CN117974719B - Processing tracking and detecting method, system and medium for optical lens - Google Patents
Processing tracking and detecting method, system and medium for optical lens Download PDFInfo
- Publication number
- CN117974719B CN117974719B CN202410365799.8A CN202410365799A CN117974719B CN 117974719 B CN117974719 B CN 117974719B CN 202410365799 A CN202410365799 A CN 202410365799A CN 117974719 B CN117974719 B CN 117974719B
- Authority
- CN
- China
- Prior art keywords
- processing
- optical lens
- model
- time stamp
- preset time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 620
- 230000003287 optical effect Effects 0.000 title claims abstract description 261
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims description 162
- 230000002159 abnormal effect Effects 0.000 claims description 103
- 230000000007 visual effect Effects 0.000 claims description 59
- 238000012423 maintenance Methods 0.000 claims description 55
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 11
- 230000008439 repair process Effects 0.000 claims description 10
- 238000005094 computer simulation Methods 0.000 claims description 9
- 239000002245 particle Substances 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 12
- 230000005856 abnormality Effects 0.000 abstract description 6
- 238000003754 machining Methods 0.000 description 10
- 230000007704 transition Effects 0.000 description 10
- 239000000463 material Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- SBIBMFFZSBJNJF-UHFFFAOYSA-N selenium;zinc Chemical compound [Se]=[Zn] SBIBMFFZSBJNJF-UHFFFAOYSA-N 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003801 milling Methods 0.000 description 3
- 238000005553 drilling Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010892 electric spark Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B3/00—Simple or compound lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Optics & Photonics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a processing tracking and detecting method, a system and a medium of an optical lens, belonging to the technical field of optical lens processing. The invention tracks the processing process of the optical lens by fusing the machine vision and the deep neural network, can evaluate the processing process of the optical lens with a preset time stamp, can timely detect the processing abnormality of the optical lens, avoids the phenomenon of continuous processing caused by the processing abnormality, and can reduce the processing cost of the optical lens.
Description
Technical Field
The present invention relates to the field of optical lens processing technologies, and in particular, to a method, a system, and a medium for tracking and detecting optical lens processing.
Background
The optical lens is used as a device for changing the light path in an optical system, plays an important role in products such as an infrared imaging device, a laser detection device, an electronic device and the like, and is widely applied to the fields of aviation, aerospace, manufacturing, medical treatment and the like. The CVD ZnSe material has excellent optical performance and is a long-wave infrared window and an optical material which are widely applied, but because the CVD ZnSe is a polycrystalline material, the CVD ZnSe material has more internal defects and lower hardness, the processing performance of the CVD ZnSe material is larger than that of the conventional monocrystal Si and monocrystal Ge, the processing technology of the conventional optical lens is still immature, and the problems of poor reliability, unstable product quality, low yield, high cost, difficult control of the production progress and the like of the processing technology exist in the production process, so that the rejection rate of the optical lens is high, and the processing cost is overhigh.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a processing tracking and detecting method, a system and a medium for an optical lens.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the first aspect of the present invention provides a method for tracking and detecting the processing of an optical lens, comprising the steps of:
Acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
Constructing a processing tracking model based on a processing model diagram of a preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
Constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into a processing tracking model for identification, and acquiring an abnormal processing area of the optical lens;
And evaluating the abnormal processing area of the optical lens, acquiring a maintenance success priori probability value of the abnormal processing area of the current optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens.
Further, in the method, processing drawing information of the optical lens is obtained, a processing path diagram of the optical lens is generated according to the processing drawing information of the optical lens, and a processing model diagram of a preset time stamp is obtained based on the processing path diagram of the optical lens, specifically including:
Acquiring processing drawing information of an optical lens, introducing an ant colony algorithm, initializing a processing starting point position, and carrying out path planning according to the processing drawing information and the processing starting point position of the optical lens to acquire an initial processing path diagram of the optical lens;
calculating a processing path mileage value of an initial processing path diagram of the optical lens, presetting a processing path mileage threshold, and re-planning the processing path diagram through an ant colony algorithm when the processing path mileage value of the initial processing path diagram of the optical lens is larger than the processing path mileage threshold;
Outputting a current processing path diagram when the processing path mileage value of the initial processing path diagram of the optical lens is not more than the processing path mileage threshold value, and taking the current processing path diagram as the processing path diagram of the optical lens;
the processing path diagram of the optical lens is dynamically simulated, a processing path dynamic simulation diagram of the optical lens is obtained, a processing model diagram of a preset time stamp is obtained from the processing path dynamic simulation diagram of the optical lens, and the processing model diagram of the preset time stamp is output.
Further, in the method, a processing tracking model is constructed based on a processing model diagram of a preset timestamp, and the method specifically comprises the following steps:
Extracting features of the processing model diagrams with preset time stamps through a feature pyramid network, obtaining multi-scale features of each processing model diagram, continuously sampling the multi-scale features of the processing model diagrams through a bilinear interpolation function, and generating target tracking features of the processing model diagrams;
Constructing a processing tracking model based on a deep neural network, introducing a SURF algorithm, correcting target tracking features of a processing model diagram through the SURF algorithm, acquiring corrected multi-scale features, and constructing a feature matrix according to the corrected multi-scale features;
Initializing the sequence of the corrected multi-scale features in the feature matrix, obtaining a sequence result, introducing a greedy algorithm, performing sequence reconstruction on the sequence result through the greedy algorithm to obtain a depth feature matrix, inputting the depth feature matrix into a processing tracking model for code learning, and presetting a model parameter threshold range;
and when the model parameters of the processing tracking model are within the threshold range of the model parameters, saving the model parameters of the processing tracking model, and outputting the processing tracking model.
Further, in the method, a visual acquisition network of the processing equipment is constructed, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing equipment, specifically comprising:
Acquiring actual working range information of the processing equipment, and initially calculating the number of a plurality of visual acquisition equipment and the arrangement positions on the processing equipment, and calculating the actual working range information of the visual acquisition equipment according to the number of the visual acquisition equipment and the arrangement positions on the processing equipment;
introducing a particle swarm algorithm, setting iteration algebra according to the particle swarm algorithm, and judging whether the actual working range information of the visual acquisition equipment is larger than the actual working range information of the processing equipment;
When the actual working range information of the visual acquisition equipment is not more than the actual working range information of the processing equipment, adjusting the number of the visual acquisition equipment and the layout positions on the processing equipment according to iteration algebra until the actual working range information of the visual acquisition equipment is more than the actual working range information of the processing equipment;
If the number of the visual acquisition devices and the layout positions on the processing devices are larger than the number, a visual acquisition network of the processing devices is constructed according to the number of the visual acquisition devices and the layout positions on the processing devices, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing devices.
Further, in the method, a processing model diagram of a preset time stamp is constructed according to processing image information of the preset time stamp, and the processing model diagram of the preset time stamp is input into a processing tracking model for identification, so that an abnormal processing area of the optical lens is obtained, and the method specifically comprises the following steps:
the processing image information of the preset time stamp is obtained through filtering and denoising processing on the processing image information of the preset time stamp, and a processing model diagram of the preset time stamp is built through three-dimensional modeling software according to the processing image information of the preset time stamp;
Inputting a processing model diagram of a preset time stamp into a processing tracking model for identification, acquiring the similarity of each processing element area in the processing model of the preset time stamp, and judging whether the similarity is larger than the preset similarity;
When the similarity is larger than the preset similarity, the corresponding processing element area is taken as a normal processing element area, and when the similarity is not larger than the preset similarity, the corresponding processing element area is taken as an abnormal processing element area;
An abnormal processing region of the optical lens is generated from the abnormal processing element region, and the abnormal processing region of the optical lens is output.
Further, in the method, by evaluating the abnormal processing area of the optical lens, a maintenance success priori probability value of the abnormal processing area of the current optical lens is obtained, and a related processing strategy is generated according to the maintenance success priori probability value of the abnormal processing area of the current optical lens, which specifically comprises:
Acquiring a historical abnormal processing area of the optical lens, introducing a Bayesian network, taking the historical abnormal processing area of the optical lens as a first independent event, acquiring historical repair data of the abnormal processing area of the optical lens, and taking the historical repair data of the abnormal processing area of the optical lens as a second independent event;
Inputting the first independent event and the second independent event into a Bayesian network to estimate a maintenance success priori probability value, and acquiring a maintenance success priori probability value corresponding to a historical abnormal processing area of the optical lens;
generating a maintenance success priori probability value of the abnormal processing area of the current optical lens according to the maintenance success priori probability value corresponding to the historical abnormal processing area of the optical lens and the abnormal processing area of the optical lens;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is larger than a preset maintenance success priori probability threshold value, the current optical lens is used as a repairable processing part;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is not greater than the preset maintenance success priori probability threshold, the current optical lens is used as an unrepairable processing part, and the unrepairable processing part is scrapped.
The second aspect of the present invention provides a system for tracking and detecting the processing of an optical lens, the system for tracking and detecting the processing of an optical lens comprising a memory and a processor, wherein the memory comprises a program for tracking and detecting the processing of an optical lens, and when the program for tracking and detecting the processing of an optical lens is executed by the processor, the following steps are realized:
Acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
Constructing a processing tracking model based on a processing model diagram of a preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
Constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into a processing tracking model for identification, and acquiring an abnormal processing area of the optical lens;
And evaluating the abnormal processing area of the optical lens, acquiring a maintenance success priori probability value of the abnormal processing area of the current optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens.
A third aspect of the present invention provides a computer-readable storage medium containing therein a processing tracking and detecting method program for an optical lens, which when executed by a processor, implements the steps of the processing tracking and detecting method for an optical lens of any one of the above.
The invention solves the defects existing in the background technology, and has the following beneficial effects:
According to the method, processing drawing information of the optical lens is obtained, a processing path diagram of the optical lens is generated according to the processing drawing information of the optical lens, a processing model diagram of a preset time stamp is obtained based on the processing path diagram of the optical lens, a processing tracking model is built based on the processing model diagram of the preset time stamp, a vision acquisition network of processing equipment is built, processing image information of the preset time stamp is obtained through the vision acquisition network of the processing equipment, the processing model diagram of the preset time stamp is built according to the processing image information of the preset time stamp, the processing model diagram of the preset time stamp is input into the processing tracking model for identification, an abnormal processing area of the optical lens is obtained, finally, a maintenance success priori probability value of the abnormal processing area of the current optical lens is obtained through evaluation of the abnormal processing area of the optical lens, and a relevant processing strategy is generated according to the maintenance success priori probability value of the abnormal processing area of the current optical lens. The invention tracks the processing process of the optical lens by fusing the machine vision and the deep neural network, can evaluate the processing process of the optical lens with a preset time stamp, can timely detect the processing abnormality of the optical lens, avoids the phenomenon of continuous processing caused by the processing abnormality, and can reduce the processing cost of the optical lens.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows an overall method flow diagram of a method of processing tracking and inspection of an optical lens;
FIG. 2 shows a first method flow diagram of a method of processing tracking and inspection of an optical lens;
FIG. 3 shows a second method flow diagram of a method of processing tracking and inspection of an optical lens;
Fig. 4 shows a system block diagram of an optical lens process tracking and inspection system.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, a first aspect of the present invention provides a method for tracking and detecting processing of an optical lens, including the following steps:
S102, acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
S104, constructing a processing tracking model based on a processing model diagram of a preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
S106, constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into a processing tracking model for identification, and acquiring an abnormal processing area of the optical lens;
S108, through evaluating the abnormal processing area of the optical lens, acquiring a maintenance success priori probability value of the abnormal processing area of the current optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens.
The invention can track the processing process of the optical lens by fusing the machine vision and the deep neural network, evaluate the processing process of the optical lens with a preset time stamp, timely detect the processing abnormality of the optical lens, avoid the phenomenon of continuous processing caused by the processing abnormality and reduce the processing cost of the optical lens.
As shown in fig. 2, further, in the method, processing drawing information of the optical lens is obtained, and a processing path diagram of the optical lens is generated according to the processing drawing information of the optical lens, and a processing model diagram of a preset timestamp is obtained based on the processing path diagram of the optical lens, specifically including:
s202, acquiring processing drawing information of an optical lens, introducing an ant colony algorithm, initializing a processing starting point position, and carrying out path planning according to the processing drawing information and the processing starting point position of the optical lens to acquire an initial processing path diagram of the optical lens;
s204, calculating a processing path mileage value of an initial processing path diagram of the optical lens, presetting a processing path mileage threshold, and re-planning the processing path diagram through an ant colony algorithm when the processing path mileage value of the initial processing path diagram of the optical lens is larger than the processing path mileage threshold;
S206, outputting a current processing path diagram and taking the current processing path diagram as the processing path diagram of the optical lens when the processing path mileage value of the initial processing path diagram of the optical lens is not more than the processing path mileage threshold value;
S208, dynamically simulating the processing path diagram of the optical lens to obtain a dynamic simulation diagram of the processing path of the optical lens, obtaining a processing model diagram of a preset time stamp from the dynamic simulation diagram of the processing path of the optical lens, and outputting the processing model diagram of the preset time stamp.
It should be noted that, the processing path diagram of the optical lens is dynamically simulated by the three-dimensional modeling software, such as UG and mastercam software, so as to obtain a processing model diagram with a preset time stamp, in fact, the processing path dynamic simulation diagram of the optical lens is actually composed of a plurality of processing model diagrams with time stamps, so as to obtain the processing model diagram with the preset time stamp, and therefore, the processing model diagram with the preset time stamp is learned by the processing tracking model, and the tracking of the processing process is completed.
As shown in fig. 3, in the method, further, a process tracking model is constructed based on a process model diagram with preset time stamps, which specifically includes:
S302, extracting features of a processing model diagram with a preset time stamp through a feature pyramid network, obtaining multi-scale features of each processing model diagram, continuously sampling the multi-scale features of the processing model diagram through a bilinear interpolation function, and generating target tracking features of the processing model diagram;
S304, constructing a processing tracking model based on a deep neural network, introducing a SURF algorithm, correcting target tracking features of a processing model diagram through the SURF algorithm, acquiring corrected multi-scale features, and constructing a feature matrix according to the corrected multi-scale features;
S306, initializing the sequence of the corrected multi-scale features in the feature matrix, obtaining a sequence result, introducing a greedy algorithm, performing sequence reconstruction on the sequence result through the greedy algorithm to obtain a depth feature matrix, inputting the depth feature matrix into a processing tracking model for coding learning, and presetting a model parameter threshold range;
And S308, when the model parameters of the processing tracking model are within the threshold range of the model parameters, saving the model parameters of the processing tracking model, and outputting the processing tracking model.
Because most of the machining processes are rapid movements, cutting, drilling, milling and other procedures are completed, the SURF algorithm is utilized to correct target tracking features of the machining model diagram, corrected multi-scale features are obtained, and therefore tracking accuracy of optical lens machining is improved. Greedy algorithm (also known as greedy algorithm) means that when solving a problem, the choice that is currently seen to be best is always made. That is, not considered in terms of overall optimality, he only made a locally optimal solution in a sense. Greedy algorithms do not yield an overall optimal solution for all problems, but rather a broad range of problems can yield an overall optimal solution or an approximation of an overall optimal solution. The method is integrated with a greedy algorithm to reconstruct the sorting results in order, so that the robustness of a processing tracking model in the learning process is improved, and the tracking precision of an optical lens is improved. SURF (Speeded Up Robust Features) is an improvement to SIFT, SURF does not use downsampling, and corrects for the target tracking features of the process model map by keeping the image size unchanged, but changing the box filter size to construct a scale pyramid.
Further, in the method, a visual acquisition network of the processing equipment is constructed, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing equipment, specifically comprising:
Acquiring actual working range information of the processing equipment, and initially calculating the number of a plurality of visual acquisition equipment and the arrangement positions on the processing equipment, and calculating the actual working range information of the visual acquisition equipment according to the number of the visual acquisition equipment and the arrangement positions on the processing equipment;
introducing a particle swarm algorithm, setting iteration algebra according to the particle swarm algorithm, and judging whether the actual working range information of the visual acquisition equipment is larger than the actual working range information of the processing equipment;
When the actual working range information of the visual acquisition equipment is not more than the actual working range information of the processing equipment, adjusting the number of the visual acquisition equipment and the layout positions on the processing equipment according to iteration algebra until the actual working range information of the visual acquisition equipment is more than the actual working range information of the processing equipment;
If the number of the visual acquisition devices and the layout positions on the processing devices are larger than the number, a visual acquisition network of the processing devices is constructed according to the number of the visual acquisition devices and the layout positions on the processing devices, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing devices.
It should be noted that, the processing equipment includes milling machine, grinding machine, laser processing equipment, electric spark processing equipment, etc., and each processing equipment has certain travel limit position (i.e. actual working range information) in three-dimensional space, so that the method can enable the vision acquisition network of the processing equipment to include the actual working range information, does not miss any monitoring position, and improves the processing tracking rationality of the optical lens.
Further, in the method, a processing model diagram of a preset time stamp is constructed according to processing image information of the preset time stamp, and the processing model diagram of the preset time stamp is input into a processing tracking model for identification, so that an abnormal processing area of the optical lens is obtained, and the method specifically comprises the following steps:
the processing image information of the preset time stamp is obtained through filtering and denoising processing on the processing image information of the preset time stamp, and a processing model diagram of the preset time stamp is built through three-dimensional modeling software according to the processing image information of the preset time stamp;
Inputting a processing model diagram of a preset time stamp into a processing tracking model for identification, acquiring the similarity of each processing element area in the processing model of the preset time stamp, and judging whether the similarity is larger than the preset similarity;
When the similarity is larger than the preset similarity, the corresponding processing element area is taken as a normal processing element area, and when the similarity is not larger than the preset similarity, the corresponding processing element area is taken as an abnormal processing element area;
An abnormal processing region of the optical lens is generated from the abnormal processing element region, and the abnormal processing region of the optical lens is output.
When the processing model diagram of a certain time stamp does not meet the requirement, the situation that the similarity is not greater than the preset similarity occurs, and the abnormal processing area of the optical lens can be detected through the method. The machining elements comprise contour machining, drilling, milling and intersecting machining, polishing machining and the like.
Further, in the method, by evaluating the abnormal processing area of the optical lens, a maintenance success priori probability value of the abnormal processing area of the current optical lens is obtained, and a related processing strategy is generated according to the maintenance success priori probability value of the abnormal processing area of the current optical lens, which specifically comprises:
Acquiring a historical abnormal processing area of the optical lens, introducing a Bayesian network, taking the historical abnormal processing area of the optical lens as a first independent event, acquiring historical repair data of the abnormal processing area of the optical lens, and taking the historical repair data of the abnormal processing area of the optical lens as a second independent event;
Inputting the first independent event and the second independent event into a Bayesian network to estimate a maintenance success priori probability value, and acquiring a maintenance success priori probability value corresponding to a historical abnormal processing area of the optical lens;
generating a maintenance success priori probability value of the abnormal processing area of the current optical lens according to the maintenance success priori probability value corresponding to the historical abnormal processing area of the optical lens and the abnormal processing area of the optical lens;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is larger than a preset maintenance success priori probability threshold value, the current optical lens is used as a repairable processing part;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is not greater than the preset maintenance success priori probability threshold, the current optical lens is used as an unrepairable processing part, and the unrepairable processing part is scrapped.
It should be noted that, the historical repair data of the abnormal processing area of the optical lens includes the number data of optical lenses which are successfully repaired and the number data of optical lenses which are failed to repair, and the maintenance success priori probability value corresponding to the historical abnormal processing area of the optical lens can be estimated through the bayesian network.
In addition, the method can further comprise the following steps:
Acquiring motion precision characteristic data information of the processing equipment in all directions through big data, and acquiring motion precision membership degrees of the processing equipment in all directions through fuzzy evaluation of the motion precision characteristic data information of the processing equipment in all directions;
introducing a Markov chain, calculating a transition probability value of the motion precision membership degree of the processing equipment in each direction to the motion precision membership degree of the next level through the Markov chain, and constructing a motion precision transition probability prediction model of the processing equipment based on a deep neural network;
Constructing a state transition probability matrix according to the transition probability value, inputting the state transition probability matrix into the motion precision transition probability prediction model of the processing equipment for coding learning, and obtaining the motion precision transition probability prediction model of the processing equipment after training;
Obtaining the motion precision membership degree of the processing equipment in each direction within a preset time, inputting the motion precision membership degree of the processing equipment in each direction within the preset time into the trained motion precision transition probability prediction model of the processing equipment for prediction, and obtaining a transition probability value of transition from the motion precision membership degree of the processing equipment in each direction to the motion precision membership degree of the next level;
When the transfer probability value of the motion precision membership of the processing equipment in each direction to the next level of motion precision membership is larger than a preset probability value, the next level of motion precision membership of the processing equipment in each direction is used as the motion precision membership of the current processing equipment in each direction.
It should be noted that, due to the use of the servo motor, the motion precision of the servo motor is reduced, and the motion precision membership degree includes a high motion precision membership degree, a medium motion precision membership degree and a low motion precision membership degree. The prediction accuracy of the motion accuracy membership degree of the processing equipment in all directions can be further improved through the fusion Markov chain and the deep neural network. The motion precision characteristic data information of the processing equipment in all directions can be subjected to fuzzy evaluation through a fuzzy clustering algorithm, a decision tree algorithm and the like.
In addition, the method can further comprise the following steps:
judging whether the motion precision membership degree is smaller than a preset motion precision membership degree, calculating a motion deviation value of a servo system, acquiring processing deviation requirement data information of an optical lens, and judging whether the motion deviation value of the servo system is smaller than the processing deviation requirement data information of the optical lens;
When the motion deviation value of the servo system is smaller than the machining deviation requirement data information of the optical lens, sending out a continuous machining instruction, and monitoring whether the motion deviation value of the servo system is smaller than the machining deviation requirement data information of the optical lens or not at all times;
When the motion deviation value of the servo system is not smaller than the processing deviation requirement data information of the optical lens, sending out a processing stopping instruction, and obtaining processing equipment corresponding to the processing deviation requirement data information of the optical lens, wherein the motion deviation value of the servo system is smaller than the processing deviation requirement data information of the optical lens at present;
And taking the processing equipment corresponding to the processing deviation requirement data information of which the current motion deviation value of the servo system is smaller than that of the optical lens as the processing equipment of the current optical lens.
The data information of the processing deviation requirement of the optical lens is the processing requirement of the optical lens, such as the roughness deviation requirement and the profile deviation requirement. The method can further formulate more reasonable processing plan according to the motion deviation value of the servo system, and reduce the generation of optical lens waste products.
As shown in fig. 4, the second aspect of the present invention provides an optical lens processing tracking and detecting system 4, where the optical lens processing tracking and detecting system 4 includes a memory 41 and a processor 42, and the memory 41 includes a processing tracking and detecting method program of the optical lens, and when the processing tracking and detecting method program of the optical lens is executed by the processor 42, the following steps are implemented:
Acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
Constructing a processing tracking model based on a processing model diagram of a preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
Constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into a processing tracking model for identification, and acquiring an abnormal processing area of the optical lens;
And evaluating the abnormal processing area of the optical lens, acquiring a maintenance success priori probability value of the abnormal processing area of the current optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens.
Further, in the system, processing drawing information of the optical lens is obtained, a processing path diagram of the optical lens is generated according to the processing drawing information of the optical lens, and a processing model diagram of a preset time stamp is obtained based on the processing path diagram of the optical lens, specifically including:
Acquiring processing drawing information of an optical lens, introducing an ant colony algorithm, initializing a processing starting point position, and carrying out path planning according to the processing drawing information and the processing starting point position of the optical lens to acquire an initial processing path diagram of the optical lens;
calculating a processing path mileage value of an initial processing path diagram of the optical lens, presetting a processing path mileage threshold, and re-planning the processing path diagram through an ant colony algorithm when the processing path mileage value of the initial processing path diagram of the optical lens is larger than the processing path mileage threshold;
Outputting a current processing path diagram when the processing path mileage value of the initial processing path diagram of the optical lens is not more than the processing path mileage threshold value, and taking the current processing path diagram as the processing path diagram of the optical lens;
the processing path diagram of the optical lens is dynamically simulated, a processing path dynamic simulation diagram of the optical lens is obtained, a processing model diagram of a preset time stamp is obtained from the processing path dynamic simulation diagram of the optical lens, and the processing model diagram of the preset time stamp is output.
Further, in the system, a processing tracking model is constructed based on a processing model diagram of a preset time stamp, which specifically includes:
Extracting features of the processing model diagrams with preset time stamps through a feature pyramid network, obtaining multi-scale features of each processing model diagram, continuously sampling the multi-scale features of the processing model diagrams through a bilinear interpolation function, and generating target tracking features of the processing model diagrams;
Constructing a processing tracking model based on a deep neural network, introducing a SURF algorithm, correcting target tracking features of a processing model diagram through the SURF algorithm, acquiring corrected multi-scale features, and constructing a feature matrix according to the corrected multi-scale features;
Initializing the sequence of the corrected multi-scale features in the feature matrix, obtaining a sequence result, introducing a greedy algorithm, performing sequence reconstruction on the sequence result through the greedy algorithm to obtain a depth feature matrix, inputting the depth feature matrix into a processing tracking model for code learning, and presetting a model parameter threshold range;
and when the model parameters of the processing tracking model are within the threshold range of the model parameters, saving the model parameters of the processing tracking model, and outputting the processing tracking model.
Further, in the system, a visual acquisition network of the processing equipment is constructed, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing equipment, which specifically comprises:
Acquiring actual working range information of the processing equipment, and initially calculating the number of a plurality of visual acquisition equipment and the arrangement positions on the processing equipment, and calculating the actual working range information of the visual acquisition equipment according to the number of the visual acquisition equipment and the arrangement positions on the processing equipment;
introducing a particle swarm algorithm, setting iteration algebra according to the particle swarm algorithm, and judging whether the actual working range information of the visual acquisition equipment is larger than the actual working range information of the processing equipment;
When the actual working range information of the visual acquisition equipment is not more than the actual working range information of the processing equipment, adjusting the number of the visual acquisition equipment and the layout positions on the processing equipment according to iteration algebra until the actual working range information of the visual acquisition equipment is more than the actual working range information of the processing equipment;
If the number of the visual acquisition devices and the layout positions on the processing devices are larger than the number, a visual acquisition network of the processing devices is constructed according to the number of the visual acquisition devices and the layout positions on the processing devices, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing devices.
Further, in the system, a processing model diagram of a preset time stamp is constructed according to processing image information of the preset time stamp, and the processing model diagram of the preset time stamp is input into a processing tracking model for identification, so that an abnormal processing area of the optical lens is obtained, and the system specifically comprises:
the processing image information of the preset time stamp is obtained through filtering and denoising processing on the processing image information of the preset time stamp, and a processing model diagram of the preset time stamp is built through three-dimensional modeling software according to the processing image information of the preset time stamp;
Inputting a processing model diagram of a preset time stamp into a processing tracking model for identification, acquiring the similarity of each processing element area in the processing model of the preset time stamp, and judging whether the similarity is larger than the preset similarity;
When the similarity is larger than the preset similarity, the corresponding processing element area is taken as a normal processing element area, and when the similarity is not larger than the preset similarity, the corresponding processing element area is taken as an abnormal processing element area;
An abnormal processing region of the optical lens is generated from the abnormal processing element region, and the abnormal processing region of the optical lens is output.
Further, in the system, by evaluating the abnormal processing area of the optical lens, a maintenance success priori probability value of the abnormal processing area of the current optical lens is obtained, and a related processing strategy is generated according to the maintenance success priori probability value of the abnormal processing area of the current optical lens, which specifically comprises:
Acquiring a historical abnormal processing area of the optical lens, introducing a Bayesian network, taking the historical abnormal processing area of the optical lens as a first independent event, acquiring historical repair data of the abnormal processing area of the optical lens, and taking the historical repair data of the abnormal processing area of the optical lens as a second independent event;
Inputting the first independent event and the second independent event into a Bayesian network to estimate a maintenance success priori probability value, and acquiring a maintenance success priori probability value corresponding to a historical abnormal processing area of the optical lens;
generating a maintenance success priori probability value of the abnormal processing area of the current optical lens according to the maintenance success priori probability value corresponding to the historical abnormal processing area of the optical lens and the abnormal processing area of the optical lens;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is larger than a preset maintenance success priori probability threshold value, the current optical lens is used as a repairable processing part;
When the maintenance success priori probability value of the abnormal processing area of the current optical lens is not greater than the preset maintenance success priori probability threshold, the current optical lens is used as an unrepairable processing part, and the unrepairable processing part is scrapped.
A third aspect of the present invention provides a computer-readable storage medium containing therein a processing tracking and detecting method program for an optical lens, which when executed by a processor, implements the steps of the processing tracking and detecting method for an optical lens of any one of the above.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The processing tracking and detecting method of the optical lens is characterized by comprising the following steps of:
Acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
constructing a processing tracking model based on the processing model diagram of the preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
Constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into the processing tracking model for identification, and obtaining an abnormal processing area of the optical lens;
the method comprises the steps of obtaining a maintenance success priori probability value of an abnormal processing area of a current optical lens by evaluating the abnormal processing area of the optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens;
constructing a processing tracking model based on the processing model diagram of the preset time stamp, specifically comprising:
extracting features of the processing model diagrams of the preset time stamp through a feature pyramid network, obtaining multi-scale features of each processing model diagram, continuously sampling the multi-scale features of the processing model diagrams through a bilinear interpolation function, and generating target tracking features of the processing model diagrams;
constructing a processing tracking model based on a deep neural network, introducing a SURF algorithm, correcting target tracking features of the processing model graph through the SURF algorithm, acquiring corrected multi-scale features, and constructing a feature matrix according to the corrected multi-scale features;
Initializing the sequence of the corrected multi-scale features in the feature matrix, obtaining a sequence result, introducing a greedy algorithm, performing sequence reconstruction on the sequence result through the greedy algorithm to obtain a depth feature matrix, inputting the depth feature matrix into the processing tracking model for coding learning, and presetting a model parameter threshold range;
and when the model parameters of the processing tracking model are within the model parameter threshold range, saving the model parameters of the processing tracking model, and outputting the processing tracking model.
2. The method for tracking and detecting the processing of an optical lens according to claim 1, wherein the method comprises the steps of obtaining processing drawing information of the optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and obtaining a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens, and specifically comprises the following steps:
Acquiring processing drawing information of an optical lens, introducing an ant colony algorithm, initializing a processing starting point position, and carrying out path planning according to the processing drawing information and the processing starting point position of the optical lens to acquire an initial processing path diagram of the optical lens;
Calculating a processing path mileage value of an initial processing path diagram of the optical lens, presetting a processing path mileage threshold, and re-planning the processing path diagram through the ant colony algorithm when the processing path mileage value of the initial processing path diagram of the optical lens is larger than the processing path mileage threshold;
Outputting a current processing path diagram when the processing path mileage value of the initial processing path diagram of the optical lens is not more than the processing path mileage threshold value, and taking the current processing path diagram as the processing path diagram of the optical lens;
and dynamically simulating the processing path diagram of the optical lens to obtain a processing path dynamic simulation diagram of the optical lens, obtaining a processing model diagram of a preset time stamp from the processing path dynamic simulation diagram of the optical lens, and outputting the processing model diagram of the preset time stamp.
3. The method for tracking and detecting the processing of the optical lens according to claim 1, wherein a vision acquisition network of processing equipment is constructed, and processing image information of a preset time stamp is acquired through the vision acquisition network of the processing equipment, specifically comprising:
Acquiring actual working range information of processing equipment, and initially calculating the number of a plurality of visual acquisition equipment and the arrangement positions on the processing equipment, and calculating the actual working range information of the visual acquisition equipment according to the number of the visual acquisition equipment and the arrangement positions on the processing equipment;
Introducing a particle swarm algorithm, setting iteration algebra according to the particle swarm algorithm, and judging whether the actual working range information of the visual acquisition equipment is larger than the actual working range information of the processing equipment;
When the actual working range information of the vision acquisition equipment is not more than the actual working range information of the processing equipment, adjusting the number of the vision acquisition equipment and the layout positions on the processing equipment according to the iteration algebra until the actual working range information of the vision acquisition equipment is more than the actual working range information of the processing equipment;
If the number of the visual acquisition devices and the layout positions on the processing devices are larger than the number, a visual acquisition network of the processing devices is constructed according to the number of the visual acquisition devices and the layout positions on the processing devices, and processing image information of a preset time stamp is acquired through the visual acquisition network of the processing devices.
4. The method for tracking and detecting the processing of the optical lens according to claim 1, wherein a processing model diagram of a preset time stamp is constructed according to the processing image information of the preset time stamp, and the processing model diagram of the preset time stamp is input into the processing tracking model for identification, so as to obtain an abnormal processing area of the optical lens, and the method specifically comprises the following steps:
The processing image information of the preset time stamp is obtained through filtering and denoising processing on the processing image information of the preset time stamp, and a processing model diagram of the preset time stamp is constructed through three-dimensional modeling software according to the processing image information of the preset time stamp;
Inputting the processing model diagram of the preset timestamp into the processing tracking model for identification, obtaining the similarity of each processing element area in the processing model of the preset timestamp, and judging whether the similarity is larger than the preset similarity;
when the similarity is larger than the preset similarity, the corresponding processing element area is taken as a normal processing element area, and when the similarity is not larger than the preset similarity, the corresponding processing element area is taken as an abnormal processing element area;
and generating an abnormal processing area of the optical lens according to the abnormal processing element area, and outputting the abnormal processing area of the optical lens.
5. The method for tracking and detecting the processing of an optical lens according to claim 1, wherein the method for acquiring the maintenance success priori probability value of the abnormal processing area of the current optical lens by evaluating the abnormal processing area of the optical lens and generating the related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens specifically comprises:
Acquiring a historical abnormal processing area of an optical lens, introducing a Bayesian network, taking the historical abnormal processing area of the optical lens as a first independent event, acquiring historical repair data of the abnormal processing area of the optical lens, and taking the historical repair data of the abnormal processing area of the optical lens as a second independent event;
Inputting the first independent event and the second independent event into the Bayesian network to estimate a maintenance success priori probability value, and acquiring a maintenance success priori probability value corresponding to a historical abnormal processing area of the optical lens;
Generating a maintenance success priori probability value of the abnormal processing area of the current optical lens according to the maintenance success priori probability value corresponding to the historical abnormal processing area of the optical lens and the abnormal processing area of the optical lens;
when the maintenance success priori probability value of the abnormal processing area of the current optical lens is larger than a preset maintenance success priori probability threshold value, taking the current optical lens as a repairable processing part;
And when the maintenance success priori probability value of the abnormal processing area of the current optical lens is not greater than a preset maintenance success priori probability threshold value, taking the current optical lens as an unrepairable processing part, and scrapping the unrepairable processing part.
6. The system for tracking and detecting the processing of the optical lens is characterized by comprising a memory and a processor, wherein the memory comprises a processing tracking and detecting method program of the optical lens, and the processing tracking and detecting method program of the optical lens is executed by the processor and realizes the following steps:
Acquiring processing drawing information of an optical lens, generating a processing path diagram of the optical lens according to the processing drawing information of the optical lens, and acquiring a processing model diagram of a preset time stamp based on the processing path diagram of the optical lens;
constructing a processing tracking model based on the processing model diagram of the preset time stamp, constructing a visual acquisition network of processing equipment, and acquiring processing image information of the preset time stamp through the visual acquisition network of the processing equipment;
Constructing a processing model diagram of a preset time stamp according to the processing image information of the preset time stamp, inputting the processing model diagram of the preset time stamp into the processing tracking model for identification, and obtaining an abnormal processing area of the optical lens;
the method comprises the steps of obtaining a maintenance success priori probability value of an abnormal processing area of a current optical lens by evaluating the abnormal processing area of the optical lens, and generating a related processing strategy according to the maintenance success priori probability value of the abnormal processing area of the current optical lens;
constructing a processing tracking model based on the processing model diagram of the preset time stamp, specifically comprising:
extracting features of the processing model diagrams of the preset time stamp through a feature pyramid network, obtaining multi-scale features of each processing model diagram, continuously sampling the multi-scale features of the processing model diagrams through a bilinear interpolation function, and generating target tracking features of the processing model diagrams;
constructing a processing tracking model based on a deep neural network, introducing a SURF algorithm, correcting target tracking features of the processing model graph through the SURF algorithm, acquiring corrected multi-scale features, and constructing a feature matrix according to the corrected multi-scale features;
Initializing the sequence of the corrected multi-scale features in the feature matrix, obtaining a sequence result, introducing a greedy algorithm, performing sequence reconstruction on the sequence result through the greedy algorithm to obtain a depth feature matrix, inputting the depth feature matrix into the processing tracking model for coding learning, and presetting a model parameter threshold range;
and when the model parameters of the processing tracking model are within the model parameter threshold range, saving the model parameters of the processing tracking model, and outputting the processing tracking model.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a processing tracking and detecting method program of an optical lens, which, when executed by a processor, implements the steps of the processing tracking and detecting method of an optical lens according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410365799.8A CN117974719B (en) | 2024-03-28 | 2024-03-28 | Processing tracking and detecting method, system and medium for optical lens |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410365799.8A CN117974719B (en) | 2024-03-28 | 2024-03-28 | Processing tracking and detecting method, system and medium for optical lens |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117974719A CN117974719A (en) | 2024-05-03 |
| CN117974719B true CN117974719B (en) | 2024-07-19 |
Family
ID=90857934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410365799.8A Active CN117974719B (en) | 2024-03-28 | 2024-03-28 | Processing tracking and detecting method, system and medium for optical lens |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117974719B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110682185A (en) * | 2019-09-09 | 2020-01-14 | 中国科学院上海光学精密机械研究所 | Processing method of high-precision exposure lens |
| CN112106182A (en) * | 2018-03-20 | 2020-12-18 | 东京毅力科创株式会社 | Self-sensing corrective heterogeneous platform incorporating integrated semiconductor processing modules and methods of use thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652940B (en) * | 2020-04-30 | 2024-06-04 | 平安国际智慧城市科技股份有限公司 | Target abnormality recognition method, target abnormality recognition device, electronic equipment and storage medium |
| CN115988866B (en) * | 2023-03-21 | 2023-06-20 | 深圳市利和兴股份有限公司 | NFC LAMI processing control method and system based on machine vision |
| CN117103266A (en) * | 2023-09-06 | 2023-11-24 | 北京神工科技有限公司 | Aircraft skin feature recognition and edge milling path planning method based on semantic segmentation |
-
2024
- 2024-03-28 CN CN202410365799.8A patent/CN117974719B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112106182A (en) * | 2018-03-20 | 2020-12-18 | 东京毅力科创株式会社 | Self-sensing corrective heterogeneous platform incorporating integrated semiconductor processing modules and methods of use thereof |
| CN110682185A (en) * | 2019-09-09 | 2020-01-14 | 中国科学院上海光学精密机械研究所 | Processing method of high-precision exposure lens |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117974719A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pereira et al. | Advancing autonomous surface vehicles: A 3D perception system for the recognition and assessment of docking-based structures | |
| CN113601306B (en) | Charging facility box body weld joint polishing method based on one-dimensional segmentation network | |
| CN117312879B (en) | Injection molding machine production data supervision and early warning method, system and medium | |
| CN113920053A (en) | Defect detection method based on deep learning, computing device and storage medium | |
| CN116758539B (en) | Embryo image blastomere identification method based on data enhancement | |
| CN117309891B (en) | Intelligent feedback mechanism-based glass tempering film detection method and system | |
| CN116618764A (en) | Production optimization method and system of mirror surface electric discharge machine | |
| Giusti et al. | Image-based measurement of material roughness using machine learning techniques | |
| Meng et al. | Physical knowledge-enhanced deep neural network for sea surface temperature prediction | |
| Hall et al. | ConvLSTM deep learning signal prediction for forecasting bending moment for tool condition monitoring | |
| CN115578574A (en) | Three-dimensional point cloud completion method based on deep learning and topology perception | |
| CN115171045A (en) | YOLO-based power grid operation field violation identification method and terminal | |
| CN117010666B (en) | Intelligent management method and system for production workstation of automobile repair tool | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN117974719B (en) | Processing tracking and detecting method, system and medium for optical lens | |
| CN116228766B (en) | Intelligent regulation and control method and system for plasma processing equipment | |
| CN116931534B (en) | Embroidery product production control method and system based on Internet of Things | |
| Eranpurwala et al. | Predicting build orientation of additively manufactured parts with mechanical machining features using deep learning | |
| US12079976B2 (en) | Methods and systems for reducing dimensionality in a reduction and prediction framework | |
| Chernyshev et al. | Digital Object Detection of Construction Site Based on Building Information Modeling and Artificial Intelligence Systems. | |
| CN117476509B (en) | Laser engraving device for semiconductor chip product and control method | |
| CN116842415B (en) | Remote monitoring method, system and medium for mirror surface electric discharge machine | |
| CN118070983B (en) | Industrial machinery production optimization method and system based on deep learning | |
| CN116977652B (en) | Workpiece surface morphology generation method and device based on multi-mode image generation | |
| CN117850216B (en) | Intelligent control method and system for acrylic lens production equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |