A method and apparatus for detecting an improperly mounted wafer

Abstract

The application discloses a method and device for detecting abnormally installed wafers, which comprises the following steps: collecting temperature data of temperature sensors arranged on each baking unit of a wafer track device within a fixed time period; taking the temperature data of the temperature sensors in each baking unit as a management unit to calculate a virtual temperature parameter data; and calculating and analyzing the abnormally installed wafers according to the virtual temperature parameter data calculated by each management unit. The application takes each baking unit as a management unit, generates a virtual temperature parameter data according to the temperature data of the temperature sensors on each baking unit, and sets the standard deviation of the temperature data by interlocking, so that each baking unit only transmits a virtual temperature parameter data, thereby greatly reducing the amount of data to be transmitted subsequently; and the interlocking between the management units is realized, thereby reducing the installation of the interlocking quantity setting.

Description

Technical Field

[0001] This invention relates to the field of semiconductor manufacturing technology, and specifically to a method and apparatus for detecting abnormally mounted wafers. Background Technology

[0002] In semiconductor lithography, due to variations in the baking unit's operation, and to address issues such as wafer misalignment due to wafer overlap and poor wafer quality caused by particle fabrication, an initial stabilization interlock is established for the baking unit. The temperature sensor's variation amplitude varies depending on the wafer displacement and particle position, allowing for interlocking based on different temperature sensors. For example, with 60 or more baking units, each equipped with 15 temperature sensors, there are over 900 (60*15=900) parameters. Monitoring these parameters and implementing interlocks between sensors is necessary for detection, and installing a large number of interlocks significantly increases costs.

[0003] Therefore, although some sensor interlocks have been installed, the large number of parameters means that installing a large number of interlocks will significantly increase costs. At the same time, transmitting the parameter data of each sensor to the central server for calculation is time-consuming and increases transmission time, resulting in longer management-level program processing and operation time. Summary of the Invention

[0004] The technical problem to be solved by this invention is that in the prior art, temperature sensors are installed on each baking unit of the track equipment, and the central server performs subsequent calculations and analyses by monitoring the parameter data of each temperature sensor. This results in a large amount of temperature data transmission, which is time-consuming. At the same time, the interlocking between sensors leads to a significant increase in costs.

[0005] The purpose of this invention is to provide a method and apparatus for detecting abnormally mounted wafers. Each baking unit is treated as a management unit. A virtual temperature parameter is generated based on temperature data from several (e.g., 15) temperature sensors on each baking unit for management. The standard deviation of these 15 temperature data points is set using an interlock. In the photolithography process of semiconductor manufacturing, the temperature sensor on the wafer carrier disk collects temperature data every second. During the wafer baking process on the wafer carrier disk, a range is defined where the maximum value minus the minimum value. If a wafer carrier disk senses 15 temperature ranges (TempRange), the equipment calculates this data as 1 sigma. The factory's interlock control system transmits the wafer carrier disk's DATA as a single data point. Each baking unit transmits only one virtual temperature parameter, significantly reducing the amount of data transmitted subsequently. Furthermore, interlocking between management units greatly reduces the number of interlocks required, resulting in shorter management-level program processing and operation times.

[0006] This invention is achieved through the following technical solution:

[0007] In a first aspect, the present invention provides a method for detecting improperly mounted wafers, the method comprising:

[0008] Temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment are collected within a fixed time period. The temperature data from several temperature sensors in each baking unit are used as a management unit to calculate and generate a virtual temperature parameter data.

[0009] Based on the virtual temperature parameter data calculated by each management unit, abnormally installed wafers are calculated and analyzed.

[0010] The baking unit is located on a wafer track device, and a wafer track device has multiple baking units.

[0011] Furthermore, the temperature data from the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range, where Range = Temp Max – Temp Min.

[0012] Furthermore, the virtual temperature parameter data is set in a value through an interlocking mechanism using the standard deviation of temperature data from several temperature sensors in each baking unit; wherein, the calculation formula for the virtual temperature parameter data is:

[0013] BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ...]

[0014] In the formula, BT represents the virtual temperature parameter data generated by a management unit; (AS Max–AS Min), (BS Max–BS Min), (CS Max–C Min), … represent the corresponding X values ​​in the standard deviation calculation formula. i The standard deviation of Xi can be calculated using the existing standard deviation calculation formula; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

[0015] For example, if each baking unit is equipped with 15 temperature sensors, then the virtual temperature parameter data is calculated based on these 15 temperature data. BT = standard deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ..., (OS Max – OS Min)], where (AS Max – AS Min) represents the relevant data of the first temperature sensor, (BS Max – BS Min) represents the relevant data of the second temperature sensor, and so on, with (OS Max – OS Min) representing the relevant data of the fifteenth temperature sensor.

[0016] The existing formula for calculating standard deviation is: X i Take the corresponding value from (AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ..., (OS Max – OS Min).

[0017] Furthermore, the various management units are interlocked.

[0018] Furthermore, an equal number of temperature sensors are arranged on each baking unit, with several temperature sensors evenly distributed from the center to the outer corner of the baking unit.

[0019] Furthermore, the calculation and analysis of abnormally installed wafers based on the virtual temperature parameter data obtained from each management unit includes:

[0020] Based on the virtual temperature parameter data calculated by each management unit, calculation and analysis are performed on the wafer track equipment to obtain abnormally installed wafers.

[0021] Alternatively, the virtual temperature parameters calculated by each management unit can be transmitted to a central server, which will then perform calculations and analysis to identify abnormally installed wafers.

[0022] Secondly, the present invention also provides a detection device for abnormally mounted wafers, which supports the aforementioned method for detecting abnormally mounted wafers, and the device includes:

[0023] The acquisition unit is used to collect temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment within a fixed time period.

[0024] The virtual temperature parameter data generation unit is used to calculate and generate a virtual temperature parameter data by taking the temperature data of several temperature sensors in each baking unit as a management unit; each management unit generates a corresponding virtual temperature parameter data.

[0025] The calculation and analysis unit is used to calculate and analyze abnormally installed wafers based on the virtual temperature parameter data obtained from each management unit.

[0026] Furthermore, the temperature data from the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range, where Range = Temp Max – Temp Min.

[0027] Furthermore, the virtual temperature parameter data is set in a value through an interlocking mechanism using the standard deviation of temperature data from several temperature sensors in each baking unit; wherein, the calculation formula for the virtual temperature parameter data is:

[0028] BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ...]

[0029] In the formula, BT represents the virtual temperature parameter data generated by a management unit; (AS Max–AS Min), (BS Max–BS Min), (CS Max–C Min), … represent the corresponding Xi in the standard deviation calculation formula; the standard deviation of Xi can be calculated using the existing standard deviation calculation formula; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

[0030] Furthermore, the various management units are interlocked.

[0031] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0032] The method and apparatus of this invention treat each baking unit as a management unit. It manages the baking process by generating a virtual temperature parameter based on temperature data from several (e.g., 15) temperature sensors on each unit. The standard deviation of these 15 temperature data points is set using an interlock. In the photolithography process of semiconductor manufacturing, the temperature sensor on the wafer carrier disk collects temperature data every second. During the baking process on the wafer carrier disk, a range is defined where the maximum value minus the minimum value. If a wafer carrier disk senses 15 temperature ranges (TempRange), the equipment calculates this data as 1 sigma. The factory's interlock control system transmits the DATA of the wafer carrier disk as a single data point. Each baking unit transmits only one virtual temperature parameter, significantly reducing the amount of data transmitted subsequently. Furthermore, interlocking between management units greatly reduces the number of interlocks required, resulting in shorter management-level program execution time and shorter operation time. Attached Figure Description

[0033] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0034] Figure 1 This is a flowchart of a method for detecting improperly mounted wafers according to the present invention.

[0035] Figure 2 Analysis of the implementation of the method for detecting abnormally mounted wafers according to the present invention. Figure 1

[0036] Figure 3 Analysis of the implementation of the method for detecting abnormally mounted wafers according to the present invention. Figure 2 .

[0037] Figure 4 This invention utilizes the difference in Range values ​​between wafers with abnormal positioning and wafers with normal positioning to detect abnormal patterns.

[0038] Figure 5 This is a structural diagram of a detection device for abnormally mounted wafers according to the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0040] Example 1

[0041] like Figures 1 to 4As shown, the present invention provides a method for detecting improperly mounted wafers, such as... Figure 1 As shown, the method includes:

[0042] Temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment are collected within a fixed time period. The temperature data from several temperature sensors in each baking unit are used as a management unit to calculate and generate a virtual temperature parameter data.

[0043] Based on the virtual temperature parameter data calculated by each management unit, abnormally installed wafers are calculated and analyzed.

[0044] The baking unit is set on a wafer track device, and a wafer track device has multiple baking units; each baking unit is equipped with an equal number of temperature sensors, and the temperature sensors are evenly distributed from the center to the outer corner of the baking unit; a wafer is mounted on the baking unit, and the temperature sensors are located below the wafer.

[0045] When the wafer is installed in the baking unit, according to Figure 2 Left side Figure 1 It is installed normally on the baking unit. Figure 2 In the diagram on the left, "Normal Wafer Position" represents the normal wafer position, and the corresponding Real temp (actual temperature) directly below "Normal Wafer Position"; "Abnormal Wafer Position" represents the abnormal wafer position, and the corresponding Real temp (actual temperature) directly below "Abnormal Wafer Position". Figure 2 The graph on the right shows the temperature variation by plate area in abnormal wafer position, indicating the temperature change in the baking unit plate area at the abnormal wafer location. The entire wafer must maintain a uniform temperature; otherwise, temperature differences may lead to defects. In this embodiment of the invention, the baking temperature used in the photolithography process of semiconductor manufacturing is controlled within the range of 50 to 400 degrees Celsius, depending on the product type.

[0046] To further illustrate this embodiment, the temperature data of the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range, where Range = Temp Max – Temp Min.

[0047] To further illustrate this embodiment, the virtual temperature parameter data is set using the standard deviation of temperature data from several temperature sensors in each baking unit in an interlocked manner; wherein, the calculation formula for the virtual temperature parameter data is:

[0048] BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ...]

[0049] In the formula, BT represents the virtual temperature parameter data generated by a management unit; (AS Max–AS Min), (BS Max–BS Min), (CS Max–C Min), … represent the corresponding X values ​​in the standard deviation calculation formula. i The standard deviation of Xi can be calculated using the existing standard deviation calculation formula; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

[0050] For example, if each baking unit has 15 temperature sensors, then the virtual temperature parameter data is calculated based on these 15 temperature data. BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ..., (OS Max – OS Min)], where (AS Max – AS Min) represents the relevant data of the first temperature sensor in the baking unit, (BS Max – BS Min) represents the relevant data of the second temperature sensor in the baking unit, and so on, with (OS Max – OS Min) representing the relevant data of the fifteenth temperature sensor in the baking unit.

[0051] The existing formula for calculating standard deviation is: X i Take the corresponding value from (AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ..., (OS Max – OS Min).

[0052] To further illustrate this embodiment, the various management units are interlocked. In the prior art, interlocking is used between temperature sensors, and then 15 temperature sensors are installed on each baking unit. For 98 baking units, this would require a large number of interlocks, significantly increasing costs. Therefore, this invention treats the temperature data from several temperature sensors in each baking unit as a single management unit, achieving interlocking between these units. Specifically, the standard deviation of the temperature data from several temperature sensors in each baking unit is used to set values ​​in an interlocking manner. This significantly reduces the installation of interlocking devices and saves costs.

[0053] To further illustrate this embodiment, the calculation and analysis of abnormally installed wafers based on virtual temperature parameter data obtained from each management unit includes:

[0054] Based on the virtual temperature parameter data calculated by each management unit, calculation and analysis are performed on the wafer track equipment to obtain abnormally installed wafers.

[0055] Alternatively, the virtual temperature parameters calculated by each management unit can be transmitted to a central server, which will then perform calculations and analysis to identify abnormally installed wafers.

[0056] In existing technologies, the baking process typically lasts 60 seconds. Each temperature sensor in the wafer track equipment measures the temperature every 1 second, and the measurement data is stored in the equipment's log system. The equipment only stores temperature data and does not perform the calculations and analyses required by this invention. The average value is calculated based on the parameter data provided by each temperature sensor during the process. Generally, 25 wafers (1 lot) are processed, and the average value calculated for each wafer is used to calculate the "average temperature," "maximum temperature," and "minimum temperature" of that lot of wafers.

[0057] The calculation method used in this invention is to subtract the minimum value from the maximum value of the data stored during each sensor processing, and the resulting value is called Range. (Temp Max – Temp.Min = Range). A wafer at 23°C is placed tightly against the plate in a baking unit at temperatures above 80°C. If the wafer's positioning is abnormal, the temperature drop will be small. Figure 4 As shown, this invention utilizes the difference in Range values ​​between wafers with abnormal positioning and wafers with normal positioning to detect abnormalities.

[0058] Specifically, such as Figure 3As shown, ① if a wafer at 23 degrees Celsius is installed in the baking unit, the temperature will return to the set standard after being lowered. ② However, as... Figure 3 As shown, if the wafer is not properly mounted, the temperature variations on the left and right sides of the wafer will be different. ③ As Figure 3 The left side shows the part where the wafer contacts the baking unit. Compared to the part on the right where they don't contact, the temperature drops significantly before returning to the set temperature value. ④ Normal and abnormal conditions are calculated using the data generated above. ⑤ In existing technology, 15 temperature data points are individually placed outside the device and transmitted via Servo for calculation. ⑥ The baking unit is located on the wafer track device; generally, 98 baking units can be set on one device. ⑦ Data from the 15 temperature sensors of the 98 baking units can be transmitted to Servo in one second. ⑧ Generally, the baking process takes 60 seconds, so 88,200 (15*98*60) data points are transmitted to Servo during wafer processing. ⑨ To calculate this data, the capacity of Servo is increased, or the data transmission time is increased from 1 second to 2 seconds. ⑩ The calculations in the method of this invention are performed in the device. If only one data point of the baking unit is transmitted to the central Servo after the calculations are performed in the device, then only the data of 98 baking units needs to be transmitted. This invention can transmit data in the device, so calculations can also be performed in the device.

[0059] The working principle is as follows: This invention aims to provide a method and apparatus for detecting abnormally mounted wafers. Each baking unit is treated as a management unit. A virtual temperature parameter is generated based on temperature data from several (e.g., 15) temperature sensors on each baking unit for management. The standard deviation of the 15 temperature data is set using an interlock. In the photolithography baking process of semiconductor manufacturing, the temperature sensor on the wafer carrier disk collects temperature data once per second. During the wafer baking process on the wafer carrier disk, a range is defined where the maximum value minus the minimum value. If a wafer carrier disk senses 15 temperature ranges (TempRange), the equipment will calculate this data as 1 sigma. The factory's interlock control system will transmit the DATA of the wafer carrier disk as a single data point. Each baking unit only transmits one virtual temperature parameter, thus significantly reducing the amount of data transmitted subsequently. Furthermore, interlocking between management units greatly reduces the number of interlocks required, resulting in shorter management-level program processing time and operation time.

[0060] In existing technologies, servers are required to manage the entire factory, while this invention only needs to be installed in the necessary parts of the equipment and baking units, thus reducing costs. Simultaneously, it reduces the number of parameters to be managed and the number of assumed interlocks, thereby reducing manufacturing time. Furthermore, this invention does not require additional hardware, allows for interlock installation, and simplifies parameter management by eliminating the need for additional parameters.

[0061] Example 2

[0062] like Figures 1 to 5 As shown, the difference between this embodiment and Embodiment 1 is that this embodiment provides a detection device for abnormally mounted wafers. This device supports the method for detecting abnormally mounted wafers described in Embodiment 1. The device includes:

[0063] The acquisition unit is used to collect temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment within a fixed time period.

[0064] The virtual temperature parameter data generation unit is used to calculate and generate a virtual temperature parameter data by taking the temperature data of several temperature sensors in each baking unit as a management unit; each management unit generates a corresponding virtual temperature parameter data.

[0065] The calculation and analysis unit is used to calculate and analyze abnormally installed wafers based on the virtual temperature parameter data obtained from each management unit.

[0066] To further illustrate this embodiment, the temperature data of the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range, where Range = Temp Max – Temp Min.

[0067] To further illustrate this embodiment, the virtual temperature parameter data is set using the standard deviation of temperature data from several temperature sensors in each baking unit in an interlocked manner; wherein, the calculation formula for the virtual temperature parameter data is:

[0068] BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ...]

[0069] In the formula, BT represents the virtual temperature parameter data generated by a management unit; (AS Max–AS Min), (BS Max–BS Min), (CS Max–C Min), … represent the corresponding Xi in the standard deviation calculation formula; the standard deviation of Xi can be calculated using the existing standard deviation calculation formula; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

[0070] For example, if each baking unit has 15 temperature sensors, then the virtual temperature parameter data is calculated based on these 15 temperature data. BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – C Min), ..., (OS Max – OS Min)], where (AS Max – AS Min) represents the relevant data of the first temperature sensor in the baking unit, (BS Max – BS Min) represents the relevant data of the second temperature sensor in the baking unit, and so on, with (OS Max – OS Min) representing the relevant data of the fifteenth temperature sensor in the baking unit.

[0071] To further illustrate this embodiment, the various management units are interlocked.

[0072] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for detecting improperly mounted wafers, characterized in that, The method includes: Temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment are collected within a fixed time period. Using the temperature data from several temperature sensors in each baking unit as a management unit, a virtual temperature parameter data is calculated and generated. Based on the virtual temperature parameter data calculated by each management unit, abnormally installed wafers are calculated and analyzed. The temperature data from the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range. The virtual temperature parameter data is set using the standard deviation of temperature data from several temperature sensors in each baking unit in an interlocked manner; wherein, the calculation formula for the virtual temperature parameter data is: BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – CS Min),…] In the formula, BT represents the virtual temperature parameter data generated by a management unit; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

2. The method for detecting abnormally mounted wafers according to claim 1, characterized in that, The various management units are interlocked.

3. The method for detecting improperly mounted wafers according to claim 1, characterized in that, Each baking unit is equipped with an equal number of temperature sensors, with some of the temperature sensors evenly distributed from the center to the outer corners of the baking unit.

4. The method for detecting abnormally mounted wafers according to claim 1, characterized in that, The method of calculating and analyzing abnormally installed wafers based on virtual temperature parameter data obtained from each management unit includes: Based on the virtual temperature parameter data calculated by each management unit, calculation and analysis are performed on the wafer track equipment to obtain abnormally installed wafers. Alternatively, the virtual temperature parameters calculated by each management unit can be transmitted to a central server, which will then perform calculations and analysis to identify abnormally installed wafers.

5. A detection device for abnormally mounted wafers, characterized in that, The device supports a method for detecting abnormally mounted wafers as described in any one of claims 1 to 4, and the device comprises: The acquisition unit is used to collect temperature data from several temperature sensors arranged on each baking unit of the wafer track equipment within a fixed time period. The virtual temperature parameter data generation unit is used to calculate and generate a virtual temperature parameter data by taking the temperature data of several temperature sensors in each baking unit as a management unit; each management unit generates a corresponding virtual temperature parameter data. The calculation and analysis unit is used to calculate and analyze abnormally installed wafers based on the virtual temperature parameter data obtained from each management unit. The temperature data from the temperature sensor refers to the maximum value minus the minimum value of the data stored during the baking process within a fixed time period. The resulting value is called the difference range. The virtual temperature parameter data is set using the standard deviation of temperature data from several temperature sensors in each baking unit in an interlocked manner; wherein, the calculation formula for the virtual temperature parameter data is: BT = Standard Deviation [(AS Max – AS Min), (BS Max – BS Min), (CS Max – CS Min),…] In the formula, BT represents the virtual temperature parameter data generated by a management unit; AS Max represents the maximum value of temperature sensor A in a management unit, and AS Min represents the minimum value of temperature sensor A in a management unit; BS Max represents the maximum value of temperature sensor B in a management unit, and BS Min represents the minimum value of temperature sensor B in a management unit; CS Max represents the maximum value of temperature sensor C in a management unit, and CS Min represents the minimum value of temperature sensor C in a management unit.

6. The detection device for abnormally mounted wafers according to claim 5, characterized in that, The various management units are interlocked.

Images