Dust amount estimation device and method

Abstract

Disclosed is a dust amount estimation device that estimates an amount of dust generated in a process for producing BPA pellets from liquid BPA introduced into a prilling tower, the dust amount estimation device including: a fine particle amount estimation unit configured to estimate an amount of fine particles generated in the process using a learned fine particle amount estimation model from flow information of the liquid BPA introduced into the prilling tower; and a dust amount estimation unit configured to estimate an amount of dust generated in the process using a learned dust amount estimation model from the amount of the fine particles estimated by the fine particle amount estimation unit.

Description

Technical Field

[0001] This application claims priority to Korean Patent Application No. 10-2021-0123536, filed on September 15, 2021, in the Republic of Korea, the disclosure of which is incorporated herein by reference.

[0002] This disclosure relates to dust quantity estimation apparatus and methods, and more specifically, to dust quantity estimation apparatus and methods capable of estimating the amount of dust generated during the manufacturing process of BPA pellets. Background Technology

[0003] Typically, the dust generated during the production of BPA (bisphenol A) pellets through a granulation tower can be stored in a dust filter. The dust filter may include a bag filter that filters dust introduced from the granulation tower and a dust bin in which the dust is ultimately stored.

[0004] Dust stored in a bag filter is flammable, and if a certain amount or more of dust is dispersed within a space, static electricity may accumulate, potentially acting as an ignition source. That is, if oxygen, static electricity (ignition source), and dust (flammable material) are present at a certain level or higher in the bag filter, there is a risk of the bag filter catching fire or exploding. Therefore, it is important to check the amount of dust stored in the bag filter to detect potential accidents in advance.

[0005] For example, in existing technologies, the dust box of a dust filter is replaced periodically, and the amount of dust stored in the dust box during the corresponding time period is confirmed afterward. However, the problem with this conventional method is that the amount of dust stored in the dust filter cannot be checked in real time.

[0006] As another example, dust filters are conventionally equipped with sensors to detect the amount of dust. However, the problem with this conventional approach is that the manufacturing cost of the BPA pellet generating equipment increases because a sensor for detecting the amount of dust must be provided. Summary of the Invention

[0007] Technical issues

[0008] This disclosure aims to address problems in the relevant field, and therefore aims to provide a dust amount estimation device and method for estimating the amount of dust generated during the BPA pellet production process in real time using a learned model.

[0009] These and other objects and advantages of this disclosure may be understood from the following detailed description and will become more fully apparent from exemplary embodiments thereof. Furthermore, it will be readily understood that the objects and advantages of this disclosure may be achieved by means of the manner shown in the appended claims and combinations thereof.

[0010] Technical solution

[0011] A dust estimation device according to one aspect of this disclosure estimates the amount of dust generated during a processing step for producing BPA pellets from liquid BPA introduced into a granulation tower, and the dust estimation device may include: a fine particle quantity estimation unit configured to estimate the amount of fine particles generated during the processing using a learned fine particle quantity estimation model based on flow rate information of the liquid BPA introduced into the granulation tower; and a dust quantity estimation unit configured to estimate the amount of dust generated during the processing using a learned dust quantity estimation model based on the amount of fine particles estimated by the fine particle quantity estimation unit.

[0012] The fine particle quantity estimation model can be pre-learned based on the flow rate information of liquid BPA introduced into the granulation tower and the predetermined fine particle quantity generation rate to estimate the amount of fine particles that can be generated by liquid BPA.

[0013] The fine particle generation rate can be predetermined and is used to represent the correspondence between the amount of liquid BPA and the amount of fine particles generated by the liquid BPA.

[0014] The fine particle quantity estimation model can be pre-learned to estimate the fine particle quantity by further considering at least one of the characteristics of the liquid BPA introduced into the granulation tower and the process conditions of the granulation tower.

[0015] The fine particle quantity estimation unit can be configured to determine the fine particle quantity generation rate corresponding to at least one of the characteristic information of liquid BPA and process condition factors, and estimate the quantity of fine particles based on the determined fine particle quantity generation rate.

[0016] The property information of liquid BPA can be configured to include at least one of the temperature information and composition information of liquid BPA.

[0017] Process conditions can be configured to include at least one of the following: the rate at which liquid BPA is injected into the granulation tower, the rate at which BPA pellets and fine particles generated during processing are discharged from the granulation tower to the outside, the amount of refrigerant introduced into the granulation tower during processing, the temperature of the refrigerant, the internal temperature of the granulation tower, and the pressure difference between the dust filter containing dust and the interior of the granulation tower.

[0018] The dust quantity estimation model can be pre-learned based on a predetermined correlation between the quantity of fine particles and the quantity of dust to estimate the quantity of dust from the estimated quantity of fine particles.

[0019] The correlation can be configured to a predetermined value based on the correspondence between the amount of fine particles generated by liquid BPA and the amount of dust.

[0020] Liquid BPA can be configured to be introduced into a granulation tower during processing and produce BPA pellets, fine particles, and dust.

[0021] According to another aspect of this disclosure, the dust quantity estimation device may further include a risk determination unit configured to determine the state of the dust filter based on the amount of oxygen and static electricity in the dust filter where dust generated during processing is stored, and the amount of dust estimated by the dust quantity estimation unit.

[0022] The risk determination unit can be configured to determine the status of the dust filter as normal or abnormal, and output a warning notification when the determined status of the dust filter is abnormal.

[0023] A BPA pellet manufacturing apparatus according to another aspect of this disclosure may include a dust quantity estimation device according to another aspect of this disclosure.

[0024] According to another aspect of this disclosure, a dust estimation method estimates the amount of dust generated during the processing of BPA pellets from liquid BPA introduced into a granulation tower, and the dust estimation method may include: a fine particle quantity estimation step, said fine particle quantity estimation step using a learned fine particle quantity estimation model to estimate the amount of fine particles generated during the processing from flow rate and characteristic information of the liquid BPA introduced into the granulation tower and process condition factors of the granulation tower; and a dust quantity estimation step, said dust quantity estimation step using a learned dust quantity estimation model to estimate the amount of dust generated during the processing from the amount of fine particles estimated in the fine particle quantity estimation step.

[0025] Beneficial effects

[0026] According to one aspect of this disclosure, an advantage is that the amount of dust generated during the BPA pellet production process can be estimated in real time based on a learned model.

[0027] The effects of this disclosure are not limited to those described above, and those skilled in the art will clearly understand other effects not mentioned in the description of the claims. Attached Figure Description

[0028] The accompanying drawings illustrate preferred embodiments of the present disclosure and, together with the foregoing disclosure, are intended to provide a further understanding of the technical features of the present disclosure. Therefore, the present disclosure is not to be construed as limited to the drawings.

[0029] Figure 1This is a schematic diagram of a BPA pellet generating apparatus for producing BPA pellets from liquid BPA.

[0030] Figure 2 This is a schematic diagram illustrating a dust quantity estimation device according to one embodiment of the present disclosure.

[0031] Figure 3 This is a diagram schematically showing the amount of fine particles and dust generated by liquid BPA.

[0032] Figure 4 This is a diagram schematically illustrating the operational configuration of a dust quantity estimation device according to one embodiment of the present disclosure.

[0033] Figure 5 This is a schematic diagram illustrating the phase transition process of liquid BPA during the processing of BPA microspheres.

[0034] Figure 6 It is a schematic representation of when Figure 5 A diagram illustrating the phase transition process of liquid BPA as the temperature changes.

[0035] Figure 7 It is a schematic representation of when Figure 5 A diagram illustrating the phase transition process of liquid BPA when its composition changes.

[0036] Figure 8 This is a diagram schematically illustrating the amount of dust estimated by a dust amount estimation device according to one embodiment of the present disclosure.

[0037] Figure 9 This is a diagram schematically illustrating a dust quantity estimation method according to another embodiment of the present disclosure. Detailed Implementation

[0038] It should be understood that the terms used in the specification and appended claims should not be construed as limited to their general and dictionary meanings, but rather as meanings and concepts corresponding to the technical aspects of this disclosure, and are interpreted based on the principle that the inventors are permitted to appropriately define the terms to obtain the best interpretation.

[0039] Therefore, the description presented herein is merely a preferred example for illustrative purposes only and is not intended to limit the scope of this disclosure. It should be understood that other equivalent and modified embodiments may be made thereto without departing from the scope of this disclosure.

[0040] Furthermore, in describing this disclosure, detailed descriptions of relevant known elements or functions are omitted herein when they are considered to obscure the key themes of this disclosure.

[0041] Terms including ordinal numbers such as "first" and "second" can be used to distinguish one element from another among multiple elements, but are not intended to restrict elements by terms.

[0042] Throughout the specification, when a part is referred to as “containing” or “including” any element, it means, unless otherwise specifically stated, that part may also include other elements without excluding them.

[0043] Furthermore, throughout the instruction manual, when one part is referred to as "connected" to another part, it is not limited to the case where they are "directly connected," but also includes the case where they are "indirectly connected" with another element inserted between them.

[0044] In the following, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0045] Figure 1 This is a schematic diagram of a BPA pellet generating apparatus for producing BPA pellets from liquid BPA.

[0046] Here, liquid BPA (bisphenol A) is molten BPA, which can be configured to be introduced into the granulation tower 10 during processing to produce BPA pellets, fine particles and dust.

[0047] Reference Figure 1 The BPA pellet generating equipment may include a granulation tower 10 and a dust filter 20. The granulation tower 10 may include a BPA input unit 11, a BPA discharge unit 12, a main unit 13, a refrigerant input unit 14, a BPA output unit 15, and a dust output unit 16.

[0048] BPA input unit 11 can be configured to introduce liquid BPA. For example, in Figure 1 In the implementation scheme, liquid BPA can be introduced into the granulation tower 10 through the BPA input unit 11.

[0049] BPA discharge unit 12 is connected to BPA input unit 11 and can be configured to discharge liquid BPA introduced through BPA input unit 11. For example, BPA discharge unit 12 may include one or more orifices through which liquid BPA can be discharged. BPA discharge unit 12 rotates at a set RPM and can discharge introduced liquid BPA into body unit 13.

[0050] The main body unit 13 can be configured such that liquid BPA discharged from the BPA discharge unit 12 drips. Specifically, the discharged liquid BPA can be cooled as it falls from the upper side to the lower side of the main body unit 13.

[0051] One or more refrigerant input units 14 can be provided in the main body unit 13 to introduce external refrigerant into the main body unit 13. Specifically, the refrigerant is a cooling gas capable of lowering the temperature of liquid BPA, such as air, nitrogen, inert gas, or a combination thereof.

[0052] Liquid BPA falling from the upper side to the lower side of the main unit 13 comes into contact with the refrigerant introduced through the refrigerant input unit 14, thus lowering its temperature, and the cooled liquid BPA can solidify. Through this solidification process, BPA microspheres can be formed from the liquid BPA. Furthermore, during the liquid BPA solidification process, fine particles and dust can be generated due to collisions between the formed BPA microspheres and the interior of the granulation tower 10 or between the BPA microspheres. Here, BPA microspheres, fine particles, and dust can be classified according to particle size. More specifically, BPA microspheres, fine particles, and dust can be classified separately according to predetermined particle sizes.

[0053] Based on the refrigerant introduced through the refrigerant input unit 14, and the difference between the internal pressure of the main unit 13 and the internal pressure of the dust filter 20, dust can be introduced into the dust filter 20 through the dust output unit 16.

[0054] On the other hand, the BPA spheres and fine particles generated by liquid BPA have a relatively larger particle size and greater weight than dust. Therefore, they are not introduced into the dust output unit 16 due to the introduced refrigerant and the pressure difference between the main unit 13 and the dust filter 20, but instead accumulate on the lower side of the main unit 13. That is, the BPA spheres and fine particles generated by liquid BPA can be located on the lower side of the main unit 13.

[0055] BPA output unit 15 is disposed on the lower side of main body unit 13, and BPA output unit 15 can be configured to output BPA balls and fine particles located on the lower side of main body unit 13 to the outside. For example, BPA output unit 15 can be configured to output BPA balls and fine particles to a conveyor belt.

[0056] The dust output unit 16 is disposed on the upper side of the main body unit 13 and can be configured to connect the interior of the main body unit 13 to the dust filter 20. Dust generated inside the main body unit 13 can be introduced into the dust filter 20 through the dust output unit 16.

[0057] In some cases, dust can be discharged to the outside of the granulation tower 10 through the BPA output unit 15, but in the following text, dust will be described as being introduced into the dust filter 20 through the dust output unit 16.

[0058] For example, dust can be generated during the process of solidifying liquid BPA discharged from BPA discharge unit 12. Furthermore, dust can be generated when the generated BPA pellets and / or fine particles collide with the underside of the main body unit 13. Additionally, dust can be generated when the BPA pellets and / or fine particles accumulated on the underside of the main body unit 13 collide with each other during their discharge to the outside via BPA output unit 15. Dust generated inside the main body unit 13 as described above can be introduced into the dust filter 20 via the dust output unit 16 through the refrigerant introduced via the refrigerant input unit 14 and / or the internal pressure difference between the main body unit 13 and the dust filter 20.

[0059] The dust filter 20 may include a bag filter 21 and a dust box 22.

[0060] The bag filter 21 can be configured to receive dust passing through the dust output unit 16. A sensing unit 23 for measuring the amount of oxygen and static electricity can be provided in the bag filter 21.

[0061] The dust box 22 can be configured such that dust accumulates in the bag filter 21. For example, the dust box 22 can be configured to be detachably mounted to the bag filter 21. Therefore, when dust accumulates in the dust box 22 at a predetermined ratio or greater, the dust box 22 mounted to the bag filter 21 can be retrieved, and a new or clean dust box 22 can be remounted to the bag filter 21.

[0062] Figure 2 This is a schematic diagram illustrating a dust quantity estimation device 100 according to one embodiment of the present disclosure.

[0063] According to one embodiment of this disclosure, a dust estimation device 100 can be configured to estimate the amount of dust generated during the processing of BPA pellets produced from liquid BPA introduced into a granulation tower 10.

[0064] For example, in Figure 1 In one implementation, the dust quantity estimation device 100 can estimate the amount of dust generated by the liquid BPA introduced into the granulation tower 10. Specifically, the dust quantity estimation device 100 can estimate the amount of dust introduced from the granulation tower 10 into the bag filter 21.

[0065] Reference Figure 2 According to one embodiment of the present disclosure, the dust quantity estimation device 100 may include a fine particle quantity estimation unit 110 and a dust quantity estimation unit 120.

[0066] The fine particle quantity estimation unit 110 can be configured to estimate the amount of fine particles generated during processing using a learned fine particle quantity estimation model based on the flow rate information of the liquid BPA introduced into the granulation tower 10.

[0067] Here, the flow rate information of liquid BPA can be information about the flow rate of liquid BPA introduced from the outside into the main body unit 13 through the BPA input unit 11.

[0068] Based on the flow rate information of liquid BPA introduced into the granulation tower 10 and the predetermined fine particle generation rate under process conditions, a fine particle quantity estimation model can be pre-learned to estimate the amount of fine particles that can be generated by the liquid BPA. Here, the fine particle generation rate can be predetermined to represent the correspondence between the amount of liquid BPA and the amount of fine particles generated by the liquid BPA.

[0069] For example, particle sizes generated during the processing of BPA microspheres can be classified as 0.15 mm or smaller, greater than 0.15 mm and 0.5 mm or smaller, greater than 0.5 mm and 0.85 mm or smaller, greater than 0.85 mm and 2 mm or smaller, or greater than 2 mm. Generally, if the particle size is 0.15 mm or smaller, the particles are classified as fine particles, and the rest can be classified as BPA microspheres.

[0070] That is, the fine particle generation rate can be predetermined as the ratio of the amount of fine particles generated during the experiment to the total amount of liquid BPA introduced into the granulation tower 10. Furthermore, based on the fine particle generation rate, when information about the amount of liquid BPA is input, the fine particle quantity estimation model can learn to output the amount of fine particles that can be generated (fine particle quantity). Therefore, the fine particle quantity estimation unit 110 can use the learned fine particle quantity estimation model to estimate the amount of fine particles corresponding to the flow rate information of the liquid BPA currently introduced into the granulation tower 10.

[0071] Dust quantity estimation unit 120 can be communicatively connected to fine particle quantity estimation unit 110.

[0072] The dust quantity estimation unit 120 can be configured to estimate the amount of dust generated during processing using a learned dust quantity estimation model based on the amount of fine particles estimated by the fine particle quantity estimation unit 110.

[0073] Based on a predetermined correlation between the amount of fine particles and the amount of dust, a dust quantity estimation model can be pre-learned to estimate the amount of dust from the estimated amount of fine particles. Here, the predetermined correlation between the amount of fine particles and the amount of dust can be pre-set based on the correspondence between the amount of fine particles generated by liquid BPA and the amount of dust.

[0074] For example, the correlation between the amount of fine particles and the amount of dust can be a value preset through experiments. Specifically, the amount of fine particles and the amount of dust generated in each predetermined time period can be obtained, and the correlation between the amount of fine particles and the amount of dust can be set based on the amount of fine particles and the amount of dust obtained in each time period. That is, the dust amount estimation unit 120 can calculate the amount of dust estimated to be generated in the processing process based on the predetermined correlation between the amount of fine particles and the amount of dust, using the amount of fine particles estimated by the fine particle amount estimation unit 110.

[0075] Figure 3 This is a diagram schematically showing the amount of fine particles and dust generated by liquid BPA.

[0076] Figure 3 The implementation scheme can be based on experimental data obtained by measuring the total amount of fine particles and dust generated weekly. Figure 3 In this implementation scheme, the total amount of fine particles generated is obtained by measuring the amount of fine particles generated by liquid BPA passing through the granulation tower 10 at weekly intervals. Furthermore, the total amount of dust generated is obtained by measuring the amount of dust stored in the dust bin 22 at weekly intervals. Additionally, the total amount of fine particles and the total amount of dust generated measured within the same week can be mapped together and displayed as follows: Figure 3 Each point in the diagram (▲).

[0077] For example, the correlation between the amount of fine particles and the amount of dust can be set as the ratio of the total amount of dust generated to the total amount of fine particles generated. For example, in Figure 3 In this implementation scheme, a correlation can be set based on the ratio of the total amount of dust generated to the total amount of fine particles generated. Preferably, the correlation can be set as a maximum or average ratio of the total amount of dust generated to the total amount of fine particles generated. More preferably, since dust may act as an ignition source, an accident that may occur in the dust filter 20 can be detected in advance when the amount of dust is estimated to be large. Therefore, the correlation between the amount of fine particles and the amount of dust can be set as the maximum ratio of the total amount of dust generated to the total amount of fine particles generated.

[0078] As another example, the correlation between the amount of fine particles and the amount of dust can be set as the correlation coefficient between the amount of fine particles generated and the amount of dust generated. For example, in Figure 3 In the implementation scheme, the correlation coefficient can be calculated using the covariance between the total amount of fine particles generated and the total amount of dust generated. Specifically, when X is set as the total amount of fine particles generated and Y is set as the total amount of dust generated, the correspondence between the total amount of fine particles generated and the total amount of dust generated can be expressed as follows: Figure 3The XY plot in the implementation scheme. Furthermore, the correlation coefficient can be calculated based on the variance between the total amounts of fine particles generated, the variance between the total amounts of dust generated, and the covariance between the total amount of fine particles generated and the total amount of dust generated. Figure 3 In the implementation plan, the correlation coefficient between the total amount of fine particles generated and the total amount of dust generated can be 0.56.

[0079] That is, the correlation between the amount of fine particles and the amount of dust generated during the experiment can be predetermined. Furthermore, based on this correlation, when information about the amount of fine particles is input, the dust quantity estimation model can learn to estimate the amount of dust that can be generated (dust quantity). Therefore, the dust quantity estimation unit 120 can use the learned dust quantity estimation model to estimate the amount of dust expected to be generated during processing from the amount of fine particles estimated by the fine particle quantity estimation unit 110.

[0080] According to one embodiment of this disclosure, a dust estimation device 100 can estimate the amount of dust generated during the processing of BPA pellets even without additional sensors for measuring the amount of dust. Furthermore, the dust estimation device 100 can estimate the amount of dust generated during the processing of BPA pellets in real time without requiring subsequent measurement of the amount of dust stored in the dust filter 20. Therefore, the dust estimation device 100 has the advantage of detecting potential fire or explosion hazards in the bag filter 21 in advance by estimating the amount of dust in real time.

[0081] Figure 4 This is a schematic diagram illustrating the operational configuration of a dust quantity estimation device 100 according to one embodiment of the present disclosure.

[0082] By further considering at least one of the characteristics of the liquid BPA introduced into the granulation tower 10 and the process conditions of the granulation tower 10, the fine particle quantity estimation model can be pre-learned to estimate the quantity of fine particles.

[0083] That is, the fine particle quantity estimation model can be learned by further considering at least one of the following: the flow rate information of liquid BPA, the characteristic information of liquid BPA, and the process condition factors of granulation tower 10.

[0084] Here, the property information of liquid BPA can be configured to include at least one of the temperature information and composition information of liquid BPA.

[0085] In addition, process conditions can be configured to include at least one of the following: the rate at which liquid BPA is injected into the granulation tower 10, the rate at which BPA pellets and fine particles generated during processing are discharged from the granulation tower 10 to the outside, the amount of refrigerant introduced into the granulation tower 10, the temperature of the refrigerant, the internal temperature of the granulation tower 10, and the pressure difference between the dust filter 20 containing dust and the interior of the granulation tower 10.

[0086] The fine particle quantity estimation unit 110 can determine the fine particle quantity generation rate corresponding to at least one of the characteristic information of liquid BPA and the process condition factors of granulation tower 10. Preferably, the fine particle quantity estimation unit 110 can determine the corresponding fine particle quantity generation rate by considering both the characteristic information of liquid BPA and the process condition factors of granulation tower 10.

[0087] For example, a plurality of fine particle generation rates can be set to correspond to the characteristic information of liquid BPA and the process condition factors of granulation tower 10, and the fine particle quantity estimation unit 110 can determine any one of the plurality of fine particle generation rates. Furthermore, the fine particle quantity estimation unit 110 can estimate the amount of fine particles using a fine particle quantity learning model to which the determined fine particle generation rates are applied, based on the flow rate information of the liquid BPA introduced into granulation tower 10.

[0088] exist Figure 4 In the implementation scheme, the flow rate information IN1 of liquid BPA, the characteristic information IN2 of liquid BPA, and the process condition factor IN3 can be input into the fine particulate matter estimation unit 110. The fine particulate matter estimation unit 110 can input the input flow rate information IN1, the input characteristic information IN2, and the input process condition factor IN3 into the fine particulate matter estimation model. Furthermore, the fine particulate matter estimation unit 110 can output the result from the fine particulate matter estimation model as the estimated fine particulate matter amount information OUT1 generated during the processing.

[0089] Furthermore, the fine particle quantity information output from the fine particle quantity estimation unit 110 can be input to the dust quantity estimation unit 120.

[0090] exist Figure 4 In the implementation scheme, the dust estimation unit 120 can receive fine particle quantity information OUT1 output from the fine particle quantity estimation unit 110, and input the received fine particle quantity information OUT1 and a predetermined correlation IN4 between the fine particle quantity and the dust quantity into the dust quantity estimation model. Furthermore, the dust quantity estimation unit 120 can output the result from the dust quantity estimation model as the estimated dust quantity information OUT2 generated during the processing.

[0091] That is, the dust estimation device 100 according to one embodiment of the present disclosure has the advantage of being able to estimate in real time the amount of dust expected to be generated during the processing of BPA pellets based on at least one of the flow rate, temperature and composition information of the liquid BPA introduced into the granulation tower 10 and the operating conditions of the granulation tower 10.

[0092] The following describes the factors input into the fine particle quantity estimation model to estimate the amount of fine particles based on the liquid BPA phase transition process during BPA pellet processing. Specifically, the composition of the liquid BPA, the temperature of the liquid BPA, and the process conditions of the granulation tower 10 are described.

[0093] Figure 5 This diagram schematically illustrates the phase transition process of liquid BPA during the processing of BPA microspheres. Specifically, Figure 5 The implementation scheme is illustrated in the diagram of a standard process for producing solid BPA (BPA microspheres, fine particles, and dust) from liquid BPA.

[0094] exist Figure 5 In the implementation scheme, at time t0, liquid BPA at temperature T1 can be discharged from BPA discharge unit 12.

[0095] The time interval t0 to t1 can be considered the liquid cooling period. During the liquid cooling period, the liquid BPA can be cooled by the temperature difference between itself and the interior of the main unit 13 and by the temperature difference between itself and the refrigerant introduced into the main unit 13 through the refrigerant input unit 14. The temperature of the liquid BPA cooled at time t1 can be T0.

[0096] The time intervals t1 to t2 can be considered the solidification period. During this period, the cooled liquid BPA can solidify. That is, temperature T0 can be considered the freezing point of liquid BPA.

[0097] For example, a phase change can occur in liquid BPA cooled to temperature T0 during the liquid cooling period, allowing the liquid BPA to solidify in the solidification zone. Specifically, during the solidification period, BPA microspheres, fine particles, and dust can be generated from the liquid BPA.

[0098] Furthermore, a solid cooling period may exist after time t2. The solid BPA produced during the solidification period can be cooled during this solid cooling period.

[0099] Figure 6 It is a schematic representation of when Figure 5 A diagram illustrating the phase transition process of liquid BPA as the temperature changes. Specifically, Figure 6 This diagram schematically illustrates the phase transition process of liquid BPA when its temperature, T2, is greater than T1, after being introduced into the granulation tower 10. That is, Figure 6The implementation plan is designed for situations where the temperature of liquid BPA increases.

[0100] exist Figure 6 In the implementation scheme, when the temperature of the liquid BPA introduced into the granulation tower 10 is increased to T2, the length of the liquid cooling period can be longer than... Figure 5 The liquid cooling period is long.

[0101] Reference Figure 5 and Figure 6 ,exist Figure 6 In the implementation scheme, only the temperature of the liquid BPA is changed, and due to the composition of the liquid BPA and the process conditions of the granulation tower 10, the temperature of the liquid BPA is adjusted accordingly. Figure 5 The implementation scheme is the same, therefore the cooling rate of the liquid BPA during the liquid cooling period can be the same as... Figure 5 The implementation scheme is the same.

[0102] However, since the temperature of liquid BPA increases to T2, the temperature of liquid BPA can reach its freezing point at time t1_chg. In this case, the freezing period can be the time from t1_chg to t2. That is, compared with... Figure 5 Compared to the solidification period of the implementation plan, Figure 6 The solidification period of the implementation scheme can be reduced to "t1_chg-t1".

[0103] That is, in Figure 6 In this implementation scheme, the solidification time of liquid BPA can be reduced as the temperature of the liquid BPA increases. In this case, since the liquid BPA can only solidify for a short period of time, therefore... Figure 6 The solid BPA particles generated in the implementation scheme can be smaller than [the specified size]. Figure 5 The solid BPA particles generated in the implementation scheme. This means in Figure 6 In the implementation plan, it can produce more Figure 5 The implementation plan includes a larger amount of fine particles.

[0104] Therefore, refer to Figure 5 and Figure 6 Since the temperature of liquid BPA can affect the amount of fine particles, the fine particle quantity estimation unit 110 can estimate the amount of fine particles generated by taking the temperature of liquid BPA into account.

[0105] Figure 7 It is a schematic representation of when Figure 5 A diagram illustrating the phase transition process of liquid BPA when its composition changes. Specifically, Figure 7 This schematically illustrates the composition of liquid BPA introduced into granulation tower 10 according to... Figure 5A diagram illustrating the phase transition process of liquid BPA when the composition of the liquid BPA in the implementation scheme is different. That is, Figure 7 The implementation plan is designed for situations where the composition of liquid BPA changes due to process condition factors.

[0106] exist Figure 7 In the implementation scheme, when the composition of the liquid BPA introduced into the granulation tower 10 changes, the length of the liquid cooling period can be longer than... Figure 5 The liquid cooling period is long.

[0107] Reference Figure 5 and Figure 7 ,exist Figure 7 In the implementation scheme, only the composition of the liquid BPA is changed, and due to the temperature of the liquid BPA and the process conditions of the granulation tower 10, Figure 5 The implementation scheme is the same, therefore the cooling rate of the liquid BPA during the liquid cooling period can be the same as... Figure 5 The implementation scheme is the same.

[0108] However, due to Figure 7 The implementation scheme alters the composition of liquid BPA, allowing the liquid BPA to reach its freezing point at time t1_chg. That is, because the freezing point of the mixture is lower than that of the pure substance, therefore... Figure 7 The freezing point of liquid BPA can be lower than [missing information]. Figure 5 The freezing point of liquid BPA. Furthermore, due to... Figure 5 and Figure 7 The cooling rate is the same in both, therefore Figure 7 The freezing point of liquid BPA can be lowered to T3. In this case, the freezing period can be from t1_chg to t2. That is, compared with... Figure 5 Compared to the solidification period of the implementation plan, Figure 7 The solidification period of the implementation scheme can be reduced to "t1_chg-t1".

[0109] That is, in Figure 7 In this implementation scheme, the solidification time of liquid BPA can be reduced by changing the composition of the liquid BPA. In this case, since liquid BPA can solidify for only a short period of time, therefore... Figure 7 The solid BPA particles generated in the implementation scheme can be smaller than [the specified size]. Figure 5 The solid BPA particles generated in the implementation scheme. This means in Figure 7 In the implementation plan, it can produce more Figure 5 The implementation plan includes a larger amount of fine particles.

[0110] Therefore, refer to Figure 5 and Figure 7Since the composition of liquid BPA is a factor that can affect the amount of fine particles, the fine particle amount estimation unit 110 can estimate the amount of fine particles generated by taking into account the composition of liquid BPA.

[0111] Furthermore, the cooling rate of liquid BPA can be changed when the temperature of the liquid BPA and / or the process conditions of the granulation tower 10 change.

[0112] exist Figure 5 In the implementation scheme, the cooling rate of the liquid BPA can be altered during the liquid cooling period when the temperature of the liquid BPA and / or the process conditions of the granulation tower 10 change. Changes in the cooling rate can affect the time it takes for the liquid BPA to reach its freezing point, and thus its solidification mechanism.

[0113] For example, as the cooling rate increases, a large number of nuclei are generated in the liquid BPA, and the size of the BPA microspheres formed by growth after nucleation can decrease, or the size of the grains constituting the BPA microspheres can decrease. That is, since the change in the solidification mechanism due to the increased cooling rate can weaken the strength of the BPA microspheres, fine particles and / or dust can be additionally generated due to collisions that occur after the solidification process of the liquid BPA. Therefore, the fine particle quantity estimation unit 110 can estimate the quantity of fine particles by further considering the temperature of the liquid BPA and the process conditions of the granulation tower 10.

[0114] Figure 8 This is a schematic diagram illustrating the amount of dust estimated by a dust amount estimation device 100 according to one embodiment of the present disclosure.

[0115] Specifically, Figure 8 This is a graph that compares the amount of dust actually generated during a predetermined time period (13 months) (●) with the estimated amount of dust estimated by the dust amount estimation unit 120 (▲).

[0116] The dust quantity estimation unit 120 can estimate the amount of dust generated by liquid BPA by considering the fine particle quantity information received from the fine particle quantity estimation unit 110 and the correlation between the amount of fine particles and the amount of dust. Therefore, referring to Figure 8 It can be seen that the amount of dust estimated by the dust amount estimation unit 120 is similar to the amount of dust actually generated.

[0117] In particular, it can be seen that even when the actual amount of dust generated tends to decrease rapidly, the amount of dust is accurately estimated by the dust amount estimation unit 120. Therefore, the dust amount estimation unit 120 can estimate the amount of dust generated during the BPA pellet processing with high accuracy from the estimated amount of fine particles.

[0118] Meanwhile, the fine particle quantity estimation unit 110, dust quantity estimation unit 120 and risk determination unit 130 included in the dust quantity estimation device 100 may optionally include processors, application-specific integrated circuits (ASICs), other chipsets, logic circuits, registers, communication modems, data processing devices, etc., known in the art, to implement the various control logics performed in this disclosure.

[0119] Furthermore, the dust quantity estimation device 100 may also include a storage unit 140. The storage unit 140 may store data required for the operation and function of each component of the dust quantity estimation device 100, data generated during the execution of operations or functions, etc. There are no particular limitations on the type of storage unit 140, as long as it is a known information storage device capable of recording, erasing, updating, and retrieving data. As examples, the information storage device may include RAM, flash memory, ROM, EEPROM, registers, etc. In addition, the storage unit 140 may store program code that defines the processes that can be executed by the fine particle quantity estimation unit 110, the dust quantity estimation unit 120, and the risk determination unit 130.

[0120] For example, storage unit 140 can store a fine particle quantity estimation model, a fine particle quantity generation rate, a dust quantity estimation model, and the correlation between the amount of dust and the amount of fine particles.

[0121] At the same time, refer to Figure 2 The dust quantity estimation device 100 according to one embodiment of the present disclosure may further include a risk determination unit 130.

[0122] The risk determination unit 130 can be configured to determine the state of the dust filter 20 based on the amount of oxygen and static electricity stored in the dust filter 20 where dust generated during the processing is stored, as well as the amount of dust estimated by the dust amount estimation unit 120.

[0123] For example, in Figure 1 In one implementation, the risk determination unit 130 can be communicatively connected to the sensing unit 23. Furthermore, the risk determination unit 130 can be communicatively connected to the dust quantity estimation unit 120.

[0124] Reference Figure 4 The risk determination unit 130 can determine the state of the dust filter 20 based on the amount of oxygen and static electricity IN5 received from the sensing unit 23 and the dust amount information OUT2 received from the dust amount estimation unit 120.

[0125] Specifically, the risk determination unit 130 can determine the state of the dust filter 20 as normal or abnormal.

[0126] Here, a normal state can mean a state in which the amounts of oxygen, static electricity, and dust are within normal ranges, and there is no risk of fire or explosion in the dust filter 20. Conversely, an abnormal state can mean a state in which at least one of the amounts of oxygen, static electricity, and dust is outside the normal range.

[0127] According to one embodiment of this disclosure, abnormal conditions may include warning conditions and hazardous conditions. A warning condition may mean a condition in which at least one of the amounts of oxygen, static electricity, and dust is outside the normal range, but the probability of fire or explosion in the dust filter 20 is low. That is, a warning condition is a condition in which at least one of the amounts of oxygen, static electricity, and dust is slightly outside the normal range, and the risk of fire or explosion is low even if the dust filter 20 is not in a normal state.

[0128] Conversely, a hazardous state can refer to a condition in which at least one of the amounts of oxygen, static electricity, and dust is outside the normal range, and there is a possibility of fire or explosion in the dust filter 20. That is, a hazardous state can be a condition in which the dust filter 20 is not in its normal state and the risk of fire or explosion is high.

[0129] For example, normal ranges, warning ranges, and danger ranges can be predetermined for each of the amounts of oxygen, static electricity, and dust. Furthermore, if the amounts of oxygen, static electricity, and dust all fall within their respective normal ranges, the risk determination unit 130 can determine the state of the dust filter 20 as normal.

[0130] As another example, if at least one of the amount of oxygen, the amount of static electricity, and the amount of dust falls within the corresponding warning range, the risk determination unit 130 can determine the state of the dust filter 20 as an abnormal state (specifically, a warning state).

[0131] As another example, if at least one of the amount of oxygen, the amount of static electricity, and the amount of dust falls within the corresponding risk range, the risk determination unit 130 can determine the state of the dust filter 20 as an abnormal state (specifically, a dangerous state).

[0132] In the above, abnormal states are only classified as warning states and dangerous states. However, abnormal states can be further subdivided based on the possibility of fire or explosion in the dust filter 20. That is, in addition to normal states, warning states, and dangerous states, the range of states corresponding to the amount of oxygen, the amount of static electricity, and the amount of dust can be further subdivided.

[0133] The risk determination unit 130 can be configured to output a warning notification when the determined state of the dust filter 20 is abnormal.

[0134] For example, the risk assessment unit 130 can output a warning notification along with the determined status of the dust filter 20 to an external display, user terminal, and / or central control server.

[0135] Furthermore, users and / or servers can temporarily halt the BPA pellet processing process based on warning notifications received from the risk assessment unit 130 to prevent fire and / or explosion in the dust filter 20. For example, the BPA pellet processing process can be temporarily suspended when the dust filter 20 is determined by the risk assessment unit 130 to be in an abnormal state (specifically, a hazardous state).

[0136] According to one embodiment of this disclosure, the dust estimation device 100 can estimate the amount of dust generated during the processing of BPA pellets in real time. Therefore, the dust estimation device 100 has the advantages of preventing accidents such as fires and / or explosions during the processing of BPA pellets, or of rapidly notifying external parties of the occurrence of such accidents.

[0137] Additionally, the dust estimation device 100 according to one embodiment of this disclosure may be included in a BPA pellet manufacturing apparatus.

[0138] For example, refer to Figure 1 and Figure 2 The BPA pellet manufacturing equipment may include a granulation tower 10, a dust filter 20, and a dust quantity estimation device 100.

[0139] exist Figure 4 In the implementation scheme, the dust quantity estimation device 100 can receive from the outside the flow rate information IN1 of liquid BPA, the characteristic information IN2 of liquid BPA, and the process condition factors IN3 of the granulation tower 10 introduced through the BPA input unit 11. Furthermore, the dust quantity estimation device 100 can be communicatively connected to the sensing unit 23 disposed in the bag filter 21 to receive the amount of oxygen and the amount of static electricity IN5 from the sensing unit 23.

[0140] Furthermore, the dust quantity estimation device 100 can estimate the amount of dust contained in the bag filter 21 in real time during the production of BPA pellets in the BPA pellet manufacturing equipment. Therefore, since the BPA pellet manufacturing equipment can check the possibility of fire and / or explosion of the dust filter 20 in real time, it has the advantage of producing BPA pellets more safely.

[0141] Figure 9 This is a diagram schematically illustrating a dust quantity estimation method according to another embodiment of the present disclosure.

[0142] Preferably, each step of the dust quantity estimation method can be performed by the dust quantity estimation device 100. In the following text, for ease of explanation, content repeated in the previous description will be omitted or briefly described.

[0143] The dust estimation method is a method for estimating the amount of dust generated during the process of producing BPA pellets from liquid BPA introduced into granulation tower 10.

[0144] Reference Figure 9 The dust quantity estimation method may include a fine particle quantity estimation step (S100) and a dust quantity estimation step (S200).

[0145] The fine particle quantity estimation step (S100) is a step of estimating the amount of fine particles generated during the processing using the flow information of liquid BPA introduced into the granulation tower 10 based on the learned fine particle quantity estimation model, and can be executed by the fine particle quantity estimation unit 110.

[0146] For example, the fine particle quantity estimation unit 110 can estimate the expected amount of fine particles to be generated in real time using the flow rate information of the liquid BPA introduced into the granulation tower 10.

[0147] exist Figure 4 In the implementation scheme, the fine particulate matter estimation unit 110 can generate fine particulate matter information from the flow rate information IN1 of liquid BPA, the characteristic information IN2 of liquid BPA, and the process condition factors IN3.

[0148] The dust quantity estimation step (S200) is a step of estimating the amount of dust generated during the processing by using the learned dust quantity estimation model based on the amount of fine particles estimated in the fine particle quantity estimation step (S100), and can be executed by the dust quantity estimation unit 120.

[0149] For example, in Figure 4 In one implementation, the dust quantity estimation unit 120 can receive fine particle quantity information OUT1 from the fine particle quantity estimation unit 110. Furthermore, the dust quantity estimation unit 120 can estimate the amount of dust that can be generated during the BPA pellet processing based on a predetermined correlation IN4 and the fine particle quantity information OUT1.

[0150] The dust estimation method according to another embodiment of this disclosure has the advantage of estimating the amount of dust generated during the BPA ball processing process in real time using a non-destructive method.

[0151] Reference Figure 9 The dust quantity estimation method may also include a risk determination step (S300).

[0152] The risk determination step (S300) is a step of determining the state of the dust filter 20 based on the amount of oxygen and static electricity stored in the dust filter 20 where dust generated during the processing is stored, as well as the amount of dust estimated by the dust amount estimation unit 120, and can be performed by the risk determination unit 130.

[0153] For example, in Figure 4 In the implementation scheme, the risk determination unit 130 can receive dust quantity information OUT2 from the dust quantity estimation unit 120. In addition, the risk determination unit 130 can receive the amount of oxygen and the amount of static electricity IN5 from the sensing unit 23 included in the dust filter 20 (more specifically, the bag filter 21).

[0154] The risk determination unit 130 can determine the state of the dust filter 20 as normal or abnormal based on the amount of oxygen, the amount of static electricity, and the amount of dust. If the state of the dust filter 20 is determined to be abnormal, the risk determination unit 130 can be configured to output a warning notification to the outside.

[0155] That is, the dust quantity estimation method according to another embodiment of the present disclosure can output a warning notification to the outside when the dust filter 20 is in an abnormal state, thereby preventing accidents such as fire and / or explosion that may occur in the dust filter 20 in advance, or quickly notifying the outside of the occurrence of such accidents.

[0156] The embodiments of the present disclosure described above can be implemented not only by devices and methods, but also by programs that implement functions corresponding to the configuration of the embodiments of the present disclosure, or by recording media on which the programs are recorded. Based on the description of the above embodiments, those skilled in the art can easily implement the programs or recording media.

[0157] The present disclosure has been described in detail. However, it should be understood that while the detailed description and specific examples indicate preferred embodiments of the present disclosure, they are given by way of example only, as various variations and modifications within the scope of the present disclosure will become apparent to those skilled in the art based on the detailed description.

[0158] Furthermore, those skilled in the art can make many substitutions, modifications, and variations to the above-described disclosure without departing from the technical aspects of this disclosure, and the disclosure is not limited to the above embodiments and drawings, and the various embodiments can be selectively combined in part or in whole to allow for various modifications.

[0159] (See attached image labels)

[0160] 10: Pelletizing tower

[0161] 11: BPA Input Unit

[0162] 12: BPA Removal Unit

[0163] 13: Main Unit

[0164] 14: Refrigerant Input Unit

[0165] 15: BPA Output Unit

[0166] 16: Dust Output Unit

[0167] 20: Dust Filter

[0168] 21: Bag filter

[0169] 22: Dust box

[0170] 23: Sensing Unit

[0171] 100: Dust Estimation Equipment

[0172] 110: Fine particle quantity estimation unit

[0173] 120: Dust Estimation Unit

[0174] 130: Risk Determination Unit

[0175] 140: Storage unit

Claims

1. A dust quantity estimation device, said dust quantity estimation device estimating the amount of dust generated during a process for producing BPA pellets from liquid BPA introduced into a granulation tower, said dust quantity estimation device comprising: A fine particle quantity estimation unit is configured to estimate the amount of fine particles generated during the processing using a learned fine particle quantity estimation model based on the flow rate information of the liquid BPA introduced into the granulation tower. and A dust quantity estimation unit is configured to estimate the amount of dust generated during the processing using a learned dust quantity estimation model, based on the amount of fine particles estimated by the fine particle quantity estimation unit. The fine particle quantity estimation model is pre-learned based on the flow rate information of the liquid BPA introduced into the granulation tower and a predetermined fine particle quantity generation rate to estimate the amount of fine particles that can be generated by the liquid BPA.

2. The dust quantity estimation device according to claim 1, The fine particle generation rate is predetermined and is used to represent the correspondence between the amount of liquid BPA and the amount of fine particles generated by the liquid BPA.

3. The dust quantity estimation device according to claim 1, The fine particle quantity estimation model is pre-learned to estimate the quantity of fine particles by further considering at least one of the characteristic information of the liquid BPA introduced into the granulation tower and the process condition factors of the granulation tower.

4. The dust quantity estimation device according to claim 3, The fine particle quantity estimation unit is configured to determine the fine particle quantity generation rate corresponding to at least one of the characteristic information of the liquid BPA and the process condition factors, and to estimate the quantity of fine particles based on the determined fine particle quantity generation rate.

5. The dust quantity estimation device according to claim 3, The characteristic information of the liquid BPA is configured to include at least one of the temperature information and composition information of the liquid BPA.

6. The dust quantity estimation device according to claim 3, The process conditions are configured to include at least one of the following: the rate at which the liquid BPA introduced into the granulation tower is injected into the granulation tower; the rate at which the BPA pellets and fine particles generated during the processing are output from the granulation tower to the outside; the amount of refrigerant introduced into the granulation tower during the processing; the temperature of the refrigerant; the internal temperature of the granulation tower; and the pressure difference between the dust filter in which the dust is stored and the interior of the granulation tower.

7. The dust quantity estimation device according to claim 1, The dust estimation model is pre-learned based on a predetermined correlation between the amount of fine particles and the amount of dust to estimate the amount of dust from the estimated amount of fine particles.

8. The dust quantity estimation device according to claim 7, The correlation is configured to be predetermined based on the correspondence between the amount of fine particles generated by the liquid BPA and the amount of dust.

9. The dust quantity estimation device according to claim 1, The liquid BPA is configured to be introduced into the granulation tower during the processing to produce the BPA pellets, the fine particles, and the dust.

10. The dust quantity estimation device according to claim 1, further comprising: A risk determination unit is configured to determine the state of the dust filter based on the amount of oxygen and static electricity stored in a dust filter containing the dust generated during the processing, and the amount of dust estimated by the dust quantity estimation unit.

11. The dust quantity estimation device according to claim 10, The risk determination unit is configured to determine the state of the dust filter as either a normal state or an abnormal state, and to output a warning notification when the determined state of the dust filter is the abnormal state.

12. A BPA pellet manufacturing apparatus, comprising a dust quantity estimation device according to any one of claims 1 to 11.

13. A dust quantity estimation method, said dust quantity estimation method estimating the amount of dust generated during a processing step for producing BPA pellets from liquid BPA introduced into a granulation tower, said dust quantity estimation method comprising: The fine particle quantity estimation step uses a learned fine particle quantity estimation model to estimate the amount of fine particles generated during the processing based on the flow rate and characteristic information of the liquid BPA introduced into the granulation tower and the process condition factors of the granulation tower. and The dust estimation step uses a learned dust estimation model to estimate the amount of dust generated during the processing, based on the amount of fine particles estimated in the fine particle estimation step. The fine particle quantity estimation model is pre-learned based on the flow rate information of the liquid BPA introduced into the granulation tower and a predetermined fine particle quantity generation rate to estimate the amount of fine particles that can be generated by the liquid BPA.

Images