionally, the obtaining of the learning correction model of the flame path processing position and the actual deformation under the preset processing parameters according to the target angular deformation change curves before and after the current processing includes:
acquiring an angular deformation change curve of the processed outer plate after the current processing according to the target angular deformation change curves before and after the current processing;
calculating and obtaining the actual angular deformation of each flame path according to the position of the flame path processed at this time and the angular deformation change curve of the processed outer plate processed at this time;
and establishing a learning correction model of the flame path processing position and the actual angular deformation under preset processing parameters according to the actual angular deformation of each flame path at different positions.
Optionally, the obtaining a secondarily-planned flame path track according to the learning and correcting model and the target angular deformation change curve after the current processing, performing secondary processing on the processed outer panel according to preset processing parameters by using the processing device, and calculating to obtain the target angular deformation change curve after the current processing includes:
determining a point where the angular deformation of the target angular deformation change curve after the processing is equal to the accumulated value of the actual angular deformation as a flame path point according to a learning correction model;
connecting adjacent flame path points to obtain a secondarily planned flame path track corresponding to the processed outer plate;
eliminating the flame path tracks with the adjacent spacing smaller than a second threshold value in the secondarily planned flame path tracks; the second threshold value is the minimum flame path distance corresponding to the process requirement for processing the outer plate;
according to the secondarily planned flame path track, locally heating the processed outer plate by using a processing device according to preset processing parameters;
and calculating and obtaining a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
In addition, the invention also provides a water-fire plate-bending flame path track self-learning generation device, which comprises:
the calculation module is used for calculating and acquiring an initial target angular deformation change curve corresponding to the processed outer plate; the initial target angular deformation change curve is a normal vector included angle change curve corresponding to grid curves of the same row or the same column of the initial curved surface of the processed outer plate and the target curved surface;
the primary processing module is used for acquiring a primary processing flame path track of the processed outer plate according to the initial target angular deformation change curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, performing primary processing on the processed outer plate according to preset processing parameters by using the processing device, and calculating to acquire a target angular deformation change curve corresponding to the processed outer plate after the current processing;
the learning correction module is used for acquiring a learning correction model of the flame path processing position and the actual deformation under the preset processing parameters according to the target angular deformation change curves before and after the current processing; when the current processing is primary processing, the target angular deformation change curve before the current processing is an initial target angular deformation change curve;
the secondary processing module is used for acquiring a secondarily planned flame path track according to the learning correction model and the target angular deformation change curve after the current processing, carrying out secondary processing on the processed outer plate according to preset processing parameters by using the processing device, and calculating to acquire the target angular deformation change curve after the current processing; the secondarily planned flame path track consists of points, wherein the target angular deformation change curve after the current processing is equal to the actual deformation accumulated value;
the judging module is used for judging whether the maximum value in the target angular deformation change curve after the current processing is smaller than a first threshold value or not; if not, sending a starting signal to the learning correction module.
Optionally, the calculation module includes:
the gridding reconstruction submodule is used for carrying out gridding reconstruction on the initial curved surface and the target curved surface of the processed outer plate and obtaining a gridding curve formed by grid point data in the same line or the same column in the initial curved surface and the target curved surface;
the fitting submodule is used for carrying out polynomial piecewise fitting on the grid curves to obtain a parameter equation corresponding to each grid curve;
the first calculation submodule is used for solving the partial derivatives of the parameter equation and obtaining the normal vectors of each point on each grid curve;
the second calculation submodule is used for calculating an included angle between the normal vector of each point of each grid curve and the reference normal vector by taking the normal vector at the starting point of each grid curve as a reference, and acquiring a normal vector included angle change curve corresponding to each grid curve;
and the third calculation sub-module is used for acquiring an initial target angular deformation change curve corresponding to the initial curved surface according to the normal vector included angle change curve corresponding to the grid curves of the same row or the same column of the initial curved surface and the target curved surface.
Optionally, the primary processing module includes:
the maximum angular deformation obtaining submodule is used for obtaining the maximum angular deformation of the single flame channel corresponding to the thickness of the outer plate to be processed according to the technological parameters of line heating;
the first flame path track generation submodule is used for connecting points which are on the target angular deformation change curve and are the same integral multiple with the maximum angular deformation to obtain a primary processing flame path track corresponding to the processed outer plate;
the primary processing submodule is used for locally heating the processed outer plate according to preset processing parameters by using the processing device according to the primary processing flame path track; the processing device keeps preset processing parameters unchanged in the local heating process, wherein the preset processing parameters comprise gas-oxygen flow, moving speed of a fire gun and distance between a fire gun nozzle and a processed outer plate;
and the fourth calculation submodule is used for calculating and acquiring a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
Optionally, the learning modification module includes:
the comparison submodule is used for acquiring the angular deformation change curve of the processed outer plate after the current processing according to the target angular deformation change curves before and after the current processing;
the fifth calculation submodule is used for calculating and acquiring the actual angular deformation of each flame path according to the position of the flame path processed at this time and the angular deformation change curve of the processed outer plate processed at this time;
and the learning correction submodule is used for establishing a learning correction model of the flame path processing position and the actual angular deformation under the preset processing parameters according to the actual angular deformation of each flame path at different positions.
Optionally, the secondary processing module includes:
the determining submodule is used for determining a point, which is equal to the accumulated value of the actual angular deformation, of the angular deformation on the target angular deformation change curve after the processing according to the learning correction model as a flame path point;
the second flame path track generation submodule is used for connecting adjacent flame path points to obtain a secondary planned flame path track corresponding to the processed outer plate;
the eliminating submodule is used for eliminating the flame path tracks with the adjacent spacing smaller than a second threshold value in the secondarily planned flame path tracks; the second threshold value is the minimum flame path distance corresponding to the process requirement for processing the outer plate;
the secondary processing submodule is used for locally heating the processed outer plate according to preset processing parameters by using the processing device according to the secondarily planned flame path track;
and the sixth calculation submodule is used for calculating and acquiring a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
The invention provides a line heating flame path track self-learning generation method, which comprises the following steps: calculating and obtaining an initial target angular deformation change curve corresponding to the processed outer plate; the initial target angular deformation change curve is a normal vector included angle change curve corresponding to grid curves of the same row or the same column of the initial curved surface of the processed outer plate and the target curved surface; acquiring a primary processing flame path track of the processed outer plate according to the initial target angular deformation change curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, performing primary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to acquire a target angular deformation change curve corresponding to the processed outer plate after the current processing; acquiring a learning correction model of the flame path processing position and the actual deformation under preset processing parameters according to the target angular deformation change curves before and after the current processing; when the current processing is primary processing, the target angular deformation change curve before the current processing is an initial target angular deformation change curve; acquiring a secondarily planned flame path track according to the learning correction model and the target angular deformation change curve after the current processing, performing secondary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to acquire the target angular deformation change curve after the current processing; the secondarily planned flame path track consists of points, wherein the target angular deformation change curve after the current processing is equal to the actual deformation accumulated value; judging whether the maximum value in the target angular deformation change curve after the current processing is smaller than a first threshold value or not; if not, executing the step of obtaining a learning correction model of the flame path processing position and the actual deformation under the preset processing parameters according to the target angular deformation change curves before and after the current processing;
therefore, on the premise that the angular deformation generated after each flame channel is processed is unknown, the method ensures that the processed outer plate is not over-processed in a mode of presetting the maximum angular deformation of a single flame channel, and obtains the actual angular deformation of the flame channel under the same processing parameters through self-learning correction, so that the flame channel track in secondary processing can be accurately formulated, the method has strong robustness and can adapt to flame channel planning under different processing conditions. In addition, the invention also provides a water-fire plate-bending flame path track self-learning generation device, which also has the beneficial effects.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a flame path trajectory self-learning generation method for line heating. The method can comprise the following steps:
step 101: calculating and obtaining an initial target angular deformation change curve corresponding to the processed outer plate; the initial target angular deformation change curve is a normal vector included angle change curve corresponding to grid curves of the same row or the same column of the initial curved surface of the processed outer plate and the target curved surface.
The purpose of this step is to calculate and obtain an initial target angular deformation change curve corresponding to the initial curved surface of the processed outer plate of the hull using a normal vector angle change curve corresponding to a grid curve of the same row or the same column of the initial curved surface of the processed outer plate of the hull and the target curved surface. The initial target angular deformation variation curve may be all initial target angular deformation variation curves corresponding to all grid curves in the same row or column of the initial curved surface.
It can be understood that the specific obtaining manner of the initial curved surface and the target curved surface of the processed outer plate of the hull in the step can be set by a designer or a user according to a practical scene and user requirements, for example, the initial curved surface and the target curved surface of the processed outer plate sent by the user can be directly received, or the initial curved surface of the processed outer plate of the hull can be collected by using a scanner or a sensor device and the target curved surface of the processed outer plate sent by the user can be received. Correspondingly, the step may further include a step of obtaining a processed curved surface of the processed outer plate and a target curved surface before the step, which is not limited in this embodiment.
Specifically, the step may include the following steps:
step 1011: and carrying out gridding reconstruction on the initial curved surface and the target curved surface of the processed outer plate to obtain a grid curve formed by grid point data of the same line or the same column in the initial curved surface and the target curved surface.
Step 1012: and performing polynomial piecewise fitting on the grid curves to obtain a parameter equation corresponding to each grid curve.
Step 1013: and solving the partial derivatives of the parameter equations to obtain the normal vectors of each point on each grid curve.
Step 1014: and taking the normal vector at the starting point of each grid curve as a reference, calculating an included angle between the normal vector of each point of each grid curve and the reference normal vector, and acquiring a normal vector included angle change curve corresponding to each grid curve.
Step 1015: and acquiring a target angular deformation change curve corresponding to the initial curved surface according to the normal vector included angle change curves corresponding to the grid curves of the same row or the same column of the initial curved surface and the target curved surface.
Specifically, the result of the step of reconstructing the mesh of the initial curved surface and the target curved surface of the processed outer plate may be as shown in fig. 2, where the solid line in fig. 2Representing an initial surface and a dotted line representing a target surface; polynomial piecewise fitting may be performed by extracting grid point data on the same row or column of both. Taking the first row in the long side direction of fig. 2 as an example, after dividing into two equal parts and fitting respectively, the fitting parametric equations of the first row of mesh curves of the initial curved surface of the machined curved surface that can be obtained are respectively: z is 0.025x2-0.0125x-0.15;Z=0.1x2-0.025x;
The fitting parametric equations of the first row of mesh curves of the target curved surface of the processed curved surface which can be obtained are respectively as follows: z is 0.075x2-0.025x;Z=0.3x2-0.05x;
The normal vector of each point on the grid curve is obtained by solving the partial derivative of the parameter equation, and as a result, as shown in fig. 3 and 4, the normal vector at the starting point of the grid curve is used as a reference (i.e., the leftmost normal vector in fig. 3 and 4), and the included angle between the normal vector of each point on the grid curve and the reference normal vector can be calculated, so as to obtain the change curve of the included angle of the normal vector of the grid curve. Finally, comparing the normal vector included angle change curves of the initial curved surface and the target curved surface, an initial target angular deformation change curve corresponding to the initial curved surface of the processed outer plate can be obtained, and the result can be shown in fig. 5.
Step 102: and obtaining a primary processing flame path track of the processed outer plate according to the initial target angular deformation change curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, performing primary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to obtain the target angular deformation change curve corresponding to the processed outer plate after the current processing.
It can be understood that the purpose of this step may be to obtain the initial processing flame path track of the processed outer plate by using the maximum angular deformation of the single flame path processing corresponding to the processed outer plate, and ensure that the processed outer plate is not over-processed on the premise that the actual angular deformation generated after each flame path processing is unknown.
Specifically, the step may include the following steps:
step 1021: and acquiring the maximum angular deformation of the single flame channel corresponding to the thickness of the outer plate according to the technological parameters of the line heating.
Step 1022: and connecting points which are on the target angular deformation change curve and are the same integral multiple of the maximum angular deformation to obtain a primary processing flame path track corresponding to the processed outer plate.
Step 1023: according to the track of the primary processing flame path, locally heating the processed outer plate by using a processing device according to preset processing parameters; the processing device keeps preset processing parameters unchanged in the local heating process, and the preset processing parameters comprise gas-oxygen flow, moving speed of a fire gun and distance between a fire gun nozzle and a processed outer plate.
Step 1024: and calculating and obtaining a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
Specifically, in this step, if the thickness of the processed outer plate is 10mm, the maximum angular deformation θ max of the single flame path can be found to be 2.5 ° by querying the process parameter table or the process parameter curve of the line heating. At this time, N points multiplied by θ max, which are 2.5 °, 5 °, 7.5 °, 10 °, 12.5 °, 15 °, 17.5 °, and 20 °, can be found on the curve shown in fig. 5. Then, connecting the points with the same multiple, finding out the flame path track (primary processing flame path track) formed by the corresponding points on the initial curved surface of the processed outer plate during the primary processing of the processed outer plate, and the result can be shown in fig. 6; the processing device is utilized to keep processing parameters (preset processing parameters) such as gas-oxygen flow, moving speed of a flame gun, distance between a flame gun nozzle and a plate unchanged, and the processed outer plate is locally heated (primarily processed) along a flame path track of primary processing; from the target curved surface of the machined outer panel after the current machining (primary machining), the target angular deformation amount change curve corresponding to the machined curved surface after the current machining can be obtained as in step 101.
Step 103: acquiring a learning correction model of the flame path processing position and the actual deformation under preset processing parameters according to the target angular deformation change curves before and after the current processing; when the current processing is the primary processing, the target angular deformation change curve before the current processing is the initial target angular deformation change curve.
It is understood that the present step may specifically include the following steps:
step 1031: and acquiring the angular deformation change curve of the processed outer plate after the current processing according to the target angular deformation change curves before and after the current processing.
Step 1032: and calculating and obtaining the actual angular deformation of each flame path according to the position of the flame path processed at this time and the angular deformation change curve of the processed outer plate processed at this time.
Step 1033: and establishing a learning correction model of the flame path processing position and the actual angular deformation under preset processing parameters according to the actual angular deformation of each flame path at different positions.
Specifically, assuming that a target angular deformation amount change curve corresponding to the machined curved surface after the current machining is shown in fig. 7, it can be known from fig. 5, 6 and 7 that the actual angular deformation amount of each flame path along the X direction sequentially is: 1.47 °, 1.41 °, 1.37 °, 1.35 °, 1.37 °, 1.42 °, 1.48 °. At the moment, a relational expression (learning and correcting model) can be established according to the position of each flame path and the actual angular deformation;
in the formula (I), the compound is shown in the specification,
representing the actual amount of angular deformation, and X represents the X coordinate of the centre point of the flame path.
Step 104: acquiring a secondarily planned flame path track according to the learning correction model and the target angular deformation change curve after the current processing, performing secondary processing on the processed outer plate according to preset processing parameters by using a processing device, and calculating to acquire the target angular deformation change curve after the current processing; and the secondarily planned flame path track consists of points of which the target angular deformation change curve after the current processing is equal to the actual deformation accumulated value.
It is understood that the present step may specifically include the following steps:
step 1041: and determining the point, which is equal to the actual angular deformation accumulated value, of the angular deformation change curve of the target angular deformation change curve processed at this time as a flame path point according to the learning correction model.
In the method for determining the flame path point in this step, starting from the starting point of the target angular deformation amount variation curve, finding a point where the actual angular deformation amount at the corresponding position is equal to the target angular deformation amount, determining the point as a first flame path point, then continuing to search on the target angular deformation amount variation curve, finding a point where the actual angular deformation amount is equal to the sum of the deformation amounts of the first flame path points, determining the point as the flame path point, and then continuing to search until the end of the target angular deformation amount variation curve is found.
Step 1042: and connecting adjacent flame path points to obtain a secondary planned flame path track corresponding to the processed outer plate.
It is understood that, in this step, the ith flame path point of the adjacent target angular deformation amount change curve corresponding to the processed curved surface of the processed outer plate may be connected to obtain a quadratic planned flame path track corresponding to the processed outer plate as shown in fig. 8, where i is less than or equal to a positive integer of the number of flame path points in the target angular deformation amount change curve, a solid line in fig. 8 represents the processed curved surface of the processed outer plate, and a dotted line represents the quadratic planned flame path track.
Step 1043: eliminating the flame path tracks with the adjacent spacing smaller than a second threshold value in the secondarily planned flame path tracks; and the second threshold is the minimum flame path distance corresponding to the process requirement for processing the outer plate.
It can be understood that the specific value setting of the second threshold in this step may be set by a designer according to a practical scenario and a user requirement, for example, the setting may be 15cm, that is, a flame path track with an adjacent distance smaller than 15cm in a secondarily-planned flame path track is eliminated. Since there is no flame path with a distance smaller than 15cm in the secondarily planned flame path corresponding to the processed outer plate of fig. 8, there is no need to correct the flame path shown in fig. 8.
Step 1044: and according to the secondarily planned flame path, locally heating the processed outer plate by using the processing device according to preset processing parameters.
It can be understood that, in the local heating manner in this step, the processing device and the preset processing parameters which are the same as those in the primary processing in step 102 may be adopted to perform the secondary processing on the processed outer panel according to the secondarily planned flame path, and the preset processing parameters in the local heating process are also kept unchanged.
Step 1045: and calculating and obtaining a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
Specifically, the method in step 101 may be referred to obtain a target angular deformation change curve after the current machining.
Step 105: judging whether the maximum value in the target angular deformation change curve after the current processing is smaller than a first threshold value or not; if not, go to step 103.
It is understood that the purpose of this step may be to determine whether the processing of the processed outer panel is completed by determining whether the maximum value in each target angular deformation amount change curve corresponding to the processed curved surface of the processed outer panel after each processing is smaller than a preset first threshold value; if not, the outer plate is not processed, and the step 103 can be executed to perform secondary processing on the outer plate; if so, the outer plate is processed to complete the processing, and the processing of the processed outer plate can be finished.
In the embodiment, on the premise that the angular deformation generated after each flame channel is processed is unknown, the maximum angular deformation of a single flame channel is preset to ensure that the processed outer plate is not over-processed, and the actual angular deformation of the flame channel under the same processing parameters is obtained through self-learning correction, so that the flame channel track during secondary processing can be accurately formulated, the robustness is high, and the flame channel planning under different processing conditions can be adapted.
Referring to fig. 9, fig. 9 is a structural diagram of a self-learning generation device for flame path trajectory of a line heating plate according to an embodiment of the present invention. The apparatus may include:
the calculation module 100 is used for calculating and acquiring an initial target angular deformation change curve corresponding to the processed outer plate; the initial target angular deformation change curve is a normal vector included angle change curve corresponding to grid curves of the same row or the same column of the initial curved surface of the processed outer plate and the target curved surface;
the primary processing module 200 is configured to obtain a primary processing flame path track of the processed outer panel according to the initial target angular deformation variation curve and the maximum angular deformation of the single flame path processing corresponding to the processed outer panel, perform primary processing on the processed outer panel according to preset processing parameters by using the processing device, and calculate and obtain a target angular deformation variation curve after the current processing corresponding to the processed outer panel;
the learning correction module 300 is configured to obtain a learning correction model of the flame path processing position and the actual deformation under the preset processing parameters according to the target angular deformation change curves before and after the current processing; when the current processing is primary processing, the target angular deformation change curve before the current processing is an initial target angular deformation change curve;
a secondary processing module 400, configured to obtain a secondarily planned flame path track according to the learning correction model and the target angular deformation variation curve after the current processing, perform secondary processing on the processed outer panel according to preset processing parameters by using the processing device, and calculate and obtain the target angular deformation variation curve after the current processing; the secondarily planned flame path track consists of points, wherein the target angular deformation change curve after the current processing is equal to the actual deformation accumulated value;
the judging module 500 is configured to judge whether a maximum value in the target angular deformation change curve after the current processing is smaller than a first threshold value; if not, a start signal is sent to the learning correction module 300.
Optionally, the computing module 100 may include:
the gridding reconstruction submodule is used for carrying out gridding reconstruction on the initial curved surface and the target curved surface of the processed outer plate and obtaining a gridding curve formed by grid point data in the same line or the same column in the initial curved surface and the target curved surface;
the fitting submodule is used for carrying out polynomial piecewise fitting on the grid curves to obtain a parameter equation corresponding to each grid curve;
the first calculation submodule is used for solving the partial derivatives of the parameter equation and obtaining the normal vectors of each point on each grid curve;
the second calculation submodule is used for calculating an included angle between the normal vector of each point of each grid curve and the reference normal vector by taking the normal vector at the starting point of each grid curve as a reference, and acquiring a normal vector included angle change curve corresponding to each grid curve;
and the third calculation sub-module is used for acquiring an initial target angular deformation change curve corresponding to the initial curved surface according to the normal vector included angle change curve corresponding to the grid curves of the same row or the same column of the initial curved surface and the target curved surface.
Optionally, the primary processing module 200 may include:
the maximum angular deformation obtaining submodule is used for obtaining the maximum angular deformation of the single flame channel corresponding to the thickness of the outer plate to be processed according to the technological parameters of line heating;
the first flame path track generation submodule is used for connecting points which are on the target angular deformation change curve and are the same integral multiple with the maximum angular deformation to obtain a primary processing flame path track corresponding to the processed outer plate;
the primary processing submodule is used for locally heating the processed outer plate according to preset processing parameters by using the processing device according to the primary processing flame path track; the processing device keeps preset processing parameters unchanged in the local heating process, wherein the preset processing parameters comprise gas-oxygen flow, moving speed of a fire gun and distance between a fire gun nozzle and a processed outer plate;
and the fourth calculation submodule is used for calculating and acquiring a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
Optionally, the learning modification module 300 may include:
the comparison submodule is used for acquiring the angular deformation change curve of the processed outer plate after the current processing according to the target angular deformation change curves before and after the current processing;
the fifth calculation submodule is used for calculating and acquiring the actual angular deformation of each flame path according to the position of the flame path processed at this time and the angular deformation change curve of the processed outer plate processed at this time;
and the learning correction submodule is used for establishing a learning correction model of the flame path processing position and the actual angular deformation under the preset processing parameters according to the actual angular deformation of each flame path at different positions.
Optionally, the secondary processing module 400 may include:
the determining submodule is used for determining a point, which is equal to the accumulated value of the actual angular deformation, of the angular deformation on the target angular deformation change curve after the processing according to the learning correction model as a flame path point;
the second flame path track generation submodule is used for connecting adjacent flame path points to obtain a secondary planned flame path track corresponding to the processed outer plate;
the eliminating submodule is used for eliminating the flame path tracks with the adjacent spacing smaller than a second threshold value in the secondarily planned flame path tracks; the second threshold value is the minimum flame path distance corresponding to the process requirement for processing the outer plate;
the secondary processing submodule is used for locally heating the processed outer plate according to preset processing parameters by using the processing device according to the secondarily planned flame path track;
and the sixth calculation submodule is used for calculating and acquiring a target angular deformation change curve after the current processing according to the processing curved surface and the target curved surface of the processed outer plate after the current processing.
In the embodiment, on the premise that the angular deformation generated after each flame channel is processed is unknown, the maximum angular deformation of a single flame channel is preset to ensure that the processed outer plate is not over-processed, and the actual angular deformation of the flame channel under the same processing parameters is obtained through self-learning correction, so that the flame channel track during secondary processing can be accurately formulated, the robustness is high, and the flame channel planning under different processing conditions can be adapted.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method and the device for generating the flame path track of the line heating plate by self-learning are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.