Intelligent control method and system for aerobic composting of sludge

Abstract

The present invention relates to an intelligent control method and system for aerobic composting of sludge, characterized in that it includes a data acquisition unit, an equipment unit, and a central control unit; the data acquisition unit includes a pile parameter acquisition system and a fan parameter acquisition system, the equipment unit includes a turning device, a variable frequency aeration blower and an aeration pipeline system, and the pile parameter acquisition system includes a temperature sensor, an oxygen concentration sensor, and a moisture content sensor. The present invention can accurately control the air volume, predict the most suitable aeration flow under different conditions, and reduce power consumption; and the synergistic effect of turning and aeration is considered, aeration and composting operations are combined, and according to the judgment of the pile condition, the effect of cooling or oxygenation can be quickly achieved, thereby ensuring the quality of sludge aerobic composting products and achieving energy saving and consumption reduction.

Description

Technical Field

[0001] The invention relates to the technical field of organic solid waste treatment and disposal, and in particular to an intelligent control method and system for sludge aerobic composting. Background Art

[0002] With the rapid development of sewage treatment facilities, the treatment and disposal of residual sludge has become a hot topic. Aerobic composting is a sludge treatment method. Its principle is to utilize the metabolism of aerobic microorganisms to degrade organic matter in sludge under high temperature and aerobic conditions and convert it into stable humus. The automatic control process of composting has developed from the initial time control to the current temperature and oxygen feedback control. Time control is to control the operation of the equipment by timing start and time stop. It is an empirical control method. It is impossible to change the composting operation according to the difference in composting conditions. The control means are extensive, the composting effect is unstable, and the energy consumption cannot reach the optimal level. Temperature feedback control can monitor the temperature of the pile in real time through the temperature sensor. When the temperature is too high, the temperature is controlled by controlling the ventilation volume and turning the pile to ensure that the pile is in a suitable temperature range, shorten the composting time, and improve the composting efficiency. The current technology monitors the two process parameters of temperature and oxygen concentration at the same time, but only one of the process equipment or aeration blower is feedback controlled separately, and the synergy and optimized operation between the two are not considered. There are two areas that can be improved in the current technology. First, aeration and turning have their own advantages in terms of effect and speed on oxygen concentration and temperature. Taking advantage of the advantages of these two control methods can speed up composting, reduce energy consumption, and improve product fertilizer efficiency. Second, with the changes in parameters such as the moisture content and porosity of the pile, there is a relatively suitable aeration intensity at different stages of composting. The current technology mostly adjusts the fan air volume according to the oxygen concentration and temperature. Using different aeration intensities at different stages can reduce energy consumption from the perspective of working conditions and mechanical efficiency.

[0003] A composting system and its air supply method and composting method (CN201810459237.4) are centered on intermittent air supply to the compost body according to time-temperature feedback combined control. The air supply frequency is controlled by time, and the air supply volume is controlled by temperature feedback. According to the fermentation stage, the intermittent air supply is divided into four stages. The air supply frequency is different in each stage. At the same time, the compost body temperature T is monitored, and the maximum temperature T1 and the minimum temperature T2 are preset. The start and stop of the air supply device and the air supply volume are controlled according to the real-time feedback of the temperature T. When T>T1, the air supply device operates at high power and the air supply volume is large. When T1>T>T2, the air supply device operates at low power and the air supply volume is small. When T>T2, the air supply device is turned off. This is an automatic control achieved only by aeration, which achieves the two purposes of oxygenation and cooling through aeration.

[0004] A control system for composting of urban domestic sludge (CN201220330290.2) is based on the difference in oxygen concentration between the inlet and outlet, the calculation of the oxygen consumption rate of the pile, and the automatic control of the aeration device according to the oxygen change rate. The temperature difference between the center and the edge of the pile is used to automatically start and stop the turning of the pile. There are two control modes in this scheme, namely, turning and aeration, but the synergy of the two operations is not taken into account. In the aeration operation, the fan is always on when the temperature exceeds Tmax. When the temperature does not exceed Tmax, the amount of oxygen required for the pile is estimated by a mathematical formula for aeration, which belongs to feedforward control. However, the formula calculation is not accurate, and the BVS (degradable organic matter) in different batches of piles will be different. As the composting process progresses, the change of BVS cannot be predicted by the formula, which may cause insufficient or excessive oxygen supply. In the turning operation, the temperature difference between the center and the edge of the pile is used as feedback information for control. If the temperature of the entire pile is too high, the equipment will only cool the pile by aeration. And the synergistic effect of aeration and turning is not taken into account. If the edge temperature is too low and the center temperature is normal, turning will still be carried out, resulting in heat loss.

[0005] At present, the automatic control technology of sludge aerobic composting mostly takes oxygen concentration and temperature as the control objects, and only adopts aeration as a control means of feedback control. Or two independent control systems, such as controlling oxygen concentration by aeration and controlling temperature difference by turning. The synergistic effect of these two control means on oxygenation and cooling is not considered. If two independent control logics are used, it is possible to turn the compost after the temperature is reduced to the normal range by aeration, resulting in too low temperature and poor composting effect.

[0006] The two control methods have their own advantages for oxygenation and cooling. Under the condition of consuming the same energy, aeration has a more obvious oxygenation effect, and turning and throwing has a more obvious cooling effect. When oxygenation is needed, aeration is better. When cooling is needed, turning and throwing is better.

[0007] Under certain adverse working conditions (such as low oxygen content, high temperature), it is difficult to quickly achieve the desired effect only through aeration.

[0008] When the aeration volume is constant, large flow and small flow will also lead to different oxygen concentration increments. The relationship between fan power and flow is not linear. The moisture content of the pile will change in different composting stages. In the early stage of composting, the moisture content is high and the pile is dense, so a large air volume may be required to achieve a better oxygenation effect. When the moisture content of the pile becomes lower, the pores become larger, and a small air volume can achieve a better oxygenation effect. In addition, the fan has higher mechanical efficiency and is more energy-efficient under a small air volume. When △O / △w is the largest, it is the most efficient and energy-saving aeration intensity; when -△O / △T is the largest, it is the aeration intensity with the least heat loss. By establishing a neural network model, the most energy-saving aeration intensity can be predicted under normal working conditions, and the aeration intensity with the least heat loss can be predicted under adverse working conditions.

[0009] Therefore, technicians in this field are committed to developing an intelligent control method and system for sludge aerobic composting. Summary of the invention

[0010] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is: taking oxygen concentration and temperature as control objects, and taking aeration and turning as control means, to perform coordinated control. When it is judged that the oxygen concentration needs to be increased, the aeration operation is performed, and when the temperature needs to be lowered, the turning operation is performed to ensure that the oxygen concentration and temperature in the pile are in the optimal range, with lower energy consumption, faster effect, and better fertilizer efficiency of the product.

[0011] To achieve the above object, the present invention provides an intelligent control method for aerobic composting of sludge, which is characterized by comprising the following steps:

[0012] Step 1: Establish a model based on a neural network machine learning algorithm; use pile parameters (air temperature, pile temperature, moisture content, oxygen concentration), aeration intensity, energy consumption (power × running time) as input, and aeration intensity as output to predict the optimal aeration intensity; use different aeration intensities under different conditions to achieve the purpose of high efficiency and energy saving, or aerate under unfavorable conditions where both temperature and oxygen concentration are below the appropriate range to achieve the purpose of minimum heat loss; conduct experiments, use different aeration intensities, and record the amount of electricity consumed to achieve the target oxygenation volume; repeat the above experiments under different pile parameters, obtain the corresponding data, and construct a neural network model. Take the maximum △O / △w as the constraint condition, and the corresponding aeration intensity is the model output, that is, the most energy-saving aeration intensity. Take the maximum -△O / △T as the constraint condition, and the corresponding aeration intensity is the model output, that is, the aeration intensity with the smallest heat loss. At different composting stages, the moisture content of the pile will change; in the early stage of composting, the moisture content is high and the pile is dense, so a larger aeration intensity may be required to achieve a higher efficiency ratio; when the moisture content of the pile becomes lower, the pores become larger, and a smaller aeration intensity can achieve a higher efficiency ratio; when the temperature and oxygen concentration are both lower than the appropriate range, the heat loss must be minimized while increasing the oxygen concentration to achieve a better heating effect; therefore, the most suitable aeration intensity is used under different conditions to achieve the purpose of high efficiency and energy saving; or oxygen is added under adverse conditions where the temperature and oxygen concentration are both lower than the appropriate range to achieve the purpose of minimum heat loss; when △O / △w is the largest, it is the most efficient and energy-saving aeration intensity; when -△O / △T is the largest, it is the aeration intensity with the smallest heat loss; therefore, it is necessary to establish a neural network model to predict and select the most suitable aeration intensity under different working conditions;

[0013] Step 2: Design feedback control: According to the characteristics of aerobic bacteria in the added bacterial agent, set the following values: the lower limit of oxygen concentration is Omin, the upper limit of oxygen concentration is Omax, the upper limit of oxygen concentration under adverse conditions is Omid, the upper limit of temperature is Tmax, and the lower limit of temperature is Tmin;

[0014] If O<Omin, aeration will start according to the prediction of the most energy-efficient aeration intensity;

[0015] When the target value O≥Omax or T≤Tmin is reached, aeration is stopped;

[0016] If T>Tmax, start flipping;

[0017] When the target value T≤Tmin or O>Omax is reached, the flipping is stopped;

[0018] If O<Omin, T<Tmin, the minimum aeration intensity for heat loss is predicted and the target value is set to Omid for aeration;

[0019] In order to prevent energy waste and machine loss caused by frequent start and stop of fans and turners, Tmin and Omax are set; Tmin and Omax here are not the upper and lower limits of the suitable growth range of microorganisms, but a target value set to prevent frequent start and stop of machines. Tmin is usually located at the lower end of the temperature range suitable for microorganisms, and Omax is usually located at the upper end of the oxygen concentration range suitable for microorganisms. Under normal circumstances, Tmin can be set to 58-60℃, and Omax can be set to 16-18%, which is related to the characteristics of the microbial agent;

[0020] Step 3:

[0021] The data acquisition module collects data at each point of the pile, and transmits the temperature, oxygen concentration, and moisture content to the data storage module and the data analysis module in sequence;

[0022] The data storage module is used to store data, and the data analysis module uses artificial neural network methods to predict the aeration volume required for the pile and transmit it to the PLC;

[0023] Step 4: Based on the neural network algorithm, the initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, energy consumption W in the historical data are used as input, △O / △w is used as a constraint condition, and aeration intensity is used as an output to establish a model, and the most energy-saving aeration intensity is selected; Based on the neural network algorithm, the ambient temperature t, initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, energy consumption W in the historical data are used as input, -△O / △T is used as a constraint condition, and aeration intensity is used as an output to establish a model, and the aeration intensity with the smallest heat loss is selected; and the fan start and stop is controlled through feedback;

[0024] Step 5: PLC monitors the pile parameters in real time and transmits the data to PLC, data storage module and data analysis module in sequence through electrical signals; PLC performs feedback control. If the oxygen concentration is lower than the set value, the aeration equipment is turned on. PLC selects the aeration intensity by reading the prediction results of the data analysis module, and controls the start and stop of the fan by monitoring the oxygen concentration; after the aeration process, it is determined whether the temperature is higher than Tmax. If the temperature is higher than the set value, PLC controls the operation of the tiller; the two control methods have their own advantages in oxygenation and cooling; under the condition of consuming the same energy, the oxygenation effect of aeration is more obvious; the cooling effect of tiller is more obvious; define α=dO / dw, β=-dT / dw; aeration α1, β1, tiller α2, β2; obviously, α1>β1, β2>α2; when oxygenation is needed, aeration is better; when cooling is needed, tiller is better;

[0025] Step 6: When the composting process begins, the oxygen concentration sensor and temperature sensor monitor the compost in real time and can perform different operations according to different temperature and oxygen concentration conditions, thereby achieving control of temperature and oxygen concentration and reducing power consumption;

[0026] During the temperature rise period, when the temperature does not reach Tmax and the oxygen concentration is insufficient, aeration is performed;

[0027] During the high temperature period, if the temperature is too high, it can be cooled down by turning the soil over; if the oxygen concentration is too low, it can be oxygenated by aeration;

[0028] (1) Aeration-turning coordinated intelligent control method, which performs aeration when it is judged that the oxygen concentration needs to be increased, and performs turning when it needs to be lowered; it reduces energy consumption; it adjusts pile parameters more quickly, and improves product fertilizer efficiency;

[0029] (2) A model for predicting aeration intensity based on a neural network; using environmental conditions and energy consumption as input and aeration intensity as output to find the most energy-efficient aeration intensity under different environmental conditions, thereby reducing energy consumption from the perspective of optimal operating conditions.

[0030] Furthermore, the neural network model in step 1 is a BP neural network model.

[0031] Furthermore, the setting principles of setting the oxygen concentration lower limit Omin, oxygen concentration upper limit Omax, oxygen concentration upper limit Omid under poor working conditions, temperature upper limit Tmax, and temperature lower limit Tmin in step 2 are as follows: Tmin and Omax are not the upper and lower limits of the growth range suitable for microorganisms, but a target value set to prevent the machine from being frequently started and stopped. Tmin is usually located at the lower end of the temperature range suitable for microorganisms, and Omax is usually located at the upper end of the oxygen concentration range suitable for microorganisms. Under normal circumstances, Tmin can be set to 58-60°C, and Omax can be set to 16-18%, which is related to the characteristics of the bacterial agent;

[0032] Furthermore, the data acquisition module in step 3 acquires data once per minute.

[0033] Furthermore, the step value in the neural network algorithm in step 4 is 2.

[0034] Furthermore, the stack parameters in step 5 include ambient temperature, stack temperature, oxygen concentration, and water content.

[0035] Furthermore, in step 6, the measurement range of the oxygen concentration sensor is 0-25%, the response time is 5s, and the measurement accuracy is 0.2%; the measurement range of the temperature sensor is -20-85°C, the response time is 5s, and the accuracy is 0.1°C.

[0036] Furthermore, the insufficient oxygen concentration in step 6 refers to an oxygen concentration below 8%.

[0037] The present invention also provides an intelligent control system for aerobic composting of sludge, which is controlled by the intelligent control method for aerobic composting of sludge, and is characterized in that it comprises a data acquisition unit, an equipment unit, and a central control unit; the data acquisition unit comprises a pile parameter acquisition mechanism and a fan parameter acquisition mechanism;

[0038] The equipment unit comprises a flipping device, a multi-speed variable frequency aeration fan and an aeration pipeline;

[0039] The pile parameter collection mechanism includes a temperature sensor, an oxygen concentration sensor, and a water content sensor;

[0040] The temperature sensors are arranged at the center and the upper, middle and lower parts of the edge of the pile body to monitor the temperature of each part of the pile body, and the average value is recorded as the pile body temperature;

[0041] The oxygen concentration sensors are arranged at the center and the upper, middle and lower parts of the edge of the stack body, and are used to monitor the oxygen concentration at various parts of the stack body, and the average value thereof is recorded as the stack body oxygen concentration; the temperature sensor and the oxygen concentration sensor are arranged to transmit the real-time monitoring data to the central control unit through electrical signals;

[0042] The fan parameter acquisition mechanism includes an air flow meter, and the fan parameter acquisition mechanism obtains power parameters and operating time parameters from the fan;

[0043] The central control unit includes a feedforward control module and a PLC (programmable logic controller), and the PLC is used to control the equipment unit;

[0044] The feedforward control module includes a data storage module and a data analysis module; the data storage module is used to store data;

[0045] The data analysis module is configured to use a neural network algorithm to predict aeration intensity.

[0046] The beneficial technical effects of the present invention are as follows:

[0047] (1) A model for predicting aeration intensity was established based on a neural network algorithm, which can accurately control the air volume, predict the most suitable aeration intensity under different conditions, and reduce energy consumption.

[0048] (2) The present invention takes into account the synergistic effect of turning and aeration and the degree of influence of these two operations on temperature and oxygen concentration, and combines aeration with compost turning operations. Based on the judgment of the compost condition, the composting efficiency can be improved and the energy consumption can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1It is a schematic diagram of a control system of a preferred embodiment of the present invention;

[0050] Figure 2 It is a control logic principle diagram of a preferred embodiment of the present invention;

[0051] Figure 3 It is a neural network model for predicting energy-saving aeration intensity of the present invention;

[0052] Figure 4 It is a neural network model for predicting aeration intensity with minimum temperature loss according to the present invention.

[0053] In the figure: 01-data acquisition unit, 02-central control unit, 03-equipment unit, 11-pile data acquisition module, 12-fan data acquisition module, 111-temperature data acquisition module, 112-oxygen concentration data acquisition module, 113-water content data acquisition module, 121-flow meter, 21-PLC control cabinet, 22-data storage module, 23-data analysis module, 31-fan, 32-turning machine. DETAILED DESCRIPTION

[0054] The following describes several preferred embodiments of the present invention with reference to the drawings in the specification, so that the technical content is clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned in the text.

[0055] In the drawings, components with the same structure are indicated by the same numerical reference numerals, and components with similar structures or functions are indicated by similar numerical reference numerals. The size and thickness of each component shown in the drawings are arbitrarily shown, and the present invention does not limit the size and thickness of each component. In order to make the illustration clearer, the thickness of the components is appropriately exaggerated in some places in the drawings.

[0056] Example 1

[0057] The present invention provides an intelligent control system for aerobic composting of sludge, and the control system consists of three units: Figure 1 As shown, it includes a data acquisition unit 01, a central control unit 02, and an equipment unit 03. Each unit is connected to each other.

[0058] Among them, the data acquisition unit 01 plays the role of real-time monitoring in feedback control and the role of data acquisition in the neural network model. It includes a pile data acquisition module 11 and a fan data acquisition module 12; to reduce errors, a number of temperature data acquisition modules 111 and oxygen concentration data acquisition modules 112 are set in the pile, and their average values ​​are used as control parameters. The moisture content data acquisition module 113 can use an FDR moisture sensor; air flow acquisition 121 is achieved through an in-pipe flow meter; fan power acquisition 122 and fan operating time acquisition 123 are obtained from the fan.

[0059] The central control unit 02 includes a PLC control cabinet 21, a data storage module 22, and a data analysis module 23. The PLC control cabinet 21 is responsible for parameter collection and the issuance of control instructions. The data storage module 22 receives the parameters transmitted by the PLC control cabinet 21 and stores the model data predicted by the data analysis module 23 based on the neural network. The data analysis module 23 performs two predictions based on the parameters obtained from the data storage module 22.

[0060] Energy-saving aeration intensity prediction module 231, based on the neural network to establish a prediction model such as Figure 3 , taking the initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, and energy consumption W as inputs, △O / △w as constraints, and aeration intensity as output, the most energy-saving aeration intensity is predicted.

[0061] The heat loss minimum aeration intensity prediction module 232 establishes a prediction model based on a neural network such as Figure 4 , taking the initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, and energy consumption W as inputs, -△O / △T as constraints, and aeration intensity as output. Predict the minimum aeration intensity for heat loss. And transmit the calculation results to the data storage module 22 and the PLC control cabinet 21.

[0062] The equipment unit 03 includes a fan 31 and a turner 32 , both of which are controlled by control instructions issued by the PLC control cabinet 21 .

[0063] Control logic such as Figure 2 As shown, the PLC control cabinet 21 sends a feedback control signal to the equipment unit 03 through the data collected from the data acquisition unit 01 when the parameter exceeds the set value. The fan 31 receives the operation signal and starts to operate. If T>Tmin, O<Omin, the most energy-saving aeration intensity is used for aeration. If T<Tmin, O<Omin, the aeration intensity with the least heat loss is used for aeration. The PLC control cabinet 21 receives the prediction results from the data analysis module 23 and sends instructions to the fan 31 to control the aeration intensity.

[0064] During the operation of the fan, feedback control is used to control the start and stop of the fan, and the data acquisition unit 01 monitors the fan in real time.

[0065] In the energy-saving aeration operation, once the condition of T≤Tmin or O>Omin is triggered, the PLC control cabinet 21 sends a signal to the fan 31 to stop the operation.

[0066] During the aeration operation with minimal heat loss, the condition of O>Omid is triggered, and the PLC control cabinet 21 sends a signal to the fan 31 to stop the operation.

[0067] After the aeration operation is completed, the turning operation is determined based on the temperature T and the set value Tmax. If it is started, the turning machine is turned off until the temperature T is lower than the target value Tmin.

[0068] Can be used throughout the composting process Figure 2 Logic for control.

[0069] The present invention also provides an aerobic composting intelligent control method, the steps are as follows:

[0070] Step 1: Establish a model based on a neural network machine learning algorithm; use pile parameters (air temperature t, pile temperature T, moisture content, oxygen concentration O), aeration intensity, energy consumption w (power × operating time) as input, and aeration intensity as output to predict the optimal aeration intensity; use different aeration intensities under different conditions to achieve the purpose of high efficiency and energy saving, or aerate under adverse conditions where the temperature and oxygen concentration are both below the appropriate range to achieve the purpose of minimizing heat loss; conduct experiments, use different aeration intensities, and record the amount of electricity consumed to achieve the target oxygenation volume; repeat the above experiments under different pile parameters, obtain the corresponding data, and establish a training set to construct a neural network model. The training set is shown in the following table

[0071]

[0072] Taking the maximum △O / △w as the constraint condition, the corresponding aeration intensity is the model output, that is, the most energy-saving aeration intensity. Taking the maximum -△O / △T as the constraint condition, the corresponding aeration intensity is the model output, that is, the aeration intensity with the minimum heat loss.

[0073] Step 2: Design feedback control: According to the characteristics of aerobic bacteria in the added bacterial agent, set the following values: the lower limit of oxygen concentration is Omin, the upper limit of oxygen concentration is Omax, the upper limit of temperature is Tmax, and the lower limit of temperature is Tmin;

[0074] In this embodiment, conventional bacterial agents are used, and the suitable temperature range is 55-65%, and the suitable oxygen concentration range is 10-15%.

[0075] Omin and Tmax can be set according to the limit value, Omin is set to 10%, Tmax is set to 65%; Omax is set at the upper limit of the suitable temperature range, set to 15%, and Tmin is set to the lower value of the suitable temperature range, set to 58°C. Set Omid to 12%, and when the temperature and oxygen concentration are both low, just increase the oxygen concentration to 12%.

[0076] If O<Omin, aeration will start according to the prediction of the most energy-efficient aeration intensity;

[0077] When the target value O≥Omax or T≤Tmin is reached, aeration is stopped;

[0078] If T>Tmax, start flipping;

[0079] When the target value T≤Tmin or O>Omax is reached, the flipping is stopped;

[0080] If O<Omin, T<Tmin, aeration is performed based on the aeration intensity prediction with the minimum heat loss and the target value is set to Omid;

[0081] Step 3:

[0082] In addition to the historical data and the experimental data in step 1 that can be used as training sets, in the subsequent composting process, the data acquisition module collects data at various points in the compost body, and transmits the temperature, oxygen concentration, and moisture content to the data storage module and the data analysis module in turn.

[0083] The data storage module is used to store data, and the data analysis module uses artificial neural network methods to predict the aeration volume required for the pile and transmit it to the PLC;

[0084] Step 4: Based on the neural network algorithm, the ambient temperature t, initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, and energy consumption W in the historical data are used as inputs, △O / △w is used as a constraint condition, and aeration intensity is used as an output to establish a model, and the most energy-saving aeration intensity is selected; Based on the neural network algorithm, the ambient temperature t, initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, and energy consumption W in the historical data are used as inputs, -△O / △T is used as a constraint condition, and aeration intensity is used as an output to establish a model, and the aeration intensity with the smallest heat loss is selected; and the fan start and stop is controlled through feedback;

[0085] Step 5: PLC monitors the pile parameters in real time, with a monitoring frequency of once a minute; transmits data to PLC, data storage module, and data analysis module in sequence through electrical signals; PLC performs feedback control. If the oxygen concentration is lower than the set value, the aeration equipment is turned on. PLC selects the aeration intensity by reading the prediction results of the data analysis module, and controls the start and stop of the fan by monitoring the oxygen concentration; after the aeration process is completed, it determines whether the temperature is higher than Tmax. If the temperature is higher than the set value, the PLC controls the operation of the tiller. If the following conditions occur, the operations performed by PLC are as follows

[0086]

[0087] Step 6: When the composting process begins, the oxygen concentration sensor and temperature sensor monitor the compost in real time and can perform different operations according to different temperature and oxygen concentration conditions, thereby achieving control of temperature and oxygen concentration and reducing power consumption;

[0088] During the temperature rise period, when the temperature does not reach Tmax and the oxygen concentration is insufficient, aeration is performed;

[0089] During the high temperature period, if the temperature is too high, it can be cooled down by turning the soil over; if the oxygen concentration is too low, it can be oxygenated by aeration;

[0090] The preferred specific embodiments of the present invention are described in detail above. It should be understood that ordinary technicians in the field can make many modifications and changes based on the concept of the present invention without creative work. Therefore, all technical solutions that can be obtained by technicians in the technical field based on the concept of the present invention through logical analysis, reasoning or limited experiments on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. An intelligent control method for sludge aerobic composting process, characterized in that: The following steps are involved: Step 1: Build a model based on a neural network machine learning algorithm, The optimal aeration intensity is predicted with pile parameters, aeration intensity, and energy consumption w as input and aeration intensity as output. The pile parameters include air temperature t, pile temperature T, moisture content, and oxygen concentration O. The energy consumption w = power × operating time. Use different aeration intensities under different conditions to achieve the goal of high efficiency and energy saving, or add oxygen under adverse conditions where both temperature and oxygen concentration are below the appropriate range to achieve the goal of minimizing heat loss. Experiments were conducted, and the amount of electricity consumed to achieve the target oxygenation volume was recorded under different aeration intensities. The above experiments were repeated under different pile parameters to obtain the corresponding data and construct a neural network model. The maximum △O / △w was used as the constraint condition, and the corresponding aeration intensity was used as the model output, i.e., the most energy-saving aeration intensity. The maximum -△O / △T was used as the constraint condition, and the corresponding aeration intensity was used as the model output, i.e., the aeration intensity with the minimum heat loss. Step 2: Design feedback control: According to the characteristics of aerobic bacteria in the added bacterial agent, set the following values: the lower limit of oxygen concentration is Omin, the upper limit of oxygen concentration is Omax, the upper limit of temperature is Tmax, and the lower limit of temperature is Tmin. If O<Omin, aeration will start according to the prediction of the most energy-saving aeration intensity. When the target value O≥Omax or T≤Tmin is reached, aeration is stopped. If T>Tmax, start flipping. When the target value T≤Tmin or O>Omax is reached, stop flipping. If O<Omin, T<Tmin, the aeration intensity with the minimum heat loss is predicted, and the target value is set to Omid for aeration, where Omid is the upper limit of oxygen concentration under adverse conditions. In order to prevent energy waste and machine loss caused by frequent start and stop of fans and turners, Tmin and Omax are set. Here, Tmin and Omax are not the upper and lower limits of the suitable growth range of microorganisms, but a target value set to prevent frequent start and stop of machines. Tmin is usually located at the lower end of the temperature range suitable for microorganisms, and Omax is usually located at the upper end of the oxygen concentration range suitable for microorganisms. Under normal circumstances, Tmin can be set to 58-60°C, and Omax can be set to 16-18%, which is related to the characteristics of the microbial agent. Step 3: The data acquisition module collects data at each point of the pile, and transmits the temperature, oxygen concentration, and moisture content to the data storage module and the data analysis module in turn. The data storage module is used to store data, and the data analysis module uses artificial neural network methods to predict the aeration volume required for the pile and transmit it to the PLC; Step 4: Based on the neural network algorithm, the ambient temperature t, initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, energy consumption W in the historical data are used as input, △O / △w is used as the constraint condition, and the aeration intensity is used as the output to establish a model, and the most energy-saving aeration intensity is selected. Based on the neural network algorithm, the ambient temperature t, initial temperature T0, final temperature T1, initial oxygen concentration O0, final oxygen concentration O1, moisture content, aeration intensity, and energy consumption W in the historical data are used as input, -△O / △T is used as the constraint condition, and the aeration intensity is used as the output to establish a model, select the aeration intensity with the minimum heat loss, and control the start and stop of the fan through feedback; Step 5: PLC monitors the pile parameters in real time and transmits the data to PLC, data storage module and data analysis module in sequence through electrical signals. The PLC performs feedback control. If the oxygen concentration is lower than the set value, the aeration equipment is turned on. The PLC selects the aeration intensity by reading the prediction results of the data analysis module, and controls the start and stop of the fan by monitoring the oxygen concentration. After the aeration process is completed, it is determined whether the temperature is higher than Tmax. If the temperature is higher than the set value, the PLC controls the operation of the tiller. Step 6: When the composting process begins, the oxygen concentration sensor and temperature sensor monitor the compost in real time and perform different operations according to different temperature and oxygen concentration conditions, thereby achieving control of temperature and oxygen concentration and reducing power consumption. During the temperature rise period, when the temperature does not reach Tmax and the oxygen concentration is insufficient, aeration is performed to supply oxygen. During the high temperature period, if the temperature is too high, it can be cooled down by turning the soil over; if the oxygen concentration is too low, it can be oxygenated by aeration.

2. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: The neural network model in step 1 is a BP neural network model.

3. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: In the step 2, the minimum oxygen concentration Omin, the maximum oxygen concentration Omax, and the maximum temperature Tmax are set. The setting principle of the minimum temperature Tmin is: in order to prevent energy waste and machine loss caused by frequent start and stop of fans and turners, Tmin and Omax are set. Here, Tmin and Omax are not the upper and lower limits of the suitable growth range of microorganisms, but a target value set to prevent frequent start and stop of machines. Tmin is usually located at the lower end of the temperature range suitable for microorganisms, and Omax is usually located at the upper end of the oxygen concentration range suitable for microorganisms. Under normal circumstances, Tmin can be set to 58-60°C, and Omax can be set to 16-18%, which is related to the characteristics of the bacterial agent.

4. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: The data acquisition module in step 3 acquires data once per minute.

5. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: The step value in the neural network algorithm in step 4 is 2.

6. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: The oxygen concentration sensor in step 6 has a measurement range of 0 to 25%, a response time of 5 seconds, and a measurement accuracy of 0.2%; the temperature sensor has a measurement range of -20 to 85°C, a response time of 5 seconds, and an accuracy of 0.1°C.

7. The intelligent control method for aerobic composting of sludge according to claim 1, characterized in that: In the step 6, insufficient oxygen concentration means that the oxygen concentration is below 8%.

Images