JP2019051458A - Dewatering system - Google Patents

Abstract

To provide a dewatering system capable of calculating an accurate status predicted value of a suspended residue (e.g., predicted moisture content of a cake).SOLUTION: A dewatering system includes: a dewatering device 1 for producing a suspended residue by removing liquid from a suspension; and an analyzer 62 for storing a pre-built calculation model based on suspension data indicating a status of suspension, operating data including multiple operating parameters of the dewatering device 1, and suspended residue data indicating a status of the suspended residue. The analyzer 62 calculates a status predicted value of the suspended residue by entering a current value of the suspension data and current values of the operating parameters into the calculation model.SELECTED DRAWING: Figure 1

Description

  In particular, the present invention relates to a dehydration system including a dehydration device that separates a suspension such as sludge or slurry into turbidity and liquid, and more particularly to a dehydration system capable of automatically operating the dehydration device.

  Conventionally, a suspension (eg, sludge) discharged from a liquid treatment facility such as a sewage treatment plant, a human waste treatment plant, or an industrial wastewater treatment plant is squeezed to separate (ie, dehydrate) water from the suspension. ) A dehydrator is used. A screw press that is an example of a dehydrator is known as a sludge dehydrator. This screw press is equipped with a filter cylinder formed from a screen (perforated plate) and a screw disposed inside the filter cylinder. By rotating the screw, the sludge put into the filter cylinder is squeezed. , Dehydrate.

  A back pressure plate that dams sludge is disposed at the downstream opening end of the filter cylinder. This back pressure plate retains cake (dehydrated sludge) sent by a rotating screw, and plugs (plugs) made of cake ). This plug applies back pressure to the cake fed later, and further squeezes the cake. The cake forming the plug is pushed by the subsequent cake and discharged from the filter tube little by little. In this way, a low moisture content cake is produced by a screw press.

JP2015-54286A

  In order to keep the moisture content of the cake finally obtained within the target range, predict the moisture content of the cake under the current operating conditions, and change the operating conditions of the screw press based on the prediction results. Is desirable. However, the moisture content of the cake can vary depending on various factors such as the state of sludge charged into the screw press and the operating state of the screw press. For this reason, it was difficult to accurately predict the moisture content of the cake and to maintain the target moisture content.

  Therefore, an object of the present invention is to provide a dehydration system that can calculate an accurate predicted state value of a turbid residue (for example, a predicted moisture content of a cake) and maintain a target moisture content.

  One aspect of the present invention includes a dehydrating apparatus that generates a turbid residue by removing liquid from a suspension, suspension data indicating a state of the suspension, and a plurality of operating parameters of the dehydrating apparatus. An analysis device for storing operation data and a calculation model preliminarily constructed based on the turbid residue data indicating the state of the turbid residue, the analysis device comprising: a current value of the suspension data; and the operation The dehydrating system is characterized in that a state prediction value of the turbid residue is calculated by inputting a current value of a parameter to the calculation model.

In a preferred aspect of the present invention, the analysis device predicts the state at a preset time interval or when a value of a data item included in the suspension data becomes equal to a preset threshold value. A value is calculated.
A preferred aspect of the present invention is characterized by further comprising a computer that constructs the calculation model by executing machine learning using the suspension data, the operation data, and the turbid residue data.
In a preferred aspect of the present invention, the computer executes machine learning using the suspension data, the operation data, and the turbid residue data to construct a new calculation model, and the new calculation model The analysis device is sent to the analysis device, and the analysis device updates the stored calculation model to the new calculation model.

In a preferred aspect of the present invention, the data processing device further includes a data integration device that generates a data set by integrating the suspension data, the operation data, and the turbid residue data.
In a preferred aspect of the present invention, the analysis device determines a plurality of numerical patterns of the operation parameters that allow the state predicted value to fall within a target range.
In a preferred aspect of the present invention, the analysis device calculates a plurality of evaluation index values respectively corresponding to the plurality of numerical patterns, determines an optimum one of the plurality of evaluation index values, and A numerical value pattern of the operation parameter corresponding to the determined evaluation index value is sent to the dehydrating apparatus.

  According to the present invention, since the calculation model constructed based on the suspension data, the dehydrator operation data, and the turbid residue data is used, the analysis device removes liquid from the suspension (eg, sludge). It is possible to accurately calculate the state prediction value of the turbid residue (for example, cake) remaining after the removal.

It is a figure which shows one Embodiment of a dehydration system. It is a conceptual diagram of a dehydration system. It is a schematic diagram which shows an example of the three patterns of the operation parameter which the predicted moisture content of a cake can be settled in a target range.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a diagram illustrating an embodiment of a dehydration system. The dehydration system includes a dehydrator 1 that dehydrates sludge, which is an example of a suspension, that is, removes liquid from the sludge to generate a turbid residue, and an operation control unit 5 that controls the operation of the dehydrator 1. Yes. The dehydrating apparatus 1 of the present embodiment includes a screw press 2 that pressurizes and dewaters sludge, and an agglomeration mixing tank 3 that sends the sludge to the screw press 2. The screw press 2 is an example of a pressure dehydrator that dehydrates sludge. As the pressure dehydrator, in addition to the screw press, other types such as a filter press and a centrifuge can be used.

  Turbid residue is a low moisture content that remains after removing the liquid from the suspension. The turbid residue remaining after removing the liquid from the sludge is commonly referred to as a cake. In the following description, the suspension is called sludge, the turbid residue is called cake, and the liquid separated from the suspension is called filtrate. Specific examples of sludge include sludge generated during the treatment of sewage or human waste. Moreover, as an example of suspensions other than sludge, the industrial waste generated at the time of manufacture of industrial products, such as foodstuffs, cosmetics, and paper, or a slurry is mentioned.

  The agglomeration mixing tank 3 includes a container 6 for containing sludge and a stirrer 8 for stirring the sludge in the container 6. The stirrer 8 includes a stirring blade 9 disposed in the container 6 and a stirring motor 10 connected to the stirring blade 9. The container 6 is connected to the sludge introduction pipe 14, and the pump 12 is provided in the sludge introduction pipe 14. The sludge is transferred to the coagulation mixing tank 3 through the sludge introduction pipe 14 by the pump 12.

  The flow rate of sludge to the flocculation mixing tank 3 can be adjusted by operating the pump 12. The pump 12 is connected to the operation control unit 5, and the operation of the pump 12, that is, the flow rate of sludge to the coagulation mixing tank 3 is controlled by the operation control unit 5. You may control the flow volume of sludge with another control apparatus which is not shown in figure. A temperature sensor 22 is attached to the sludge introduction pipe 14. The temperature sensor 22 is configured to measure the temperature of the sludge introduced into the coagulation mixing tank 3. Further, a sludge concentration meter 24 is attached to the sludge introduction pipe 14, and the concentration of suspended substances in the sludge introduced into the coagulation mixing tank 3 is measured by the sludge concentration meter 24.

  A flocculant is injected into the sludge in the flocculation mixing tank 3. The sludge is stirred by the stirrer 8 together with the flocculant. By stirring the flocculant and the sludge in the flocculation mixing tank 3, a flocculation floc in which suspended substances in the sludge are gathered is formed. Although the agglomeration mixing tank 3 shown in FIG. 1 is a one-stage tank, the agglomeration mixing tank 3 may be a multi-stage tank. The stirring strength of sludge can be adjusted by the rotational speed of the stirrer 8. The stirrer 8 is connected to the operation control unit 5, and the operation of the stirrer 8, that is, the stirring strength of sludge is controlled by the operation control unit 5.

  The agglomeration mixing tank 3 is connected to a sludge inlet 20 of the screw press 2 by a sludge transfer pipe 18. The sludge stirred in the coagulation mixing tank 3 is transferred to the screw press 2 through the sludge transfer pipe 18. In one embodiment, a concentrator may be provided between the agglomeration mixing tank 3 and the screw press 2.

  The screw press 2 rotates the filter cylinder 30, the screw shaft 35 concentrically arranged in the filter cylinder 30, the screw blade 36 fixed to the outer surface of the screw shaft 35, the screw shaft 35 and the screw blade 36. And a screw motor 38 for sending the sludge toward the discharge chamber 41. The filtration cylinder 30 is comprised from perforated plates, such as punching metal. One end of the filtration cylinder 30 is sealed by a blocking wall 40, and the other end of the filtration cylinder 30 is connected to the discharge chamber 41. A sludge inlet 20 adjacent to the blocking wall 40 is formed in the filtration cylinder 30.

  The screw shaft 35 extends through the filtration cylinder 30. The screw shaft 35 has a truncated cone shape whose diameter gradually increases toward the downstream side. The screw shaft 35 extends through the blocking wall 40, and the end of the screw shaft 35 is connected to a screw motor 38. The screw motor 38 is connected to the operation control unit 5, and the operation of the screw motor 38, that is, the rotational speed of the screw blade 36 is controlled by the operation control unit 5.

  The screw blade 36 is a single blade extending in a spiral shape along the longitudinal direction of the screw shaft 35. A minute gap is formed between the inner surface of the filtration cylinder 30 and the screw blade 36, and the screw blade 36 can rotate without contacting the filtration cylinder 30. The sludge introduced into the filter cylinder 30 from the sludge inlet 20 is transferred toward the discharge chamber 41 through the filter cylinder 30 by the rotating screw blades 36.

  A space in which the sludge is transferred in the filter cylinder 30 is formed by the inner surface of the filter cylinder 30, the screw blades 36, and the screw shaft 35. The volume of this space gradually decreases along the direction of sludge progression. Therefore, as this space is moved by the screw blades 36, the sludge is squeezed and dehydrated. The filtrate that has passed through the filtration cylinder 30 is collected by a filtrate receiver 45 disposed below the filtration cylinder 30 and then discharged.

  An annular back pressure plate 50 is disposed facing the downstream end of the filtration cylinder 30. The back pressure plate 50 has a truncated cone shape having a tapered surface for receiving dewatered sludge transferred through the filter cylinder 30. A through-hole through which the screw shaft 35 passes is formed at the center of the back pressure plate 50, and the back pressure plate 50 is disposed concentrically with the screw shaft 35. The back pressure plate 50 is not fixed to the screw shaft 35, and the back pressure plate 50 does not rotate.

  The back pressure plate 50 is connected to a back pressure plate driving device 51. The back pressure plate driving device 51 is configured to move the back pressure plate 50 in the axial direction of the screw shaft 35. A gap between the back pressure plate 50 and the downstream end of the filter cylinder 30 is adjusted by the back pressure plate 50. The back pressure plate driving device 51 is constituted by, for example, a hydraulic cylinder or an electric cylinder. The back pressure plate driving device 51 is connected to the operation control unit 5, and the operation of the back pressure plate driving device 51, that is, the position of the back pressure plate 50 in the axial direction is controlled by the operation control unit 5.

  Next, the operation of the screw press 2 will be described. Sludge is introduced into the filter cylinder 30 from the sludge inlet 20. The sludge is transferred toward the discharge chamber 41 through the filter cylinder 30 by the rotating screw blades 36. The sludge is squeezed and dehydrated as it moves through the filter cylinder 30. The filtrate that has passed through the filter cylinder 30 is collected by the filtrate receiver 45 and discharged. The sludge is dehydrated in the filter cylinder 30 to form a cake. The cleaning device 55 supplies the cleaning liquid to the outer peripheral surface of the filtration cylinder 30 at a preset time interval.

  The cake that has moved in the filter cylinder 30 is pressed against the back pressure plate 50. The cake is compressed by being prevented from moving by the back pressure plate 50. This compressed cake forms a plug 52 that seals the downstream end of the filtration cylinder 30. The plug 52 reduces the moisture content of the cake in the filter cylinder 30 by applying a back pressure to the subsequent cake. The cake is pushed by the subsequent cake while passing through the gap between the back pressure plate 50 and the downstream end of the filtration cylinder 30 while forming the plug 52 in the filtration cylinder 30 and gradually enters the discharge chamber 41. Discharged. The cake is discharged from the discharge chamber 41 through a chute 53 provided in the lower portion of the discharge chamber 41. In this way, the liquid is removed from the sludge and a low moisture content cake is produced.

  The gap between the back pressure plate 50 and the downstream end of the filtration cylinder 30 varies depending on the axial position of the back pressure plate 50, and as a result, the compressive force applied to the sludge in the filtration cylinder 30 varies. More specifically, when the gap between the back pressure plate 50 and the downstream end of the filtration cylinder 30 becomes small, a larger force is required to push out the plug 52, and therefore compression applied to the sludge in the filtration cylinder 30 Power increases. Therefore, the compression force applied to the sludge can be adjusted not only by the rotational speed of the screw blades 36 but also by the position of the back pressure plate 50.

  The moisture content of the cake produced | generated with the dehydration apparatus 1 changes depending on the state of the sludge thrown into the dehydration apparatus 1, and the driving | running state of the dehydration apparatus 1 (including the screw press 2 and the coagulation mixing tank 3). The dehydration system includes an analysis device 62 that calculates the predicted moisture content of the cake generated by the dehydrator 1 based on the state of sludge and the operating state of the dehydrator 1. In this embodiment, a turbid residue is a cake produced | generated with the dehydration apparatus 1, and the state predicted value of a turbid residue is a predicted moisture content of a cake.

  The analysis device 62 indicates sludge data (suspension data) indicating the state of the sludge to be input to the dehydrator 1, operation data indicating the operation state of the dehydrator 1, and the state of the cake generated by the dehydrator 1. A calculation model built in advance based on cake data (turbid residue data) is stored in advance. The analysis device 62 calculates the predicted moisture content of the cake using this calculation model. The data items included in the sludge data, operation data, and cake data are as follows.

Sludge data (1) Sludge temperature (2) Air temperature (3) Concentration of suspended solids in sludge (4) Proportion of fiber material contained in sludge (eg expressed in weight percent)
(5) Ratio of organic substances contained in sludge (for example, expressed in weight percent)

Operation data (a) Flow rate of sludge introduced into the flocculation mixing tank 3 (b) Injection rate of the flocculant injected into the flocculation mixing tank 3 (c) Rotational speed of the stirrer 8 in the flocculation mixing tank 3 (d) Screw blade Rotational speed of 36 (e) Position of back pressure plate 50 (f) Pressure of cleaning liquid (g) Frequency of cleaning (h) Torque of screw blade 36 (i) Pressure in filter cylinder 30 of screw press 2

Cake data (I) Moisture content

  The dewatering system further includes a data integration device 65 that integrates the above-described sludge data, operation data, and cake data to create a data set. The data items included in the above-described sludge data, operation data, and cake data are examples, and the present invention is not limited to the above-described examples.

The temperature of the sludge that is the data item (1) is measured by the temperature sensor 22 described above. The measured value of the sludge temperature is sent to the data integration device 65.
The air temperature as the data item (2) is measured by a thermometer 70 installed in the vicinity of the screw press 2. The measured value of the temperature is sent to the data integration device 65.
The concentration which is the data item (3) is measured by the sludge densitometer 24. The concentration measurement value is sent to the data integration device 65.
Each numerical value of the data items (4) and (5) is periodically measured and input to the data integration device 65.

Among the data items included in the operation data, the data items (a) to (h) are operation parameters that determine the operation state of the dehydrator 1 and are variable parameters.
The injection rate of the flocculant, which is the data item (b), can be obtained by a known technique as described in JP-A-2017-121601. Alternatively, the flocculant injection rate may be a value proportional to the concentration measured by the sludge concentration meter 24. The injection rate of the flocculant can be adjusted by controlling a flocculant injection pump (not shown).
The data item (h) can be calculated from the current or power supplied to the screw motor 38.
The data item (i) represents the pressure applied to the sludge in the filtration cylinder 30. This pressure is measured by a pressure sensor 71 arranged in the filtration cylinder 30. The measurement value of the pressure in the filter cylinder 30 is sent from the pressure sensor 71 to the data integration device 65.

  The data item (I) is the moisture content (%) of the cake generated by the dehydrator 1 and is an actual measurement value.

  The numerical values of all the data items (1) to (5), (a) to (i), and (I) described above are sent to the data integration device 65. The data integration device 65 integrates sludge data, operation data, and cake data to create a data set. More specifically, the data integration device 65 associates the numerical value of each data item with the time when the numerical value was acquired, and creates a data set indicating the relationship between the numerical value of each data item and the corresponding time. . The data set is created as a CSV file, for example. The data integration device 65 is configured to receive a command from the analysis device 62 described above, create a data set, and send the data set to the analysis device 62. A data logger or the like is used for the data integration device 65. The data integration device 65 and the operation control unit 5 may be configured as a single device.

  The analysis device 62 predicts the cake by inputting the current values of the data items (1) to (5) of the sludge data included in the data set and the current values of the operation parameters (a) to (h) into the calculation model. Calculate moisture content. The dehydration system further includes a computer 80 that builds a calculation model based on the data set. The computer 80 is connected to the analysis device 62 via a network such as the Internet.

  The computer 80 is configured to receive a data set from the analysis device 62 and build a calculation model for calculating the predicted moisture content of the cake. The computer 80 may receive the data set from the data integration device 65. The computer 80 includes a storage device 81, and a program for causing the computer 80 to construct a calculation model is stored in the storage device 81. The algorithm that this program causes the computer 80 to execute is machine learning. That is, the program causes the computer 80 to execute machine learning using the data set, and constructs a calculation model derived from the data set. Specific examples of machine learning algorithms include deep learning, random forest, regression tree, support vector regression, and partial least square regression. Simple multiple regression analysis is not used in this embodiment because if the explanatory variables have collinearity, the obtained regression equation will not be stable and the prediction accuracy will not increase.

  A calculation model used before the operation of the dehydrating apparatus 1 is constructed by the computer 80 using data obtained by a jar test or a dehydration test for determining the injection rate of the flocculant. When the operation of the dehydrator 1 is started, a data set including sludge data, operation data, and cake data is sent to the computer 80 regularly or irregularly. Each time the computer 80 receives a data set, the computer 80 constructs a new calculation model, and sends the constructed new calculation model to the analysis device 62. The analysis device 62 updates the stored calculation model to a new calculation model. The data set sent from the analysis device 62 or the data integration device 65 is stored in the storage device 81 and a database is constructed in the storage device 81.

  FIG. 2 is a conceptual diagram of the dehydration system. As shown in FIG. 2, sludge data, operation data, and cake data are sent to a data integration device 65, and the data integration device 65 integrates these data to create a data set. The analysis device 62 receives the data set from the data integration device 65 regularly or irregularly, and inputs the current value of the sludge data and the current value of the operation parameter into the calculation model, thereby calculating the predicted moisture content of the cake. For example, the analysis device 62 may receive a data set from the data integration device 65 at a preset time interval (for example, 30 minutes to 120 minutes) and calculate the predicted moisture content of the cake or included in the sludge data. When the numerical value of a certain data item becomes equal to a preset threshold value, the data set may be received from the data integration device 65 to calculate the predicted moisture content of the cake. In the example shown in FIG. 2, the analysis device 62 receives the data set from the data integration device 65 when the numerical value of the concentration contained in the sludge data becomes equal to a preset threshold value, and predicts the moisture content of the cake. Is calculated.

  In the present embodiment, the analysis device 62 does not always receive the data set from the data integration device 65 and calculates the predicted moisture content of the cake, but the data set is a data integration device at a certain time interval or irregularly. Since the data is received from 65, the data transmission load can be reduced. Furthermore, the processing capability (calculation capability) required for the analysis device 62 is low, and an inexpensive computer can be used for the analysis device 62.

  According to the present embodiment, the calculation model constructed based on the sludge data, the operation data of the dewatering device 1 and the cake data is used, so the analysis device 62 calculates the accurate predicted moisture content of the cake. Can do. When the communication between the analysis device 62 and the computer 80 is interrupted, the analysis device 62 cannot update the calculation model, but calculates the predicted moisture content of the cake using the stored current calculation model. Can do. Therefore, the dehydrator 1 can continue its operation.

  In one embodiment, the analysis device 62 is an edge server disposed in a factory where the dehydrating device 1 (screw press 2 and coagulation mixing tank 3) is installed, and the computer 80 is a host disposed outside the factory. It is a server. The computer 80 may be installed at a remote place. Further, in one embodiment, the host server may be connected to a plurality of edge servers arranged in a plurality of factories, and may send a newly constructed calculation model to each of these edge servers.

  The analysis device 62 is configured to determine a plurality of numerical patterns of operating parameters that allow the predicted moisture content of the cake to be within the target range. The target range is a predetermined numerical range, for example, a numerical range indicating that the moisture content of the cake is 70% or less. Usually, there are several combinations of operating parameter values that allow the predicted moisture content of the cake to fall within the target range. For example, the water content of the cake produced by the screw press 2 can be set to 70% or less, the sludge flow rate (operation parameter of the data item (a)), the injection rate of the flocculant (operation parameter of the data item (b)). ) And a combination of rotational speeds of the screw blades 36 (operation parameters of the data item (d)) exist in a plurality of patterns.

  Therefore, the analysis device 62 calculates the predicted moisture content of the cake by inputting the current value of the sludge data and the current value of the operation parameter into the calculation model, and the predicted moisture content of the cake can be within the target range. Determine multiple numerical patterns of operating parameters. In FIG. 2, the analysis device 62 determines three numerical patterns, that is, a numerical pattern A, a numerical pattern B, and a numerical pattern C.

FIG. 3 is a schematic diagram illustrating an example of three numerical patterns of operation parameters that allow the predicted moisture content of the cake to be within the target range. The combination of numerical values constituting the operation parameter differs between the numerical patterns, but the calculated predicted moisture content of the cake is within the target range in any numerical pattern. The analysis device 62 is configured to calculate a cost estimation value that is expected when the dehydration device 1 (screw press 2 and coagulation mixing tank 3) is operated with operation parameters in each numerical pattern. The estimated cost value is an evaluation index value for selecting one numerical pattern from a plurality of numerical patterns, and is calculated for each numerical pattern. In the present embodiment, the cost estimation value is the cost [yen / m ³ ] per unit volume of the sludge to be treated.

  The analysis device 62 calculates a plurality of evaluation index values respectively corresponding to a plurality of numerical patterns of operating parameters, determines an optimum evaluation index value among the plurality of evaluation index values, and sets the determined evaluation index value The numerical value of the operation parameter of the corresponding numerical pattern is sent to the dehydrator 1. More specifically, the analysis device 62 calculates a plurality of cost trial calculation values respectively corresponding to a plurality of numerical patterns of operation parameters, and determines the smallest cost trial calculation value among the plurality of cost trial calculation values. The numerical value of the operation parameter of the numerical pattern corresponding to the estimated cost value is sent to the dehydrator 1. The estimated cost value can be calculated using the electricity rate and the coagulant cost.

  In the example shown in FIG. 3, the cost estimation value of the numerical pattern B is the lowest. Therefore, the analysis device 62 determines the numerical pattern B having the lowest cost calculation value and sends the numerical value of the operation parameter of the numerical pattern B to the operation control unit 5 of the dehydrating apparatus 1. The current value of the operation parameter of the dehydrator 1 is replaced with the value of the operation parameter of the numerical pattern B or displayed on a display device (not shown) of the dehydrator 1.

  In the embodiment described above, the dehydrating apparatus 1 includes the screw press 2 as a pressure dehydrator. In one embodiment, the dehydrating apparatus 1 includes a type other than the screw press as a pressure dehydrator, such as a filter press and a centrifuge. May be. Moreover, the coagulation mixing tank 3 may be comprised from two tanks, a mixing tank and a coagulation tank.

  The embodiment described above is described for the purpose of enabling the person having ordinary knowledge in the technical field to which the present invention belongs to implement the present invention. Various modifications of the above embodiment can be naturally made by those skilled in the art, and the technical idea of the present invention can be applied to other embodiments. Accordingly, the present invention is not limited to the described embodiments, but is to be construed in the widest scope according to the technical idea defined by the claims.

DESCRIPTION OF SYMBOLS 1 Dehydrator 2 Screw press 3 Coagulation mixing tank 5 Operation control part 6 Container 8 Stirrer 9 Stirrer blade 10 Stirrer motor 12 Pump 14 Sludge introduction pipe 18 Sludge transfer pipe 20 Sludge inlet 22 Temperature sensor 24 Sludge concentration meter 30 Filter cylinder 35 Screw Shaft 36 Screw blade 38 Screw motor 40 Blocking wall 41 Discharge chamber 45 Filtrate receiver 50 Back pressure plate 51 Back pressure plate drive device 52 Plug 53 Chute 55 Cleaning device 62 Analysis device 65 Data integration device 71 Pressure sensor 80 Computer 81 Storage device

Claims (7)

A dehydrator that removes liquid from the suspension to produce a turbid residue;
Stores suspension data indicating the state of the suspension, operation data including a plurality of operation parameters of the dewatering device, and a calculation model built in advance based on turbid residue data indicating the state of the turbid residue Equipped with an analysis device
The analysis apparatus calculates a predicted state value of the turbid residue by inputting a current value of the suspension data and a current value of the operation parameter into the calculation model.   The analysis device calculates the predicted state value at a preset time interval or when a value of a data item included in the suspension data becomes equal to a preset threshold value. The dehydration system according to claim 1.   The dehydration according to claim 1, further comprising a computer that performs machine learning using the suspension data, the operation data, and the turbid residue data to construct the calculation model. system. The computer executes machine learning using the suspension data, the operation data, and the turbid residue data to construct a new calculation model, and sends the new calculation model to the analysis device.
The dehydration system according to claim 3, wherein the analysis device updates the stored calculation model to the new calculation model.   5. The data integration device according to claim 1, further comprising a data integration device that integrates the suspension data, the operation data, and the turbid residue data to create a data set. Dehydration system.   The dehydrating system according to any one of claims 1 to 5, wherein the analysis device determines a plurality of numerical patterns of the operation parameters that allow the predicted state value to fall within a target range. The analysis device includes:
Calculating a plurality of evaluation index values respectively corresponding to the plurality of numerical patterns;
Determining an optimal evaluation index value among the plurality of evaluation index values;
The dehydrating system according to claim 6, wherein a numerical value of the operation parameter in a numerical pattern corresponding to the determined evaluation index value is sent to the dehydrating apparatus.

Images