CN115907348A - Method, device and equipment for detecting and controlling quality of polycrystalline silicon product - Google Patents
Method, device and equipment for detecting and controlling quality of polycrystalline silicon product Download PDFInfo
- Publication number
- CN115907348A CN115907348A CN202211375667.0A CN202211375667A CN115907348A CN 115907348 A CN115907348 A CN 115907348A CN 202211375667 A CN202211375667 A CN 202211375667A CN 115907348 A CN115907348 A CN 115907348A
- Authority
- CN
- China
- Prior art keywords
- data
- preset
- cpk
- rule
- judgment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a method, a device and equipment for detecting and controlling the quality of a polycrystalline silicon product, and relates to the technical field of polycrystalline silicon production detection, wherein the method comprises the following steps: periodically acquiring detection data obtained by detecting the content of preset impurities at preset detection points; acquiring a process capability index (CPK) corresponding to the preset detection point according to the detection data, and constructing a mean range diagram; obtaining data abnormity judgment information and/or an output result of data abnormity reasons according to the mean range diagram and the CPK; and according to the output result, carrying out local tuning treatment on the equipment parameters corresponding to the preset detection point. The embodiment of the application realizes real-time detection and control of product quality, improves the yield, greatly shortens the time from problem finding to problem solving, is favorable for reducing the cost caused by the product quality problem, and ensures the stability of the operation of the whole system.
Description
Technical Field
The application relates to the technical field of polycrystalline silicon production detection, in particular to a method, a device and equipment for detecting and controlling the quality of a polycrystalline silicon product.
Background
In the existing polycrystalline silicon production process, the adjustment of process parameters is realized by collecting relevant data, manually sorting and analyzing the collected data, formulating and transmitting formulated measures to operators to adjust partial parameters, and for a polycrystalline silicon production system, when data is detected to be abnormal through off-line detection, manual intervention is carried out, so that the first time of abnormal occurrence is passed, only after-control can be carried out, and the problems of quality loss cost and system stability cannot be timely reduced.
Based on the defects of the problems, an on-line monitoring and control system for the quality of polysilicon products is needed to be developed.
Disclosure of Invention
The technical purpose to be achieved by the embodiment of the application is to provide a method, a control device and equipment for detecting and controlling the quality of a polycrystalline silicon product, which are used for solving the problem of hysteresis in monitoring and adjusting process parameters in the current polycrystalline silicon production process.
In order to solve the above technical problem, an embodiment of the present application provides a method for detecting and controlling quality of a polycrystalline silicon product, including:
periodically acquiring detection data obtained by detecting the content of preset impurities at preset detection points;
acquiring a Process capability index (CPK for short) corresponding to the preset detection point according to the detection data, and constructing a mean range diagram;
obtaining data abnormity judgment information and/or an output result of data abnormity reasons according to the mean range diagram and the CPK;
and according to the output result, carrying out local tuning treatment on the equipment parameters corresponding to the preset detection point.
Specifically, the method for acquiring the CPK corresponding to the preset detection point according to the detection data and constructing a mean range diagram includes:
substituting the detection data into a preset data model corresponding to the preset detection point, wherein a preset number of data bits are arranged in the preset data model, and the data bits are arranged according to a time sequence;
obtaining the CPK according to the data in the preset data model and predetermined design parameters corresponding to the preset detection point, and constructing the mean range diagram, wherein the design parameters at least comprise: an upper control limit, a lower control limit, an upper specification limit, a lower specification limit, and a target value.
Specifically, the obtaining of the data abnormality judgment information and/or the output result of the data abnormality cause according to the mean range diagram and the CPK according to the method described above includes:
obtaining a target CPK interval corresponding to the preset data model according to the CPK;
judging different rules according to the mean range control diagram to obtain a judgment result of whether the mean range diagram meets at least one different judgment rule;
and when the target CPK interval is a preset CPK interval and/or the judgment result meets at least one judgment rule, determining that the data abnormity judgment information is data abnormity, otherwise, determining that the data abnormity judgment information is data abnormity.
Further, the method as described above, when it is determined that the data abnormality determination information is data abnormality, further includes:
determining an abnormal reason corresponding to the preset data model according to the target CPK interval, the judgment rule met by the mean range diagram and a preset judgment comparison table, wherein the judgment comparison table comprises: and the average extreme difference control chart comprises a corresponding relation between each judgment rule in the judgment rules of the average extreme difference control chart and at least two preset CPK intervals and the abnormal reason.
Specifically, as described above, in the mean range diagram, the mean range diagram is divided into a region C, a region B, and a region a in sequence symmetrically from the center line according to the number of total standard deviations; the average range control chart judgment rule comprises the following steps:
a first rule of discriminant: 1 point falls outside zone a;
a second discriminant rule: 9 consecutive points fall on the same side of the centerline;
the third rule of discriminant: 6 successive points increment or decrement;
the fourth rule of discriminant: adjacent points in the continuous 14 points are alternately arranged up and down;
a fifth discriminant rule: 2 points of the continuous 3 points fall outside the B area on the same side of the central line;
a sixth rule of discriminant: 4 of the 5 continuous points fall outside the C area on the same side of the central line;
a seventh discriminant rule: 15 continuous points fall within the C area on both sides of the central line;
the eighth discriminant rule: the continuous 8 points lie on either side of the centerline and none are in zone C.
Preferably, in the method as described above, the predetermined detection point includes at least one of a cold hydrogenation rough separation column line, a high-boiling cracking recovery line, a refined material line, a high-low boiling recovery column line and a chlorosilane reduction recovery line.
Preferably, in the method as described above, the preset impurities are: phosphorus or a metal impurity.
Still another embodiment of the present application provides a control apparatus including:
the first processing module is used for periodically acquiring detection data obtained by detecting the content of the preset impurities at preset detection points;
the second processing module is used for acquiring the CPK corresponding to the preset detection point according to the detection data and constructing a mean range diagram;
the third processing module is used for obtaining data abnormity judgment information and/or an output result of data abnormity reasons according to the mean range diagram and the CPK;
and the fourth processing module is used for carrying out local optimization processing on the equipment parameters corresponding to the preset detection points according to the output result.
Yet another embodiment of the present application further provides an apparatus comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method of polysilicon product quality detection and control as described above.
Still another embodiment of the present application further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of polysilicon product quality detection and control as described above.
Compared with the prior art, the method, the device and the equipment for detecting and controlling the quality of the polycrystalline silicon product provided by the embodiment of the application have at least the following beneficial effects:
this application is through acquireing the detection data that preset detection point detected in real time, and through asking for the mode of CPK and the extremely poor picture of the mean value of structure, obtain the output result of data abnormal judgment information and/or the different reasons of data, and carry out relevant equipment parameter local optimization according to the output result is automatic, the real-time detection and the control to product quality have been realized, the yields has been improved, the time from finding the problem to solving the problem has been reduced greatly, be favorable to reducing the cost because of the product quality problem brings, and guarantee the stability of entire system operation.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting and controlling the quality of a polysilicon product according to the present application.
FIG. 2 is a diagram of a mean range plot.
Fig. 3 is a schematic structural diagram of the control device of the present application.
Detailed Description
To make the technical problems, technical solutions and advantages to be solved by the present application clearer, the following detailed description is made with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to facilitate a thorough understanding of embodiments of the present application. Accordingly, it will be apparent to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present application, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.
Referring to fig. 1, an embodiment of the present application provides a method for detecting and controlling quality of a polycrystalline silicon product, including:
and S101, periodically acquiring detection data obtained by detecting the content of the preset impurities at preset detection points. In this step, the predetermined preset detection point is detected with respect to the preset impurity content, and the detection data is obtained, so as to facilitate the subsequent data processing. In an embodiment, the preset detection point includes, but is not limited to, at least one of a cold hydrogenation rough fractionation tower pipeline, a high-boiling cracking recovery pipeline, a refined material pipeline, a high-low boiling recovery tower pipeline, and a reduction recovery chlorosilane pipeline, and is respectively used for detecting preset impurity contents corresponding to the cold hydrogenation rough distillation process, the cold hydrogenation high-boiling cracking process, the rectification refined material process, and the high-low boiling recovery process, wherein the product quality of the polycrystalline silicon product can be represented by the preset impurity contents. Specifically, since impurities in the polycrystalline silicon product include: in a specific embodiment, the predetermined impurity is preferably at least one of simple substances of carbon (C), oxygen (O), boron (B), phosphorus (P), iron (Fe), aluminum (Al), zinc (Zn), chromium (Cr), gold (Au), copper (Cu), magnesium (Mg), sulfur (S), silver (Ag), tin (Sn), lead (Pb), antimony (Sb), titanium (Ti), and compounds thereof, and is preferably higher in content and easier to detect: phosphorus (P) or a metal impurity (e.g., iron (Fe), aluminum (Al), etc.) in order to improve detection efficiency.
And S102, acquiring the CPK corresponding to the preset detection point according to the detection data, and constructing a mean range diagram. In this step, after the detection data is obtained, the CPK corresponding to the preset detection point at present is obtained based on the detection data, and a mean range diagram is constructed according to the detection data, so as to integrate the CPK and the mean range diagram to determine whether the data is abnormal and/or determine the reason of the abnormality.
And step S103, obtaining data abnormity judgment information and/or an output result of the data abnormity reason according to the mean range diagram and the CPK. In this step, whether data abnormality exists in the current detection point can be judged based on the CPK and the mean value range diagram to obtain data abnormality judgment information, and further, a reason for the data abnormality in case of the data abnormality can be determined, so that equipment corresponding to the detection point can be adjusted, and normal operation of the whole production line can be ensured.
And step S104, carrying out local optimization processing on the equipment parameters corresponding to the preset detection point according to the output result. In this step, local tuning is performed on the device parameters corresponding to the preset detection point according to the data abnormality judgment information and/or the abnormality reason carried in the output result, so as to realize real-time adjustment on production. Specifically, when the data abnormality judgment information carried in the output result is abnormal, the specific step of the local tuning processing is not processing; when the data abnormality judgment information indicates that abnormality exists, optimizing the corresponding equipment parameters according to the corresponding abnormality reason, for example, under the condition that the preset detection point is a refining material pipeline, the equipment parameters of the rectifying tower can be optimized, for example: at least one of the column temperature, the column pressure, the reflux ratio, and the like is adjusted. In one embodiment, the optimization process is also performed with reference to current equipment parameters and production parameters.
To sum up, this application is through the detection data that acquires in real time and predetermine the check point and detect to through the mode of asking CPK and the extremely poor picture of construction mean value, obtain the output result of the unusual reason of data abnormal judgement information and/or data, and carry out relevant equipment parameter local tuning automatically according to the output result and handle, realized real-time detection and control to product quality, improved the yields, reduced the time from finding the problem to solving the problem greatly, be favorable to reducing the cost because of product quality problem brings, and guarantee the stability of entire system operation.
Specifically, the method for obtaining the process capability index CPK corresponding to the preset detection point according to the detection data and constructing the mean range diagram includes:
and substituting the detection data into a preset data model corresponding to the preset detection point, wherein a preset number of data bits are arranged in the preset data model, and the data bits are arranged according to a time sequence. In this step, to meet the requirement of the subsequent acquisition of the CPK and the construction of the mean range diagram on the data amount, the detection data is substituted into a preset data model with a preset number of data bits, and the data bits are replaced in the preset data model according to the time sequence, specifically, the data structure includes, but is not limited to, a sequence queue and a circular queue. The predetermined number of data bits in one implementation is at least 25 to improve the accuracy, representation, and precision of the processed data.
Obtaining the CPK according to the data in the preset data model and the predetermined design parameters corresponding to the preset detection point, and constructing the mean range diagram, wherein the design parameters at least comprise: an upper control limit, a lower control limit, an upper specification limit, a lower specification limit, and a target value. The method comprises the following steps of firstly obtaining the total standard deviation of the quality characteristic value distribution corresponding to a preset data model, specifically obtaining each data in the preset data model as a sample, and also presetting the total standard deviation;
and then solving a corresponding CPK according to a preset CPK calculation formula, wherein the CPK calculation formula is as follows:
wherein USL is the upper specification limit value, LSL is the lower specification limit value, and M is the target value; and sigma is the total standard deviation, and mu is the average value of all detection data in a preset data model.
Meanwhile, a mean range diagram is constructed according to data in a preset data model and design parameters.
Specifically, the obtaining of the data abnormality judgment information and/or the output result of the data abnormality cause according to the mean range diagram and the CPK according to the method described above includes:
obtaining a target CPK interval corresponding to the preset data model according to the CPK;
judging different rules according to the mean range control diagram to obtain a judgment result of whether the mean range diagram meets at least one different judgment rule;
and when the target CPK interval is a preset CPK interval and/or the judgment result meets at least one abnormality judgment rule, determining that the data abnormality judgment information is data abnormality, otherwise, determining that the data abnormality judgment information is data abnormality.
In a specific implementation of the present application, when obtaining an output result according to the mean range diagram and the CPK, the determination of the data anomaly determination information is preferentially performed, that is, whether data anomaly exists currently is determined according to at least one of the mean range diagram and the CPK. Specifically, the process of determining according to the CPK is as follows: determining a target CPK interval corresponding to the obtained CPK according to the obtained CPK, and determining that data abnormality exists when the target CPK interval is a preset CPK interval, where it should be noted that the preset CPK interval includes: CPK is less than 1 and 1 is not less than 1.33.
The process of judging according to the mean range diagram is as follows: and judging whether the positions of the points in the mean range diagram meet at least one abnormal judgment rule or not according to the abnormal judgment rule of the mean range control diagram, and determining that data abnormality exists when the positions meet the at least one abnormal judgment rule. It should be noted that, as shown in fig. 2, in the mean range diagram, the mean range diagram is divided into a region C, a region B and a region a symmetrically from a Center Line (CL) in sequence according to the number of total standard deviations, wherein the center line is a target value in the design parameter, and boundaries of the region a away from the center line are an upper control limit value (UCL) and a lower control limit value (LCL) in the design parameter, respectively; the average range control chart judgment rule comprises the following steps:
a first rule of discriminant: 1 point falls outside zone a;
the second rule of discriminant: 9 consecutive points fall on the same side of the centerline;
the third rule of discriminant: 6 successive points increment or decrement;
the fourth rule of discriminant: adjacent points in the continuous 14 points are alternately arranged up and down;
a fifth rule of exception judgment: 2 points in the continuous 3 points fall outside the B area on the same side of the central line;
a sixth rule of discriminant: 4 of the 5 continuous points fall outside the C area on the same side of the central line;
a seventh discriminant rule: 15 continuous points fall within the C area on both sides of the central line;
the eighth discriminant rule: the 8 consecutive points lie on either side of the centerline and none are in zone C.
The data abnormity judgment information is obtained through the two different judgment modes, and the accuracy of the obtained data abnormity judgment information is guaranteed.
Further, as described above, in a case where it is determined that the data abnormality determination information is data abnormality, the method further includes:
determining an abnormal reason corresponding to the preset data model according to the target CPK interval, a target abnormality judgment rule met by the mean range diagram and a preset abnormality judgment comparison table, wherein the abnormality judgment comparison table comprises: and the mean range extreme control chart comprises a corresponding relation between each judgment rule in the judgment rules of the mean range extreme control chart and the CPK interval and the abnormal reason.
In another embodiment of the present application, when the cause of the data abnormality needs to be determined, a difference determination comparison table is configured in advance, in the difference determination comparison table, the mean range deviation control chart difference determination rule and/or the CPK interval is used as the cause, and the corresponding cause of the abnormality is used as the result and is corresponded. In one embodiment: when the mean range diagram meets the third abnormality judgment rule, the cause of the abnormality can be preliminarily determined to be insufficient maintenance level of the process system, and then further determination is performed according to the target CPK interval, for example, if the target CPK interval is that CPK is less than 1, the specific cause is insufficient capacity of the process system, and if the target CPK interval is that CPK is greater than 1, the specific cause is other causes in the third abnormality judgment rule. In another embodiment, in the case that the criterion of the extreme difference mean control diagram is not satisfied but belongs to the preset PK interval, the determination may be performed only according to the target CPK interval, when the target CPK interval is CPK < 1, the specific reason is the parameter setup problem, and if the target CPK interval is CPK > 1, the specific reason is the human operation reason.
It should be noted that the CPK interval in the discrimination comparison table includes other intervals besides the preset CPK interval, for example: CPK is more than or equal to 1.33 and less than or equal to 1.67, CPK is more than or equal to 1.67, or CPK is more than or equal to 1.33.
Wherein CPK < 1 indicates abnormality and needs to be improved;
1 ≦ CPK < 1.33 indicates normal, but there is a risk;
1.33 ≦ CPK indicates Normal, more specifically, 1.33 ≦ CPK < 1.67 indicates Normal can continue to remain, and 1.67 ≦ CPK indicates Normal, which may relax the test appropriately.
In practical applications, the steps of the method may be executed separately for each predetermined detection point, or the steps of the method may be executed as a whole after merging data detected by a plurality of predetermined detection points.
Referring to fig. 3, still another embodiment of the present application further provides a control apparatus including:
the first processing module 301 is configured to periodically obtain detection data obtained by detecting a content of a preset impurity at a preset detection point;
a second processing module 302, configured to obtain a CPK corresponding to the preset detection point according to the detection data, and construct a mean range diagram;
a third processing module 303, configured to obtain data anomaly determination information and/or an output result of a data anomaly reason according to the mean range diagram and the CPK;
a fourth processing module 304, configured to perform local tuning processing on the device parameter corresponding to the preset detection point according to the output result.
Specifically, as for the control device, the second processing module includes:
the first processing unit is used for substituting the detection data into a preset data model corresponding to the preset detection point, a preset number of data bits are arranged in the preset data model, and the data bits are arranged according to a time sequence;
a second processing unit, configured to obtain the CPK according to data in the preset data model and predetermined design parameters corresponding to the preset detection point, and construct the mean range diagram, where the design parameters at least include: an upper control limit, a lower control limit, an upper specification limit, a lower specification limit, and a target value.
Specifically, as for the control device, the third processing module includes:
the third processing unit is used for obtaining a target CPK interval corresponding to the preset data model according to the CPK;
the fourth processing unit is used for judging the abnormal rules according to the mean range control diagram to obtain a judgment result of whether the mean range diagram meets at least one abnormal rule;
a fifth processing unit, configured to determine that the data anomaly determination information is a data anomaly when the target CPK interval is a preset CPK interval and/or the determination result satisfies at least one anomaly determination rule, and otherwise, determine that the data anomaly determination information is a data anomaly.
Further, the control device as described above, when it is determined that the data abnormality determination information is a data abnormality, further includes:
a sixth processing unit, configured to determine an abnormal reason corresponding to the preset data model according to the target CPK interval, the difference judgment rule that is satisfied by the mean range diagram, and a preset difference judgment comparison table, where the difference judgment comparison table includes: and the mean range extreme control chart comprises a corresponding relation between each judgment rule in the judgment rules of the mean range extreme control chart and the CPK interval and the abnormal reason.
Specifically, the control device described above, in the mean range diagram, divides the mean range diagram into a C region, a B region, and an a region in order symmetrically from a center line, which is a target value in the design parameter, according to the number of total standard deviations; the mean range control chart abnormity judging rule comprises the following steps:
a first rule of discriminant: 1 point falls outside zone a;
the second rule of discriminant: 9 consecutive points fall on the same side of the centerline;
the third rule of discriminant: 6 successive points increment or decrement;
the fourth rule of discriminant: adjacent points in the continuous 14 points are alternately arranged up and down;
a fifth rule of exception judgment: 2 points of the continuous 3 points fall outside the B area on the same side of the central line;
a sixth rule of discriminant: 4 of the 5 continuous points fall outside the C area on the same side of the central line;
a seventh discriminant rule: 15 continuous points fall within the C area on both sides of the central line;
the eighth exception judgment rule: the continuous 8 points lie on either side of the centerline and none are in zone C.
Preferably, as the control device, the preset detection point includes at least one of a cold hydrogenation rough separation tower line, a high-boiling cracking recovery line, a refined material line, a high-low boiling recovery tower line and a chlorosilane reduction recovery line.
Preferably, in the control device as described above, the preset impurities are: phosphorus or a metal impurity.
The control device of the invention is a device corresponding to the embodiment of the method for detecting and controlling the quality of the polysilicon product, and all the implementation means in the embodiment of the method are suitable for the embodiment of the device, and the same technical effect can be achieved.
Yet another embodiment of the present application also provides an apparatus comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method for polysilicon product quality inspection and control as described above.
Still another embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the method for polysilicon product quality detection and control as described above.
Further, the present application may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion.
While the foregoing is directed to the preferred embodiment of the present application, it will be appreciated by those skilled in the art that various changes and modifications may be made therein without departing from the principles of the application, and it is intended that such changes and modifications be covered by the appended claims.
Claims (10)
1. A method for detecting and controlling the quality of a polycrystalline silicon product is characterized by comprising the following steps:
periodically acquiring detection data obtained by detecting the content of preset impurities at preset detection points;
acquiring a process capability index (CPK) corresponding to the preset detection point according to the detection data, and constructing a mean range diagram;
obtaining data abnormity judgment information and/or an output result of data abnormity reasons according to the mean range diagram and the CPK;
and carrying out local optimization processing on the equipment parameters corresponding to the preset detection point according to the output result.
2. The method according to claim 1, wherein the obtaining a process capability index (CPK) corresponding to the preset detection point according to the detection data and constructing a mean range diagram comprises:
substituting the detection data into a preset data model corresponding to the preset detection point, wherein a preset number of data bits are arranged in the preset data model, and the data bits are arranged according to a time sequence;
obtaining the CPK according to the data in the preset data model and the predetermined design parameters corresponding to the preset detection point, and constructing the mean range diagram, wherein the design parameters at least comprise: an upper control limit, a lower control limit, an upper specification limit, a lower specification limit, and a target value.
3. The method according to claim 1, wherein obtaining data anomaly determination information and/or an output result of a data anomaly cause according to the mean range diagram and the CPK comprises:
obtaining a target CPK interval corresponding to the preset data model according to the CPK;
judging an anomaly rule according to a mean range control diagram to obtain a judgment result of whether the mean range diagram meets at least one anomaly judgment rule;
and when the target CPK interval is a preset CPK interval and/or the judgment result meets at least one abnormality judgment rule, determining that the data abnormality judgment information is data abnormality, otherwise, determining that the data abnormality judgment information is data abnormality.
4. The method according to claim 3, wherein in a case where it is determined that the data abnormality determination information is that there is a data abnormality, the method further comprises:
determining an abnormal reason corresponding to the preset data model according to the target CPK interval, the judgment rule met by the mean range diagram and a preset judgment comparison table, wherein the judgment comparison table comprises: and the average extreme difference control chart comprises a corresponding relation between each judgment rule in the judgment rules of the average extreme difference control chart and at least two preset CPK intervals and the abnormal reason.
5. The method according to claim 3 or 4, wherein in the mean range diagram, the mean range diagram is divided into a region C, a region B and a region A in sequence symmetrically from the center line according to the number of overall standard deviations; the average range control chart judgment rule comprises the following steps:
a first rule of discriminant: 1 point falls outside zone a;
the second rule of discriminant: 9 consecutive points fall on the same side of the centerline;
the third rule of discriminant: 6 successive points increment or decrement;
a fourth discriminant rule: adjacent points in each continuous 14 points are alternately arranged up and down;
a fifth rule of exception judgment: 2 points in the continuous 3 points fall outside the B area on the same side of the central line;
a sixth rule of discriminant: 4 of the 5 continuous points fall outside the C area on the same side of the central line;
a seventh discriminant rule: 15 continuous points fall within the C area on both sides of the central line;
the eighth exception judgment rule: the continuous 8 points lie on either side of the centerline and none are in zone C.
6. The method of claim 1, wherein the predetermined detection point comprises at least one of a cold hydrogenation rough separation column line, a high-boiling cracking recovery line, a refined feed line, a high-low boiling recovery column line, and a reduction recovery chlorosilane line.
7. The method according to claim 1, characterized in that the predetermined impurities are: phosphorus or a metal impurity.
8. A control device, characterized by comprising:
the first processing module is used for periodically acquiring detection data obtained by detecting the content of preset impurities at preset detection points;
the second processing module is used for acquiring the CPK corresponding to the preset detection point according to the detection data and constructing a mean range diagram;
the third processing module is used for obtaining data abnormity judgment information and/or an output result of data abnormity reasons according to the mean range diagram and the CPK;
and the fourth processing module is used for carrying out local tuning and optimizing processing on the equipment parameters corresponding to the preset detection points according to the output result.
9. An apparatus comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the method of polysilicon product quality inspection and control of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for polysilicon product quality inspection and control according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211375667.0A CN115907348A (en) | 2022-11-04 | 2022-11-04 | Method, device and equipment for detecting and controlling quality of polycrystalline silicon product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211375667.0A CN115907348A (en) | 2022-11-04 | 2022-11-04 | Method, device and equipment for detecting and controlling quality of polycrystalline silicon product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115907348A true CN115907348A (en) | 2023-04-04 |
Family
ID=86488779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211375667.0A Pending CN115907348A (en) | 2022-11-04 | 2022-11-04 | Method, device and equipment for detecting and controlling quality of polycrystalline silicon product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907348A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952523A (en) * | 2024-03-27 | 2024-04-30 | 成都思越智能装备股份有限公司 | Method, device, equipment and storage medium for monitoring and early warning of trolley of stereoscopic warehouse |
-
2022
- 2022-11-04 CN CN202211375667.0A patent/CN115907348A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952523A (en) * | 2024-03-27 | 2024-04-30 | 成都思越智能装备股份有限公司 | Method, device, equipment and storage medium for monitoring and early warning of trolley of stereoscopic warehouse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110263494B (en) | Alumina production operation optimization system and method based on cloud edge cooperation | |
| CN115907348A (en) | Method, device and equipment for detecting and controlling quality of polycrystalline silicon product | |
| CN109365769B (en) | Crystallizer bleed-out forecasting method based on mixed model judgment | |
| CN110991916A (en) | Casting blank quality judgment system and method | |
| CN108256260A (en) | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine | |
| CN116991130A (en) | Intelligent automatic control system and method for petrochemical production | |
| CN112232703A (en) | Casting blank quality determination method and system | |
| CN112250538B (en) | Isopropyl benzene refining process flow | |
| CN104977847B (en) | A kind of steady state condition method of discrimination optimized towards Atmospheric vacuum | |
| US7916140B2 (en) | Method and a system for operating a controllable multi-variable process | |
| NO347531B1 (en) | A method for using an anode rod's equidistant voltage drop to predict anode power | |
| CN113240244A (en) | Automatic casting blank grading judgment method suitable for tracking steel-making production | |
| CN108364095A (en) | Molten steel quality diagnosis method in steelmaking production process based on data mining | |
| CN117670051A (en) | Unmanned urban and rural water supply operation and maintenance analysis system | |
| CN107121490A (en) | The evaluation method of running status in a kind of hydrometallurgy process | |
| CN112446645A (en) | Power management service system based on Internet of things | |
| CN108681579A (en) | A kind of big data missing rate analysis method | |
| CN114841277A (en) | Method and system for predicting yield of converter tapping alloy | |
| CN113487126A (en) | Dynamic detection method for unqualified product | |
| CN1322862A (en) | Aluminium electrolyzing production control system | |
| CN115301731B (en) | Equidistant rolling method for spiral conical rollers of large-size titanium alloy bars | |
| CN117217098B (en) | Steel pipe mechanical property prediction method and device based on digital twin and deep learning | |
| CN116976148B (en) | Method and system for monitoring ion content change in copper electrolysis process | |
| CN113198838B (en) | Target convexity early warning method and system for hot continuous rolling strip steel and industrial control equipment | |
| CN111488922B (en) | Intermediate blank camber classification identification and quality judgment method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |