JP2021037508A - Dewatering system - Google Patents

Abstract

To provide a dewatering system capable of acquiring image data of the condition of suspensions such as sludge and slurry, determining whether the operating condition is right or wrong based on the image data, and keeping the water content of turbid residue within the target range and maintain it stably.SOLUTION: A dewatering system includes a suspension reservoir 1, an aggregation apparatus 3, a dewatering apparatus 5, imaging devices 29,31,33,64,65 which generate image data of at least one of the suspension, aggregate, turbidity residue, and liquid removed from the suspension, and a control system 6 having a learned model constructed by machine learning algorithm. The control system 6 has a processing unit 6b which inputs the image data into the learned model and performs operations to output from the learned model, the optimal operating parameters of the dewatering system capable of keeping the moisture content of the turbid residue discharged from the dewatering unit 5 within the target range.SELECTED DRAWING: Figure 1

Description

The present invention relates to a dehydration system that separates a suspension such as sludge or slurry into a turbid substance and a liquid, and particularly to a dehydration system capable of optimal automatic operation.

Traditionally, suspensions (eg, sludge) discharged from liquid treatment facilities such as sewage treatment plants, urine treatment plants, and industrial wastewater treatment plants are squeezed to separate water from the suspension (ie, dehydrate). ) A dehydrator is used. In the dehydration step, the suspension in which the coagulant is injected is stirred in a coagulation tank to form a coagulation floc to facilitate solid-liquid separation, and then dehydrated by a concentrator or a dehydrator.

A screw press, which is an example of a dewatering device, is known as a sludge dewatering machine. This screw press includes a filter cylinder formed from a screen (perforated plate) and a screw arranged inside the filter cylinder, and by rotating the screw, sludge charged into the filter cylinder is squeezed. , Dehydrate. A back pressure plate that dams up sludge is placed at the downstream opening end of the filtration tube, and this back pressure plate allows the cake (dehydrated sludge) sent by the rotating screw to stay, and a plug (plug) made of cake. ) Is formed. This plug applies back pressure to the cake that is delivered later, further squeezing the cake. The cake forming the plug is pushed by the subsequent cake and gradually discharged from the filter tube. In this way, a cake with a low water content is formed by a screw press.

Japanese Unexamined Patent Publication No. 2018-111065 Japanese Unexamined Patent Publication No. 2000-246147

By keeping the water content of the cake finally obtained by the sludge dewatering treatment low, the amount of cake to be discarded can be reduced. In order to keep the moisture content of the cake as low and stable as possible, it is important to operate the sludge to optimize the sludge condition in each process of agglomeration and dehydration according to the sludge properties and load. However, the moisture content of the cake can change due to various factors such as sludge properties that fluctuate daily and the operating condition of the equipment in each process.

On the other hand, AI has made it possible to realize fully automated operation by collecting various information inside and outside the sewage treatment facility and using the collected information to set (or reset) the appropriate operation pattern of the dehydrator. There is a dehydration method of a (artificial intelligence) control method (see, for example, Patent Document 1). However, even if the operation is controlled based on various collected information, it is difficult to completely grasp the sludge properties derived from various substances discharged as sewage or the like as a result of different human life every day. In order to optimize the operation of the dehydrator, it is necessary for the operator to visually check the current sludge to grasp the state of sludge in each process.

However, in order for the operator to optimize the operating condition based on the visual inspection of sludge, the operator's abundant experience and know-how are required. Furthermore, the operating condition may differ depending on the operator, and as a result, the moisture content of the cake may not be stable.

Therefore, in the present invention, the state of a suspension such as sludge or slurry is acquired as image data, the quality of the operating state is determined based on the image data, and the water content of the turbid residue (for example, cake) is within the target range. It is an object of the present invention to provide a dehydration system that can be contained and maintained stably.

In one aspect, it is a dehydration system for removing liquid from a suspension, in which a suspension storage tank for storing the suspension and agglomeration for stirring the suspension and a coagulant to form agglomerates. The device, a dehydrator that removes liquid from the agglomerates to form a turbid residue with a concentration of 3-50 wt%, and the suspension, the agglomerates, the turbid residue, and the suspension. The control system includes an image pickup device that generates at least one image data of the liquid and a control system having a trained model constructed by a machine learning algorithm, and the control system includes a storage device in which the trained model is stored. , The image data is input to the trained model, and the optimum operating parameters of the dehydration system capable of keeping the water content of the turbid residue discharged from the dehydrator within the target range are output from the trained model. A dehydration system is provided that includes a processing device that performs operations to perform.

In one aspect, it is a dehydration system for removing a liquid from a suspension, in which a suspension storage tank for storing the suspension and agglomeration for stirring the suspension and a coagulant to form agglomerates. An apparatus, a concentrator that removes a liquid from the agglomerate to form a concentrate having a concentration of 3 to 15 wt%, and a dehydrator that removes the liquid from the concentrate to form a turbid residue having a concentration of 3 to 50 wt%. And an imaging device that generates at least one of the suspension, the agglomerates, the concentrate, the turbid residue, and the liquid removed from the suspension, and a machine learning algorithm. A control system having the trained model is provided, and the control system inputs the storage device in which the trained model is stored and the image data into the trained model, and the turbidity discharged from the dehydration device. Provided is a dehydration system comprising a processing device that performs an operation to output the optimum operating parameters of the dehydration system from the trained model capable of keeping the water content of the residue within a target range.

In one aspect, the concentrator is a rotary disk type liquid drainer.
In one aspect, the control system can input the image data and the state data of the dehydration system into the trained model to keep the water content of the turbid residue discharged from the dehydrator within the target range. It is configured to cause the processing apparatus to perform an operation for outputting the optimum operating parameters of the dehydration system that can be performed from the trained model.

In one aspect, it is a dehydration system for removing liquid from a suspension, a coagulator that stirs the suspension and a flocculant to form agglomerates, and a coagulant that removes the liquid from the agglomerates and becomes turbid. The control system includes a dehydrator that forms a residue, an image pickup device that generates image data of the turbid residue discharged from the dehydrator, and a control system having a trained model constructed by a machine learning algorithm. , The storage device in which the trained model is stored and the image data are input to the trained model, and an operation index value indicating that the operating state of the dehydration system is normal or abnormal is output from the trained model. A dehydration system is provided that includes a processing device that performs operations to perform.

In one aspect, the control system is configured to calculate a moving average of the driving index values.
In one aspect, the control system determines that the operation of the dehydration system is abnormal when the moving average of the operating index values exceeds a threshold.
In one aspect, the control system resets the operation of determining an operating abnormality of the dehydration system when the moving average of the operating index values drops to a predetermined normal level.

According to the present invention, the trained model constructed by the machine learning algorithm can keep the water content of the turbid residue (for example, cake) remaining after removing the liquid from the suspension (for example, sludge) within the target range. The overall operation of the dehydration system can be optimized by generating the optimum operating parameters that can be made and applying the operating parameters to the aggregator and / or dehydrator.

In particular, according to the present invention, instead of the operating parameters previously determined by veteran operators based on the visual inspection of the suspension, the dehydration system uses a trained model to determine the water content of the turbid residue. Optimal operating parameters that can be kept within the target range can be generated. Therefore, the dehydration system can determine the excess or deficiency of the coagulant addition rate, adjust the stirring speed for coagulation, adjust the operation parameters of the dehydrator, etc. in real time, as accurately as or better than the veteran operator. It is possible to do.

It is a figure which shows one Embodiment of a dehydration system. It is a schematic diagram which shows an example of a trained model. It is a figure which shows the other embodiment of the dehydration system. It is a figure which shows still another embodiment of a dehydration system. It is a graph which shows the execution result using the dehydration system. It is a graph which shows the execution result using the dehydration system. It is a graph which shows the execution result using the dehydration system. It is a graph which shows the time change of the operation index value output from the 2nd trained model during operation of a dehydration system. It is a graph which shows the time change of the moving average of the operation index value shown in FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing an embodiment of a dehydration system. The dehydration system includes a suspension storage tank 1 for storing a suspension, a coagulation device 3 for injecting a coagulant into the suspension and agitating the coagulant and the suspension to form agglomerates, and a coagulation device 3. A concentrator 4 that removes a liquid from an object to form a concentrate, a dehydrator 5 that further removes the liquid from a concentrate composed of concentrated aggregates to form a turbid residue, an aggregator 3, and a concentrator. A control system 6 for controlling the operation of the dehydration device 5 and the dehydration device 5 is provided. The concentrator 4 is a device for removing a liquid from the agglomerates formed by the agglutinator 3 to form a concentrate having a concentration of 3 to 15 wt%, and the dehydrating device 5 is a device for forming the agglomerates formed by the agglutinator 3. Alternatively, the device removes the liquid from the concentrate formed by the concentrator 4 to form a turbid residue having a concentration of 3 to 50 wt%.

The turbid residue is a substance with a low water content that remains after removing the liquid from the suspension. The turbid residue that remains after the liquid is removed from the suspension by the dehydrator 5 is commonly referred to as a cake. In the following description, the suspension is referred to as sludge and the turbid residue is referred to as cake. Specific examples of sludge include sludge generated during the treatment of sewage or human waste and industrial wastewater. Examples of suspensions other than sludge include industrial wastes or slurries generated during the production of industrial products such as foods, cosmetics, and paper.

In the present embodiment, the concentrator 4 is a rotary disk type liquid removing device (for example, a slit saver manufactured by Kenden Co., Ltd.). This type of concentrator 4 is preferable because it is easy to grasp the change of state of the concentrated sludge, but the type of the concentrator 4 is not particularly limited. For example, the concentrator 4 may be a drum type, a screw type, or a belt type. The dehydrator 5 of the present embodiment is composed of a screw press that pressurizes and dehydrates sludge. The screw press is an example of a pressure dehydrator that dehydrates sludge. As the screw press, a press-fit type, a shaft sliding type, and a two-stage type can be used. The dehydrator 5 shown in FIG. 1 is a shaft-sliding type screw press. Further, as the pressure dehydrator, other types such as a filter press and a centrifuge can be used in addition to the screw press.

As shown in FIG. 1, the coagulation device 3 includes a coagulation and mixing tank 7 for accommodating sludge and mixing sludge with a coagulant, a stirrer 8 for stirring sludge in the coagulation and mixing tank 7, and a coagulation and mixing tank 7. It is provided with a sludge introduction pipe (suspension introduction pipe) 14 connected to the sludge introduction pipe 14 and a pump 12 provided in the sludge introduction pipe 14. The stirrer 8 includes a stirrer blade 9 arranged in the coagulation mixing tank 7 and a stirrer motor 10 connected to the stirrer blade 9. The suspension storage tank 1 is connected to the coagulation mixing tank 7 by a sludge introduction pipe 14. The sludge is transferred from the suspension storage tank 1 to the coagulation mixing tank 7 through the sludge introduction pipe 14 by the pump 12. The flow rate of sludge to the coagulation mixing tank 7 can be adjusted by operating the pump 12.

The pump 12 is connected to the control system 6, and the operation of the pump 12, that is, the flow rate of sludge to the coagulation mixing tank 7, is controlled by the control system 6. A temperature sensor 22 is attached to the sludge introduction pipe 14. The temperature sensor 22 is configured to measure the temperature of sludge introduced into the coagulation mixing tank 7. Further, a sludge concentration meter (suspension 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 7 is measured by the sludge concentration meter 24. ..

The dehydration system includes a suspension imaging device 29 that generates image data of sludge (suspension before treatment) in the suspension storage tank 1. The suspension imaging device 29 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the suspension imaging device 29 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object. The suspension imaging device 29 is connected to the control system 6, and the image data of the sludge (suspension) generated by the suspension imaging device 29 is sent to the control system 6.

The coagulation device 3 further includes a water supply line 26 connected to the coagulation mixing tank 7 and a flow rate control valve 27 attached to the water supply line 26. The water supply line 26 supplies water into the coagulation and mixing tank 7 to dilute the sludge in the coagulation and mixing tank 7. The flow rate of water supplied to the coagulation mixing tank 7 through the water supply line 26 is adjusted by the flow rate control valve 27. The flow rate control valve 27 is connected to the control system 6, and the operation of the flow rate control valve 27, that is, the flow rate of water is controlled by the control system 6. In one embodiment, the water supply line 26 may be connected to the sludge introduction pipe 14 and water may be directly supplied to the sludge introduction pipe 14.

The coagulation device 3 further includes a coagulant supply device 28 connected to the coagulation mixing tank 7. The coagulant supply device 28 is configured to inject the coagulant into the sludge in the coagulation mixing tank 7 at a predetermined flow rate. The flow rate of the coagulant injected into the sludge in the coagulation mixing tank 7 is adjusted by the coagulant supply device 28. The coagulant supply device 28 is connected to the control system 6, and the operation of the coagulant supply device 28, that is, the flow rate of the coagulant is controlled by the control system 6. The sludge is agitated by the stirrer 8 together with the flocculant. By stirring the coagulant and the sludge in the coagulation mixing tank 7, agglomerates in which the suspended substances in the sludge are aggregated are formed. The agglomerates formed in the agglutinating mixing tank 7 are generally called agglutinating flocs.

The dehydration system includes an agglomerate imaging device 31 that generates image data of the agglomerates formed by the agglutinating device 3. The agglomerate imaging device 31 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the agglutination imaging device 31 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object.

The agglutination image pickup device 31 faces the inside of the agglutination mixture tank 7, and is arranged so as to generate image data of the agglutination in the agglutination mixture tank 7. The agglomerate imaging device 31 is connected to the control system 6, and the image data of the agglomerates generated by the agglutination imaging device 31 is sent to the control system 6. In one embodiment, the agglutination image pickup device 31 may be arranged so as to face the outlet of the agglutination mixture tank 7 and generate image data of the agglutination discharged from the agglutination mixture tank 7.

The coagulation-mixing tank 7 shown in FIG. 1 is a single-stage tank, but the coagulation-mixing tank 7 may be a multi-stage tank. The stirring strength of sludge can be adjusted by the rotation speed of the stirrer 8. The stirrer 8 is connected to the control system 6, and the operation of the stirrer 8, that is, the agitation intensity of sludge is controlled by the control system 6. The coagulation mixing tank 7 may be provided with side glasses so that the state of coagulation inside the coagulation mixing tank 7 can be observed.

The coagulation mixing tank 7 is connected to the concentrator 4 by a sludge transfer pipe 18. The concentrator 4 is arranged between the coagulator 3 and the dehydrator 5. The sludge composed of the agglomerates formed by the agglutinating device 3 is transferred to the concentrating device 4 through the sludge transfer pipe 18. The agglomerates are concentrated and dehydrated by the concentrator 4. An example of the concentrating device 4 is a rotary disk type liquid removing device.

The dehydration system further includes a concentrate imaging device 32 that produces image data of the concentrate (concentrated agglomerates) formed by the concentrator 4. The concentrate image pickup device 32 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the concentrate imaging device 32 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object.

The concentrate image pickup device 32 is arranged adjacent to the concentrate device 4. More specifically, the concentrate imaging device 32 faces the inside of the concentration device 4 and is arranged so as to generate image data of the agglomerates in the process of being concentrated by the concentration device 4. In one embodiment, the concentrate imaging device 32 faces the upper part of the concentrator 4 from the inlet of the concentrator 4 or the inlet of the concentrator 4, and captures image data of the concentrate in a state where the liquid is removed from the agglomerates. It may be arranged to produce, or the concentrate imaging device 32 faces the outlet of the concentrator 4 to generate image data of the agglomerates, i.e. the concentrate, after being concentrated by the concentrator 4. It may be arranged. The concentrate image pickup device 32 is connected to the control system 6, and the image data of the concentrate generated by the concentrate image pickup device 32 is sent to the control system 6.

The dehydration system further includes a separation liquid imaging device 33 that produces image data of the liquid separated from the agglomerates by the concentrator 4. The separation liquid imaging device 33 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the separation liquid imaging device 33 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object. The separation liquid imaging device 33 is arranged adjacent to the drainage drain 4a of the concentrating device 4, and is arranged so as to generate image data of the liquid discharged from the concentrating device 4. In one embodiment, the concentrator 4 has a liquid receiver (not shown) that receives the liquid discharged from the concentrator 4, and the separation liquid imaging device 33 may be arranged facing the inside of the liquid receiver. .. The separation liquid imaging device 33 is connected to the control system 6, and the image data of the liquid generated by the separation liquid imaging device 33 is sent to the control system 6.

The outlet of the concentrator 4 is arranged above the inlet 35 of the dehydrator 5, and the sludge made of the concentrate formed by the concentrator 4 is charged into the inlet 35 of the dehydrator 5. In this embodiment, the dehydrator 5 is a screw press. The dehydrator 5 as a screw press includes a filter cylinder 36, a screw shaft 37 concentrically arranged in the filter cylinder 36, a screw blade 38 fixed to the outer surface of the screw shaft 37, a screw shaft 37, and a screw blade. It includes a screw motor 40 that rotates 38 to send sludge toward the discharge chamber 41, and a shaft sliding actuator 42 connected to the screw motor 40.

The filtration tube 36 is made of a perforated plate such as punching metal. One end of the filtration cylinder 36 is sealed by a closing wall 44, and the other end of the filtration cylinder 36 is connected to the discharge chamber 41. The inlet 35 is formed in the filtration tube 36 and is adjacent to the closing wall 44.

The screw shaft 37 extends through the inside of the filtration tube 36. The screw shaft 37 has a truncated cone shape in which the diameter gradually increases toward the downstream side. The screw shaft 37 extends through the closing wall 44, and the end of the screw shaft 37 is connected to the screw motor 40. The screw motor 40 has a built-in inverter (not shown). The screw motor 40 is connected to the control system 6, and the operation of the screw motor 40, that is, the rotational speeds of the screw shaft 37 and the screw blade 38 are controlled by the control system 6.

The screw blade 38 is a single blade that spirally extends along the longitudinal direction of the screw shaft 37. A minute gap is formed between the inner surface of the filter cylinder 36 and the screw blade 38, and the screw blade 38 can rotate without contacting the filter cylinder 36. The sludge charged into the filtration cylinder 36 from the inlet 35 is transferred into the filtration cylinder 36 toward the discharge chamber 41 by the rotating screw blades 38.

The space in which sludge is transferred in the filter cylinder 36 is formed by the inner surface of the filter cylinder 36, the screw blades 38, and the screw shaft 37. The volume of this space gradually decreases along the direction of sludge travel. Therefore, the sludge is squeezed and dehydrated as it is moved through this space by the screw blades 38. The filtrate that has passed through the filter cylinder 36 is collected by the filtrate receiver 45 arranged below the filtration cylinder 36, and then discharged through the drain 46.

An annular back pressure plate 50 is arranged so as to face the downstream end of the filtration tube 36. The back pressure plate 50 has the shape of a truncated cone having a tapered surface for receiving the dehydrated sludge transferred in the filtration cylinder 36. A through hole through which the screw shaft 37 penetrates is formed in the central portion of the back pressure plate 50, and the back pressure plate 50 is arranged concentrically with the screw shaft 37. The back pressure plate 50 is not fixed to the screw shaft 37, and the back pressure plate 50 does not rotate.

The back pressure plate 50 is connected to the back pressure plate drive 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 37. The gap between the back pressure plate 50 and the downstream end of the filtration tube 36 is adjusted by the back pressure plate drive device 51. The back pressure plate drive device 51 is composed of, for example, a hydraulic cylinder or an electric cylinder. The back pressure plate drive device 51 is connected to the control system 6, and the operation of the back pressure plate drive device 51, that is, the axial position of the back pressure plate 50 is controlled by the control system 6.

The shaft sliding actuator 42 is configured to move the screw motor 40 in the axial direction of the screw shaft 37. When the shaft sliding actuator 42 moves the screw motor 40 in the axial direction, the screw shaft 37 and the screw blade 38 connected to the screw motor 40 are moved in the axial direction of the screw shaft 37 in the filtration cylinder 36.

Next, the operation of the dehydrator 5 will be described. The sludge made of the concentrate formed by the concentrator 4 is charged into the filter cylinder 36 from the inlet 35. The sludge is transferred into the filtration tube 36 toward the discharge chamber 41 by the rotating screw blade 38. As it is moved through the filter tube 36, the sludge is squeezed and dehydrated. The filtrate that has passed through the filter cylinder 36 is collected by the filtrate receiver 45 and discharged through the drain 46. The sludge is dehydrated in the filter tube 36 to form a cake. The cleaning device 55 supplies the cleaning liquid to the outer peripheral surface of the filtration tube 36 at preset time intervals.

The cake that has moved in the filter cylinder 36 is pressed against the back pressure plate 50. The cake is compressed by hindering its movement by the back pressure plate 50. The compressed cake forms a plug 52 that seals the downstream end of the filter tube 36. The plug 52 reduces the water content of the cake in the filter tube 36 by applying back pressure to the subsequent cake. While forming the plug 52 in the filtration tube 36, the cake is pushed by the subsequent cake, passes through the gap between the back pressure plate 50 and the downstream end of the filtration tube 36, and gradually enters the discharge chamber 41. It is discharged. The cake is discharged from the discharge chamber 41 through the discharge port 53 provided in the lower part of the discharge chamber 41. In this way, the liquid is removed from the sludge to form a cake with a low water content.

The clearance between the back pressure plate 50 and the downstream end of the filter cylinder 36 changes depending on the axial position of the back pressure plate 50, and as a result, the compressive force applied to the sludge in the filter cylinder 36 changes. More specifically, when the gap between the back pressure plate 50 and the downstream end of the filter cylinder 36 becomes smaller, a larger force is required to push out the plug 52, so that the compression applied to the sludge in the filter cylinder 36 is applied. Power increases. Therefore, the compressive force applied to the sludge can be adjusted not only by the rotation speed of the screw blade 38 but also by the position of the back pressure plate 50. A pressure sensor 61 is arranged in the filter cylinder 36, and the pressure of sludge in the filter cylinder 36 is measured by the pressure sensor 61. The pressure sensor 61 is connected to the control system 6, and the measured value of the sludge pressure is sent to the control system 6. The position of the pressure sensor 61 is not particularly limited as long as it is inside the filter cylinder 36, and may be any of the front stage, the middle stage, or the rear stage in the filter cylinder 36, and a plurality of pressure sensors 61 are arranged in the filter cylinder 36. You may.

The plug 52 is made of a cake with a low moisture content. When the water content of the cake forming the plug 52 decreases, the plug 52 becomes hard and may block the downstream end of the filtration tube 36. In such a case, the shaft sliding actuator 42 can forcibly discharge a hard cake having a low water content by moving the screw shaft 37 and the screw blade 38 in the axial direction. As a result, the dehydrator 5 enables stable continuous operation.

The dehydration system includes a cake imaging device 64 that generates image data of a cake (a turbid residue having a low water content) formed by the dehydrator 5, and a dehydration filtrate that generates image data of a filtrate discharged from the dehydrator 5. The image pickup apparatus 65 is provided. The cake imaging device 64 and the dehydration filtrate imaging device 65 are digital cameras equipped with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the cake imaging device 64 and the dehydration filtrate imaging device 65 may be hyperspectral cameras capable of capturing an object by decomposing light for each wavelength.

The cake imaging device 64 may be arranged adjacent to the discharge port 53 of the dehydrating device 5, or may be arranged adjacent to the back pressure plate 50 from which the cake is discharged. Further, the cake imaging device 64 may be arranged in the discharge port 53 or the discharge chamber 41. The dehydration filtrate imaging device 65 is arranged adjacent to the drain 46 of the dehydration device 5. In one embodiment, the dehydrated filtrate imaging device 65 may be arranged facing the inside of the filtrate receiver 45 to generate image data of the filtrate received by the filtrate receiver 45. Further, in one embodiment, the dehydration filtrate imaging device 65 may be arranged so as to face the lower surface of the filter tube 36. The cake imager 64 and the dehydration filtrate imager 65 are connected to the control system 6, and the cake image data and the filtrate image data generated by the cake imager 64 and the dehydration filtrate imager 65 are controlled. It is designed to be sent to system 6.

The dehydration system further includes a filter tube imaging device 66 that generates image data of the outer surface of the filter tube 36. The filter tube imaging device 66 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the filter tube imaging device 66 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object.

The filter tube imaging device 66 is arranged above the filter tube 36, and generates image data of the outer surface of the filter tube 36 when the dehydrator device 5 is squeezing sludge. More specifically, the filter tube imaging device 66 is arranged so as to generate image data of turbidity (solid matter in sludge) leaking from the filter tube 36. In one embodiment, the filter tube imager 66 may be arranged laterally or below the filter tube 36. The filter tube image pickup device 66 is connected to the control system 6, and the image data of the outer surface of the filter tube 36 generated by the filter tube image pickup device 66 is sent to the control system 6.

The water content of the cake (turbid residue) formed by the dehydrator 5 is the state of the sludge introduced into the coagulator 3 and the operating state of the dehydration system (that is, the coagulator 3, the concentrator 4, and the dehydrator 5). It changes depending on the operating condition).

Therefore, the control system 6 acquires the image data generated by the above-mentioned imaging devices 29, 31, 32, 33, 64, 65, 66, and optimizes the operation parameters of the dehydration system based on these image data. It is configured in. The control system 6 inputs the storage device 6a in which the trained model constructed by the machine learning algorithm is stored and the image data into the trained model, and the water content of the cake (turbid residue) discharged from the dehydration device 5. Is provided with a processing device 6b that executes an operation for outputting the optimum operating parameters of the dehydration system that can keep the above within the target range from the trained model.

The storage device 6a includes a main storage device accessible to the processing device 6b, and an auxiliary storage device for storing programs, trained models, and data. The main storage device is, for example, a random access memory (RAM), and the auxiliary storage device is a storage device such as a hard disk drive (HDD) or a solid state drive (SSD). The processing device 6b is composed of a CPU (central processing unit), a GPU (graphic processing unit), and the like.

The control system 6 is composed of at least one computer. The at least one computer may be one server or a plurality of servers. The control system 6 may be an edge server connected to the image pickup devices 29, 31, 32, 33, 64, 65, 66 by a communication line, or the image pickup devices 29, 31, 32, 33 via a network such as the Internet. , 64, 65, 66 may be a cloud server, or a fog computing device installed in a network connected to image pickup devices 29, 31, 32, 33, 64, 65, 66 ( It may be a gateway, fog server, router, etc.). The control system 6 may be a plurality of servers connected by a network such as the Internet. For example, the control system 6 may be a combination of an edge server and a cloud server.

The trained model is composed of a neural network. The storage device 6a stores a program for constructing a trained model according to a machine learning algorithm. The processing device 6b constructs a trained model by executing an operation according to an instruction included in the program. Building a trained model according to a machine learning algorithm involves optimizing parameters such as neural network weights.

Examples of machine learning algorithms include the SVR method (support vector regression method), PLS method (partial least squares method: Partial First Squares), deep learning method (deep learning method), random forest method, and decision tree method. However, the deep learning method is particularly preferable. The deep learning method is a learning method based on a neural network in which hidden layers are multi-layered. In this specification, machine learning using a neural network composed of an input layer, two or more hidden layers, and an output layer is referred to as deep learning. By using the deep learning method, it is possible to determine the state of sludge, agglomerates, concentrates, etc., which have been determined based on human eyes and experience, by a computer based on image data.

The trained model keeps the past image data generated by the imaging devices 29, 31, 32, 33, 64, 65, 66 and the water content of the cake (turbid residue) discharged from the dehydrating device 5 within the target range. It is a model constructed according to a machine learning algorithm using training data including multiple combinations with the optimum operating parameters of the dehydration system that can be stored in. The past image data generated by the above imaging device is an explanatory variable, and the optimum operating parameter of the dehydration system that can keep the water content of the cake (turbid residue) discharged from the dehydrator 5 within the target range is The objective variable. The optimum operation parameter that constitutes the training data is the correct answer data, and the operation is determined by a skilled operator based on the state of sludge, agglomerates, concentrates, etc. and the water content of the cake discharged from the dehydrator 5. It is a parameter. The training data is also called training data or teacher data.

Keep the image data generated by the imagers 29, 31, 32, 33, 64, 65, 66 and the moisture content of the cake within the target range in order to optimize the parameters (weights, etc.) of the trained model. Training data including many combinations with the optimum operating parameters that can be performed is prepared. The control system 6 constructs a trained model by a machine learning algorithm using this training data. The parameters of the trained model may include biases in addition to weights. The trained model constructed in this way is stored in the storage device 6a.

The control system 6 acquires image data from the image pickup apparatus 29, 31, 32, 33, 64, 65, 66 at a predetermined cycle and stores the image data in the storage apparatus 6a. The control system 6 inputs the image data to the trained model, and outputs the optimum operation parameters that can keep the moisture content of the cake within the target range from the trained model.

In the present embodiment, the image data generated by all of the above-mentioned image pickup devices 29, 31, 32, 33, 64, 65, 66 is input to the trained model, but in one embodiment, the image pickup devices 29, 31 , 32, 33, 64, 65, 66 may be input to the trained model with image data generated by at least one of them. In this case, the same type of image data as the image data input to the trained model is used to build the trained model. For example, when the image data generated by the agglomerate imager 31 and the concentrate imager 32 is input to the trained model, the past image data generated by the agglomerate imager 31 and the concentrate imager 32 is input. A trained model is constructed using the training data included.

FIG. 2 is a schematic diagram showing an example of the trained model. The trained model is a neural network having an input layer 201, a plurality of hidden layers (also referred to as intermediate layers) 202, and an output layer 203. The model shown in FIG. 2 has four hidden layers 202, but the configuration of the trained model is not limited to the embodiment shown in FIG. The trained model may have five or more hidden layers 202.

Image data is input to the input layer 201 of the trained model. More specifically, the numerical value of each pixel constituting the image data is input to the input layer 201. When the image data is color image data, numerical values representing red, green, and blue of each pixel are input to the corresponding nodes (neurons) of the input layer 201 of the trained model. The control system 6 composed of at least one computer executes the calculation according to the algorithm of the multi-layer perceptron constituting the neural network, and the output layer 203 of the trained model determines the water content of the cake discharged from the dehydrator 5. Outputs a numerical value that represents the operating parameters that can be kept within the target range. However, the configuration of the trained model shown in FIG. 2 is an example, and the present invention is not limited to the example shown in FIG.

Specific examples of the operation parameters output from the trained model are as follows.
・ Excess or deficiency of sludge flow rate to the coagulation mixing tank 7 → Increase or maintenance or decrease of the rotation speed of the pump 12 ・ Inappropriate for the suitability of the coagulant → Maintain or maintain the use of the coagulant・ Excess or deficiency of the flow rate of the coagulant for the appropriate range → Increase or maintenance or decrease of the operating speed of the coagulant supply device 28 ・ Excess or deficiency of the stirring speed of the stirrer 8 → Rotation of the stirring motor 10 Increase or maintain or decrease the speed ・ Excess or deficiency of the flow rate of water supplied to the coagulation mixing tank 7 → Increase or maintain or decrease the opening of the flow control valve 27 ・ Operating speed of the concentrator 4 Excess or deficiency with respect to the appropriate range → increase or maintenance, or decrease ・ Excess or deficiency with respect to the appropriate range of the adjustment variable (for example, pressing plate pressure adjustment) of the concentrator 4 → increase or maintenance or decrease ・ Rotation speed of the screw shaft 37 Excess or deficiency with respect to the appropriate range → Increase or maintenance or decrease of the rotation speed of the screw motor 40 ・ Excess or deficiency with respect to the appropriate range of the opening degree of the back pressure plate 50 → Increase or maintenance or decrease ・ Appropriate rotation torque of the screw shaft 37 Excess or deficiency of the range → Increase, maintain, or decrease the current to the screw motor 40

The above-mentioned operation parameters are examples, and the operation parameters output from the trained model may be only one of the above-mentioned operation parameters.

Conventionally, a skilled operator visually determines the state of agglomerates, concentrates, cakes, etc., and appropriately sets the above operating parameters based on experience. However, in the present embodiment, the control system is used. In No. 6, image data such as agglomerates, concentrates, and cakes are input to the model, and the optimum operation parameters are output from the trained model. By applying these operating parameters to the aggregating device 3, the concentrating device 4, and the dehydrating device 5, the overall operation of the dehydrating system can be optimized.

In order to output more optimized operating parameters from the trained model, the training data used to build the trained model is the past image data as well as the dehydration system when the past image data was generated. It may include state data. Specific examples of the state data of the dehydration system are as follows.
-Sludge temperature (measured by temperature sensor 22)
-Flow rate of sludge to the coagulation mixing tank 7 (estimated from the rotation speed of the pump 12)
・ Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids amount)
・ Physical characteristics of flocculant (cationism, molecular weight)
-Flow rate of coagulant (operating speed of coagulant supply device 28)
-Stirring speed of the stirrer 8 (rotational speed of the stirrer motor 10)
-Flow rate of water to the coagulation mixing tank 7 (opening of flow control valve 27)
-Operating speed of the concentrator 4 (rotational speed of the drive motor of the concentrator 4)
-Operating torque of the concentrator 4 (current value to the drive motor of the concentrator 4)
-Flow rate of the liquid separated by the concentrator 4 (measured by a flow meter (not shown))
-Sludge concentration concentrated by the concentrator 4 (measured by a concentration sensor (not shown))
-Rotation speed of screw shaft 37-Current value (torque value) to screw motor 40
-Sludge pressure in the filter tube 36 (measured by the pressure sensor 61)
Opening degree of back pressure plate 50 (set value of back pressure plate drive device 51)
-Pressure of back pressure plate 50 (measured by a pressure sensor (not shown))
-Measured value of cake moisture content (measured by a measuring device (not shown) or manually)

The item of the state data of the dehydration system described above is an example, and the state data of the dehydration system may be only one of the above items.

The trained model is the past image data generated by at least one of the imaging devices 29, 31, 32, 33, 64, 65, 66 and the state of the dehydration system when the past image data is generated. It is constructed according to a machine learning algorithm using learning data that includes multiple combinations of data and optimal operating parameters of a dehydration system that can keep the moisture content of the cake discharged from the dehydrator 5 within the target range. .. The past image data and the state data of the dehydration system when the past image data are generated are explanatory variables, and the dehydration system capable of keeping the water content of the cake discharged from the dehydrator 5 within the target range. The optimum operating parameter of is the objective variable. While the dehydration system is in operation, the control system 6 captures the current image data generated by at least one of the imaging devices 29, 31, 32, 33, 64, 65, 66 and the current state data of the dehydration system. The processing device 6b is made to perform an operation for inputting to the trained model and outputting the optimum operation parameters of the dehydration system from the trained model.

FIG. 3 is a diagram showing another embodiment of the dehydration system. The dehydration system shown in FIG. 3 differs from the embodiment of FIG. 1 in that a two-stage screw press is used as the dehydration device 5, and a shaft-sliding type screw press is used. In this embodiment, the shaft sliding actuator 42 shown in FIG. 1 is not provided. Since the configurations and operations of the embodiments not particularly described are the same as those of the embodiments shown in FIGS. 1 and 2, the duplicated description thereof will be omitted.

The dehydrator 5 composed of a two-stage screw press is arranged concentrically with the filtration cylinder 36 in the filtration cylinder 36 and the first screw 71 and the second screw 72 for transferring sludge. A first screw motor 75 that rotates the first screw 71 and a second screw motor 76 that rotates the second screw 72 independently of the first screw 71 are provided. The operations of the first screw motor 75 and the second screw motor 76 are controlled by the control system 6.

The first screw motor 75 and the second screw motor 76 may be directly connected to the first screw 71 and the second screw 72, respectively, or the first screw may be connected to a torque transmission mechanism composed of a chain, a sprocket, or the like. It may be connected to 71 and the second screw 72, respectively.

The filtration cylinder 36 is formed of a screen (perforated plate) such as punching metal. An inlet 35 is formed at the upstream end of the filtration tube 36. The sludge charged into the filter cylinder 36 from the charging port 35 is transferred in the filter cylinder 36 in a predetermined transfer direction by the rotating first screw 71 and the second screw 72. The downstream end of the filtration tube 36 is connected to the discharge chamber 41.

The second screw 72 is connected to the first screw 71 so that it can rotate independently of the first screw 71. The first screw 71 and the second screw 72 extend through the filtration cylinder 36 and the discharge chamber 41, respectively. The discharge chamber 41 is connected to the filtration cylinder 36. A plug 77 made of cake is discharged from the filtration tube 36 into the discharge chamber 41. The axial length of the second screw 72 is shorter than the axial length of the first screw 71. The first screw 71 has a truncated cone-shaped first screw shaft 71A whose diameter gradually increases along the sludge transfer direction, and a first screw blade 71B fixed to the outer surface of the first screw shaft 71A. doing. The second screw 72 has a cylindrical second screw shaft 72A and a second screw blade 72B fixed to the outer surface of the second screw shaft 72A.

The upstream end of the filter tube 36 is sealed by a closing wall 44. The upstream end of the first screw shaft 71A extends through the closing wall 44 and is connected to a first screw motor 75 for rotating the first screw 71. The second screw shaft 72A of the second screw 72 is arranged concentrically with the first screw shaft 71A. The outer diameter of the second screw shaft 72A is the same as the maximum diameter of the first screw shaft 71A. The downstream end of the second screw shaft 72A extends through the wall 41A constituting the discharge chamber 41 and is connected to the second screw motor 76 for rotating the second screw 72. The lower part of the discharge chamber 41 is connected to the discharge port 53.

The first screw motor 75 is connected to the control system 6. An inverter (not shown) is built in the first screw motor 75, and the control system 6 is configured to be able to control the operation of the first screw motor 75 via the inverter. That is, the control system 6 can control the rotation speed and the rotation direction of the first screw motor 75 via the inverter. The control system 6 can issue a command to the first screw motor 75 to rotate the first screw 71 independently of the second screw 72.

The second screw motor 76 is also connected to the control system 6. An inverter (not shown) is built in the second screw motor 76, and the control system 6 is configured to be able to control the operation of the second screw motor 76 via the inverter. That is, the control system 6 can control the rotation speed and the rotation direction of the second screw motor 76 via the inverter. The control system 6 can issue a command to the second screw motor 76 to rotate the second screw 72 independently of the first screw 71.

The first screw blade 71B extends spirally along the axial direction of the first screw shaft 71A, and the second screw blade 72B spirally extends along the axial direction of the second screw shaft 72A. The total length of the portion of the first screw 71 to which the first screw blade 71B is fixed and the portion of the second screw 72 to which the second screw blade 72B is fixed is the axial length of the filtration tube 36. Same or longer.

A minute gap is formed between the inner surface of the filtration cylinder 36 and the first screw blade 71B so that the first screw blade 71B can rotate without contacting the filtration cylinder 36. Similarly, a minute gap is formed between the inner surface of the filter cylinder 36 and the second screw blade 72B, so that the second screw blade 72B can rotate without contacting the filter cylinder 36. ing. The sludge charged into the filtration cylinder 36 from the input port 35 formed at the upstream end of the filtration cylinder 36 can be transferred toward the discharge chamber 41 by the rotating first screw blade 71B and the second screw blade 72B. it can.

The pitch of the second screw blade 72B is smaller than the pitch of the first screw blade 71B. Further, the number of turns of the second screw blade 72B is less than three. In the present embodiment, the winding direction of the second screw blade 72B (that is, the spiral direction) is opposite to the winding direction of the first screw blade 71B. Therefore, when the sludge charged from the charging port 35 is sent out to the discharge chamber 41, the second screw 72 is rotated in the direction opposite to that of the first screw 71, as shown in FIG.

The winding direction of the second screw blade 72B may be the same as the winding direction of the first screw blade 71B. In this case, when the sludge charged from the charging port 35 is sent out to the discharge chamber 41, the second screw 72 is rotated in the same direction as the first screw 71.

The filtration cylinder 36 is divided into a dehydration region 1A in which the first screw 71 is arranged and a plug forming region 1B in which the second screw 72 is arranged. The space to which sludge is transferred in the dehydration region 1A is formed by the inner surface of the filtration cylinder 36, the first screw blade 71B, and the first screw shaft 71A. As shown in FIG. 3, the cross-sectional area of this transfer space gradually decreases along the sludge transfer direction. Therefore, as the sludge charged from the charging port 35 is transferred through this transfer space by the first screw blade 71B, the sludge is squeezed and dehydrated. The filtrate that has passed through the filter cylinder 36 is collected by the filtrate receiver 45 arranged below the filtration cylinder 36. A drain 46 is connected to the filtrate receiver 45, and the filtrate collected by the filtrate receiver 45 is discharged from the dehydrator 5 via the drain 46.

The space to which sludge is transferred in the plug forming region 1B is formed by the inner surface of the filtration cylinder 36, the second screw blade 72B, and the second screw shaft 72A. As shown in FIG. 3, the cross-sectional area of this transfer space is constant. In the plug forming region 1B, the plug 77 is formed by the sludge (that is, cake) dehydrated in the dehydrating region 1A. The plug 77 reduces the moisture content of the cake in the filter tube 36 by applying back pressure to the subsequent cake. The cake is pushed by the subsequent cake while forming the plug 77 in the plug forming region 1B, and is gradually discharged to the discharge chamber 41. The cake is discharged from the discharge chamber 41 through the discharge port 53 provided in the lower part of the discharge chamber 41. In this way, the liquid is removed from the sludge to form a cake with a low water content.

Similar to the embodiment shown in FIG. 1, the control system 6 inputs image data such as sludge, agglomerates, and concentrates into the trained model, and keeps the water content of the cake discharged from the dehydrator 5 within the target range. It is configured to output the optimum operating parameters that can be accommodated.
Specific examples of the operation parameters output from the trained model are as follows.
・ Excess or deficiency of sludge flow rate to the coagulation mixing tank 7 → Increase or maintenance or decrease of the rotation speed of the pump 12 ・ Inappropriate for the suitability of the coagulant → Maintain or maintain the use of the coagulant・ Excess or deficiency of the flow rate of the coagulant for the appropriate range → Increase or maintenance or decrease of the operating speed of the coagulant supply device 28 ・ Excess or deficiency of the stirring speed of the stirrer 8 → Rotation of the stirring motor 10 Increase or maintenance or decrease of speed ・ Excess or deficiency of the flow rate of water supplied to the coagulation mixing tank 7 → Increase or maintenance or decrease of the opening degree of the flow control valve 27 ・ Operating speed of the concentrator 4 Excess or deficiency with respect to the appropriate range → Increase or maintenance or decrease ・ Excess or deficiency with respect to the appropriate range of the adjustment variable (for example, pressing plate pressure adjustment) of the concentrator 4 → Increase or maintenance or decrease ・ Rotation speed of the first screw 71 Excess or deficiency with respect to the appropriate range of → Increase or maintenance or decrease of the rotation speed of the first screw motor 75 ・ Excess or deficiency with respect to the appropriate range of the rotation speed of the second screw 72 → Increase or decrease of the rotation speed of the second screw motor 76 Maintenance or decrease ・ Excess or deficiency of the rotation torque of the first screw 71 with respect to the appropriate range → Increase or maintenance or decrease of the current to the first screw motor 75 ・ Excess or deficiency of the rotation torque of the second screw 72 with respect to the appropriate range → Increase, maintain, or decrease current to second screw motor 76

The above-mentioned operation parameters are examples, and the operation parameters output from the trained model may be only one of the above-mentioned operation parameters.

In order to output more optimized operating parameters from the model, the training data used to build the trained model is, in addition to the past image data, the state data of the dehydration system when the past image data was generated. May include. Specific examples of the state data of the dehydration system are as follows.
-Sludge temperature (measured by temperature sensor 22)
-Flow rate of sludge to the coagulation mixing tank 7 (rotational speed of pump 12)
・ Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids amount)
・ Physical characteristics of flocculant (cationism, molecular weight)
-Flow rate of coagulant (operating speed of coagulant supply device 28)
-Stirring speed of the stirrer 8 (rotational speed of the stirrer motor 10)
-Flow rate of water to the coagulation mixing tank 7 (opening of flow control valve 27)
-Operating speed of the concentrator 4 (rotational speed of the drive motor)
-Operating torque of the concentrator 4 (current value to the drive motor)
-Flow rate of the liquid separated by the concentrator 4 (measured by a flow meter (not shown))
-Sludge concentration concentrated by the concentrator 4 (measured by a concentration sensor (not shown))
-Rotation speed of the first screw 71-Current value (torque value) to the first screw motor 75
-Rotation speed of the second screw 72-Current value (torque value) to the second screw motor 76
-Sludge pressure in the filter tube 36 (measured by the pressure sensor 61)
-Measured value of cake moisture content (measured by a measuring device (not shown) or manually)

The item of the state data of the dehydration system described above is an example, and the state data of the dehydration system may be only one of the above items.

The trained model is the past image data generated by at least one of the imaging devices 29, 31, 32, 33, 64, 65, 66 and the state of the dehydration system when the past image data is generated. It is constructed according to a machine learning algorithm using learning data that includes multiple combinations of data and optimal operating parameters of a dehydration system that can keep the moisture content of the cake discharged from the dehydrator 5 within the target range. .. While the dehydration system is in operation, the control system 6 captures the current image data generated by at least one of the imaging devices 29, 31, 32, 33, 64, 65, 66 and the current state data of the dehydration system. The processing device 6b is made to perform an operation for inputting to the trained model and outputting the optimum operation parameters of the dehydration system from the trained model.

In the embodiments shown in FIGS. 1 and 3, the dehydration system includes a concentrator 4, but in one embodiment, the concentrator 4 may be omitted. In this case, the agglomerates (aggregated flocs) formed by the agglutinating device 3 are transferred to the inlet 35 of the dehydrating device 5 through the sludge transfer pipe 18.

FIG. 4 is a diagram showing another embodiment of the dehydration system. In the dehydration system shown in FIG. 4, a belt press type dehydrator is adopted as the dehydrator 5. The above-mentioned concentrator 4 is not provided. Since the configurations and operations of the embodiments not particularly described are the same as those of the embodiments shown in FIGS. 1 and 2, the duplicated description thereof will be omitted.

The aggregating device 3 is provided in a granulation tank 80 for accommodating sludge, a stirrer 8 for stirring sludge in the granulation tank 80, a sludge introduction pipe 14 connected to the granulation tank 80, and a sludge introduction pipe 14. The provided pump 12 is provided. The stirrer 8 includes a stirrer blade 9 arranged in the granulation tank 80 and a stirrer motor 10 connected to the stirrer blade 9. The suspension storage tank 1 is connected to the coagulation granule tank 80 by a sludge introduction pipe 14. The sludge is transferred from the suspension storage tank 1 to the granulation tank 80 through the sludge introduction pipe 14 by the pump 12. The flow rate of sludge to the granulation tank 80 can be adjusted by operating the pump 12.

The pump 12 is connected to the control system 6, and the operation of the pump 12, that is, the flow rate of sludge to the granulation tank 80 is controlled by the control system 6. A temperature sensor 22 is attached to the sludge introduction pipe 14. The temperature sensor 22 is configured to measure the temperature of sludge introduced into the granulation tank 80. Further, a sludge concentration meter (suspension concentration meter) 24 is attached to the sludge introduction pipe 14, and the concentration of suspended substances in the sludge introduced into the granulation tank 80 is measured by the sludge concentration meter 24. ..

The coagulator 3 further includes a coagulant supply device 28 connected to the granulation tank 80. The coagulant supply device 28 is configured to inject the coagulant into the sludge in the granulation tank 80 at a predetermined flow rate. The flow rate of the coagulant injected into the sludge in the granulation tank 80 is adjusted by the coagulant supply device 28. The coagulant supply device 28 is connected to the control system 6, and the operation of the coagulant supply device 28, that is, the flow rate of the coagulant is controlled by the control system 6. The sludge is stirred together with the coagulant by the stirring blade 9 of the stirrer 8. By stirring the coagulant and the sludge in the granulation tank 80, agglomerates in which the suspended substances in the sludge are aggregated are formed. The agglomerates formed in the granulation tank 80 are generally called pellets.

The dehydration system includes a suspension imaging device 29 that generates image data of sludge (suspension before treatment) in the suspension storage tank 1. The suspension imaging device 29 is a digital camera provided with an image sensor (for example, a CCD image sensor or a CMOS image sensor) capable of generating a still image or a continuous image of an object. Alternatively, the suspension imaging device 29 may be a hyperspectral camera capable of decomposing light for each wavelength and imaging an object. The suspension imaging device 29 is connected to the control system 6, and the image data of the sludge (suspension) generated by the suspension imaging device 29 is sent to the control system 6.

The dehydration system includes an agglomerate imaging device 31 that generates image data of agglomerates (pellets) formed by the agglutinating device 3. The agglomerate imaging device 31 faces the inside of the granulation tank 80, and is arranged so as to generate image data of the agglomerates in the granulation tank 80. In one embodiment, the agglomerate imaging device 31 may be arranged so as to face the outlet of the granulation tank 80 and generate image data of the agglomerates discharged from the granulation tank 80. The agglomerate imaging device 31 is connected to the control system 6, and the image data of the agglomerates generated by the agglutination imaging device 31 is sent to the control system 6.

The stirring strength of sludge can be adjusted by the rotation speed of the stirrer 8. The stirrer 8 is connected to the control system 6, and the operation of the stirrer 8, that is, the agitation intensity of sludge is controlled by the control system 6.

The granulation tank 80 is connected to the belt press type dehydrator 5 by a sludge transfer pipe 18. The dehydrator 5 includes an endless pretreatment filter cloth belt 82, a plurality of support rollers 83a to 83c for supporting the pretreatment filter cloth belt 82, an endless first filter cloth belt 86, and a first filter cloth belt. The first guide rollers 88a to 88e supporting the 86, the endless second filter cloth belt 90, the second guide rollers 91a to 91f supporting the second filter cloth belt 90, the first filter cloth belt 86 and the first filter cloth belt 90. It includes a plurality of squeezing rollers 95A to 95E that support the two filter cloth belts 90, and a drive device 98 that moves the first filter cloth belt 86 and the second filter cloth belt 90.

The pretreatment filter cloth belt 82 is arranged on the upstream side of the squeezing rollers 95A to 95E in the sludge transfer direction. A part of the pretreatment filter cloth belt 82 is supported by support rollers 83a and 83b so as to form an inclined portion 82A inclined upward along the sludge transfer direction. The support roller 83a is connected to the drive shaft of the electric motor 100. When the electric motor 100 rotates the support roller 83a, the pretreatment filter cloth belt 82 moves in the direction in which the sludge on the inclined portion 82A rises.

The drive device 98 includes an electric motor 98A, a drive wheel 98B fixed to a drive shaft of the electric motor 98A, and a belt 98C as a drive force transmitting member supported by the drive wheel 98B. A chain may be used instead of the belt 98C. The belt 98C is connected to the first guide roller 88c and further connected to the second guide roller 91f. When the electric motor 98A rotates the drive wheel 98B, the rotation of the drive wheel 98B is transmitted to the first guide roller 88c and the second guide roller 91f by the belt 98C. The first guide roller 88c and the second guide roller 91f rotate at the same speed, whereby the first filter cloth belt 86 and the second filter cloth belt 90 move in the same direction at the same speed.

The first filter cloth belt 86 is supported by the first guide rollers 88a to 88e and a plurality of squeezing rollers 95A to 95E. The first guide roller 88d is connected to the first filter cloth tensioning device 101. The first filter cloth tensioning device 101 is configured to adjust the tension of the first filter cloth belt 86 by moving the position of the first guide roller 88d.

The second filter cloth belt 90 is supported by the second guide rollers 91a to 91f and a plurality of squeezing rollers 95A to 95E. The second guide roller 91a is connected to the second filter cloth tensioning device 102. The second filter cloth tensioning device 102 is configured to adjust the tension of the second filter cloth belt 90 by moving the position of the second guide roller 91a.

The sludge composed of agglomerates (pellets) formed by the agglutinating device 3 is transferred onto the pretreatment filter cloth belt 82 through the sludge transfer pipe 18. As for the sludge, the liquid in the sludge falls due to gravity while ascending the inclined portion 82A of the pretreatment filter cloth belt 82. This step is a gravity dehydration step.

By moving the pretreatment filter cloth belt 82, the sludge on the pretreatment filter cloth belt 82 is transferred onto the first filter cloth belt 86. The first filter cloth belt 86 and the second filter cloth belt 90 extending between the plurality of pressing rollers 95A to 95E face each other. As the first filter cloth belt 86 is moved, sludge is sandwiched between the first filter cloth belt 86 and the second filter cloth belt 90. The sludge is sandwiched between the first filter cloth belt 86 and the second filter cloth belt 90 and squeezed while the first filter cloth belt 86 and the second filter cloth belt 90 are wound around the squeezing rollers 95A to 95E. .. As a result, the sludge becomes a cake (turbid residue) with a low water content. The cake having a low water content is discharged from the discharge port 53.

A filtrate receiver 45 is arranged below the squeezing rollers 95A to 95E. The filtrate removed from the sludge is collected by the filtrate receiver 45. A drain 46 is connected to the filtrate receiver 45, and the filtrate collected by the filtrate receiver 45 is discharged from the dehydrator 5 via the drain 46.

The dehydration system includes a cake imaging device 64 that generates image data of a cake (a turbid residue having a low water content) formed by the dehydrator 5, and a dehydration filtrate that generates image data of a filtrate discharged from the dehydrator 5. The image pickup apparatus 65 is provided. The cake imaging device 64 is arranged adjacent to the discharge port 53 of the dehydrating device 5, and the dehydrated filtrate imaging device 65 is arranged adjacent to the drain 46 of the dehydrating device 5. The cake imaging device 64 may be arranged in the discharge port 53. The cake imager 64 and the dehydration filtrate imager 65 are connected to the control system 6, and the cake image data and the filtrate image data generated by the cake imager 64 and the dehydration filtrate imager 65 are controlled. It is designed to be sent to system 6.

The control system 6 acquires the image data generated by the image pickup devices 29, 31, 64, 65 from the image pickup devices 29, 31, 64, 65, and optimizes the operation parameters of the dehydration system based on the image data. It is configured in. The control system 6 inputs the storage device 6a in which the trained model constructed by the machine learning algorithm is stored and the image data into the trained model, and the water content of the cake (turbid residue) discharged from the dehydration device 5. Is provided with a processing device 6b that executes an operation for outputting the optimum operating parameters of the dehydration system that can keep the above within the target range from the trained model.

The trained model is dehydrated so that the past image data generated by the imaging devices 29, 31, 64, 65 and the water content of the cake (turbid residue) discharged from the dehydrating device 5 can be kept within the target range. It is a model constructed according to a machine learning algorithm using learning data including multiple combinations with the optimum operation parameters of the system. The past image data generated by the image pickup devices 29, 31, 64, 65 is an explanatory variable, and the dehydration system capable of keeping the water content of the cake (turbid residue) discharged from the dehydration device 5 within the target range. The optimum operating parameter of is the objective variable. The optimum operation parameters constituting the training data are correct answer data, and are operation parameters determined by a skilled operator based on the state of sludge, agglomerates, etc. and the water content of the cake discharged from the dehydrator 5. ..

In order to optimize the parameters (weights, etc.) of the trained model, the image data generated by the imaging devices 29, 31, 64, 65 and the optimum operating parameters that can keep the moisture content of the cake within the target range. Learning data including many combinations with and is prepared. The control system 6 constructs a trained model by a machine learning algorithm using this training data. The parameters of the trained model may include biases in addition to weights. The trained model constructed in this way is stored in the storage device 6a.

The control system 6 acquires image data from the image pickup devices 29, 31, 64, and 65 at a predetermined cycle and stores the image data in the storage device 6a. The control system 6 inputs the image data to the trained model, and outputs the optimum operation parameters that can keep the moisture content of the cake within the target range from the trained model.

In the present embodiment, the image data generated by all of the above-described image pickup devices 29, 31, 64, 65 is input to the trained model, but in one embodiment, of the image pickup devices 29, 31, 64, 65. The image data generated by at least one of may be input to the trained model. In this case, the same type of image data as the image data input to the trained model is used to build the trained model. For example, when the image data generated by the agglomerate imaging device 31 is input to the trained model, the trained model is constructed using the training data including the past image data generated by the agglomerate imaging device 31. To.

Similar to the embodiment shown in FIG. 1, the control system 6 inputs the image data into the trained model and sets the optimum operating parameters capable of keeping the moisture content of the cake discharged from the dehydrator 5 within the target range. It is configured to output from the trained model.
Specific examples of the operation parameters output from the trained model are as follows.
・ Excess or deficiency of sludge flow rate to the granulation tank 80 → Increase or maintenance or decrease of the rotation speed of the pump 12 ・ Inappropriate for the compatibility of the coagulant → Maintain or maintain the use of the coagulant or the coagulant・ Excess or deficiency of the flow rate of the coagulant for the appropriate range → Increase or maintenance or decrease of the operating speed of the coagulant supply device 28 ・ Excess or deficiency of the stirring speed of the stirrer 8 → Rotation of the stirring motor 10 Increase, maintenance, or decrease of speed ・ Movement speed of 1st filter cloth belt 86 and 2nd filter cloth belt 90 → Increase, maintenance, or decrease of rotation speed of motor 98A ・ 1st filter cloth belt 86 and 2nd Tension force of filter cloth belt 90 → Change or maintain the position of guide rollers 88d, 91a

The above-mentioned operation parameters are examples, and the operation parameters output from the trained model may be only one of the above-mentioned operation parameters.

In order to output more optimized operating parameters from the model, the training data used to build the model includes past image data as well as state data of the dehydration system when the past image data was generated. It may be. Specific examples of the state data of the dehydration system are as follows.
-Sludge temperature (measured by temperature sensor 22)
-Flow rate of sludge to the granulation tank 80 (rotational speed of pump 12)
・ Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids amount)
・ Physical characteristics of flocculant (cationism, molecular weight)
-Flow rate of coagulant (operating speed of coagulant supply device 28)
-Stirring speed of the stirrer 8 (rotational speed of the stirrer motor 10)
-Movement speed of the first filter cloth belt 86 and the second filter cloth belt 90 (rotational speed of the electric motor 98A)
-Position of guide rollers 88d, 91a

The item of the state data of the dehydration system described above is an example, and the state data of the dehydration system may be only one of the above items.

The trained model includes past image data generated by at least one of the imaging devices 29, 31, 64, and 65, state data of the dehydration system when the past image data is generated, and the dehydration device 5. It is constructed according to a machine learning algorithm using learning data that includes multiple combinations with optimal operating parameters of a dehydration system that can keep the water content of the cake discharged from the target range. While the dehydration system is in operation, the control system 6 inputs the current image data generated by at least one of the imaging devices 29, 31, 64, 65 and the current state data of the dehydration system into the trained model. Then, the processing device 6b is made to execute an operation for outputting the optimum operation parameters of the dehydration system from the model.

The solid-liquid separation performance when sludge is agglomerated with a coagulant such as a polymer to form agglomerated flocs and the sludge containing the agglomerated flocs is solid-liquid separated depends on the type and properties of the sludge, the coagulant used, and solid-liquid separation. It depends on the type of device. When a situation change occurs with respect to the solid-liquid separation state, it is necessary for the plant operator at the site to quickly detect the change and adjust and change the operating conditions as appropriate to maintain the optimized state of solid-liquid separation as continuously as possible. is there. When judging and evaluating this "solid-liquid separation state of sludge", the place where the change of state appears strongly differs greatly depending on the type of sludge. Therefore, in the examples, the following three types of sludge are dehydrated. I went to the facility. Needless to say, the items adopted and taken in as input signals in these three examples may be increased or decreased due to seasonal fluctuations in sludge properties and changes in the operating environment to improve efficiency.

In Examples 1 to 3 above, each skilled operator who operates and manages the shaft-sliding type screw press shown in FIG. 1 operating in a dehydration treatment facility for each of three different types of sludge Throughout a certain period of time, the operating conditions were optimized with reference to the above-mentioned operating parameters and the above-mentioned image data (7 locations). Every time the operating conditions were changed for optimization, it was recorded which operating parameters and image data were used as the basis for changing the operating conditions, and multivariate analysis was performed based on the statistical data of those records. Furthermore, the contribution of each operation parameter or each image data, which is the basis for changing the operation operation item for operation optimization, is statistically organized, and the adoption input that is particularly important and necessary for each of the three sludge dewatering treatment facilities. Operational parameters or image data as data were extracted. As a result, it was found that the input data shown below for each processing facility is almost necessary and sufficient data for operation optimization. The probability that these data were taken in as input data to this dehydration system and the operation parameter contents output as output data matched the actual operation contents of the skilled operator was 93% or more in all three processing facilities. The operating conditions of Examples 1 to 3 will be individually described below.

Based on the operation record data, the output data from the adoption of this dehydration system, and the statistical analysis results thereof, in the sewage mixed raw sludge of Example 1, "pressure in the dehydrator", "screw shaft torque", and "sluice discharge near the screw outlet". It was found that the approximate solid-liquid separation state can be judged and evaluated by the three elements of "image". The match rate between the output data of the dehydration system using these three input data and the actual operation contents of the skilled operator reached 94%. FIG. 5 shows the test results of Example 1. In general, mixed raw sludge has a relatively large amount of coarse suspended matter of 74 μm or more (the larger the better the solid-liquid separability), which contributes to solid-liquid separability, which is 10 to 40%, forming a firm and strong dehydrated cake. The moisture content of the cake is dehydrated to about 60 to 70%. Therefore, the dehydration performance is strongly reflected in the pressure in the dehydrator and the screw shaft torque, and the solid-liquid separation state (drip condition of the filtrate) at the final stage of the dehydration process is characterized by the dehydration filtrate image (second stage). It is thought that it appeared as an image.
The moisture content of the dehydrated cake during the operation period of this test achieved the target moisture content with respect to the predetermined sludge flow rate.

Based on the operation record data, the output data obtained by adopting this dehydration system, and the statistical analysis results thereof, in the mixed biomass methane fermentation sludge of Example 2, the approximate solid-liquid separation state is judged and evaluated only by the "upper image of the concentrator". It turns out that it can be done. The match rate between the output data of this dehydration system using only this input data and the actual operation contents of the skilled operator reached 93%. FIG. 6 shows the test results of Example 2.

In general, mixed biomass methane fermentation sludge contains many processed food products and food residues with a relatively high salt concentration, so the appropriate addition rate of coagulant may exceed 4% per solid matter. .. Furthermore, the quality and quantity of organic matter that is put into the methane fermenter every day fluctuates greatly, and controlling the injection rate of the flocculant within an appropriate range is the most important for the solid-liquid separability of the sludge. It is probable that it was the movement (spreading, rolling, solid-liquid interface, etc.) of the coagulated and condensed sludge in the draining zone of the concentrator that could accurately express the fluctuation of the appropriate injection rate in real time. As a skilled operator, by constantly monitoring the image from the upper part of this concentrator draining zone, it is possible to quickly detect changes in solid-liquid separability mainly due to fluctuations in the proper injection rate of coagulant, and to determine the operating conditions of the dehydration system. It is probable that it could be optimized again.
The moisture content of the dehydrated cake during the operation period of this test achieved the target moisture content with respect to the predetermined sludge flow rate.

Based on the operation record data, the output data obtained by adopting this dehydration system, and the statistical analysis results thereof, the surplus sludge in the activated sludge treatment facility of the wastewater of the drinking water manufacturing plant of Example 3 is "an image of agglomerated flocs in a coagulation mixing tank". , "Upper image of concentrator", "turbidity leak state from dehydrator", "image showing turbidity of dehydrated filtrate", and "sludge pH" and "pressure inside dehydrator", total 6 elements It was found that it is possible to judge and evaluate the approximate solid-liquid separation state by comprehensively evaluating by looking at. The match rate between the output data of this dehydration system using these six input data and the actual operation contents of the skilled operator reached 95%. FIG. 7 shows the test results of Example 3. The excess sludge from the wastewater treatment facility of the drinking water manufacturing plant targeted this time has a very small amount of coarse suspended matter of 74 μm or more that contributes to solid-liquid separability, which is less than 3%. (Good liquid separability) was also relatively large at 88%, which was a sludge property that was difficult to dehydrate, but the shape and texture of aggregated flocs empirically known by skilled operators, the movement of sludge on the upper part of the concentrator, and the dehydrator. By outputting the optimum operation parameters by this dehydration system based on the data centered on the images such as the SS leak state from the above, it is possible to perform the operation operation equivalent to that of a skilled operator who has read the characteristics of this poorly dehydrated sludge. It is thought that it became.
The moisture content of the dehydrated cake during the operation period of this test achieved the target moisture content with respect to the predetermined sludge flow rate.

The above-described embodiment outputs the current optimum operating parameters while achieving the target water content, but it can also be applied to the prediction of the future operating state. For example, the future in this dehydration system It is also possible to predict the water content of the discharged dehydrated cake and the operation failure of the equipment in the dehydration process that may occur in the future.

In one embodiment, the control system 6 adds to or in place of the trained model described above that outputs the optimum operating parameters of the dehydration system to determine whether the operation of the dehydration system is normal or abnormal. It may be equipped with a trained model of. If an abnormality occurs in the operating state of the dehydration system, the water content of the obtained dehydrated cake becomes high, which may have a great influence on the subsequent treatment. Although the frequency of such operation abnormalities is not high, it is important to correctly detect the operation abnormalities of the dehydration system when they occur.

Therefore, the present embodiment provides a dehydration system capable of correctly detecting an operation abnormality of the dehydration system using a trained model. In the following description, the above-mentioned trained model that outputs the optimum operation parameters of the dehydration system is referred to as the first trained model, and the trained model for determining whether the operation of the dehydration system is normal or abnormal is referred to as the first trained model. 2 Called a trained model.

The second trained model is stored in the storage device 6a of the control system 6. In one example, the second trained model is composed of a neural network. The storage device 6a stores a program for constructing the second trained model according to the machine learning algorithm. The processing device 6b constructs a second trained model by executing an operation according to an instruction included in the program. Since the details of the second trained model are the same as those of the first trained model, the duplicate description thereof will be omitted.

The second trained model uses the training data including a plurality of combinations of the past image data generated by the cake imaging device 64 and the operation index value indicating that the operation state of the dehydration system is normal or abnormal. , A model built according to a machine learning algorithm. As shown in FIGS. 1, 3, and 4, the cake imaging device 64 is arranged so as to generate image data of a cake (a turbid residue having a low water content) formed by the dehydrating device 5. In one example, the cake imager 64 is placed above the discharge conveyor (not shown) for carrying out the cake formed by the dehydrator 5 and is arranged to generate image data of the cake on the discharge conveyor. You may.

The past image data generated by the cake imaging device 64 is an explanatory variable, and the operating index value indicating that the operating state of the dehydration system is normal or abnormal is the objective variable. Whether the dehydration system is operating normally or abnormally is determined by the operator. Examples of the operation index value include a first numerical value (for example, 0) indicating that the operating state of the dehydration system is normal, and a second numerical value (for example, 1) indicating that the operating state of the dehydration system is abnormal. Be done. Causes of abnormal operating conditions of the dehydration system include poor dissolution concentration of coagulant, unexpected fluctuation of sludge concentration, and clogging of sludge in the dehydrator 5.

A large number of image data generated by the cake imager 64 in order to optimize the parameters (weights, etc.) of the second trained model and operating index values indicating that the operating state of the dehydration system is normal or abnormal. Learning data (also called training data or teacher data) including the combination of is prepared. The control system 6 constructs a second trained model by a machine learning algorithm using this training data. The parameters of the second trained model may include biases in addition to weights. The second trained model constructed in this way is stored in the storage device 6a.

During the operation of the dehydration system, the control system 6 acquires the current image data from the cake imaging device 64 at a predetermined cycle and stores it in the storage device 6a. The control system 6 inputs image data to the second trained model, and processes the processing device 6b to output an operation index value indicating that the operating state of the dehydration system is normal or abnormal from the second trained model. To execute.

FIG. 8 is a graph showing the time change of the operation index value output from the second trained model during the operation of the dehydration system. In FIG. 8, the vertical axis represents the operation index value, and the horizontal axis represents the operation time. The interval of output of the determination result by the second trained model is appropriately set. Although the example in seconds is shown in FIG. 8, it may be in minutes, hours, or days at intervals. In the first half of the graph of FIG. 8, the numerical value 0 indicating that the operation is normal continues, but the numerical value 1 indicating an operation abnormality is gradually output. As shown in FIG. 8, while the same numerical value is continuously output from the second trained model, different numerical values may be output from time to time. This is because the second trained model could not correctly determine the operating state of the dehydration system.

FIG. 9 is a graph showing the temporal change of the moving average of the driving index value shown in FIG. In FIG. 8, the vertical axis represents the moving average of the driving index values, and the horizontal axis represents the driving time. The control system 6 calculates the moving average of the operation index values output from the second trained model. The time interval of the moving average is set as appropriate. The control system 6 compares the moving average of the operating index value with the threshold value, and when the moving average of the operating index value exceeds the threshold value, determines that an abnormality has occurred in the operation of the dehydration system. Then, the control system 6 issues an alarm indicating an operation abnormality of the dehydration system. Since the operator can know from the alarm that an abnormality has occurred in the operation of the dehydration system, the operation abnormality can be resolved by taking appropriate measures for the processing system.

As can be seen from FIG. 9, the moving average of the operating index value continues to fluctuate even after the threshold value is once exceeded, and thus exceeds or falls below the threshold value. Therefore, once the control system 6 determines that an abnormality has occurred in the operation of the dehydration system, the control system 6 does not perform the operation of determining the operation abnormality and gives an alarm unless the moving average of the operation index value drops to a predetermined normal level. Do not release. When the operation abnormality of the dehydration system is resolved, the moving average of the operation index values gradually decreases. When the moving average of the operation index value drops to a predetermined normal level, the control system 6 resets the operation abnormality determination operation of the dehydration system and restarts the operation abnormality determination operation. Further, the control system 6 cancels the alarm.

According to the present embodiment, the control system 6 can correctly determine that an abnormality has occurred in the dehydration system based on the operation index value output from the second trained model.

The control system 6 selects one or both of the first trained model that outputs the optimum operation parameters of the dehydration system and the second trained model that determines whether the operation of the dehydration system is normal or abnormal. You may prepare.

The above-described embodiment is described for the purpose of enabling a person having ordinary knowledge in the technical field to which the present invention belongs to carry out 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. Therefore, the present invention is not limited to the described embodiments, but is construed in the broadest range according to the technical idea defined by the claims.

1 Suspension storage tank 3 Coagulation device 4 Concentrator 5 Dehydration device 6 Control system 6a Storage device 6b Processing device 7 Coagulation mixing tank 8 Stirrer 9 Stirrer blade 10 Stirrer motor 12 Pump 14 Sludge introduction pipe 18 Sludge transfer pipe 22 Temperature sensor 24 Sludge concentration meter 26 Water supply line 27 Flow control valve 28 Coagulant supply device 29 Suspension imager 31 Aggregate imager 32 Concentrate imager 33 Separation solution imager 35 Input port 36 Filtration cylinder 37 Screw shaft 38 Screw blade 40 Screw motor 41 Discharge chamber 42 Shaft sliding actuator 44 Closure wall 45 Filter fluid receiver 46 Drain 50 Back pressure plate 51 Back pressure plate drive device 52 Plug 53 Discharge port 55 Cleaning device 61 Pressure sensor 64 Cake imager 65 Dehydrated filtrate imager 66 Filtration Cylinder imager 71 1st screw 71A 1st screw shaft 71B 1st screw blade 72 2nd screw 72A 2nd screw shaft 72B 2nd screw blade 75 1st screw motor 76 2nd screw motor 77 Plug 80 Granulation tank 82 Pretreatment Filter cloth belt 83a to 83c Support roller 86 First filter cloth belt 88a to 88e First guide roller 90 Second filter cloth belt 91a to 91f Second guide roller 95A to 95E Squeezing roller 98 Drive device 98A Electric motor 98B Drive wheel 98C Belt 100 Electric machine 101 1st filter cloth tensioning device 102 2nd filter cloth tensioning device

Claims (4)

A dehydration system for removing liquids from suspensions
A suspension storage tank for storing suspension and
A coagulator that stirs the suspension and the coagulant to form agglomerates,
A dehydrator that removes the liquid from the agglomerates to form a turbid residue with a concentration of 3 to 50 wt%.
An imaging device that produces at least one image data of the suspension, the agglomerates, the turbid residue, and the liquid removed from the suspension.
Equipped with a control system with a trained model built by machine learning algorithms
The control system can input the storage device in which the trained model is stored and the image data into the trained model, and keep the water content of the turbid residue discharged from the dehydrator within the target range. A dehydration system comprising a processing device that performs an operation to output the optimum operating parameters of the dehydration system capable from the trained model. A dehydration system for removing liquids from suspensions
A suspension storage tank for storing suspension and
A coagulator that stirs the suspension and the coagulant to form agglomerates,
A concentrator that removes the liquid from the agglomerates to form a concentrate having a concentration of 3 to 15 wt%.
A dehydrator that removes the liquid from the concentrate to form a turbid residue with a concentration of 3 to 50 wt%.
An imaging device that produces at least one image data of the suspension, the agglomerates, the concentrate, the turbid residue, and the liquid removed from the suspension.
Equipped with a control system with a trained model built by machine learning algorithms
The control system can input the storage device in which the trained model is stored and the image data into the trained model, and keep the water content of the turbid residue discharged from the dehydrator within the target range. A dehydration system comprising a processing device that performs an operation to output the optimum operating parameters of the dehydration system capable from the trained model. The dehydration system according to claim 2, wherein the concentrating device is a rotary disk type liquid removing device. The control system inputs the image data and the state data of the dehydration system into the trained model, and the dehydration system capable of keeping the water content of the turbid residue discharged from the dehydrator within a target range. The dehydration system according to any one of claims 1 to 3, wherein the processing apparatus is configured to perform an operation for outputting the optimum operation parameters of the above from the trained model.

Images