Abrégé

A production management and control system for ammonium fluoride production and a control method therefor, using an artificial intelligence control technology. Dynamic intelligent control of a flow rate of cooling water is performed by using addition flow rate values of liquid ammonia, addition flow rate values of anhydrous hydrogen fluoride, reaction temperature values, flow rate values of the cooling water and pH values of a reaction liquid at a plurality of predetermined time points within a predetermined time period as input data, and using a deep neural network model as a feature extractor and according to the cooperation of real-time dynamic features of the flow rate when the liquid ammonia and the anhydrous hydrogen fluoride are added to a reaction tank and change features of reaction temperatures; and in this process, pH value change feature information of the reaction liquid is also added as a basis for a final result, so as to improve the reaction efficiency and the product quality.

Classes IPC  ?

• C01C 1/16 - Halogénures d'ammonium
• G05D 27/02 - Commande simultanée des variables entrant dans plusieurs des groupes principaux caractérisée par l'utilisation de moyens électriques

Abrégé

The invention belongs to the field of fine chemical engineering, and relates to an ITO etching solution and a usage method thereof. The etching solution is composed of an A phase, a neutralizing solution, and a B phase; the A phase is composed of the following raw materials in percent by mass: 3-5 wt% glucosaminoglycan, 1.5-2.5 wt% formic acid, and the remainder water; the B phase is composed of the following raw materials in percent by mass: 20-28 wt% iron trichloride, 0.01-0.1 wt% anionic surfactant, 0.05-0.5 wt% nonionic surfactant, 13-18 wt% non-oxidizing acid, and the remainder water. The addition of A-phase processing effectively avoids the problem of ITO electrode pattern loss and even damage caused by excessive etching during an ITO etching process, thereby greatly improving the product pass rate while simultaneously breaking-through limitations to the degree of complexity of traditional ITO conductive film patterns.

Classes IPC  ?

• C23F 1/18 - Compositions acides pour le cuivre ou ses alliages
• C23F 1/16 - Compositions acides
• C09K 13/06 - Compositions pour l'attaque chimique, la gravure, le brillantage de surface ou le décapage contenant un acide inorganique avec une substance organique
• C09K 13/04 - Compositions pour l'attaque chimique, la gravure, le brillantage de surface ou le décapage contenant un acide inorganique

Abrégé

The present application relates to intelligent batching in the field of intelligent production. Specifically disclosed are an automatic batching system and method for film stripping solution production. A surface state feature of an image of an object to be stripped is mined by means of a convolutional neural network model based on deep learning, and adjustment of the mass percentage of a polyether surfactant is assisted on the basis of a global association feature of the mass percentage of each component of a film stripping solution during batching and a logic association feature between components of the film stripping solution, so as to obtain a better formula adapted to a specific object to be stripped, and obtain a better film stripping effect, thereby ensuring the quality of a PCB.

Classes IPC  ?

• G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
• G16C 20/60 - Chimie combinatoire in silico

Abrégé

An automatic batching system for buffered oxide etch production and a batching method thereof. The present invention uses artificial intelligence control technology, and on the basis of a deep neural network model, dynamic implicit features of hydrogen injection speed, a liquid chromatogram of a buffered oxide etch and a surface tension value of the buffered oxide etch are respectively extracted in time dimension. In this way, the hydrogen injection speed can be controlled on the basis of the real-time condition and dynamic change features of the surface tension of the etch, and thus the etching rate and etching quality of the buffered oxide etch in a using process can be ensured.

Classes IPC  ?

• G06V 10/80 - Fusion, c.-à-d. combinaison des données de diverses sources au niveau du capteur, du prétraitement, de l’extraction des caractéristiques ou de la classification
• G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
• B01F 35/71 - Mécanismes d'alimentation
• C09K 13/08 - Compositions pour l'attaque chimique, la gravure, le brillantage de surface ou le décapage contenant un acide inorganique contenant un composé du fluor

Abrégé

Disclosed are a control system for an intelligent production line of electronic-grade potassium hydroxide, and a control method thereof, which relate to intelligent control in the field of intelligent manufacturing. The control system uses artificial intelligence control technology, and performs, on the basis of a deep neural network model, deep mining of the dynamic change characteristics of the power of a sprayer and the dynamic characteristics of image frames of spray impurity removal, so as to dynamically control in real time the power of the sprayer in the intelligent production line of electronic-grade potassium hydroxide, and hence ensure the crystal yield outcome and impurity transmission efficiency.

Classes IPC  ?

• G05B 19/042 - Commande à programme autre que la commande numérique, c.-à-d. dans des automatismes à séquence ou dans des automates à logique utilisant des processeurs numériques

Abrégé

A feeding device for preparing an electronic-grade TFT developing solution, the feeding device comprising a main storage cabin (1), raw material cabins (11) being symmetrically formed on a left side and a right side in the main storage cabin (1), and a liquid storage cabin (12) being provided between the raw material cabins (11), wherein a sealing cover is mounted above the raw material cabins (11), a main frame body (13) is fixedly connected to a back side of the main storage cabin (1), a mounting frame (14) is fixedly connected to a front side of the main storage cabin (1), and a quantitative liquid-pumping mechanism (2) is provided on a front side of the mounting frame (14). Quantitative ultrapure water is pumped into the interior of a quantitative measuring cylinder (23) by means of forward driving of a driving air cylinder (21), and the ultrapure water is prompted to be automatically added into a tank after reverse driving of the driving air cylinder (21). During the process, automatic feeding can be achieved without manual intervention, and pollution to the ultrapure water can be reduced to the maximum extent, so that relatively pure ultrapure water can be provided for preparation of the TFT developing solution, and then the purity of the developing solution prepared subsequently is improved.

Classes IPC  ?

• B01F 33/81 - Combinaisons de mélangeurs similaires, p. ex. avec des dispositifs d'agitation rotatifs dans plusieurs récipients
• B01F 35/71 - Mécanismes d'alimentation

Abrégé

An automatic batching system for the production of photoresist stripping liquid, and a batching method therefor, comprising: a deep neural network model being used as a feature extractor to extract and use as a reference the surface features of an ideal printed circuit board to be stripped, and on the basis of said reference features, intelligently and accurately judging the proportion of hydroxide and alkali metal amine-type composition added. It is thus possible to avoid corrosion of a metal pattern in a printed circuit and erosion of a lower portion, and to further improve a stripping effect while avoiding the negative effect that the introduction thereof is difficult to accept.

Classes IPC  ?

• B01F 35/22 - Commande ou régulation
• B01F 35/81 - Formation de mélanges avec un rapport variable ou avec des gradients
• G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
• G06N 3/08 - Méthodes d'apprentissage

Abrégé

The present invention relates to the technical field of developing solutions. Disclosed is a dissolving device used for preparing an electronic-grade TFT developing solution. The device comprises a dissolving bin (1), wherein a stirring assembly (2) is arranged in the dissolving bin (1), a gas collection driving assembly (3) is arranged above the stirring assembly (2), an intermittently supplementing assembly (4) is arranged on one side of the gas collection driving assembly (3), an auxiliary chamber (101) is arranged on the dissolving bin (1), a driving gear (201) is arranged in the stirring assembly (2), and a driven gear (202) is meshed with the driving gear (201) on one side. Driven by a motor, the driving gear (201) drives, by means of the driven gear (202), a first rotation column (203) fixedly connected to the driven gear (202) to rotate; by means of a second rotation column (206), a third rotation column (207) and a connecting rod (211) on a disc, the rotating first rotation column (203) drives a gas ejection block (212) to rotate; when the gas ejection block (212) rotates, a gas pump arranged in the gas ejection block (212) ejects gas out of a gas outlet (213), at this time, a developing solution and an additive in the dissolving bin (1) are disturbed in gas flow, and in addition, the connecting rod (211) drives the gas ejection block (212) to rotate, so that the stirring amplitude of a mixed solution can be greatly improved.

Classes IPC  ?

• B01F 21/10 - Dissolution en utilisant des agitateurs entraînés
• B01F 33/40 - Mélangeurs utilisant l'agitation de gaz ou de liquide, p. ex. avec des tubes d'alimentation en air
• B01F 27/90 - Mélangeurs à agitateurs tournant dans des récipients fixesPétrins avec des agitateurs tournant autour d'un axe sensiblement vertical avec des palettes ou des bras

Abrégé

The present application relates to the field of photoresist cleaning liquids under intelligent manufacturing, and particularly discloses an automatic proportioning system for photoresist cleaning liquid production and a proportioning method therefor. The automatic proportioning system for photoresist cleaning liquid production intelligently determines the local optimal qualities of formula ingredients one by one by using a deep-learning-based neural network technique, and determines, in this way, the optimum ratio of a photoresist cleaning liquid for a specific object, such that automatic proportioning is performed on the basis of the optimum ratio.

Classes IPC  ?

• G06N 3/08 - Méthodes d'apprentissage
• G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
• G06F 17/16 - Calcul de matrice ou de vecteur
• B01F 35/80 - Formation d'un rapport prédéterminé des substances à mélanger

Abrégé

The present application relates to the field of intelligent detection of electronic grade gases, and specifically discloses an intelligent toxic and harmful gas alarm system for the preparation of electronic grade hydrogen peroxide, and an alarm method thereof. In the present application, a convolutional neural network model is used to extract high-dimensional implicit correlation features among hydrogen peroxide concentrations at different positions of a place to be monitored and topological features of multiple gas chromatographs so as to generate feature vectors and a feature matrix; in order to fuse feature information of the feature vectors and the feature matrix to enhance the spatial correlation of hydrogen peroxide distribution on the basis of the topological features so as to improve the accuracy of classification, a classification feature vector is further generated by means of a class representation of spatial mapping of the feature vectors to the feature matrix, so that a simultaneous projection of the feature vectors to a high-dimensional feature space of the feature matrix under a specific label class probability is achieved, and the dimensional alignment of feature distributions of the feature vectors in the high-dimensional feature space is improved, thereby improving the sensitivity and accuracy of early warning classification.

Classes IPC  ?

• G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p. ex. des objets vidéo
• G06V 10/80 - Fusion, c.-à-d. combinaison des données de diverses sources au niveau du capteur, du prétraitement, de l’extraction des caractéristiques ou de la classification
• G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
• G08B 21/14 - Alarmes réagissant aux gaz toxiques
• G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
• G06N 3/08 - Méthodes d'apprentissage

Abrégé

An automatic proportioning system for production of a neutral cleaning agent and a proportioning method thereof. The automatic proportioning system for production of a neutral cleaning agent uses neural network technology based on deep learning to intelligently and dynamically infer a relatively good proportioning scheme for a neutral cleaning agent on the basis of a formulation as a whole and the association between ingredients of the formulation, such that intelligent proportioning for the neutral cleaning agent can be achieved for different cleaning objects. Therefore, the performance and effect of a manufactured neutral cleaning agent can be better.

Classes IPC  ?

• G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
• G06N 3/08 - Méthodes d'apprentissage
• C11D 7/26 - Composés organiques contenant de l'oxygène
• C11D 7/32 - Composés organiques contenant de l'azote