JP7530318B2 - Drying equipment control system - Google Patents

Description

The present invention relates to a drying system that dries sludge while stirring it, and in particular to a drying system that can provide optimal automatic operation and support for operator operation.

Conventionally, drying devices have been known that agitate and transport sludge discharged from water treatment and the like, and then dry it (see, for example, Patent Document 1). In this type of drying device, a shaft equipped with multiple rows of blades (paddles) is used to agitate and transport the sludge. When the shaft rotates, the blades attached to the shaft also rotate around the shaft, and as a result, the sludge supplied to one end of the shaft is transported to the other end of the shaft while being agitated. During this agitation and transport, the sludge is heated and dried.

In this type of drying equipment, the blades fixed to the two shafts overlap each other to enhance the mixing effect. There is a demand for new drying equipment that is easy to operate and manage, such as stabilizing the moisture content of the sludge after drying and reliably preventing poor dispersion and over-drying of the sludge, while also reducing initial costs.

JP 2014-131784 A JP 2020-114569 A JP 2020-113151 A JP 2019-051458 A

The above-mentioned Patent Document 1 discloses a sludge drying device that dries sludge while stirring and transporting it, and a sludge drying system that includes the device. The moisture content of the sludge varies depending on various factors such as the sludge being treated and the operating state of the drying device, and in order to keep the moisture content within the target moisture content, an operator must control the operation based on visual inspection and experience. However, stable operation is difficult because it requires the operator's experience and know-how, and the operating state varies depending on the operator.

The above-mentioned Patent Document 2 discloses a method for estimating the moisture content of the dehydrated cake discharged from the dehydrator. However, the Patent Document 2 does not propose predicting the moisture content and then adjusting the operating parameters to keep the moisture content within a target range.

The above-mentioned Patent Document 3 discloses updating the model when the error exceeds a threshold value. However, if the moisture content to be predicted is not actually measured, it is not possible to grasp the error between the predicted value and the actual measured value.

The above-mentioned Patent Document 4 discloses a technology for calculating a predicted state value of the turbid residue discharged from a dehydration system and outputting operation parameters that keep the predicted value within a target range. However, when focusing on stable operation and efficiency when outputting operation parameters, further improvements are required.

The present invention was made in consideration of the above-mentioned problems in the past, and its purpose is to provide a control system for a drying device that enables better operational management, labor savings, and improved stable operation.

In one aspect, a control system for a drying device for drying sludge is provided, the control system comprising a model constructed by machine learning using training data including at least the operating parameters of the drying device and status data of the drying device, the control system being configured to input the operating parameters and the status data into the model, calculate a predicted value of the moisture content of the dried sludge discharged from the drying device according to the model, and determine optimal values of the operating parameters that can bring the moisture content within a target range.

In one aspect, when adjusting the operation of the drying device, a priority order of the operating parameters to be adjusted is determined in advance.
In one aspect, the control system is configured to determine the priority order according to the importance of features calculated during the machine learning.
In one aspect, the control system is configured to adjust the operating parameter in a stepwise manner when a difference between a current value of the operating parameter and the optimal value is greater than a predetermined adjustment width.
In one aspect, the status data includes at least one of operating parameters and status data of a dehydration system installed upstream of the drying device, and an estimated moisture content of the dehydrated sludge calculated according to a trained model incorporated into the dehydration system.

In one aspect, the model includes a first model constructed by machine learning using training data that includes the operating parameters and does not include the state data, and a second model constructed by machine learning using training data that includes both the operating parameters and the state data.
In one aspect, the first model is used to determine optimal values of the operating parameters, and the second model is used to calculate a predicted value of the moisture content.
In one aspect, the control system is configured to, when a difference between the predicted moisture content calculated according to the first model and the moisture content calculated according to the second model exceeds a predetermined tolerance, perform machine learning for the first model again and update the first model.

In one aspect, the training data includes values of the operating parameters that are distributed within a wider range than during normal operation of the drying device.
In one aspect, the control system is configured to perform the machine learning on a regular or irregular basis to update the model.
In one aspect, the control system is configured to use a web application to display data obtained from the drying device, operate the drying device, and update the model.
In one aspect, the training data includes, in addition to the operating parameters and the status data, at least one of sludge image data, sludge sound data, and vibration data generated due to sludge, and the control system is configured to input the operating parameters and the status data, and at least one of sludge image data, sludge sound data, and sludge vibration data into the model, and calculate a predicted value of the moisture content of the dried sludge discharged from the drying device in accordance with the model.

According to the present invention, the following effects can be obtained.
The moisture content of dried sludge is estimated based on operating parameters and status data, and the optimal operating parameters are determined to keep the moisture content within the target range, achieving stable operation and making it possible for even inexperienced operators to operate the system.
By giving priority to adjusting the operating parameters that have a large effect on the moisture content, the moisture content can be efficiently kept within the target range.
Drying devices are often used in conjunction with a dehydration system, and by incorporating data from the dehydration system, the operating conditions and sludge conditions up to the previous stage can be reflected in the model, enabling more accurate estimation of the moisture content.
By gradually adjusting the operating parameters, stable operation can be achieved and the moisture content can be kept within the target range more efficiently and accurately.
By comparing the outputs of multiple trained models, it is possible to detect a decrease in the accuracy of a trained model. Furthermore, it is possible to monitor the prediction accuracy even when the moisture content is not actually measured.
By creating training data that contains a wider variety of values than those used during normal operation and that contains data that is distributed over a wider range, the scope of application of the model can be expanded, making it possible to build a more accurate model.
Using a web application, it is possible to perform remote monitoring, update models, and control the operation of the drying equipment, thereby improving efficiency.

1 is a schematic diagram showing an embodiment of a drying system including a drying device for drying sludge and a control system for controlling the drying device; FIG. 2 is a top view of the drying device shown in FIG. 1 . FIG. 2 is a view of the paddle as seen from the axial direction of the shaft. FIG. 1 illustrates one embodiment of a dewatering system. FIG. 13 illustrates another embodiment of the dewatering system. FIG. 13 illustrates yet another embodiment of a dehydration system. This is a diagram explaining a flow for creating a model through machine learning using training data and calculating a predicted value of moisture content using the trained model. FIG. 2 is a schematic diagram showing a specific example of a display unit. 4 is a graph showing the importance of operation parameters. FIG. 1 is a schematic diagram illustrating an embodiment of a drying system including an arrangement for acquiring image data. FIG. 1 is a schematic diagram illustrating an embodiment of a drying system including an arrangement for acquiring sound data. FIG. 1 is a schematic diagram illustrating an embodiment of a drying system including an arrangement for acquiring vibration data.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
1 is a schematic diagram showing an embodiment of a drying system including a drying apparatus for drying sludge and a control system for controlling the drying apparatus. This drying system is suitable for drying turbid residue obtained by dehydrating a suspension such as sludge or slurry. In particular, the drying system is suitable for use in drying dehydrated cake discharged from a dehydration apparatus such as a screw press apparatus. Examples of sludge to be dried by the drying apparatus in the embodiment described below include such turbid residue and dehydrated cake.

The drying system includes a drying device 5 that dries sludge such as dewatered turbid residue, and a control system 10 that calculates a predicted moisture content of the sludge dried by the drying device 5. The drying device 5 includes an input conveyor 1 that transports the sludge, a housing 15 that has a drying chamber 14 formed therein that receives the sludge transported by the input conveyor 1, an agitator rotor 17 that agitates the sludge in the drying chamber 14, and an electric motor 18 that rotates the agitator rotor 17. In this embodiment, two agitator rotors 17 are provided, but only one agitator rotor 17 is shown in FIG. 1.

The sludge fed into the drying device 5 is a turbid residue with a low water content that remains after a suspension such as sludge or slurry with a high water content is dehydrated using a dehydrator (e.g., a screw press or belt press). This turbid residue is generally called dehydrated cake. Specific examples of suspensions include sludge generated during the treatment of sewage or human waste, industrial wastewater, industrial waste generated during the manufacture of industrial products such as food, cosmetics, and paper, and slurries.

Figure 2 is a top view of the drying device 5 shown in Figure 1. As shown in Figure 2, each stirring rotor 17 includes a shaft 17A and a number of paddles 17B fixed to the shaft 17A. Both ends of the shaft 17A extend through the housing 15 and are rotatably supported by bearings (not shown). The paddles 17B are disposed in the drying chamber 14. The paddles 17B are arranged along the axial direction of the shaft 17A.

Each paddle 17B is inclined with respect to a direction perpendicular to the axial direction of the shaft 17A. Furthermore, the inclination angle of half of all the paddles 17B is different from the inclination angle of the other half of the paddles 17B. These paddles 17B with different inclination angles are arranged alternately along the axial direction of the shaft 17A.

Figure 3 is a view of the paddle 17B from the axial direction of the shaft 17A. As shown in Figure 3, the paddle 17B has a fan shape. Each paddle 17B is fixed to the outer circumferential surface of the shaft 17A, and two paddles 17B form a set and surround the outer circumferential surface of the shaft 17A. When viewed from the axial direction of the shaft 17A, the outermost edge of the paddle 17B fixed to one shaft 17A overlaps the outermost edge of the paddle 17B fixed to the other shaft 17A. This overlapping arrangement improves the efficiency of stirring the sludge. In reality, the paddle 17B fixed to one shaft 17A is not in contact with the paddle 17B fixed to the other shaft 17A.

As shown in FIG. 2, two gears 20 are fixed to the two shafts 17A. These gears 20 mesh with each other. Therefore, the two shafts 17A, i.e., the two stirring rotors 17, rotate in opposite directions. The electric motor 18 is connected to one of the two shafts 17A via a torque transmission mechanism 22. The torque transmission mechanism 22 is composed of a combination of a sprocket and a chain, or a combination of a pulley and a belt. When the electric motor 18 operates, the two stirring rotors 17 rotate in opposite directions. The electric motor 18 has a built-in inverter (not shown). The electric motor 18 is connected to the control system 10, and the operation of the electric motor 18, i.e., the rotation speed of the stirring rotors 17, is controlled by the control system 10.

The two shafts 17A are hollow shafts, and each paddle 17B is also a hollow paddle. That is, a space extending in the axial direction is formed inside each shaft 17A, and a space is also formed inside each paddle 17B. The space inside the shaft 17A and the space inside the paddle 17B are mutually connected. The drying device 5 has two steam supply lines 50 connected to one end of each of the two shafts 17A. Steam is supplied from the steam supply lines 50 into the shaft 17A, flows through the space inside the shaft 17A and the space inside the paddle 17B, and is discharged from the other end of the shaft 17A. The steam heats the shaft 17A and the paddle 17B, and their surfaces become hot.

The two steam supply lines 50 are connected to a boiler 51. The pressure and flow rate of the steam flowing through the steam supply lines 50 are controlled by a steam pressure control valve 52 installed in the steam supply lines 50. The steam pressure control valve 52 is connected to the control system 10 and is controlled by the control system 10. More specifically, the pressure of the steam supplied to the stirring rotor 17 is controlled by the control system 10 via the steam pressure control valve 52.

Returning to FIG. 1, the housing 15 has an inlet 25 through which sludge is introduced and an outlet 26 through which dried sludge is discharged. The drying device 5 has a dry gas supply line 30 and a dry gas discharge line 31 connected to the housing 15. Dry gas is supplied into the housing 15 through the dry gas supply line 30, contacts the sludge in the housing 15, and is discharged from the housing 15 through the dry gas discharge line 31. The dry gas supplied from the dry gas supply line 30 is a high-temperature gas that has been dehumidified in advance, and is preheated by a heat source (not shown) such as steam or a heater.

A temperature measuring device 32 and a flow rate measuring device 33 are attached to the dry gas supply line 30. The temperature measuring device 32 is configured to measure the temperature of the dry gas flowing through the dry gas supply line 30, and the flow rate measuring device 33 is configured to measure the flow rate of the dry gas flowing through the dry gas supply line 30. In addition, a temperature measuring device 35 is attached to the dry gas exhaust line 31 to measure the temperature of the dry gas flowing through the dry gas exhaust line 31. The temperature measuring device 32, the flow rate measuring device 33, and the temperature measuring device 35 are connected to the control system 10, and the measured values of the temperature and flow rate of the dry gas supplied into the housing 15 and the measured value of the temperature of the dry gas exhausted from the housing 15 are sent to the control system 10.

The drying device 5 is equipped with a temperature measuring device 40 that measures the surface temperature of the housing 15 and a pressure measuring device 41 that measures the pressure inside the housing 15. The temperature measuring device 40 and the pressure measuring device 41 are connected to the control system 10, and the measured values of the surface temperature of the housing 15 and the measured values of the pressure inside the housing 15 are sent to the control system 10.

The drying device 5 includes a weir 56 disposed in the housing 15 and a vertical movement device 58 for moving the weir 56 up and down. The weir 56 is disposed in the housing 15 and is located downstream of the paddle 17B in the sludge flow direction. The interior of the housing 15 is divided into a drying chamber 14 and a discharge chamber 60 by the weir 56. The discharge port 26 is located below the discharge chamber 60. The sludge in the drying chamber 14 is moved to the discharge chamber 60 over the upper edge of the weir 56. The weir 56 has the function of controlling the amount and time of sludge retention in the drying chamber 14. That is, when the weir 56 is moved upward (when the height of the weir 56 is raised), the amount and time of sludge retention in the drying chamber 14 increases, resulting in the sludge being dried further. The lifting device 58 is connected to the control system 10, and the operation of the lifting device 58, i.e., the height of the weir 56 (the vertical position of the weir 56), is controlled by the control system 10.

The operation of the drying device 5 is as follows. The electric motor 18 rotates the two stirring rotors 17 in the opposite directions, while steam is supplied from the steam supply line 50 into the stirring rotors 17. The stirring rotors 17 are heated by the steam, and the surface of the stirring rotors 17 becomes hot. Furthermore, dry gas flows into the drying chamber 14 through the dry gas supply line 30, flows through the drying chamber 14, and is discharged through the dry gas discharge line 31. The sludge is introduced into the drying chamber 14 through the inlet 25. The sludge is moved little by little toward the discharge chamber 60 by the paddle 17B of the rotating stirring rotor 17. While being moved by the stirring rotor 17, the sludge is dried by contact with the hot stirring rotor 17 and with the dry gas. The dried sludge moves over the weir 56 into the discharge chamber 60 and is discharged from the drying device 5 through the discharge port 26. A discharge conveyor 64 is disposed below the discharge outlet 26, and the dried sludge falls onto the discharge conveyor 64 through the discharge outlet 26 and is transported by the discharge conveyor 64.

The drying device 5 is connected to a control system 10 that controls the drying operation. The control system 10 includes a storage device 10a that executes machine learning, described below, to create a model and stores a program for using the model, and a computing device 10b that executes calculations according to instructions included in the program. The storage device 10a includes a main storage device such as a random access memory (RAM) and an auxiliary storage device such as a hard disk drive (HDD) or a solid state drive (SSD). Examples of the computing device 10b include a CPU (central processing unit) and a GPU (graphic processing unit). However, the specific configuration of the control system 10 is not limited to these examples.

The control system 10 is composed of at least one computer. The at least one computer may be one server or multiple servers. The control system 10 may be an edge server connected to the drying device 5 via a communication line, or may be a cloud server or a fog server connected to the drying device 5 via a communication network such as the Internet or a local area network. The control system 10 may be disposed in a gateway, a router, or the like.

The control system 10 may be multiple servers connected by a communication network such as the Internet or a local area network. For example, the control system 10 may be a combination of an edge server and a cloud server. The storage device 10a and the computing device 10b may each be located in multiple computers installed in separate locations.

Next, the functions of the control system 10 will be described. The control system 10 is configured to calculate a predicted value of the moisture content of the dried sludge discharged from the drying device 5 using a model (i.e., a trained model) constructed by machine learning. The model is stored in the storage device 10a. The calculation device 10b of the control system 10 is configured to input the state data of the drying device 5 described below into the trained model, and to calculate a predicted value of the moisture content of the dried sludge according to the algorithm of the trained model.

A trained model is created by machine learning using training data. Explanatory variables are input to the model, and a target variable is output from the model.
Explanatory variable: A variable used to derive the variable to be predicted (target variable).
Objective variable: a variable to be predicted. In this embodiment, the moisture content of the dried sludge discharged from the drying device 5 is the objective variable.

The explanatory variables included in the training data include not only the operating parameters of the drying device 5 used during past drying operations, but also state data of the drying device 5 (e.g., the moisture content of the sludge fed into the drying device 5) described below. The objective variable is the moisture content of the dried sludge corresponding to the operating parameters and state data. The control system 10 uses the training data including the explanatory variables and the objective variable to create a model according to a machine learning algorithm. The model may be either a regression model or a classification model.

Examples of machine learning algorithms include the SVR method (support vector regression method), the PLS method (partial least squares method), the deep learning method, the random forest method, and the decision tree method. In this embodiment, the random forest method is used for machine learning, but the present invention is not limited to this.

The training data used in the machine learning of the above model includes operating parameters of the drying device 5, status data of the drying device 5, and actual measurement data of the moisture content of the corresponding dried sludge.
The operating parameters of the drying device 5 are as follows:
Flow rate of sludge fed into the drying device 5 (conveying speed of the feeding conveyor 1)
Rotation speed of the stirring rotor 17 of the drying device 5 (rotation speed of the motor 18)
Torque current value of the electric motor 18 of the drying device 5 Height of the weir 56 (setting value of the vertical movement device 58)
Pressure of steam injected into the stirring rotor 17 (opening degree of the steam pressure control valve 52)
The temperature of the dry gas supplied to the housing 15 (measured by the temperature measuring device 32)
The flow rate of the dry gas supplied to the housing 15 (measured by the flow meter 33)

Specific examples of the status data of the drying device 5 are as follows.
The type of sludge fed into the drying device 5 (for example, in water treatment, digested sludge, mixed raw sludge, etc., the treatment plant where the sludge was generated)
The temperature of the sludge fed into the drying device 5 (measured by a measuring device not shown)
- Moisture content of the sludge fed into the drying device 5 (measured by a measuring device not shown)
Surface temperature of the drying device 5 (measured by the temperature measuring device 40)
Pressure in the drying device 5 (measured by the pressure measuring device 41)
Flow rate of steam injected into the stirring rotor 17 (opening degree of the steam pressure control valve 52)
The temperature of the dry gas exhausted from the housing 15 (measured by the temperature measuring device 35)
The amount of drainage resulting from condensation of steam discharged from the steam supply line 50 (measured by a measuring device not shown)

The above-mentioned items of operating parameters and status data are examples, and the operating parameters and status data may be only any of the above items.

In this embodiment, the operating parameters of the drying device 5 are varied little by little within a wide range, taking on a more diverse range of values than during normal operation of the drying device 5, while drying the sludge and obtaining actual measured values of moisture content. The control system 10 performs machine learning using the thus obtained operating parameters, the values of which are distributed within a wider range than during normal operation, the above-mentioned state data, and training data including the corresponding actual measured values of moisture content. Furthermore, the control system 10 obtains training data periodically or irregularly as described above, and performs machine learning using the obtained training data to update the model.

In one embodiment, the status data of the drying device 5 may include output values such as the operating parameters and status data of a dehydration system installed upstream of the drying device 5, and an estimated moisture content of the dehydrated sludge calculated according to a trained model incorporated in the dehydration system. Specific examples of dehydration systems are described below.

The dewatering system is disposed upstream of the input conveyor 1 in FIG. 1 and is configured to dewater a suspension such as sludge. FIG. 4 is a schematic diagram showing one embodiment of the dewatering system. The dewatering system includes a suspension storage tank 101 for storing a suspension, a flocculating device 103 for injecting a flocculant into the suspension and stirring the flocculant and the suspension to form a flocculate, a concentrating device 104 for removing liquid from the flocculate to form a concentrate, and a dewatering device 105 for further removing liquid from the concentrate consisting of the concentrated flocculate to form a turbid residue. The concentrating device 104 is a device for removing liquid from the flocculate formed by the flocculating device 103 to form a concentrate with a concentration of 3 to 15 wt%, and the dewatering device 105 is a device for removing liquid from the flocculate formed by the flocculating device 103 or the concentrate formed by the concentrating device 104 to form a turbid residue with a concentration of 3 to 50 wt%.

The turbid residue is a low-water content material that remains after the liquid is removed from the suspension. The turbid residue that remains after the liquid is removed from the suspension by the dewatering device 105 is generally called cake. In the following description, the suspension is called sludge, and the turbid residue is called cake. Specific examples of sludge include sludge generated during the treatment of sewage, human waste, and industrial wastewater. Examples of suspensions other than sludge include industrial waste generated during the manufacture of industrial products such as food, cosmetics, and paper, or slurry.

In this embodiment, the concentrator 104 is a rotating disk type dewatering device (for example, a Slit Saver manufactured by Kendensha Co., Ltd.). This type of concentrator 104 is preferable because it is easy to grasp the change in the state of the concentrated sludge, but the type of the concentrator 104 is not particularly limited. For example, the concentrator 104 may be a drum type, a screw type, or a belt type. The dewatering device 105 in this embodiment is composed of a screw press that pressurizes and dewaters the sludge. The screw press is an example of a pressurized dewatering machine that dewaters the sludge. The screw press can be of a pressurized type, a shaft sliding type, or a two-stage type. The dewatering device 105 shown in FIG. 4 is a shaft sliding type screw press. In addition to the screw press, other types such as a filter press and a centrifuge can also be used as the pressurized dewatering machine.

As shown in FIG. 4, the flocculation device 103 includes a flocculation mixing tank 107 that contains sludge and mixes the sludge with a flocculant, an agitator 108 for agitating the sludge in the flocculation mixing tank 107, a sludge inlet pipe (suspension inlet pipe) 114 connected to the flocculation mixing tank 107, and a pump 112 attached to the sludge inlet pipe 114. The agitator 108 includes an agitator blade 109 disposed in the flocculation mixing tank 107 and an agitator motor 110 connected to the agitator blade 109. The suspension storage tank 101 is connected to the flocculation mixing tank 107 by the sludge inlet pipe 114. The sludge is transferred from the suspension storage tank 101 to the flocculation mixing tank 107 through the sludge inlet pipe 114 by the pump 112. The flow rate of the sludge to the flocculation mixing tank 107 can be adjusted by operating the pump 112.

A temperature sensor 122 is attached to the sludge inlet pipe 114. This temperature sensor 122 is configured to measure the temperature of the sludge introduced into the flocculation mixing tank 107. Furthermore, a sludge concentration meter (suspension concentration meter) 124 is attached to the sludge inlet pipe 114, and the concentration of suspended solids in the sludge introduced into the flocculation mixing tank 107 is measured by the sludge concentration meter 124.

The flocculation device 103 further includes a water supply line 126 connected to the flocculation mixing tank 107, and a flow control valve 127 attached to the water supply line 126. The water supply line 126 supplies water to the flocculation mixing tank 107 to dilute the sludge in the flocculation mixing tank 107. The flow rate of the water supplied to the flocculation mixing tank 107 through the water supply line 126 is adjusted by the flow control valve 127. In one embodiment, the water supply line 126 may be connected to the sludge inlet pipe 114, and water may be supplied directly to the sludge inlet pipe 114.

The flocculation device 103 further includes a flocculant supply device 128 connected to the flocculation mixing tank 107. The flocculant supply device 128 is configured to inject a flocculant into the sludge in the flocculation mixing tank 107 at a predetermined flow rate. The flow rate of the flocculant injected into the sludge in the flocculation mixing tank 107 is adjusted by the flocculant supply device 128. The sludge is agitated together with the flocculant by the agitator 108. By agitating the flocculant and sludge in the flocculation mixing tank 107, a flocculant is formed in which suspended solids in the sludge gather. The flocculant formed in the flocculation mixing tank 107 is generally called a flocculated floc.

The flocculation mixing tank 107 shown in FIG. 4 is a single-stage tank, but the flocculation mixing tank 107 may be a multi-stage tank. The mixing strength of the sludge can be adjusted by the rotation speed of the agitator 108. The flocculation mixing tank 107 may be provided with a side glass so that the state of the flocs inside can be observed.

The flocculation mixing tank 107 is connected to the thickener 104 by a sludge transfer pipe 118. The thickener 104 is disposed between the flocculation device 103 and the dewatering device 105. Sludge consisting of flocculants formed by the flocculation device 103 is transferred to the thickener 104 through the sludge transfer pipe 118. The flocculants are thickened and dewatered by the thickener 104. An example of the thickener 104 is a rotating disk type dewatering device.

The outlet of the concentrator 104 is located above the inlet 135 of the dehydrator 105, and the sludge consisting of the concentrate formed by the concentrator 104 is fed into the inlet 135 of the dehydrator 105. In this embodiment, the dehydrator 105 is a screw press. The dehydrator 105 as a screw press includes a filter cylinder 136, a screw shaft 137 arranged concentrically within the filter cylinder 136, a screw blade 138 fixed to the outer surface of the screw shaft 137, a screw motor 140 that rotates the screw shaft 137 and the screw blade 138 to send the sludge toward the discharge chamber 141, and a shaft sliding actuator 142 connected to the screw motor 140.

The filter cylinder 136 is made of a perforated plate such as punched metal. One end of the filter cylinder 136 is sealed by a blocking wall 144, and the other end of the filter cylinder 136 is connected to the discharge chamber 141. The inlet 135 is formed in the filter cylinder 136 and is adjacent to the blocking wall 144.

The screw shaft 137 extends through the filter tube 136. The screw shaft 137 has a truncated cone shape whose diameter gradually increases toward the downstream side. The screw shaft 137 extends through the blocking wall 144, and the end of the screw shaft 137 is connected to the screw motor 140. The screw motor 140 has a built-in inverter (not shown).

The screw blade 138 is a single blade that extends in a spiral shape along the longitudinal direction of the screw shaft 137. A small gap is formed between the inner surface of the filter cylinder 136 and the screw blade 138, allowing the screw blade 138 to rotate without coming into contact with the filter cylinder 136. The sludge introduced into the filter cylinder 136 from the inlet 135 is transported through the filter cylinder 136 toward the discharge chamber 141 by the rotating screw blade 138.

The space through which the sludge is transported within the filter cylinder 136 is formed by the inner surface of the filter cylinder 136, the screw blades 138, and the screw shaft 137. The volume of this space gradually decreases along the direction in which the sludge moves. Therefore, as the sludge is moved through this space by the screw blades 138, it is squeezed and dewatered. The filtrate that passes through the filter cylinder 136 is collected by the filtrate receiver 145 located below the filter cylinder 136, and then discharged through the drain 146.

An annular back pressure plate 150 is disposed opposite the downstream end of the filter tube 136. This back pressure plate 150 has a truncated cone shape with a tapered surface for receiving the dewatered sludge transported inside the filter tube 136. A through hole through which the screw shaft 137 passes is formed in the center of the back pressure plate 150, and the back pressure plate 150 is disposed concentrically with the screw shaft 137. The back pressure plate 150 is not fixed to the screw shaft 137, and the back pressure plate 150 does not rotate.

The back pressure plate 150 is connected to a back pressure plate drive device 151. This back pressure plate drive device 151 is configured to move the back pressure plate 150 in the axial direction of the screw shaft 137. The gap between the back pressure plate 150 and the downstream end of the filter tube 136 is adjusted by the back pressure plate drive device 151. The back pressure plate drive device 151 is configured, for example, by a hydraulic cylinder or an electric cylinder.

The shaft sliding actuator 142 is configured to move the screw motor 140 in the axial direction of the screw shaft 137. When the shaft sliding actuator 142 moves the screw motor 140 in the axial direction, the screw shaft 137 and the screw blades 138 connected to the screw motor 140 are moved in the axial direction of the screw shaft 137 within the filter tube 136.

Next, the operation of the dehydration device 105 will be described. Sludge consisting of the concentrate formed by the concentrator 104 is fed into the filter cylinder 136 from the inlet 135. The sludge is transported through the filter cylinder 136 toward the discharge chamber 141 by the rotating screw blades 138. As the sludge moves through the filter cylinder 136, it is squeezed and dehydrated. The filtrate that passes through the filter cylinder 136 is collected by the filtrate receiver 145 and discharged through the drain 146. The sludge is dehydrated in the filter cylinder 136 to form a cake. The cleaning device 155 supplies cleaning liquid to the outer circumferential surface of the filter cylinder 136 at preset time intervals.

The cake moving through the filter tube 136 is pressed against the back pressure plate 150. The cake is compressed by being prevented from moving by the back pressure plate 150. This compressed cake forms a plug 152 that seals the downstream end of the filter tube 136. The plug 152 applies back pressure to the following cake, thereby reducing the moisture content of the cake in the filter tube 136. While forming the plug 152 in the filter tube 136, the cake is pushed by the following cake and passes through the gap between the back pressure plate 150 and the downstream end of the filter tube 136, and is discharged little by little into the discharge chamber 141. The cake is discharged from the discharge chamber 141 through the discharge port 153 provided at the bottom of the discharge chamber 141. In this way, the liquid is removed from the sludge, and a cake with a low moisture content is formed. The cake is transported to the input port 25 of the drying device 5 by the input conveyor 1 shown in FIG. 1.

The gap between the back pressure plate 150 and the downstream end of the filter tube 136 changes depending on the axial position of the back pressure plate 150, and as a result, the compressive force applied to the sludge in the filter tube 136 changes. More specifically, when the gap between the back pressure plate 150 and the downstream end of the filter tube 136 becomes smaller, a larger force is required to push out the plug 152, and the compressive force applied to the sludge in the filter tube 136 increases. Therefore, the compressive force applied to the sludge can be adjusted not only by the rotation speed of the screw blade 138 but also by the position of the back pressure plate 150. A pressure sensor 161 is disposed in the filter tube 136, and the pressure of the sludge in the filter tube 136 is measured by the pressure sensor 161. The position of the pressure sensor 161 is not particularly limited as long as it is within the filter tube 136, and may be any of the front stage, middle stage, or rear stage in the filter tube 136, and multiple pressure sensors 161 may be disposed in the filter tube 136.

The plug 152 is formed from a cake with a low moisture content. If the moisture content of the cake forming the plug 152 decreases, the plug 152 may harden and block the downstream end of the filter tube 136. In such a case, the shaft sliding actuator 142 can forcibly discharge the hard cake with a low moisture content by moving the screw shaft 137 and the screw blades 138 in the axial direction. As a result, the dewatering device 105 can operate stably and continuously.

Illustrative operating parameters and status data for a dewatering system are as follows:
- Sludge temperature (measured by temperature sensor 122)
Flow rate of sludge into the coagulation mixing tank 107 (estimated from the rotation speed of the pump 112)
- Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids)
・Physical properties of flocculant (cationicity, molecular weight)
Flow rate of flocculant (operating speed of flocculant supply device 128)
The stirring speed of the stirrer 108 (the rotation speed of the stirring motor 110)
Flow rate of water to the flocculation mixing tank 107 (opening degree of the flow control valve 127)
- Operating speed of the concentrator 104 (rotation speed of the drive motor of the concentrator 104)
Operating torque of the concentrator 104 (current value to the drive motor of the concentrator 104)
The flow rate of the liquid separated by the concentrator 104 (measured by a flow meter, not shown)
Concentration of sludge thickened by the thickening device 104 (measured by a concentration sensor not shown)
Rotational speed of the screw shaft 137 Current value (torque value) to the screw motor 140
The pressure of the sludge in the filter cylinder 136 (measured by the pressure sensor 161)
Opening degree of the back pressure plate 150 (setting value of the back pressure plate driver 151)
Pressure of the back pressure plate 150 (measured by a pressure sensor not shown)
- Measurement value of cake moisture content (measured by a measuring device not shown or manually)

The above-mentioned items of operating parameters and status data of the dehydration system are examples, and the operating parameters and status data of the dehydration system may be only any of the above items.

Figure 5 is a diagram showing another embodiment of a dehydration system. The dehydration system shown in Figure 5 differs from the embodiment in Figure 4, which uses a shaft-sliding screw press, in that a two-stage screw press is used as the dehydration device 105. In this embodiment, the shaft-sliding actuator 142 shown in Figure 4 is not provided. The configurations and operations of the embodiments not specifically described are the same as those of the embodiment shown in Figure 4, so duplicated descriptions will be omitted.

The dewatering device 105, which is composed of a two-stage screw press, is equipped with a filter cylinder 136, a first screw 171 and a second screw 172 that are arranged concentrically with the filter cylinder 136 within the filter cylinder 136 and transport sludge, a first screw motor 175 that rotates the first screw 171, and a second screw motor 176 that rotates the second screw 172 independently of the first screw 171.

The first screw motor 175 and the second screw motor 176 may be directly connected to the first screw 171 and the second screw 172, respectively, or may be connected to the first screw 171 and the second screw 172, respectively, via a torque transmission mechanism composed of a chain, sprockets, etc.

The filter cylinder 136 is formed from a screen (perforated plate) such as punched metal. An inlet 135 is formed at the upstream end of the filter cylinder 136. Sludge fed into the filter cylinder 136 from the inlet 135 is transported in a predetermined transport direction within the filter cylinder 136 by the rotating first screw 171 and second screw 172. The downstream end of the filter cylinder 136 is connected to the discharge chamber 141.

The second screw 172 is connected to the first screw 171 so as to be rotatable independently of the first screw 171. The first screw 171 and the second screw 172 extend through the filter tube 136 and the discharge chamber 141, respectively. The discharge chamber 141 is connected to the filter tube 136. A plug 177 made of cake is discharged from the filter tube 136 to this discharge chamber 141. The axial length of the second screw 172 is shorter than the axial length of the first screw 171. The first screw 171 has a first screw shaft 171A having a truncated cone shape whose diameter gradually increases along the sludge transport direction, and a first screw blade 171B fixed to the outer surface of the first screw shaft 171A. The second screw 172 has a cylindrical second screw shaft 172A and a second screw blade 172B fixed to the outer surface of the second screw shaft 172A.

The upstream end of the filter tube 136 is sealed by a blocking wall 144. The upstream end of the first screw shaft 171A extends through this blocking wall 144 and is connected to a first screw motor 175 for rotating the first screw 171. The second screw shaft 172A of the second screw 172 is arranged concentrically with the first screw shaft 171A. The outer diameter of the second screw shaft 172A is the same as the maximum diameter of the first screw shaft 171A. The downstream end of the second screw shaft 172A extends through the wall 141A that constitutes the discharge chamber 141 and is connected to a second screw motor 176 for rotating the second screw 172. The lower part of the discharge chamber 141 is connected to the discharge port 153.

The first screw motor 175 has a built-in inverter (not shown), and the motor control unit 106 is configured to be able to control the operation of the first screw motor 175 via the inverter. That is, the motor control unit 106 can control the rotation speed and rotation direction of the first screw motor 175 via the inverter. The motor control unit 106 can issue a command to the first screw motor 175 to rotate the first screw 171 independently of the second screw 172.

The second screw motor 176 is also connected to the motor control unit 106. The second screw motor 176 has a built-in inverter (not shown), and the motor control unit 106 is configured to be able to control the operation of the second screw motor 176 via the inverter. In other words, the motor control unit 106 can control the rotation speed and rotation direction of the second screw motor 176 via the inverter. The motor control unit 106 can issue a command to the second screw motor 176 to rotate the second screw 172 independently of the first screw 171.

The first screw blade 171B extends helically along the axial direction of the first screw shaft 171A, and the second screw blade 172B extends helically along the axial direction of the second screw shaft 172A. The combined length of the portion of the first screw 171 to which the first screw blade 171B is fixed and the portion of the second screw 172 to which the second screw blade 172B is fixed is equal to or longer than the axial length of the filter tube 136.

A small gap is formed between the inner surface of the filter tube 136 and the first screw blade 171B, allowing the first screw blade 171B to rotate without contacting the filter tube 136. Similarly, a small gap is formed between the inner surface of the filter tube 136 and the second screw blade 172B, allowing the second screw blade 172B to rotate without contacting the filter tube 136. Sludge introduced into the filter tube 136 from the inlet 135 formed at the upstream end of the filter tube 136 can be transported toward the discharge chamber 141 by the rotating first screw blade 171B and second screw blade 172B.

The pitch of the second screw blade 172B is smaller than the pitch of the first screw blade 171B. Furthermore, the number of turns of the second screw blade 172B is less than three. In this embodiment, the winding direction (i.e., the helical direction) of the second screw blade 172B is opposite to the winding direction of the first screw blade 171B. Therefore, when the sludge introduced from the inlet 135 is sent to the discharge chamber 141, the second screw 172 is rotated in the opposite direction to the first screw 171, as shown in FIG. 5.

The winding direction of the second screw blade 172B may be the same as the winding direction of the first screw blade 171B. In this case, when the sludge input from the input port 135 is sent to the discharge chamber 141, the second screw 172 is rotated in the same direction as the first screw 171.

The filter cylinder 136 is divided into a dewatering area 1A in which the first screw 171 is arranged, and a plug formation area 1B in which the second screw 172 is arranged. The space in which the sludge is transported in the dewatering area 1A is formed by the inner surface of the filter cylinder 136, the first screw blade 171B, and the first screw shaft 171A. The cross-sectional area of this transport space gradually decreases along the sludge transport direction, as shown in FIG. 5. Therefore, as the sludge introduced from the inlet 135 is transported through this transport space by the first screw blade 171B, the sludge is squeezed and dewatered. The filtrate that passes through the filter cylinder 136 is collected by the filtrate receiver 145 arranged below the filter cylinder 136. A drain 146 is connected to the filtrate receiver 145, and the filtrate collected by the filtrate receiver 145 is discharged from the dewatering device 105 via the drain 146.

The space through which the sludge is transported in the plug formation region 1B is formed by the inner surface of the filter tube 136, the second screw blade 172B, and the second screw shaft 172A. As shown in FIG. 5, the cross-sectional area of this transport space is constant. In the plug formation region 1B, a plug 177 is formed by the sludge (i.e., cake) dewatered in the dewatering region 1A. The plug 177 applies back pressure to the subsequent cake, thereby reducing the moisture content of the cake in the filter tube 136. While forming the plug 177 in the plug formation region 1B, the cake is pushed by the subsequent cake and is discharged little by little into the discharge chamber 141. The cake is discharged from the discharge chamber 141 through the discharge port 153 provided at the bottom of the discharge chamber 141. In this way, the liquid is removed from the sludge, and a cake with a low moisture content is formed. The cake is transported to the input port 25 of the drying device 5 by the input conveyor 1 shown in FIG. 1.

Specific examples of the operating parameters and status data of the dehydration system of this embodiment are as follows.
- Sludge temperature (measured by temperature sensor 122)
Flow rate of sludge to the coagulation mixing tank 107 (rotation speed of pump 112)
- Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids)
・Physical properties of flocculant (cationicity, molecular weight)
Flow rate of flocculant (operating speed of flocculant supply device 128)
The stirring speed of the stirrer 108 (the rotation speed of the stirring motor 110)
Flow rate of water to the flocculation mixing tank 107 (opening degree of the flow control valve 127)
- Operating speed of the concentrator 104 (rotation speed of the drive motor)
Operating torque of the concentrator 104 (current value to the drive motor)
The flow rate of the liquid separated by the concentrator 104 (measured by a flow meter, not shown)
Concentration of sludge thickened by the thickening device 104 (measured by a concentration sensor not shown)
Rotational speed of the first screw 171 Current value (torque value) to the first screw motor 175
Rotational speed of the second screw 172 Current value (torque value) to the second screw motor 176
The pressure of the sludge in the filter cylinder 136 (measured by the pressure sensor 161)
- Measurement value of cake moisture content (measured by a measuring device not shown or manually)

The above-mentioned items of operating parameters and status data of the dehydration system are examples, and the operating parameters and status data of the dehydration system may be only any of the above items.

In the embodiment shown in Figures 4 and 5, the dewatering system includes a thickener 104, but in one embodiment, the thickener 104 may be omitted. In this case, the flocs (flocs) formed in the flocculation device 103 are transported through the sludge transport pipe 118 to the inlet 135 of the dewatering device 105.

Figure 6 is a diagram showing yet another embodiment of a dehydration system. In the dehydration system shown in Figure 6, a belt press type dehydration device is used as the dehydration device 105. The concentrating device 104 described above is not provided. The configuration and operation of the embodiments not specifically described are the same as those of the embodiment shown in Figure 4, so duplicated descriptions will be omitted.

The flocculation device 103 includes a granulation tank 180 for storing sludge, an agitator 108 for agitating the sludge in the granulation tank 180, a sludge inlet pipe 114 connected to the granulation tank 180, and a pump 112 attached to the sludge inlet pipe 114. The agitator 108 includes an agitator blade 109 disposed in the granulation tank 180 and an agitator motor 110 connected to the agitator blade 109. The suspension storage tank 101 is connected to the flocculation tank 180 by the sludge inlet pipe 114. The sludge is transferred from the suspension storage tank 101 to the granulation tank 180 through the sludge inlet pipe 114 by the pump 112. The flow rate of the sludge to the granulation tank 180 can be adjusted by operating the pump 112.

A temperature sensor 122 is attached to the sludge inlet pipe 114. This temperature sensor 122 is configured to measure the temperature of the sludge introduced into the granulation tank 180. Furthermore, a sludge concentration meter (suspension concentration meter) 124 is attached to the sludge inlet pipe 114, and the concentration of suspended solids in the sludge introduced into the granulation tank 180 is measured by the sludge concentration meter 124.

The flocculation device 103 further includes a flocculant supply device 128 connected to the granulation tank 180. The flocculant supply device 128 is configured to inject a flocculant into the sludge in the granulation tank 180 at a predetermined flow rate. The flow rate of the flocculant injected into the sludge in the granulation tank 180 is adjusted by the flocculant supply device 128. The sludge is agitated together with the flocculant by the agitator blades 109 of the agitator 108. By agitating the flocculant and sludge in the granulation tank 180, a flocculant is formed in which suspended matter in the sludge gathers. The flocculant formed in the granulation tank 180 is generally called a pellet. The agitation strength of the sludge can be adjusted by the rotation speed of the agitator 108.

The granulation tank 180 is connected to the belt press type dewatering device 105 by the sludge transfer pipe 118. The dewatering device 105 is equipped with an endless pretreatment filter cloth belt 182, a plurality of support rollers 183a to 183c that support the pretreatment filter cloth belt 182, an endless first filter cloth belt 186, first guide rollers 188a to 188e that support the first filter cloth belt 186, an endless second filter cloth belt 190, second guide rollers 191a to 191f that support the second filter cloth belt 190, a plurality of compression rollers 195A to 195E that support the first filter cloth belt 186 and the second filter cloth belt 190, and a drive device 198 that moves the first filter cloth belt 186 and the second filter cloth belt 190.

The pretreatment filter belt 182 is disposed upstream of the squeezing rollers 195A-195E in the sludge transport direction. A portion of the pretreatment filter belt 182 is supported by support rollers 183a and 183b so as to form an inclined portion 182A that is inclined upward along the sludge transport direction. The support roller 183a is connected to the drive shaft of the electric motor 200. When the electric motor 200 rotates the support roller 183a, the pretreatment filter belt 182 moves in a direction in which the sludge on the inclined portion 182A rises.

The driving device 198 includes an electric motor 198A, a driving wheel 198B fixed to the driving shaft of the electric motor 198A, and a belt 198C supported by the driving wheel 198B as a driving force transmission member. A chain may be used instead of the belt 198C. The belt 198C is connected to the first guide roller 188c and further to the second guide roller 191f. When the electric motor 198A rotates the driving wheel 198B, the rotation of the driving wheel 198B is transmitted to the first guide roller 188c and the second guide roller 191f by the belt 198C. The first guide roller 188c and the second guide roller 191f rotate at the same speed, and as a result, the first filter cloth belt 186 and the second filter cloth belt 190 move in the same direction at the same speed.

The first filter cloth belt 186 is supported by first guide rollers 188a-188e and a number of compression rollers 195A-195E. The first guide roller 188d is connected to a first filter cloth tensioning device 201. This first filter cloth tensioning device 201 is configured to adjust the tension of the first filter cloth belt 186 by moving the position of the first guide roller 188d.

The second filter cloth belt 190 is supported by second guide rollers 191a-191f and a number of compression rollers 195A-195E. The second guide roller 191a is connected to a second filter cloth tensioning device 202. This second filter cloth tensioning device 202 is configured to adjust the tension of the second filter cloth belt 190 by moving the position of the second guide roller 191a.

The sludge consisting of the flocculants (pellets) formed by the flocculation device 103 is transferred through the sludge transfer pipe 118 onto the pretreatment filter cloth belt 182. As the sludge rises up the inclined portion 182A of the pretreatment filter cloth belt 182, the liquid in the sludge falls due to gravity. This process is the gravity dewatering process.

By the movement of the pretreatment filter cloth belt 182, the sludge on the pretreatment filter cloth belt 182 is transferred onto the first filter cloth belt 186. The first filter cloth belt 186 and the second filter cloth belt 190, which extend between the multiple compression rollers 195A to 195E, face each other. As the first filter cloth belt 186 moves, the sludge is sandwiched between the first filter cloth belt 186 and the second filter cloth belt 190. While the first filter cloth belt 186 and the second filter cloth belt 190 are wound around the compression rollers 195A to 195E, the sludge is sandwiched between the first filter cloth belt 186 and the second filter cloth belt 190 and squeezed. As a result, the sludge becomes a cake (turbid residue) with a low moisture content. The cake with a low moisture content is discharged from the discharge port 153. The cake is transported to the input port 25 of the drying device 5 by the input conveyor 1 shown in FIG. 1.

A filtrate receiver 145 is disposed below the compression rollers 195A-195E. The filtrate removed from the sludge is collected by the filtrate receiver 145. A drain 146 is connected to the filtrate receiver 145, and the filtrate collected by the filtrate receiver 145 is discharged from the dehydrator 105 via the drain 146.

Specific examples of the operating parameters and status data of the dehydration system of this embodiment are as follows.
- Sludge temperature (measured by temperature sensor 122)
Flow rate of sludge into the granulation tank 180 (rotation speed of the pump 112)
- Sludge properties (pH, alkalinity, TS, VTS, SS, VSS, suspended solids)
・Physical properties of flocculant (cationicity, molecular weight)
Flow rate of flocculant (operating speed of flocculant supply device 128)
The stirring speed of the stirrer 108 (the rotation speed of the stirring motor 110)
The moving speed of the first filter cloth belt 186 and the second filter cloth belt 190 (the rotation speed of the motor 198A)
Positions of guide rollers 188d and 191a

The above-mentioned items of operating parameters and status data of the dehydration system are examples, and the operating parameters and status data of the dehydration system may be only any of the above items.

Figure 7 is a diagram illustrating a flow for creating a model through machine learning using training data and calculating a predicted value of moisture content using the trained model. The arithmetic device 10b of the control system 10 executes machine learning using the training data according to instructions included in the program stored in the storage device 10a to construct a model. The obtained model is stored in the storage device 10a. A trained model constructed in advance may also be stored in the storage device 10a. The control system 10 inputs the operating parameters and status data of the drying device 5 into the trained model and calculates a predicted value of the moisture content of the dried sludge according to the model.

The control system 10 may be installed in a remote location away from the drying device 5. For example, the control system 10 may be connected to the drying device 5 via a communication network such as the Internet or a local area network, and may be installed in a remote monitoring room that monitors multiple drying devices. In one embodiment, the control system 10 has a Web application, and may use the Web application to display data acquired from the drying device 5, operate the drying device 5, send and receive data, learn the model by machine learning, and update the model. Furthermore, as shown in FIG. 7, the control system 10 may have a display unit 46 for notifying the predicted value of the moisture content of the dried sludge calculated according to the learned model, the current operating parameters, and the current state data. The display unit 46 may be installed in a remote location away from the drying device 5. For example, the display unit 46 may be installed in a remote monitoring room that monitors multiple drying devices 5. FIG. 8 shows a specific example of the display unit 46. Note that in FIG. 8, the display unit 46 is shown as a specific example of the notification, but the notification may be made by voice.

As shown in FIG. 7, the control system 10 is configured to search for optimal values of the operating parameters of the drying device 5 that can bring the moisture content of the dried sludge within a predetermined target range, and output the determined optimal values of the operating parameters. More specifically, the arithmetic unit 10b of the control system 10 selects one of multiple sets of values of the operating parameters according to instructions included in the program stored in the memory unit 10a, inputs the selected one set of values into the trained model, determines whether the predicted value of the moisture content calculated according to the trained model falls within the target range, and determines the optimal values of the operating parameters that can bring the predicted value of the moisture content within the target range.

The control system 10 adjusts the operating parameters of the dryer 5 so that the current values of the operating parameters become the determined optimal values. As a result, the dryer 5 is operated with the optimized operating parameters, and can produce dried sludge whose moisture content falls within the target range.

The operation adjustment of the drying device 5 based on the optimal values of the operating parameters determined by the above search may be performed according to a predetermined priority order of the operating parameters. That is, the control system 10 adjusts the operating parameter with the highest priority order first, and then adjusts the operating parameter with the next highest priority order. In this way, the control system 10 sequentially adjusts the operating parameters according to the predetermined priority order. By giving priority to adjusting the operating parameters that have a large effect on the moisture content, the moisture content can be efficiently kept within the target range.

In one embodiment, the control system 10 may determine the priority of the operating parameters according to the importance of the feature calculated during machine learning. For example, in an embodiment in which a random forest is used as the machine learning algorithm, the computing device 10b of the control system 10 may calculate the importance corresponding to the amount of reduction in Gini importance and determine the priority of the operating parameters according to the obtained importance. In one embodiment, the priority of the operating parameters may be preset by an operator.

When adjusting the operating parameters according to the determined optimal values, if the difference between the current value of the operating parameters and the determined optimal values is greater than a predetermined adjustment range, the control system 10 can adjust the operating parameters in stages in increments of the adjustment range. For example, if the difference between the current value of the flow rate of sludge fed into the drying device 5 and the optimal flow rate is 100, and the predetermined adjustment range is 50, the sludge supply flow rate is adjusted in two stages. In this way, by adjusting the operating parameters in stages, stable operation can be achieved and the moisture content can be more efficiently and accurately kept within the target range. The adjustment range or the number of stages can be set in advance.

The control system 10 may have multiple models for calculating multiple predicted values of the moisture content of the dried sludge. In one embodiment, the multiple models include a first model using a controllable explanatory variable and a second model using a controllable explanatory variable and an uncontrollable explanatory variable. In one example, the controllable explanatory variable used to construct the first model is the above-mentioned operating parameter. That is, training data that includes the operating parameters, which are controllable explanatory variables, and does not include state data, which is an uncontrollable explanatory variable, is used for the machine learning to construct the first model. The training data used for the machine learning of the second model includes both the operating parameters and state data.

In one embodiment, the first model is used to determine the optimal values of the operating parameters that allow the moisture content of the dried sludge to fall within a predetermined target range, and the second model is used to predict the moisture content with greater accuracy. The first model is expected to predict the moisture content with lower accuracy than the second model. If the difference between the moisture content calculated according to the first model and the moisture content calculated according to the second model exceeds a predetermined tolerance, the control system 10 may perform machine learning for the first model again to update the first model.

Here, an example of an actual drying system will be described. In this example, a drying system for drying dewatered sewage sludge was used. Using training data including operating parameters such as the height of the weir 56 of the drying device 5 and past state data such as the moisture content of the supplied sludge, a model was constructed that estimates the moisture content of the sludge discharged from the drying device 5 using random forest as a machine learning algorithm. While the drying device 5 is in operation, the operating parameters used as training data and the current values of the state data are input into the trained model, and a predicted value of the moisture content at that time is calculated.

The operating parameters were adjusted according to their priority so that the moisture content would fall within the target range. In this example, the importance of each operating parameter calculated when building the model is shown in Figure 9. The priority when adjusting the operating parameters was determined according to the level of importance, and the sludge supply volume, which has the greatest importance, was adjusted with the highest priority.

When the sludge supply rate input into the trained model was 800 kg/h, the predicted moisture content was 45%. The optimal sludge supply rate, which has the first priority, was calculated to be 700 kg/h in order to keep the moisture content within the target range of 40 to 42%. The sludge supply rate was set to be adjusted in stages when the adjustment range exceeded 100. Therefore, when the sludge supply rate was adjusted from 800 kg/h to 700 kg/h, the sludge supply rate was changed in two stages (from 800 kg/h to 750 kg/h, and from 750 kg/h to 700 kg/h). If the moisture content of the dried sludge does not fall within the target range even when the sludge supply rate is changed to the optimal value, the height of the weir 56, which has the second priority, is adjusted.

In one embodiment, the control system 10 is electrically connected to the dehydration system described with reference to FIGS. 4 and 5. The operation parameters and status data of the dehydration system, and the estimated moisture content of the dehydrated sludge calculated according to the trained model incorporated in the dehydration system (hereinafter, collectively referred to as the operation index data of the dehydration system) are transmitted to the control system 10. In one embodiment, the status data of the drying device 5 may include the operation index data of the dehydration system. The control system 10 performs machine learning using training data including such status data of the drying device 5, the operation parameters of the drying device 5, and the corresponding actual measured moisture content values, to construct a model. The obtained model is stored in the storage device 10a. The control system 10 inputs the operation parameters and status data of the drying device 5 (including the current operation index data of the dehydration system) into the trained model, and calculates the predicted moisture content of the dried sludge according to the model.

In one embodiment, the control system 10 may perform machine learning and construct a model using training data that further includes at least one of sludge image data, sludge sound data, and vibration data generated due to sludge, in addition to the operating parameters and status data of the drying device 5. The image data is, for example, at least one of image data of sludge before it is input into the drying device 5, image data of sludge in the drying device 5, and image data of sludge dried by the drying device 5. The sound data is, for example, at least one of sound data of sludge generated when input into the drying device 5, sound data of sludge in the drying chamber 14 of the drying device 5, and sound data of sludge generated when discharged from the drying chamber 14 of the drying device 5. The vibration data is, for example, at least one of vibration data of an elastic member that comes into contact with the sludge input into the drying device 5, and vibration data of an elastic member that comes into contact with the sludge discharged from the drying chamber 14 of the drying device 5.

One, two, or all of the image data, sound data, and vibration data may be used. During operation of the drying device 5, the trained model is input with the same type of data used for machine learning. Because at least one of the image data, sound data, and vibration data is used for machine learning of the model, the control system 10 can use the trained model to calculate a more accurate prediction of the moisture content.

Hereinafter, an embodiment of a drying system having a configuration for acquiring image data, sound data, and vibration data will be described.
Fig. 10 is a schematic diagram showing an embodiment of a drying system having a configuration for acquiring image data. Configurations and operations that are not specifically described are the same as those of the embodiment described with reference to Figs. 1 to 9, and therefore duplicated descriptions will be omitted.

As shown in FIG. 10, the control system 10 includes an imaging device 7 that generates image data of the sludge before it is fed into the drying device 5. The imaging device 7 is arranged near the inlet 25 of the drying device 5 and is arranged to generate image data of the sludge before it is dried. In one embodiment, the imaging device 7 may be arranged to generate image data of the sludge on the input conveyor 1, or may be arranged near the outlet of a dewatering device (not shown) arranged upstream of the input conveyor 1. The imaging device 7 is connected to a storage device 10a of the control system 10, and the image data of the sludge generated by the imaging device 7 is stored in the storage device 10a.

The control system 10 further includes an imaging device 8 that generates image data of the sludge in the drying device 5. The imaging device 8 is fixed to the upper wall of the housing 15 of the drying device 5 and is arranged facing the interior of the drying device 5, more specifically, the interior of the drying chamber 14. In one embodiment, a plurality of imaging devices 8 may be arranged along the axial direction of the stirring rotor 17. The imaging device 8 is arranged to generate image data of the sludge in the process of being dried, i.e., the sludge being stirred by the stirring rotor 17. The imaging device 8 is connected to a storage device 10a of the control system 10, and the image data of the sludge generated by the imaging device 8 is stored in the storage device 10a.

The control system 10 further includes an imaging device 9 that generates image data of the sludge dried by the drying device 5. The imaging device 9 is disposed near the discharge outlet 26 of the drying device 5. More specifically, the imaging device 9 is disposed facing the discharge outlet 26 and disposed to generate image data of the sludge discharged from the drying chamber 14 of the drying device 5. In one embodiment, the imaging device 9 may be disposed inside or outside the discharge chamber 60. Furthermore, in one embodiment, the imaging device 9 may be disposed to generate image data of the sludge on the discharge conveyor 64. The imaging device 9 is connected to a storage device 10a of the control system 10, and the image data of the sludge generated by the imaging device 9 is stored in the storage device 10a.

Imaging device 7, imaging device 8, and imaging device 9 are digital cameras equipped with image sensors (e.g., CCD image sensors or CMOS image sensors) capable of generating still or continuous images of an object. Alternatively, at least one of imaging device 7, imaging device 8, and imaging device 9 may be an infrared camera or a hyperspectral camera capable of resolving light into wavelengths to capture an image of an object.

The control system 10 performs machine learning using training data including image data generated by the imaging devices 7, 8, and 9, the operating parameters of the drying device 5, and the status data of the drying device 5, to create a model that calculates a predicted value of the moisture content of the dried sludge. During operation of the drying device 5, the control system 10 inputs the image data generated by the imaging devices 7, 8, and 9, the operating parameters of the drying device 5, and the status data of the drying device 5 into the trained model, and calculates a predicted value of the moisture content of the dried sludge according to the trained model.

Figure 11 is a schematic diagram showing an embodiment of a drying system equipped with a configuration for acquiring sound data. Configurations and operations that are not specifically described are the same as those in the embodiment described with reference to Figures 1 to 9, and therefore will not be described again.

As shown in FIG. 11, the control system 10 includes a sound detector 71 that detects the sound of the sludge generated when it is fed into the drying device 5 and generates sound data, a sound detector 72 that detects the sound of the sludge in the drying chamber 14 of the drying device 5 and generates sound data, and a sound detector 73 that detects the sound of the sludge generated when it is discharged from the drying chamber 14 of the drying device 5 and generates sound data. The specific configurations of the sound detectors 71, 72, and 73 are not particularly limited, but in this embodiment, microphones that convert sound into electrical signals are used. The sound data generated by the sound detectors 71, 72, and 73 is data consisting of digital signals. For example, the sound data is sound waveform data showing the relationship between amplitude and time, or sound waveform data showing the relationship between frequency and sound volume. The sound data may be data extracted from the range where sound is generated from the sludge, or time-series data extracted in frames of a certain time length. For example, MFCC (Mel Frequency Cepstrum Coefficient), which is a feature value extracted from the sound data, is input to the trained model. For example, preprocessing is performed on sound data, and the spectrogram is input as image data into a trained model.

The sound detector 71 is disposed in the drying chamber 14. More specifically, the sound detector 71 is disposed below the inlet 25 of the housing 15, and detects the sound of the sludge generated when the sludge introduced through the inlet 25 falls onto the pile of sludge already contained in the housing 15, and generates sound data. In one embodiment, a collision member (not shown) may be disposed in the housing 15 and below the inlet 25, and the sound detector 71 may detect the sound of the sludge generated when it falls onto the collision member and generate sound data. The sound detector 71 is connected to the storage device 10a of the control system 10, and the sound data generated by the sound detector 71 is stored in the storage device 10a.

At least a portion of the sound detector 72 is located inside the drying chamber 14. More specifically, the sound detector 72 is fixed to the upper wall of the housing 15. The sound detector 72 detects the sound of the sludge generated during the process of drying in the drying device 5 (inside the drying chamber 14), i.e., the sound of the sludge generated when being stirred by the stirring rotor 17, and generates sound data. The sound detector 72 is connected to the memory device 10a of the control system 10, and the sound data generated by the sound detector 72 is stored in the memory device 10a.

The sound detector 73 is disposed below the discharge port 26 of the housing 15, and detects the sound generated when the sludge discharged from the drying chamber 14 falls onto the discharge conveyor 64, and generates sound data. In one embodiment, the sound detector 73 may be disposed in the discharge chamber 60 or in the discharge port 26. Furthermore, in one embodiment, a collision member (not shown) may be disposed in the discharge chamber 60, in the discharge port 26, or below the discharge port 26, and the sound detector 73 may detect the sound of the sludge when it falls onto the collision member and generate sound data. The sound detector 73 is connected to the storage device 10a of the control system 10, and the sound data generated by the sound detector 73 is stored in the storage device 10a.

In general, the sounds generated by sludge differ depending on whether the moisture content of the sludge is high or low. Specifically, when the moisture content of sludge is high, a wet sound is generated, whereas when the moisture content of sludge is low, a dry sound is generated. Therefore, the sounds generated by sludge when it is added, dried, and discharged vary depending on the moisture content of the sludge.

The control system 10 performs machine learning using training data including the sound data generated by the sound detectors 71, 72, and 73, the operating parameters of the dryer 5, and the status data of the dryer 5, to create a model that calculates a predicted value of the moisture content of the dried sludge. During operation of the dryer 5, the control system 10 inputs the sound data generated by the sound detectors 71, 72, and 73, the operating parameters of the dryer 5, and the status data of the dryer 5 into the trained model, and calculates a predicted value of the moisture content of the dried sludge according to the trained model.

Figure 12 is a schematic diagram showing an embodiment of a drying system equipped with a configuration for acquiring vibration data. Configurations and operations that are not specifically described are the same as those in the embodiment described with reference to Figures 1 to 9, and therefore will not be described again.

As shown in FIG. 12, the control system 10 includes an elastic member 81 that comes into contact with the sludge fed into the drying device 5, a vibration detector 82 that is fixed to the elastic member 81 and generates vibration data of the elastic member 81, an elastic member 85 that comes into contact with the sludge discharged from the drying chamber 14 of the drying device 5, and a vibration detector 86 that is fixed to the elastic member 85 and generates vibration data of the elastic member 85. The specific configurations of the vibration detector 82 and the vibration detector 86 are not particularly limited, but in this embodiment, a vibration sensor or acceleration sensor that converts vibration into an electrical signal is used.

The vibration detector 82 is fixed to an elastic member 81 arranged below the inlet 25 of the housing 15. The elastic member 81 is arranged in the drying chamber 14. In this embodiment, the elastic member 81 is plate-shaped. One end of the elastic member 81 is fixed to the side wall of the housing 15, and the vibration detector 82 is fixed to the other end of the elastic member 81. The sludge introduced through the inlet 25 falls onto the elastic member 81, and the vibration detector 82 vibrates together with the elastic member 81. The vibration detector 82 detects the vibration generated when the sludge falls onto the elastic member 81 and generates vibration data. The vibration detector 82 is connected to the storage device 10a of the control system 10, and the vibration data generated by the vibration detector 82 is stored in the storage device 10a.

The vibration detector 86 is fixed to an elastic member 85 arranged below the discharge port 26 of the housing 15. In this embodiment, the elastic member 85 is plate-shaped. One end of the elastic member 85 is fixed to a fixing member (not shown), and the vibration detector 86 is fixed to the other end of the elastic member 85. In one embodiment, the elastic member 85 and the vibration detector 86 may be arranged in the discharge chamber 60 or in the discharge port 26.

The sludge discharged from the drying chamber 14 falls onto the elastic member 85, and the vibration detector 86 vibrates together with the elastic member 85. The vibration detector 86 detects the vibrations generated when the sludge falls onto the elastic member 85, and generates vibration data. The vibration detector 86 is connected to the storage device 10a of the control system 10, and the vibration data generated by the vibration detector 86 is stored in the storage device 10a.

The vibration data generated by the vibration detector 82 and the vibration detector 86 is, for example, data showing the relationship between amplitude and time, and is data consisting of digital signals. In general, when the moisture content of the sludge is high and when it collides with the elastic members 81 and 85, the way in which these members vibrate differs. Specifically, when the moisture content of the sludge is high, larger lumps come into contact with the elastic members 81 and 85, and the period of vibration tends to be shorter. In contrast, when the moisture content of the sludge is low, smaller lumps come into contact with the elastic members 81 and 85, and the period of vibration tends to be longer. Therefore, the vibration data of the elastic members 81 and 85 changes depending on the moisture content of the sludge.

The control system 10 performs machine learning using training data including the vibration data generated by the vibration detector 82 and the vibration detector 86, the operating parameters of the dryer 5, and the status data of the dryer 5, to create a model that calculates a predicted value of the moisture content of the dried sludge. During operation of the dryer 5, the control system 10 inputs the vibration data generated by the vibration detector 82 and the vibration detector 86, the operating parameters of the dryer 5, and the status data of the dryer 5 into the trained model, and calculates a predicted value of the moisture content of the dried sludge according to the trained model.

In one embodiment, all of the imaging devices 7, 8, and 9, the sound detectors 71, 72, and 73, and the vibration detectors 82 and 86 may be provided. Alternatively, a combination of two of the imaging devices 7, 8, and 9, the sound detectors 71, 72, and 73, and the vibration detectors 82 and 86 may be provided.

The above-described embodiments have been described for the purpose of enabling a person having ordinary knowledge in the technical field to which the present invention pertains to practice the present invention. Various modifications of the above-described embodiments would naturally be possible for a person skilled in the art, and the technical ideas of the present invention may also be applied to other embodiments. Therefore, the present invention is not limited to the described embodiments, but is to be interpreted in the broadest scope in accordance with the technical ideas defined by the scope of the claims.

REFERENCE SIGNS LIST 1: Input conveyor 5: Drying device 7: Imaging device 8: Imaging device 9: Imaging device 10: Control system 10a: Memory device 10b: Processing device 14: Drying chamber 15: Housing 17: Stirring rotor 17A: Shaft 17B: Paddle 18: Motor 20: Gear 22: Torque transmission mechanism 25: Input inlet 26: Discharge outlet 30: Dry gas supply line 31: Dry gas discharge line 32: Temperature measuring device 33: Flow rate measuring device 35: Temperature measuring device 40: Temperature measuring device 41: Pressure measuring device 46: Display unit 50: Steam supply line 51: Boiler 52: Steam pressure control valve 56: Weir 58: Up-down movement device 60: Discharge chamber 64: Discharge conveyor 71: Sound detector 72: Sound detector 73: Sound detector 81: Elastic member 82: Vibration detector 85: Elastic member 86: Vibration detector

Claims (15)

1. A control system for a dryer for drying sludge by applying heat to the sludge , comprising:
A model is provided that is constructed by machine learning using training data including operating parameters of the drying device and status data of the drying device, and including actual measurement data of the moisture content of the corresponding dried sludge ;
The status data of the drying device includes status data of sludge introduced into the drying device,
The control system for a drying apparatus is characterized in that it is configured to input the operating parameters and status data of the drying apparatus into the model, calculate a predicted value of the moisture content of the dried sludge discharged from the drying apparatus according to the model, and further determine optimal values of the operating parameters that can keep the moisture content within a target range. 2. The control system for a drying device according to claim 1, wherein the drying device is configured to dry the sludge by an agitating rotor heated by steam. The control system for a drying device as described in claim 2, characterized in that the operating parameters are at least one of the flow rate of sludge fed into the drying device, the rotation speed of the agitator rotor, the torque current value of the electric motor that rotates the agitator rotor, the height of a weir that controls the amount and retention time of sludge in the drying device, the pressure of steam injected into the agitator rotor, the temperature of the drying gas supplied to the drying device, and the flow rate of the drying gas supplied to the drying device. 3. The control system for a drying device as described in claim 2, characterized in that the status data of the drying device is at least one of the type of sludge fed into the drying device, the temperature of the sludge fed into the drying device, the moisture content of the sludge fed into the drying device, the surface temperature of the drying device, the pressure inside the drying device, the flow rate of steam injected into the agitating rotor, the temperature of the drying gas discharged from the drying device after being supplied to the drying device to dry sludge, and the amount of drain condensed from the steam discharged from a steam supply line connected to the agitating rotor. The control system for a drying device according to claim 1, characterized in that, when adjusting the operation of the drying device, the priority of the operating parameters to be adjusted is determined in advance. The control system for a drying device according to claim 5 , wherein the control system is configured to determine the priority order according to the importance of feature amounts calculated during the machine learning. 7. The control system for a drying device according to claim 6, wherein the control system is configured to adjust the operating parameter in a stepwise manner when a difference between a current value of the operating parameter and the optimal value is greater than a predetermined adjustment range. A control system for a drying device as described in any one of claims 1 to 7, characterized in that the status data of the drying device includes at least one of operating parameters and status data of a dehydration system installed upstream of the drying device, and an estimated moisture content of the dehydrated sludge calculated according to a learned model incorporated into the dehydration system. The model is
A first model constructed by machine learning using training data including the operating parameters and not including state data of the drying device ;
The drying device control system according to any one of claims 1 to 8 , further comprising a second model constructed by machine learning using training data including both the operating parameters and status data of the drying device. the first model is used to determine optimal values of the operating parameters;
10. The control system of claim 9 , wherein the second model is used to calculate the predicted moisture content. The control system for a drying device according to claim 9 or 10, characterized in that, when a difference between the predicted moisture content calculated according to the first model and the moisture content calculated according to the second model exceeds a predetermined tolerance, the control system is configured to perform machine learning for the first model again and update the first model. 12. The control system for a drying device according to claim 1, wherein the numerical values of the operating parameters included in the training data are distributed within a wider range than during normal operation of the drying device. The control system for a drying device according to any one of claims 1 to 12 , wherein the control system is configured to perform the machine learning on a regular or irregular basis to update the model. The control system for a drying device according to claim 13, characterized in that the control system is configured to use a web application to display data acquired from the drying device, to operate the drying device, and to update the model. The training data includes at least one of image data of sludge, sound data of sludge, and vibration data generated due to sludge, in addition to the operating parameters and the state data of the drying device ;
A control system for a drying device as described in any one of claims 1 to 14, characterized in that the control system is configured to input the operating parameters and status data of the drying device , and at least one of sludge image data, sludge sound data, and sludge vibration data into the model, and calculate a predicted value of the moisture content of the dried sludge discharged from the drying device according to the model.

Images