Intelligent management method of chip probe production equipment
By constructing time series bending accuracy feature data and deep neural network prediction model, the bending accuracy of chip probe production equipment is predicted, which solves the defective product problem caused by the reduction in equipment bending accuracy, and achieves production optimization and cost reduction.
Patent Information
- Application Number
- CN202510126638.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-27
- Publication Date
- 2025-06-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
During the processing process of chip probe production equipment, due to the increase in service life and frequency of use, the bending accuracy of chip probes decreases, resulting in defective products, and thus causing production losses.
By collecting the bending accuracy change feature data of chip probe production equipment during the production process, building bending accuracy change feature data based on time series, and building a bending accuracy feature data prediction model based on deep neural networks, predicting the current bending accuracy feature data of each chip probe production equipment, initially selecting equipment that can perform normal processing tasks, and performing production optimization and monitoring.
By dynamically optimizing production planning, we can reduce the defective rate of chip probes during bending, reduce production costs, and reduce the production losses of chip probes.
Smart Images
Figure CN120087604A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of chip probe production equipment management, and particularly to an intelligent management method for chip probe production equipment. Background Art
[0002] A chip probe is an important tool for detecting a chip during the chip processing process. It can detect parameters such as the normal conduction of microcircuit electrical signals on the chip, the electrical signal strength, the electrical signal transmission direction, and the electrical signal transmission interval time on the chip, so as to conduct quality inspection on the chip. The probe mainly consists of a needle rod part and a needle cone part. When the probe is processed, a bending treatment needs to be carried out on the needle cone part. The traditional bending method is that workers put the needle cone part of the probe into a press bender, and the probe is deformed and bent through the cooperation and extrusion of a punch and a die in the press bender. However, during the processing of chip probe production equipment, due to the increase in service life and usage frequency, the chip probe may not meet the ideal requirements, resulting in defective products of the chip probe. If the abnormality is not detected in time, certain production losses will be caused. Summary of the Invention
[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent management method for chip probe production equipment.
[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:
[0005] The second aspect of the present invention provides an intelligent management method for chip probe production equipment, including the following steps:
[0006] Collect the bending accuracy change characteristic data of the chip probe production equipment during the production process, and construct the bending accuracy change characteristic data based on time series according to the bending accuracy change characteristic data of the chip probe production equipment during the production process;
[0007] Construct a bending accuracy characteristic data prediction model according to the bending accuracy change characteristic data based on time series, and predict the bending accuracy characteristic data of each chip probe production equipment at the current time stamp through the bending accuracy characteristic data prediction model;
[0008] Collect the bending requirement data information of each chip probe from the chip probe bending drawing, and initially select the chip probe production equipment that can normally perform the processing task according to the bending accuracy characteristic data of each chip probe production equipment at the current time stamp;
[0009] Optimize production according to the bending requirement data information of each chip probe and the chip probe production equipment that can normally perform the processing task, and monitor the production status of each chip probe production equipment.
[0010] Further, in this method, characteristic data of the bending accuracy change during the production process of the chip probe production equipment is collected, and based on the characteristic data of the bending accuracy change during the production process of the chip probe production equipment, characteristic data of the bending accuracy change based on time series is constructed, specifically as follows:
[0011] Collect characteristic data of the bending accuracy change during the production process of the chip probe production equipment, and obtain the bending accuracy characteristic data of the chip probe production equipment during the production process at each timestamp according to the characteristic data of the bending accuracy change during the production process of the chip probe production equipment;
[0012] Introduce the cosine metric algorithm, and calculate the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during the production process at each timestamp based on the cosine metric algorithm;
[0013] Set a cosine distance threshold, and determine whether there is a situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps is greater than the cosine distance threshold;
[0014] When there is no situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps is greater than the cosine distance threshold, the characteristic data of the bending accuracy change during the production process of the corresponding chip probe production equipment can be used as reference data;
[0015] Re - sort the reference data in the order of timestamps, construct the characteristic data of the bending accuracy change based on time series, and output the characteristic data of the bending accuracy change based on time series.
[0016] Further, in this method, a prediction model for the bending accuracy characteristic data is constructed based on the characteristic data of the bending accuracy change based on time series, specifically including:
[0017] Construct a prediction model for the bending accuracy characteristic data based on a deep neural network, and input the characteristic data of the bending accuracy change based on time series into the prediction model for the bending accuracy characteristic data for training;
[0018] Set a learning rate and a training end condition, learn the prediction model for the bending accuracy characteristic data according to the learning rate, and determine whether the prediction model for the bending accuracy characteristic data reaches the training end condition;
[0019] When the prediction model for the bending accuracy characteristic data reaches the training end condition, save the model parameters of the prediction model for the bending accuracy characteristic data and output the prediction model for the bending accuracy characteristic data.
[0020] When the bending accuracy feature data prediction model does not reach the training end condition, continue to train the bending accuracy feature data prediction model until the training end condition is reached.
[0021] Further, in this method, predicting the bending accuracy feature data of each chip probe production device at the current timestamp through the bending accuracy feature data prediction model specifically includes:
[0022] Obtain the bending accuracy feature data of each probe production device within a preset time, and input the bending accuracy feature data of the probe production device within the preset time into the bending accuracy feature data prediction model for prediction;
[0023] Through prediction, obtain the bending accuracy feature data of each chip probe production device at the current timestamp, and output the bending accuracy feature data of each chip probe production device at the current timestamp.
[0024] Further, in this method, initially selecting the chip probe production devices that can normally perform processing tasks according to the bending accuracy feature data of each chip probe production device at the current timestamp specifically includes:
[0025] Set a normal bending accuracy threshold, and determine whether the bending accuracy feature data of the chip probe production device at the current timestamp is greater than the normal bending accuracy threshold;
[0026] When the bending accuracy feature data of the chip probe production device at the current timestamp is greater than the normal bending accuracy threshold, then use the corresponding chip probe production device as the chip probe production device that can normally perform processing tasks;
[0027] When the bending accuracy feature data of the chip probe production device at the current timestamp is not greater than the normal bending accuracy threshold, then use the corresponding chip probe production device as the chip probe production device that cannot normally perform processing tasks.
[0028] Further, in this method, performing production optimization according to the bending requirement data information of each chip probe and the chip probe production devices that can normally perform processing tasks specifically includes:
[0029] Obtain the bending accuracy feature data of the chip probe production devices that can normally perform processing tasks at the current timestamp, and initialize the chip probe production devices for bending work according to the bending accuracy feature data of the chip probe production devices that can normally perform processing tasks at the current timestamp;
[0030] Construct a working data set of the chip probe production equipment according to the chip probe production equipment that performs the bending operation after initialization, and determine whether there is a chip probe production equipment in the working data set of the chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe;
[0031] When there is a chip probe production equipment in the working data set of the chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe, update the working data set of the chip probe production equipment until there is no chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe;
[0032] When there is no chip probe production equipment in the working data set of the chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe, output the working data set of the chip probe production equipment, and perform production optimization according to the working data set of the chip probe production equipment.
[0033] The second aspect of the present invention provides an intelligent management system for a chip probe production equipment, including a memory and a processor. The memory includes an intelligent management method program for the chip probe production equipment. When the intelligent management method program for the chip probe production equipment is executed by the processor, the steps of any one of the intelligent management methods for the chip probe production equipment are implemented.
[0034] The third aspect of the present invention provides a computer-readable storage medium, including an intelligent management method program for the chip probe production equipment. When the intelligent management method program for the chip probe production equipment is executed by a processor, the steps of any one of the intelligent management methods for the chip probe production equipment are implemented.
[0035] The present invention solves the defects existing in the background technology, and the present invention has the following beneficial effects:
[0036] The present invention collects the characteristic data of the bending precision change during the production process of the chip probe production equipment, constructs the characteristic data of the bending precision change based on time series according to the characteristic data of the bending precision change during the production process of the chip probe production equipment, and then constructs a prediction model of the bending precision characteristic data based on the characteristic data of the bending precision change based on time series. The bending precision characteristic data of each chip probe production equipment at the current time stamp is predicted through the bending precision characteristic data prediction model. Thus, by collecting the bending requirement data information of each chip probe from the chip probe bending drawing, and initially selecting the chip probe production equipment that can normally perform the processing task according to the bending precision characteristic data of each chip probe production equipment at the current time stamp. Finally, production optimization is carried out according to the bending requirement data information of each chip probe and the chip probe production equipment that can normally perform the processing task, and the production status of each chip probe production equipment is monitored. The present invention dynamically optimizes the production plan of the chip probe production equipment by determining whether the bending precision data of the chip probe production equipment is within the threshold range of the bending process data during the bending process of the chip probe, so as to reduce the defective rate of the chip probe during the bending process, reduce the production cost, and reduce the production loss of the chip probe. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.
[0038] Figure 1 Shows the overall flowchart of the intelligent management method of the chip probe production equipment;
[0039] Figure 2 Shows a partial method flowchart of the intelligent management method of the chip probe production equipment;
[0040] Figure 3 Shows the system block diagram of the intelligent management system of the chip probe production equipment. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0041] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.
[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited by the specific embodiments disclosed below.
[0043] As Figure 1 shown, the second aspect of the present invention provides an intelligent management method for a chip probe production device, including the following steps:
[0044] S102: Collect the bending accuracy change characteristic data of the chip probe production device during the production process, and construct the bending accuracy change characteristic data based on time series according to the bending accuracy change characteristic data of the chip probe production device during the production process;
[0045] S104: Construct a bending accuracy characteristic data prediction model according to the bending accuracy change characteristic data based on time series, and predict the bending accuracy characteristic data of each chip probe production device at the current timestamp through the bending accuracy characteristic data prediction model;
[0046] S106: Collect the bending requirement data information of each chip probe from the chip probe bending drawing, and preliminarily select the chip probe production devices that can normally perform the processing tasks according to the bending accuracy characteristic data of each chip probe production device at the current timestamp;
[0047] S108: Optimize the production according to the bending requirement data information of each chip probe and the chip probe production devices that can normally perform the processing tasks, and monitor the production status of each chip probe production device.
[0048] It should be noted that the present invention dynamically optimizes the production plan of the chip probe production device by determining whether the bending accuracy data of the chip probe production device is within the threshold range of the bending process data during the bending process of the chip probe, so as to reduce the defective rate of the chip probe during the bending process, reduce the production cost, and reduce the production loss of the chip probe.
[0049] It should be noted that among them, the bending accuracy data includes descriptions such as bending angle data and bending deviation data.
[0050] Further, in this method, collecting the bending accuracy change characteristic data of the chip probe production device during the production process, and constructing the bending accuracy change characteristic data based on time series according to the bending accuracy change characteristic data of the chip probe production device during the production process, specifically:
[0051] Collect the characteristic data of the bending accuracy change of the chip probe production equipment during the production process, and obtain the bending accuracy characteristic data of the chip probe production equipment during the production process for each timestamp according to the characteristic data of the bending accuracy change of the chip probe production equipment during the production process;
[0052] Introduce the cosine metric algorithm, and calculate the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during the production process for each timestamp based on the cosine metric algorithm;
[0053] Set the cosine distance threshold, and determine whether there is a situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during the production process is greater than the cosine distance threshold;
[0054] When there is no situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during the production process is greater than the cosine distance threshold, then the corresponding characteristic data of the bending accuracy change of the chip probe production equipment during the production process can be used as reference data;
[0055] Re - sort the reference data in the order of timestamps, construct the characteristic data of the bending accuracy change based on the time series, and output the characteristic data of the bending accuracy change based on the time series.
[0056] It should be noted that, actually, there may be a large - floating jump between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during each timestamp. This process is not a normal degradation of the bending accuracy, but is affected by external factors. At this time, when there is no situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment at two adjacent timestamps in the bending accuracy characteristic data of the chip probe production equipment during the production process is greater than the cosine distance threshold, then the corresponding characteristic data of the bending accuracy change of the chip probe production equipment during the production process can be used as reference data, and the reference data can be used as training data, so as to improve the prediction accuracy of the model and avoid the interference of other abnormal data on the model training.
[0057] Furthermore, in this method, construct a prediction model for the bending accuracy characteristic data according to the characteristic data of the bending accuracy change based on the time series, specifically including:
[0058] Construct a prediction model for the bending accuracy characteristic data based on a deep neural network, and input the characteristic data of the bending accuracy change based on the time series into the prediction model for the bending accuracy characteristic data for training;
[0059] Set the learning rate and the training end condition, learn the bending accuracy feature data prediction model according to the learning rate, and determine whether the bending accuracy feature data prediction model reaches the training end condition;
[0060] When the bending accuracy feature data prediction model reaches the training end condition, save the model parameters of the bending accuracy feature data prediction model and output the bending accuracy feature data prediction model;
[0061] When the bending accuracy feature data prediction model does not reach the training end condition, continue to train the bending accuracy feature data prediction model until the training end condition is reached.
[0062] It should be noted that the training end condition includes data such as the prediction accuracy of the model and the training parameters of the model. Deep neural networks include multi-layer perceptron neural networks, bp neural networks, convolutional neural networks, long short-term memory neural networks, etc.
[0063] Further, in this method, the bending accuracy feature data of each chip probe production device at the current timestamp is predicted by the bending accuracy feature data prediction model, specifically including:
[0064] Obtain the bending accuracy feature data of each probe production device within a preset time, and input the bending accuracy feature data of the probe production device within the preset time into the bending accuracy feature data prediction model for prediction;
[0065] Through prediction, obtain the bending accuracy feature data of each chip probe production device at the current timestamp, and output the bending accuracy feature data of each chip probe production device at the current timestamp.
[0066] Further, in this method, the chip probe production devices that can normally perform processing tasks are initially selected according to the bending accuracy feature data of each chip probe production device at the current timestamp, specifically including:
[0067] Set a normal bending accuracy threshold, and determine whether the bending accuracy feature data of the chip probe production device at the current timestamp is greater than the normal bending accuracy threshold;
[0068] When the bending accuracy feature data of the chip probe production device at the current timestamp is greater than the normal bending accuracy threshold, the corresponding chip probe production device is used as the chip probe production device that can normally perform processing tasks;
[0069] When the bending accuracy feature data of the chip probe production device at the current timestamp is not greater than the normal bending accuracy threshold, the corresponding chip probe production device is used as the chip probe production device that cannot normally perform processing tasks.
[0070] Such asFigure 2 As shown, further, in this method, production optimization is carried out according to the bending requirement data information of each chip probe and the chip probe production equipment that can normally perform processing tasks, specifically including:
[0071] S202: Obtain the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks at the current timestamp, and initialize the chip probe production equipment for bending work according to the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks at the current timestamp;
[0072] S204: Construct a chip probe production equipment working data set according to the initialized chip probe production equipment for bending work, and determine whether there is a chip probe production equipment in the chip probe production equipment working data set whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe;
[0073] S206: When there is a chip probe production equipment in the chip probe production equipment working data set whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe, update the chip probe production equipment working data set until there is no chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe;
[0074] S208: When there is no chip probe production equipment in the chip probe production equipment working data set whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe, output the chip probe production equipment working data set, and perform production optimization according to the chip probe production equipment working data set.
[0075] It should be noted that through this method, the production plan can be optimized, thereby reducing the defective rate of chip probes during the bending process, reducing production costs, and reducing the production losses of chip probes.
[0076] In addition, this method also includes:
[0077] Obtain the bending accuracy characteristic data of the chip probe production equipment under each working environment factor through big data, construct a knowledge graph, and input the bending accuracy characteristic data of the chip probe production equipment under each working environment factor into the knowledge graph for storage;
[0078] Obtain the working environment factor of the current chip probe production equipment, input the working environment factor of the current chip probe production equipment into the knowledge graph for data matching, and obtain the bending accuracy characteristic data of the chip probe production equipment under the working environment factor of the current chip probe production equipment;
[0079] Update the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks according to the bending accuracy characteristic data of the chip probe production equipment under the working environment factors of the current chip probe production equipment;
[0080] Judge whether the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks after the update is lower than the bending requirement data information of the chip probe;
[0081] When the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks after the update is lower than the bending requirement data information of the chip probe, then find the environmental characteristics where the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks after the update is not lower than the bending requirement data information of the chip probe, and adjust the working environment of the current chip probe production equipment through the environmental control equipment.
[0082] It should be noted that the environmental temperature and humidity have a certain impact on the bending accuracy of the chip probe production equipment. When the bending accuracy characteristic data of the chip probe production equipment that can normally perform processing tasks after the update is lower than the bending requirement data information of the chip probe, then adjust the working environment of the current chip probe production equipment through the environmental control equipment until it is not lower than the bending requirement data information of the chip probe, which can improve the bending accuracy of the chip probe, reduce the production of defective products, and reduce production losses.
[0083] In addition, monitor the production status of each chip probe production equipment, specifically including:
[0084] Obtain the optimal processing parameter characteristic data under each material type, each material temperature, and each bending thickness through big data, and store the processing parameter characteristic data under each material type and each bending thickness in the knowledge graph;
[0085] Obtain the material type information, real-time material temperature, and bending thickness information of the current chip probe, and input the material type information, real-time material temperature, and bending thickness information of the current chip probe into the knowledge graph for data matching to obtain the optimal processing parameter characteristic data of the material type information and bending thickness information of the current chip probe;
[0086] Obtain the processing parameter information of each chip probe production equipment during the bending process, and compare the processing parameter information of the chip probe production equipment during the bending process with the optimal processing parameter characteristic data of the material type information and bending thickness information of the current chip probe to obtain the deviation rate;
[0087] When the deviation rate is greater than a preset deviation rate threshold, the optimal processing parameter characteristic data of the material type information and the bending thickness information of the current chip probe are adjusted until the deviation rate is not greater than the preset deviation rate threshold.
[0088] It should be noted that due to different material types, material temperatures, and material thicknesses having different yield strengths, elastic moduli, etc., the chip probe will have different optimal processing parameters. When the deviation rate is greater than the preset deviation rate threshold, the optimal processing parameter characteristic data of the material type information and the bending thickness information of the current chip probe are adjusted until the deviation rate is not greater than the preset deviation rate threshold. This can improve the success rate of bending, reduce the production of defective products, and optimize the bending of the chip probe.
[0089] As Figure 3 shown, the second aspect of the present invention provides an intelligent management system 4 for a chip probe production device, including a memory 41 and a processor 42. The memory 41 includes an intelligent management method program for the chip probe production device. When the intelligent management method program for the chip probe production device is executed by the processor 42, the steps of the intelligent management method for the chip probe production device in any one of the above are implemented.
[0090] The third aspect of the present invention provides a computer-readable storage medium, including an intelligent management method program for a chip probe production device. When the intelligent management method program for the chip probe production device is executed by a processor, the steps of the intelligent management method for the chip probe production device in any one of the above are implemented.
[0091] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.
[0092] The units described as separate components above may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0093] In addition, each functional unit in the embodiments of the present invention may all be integrated into one processing unit, or each unit may be separately taken as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated unit may be implemented in the form of hardware, or in the form of a hardware plus software functional unit.
[0094] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.
[0095] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes 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 various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.
[0096] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims
1. An intelligent management method for chip probe production equipment, characterized in that: The following steps are involved: Collecting bending accuracy change characteristic data of a chip probe production device during the production process, and constructing bending accuracy change characteristic data based on a time series according to the bending accuracy change characteristic data of the chip probe production device during the production process; Constructing a bending precision characteristic data prediction model according to the bending precision change characteristic data based on the time series, and predicting the bending precision characteristic data of each chip probe production device at the current timestamp by using the bending precision characteristic data prediction model; By collecting the bending requirement data information of each chip probe from the chip probe bending drawing, and preliminarily selecting the chip probe production equipment that can normally perform the processing task according to the bending accuracy feature data of each chip probe production equipment at the current timestamp; Production optimization is performed based on the bending requirement data information of each chip probe and the chip probe production equipment that can normally perform the processing task, and the production status of each chip probe production equipment is monitored.
2. The intelligent management method of chip probe production equipment according to claim 1, characterized in that: Collect the bending accuracy change characteristic data of the chip probe production equipment during the production process, and construct the bending accuracy change characteristic data based on the time series according to the bending accuracy change characteristic data of the chip probe production equipment during the production process, specifically: Collecting bending accuracy change characteristic data of the chip probe production equipment during the production process, and obtaining the bending accuracy characteristic data of the chip probe production equipment during the production process in each timestamp according to the bending accuracy change characteristic data of the chip probe production equipment during the production process; A cosine measurement algorithm is introduced, and a cosine distance between the bending accuracy feature data of the chip probe production equipment during the production process of two adjacent timestamps in the bending accuracy feature data of the chip probe production equipment during the production process in each timestamp is calculated based on the cosine measurement algorithm; Setting a cosine distance threshold, and determining whether there is a situation where the cosine distance between the bending precision feature data of the chip probe production equipment in the production process with two adjacent timestamps is greater than the cosine distance threshold; When there is no situation where the cosine distance between the bending accuracy characteristic data of the chip probe production equipment in the production process with two adjacent timestamps is greater than the cosine distance threshold, the bending accuracy change characteristic data of the corresponding chip probe production equipment in the production process can be used as reference data; The reference data are reordered in the order of timestamps, bending accuracy change characteristic data based on time series are constructed, and the bending accuracy change characteristic data based on time series are output.
3. The intelligent management method of chip probe production equipment according to claim 1, characterized in that: Constructing a bending accuracy characteristic data prediction model according to the bending accuracy change characteristic data based on the time series, specifically comprising: Constructing a bending accuracy feature data prediction model based on a deep neural network, and inputting the bending accuracy change feature data based on the time series into the bending accuracy feature data prediction model for training; Setting a learning rate and a training end condition, learning the bending precision feature data prediction model according to the learning rate, and determining whether the bending precision feature data prediction model meets the training end condition; When the bending precision feature data prediction model reaches the training end condition, the model parameters of the bending precision feature data prediction model are saved, and the bending precision feature data prediction model is output; When the bending precision feature data prediction model does not meet the training end condition, the bending precision feature data prediction model continues to be trained until the training end condition is met.
4. The intelligent management method of chip probe production equipment according to claim 1, characterized in that: Predicting the bending accuracy feature data of each chip probe production device at the current timestamp by using the bending accuracy feature data prediction model specifically includes: Acquire the bending accuracy characteristic data of each probe production device within a preset time, and input the bending accuracy characteristic data of the probe production device within the preset time into the bending accuracy characteristic data prediction model for prediction; By prediction, the bending precision characteristic data of each chip probe production device at the current time stamp is obtained, and the bending precision characteristic data of each chip probe production device at the current time stamp is output.
5. The intelligent management method for chip probe production equipment according to claim 1, characterized in that: Preliminary selection of chip probe production equipment that can normally perform processing tasks is performed based on the bending accuracy feature data of each chip probe production equipment at the current timestamp, specifically including: Setting a normal bending accuracy threshold, and determining whether the bending accuracy characteristic data of the chip probe production equipment at a current timestamp is greater than the normal bending accuracy threshold; When the bending accuracy characteristic data of the chip probe production equipment at the current timestamp is greater than the normal bending accuracy threshold, the corresponding chip probe production equipment is used as a chip probe production equipment that can normally perform processing tasks; When the bending accuracy characteristic data of the chip probe production equipment at the current timestamp is not greater than the normal bending accuracy threshold, the corresponding chip probe production equipment is regarded as a chip probe production equipment that performs abnormal processing tasks.
6. The intelligent management method for chip probe production equipment according to claim 1, characterized in that: Production optimization is performed based on the bending requirement data information of each chip probe and chip probe production equipment that can normally perform processing tasks, specifically including: Acquire the bending accuracy characteristic data of the chip probe production equipment that can normally perform the processing task at the current timestamp, and initialize the chip probe production equipment that performs the bending work according to the bending accuracy characteristic data of the chip probe production equipment that can normally perform the processing task at the current timestamp; Constructing a chip probe production equipment work data set according to the chip probe production equipment that performs bending work after initialization, and determining whether there is a chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe in the chip probe production equipment work data set; When there is a chip probe production equipment whose bending precision characteristic data is lower than the bending requirement data information of the chip probe in the chip probe production equipment working data set, the chip probe production equipment working data set is updated until there is no chip probe production equipment whose bending precision characteristic data is lower than the bending requirement data information of the chip probe; When there is no chip probe production equipment whose bending accuracy characteristic data is lower than the bending requirement data information of the chip probe in the chip probe production equipment working data set, the chip probe production equipment working data set is output, and production optimization is performed according to the chip probe production equipment working data set.
7. An intelligent management system for chip probe production equipment, characterized in that: It comprises a memory and a processor, wherein the memory comprises a program of an intelligent management method for chip probe production equipment, and when the program of the intelligent management method for chip probe production equipment is executed by the processor, the steps of the intelligent management method for chip probe production equipment as described in any one of claims 1-6 are implemented.
8. A computer-readable storage medium, characterized in that: It comprises a program of an intelligent management method for chip probe production equipment, and when the program of the intelligent management method for chip probe production equipment is executed by a processor, the steps of the intelligent management method for chip probe production equipment as described in any one of claims 1-6 are implemented.