Intelligent production monitoring method for yttrium hydroxide and application

Abstract

The application discloses a kind of intelligent production monitoring method and application of yttrium hydroxide, belong to intelligent monitoring, comprising: S1, from the outlet of belt dryer yttrium hydroxide product is when, first NIR probe scanning forms downstream timestamp spectrogram;S2, server is positioned from downstream timestamp spectrogram and exports water hydroxyl combined frequency area first absorbance, yttrium hydroxide structure hydroxyl combined frequency area first absorbance and carbon-oxygen bond combined frequency area first absorbance, water hydroxyl combined frequency area first absorbance is recorded as A1, yttrium hydroxide structure hydroxyl combined frequency area first absorbance is recorded as B1, carbon-oxygen bond combined frequency area first absorbance is recorded as C1;S3, server is calculated by burning loss prediction formula burning loss prediction value;S4, server determines Y, if Y≤threshold value, then production continues, if Y>threshold value, output alarm instruction, stop production.The application ensures that the online product produced meets customer needs.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring, and in particular to an intelligent production monitoring method and application for yttrium hydroxide. Background Technology

[0002] The current production method for yttrium hydroxide is intermittent, with each process disconnected from the next. This intermittent production method results in batches of products with varying quality. As yttrium hydroxide is a raw material for electronic or medical products, unstable or substandard quality is highly detrimental to its subsequent use. To meet customer needs, the current quality control for yttrium hydroxide production involves testing the loss on ignition (LOI) of the final product (LOI refers to the percentage by mass of all volatile substances lost after a sample is burned under specified high-temperature conditions (e.g., 800°C or 1000°C)) to determine if the product meets customer requirements.

[0003] Due to the inherent defects of intermittent production, continuous production has become an industry requirement. However, in continuous production, how to control the products produced to meet customer requirements has become a challenge for the industry.

[0004] The above background information is provided to facilitate understanding of the present invention and is not intended to be publicly known technology disclosed to the general public prior to the application of this invention. Summary of the Invention

[0005] In view of the above-mentioned defects, the present invention provides a solution that aims to improve at least one of the problems mentioned in the background art.

[0006] The technical solution is: an intelligent production monitoring method for yttrium hydroxide, comprising:

[0007] S1, when the yttrium hydroxide product exiting the belt dryer passes through the first NIR probe, the first NIR probe scans and forms a downstream timestamp spectrum;

[0008] S2, the server locates and outputs the first absorbance of the water-hydroxy combination frequency region, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region, and the first absorbance of the carbon-oxygen bond frequency region from the downstream timestamp spectrum. The first absorbance of the water-hydroxy combination frequency region is recorded as A1, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region is recorded as B1, and the first absorbance of the carbon-oxygen bond frequency region is recorded as C1.

[0009] S3, the server calculates the predicted value of loss on ignition using the loss on ignition prediction formula, and the predicted value of loss on ignition is denoted as Y. The loss on ignition prediction formula is: Y = k + k1*A1 + k2*B1 + k3*C1, where k is a constant, k1 is the contribution coefficient of water hydroxyl groups to loss on ignition, k2 is the contribution coefficient of yttrium hydroxide structural hydroxyl groups to loss on ignition, and k3 is the contribution coefficient of carbon-oxygen bonds to loss on ignition.

[0010] S4, the server determines Y. If Y ≤ threshold, production continues; if Y > threshold, an alarm command is output to stop production.

[0011] This invention monitors yttrium hydroxide exiting the drying outlet of a continuous production line by installing a first NIR probe, thereby ensuring that the produced online products meet customer requirements.

[0012] Furthermore, it also includes:

[0013] S5, retrieve the upstream timestamp spectrum generated by the second NIR probe when the yttrium hydroxide product in S1 passes through the second NIR probe;

[0014] S6, the server locates and outputs the second absorbance of the water-hydroxyl combination region, the second absorbance of the yttrium hydroxide-structured hydroxyl combination region, and the second absorbance of the carbon-oxygen bond combination region from the upstream timestamp spectrum. The second absorbance of the water-hydroxyl combination region is denoted as A2, the second absorbance of the yttrium hydroxide-structured hydroxyl combination region is denoted as B2, and the second absorbance of the carbon-oxygen bond combination region is denoted as C2.

[0015] S7, the server determines and outputs the location of the anomaly on the production line based on A2, B2 and C2.

[0016] This invention also involves installing a second NIR probe in the continuous production drying process to monitor the crude product entering the drying process, identify the problem points where products do not meet customer quality requirements, and then precisely resolve the problems.

[0017] Furthermore, in S7, if A2 is not within the threshold, an abnormality is determined and output as to exist at the belt vacuum filter or the washing area; if B2 is not within the threshold, an abnormality is determined and output as to exist at the tubular reactor; if C2 is not within the threshold, an abnormality is determined and output as to exist at the tubular reactor; if A2, B2 and C2 are all within the threshold, an abnormality is determined and output as to exist at the belt dryer.

[0018] Furthermore, the application scenario of this intelligent production monitoring method for yttrium hydroxide is a production line for continuous production of yttrium hydroxide. This production line includes: a tubular reactor, a belt vacuum filter, a washing zone, and a belt dryer arranged in sequence. The filter belt passes through the belt vacuum filter, the washing zone, and the belt dryer respectively. A first monitoring point is set at the outlet of the belt dryer, and a first NIR probe is installed at the first monitoring point. A second monitoring point is set at the inlet of the belt dryer, and a second NIR probe is installed at the second monitoring point.

[0019] Furthermore, the time difference between the formation of the downstream timestamp spectrum and the upstream timestamp spectrum is the distance between the outlet and inlet of the belt dryer / the transmission speed of the filter belt.

[0020] Furthermore, the first NIR probe is a contact type, while the second NIR probe is a non-contact type.

[0021] Furthermore, in S3, the values ​​of k, k1, k2, and k3 are obtained in the following way:

[0022] S31. Collect yttrium hydroxide samples, with a sample size of no less than 100, denoted as N.

[0023] S32, use the first NIR probe to scan each yttrium hydroxide sample to obtain N modeling spectra;

[0024] S33, Use the loss on ignition detection method to obtain the true loss on ignition for each sample, and obtain N true loss on ignition values;

[0025] S34, Establish the correlation model: Use the spectral data from N modeling spectra as the X variable and the actual loss on ignition as the Y variable to generate a prediction model and obtain the values ​​of k, k1, k2, and k3.

[0026] The present invention also provides an electronic device.

[0027] The technical solution is: an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the intelligent production monitoring method for yttrium hydroxide as described above.

[0028] The invention also provides a computer-readable storage medium.

[0029] The technical solution is: a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the intelligent production monitoring method for yttrium hydroxide as described above.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0031] The first NIR probe of this invention is used to meet customers' quality requirements for yttrium hydroxide products and produce qualified products. By using the second NIR probe in conjunction with the first NIR probe, the abnormal points in the process that cause quality defects can be quickly identified, which facilitates process personnel to quickly solve problems and restore normal production. Attached Figure Description

[0032] Figure 1 This is an application scenario diagram of the present invention;

[0033] Figure 2 This is a flowchart of Embodiment 1 of the present invention;

[0034] Figure 3 This is a flowchart of Embodiment 2 of the present invention;

[0035] In the diagram: 1. Tubular reactor, 2. Filter belt, 3. Belt vacuum filter, 4. Washing zone, 5. Belt dryer, 6. First monitoring point, 7. Second monitoring point. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0038] Loss on ignition (LOI), a comprehensive indicator used to determine whether a product meets customer requirements, is currently tested using a precision balance. A certain amount of sample is weighed, placed in a pre-weighed muffle furnace, and heated at a specific temperature (e.g., 800°C) for 15-20 minutes. After cooling, the sample is weighed again, and the LOI is calculated based on the changes before and after heating. A smaller LOI indicates higher product quality, and vice versa. Because LOI cannot be directly obtained online using instruments such as optical instruments, it is currently impossible to monitor whether the produced products meet customer requirements in real time; it can only be determined manually after the products have been manufactured.

[0039] The inventors discovered that the loss on ignition (LOI) of yttrium hydroxide products is related to the water hydroxyl groups, the structural hydroxyl groups of yttrium hydroxide, and the carbon-oxygen bonds. Based on this, they indirectly achieved LOI prediction, thereby enabling real-time monitoring of whether the produced products meet customer requirements.

[0040] Please refer to Figure 1 , Figure 1 This is an application scenario diagram of the present invention, namely a schematic diagram of a production line for the continuous production of yttrium hydroxide.

[0041] Figure 1The continuous production line for yttrium hydroxide consists of a tubular reactor 1, a belt vacuum filter 3, a washing zone 4, and a belt dryer 5 arranged sequentially. The filter belt 2 serves as a conveyor belt, passing through the belt vacuum filter 3, the washing zone 4, and the belt dryer 5. In this invention, the initial yttrium hydroxide product from the continuous tubular reactor 1 is continuously spread on the filter belt 2. The filter belt 2 carries the initial yttrium hydroxide product into the belt vacuum filter 3 for filtration. After filtration, it enters the washing zone 4 to remove impurities. After washing, it enters the belt dryer 5 for drying, and after drying, the yttrium hydroxide product is obtained.

[0042] Example 1

[0043] Please refer to this again. Figure 1 and reference Figure 2 , Figure 2 This is a flowchart of this embodiment.

[0044] In this embodiment, a first monitoring point 6 is provided at the outlet of the belt dryer 5, and a first NIR probe is installed at the first monitoring point 6.

[0045] An intelligent production monitoring method for yttrium hydroxide includes:

[0046] S1, when the yttrium hydroxide product exiting the belt dryer passes through the first NIR probe, the first NIR probe scans and forms a downstream timestamp spectrum.

[0047] S2, the server locates and outputs the first absorbance of the water-hydroxy combination frequency region, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region, and the first absorbance of the carbon-oxygen bond frequency region from the downstream timestamp spectrum. The first absorbance of the water-hydroxy combination frequency region is denoted as A1, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region is denoted as B1, and the first absorbance of the carbon-oxygen bond frequency region is denoted as C1.

[0048] S3, the server calculates the predicted value of loss on ignition using the loss on ignition prediction formula, denoted as Y. The loss on ignition prediction formula is: Y = k + k1*A1 + k2*B1 + k3*C1, where k is a constant, k1 is the contribution coefficient of the aqueous hydroxyl group to the loss on ignition, k2 is the contribution coefficient of the yttrium hydroxide structural hydroxyl group to the loss on ignition, and k3 is the contribution coefficient of the carbon-oxygen bond to the loss on ignition.

[0049] S4, the server determines Y. If Y ≤ threshold, production continues; if Y > threshold, an alarm command is output to stop production.

[0050] In S3, the values ​​of k, k1, k2, and k3 are obtained in the following way:

[0051] S31. Collect yttrium hydroxide samples, with a sample size of no less than 100, denoted as N.

[0052] S32, use the first NIR probe to scan each yttrium hydroxide sample to obtain N modeling spectra.

[0053] S33, use the loss on ignition detection method to obtain the true loss on ignition for each sample, and obtain N true loss on ignition values.

[0054] S34. Establish a correlation model (i.e., the loss on ignition prediction formula): Spectral data from N modeling spectra (the first absorbance in the water hydroxyl combination frequency region, the first absorbance in the yttrium hydroxide structure hydroxyl combination frequency region, and the first absorbance in the carbon-oxygen bond combination frequency region) are used as X variables (i.e., A1, B1, C1), and the actual loss on ignition is used as Y variable. Generate a prediction model and obtain the values ​​of k, k1, k2, and k3.

[0055] S35. Use the first NIR probe to scan the new yttrium hydroxide sample to obtain the spectrum of the new yttrium hydroxide sample. Substitute A1, B1, and C1 of the spectrum of the new yttrium hydroxide sample into the loss on ignition prediction formula to obtain the predicted value of loss on ignition. Compare the predicted value of loss on ignition with the actual loss on ignition of the new yttrium hydroxide sample. If they are basically equal (within the allowable error range), it means that the model is correct. The values ​​of k, k1, k2, and k3 can be used for actual production monitoring.

[0056] In one or more specific embodiments of the present invention, in order to monitor more accurately, the first NIR probe is a contact type. The contact type NIR probe has a strong signal, is less affected by ambient light interference, and is convenient for controlling product quality.

[0057] Example 2

[0058] Although Example 1 can monitor online in real time whether the produced products meet customer requirements, it cannot find the reasons why the products do not meet the requirements, and cannot quickly and effectively solve the problems and resume production.

[0059] Please refer to this again. Figure 1 and reference Figure 3 , Figure 3 This is a flowchart of this embodiment.

[0060] In this embodiment, a first monitoring point 6 is provided at the outlet of the belt dryer 5, and a first NIR probe is installed at the first monitoring point 6. A second monitoring point 7 is provided at the inlet of the belt dryer 5, and a second NIR probe is installed at the second monitoring point 7.

[0061] An intelligent production monitoring method for yttrium hydroxide includes:

[0062] S1, when the yttrium hydroxide product exiting the belt dryer passes through the first NIR probe, the first NIR probe scans and forms a downstream timestamp spectrum.

[0063] S2, the server locates and outputs the first absorbance of the water-hydroxy combination frequency region, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region, and the first absorbance of the carbon-oxygen bond frequency region from the downstream timestamp spectrum. The first absorbance of the water-hydroxy combination frequency region is denoted as A1, the first absorbance of the yttrium hydroxide-structured hydroxy combination frequency region is denoted as B1, and the first absorbance of the carbon-oxygen bond frequency region is denoted as C1.

[0064] S3, the server calculates the predicted value of loss on ignition using the loss on ignition prediction formula, denoted as Y. The loss on ignition prediction formula is: Y = k + k1*A1 + k2*B1 + k3*C1, where k is a constant, k1 is the contribution coefficient of the aqueous hydroxyl group to the loss on ignition, k2 is the contribution coefficient of the yttrium hydroxide structural hydroxyl group to the loss on ignition, and k3 is the contribution coefficient of the carbon-oxygen bond to the loss on ignition.

[0065] S4, the server determines Y. If Y ≤ threshold, production continues. If Y > threshold, an alarm command is output, production stops, and the process proceeds to S5.

[0066] S5 retrieves the upstream timestamp spectrum generated by the second NIR probe when the yttrium hydroxide product in S1 passes through the second NIR probe.

[0067] This step retrieves the upstream timestamp spectrum of the yttrium hydroxide product scanned by the first NIR probe in S1 when it passes through the second NIR probe. The second NIR probe scans before the first NIR probe. In actual production, this time is the time before the first NIR probe scans. The time before the first NIR probe scans is the distance between the outlet and inlet of the belt dryer 5 / the transmission speed of the filter belt 2.

[0068] S6, the server locates and outputs the second absorbance of the water-hydroxy combination frequency region, the second absorbance of the yttrium hydroxide-structured hydroxy combination frequency region, and the second absorbance of the carbon-oxygen bond frequency region from the upstream timestamp spectrum. The second absorbance of the water-hydroxy combination frequency region is denoted as A2, the second absorbance of the yttrium hydroxide-structured hydroxy combination frequency region is denoted as B2, and the second absorbance of the carbon-oxygen bond frequency region is denoted as C2.

[0069] S7, the server determines and outputs the location of the anomaly on the production line based on A2, B2, and C2. If A2 is not within the threshold, an anomaly is determined and output as occurring at belt vacuum filter 3 or washing area 4; if B2 is not within the threshold, an anomaly is determined and output as occurring at tubular reactor 1; if C2 is not within the threshold, an anomaly is determined and output as occurring after tubular reactor 1; if A2, B2, and C2 are all within the threshold, an anomaly is determined and output as occurring at belt dryer 5.

[0070] In this embodiment, the first NIR probe is used to meet the customer's quality requirements for yttrium hydroxide products and produce qualified products. By using the second NIR probe in conjunction with the first NIR probe, the abnormal points in the process that cause quality defects can be quickly identified, which facilitates process personnel to quickly solve problems and restore normal production.

[0071] In this embodiment, the values ​​of k, k1, k2, and k3 are the same as in Embodiment 1.

[0072] In one or more specific embodiments of the present invention, in order to monitor more accurately, the first NIR probe is a contact type. The contact type NIR probe has a strong signal, is less affected by ambient light interference, and is convenient for controlling product quality.

[0073] In one or more embodiments of the present invention, in order to better adapt to continuous production lines and to better adapt to monitoring yttrium hydroxide products from the washing area, the second NIR probe is non-contact.

[0074] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the steps of the intelligent production monitoring method for yttrium hydroxide described above.

[0075] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the intelligent production monitoring method for yttrium hydroxide as described above.

[0076] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. 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 intelligent production monitoring of yttrium hydroxide, characterized by, include: S1, when the yttrium hydroxide product exiting the belt dryer passes through the first NIR probe, the first NIR probe scans and forms a downstream timestamp spectrum; S2, the server locates and outputs the first absorbance of the water-hydroxy combination frequency region, the first absorbance of the yttrium hydroxide structure hydroxy combination frequency region, and the first absorbance of the carbon-oxygen bond frequency region from the downstream timestamp spectrum. The first absorbance of the water-hydroxy combination frequency region is recorded as A1, the first absorbance of the yttrium hydroxide structure hydroxy combination frequency region is recorded as B1, and the first absorbance of the carbon-oxygen bond frequency region is recorded as C1. S3, the server calculates the predicted value of loss on ignition using the loss on ignition prediction formula, and the predicted value of loss on ignition is denoted as Y. The loss on ignition prediction formula is: Y = k + k1*A1 + k2*B1 + k3*C1, where k is a constant, k1 is the contribution coefficient of water hydroxyl groups to loss on ignition, k2 is the contribution coefficient of yttrium hydroxide structural hydroxyl groups to loss on ignition, and k3 is the contribution coefficient of carbon-oxygen bonds to loss on ignition. S4, the server determines Y. If Y ≤ threshold, production continues; if Y > threshold, an alarm command is output to stop production. Also includes: S5, retrieve the upstream timestamp spectrum generated by the second NIR probe when the yttrium hydroxide product in S1 passes through the second NIR probe; S6, the server locates and outputs the second absorbance of the water-hydroxyl combination region, the second absorbance of the yttrium hydroxide-structured hydroxyl combination region, and the second absorbance of the carbon-oxygen bond combination region from the upstream timestamp spectrum. The second absorbance of the water-hydroxyl combination region is denoted as A2, the second absorbance of the yttrium hydroxide-structured hydroxyl combination region is denoted as B2, and the second absorbance of the carbon-oxygen bond combination region is denoted as C2. S7, the server determines and outputs the location of the anomaly on the production line based on A2, B2, and C2; In S7, if A2 is not within the threshold, an abnormality is determined and output as to exist at the belt vacuum filter or the washing area; if B2 is not within the threshold, an abnormality is determined and output as to exist at the tubular reactor; if C2 is not within the threshold, an abnormality is determined and output as to exist after the tubular reactor; if A2, B2 and C2 are all within the threshold, an abnormality is determined and output as to exist at the belt dryer. 2.The intelligent production monitoring method of yttrium hydroxide according to claim 1, characterized in that, The application scenario of this intelligent production monitoring method for yttrium hydroxide is a production line for continuous production of yttrium hydroxide. The production line includes: a tubular reactor, a belt vacuum filter, a washing zone, and a belt dryer arranged in sequence. The filter belt passes through the belt vacuum filter, the washing zone, and the belt dryer respectively. A first monitoring point is set at the outlet of the belt dryer, and a first NIR probe is installed at the first monitoring point. A second monitoring point is set at the inlet of the belt dryer, and a second NIR probe is installed at the second monitoring point.

3. The intelligent production monitoring method for yttrium hydroxide according to claim 2, characterized in that, The time difference between the formation of the downstream timestamp spectrum and the upstream timestamp spectrum is the distance between the outlet and inlet of the belt dryer / the transmission speed of the filter belt.

4. The intelligent production monitoring method for yttrium hydroxide according to claim 1, characterized in that, The first NIR probe is a contact type, and the second NIR probe is a non-contact type. 5.The intelligent production monitoring method of yttrium hydroxide according to any one of claims 1-4, characterized in that, In S3, the values ​​of k, k1, k2, and k3 are obtained in the following way: S31. Collect yttrium hydroxide samples, with a sample size of no less than 100, denoted as N. S32, use the first NIR probe to scan each yttrium hydroxide sample to obtain N modeling spectra; S33, Use the loss on ignition detection method to obtain the true loss on ignition for each sample, and obtain N true loss on ignition values; S34, Establish the correlation model: Use the spectral data from N modeling spectra as the X variable and the actual loss on ignition as the Y variable to generate a prediction model and obtain the values ​​of k, k1, k2, and k3.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the intelligent production monitoring method for yttrium hydroxide as described in any one of claims 1 to 5.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that When executed by a processor, the computer program implements the steps of the intelligent production monitoring method for yttrium hydroxide as described in any one of claims 1 to 5.

Images