KR20230128707A - A method for detecting anomaly of electronic device based on air analysis - Google Patents

Abstract

A method for detecting signs of failure for at least one electronic device based on air analysis is provided. The at least one electronic equipment is configured to be mounted inside the at least one box, and the method includes air analysis information on air inside the box in which the electronic equipment is mounted - the air analysis information is based on a sensor for characteristics of the air inside the box. Obtaining - including the measured value of ; and determining whether a failure symptom occurs in the electronic equipment based on normal state information including air analysis information when the electronic equipment is in a normal state and the obtained air analysis information.

Description

A METHOD FOR DETECTING ANOMALY OF ELECTRONIC DEVICE BASED ON AIR ANALYSIS

The present invention relates to a method for detecting signs of failure of electronic equipment, and more particularly, to a method for detecting signs of failure of electronic equipment in advance based on air analysis.

For example, expensive semiconductor equipment or other manufacturing production facilities necessarily include electronic equipment such as electronic control units (ECUs) or electronic circuit boards. Such electronic equipment may fail due to causes such as corrosion or fusion caused by dust, contamination, or other chemicals according to the production environment, resulting in combustion due to resistance or heat generation, or circuit fusion. Failure of such electronic equipment makes quality control in the process difficult and can lower productivity, frequently causing large and small financial damages. Therefore, it is important to minimize the loss of money and other things that may occur by detecting symptoms in advance for these failures.

Korean Patent Registration No. 10-0396468 ("Air sampling carrier and air analysis device and method", Samsung Electronics Co., Ltd.)

An object of the present invention to solve the above problems is to analyze the air inside the box in which the electronic equipment is mounted and to consider the characteristics of air in a normal state and the measured air together, so that there are no signs of abnormality in the electronic equipment. It is to provide a method for detecting failure symptoms of electronic equipment based on air analysis, which can detect failure symptoms of electronic equipment in advance and minimize tangible and intangible damage that may occur by determining whether or not it occurs.

Another object of the present invention for solving the above problems is air circulation for circulating the air of each of a plurality of boxes in one air analysis equipment in analyzing the air inside a plurality of boxes in which a plurality of electronic equipment is mounted, respectively. By having a pipe and controlling the opening and closing of the air circulation pipe for each box, it is possible to diagnose a large number of electronic equipment through a small amount of air analysis device by analyzing the air of a box in which a specific electronic equipment is mounted, To provide a method for detecting signs of failure for electronic equipment based on air analysis.

However, the problem to be solved by the present invention is not limited thereto, and may be expanded in various ways without departing from the spirit and scope of the present invention.

In order to achieve the above object, a method for detecting a symptom of failure of an electronic device according to an embodiment of the present invention is a method of detecting a symptom of failure of at least one electronic device based on air analysis, wherein the at least one electronic device Is configured to be mounted inside at least one box, the method is performed by a computing device, and the method includes air analysis information on air inside a box in which electronic equipment is mounted - the air analysis information, the air inside the box Obtaining - including a sensor-based measured value for a characteristic of ; and determining whether a failure symptom occurs in the electronic equipment based on normal state information including air analysis information when the electronic equipment is in a normal state and the obtained air analysis information.

According to one aspect, the air analysis information may include information about components of air inside a box in which electronic equipment to be analyzed is mounted.

According to one aspect, the air analysis information may further include measurement information on at least one of air density, temperature, humidity, and whether or not smoke is generated in the air inside the box in which the electronic equipment to be analyzed is mounted.

According to one aspect, the electronic equipment includes at least one of an electronic control unit (ECU), a printed circuit board (PCB), or an electronic circuit board, and manufactures semiconductor equipment or industrial products in a semiconductor process. It may be electronic equipment included in production facilities.

According to one aspect, the at least one electronic device includes a first electronic device mounted on a first box and a second electronic device mounted on a second box different from the first box, and obtaining the air analysis information. The step of doing is configured to obtain air analysis information on the air inside any one of the first box or the second box, and the step of determining whether or not a failure symptom has occurred is the first electronic equipment or the first electronic equipment or the first box. 2 It can be configured to determine whether any one of the electronic equipment has a failure symptom.

According to one aspect, the sensor-based measurement value is obtained by at least one sensor mounted in at least one air measuring box, and the first air circulation pipe between the first box and the air measuring box determines the measured value. The air inside the first box is configured to circulate to the air measuring box, and the air inside the second box circulates to the air measuring box based on a second air circulation pipe between the second box and the air measuring box. The obtaining of the air analysis information may include controlling at least one of a first electric opening and closing unit included in the first air circulation pipe and a second electric opening and closing unit included in the second air circulation pipe. By doing so, the air inside any one of the first box or the second box can be circulated to the air measuring box.

According to one aspect, the method may include transmitting information about an electronic device having a failure symptom among the first electronic device and the second electronic device to a manager device; and a first process related to the first electronic equipment and the second electronic equipment among the first electronic equipment and the second electronic equipment in the semiconductor equipment of the semiconductor process or the industrial product manufacturing production facility, a process before and after the first process, or the first process. It may include changing a control setting for at least one of the associated processes of the.

According to one aspect, the step of determining whether a failure symptom occurs may include a plurality of learning data sets, each of which includes air component information, air density information, air temperature information, humidity information, and smoke generation information. Including sample air analysis information including as an input value, and including as an output value whether or not a failure symptom labeled with respect to the sample air analysis information occurs - generating a model for determining whether a failure symptom occurs by learning an artificial neural network based on ; and outputting whether or not a failure symptom occurs for the electronic equipment by inputting the obtained air analysis information into the failure symptom occurrence determination model. can include

According to one aspect, at least one box in which the at least one electronic device is mounted includes an optical output port outputting an optical signal into the box and an optical input port receiving an optical signal output from the optical output port. In the obtaining of the air analysis information, the air analysis information may be obtained by using an optical signal output from the light output port and an optical signal received from the optical input port.

According to one aspect, the at least one box in which the at least one electronic equipment is mounted includes an image information acquisition device configured to obtain image data of air inside the box, and the obtaining of the air analysis information comprises: , The air analysis information may be obtained based on analyzing the acquired image data of the air inside the box.

The disclosed technology may have the following effects. However, it does not mean that a specific embodiment must include all of the following effects or only the following effects, so it should not be understood that the scope of rights of the disclosed technology is limited thereby.

According to the method for detecting signs of failure of electronic equipment based on air analysis according to an embodiment of the present invention described above, by analyzing the air inside the box in which the electronic equipment is mounted, the air characteristics in a normal state and the measured It is possible to detect signs of failure of electronic equipment in advance and minimize tangible and intangible damage that may occur by determining whether or not an abnormal symptom occurs in electronic equipment by considering the characteristics of air together.

In addition, in analyzing the air inside a plurality of boxes in which a plurality of electronic equipment is mounted, one air analysis equipment is provided with an air circulation pipe for circulating air in each of the plurality of boxes, and an air circulation pipe for each box. By controlling the opening and closing of the air in the box in which the specific electronic equipment is mounted, it is possible to diagnose a large number of electronic equipment through a small amount of air analysis device.

1 is a flowchart of a method for detecting a failure symptom for at least one electronic device based on air analysis according to an embodiment of the present invention.
FIG. 2 is a flowchart of an example of an artificial neural network-based decision in the step of determining whether a failure symptom occurs in FIG. 1;
FIG. 3 is a flowchart of an example of optical analysis-based determination in the step of determining whether a failure symptom has occurred in FIG. 1;
FIG. 4 is a flowchart of an example of image analysis-based determination in the step of determining whether a failure symptom has occurred in FIG. 1;
5 is an exemplary conceptual diagram of a monitoring system for process equipment including electronic equipment.
6 shows configurations of process equipment and a monitoring system to which a method for detecting signs of failure of electronic equipment based on air analysis according to an embodiment of the present invention can be applied.
Fig. 7 is a block diagram showing an exemplary configuration of the analysis device of Fig. 6;
8 is a conceptual diagram of a failure symptom prediction model based on an artificial neural network according to an aspect of the present invention.
9 shows an exemplary configuration for optical analysis-based failure symptom determination according to one aspect of the present invention.
10 shows an exemplary configuration for determining the occurrence of a failure symptom based on image analysis according to an aspect of the present invention.
11 is a block diagram illustrating the configuration of an exemplary computing system in which a method according to an embodiment of the present invention may be performed.

Since the present invention can make various changes and have various embodiments, specific embodiments are illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in more detail. In order to facilitate overall understanding in the description of the present invention, the same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

outline

As reviewed above, for example, expensive semiconductor equipment or other manufacturing production facilities necessarily include electronic equipment such as an Electronic Control Unit (ECU) or an electronic circuit board. With the development of IT and robot device industries, the number of electronic equipment provided in process facilities is increasing day by day, and the design relationship between the electronic equipment itself and a plurality of electronic equipment is also becoming more and more complicated.

Within process facilities, these electronic equipments fail for various reasons, such as resistance or heat generation resulting from combustion or circuit fusion due to various causes such as corrosion or fusion caused by dust, contamination, and other chemicals in the production environment. this can happen In addition, there may be cases in which problems occur in electronic equipment due to various causes.

Failure of such electronic equipment makes quality control in the process difficult and can lower productivity, frequently causing large and small financial damages. In particular, for example, in a high value-added process such as a semiconductor process, even a short-term decrease in process productivity due to a minor failure or abnormality of electronic equipment can lead to huge financial losses.

Therefore, it is important to minimize the loss of money and other things that may occur due to problems in electronic equipment by detecting and preparing for symptoms in advance and taking measures against the occurrence of failures or abnormal situations of such electronic equipment.

Embodiments of the present invention are intended to solve this problem, and by analyzing the air inside the box in which the electronic equipment is mounted and considering the characteristics of the air in a normal state and the measured air together, the ideal for the electronic equipment It can be used to determine whether or not symptoms occur. Therefore, it is possible to detect signs of failure of electronic equipment in advance and minimize tangible and intangible damage that may occur.

In addition, according to embodiments of the present invention, in analyzing the air inside a plurality of boxes in which a plurality of electronic equipment is mounted, an air circulation pipe for circulating the air of each of the plurality of boxes is provided to one air analysis equipment. By providing and controlling the opening and closing of the air circulation pipe for each box, it is possible to analyze the air of a box in which a specific electronic device is mounted, thereby diagnosing a large number of electronic devices through a small amount of air analysis device. Therefore, while minimizing the cost of expensive air analysis equipment, it is possible to detect anomalies in a large amount of electronic equipment in advance.

Electronic Equipment Anomaly Detection System Configuration

5 is an exemplary conceptual diagram of a monitoring system for process equipment including electronic equipment, and FIG. 6 is a method to which a method for detecting signs of failure of electronic equipment based on air analysis according to an embodiment of the present invention may be applied. It shows the configuration of process equipment and monitoring system.

First, as shown in FIG. 5 , an exemplary process facility 1000 may include a plurality of facilities for the entire process, and at least some of the plurality of facilities include, for example, first electronic equipment (100-1 ), and a plurality of electronic devices such as the second electronic device 100-2 to the nth electronic device 100-n. FIG. 5 illustratively shows an analysis device 200 for detecting failure symptoms for a plurality of electronic devices 100-1, 100-2, and 100-n.

As shown in FIG. 5 , one analysis device 200 may be configured to perform analysis on a plurality of electronic devices 100-1, 100-2, and 100-n, or according to another aspect. An analysis device is assigned to each of the electronic devices 100-1, 100-2, and 100-n, or at least a portion of the electronic devices 100-1, 100-2, and 100-n is grouped into one It may also be configured such that one analysis device is assigned to a group.

Information according to the analysis result of the analysis device 200 may be transmitted to the server 300 through a wired or wireless communication network, for example. Server 300 can be implemented by any computing device that includes a processor and memory, such as a desktop or workstation, for example.

For example, through the control monitor 400 that can be provided in the integrated control room, the control room manager can detect a failure or Various monitoring information can be identified, including whether or not abnormal symptoms have occurred.

According to one aspect, the determination information on whether a failure or an anomaly is determined by the server 300 may be transmitted to the manager device 500 through various means such as a wired or wireless communication network or a cloud network. The manager device 500 may be, for example, a mobile device, so that a manager located at the site of the process facility 1000 conveniently receives information about the occurrence of an abnormal symptom on at least one of the electronic equipment, thereby taking action more quickly. It may be configured to perform.

6 shows configurations of process equipment and a monitoring system to which a method for detecting signs of failure of electronic equipment based on air analysis according to an embodiment of the present invention can be applied. Hereinafter, with reference to FIG. 6 , configurations of process equipment and a monitoring system for detecting signs of failure of electronic equipment based on air analysis according to an embodiment of the present invention will be described in more detail.

As shown in FIGS. 5 and 6 , a plurality of electronic devices 100-1, 100-2, and 100-n may be provided in a process facility. According to one aspect of the present invention, each of the plurality of electronic devices 100-1, 100-2, and 100-n is configured to be mounted inside a corresponding box 110-1, 110-2, and 110-n. And, by analyzing the air inside each box 110-1, 110-2, 110-n, the electronic equipment mounted inside each box 110-1, 110-2, 110-n It may be configured to detect in advance whether a failure symptom occurs.

For example, the first electronic equipment 100-1 is mounted on the first box 110-1, and by analyzing the air inside the first box 110-1, the first electronic equipment 100-1 ), the second electronic equipment 100-2 is mounted in the second box 110-2 and analyzes the air inside the second box 110-2. 2 It is possible to determine whether the electronic equipment 100-2 has a failure symptom, the n-th electronic equipment 100-n is mounted in the n-th box 110-n, and the n-th box 110-n By analyzing the air, it is possible to determine whether the nth electronic equipment 100-n has a failure symptom.

Here, at least one of the plurality of boxes 110-1, 110-2, and 110-n may be additionally provided to detect signs of failure of electronic equipment in an existing process facility. In addition, at least one of the plurality of boxes 110-1, 110-2, and 110-n may be a box prepared in advance according to characteristics of existing process equipment to detect signs of failure of electronic equipment. For example, a process facility subject to electronic equipment failure symptom detection may be a semiconductor processing facility, and at least some processes in the semiconductor processing facility may be configured to be performed inside a closed or vacuum clean room. At least one of the plurality of boxes 110-1, 110-2, and 110-n may mean a clean room.

Analysis of air inside at least one of the plurality of boxes 110-1, 110-2, and 110-n may be performed by, for example, one analyzer 200. As exemplarily shown in FIG. 6 , an air measurement box 210 may be provided in a process facility, and an analyzer 200 may be mounted inside the air measurement box 210 .

Air inside at least one of the plurality of boxes 110-1, 110-2, and 110-n may be circulated to the air measurement box 210 through corresponding air circulation pipes, respectively, and each air circulation pipe Air inside any one of the plurality of boxes 110-1, 110-2, and 110-n is circulated into the air measuring box 210 based on the opening/closing units provided in the box 210 and is analyzed by the analyzing device 200. can be made

In other words, the air circulation pipe and the air circulation motor 220 are used to detect malfunctions or abnormal signs of the plurality of electronic equipments 100-1, 100-2, and 100-n using one analysis device 200. can be used Each detection target box (110-1, 110-2, 110-n) is equipped with an automatic opening and closing device for the air circulation pipe individually, so that only one box is subject to air when analyzed through the central analysis device (200). analysis can be performed. That is, the plurality of boxes 110-1, 110-2, and 110-n may each have an air circulation pipe and an automatic opening/closing device, and opening only the automatic opening/closing device for one box at the moment of air analysis Therefore, it is possible to analyze only the air within the corresponding box.

For example, to properly control the electric opening/closing units 10a and 10b and the air circulation motor 220 for the first box 110-1 to perform analysis on the first electronic equipment 100-1 As a result, the air inside the first box 110-1 can be transferred to the air measurement box 210 through the first input air circulation pipe 101a-1 and analyzed by the analyzer 200, It is returned to the first box 110-1 through the one-output air circulation pipe 101b-1 and removed from the inside of the air measuring box 210, and can be prepared for performing air analysis on other electronic equipment.

In addition, by appropriately controlling the electric opening/closing units 20a, 20b and the air circulation motor 220 for the second box 110-2 to perform analysis on the second electronic equipment 100-2. , the air inside the second box 110-2 is delivered to the air measurement box 210 through the second input air circulation pipe 101a-2 and can be analyzed by the analyzer 200, and the second output It is returned to the second box 110-2 through the air circulation pipe 101b-2 and removed from the inside of the air measuring box 210, and can be prepared to perform air analysis on other electronic equipment.

Similarly, by appropriately controlling the electric opening/closing units 30a and 30b and the air circulation motor 220 for the nth box 110-n to perform analysis on the nth electronic equipment 100-n , the air inside the nth box 110-n is delivered to the air measuring box 210 through the nth input air circulation pipe 101a-n and can be analyzed by the analyzer 200, and the nth output It is returned to the nth box 110-n through the air circulation pipe 101n-1, removed from the inside of the air measurement box 210, and can be prepared for performing air analysis on other electronic equipment.

The analysis device 200 may include, for example, a communication module 230, and information on air analysis results performed by the analysis device 200 may be transmitted to the server 300 through a wired or wireless network. there is. Server 300 can be implemented by any computing device. According to one aspect, server 300 can be a sensor data collection and analysis server.

The information on the air analysis result by the analysis device 200 and/or the failure sign detection result of at least one of the electronic equipment by the server 300 may be output by the control monitor 400 . In addition, the information on the air analysis result by the analysis device 200 and/or the failure sign detection result for at least one of the electronic equipment by the server 300 are transmitted to the manager device 500 through wired or wireless communication. It is possible to enable the manager of the process facility to easily acquire monitoring information. According to one aspect of the present invention, a server 300 that determines whether a failure symptom of electronic equipment has occurred based on data from the analysis device 200, and a control monitor that transmits and receives information with the server 300 through wired or wireless communication ( 400) and/or the manager device 500, it is possible to construct an analysis and inquiry system for electronic equipment, a notification system, and an interlocking control system.

Fig. 7 is a block diagram showing an exemplary configuration of the analysis device of Fig. 6; As shown in FIG. 7 , the analysis device 200 according to one aspect of the present invention includes an air component sensor 251, an air density sensor 253, an air temperature sensor 255, a humidity sensor 257 or smoke detection. At least one of the sensors 259 may be provided. For example, the server 300 compares the measured air component with the normal air component based on the information on the air component measured by the air component sensor 251 of the analyzer 200 to determine the electronic From the current state of the equipment, it is possible to determine whether any indications of failure have occurred. In addition, it is possible to determine whether a fault symptom occurs by further considering at least some of detected values, such as at least one of density, temperature, humidity, and smoke. Here, the analysis device 200 may convert a measurement value measured by at least one sensor and transmit the converted measurement value to the server 300 using a wired or wireless network or other communication means.

The server 300 may analyze the collected detection values by use and purpose to monitor and report an abnormal situation in real time. Using the analyzed abnormal symptom data, it is possible to interlock so that the corresponding process related to the electronic equipment in which the symptom of failure is detected, a process before and after, or a related process that may be a problem can be automatically controlled.

In addition, by using the detected data, big data analysis technology and artificial intelligence (AI) can be applied to improve the quality of accurate anomaly detection and interlock and automate control by anomalies.

Hereinafter, a method for detecting a failure symptom for at least one electronic equipment based on air analysis according to an embodiment of the present invention will be described in more detail with reference to configurations of exemplary process equipment and monitoring systems.

Air analysis-based electronic equipment failure symptom detection method

1 is a flowchart of a method for detecting a failure symptom for at least one electronic device based on air analysis according to an embodiment of the present invention. Hereinafter, with reference to FIG. 1 , a method for detecting a failure symptom for at least one electronic device based on air analysis according to an embodiment of the present invention will be described in more detail. A method according to an embodiment of the present invention may be performed by any computing device including a processor and a memory. The computing device may be, for example, the server 300 as shown in FIG. 6, and although the method is exemplarily described below by the server 300, any computing device may be used in an embodiment of the present invention. Note that the following method can be performed.

In addition, as described above with reference to FIG. 6, at least one electronic equipment (100-1, 100-2, 100-n) is at least one box (110-1, 110-2, 110-n) n) can be configured to be mounted inside each.

According to one aspect of the present invention, the electronic equipment to be detected for whether or not a failure symptom occurs is at least one of an Electronic Control Unit (ECU), a Printed Circuit Board (PCB), or an electronic circuit board. It may include, but is not limited to. In addition, the electronic equipment to be detected may be, but is not limited to, semiconductor equipment in a semiconductor process or electronic equipment included in an industrial product manufacturing production facility.

As shown in FIG. 1 , a method for detecting a failure symptom for at least one electronic device based on air analysis according to an embodiment of the present invention includes air analysis information about air inside a box in which the electronic device is mounted. It includes obtaining (step 100) and determining whether a failure symptom has occurred based on the normal state information and the obtained air analysis information (step 200).

More specifically, as shown in FIG. 1 , the server 300 may acquire air analysis information on air inside a box in which electronic equipment is mounted (step 100). More specifically, air analysis information based on information measured by the analysis device 200 of FIG. 6 may be received through a wired or wireless network, for example.

Here, the air analysis information may include sensor-based measurement values of characteristics of air inside the box. As exemplarily described above with reference to FIG. 6 , the air component sensor 251, the air density sensor 253, the air temperature sensor 255, the humidity sensor 257 or the smoke included in the analysis device 200 Sensor measurement values measured by at least one of the detection sensors 259 may be included in the air analysis information.

More specifically, the air analysis information may include information about components of air inside a box in which electronic equipment to be analyzed is mounted. In addition, according to one aspect, the air analysis information may further include measurement information on at least one of air density, temperature, humidity, and whether or not smoke is generated in the air inside the box in which the electronic equipment to be analyzed is mounted.

Referring back to FIG. 1 , the server 300 determines whether a failure symptom occurs for the electronic equipment based on normal state information including air analysis information when the electronic equipment is in a normal state and the obtained air analysis information. (Step 200) Yes.

For example, in detecting signs of failure of electronic equipment included in process equipment in advance, resistance or heat is generated when at least some components or certain parts of the electronic equipment are corroded or contaminants are fused according to process equipment and other production environments An abnormal situation may occur in electronic equipment, such as burning or melting of a circuit, and malfunction of electronic equipment does not occur immediately, but if the situation continues, it may reach a dangerous level to the extent that malfunction of electronic equipment occurs. For example, in a situation in which the electronic equipment reaches a dangerous level, the electronic equipment may diffuse certain chemical components or other substances that change the characteristics of the air, or heat into the air inside the box in which the electronic equipment is mounted. Therefore, air condition information when the electronic equipment is in a normal state, eg, air component information, is compared with air analysis information about the electronic equipment obtained at the time of detection, eg, air component information. By doing so, it is possible to determine whether a failure or an abnormal symptom has occurred in the electronic equipment.

According to one aspect of the present invention, when a predetermined first component is detected in the air inside a box in which electronic equipment to be detected is mounted, it may be determined that a failure symptom of the corresponding electronic equipment has occurred. Alternatively, it may be determined that a failure symptom has occurred for the corresponding electronic equipment in response to a determination that the density or concentration of the second predetermined component in the air exceeds the first predetermined threshold. In addition, at least one or a plurality of combination conditions among analysis of various air components, air density, air temperature, humidity, and smoke generation may be set, and when the corresponding conditions are met, it may be determined that a failure symptom for the electronic equipment has occurred. In addition, a set criterion for determining the occurrence of a symptom of a failure may be configured differently according to the type of electronic equipment to be detected. For example, setting criteria for determining occurrence of different failure symptoms may be configured for each of the first type ECU, the second type ECU, the first type electronic circuit board, and the second type electronic circuit board.

Meanwhile, as described above with reference to FIG. 6 , it is possible for one analysis device 200 to obtain air analysis information for detecting whether or not a failure symptom occurs for two or more electronic devices. In relation to this, at least one electronic device to be detected according to an aspect of the present invention is, for example, the first electronic device 100-1 mounted in the first box 110-1 as shown in FIG. ) and a second electronic equipment 100-2 mounted on a second box 110-2 different from the first box.

Here, the step of obtaining the air analysis information as shown in FIG. 1 (step 100) is the air analysis of the air inside any one of the first box 110-1 or the second box 110-2. It can be configured to obtain information, and the step of determining whether a failure symptom has occurred as shown in FIG. 1 (step 200) is, among the first electronic equipment 100-1 or the second electronic equipment 100-2 It can be configured to determine whether a failure symptom has occurred for either one.

To this end, for example, as described with reference to FIG. 6, a sensor-based measurement value that may be included in the air analysis information is obtained by at least one sensor mounted on at least one air measuring box 210, Based on the first air circulation pipes 101a-1 and 101b-1 between the first box 110-1 and the air measuring box 210, the air inside the first box 110-1 is transferred to the air measuring box ( 210) may be configured to cycle. In addition, the air inside the second box 110-2 is measured based on the second air circulation pipes 101a-2 and 101b-2 between the second box 110-2 and the air measuring box 210. It can be configured to cycle to box 210.

Here, the step of acquiring the air analysis information as shown in FIG. 1 (step 100) includes the first motorized opening and closing units 10a, 10b provided in the first air circulation pipe or the first air circulation pipe provided in the second air circulation pipe. By controlling at least one of the two motorized opening/closing units 20a and 20b, the air inside any one of the first box 110-1 or the second box 110-2 is circulated to the air measuring box 210. can make it happen

Referring back to FIG. 1 , the method according to an embodiment of the present invention further includes transmitting information about the electronic equipment having a failure symptom among the first electronic equipment and the second electronic equipment to the manager device (step 300). can include For example, the server 300 may notify the manager device 500 based on a wired or wireless communication network when determining that a failure symptom is detected for the first electronic equipment 100-1. Therefore, the manager of the electronic equipment can more quickly recognize the fact that a failure symptom has occurred in any one of the electronic equipment.

According to one aspect of the present invention, a method according to an embodiment of the present invention relates to a first electronic equipment and a second electronic equipment in a semiconductor equipment in a semiconductor process or in a manufacturing facility for manufacturing a manufactured product. The method may further include changing control settings for at least one of the first process, processes before and after the first process, or processes related to the first process (step 400).

For example, if the server 300 determines that a failure symptom has occurred with respect to the first electronic equipment 100-1, for example, the server 300 automatically sets a control for a process associated with the first electronic equipment 100-1. can be configured to change.

A process of a semiconductor process or other manufacturing production facility may consist of a combination of a plurality of sub-processes. For example, the entire process may include sequential processes consisting of process A, process B, process C, process D, and process S, process T, and process U, respectively. Here, process T may be configured to be performed only when it is confirmed whether process B normally proceeds, or the speed of process T may be determined in association with the speed of process B.

In such an exemplary process, for example, when a failure symptom is detected for the first electronic equipment 100-1 associated with process B, the server 300 performs an example for process B, which is a process related to the electronic equipment. It may be configured to automatically change control settings, such as stopping process B or slowing down process B. In addition, the server 300 may automatically change control settings for at least one of process A and/or process C, which is a preceding process of process B, or process D. Furthermore, the server 300 can automatically change control settings for process T, which is a process related to process B. That is, according to one aspect of the present invention, the corresponding process, the before and after process, or the related process that may be a problem can be automatically controlled using the analyzed anomaly symptom data.

On the other hand, according to one aspect of the present invention, the air analysis-based determination of whether a failure symptom occurs for electronic equipment may be performed using artificial intelligence (AI). That is, it is possible to determine whether or not a failure symptom occurs in electronic equipment using an artificial neural network.

In relation to this, FIG. 2 is a flowchart of an example of artificial neural network-based determination in the step of determining whether a failure symptom occurs in FIG. 1, and FIG. 8 is a conceptual diagram of an artificial neural network-based failure symptom prediction model according to an aspect of the present invention.

According to an embodiment of the present invention, as shown in FIG. 2 , determining whether a failure symptom has occurred (step 200) includes generating a failure symptom occurrence determination model (step 210) and whether or not a failure symptom has occurred. An operation 220 of outputting whether or not a symptom of failure of the electronic equipment has occurred based on the decision model may be included.

First, as shown in FIG. 2 , an artificial neural network may be trained based on a plurality of training data sets to generate a failure symptom determination model (step 210). As shown in FIG. 8 , when air component information is input, an artificial neural network 700 may be trained to output whether or not an anomaly symptom occurs according to the air component information, and a model for determining whether a malfunction symptom occurs may be generated. Here, among a plurality of learning data for training the artificial neural network 700, each training data set is a sample including air component information, air density information, air temperature information, humidity information, and smoke generation information. Air analysis information may be included as an input value, and whether a malfunction symptom labeled with respect to the sample air analysis information may be included as an output value.

For example, such a training data set includes air analysis information for electronic equipment to be analyzed - at least one of air component information, air density information, air temperature information, humidity information, and smoke generation information according to one aspect. Including the above - is repeatedly obtained at predetermined time intervals to accumulate air analysis information for a plurality of time points, and when a failure occurs in the corresponding electronic equipment, the air analysis information at a preceding time point for a predetermined length of time from the point of failure is collected. It can be secured by taking out. For example, air analysis information at a time point preceding by a predetermined period length from the time of failure corresponds to sample air analysis information, and whether a failure symptom occurs for this corresponds to a label value indicating 'occurrence' (eg, occurrence of abnormal symptoms It is possible to secure a training data set so that it can be labeled as '1' for abnormal symptoms and '0' for non-occurrence of anomalies). By securing a plurality of training data sets and training the artificial neural network, it is possible to improve the detection accuracy of whether or not abnormal symptoms occur in the model for determining whether or not a malfunction symptom occurs.

Referring back to FIG. 2 , by inputting the air analysis information obtained at the time of the detection target into the learned failure symptom determination model, whether or not a failure symptom occurs for the electronic equipment to be detected can be output (step 220). there is.

According to another embodiment of the present invention, it is possible to determine whether a failure symptom occurs in the electronic equipment based on an optical analysis of the air inside the box in which the electronic equipment to be analyzed is mounted.

In relation to this, FIG. 3 is a flowchart of an example of optical analysis-based determination in the step of determining whether a failure symptom occurs in FIG. 1 , and FIG. 9 illustrates an exemplary configuration for optical analysis-based failure symptom generation determination according to an aspect of the present invention. indicate

First, as shown in FIG. 9 , according to an aspect of the present invention, at least one box 110 in which at least one electronic equipment 100 is mounted includes a light that outputs an optical signal into the box 110. An output port 910 and an optical input port 920 receiving an optical signal output from the optical output port may be provided.

Here, the step of obtaining the air analysis information as shown in FIG. 1 (step 100) is, as shown in FIG. 3, the optical signal output from the optical output port 910 and the optical signal received from the optical input port 920 Air analysis information may be obtained using the optical signal (step 230). For example, the optical output port 910 may be configured to always output an optical signal of uniform intensity, and in a normal state, an optical signal having an intensity lower than that of an optical signal received at the optical input port 920 is an optical signal. When received at the input port 920, it can be determined that a failure symptom has occurred in the target electronic equipment. Alternatively, the optical analysis device 900 of FIG. 9 may be a spectrum analyzer, and the spectrum of the optical signal received from the optical input port 920 in a normal state and the spectrum of the optical signal received at the time of analysis are higher than a predetermined standard. When it is determined that they are different, it may be determined that a failure symptom is detected in the electronic equipment.

According to another embodiment of the present invention, it is possible to determine whether or not a failure symptom occurs in the electronic equipment based on an image analysis of the air inside the box in which the electronic equipment is mounted.

In relation to this, FIG. 4 is a flowchart of an example of image analysis-based determination in the step of determining whether a failure symptom occurs in FIG. 1 , and FIG. 10 is an exemplary configuration for image analysis-based failure symptom determination according to an aspect of the present invention. indicates

First, as shown in FIG. 10, according to an aspect of the present invention, at least one box 110 in which at least one electronic equipment 100 is mounted is configured to obtain image data for air inside the box. An image information acquisition device 1110 may be provided.

Here, in the step of obtaining air analysis information as shown in FIG. 1 (step 100), air analysis information is obtained based on analyzing image data of the air inside the box obtained as shown in FIG. 4 (Step 240) Yes. For example, image information about the inside of the box 110 obtained by the image information acquisition device 1110 is transmitted to the image analysis device 1100, and the image analysis device 1100 determines the box for the normal state of the electronic equipment. By comparing the internal image with the image at the time of measurement, it is possible to determine whether or not a failure symptom occurs in the electronic equipment. Such image analysis may be performed, for example, based on changes in air components or densities, but is not limited thereto. The image information acquisition device 1110 may be configured to acquire an ultra-micron magnified image, for example. In addition, by learning an artificial neural network based on a plurality of video images and a plurality of learning data sets labeled with the corresponding failure symptom occurrence, and inputting the detection point image to the learned artificial neural network, whether or not the failure symptom of the electronic equipment has occurred It may also be configured to determine.

11 is a block diagram illustrating the configuration of an exemplary computing system in which a method according to an embodiment of the present invention may be performed. Referring to FIG. 8 , a computing system 800 may include a flash storage 810 , a processor 820 , a RAM 830 , an input/output device 840 and a power supply 850 . In addition, the flash storage 810 may include a memory device 811 and a memory controller 812 . Meanwhile, although not shown in FIG. 8 , the computing system 800 may further include ports capable of communicating with video cards, sound cards, memory cards, USB devices, etc., or with other electronic devices. .

Computing system 800 may be implemented as a personal computer or as portable electronic equipment such as a notebook computer, a mobile phone, a personal digital assistant (PDA), and a camera.

Processor 820 can perform certain calculations or tasks. Depending on the embodiment, the processor 820 may be a micro-processor or a central processing unit (CPU). The processor 820 communicates with the RAM 830, the input/output device 840, and the flash storage 810 through a bus 860 such as an address bus, a control bus, and a data bus. communication can be performed. Flash storage 810 can be implemented using the flash storage of the embodiments shown in FIGS. 5-7 .

According to one embodiment, the processor 820 can also be coupled to an expansion bus, such as a Peripheral Component Interconnect (PCI) bus.

The RAM 830 may store data necessary for the operation of the computing system 800 . Any type of random access memory including, for example, DRAM, mobile DRAM, SRAM, PRAM, FRAM, MRAM, RRAM, RAM (830).

The input/output device 840 may include input means such as a keyboard, keypad, and mouse, and output means such as a printer and a display. The power supply 850 can supply an operating voltage necessary for the operation of the computing system 800 .

The method according to the present invention described above may be implemented as computer readable codes on a computer readable recording medium. Computer-readable recording media includes all types of recording media in which data that can be decoded by a computer system is stored. For example, there may be read only memory (ROM), random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in computer systems connected through a computer communication network, and stored and executed as readable codes in a distributed manner.

Although the above has been described with reference to the drawings and examples, it does not mean that the scope of protection of the present invention is limited by the drawings or examples, and those skilled in the art will understand the scope of the present invention described in the claims below. It will be understood that various modifications and changes may be made to the present invention without departing from the spirit and scope.

Specifically, the described features may be implemented within digital electronic circuitry, or within computer hardware, firmware, or combinations thereof. Features may be implemented in a computer program product embodied within storage, eg, in a machine-readable storage device, for execution by a programmable processor. And features can be performed by a programmable processor executing a program of instructions to perform the functions of the described embodiments by operating on input data and generating output. The described features include at least one programmable processor, at least one input device, and at least one output device coupled to receive data and instructions from and to transmit data and instructions to the data storage system. It can be executed within one or more computer programs that can be executed on a programmable system including. A computer program contains a set of instructions that can be used directly or indirectly within a computer to perform a particular action for a given result. A computer program is written in any programming language, including compiled or interpreted languages, and contained as modules, components, subroutines, or other units suitable for use in other computer environments, or as stand-alone programs. can be used in any form.

Suitable processors for execution of a program of instructions include, for example, both general and special purpose microprocessors, and either a single processor or multiple processors in a computer of another kind. Also, storage devices suitable for embodying computer program instructions and data embodying the described features include, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic memory devices such as internal hard disks and removable disks. devices, magneto-optical disks and all forms of non-volatile memory including CD-ROM and DVD-ROM disks. The processor and memory may be integrated within or added by ASICs (application-specific integrated circuits).

Although the present invention described above has been described based on a series of functional blocks, it is not limited by the above-described embodiments and the accompanying drawings, and various substitutions, modifications, and changes are made within the scope of the technical spirit of the present invention. That this is possible will be apparent to those skilled in the art.

Combinations of the above-described embodiments are not limited to the above-described embodiments, and various types of combinations may be provided as well as the above-described embodiments according to implementation and/or needs.

In the foregoing embodiments, the methods are described on the basis of a flow chart as a series of steps or blocks, but the present invention is not limited to the order of steps, and some steps may occur in a different order or concurrently with other steps as described above. there is. In addition, those skilled in the art will understand that the steps shown in the flow chart are not exclusive, that other steps may be included, or that one or more steps of the flow chart may be deleted without affecting the scope of the present invention. You will understand.

The foregoing embodiment includes examples of various aspects. It is not possible to describe all possible combinations to represent the various aspects, but those skilled in the art will recognize that other combinations are possible. Accordingly, it is intended that the present invention cover all other substitutions, modifications and variations falling within the scope of the following claims.

Claims (10)

A method of detecting a failure symptom for at least one electronic equipment based on air analysis, wherein the at least one electronic equipment is configured to be mounted inside at least one box, the method being performed by a computing device, the method comprising: silver,
Acquiring air analysis information on air inside a box in which electronic equipment is mounted, wherein the air analysis information includes sensor-based measurement values of characteristics of air inside the box; and
Determining whether a failure symptom occurs for the electronic equipment based on normal state information including air analysis information when the electronic equipment is in a normal state and the obtained air analysis information, detection method.
According to claim 1,
The air analysis information,
A method for detecting signs of failure of electronic equipment, including information about components of air inside a box in which electronic equipment to be analyzed is mounted.
According to claim 2,
The air analysis information,
A method for detecting signs of failure of electronic equipment, further comprising measurement information on at least one of air density, temperature, humidity, and whether or not smoke is generated in the air inside the box in which the electronic equipment to be analyzed is mounted.
According to claim 1,
The electronic equipment,
At least one of an Electronic Control Unit (ECU), a Printed Circuit Board (PCB), or an electronic circuit board;
A method for detecting signs of failure of electronic equipment, which is electronic equipment included in semiconductor equipment in a semiconductor process or industrial product manufacturing production facilities.
According to claim 4,
The at least one electronic device includes a first electronic device mounted on a first box and a second electronic device mounted on a second box different from the first box,
The obtaining of the air analysis information is configured to obtain air analysis information on air inside any one of the first box and the second box,
Wherein the determining whether a failure symptom has occurred is configured to determine whether a failure symptom has occurred in any one of the first electronic device and the second electronic device.
According to claim 5,
The sensor-based measurements are obtained by at least one sensor mounted on at least one air measurement box;
Based on a first air circulation pipe between the first box and the air measuring box, the air inside the first box is circulated to the air measuring box, and the second air pipe between the second box and the air measuring box is configured to circulate. Based on the air circulation pipe, the air inside the second box is configured to circulate to the air measuring box,
The obtaining of the air analysis information may include controlling at least one of a first electric opening and closing unit included in the first air circulation pipe and a second electric opening and closing unit included in the second air circulation pipe. A method for detecting signs of failure of electronic equipment, wherein air inside the box or the second box is circulated to the air measuring box.
According to claim 6,
The method,
transmitting information about an electronic device having a failure symptom among the first electronic device and the second electronic device to a manager device; and
A first process related to the electronic equipment in which a failure symptom occurs among the first electronic equipment and the second electronic equipment in semiconductor equipment in a semiconductor process or industrial product manufacturing production facility, a process before and after the first process, or a process of the first process A method for detecting signs of failure of electronic equipment, comprising the step of changing control settings for at least one of the associated processes.
According to claim 3,
The step of determining whether the failure symptom occurs,
A plurality of learning data sets - Each learning data set includes sample air analysis information including air component information, air density information, air temperature information, humidity information, and smoke generation information as an input value, and the sample generating a model for determining whether a failure symptom occurs by learning an artificial neural network based on - including as an output value whether or not a failure symptom has been labeled for the air analysis information; and
outputting whether or not a failure symptom occurs for the electronic equipment by inputting the obtained air analysis information into the failure symptom occurrence determination model; Including, a method for detecting signs of failure of electronic equipment.
According to claim 1,
At least one box in which the at least one electronic device is mounted has an optical output port for outputting an optical signal into the box and an optical input port for receiving an optical signal output from the optical output port;
The obtaining of the air analysis information may include obtaining the air analysis information using an optical signal output from the optical output port and an optical signal received from the optical input port.
According to claim 1,
At least one box in which the at least one electronic equipment is mounted has an image information acquisition device configured to acquire image data of air inside the box,
Wherein the obtaining of the air analysis information comprises obtaining the air analysis information based on analyzing the acquired image data of the air inside the box.