A method, system and device for stabilizing and controlling landfill stock waste

Abstract

The present invention relates to a method, system and device for controlling the stabilization of stock garbage in a landfill, and belongs to the technical field of garbage treatment. The present invention obtains the oxygen concentration state of each monitoring area according to an oxygen concentration state monitoring model, identifies and analyzes the oxygen concentration state of each monitoring area, obtains the analysis result, and finally introduces a genetic algorithm to dynamically control the working parameter data of the oxygen supplement device according to the analysis result. The present invention obtains oxygen concentration data through a wireless sensor monitoring network, and dynamically identifies and monitors the oxygen concentration state by fusing a Markov chain and a deep neural network, and can dynamically control the oxygen supplement device according to the oxygen concentration state, so that the aerobic decomposition process of the landfill is in a stable state, and the effect of aerobic decomposition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of garbage disposal, and in particular to a method, system and device for controlling the stabilization of stock garbage in a landfill. Background Art

[0002] At present, due to the short time of universal implementation of sanitary landfill management technology, economically developed cities did not generally adopt it until the mid-to-late 1990s, and the longest time is less than 20 years. In some economically underdeveloped areas, many cities still use informal landfill technology for landfill. Therefore, there are a large number of informal landfills that are already filled with garbage. These landfills not only occupy a large amount of land resources, cause serious pollution to water bodies and the atmosphere, but also have an adverse impact on the image and development of the city. With the rapid development of urban construction, some informal landfills are located in urban areas, which affects and restricts the development of urban areas and affects the normal life of the people around the landfills. Therefore, it is necessary to close and stabilize them as soon as possible to return a healthy and green natural environment. In situ aerobic degradation management is to transform the landfill into a bioreactor, change the physical and chemical conditions in the landfill, establish an environment suitable for the growth of microorganisms, use the role of microorganisms to accelerate the decomposition of biodegradable organic matter in the garbage, and shorten the degradation time of the landfill. However, in the process of biodegradation, if the oxygen content does not meet the requirements, the degradation effect will be reduced. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method, system and device for controlling the stabilization of stock garbage in a landfill.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for controlling the stabilization of waste in a landfill, comprising the following steps:

[0006] By arranging wireless sensors in the landfill, a wireless sensor monitoring network is constructed, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area;

[0007] By processing and analyzing the oxygen concentration data of each monitoring area, the processed oxygen concentration data is obtained, a Markov chain and a deep neural network are introduced, and an oxygen concentration state monitoring model is constructed based on the processed oxygen concentration data, the Markov chain and the deep neural network;

[0008] Acquire the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identify and analyze the oxygen concentration state of each monitoring area to obtain analysis results;

[0009] A genetic algorithm is introduced to dynamically control the working parameter data of the oxygen supplementation device according to the analysis results.

[0010] Furthermore, in this method, wireless sensors are arranged in the landfill to construct a wireless sensor monitoring network, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area, specifically:

[0011] Acquire area information and geographic location information of the landfill, and initialize the layout location information of the wireless sensor and the layout location information of the communication device based on the area information and geographic location information of the landfill to build a wireless sensor monitoring network;

[0012] Calculate the Euclidean distance value based on the arrangement location information of the wireless sensor and the arrangement location information of the communication device, use the Euclidean distance value as the communication distance between the wireless sensor and the communication device, and estimate the collection delay data of each wireless sensor in the wireless sensor monitoring network based on the communication distance;

[0013] Setting a collection delay threshold data, obtaining the collection delay data of each wireless sensor by estimation, and determining whether the collection delay data of each wireless sensor is less than the collection delay threshold data;

[0014] When the acquisition delay data of each wireless sensor is not all less than the acquisition delay threshold data, rearrange the arrangement position information of the line sensor and the arrangement position information of the communication device until the acquisition delay data of each wireless sensor is all less than the acquisition delay threshold data;

[0015] When the collection delay data of each wireless sensor is less than the collection delay threshold data, the layout position information of the wireless sensor and the layout position information of the communication device are output to form a wireless sensor monitoring network, and data collection is performed through the wireless sensor monitoring network to obtain the oxygen concentration data of each monitoring area.

[0016] Furthermore, in this method, the oxygen concentration data of each monitoring area is processed and analyzed to obtain the processed oxygen concentration data, specifically:

[0017] Obtaining oxygen concentration data of each monitoring area in each timestamp, and obtaining data acquisition delay data of each data according to the oxygen concentration data of each monitoring area in each timestamp;

[0018] Determine whether the data collection delay data of each data is less than the collection delay threshold data, and when the data collection delay data of each data is less than the collection delay threshold data, take the corresponding data as credible data, and output the credible data as processed oxygen concentration data;

[0019] When the data collection delay data of each data is not less than the collection delay threshold data, the corresponding data is regarded as unreliable data and is eliminated.

[0020] Furthermore, in this method, a Markov chain and a deep neural network are introduced, and an oxygen concentration state monitoring model is constructed based on the processed oxygen concentration data, the Markov chain and the deep neural network, specifically including:

[0021] Building an oxygen concentration state monitoring model based on a deep neural network, building oxygen concentration change characteristic data based on a time series based on the processed oxygen concentration data, and taking the oxygen concentration data of each timestamp in the oxygen concentration change characteristic data as a state value;

[0022] Obtaining the state value of each timestamp, constructing a state value matrix, introducing a Markov chain, inputting the state value matrix into the Markov chain for calculation, and obtaining a transition probability value of each state value in the state value matrix transferring to another state value;

[0023] When the transition probability value is greater than a preset transition probability threshold, the corresponding state value is updated to another state value; when the transition probability value is not greater than the preset transition probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated;

[0024] An updated state value matrix is ​​obtained, and the updated state value matrix is ​​input into the oxygen concentration state monitoring model for learning. After the training is completed, the oxygen concentration state monitoring model is output.

[0025] Furthermore, in the present method, the oxygen concentration state of each monitoring area is obtained according to the oxygen concentration state monitoring model, and the oxygen concentration state of each monitoring area is identified and analyzed to obtain the analysis result, which specifically includes:

[0026] Preset an oxygen concentration state threshold, and determine whether the oxygen concentration state of each monitoring area is greater than the oxygen concentration state threshold;

[0027] When the oxygen concentration state of the monitoring area is less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state less than the oxygen concentration state threshold is regarded as an abnormal monitoring area, and an analysis result is generated;

[0028] When the oxygen concentration state of the monitoring area is not less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state not less than the oxygen concentration state threshold is regarded as a normal monitoring area, and an analysis result is generated.

[0029] Furthermore, in this method, a genetic algorithm is introduced, and the working parameter data of the oxygen supplementation device is dynamically controlled according to the analysis results by the genetic algorithm, specifically:

[0030] When the analysis result is an abnormal monitoring area, a genetic algorithm is introduced, and a genetic generation is set based on the genetic algorithm to initialize the working parameter data of the oxygen supplementation device to obtain the garbage quality in the landfill;

[0031] Calculating a treatment compliance rate based on the working parameter data of the oxygen supplementation device and the mass of the garbage in the landfill, setting a treatment compliance rate threshold, and determining whether the treatment compliance rate is greater than the treatment compliance rate threshold;

[0032] When the control standard achievement rate is greater than the control standard achievement rate threshold, the working parameter data of the oxygen supplementation device is output, and the oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device;

[0033] When the governance compliance rate is not greater than the governance compliance rate threshold, genetic iteration is performed based on genetic algebraic pairs, the working parameter data of the oxygen supplementation device is adjusted until the governance compliance rate is no greater than the governance compliance rate threshold, the working parameter data of the oxygen supplementation device is output, and oxygen supplementation control is performed on the oxygen supplementation device based on the working parameter data of the oxygen supplementation device.

[0034] A second aspect of the present invention provides a landfill stock waste stabilization control system, the system comprising a memory and a processor, the memory comprising a landfill stock waste stabilization control method program, and when the landfill stock waste stabilization control method program is executed by the processor, any step of the landfill stock waste stabilization control method is implemented.

[0035] A third aspect of the present invention provides a terminal device, including:

[0036] An acquisition module is responsible for arranging wireless sensors in the landfill to build a wireless sensor monitoring network, collecting data through the wireless sensor monitoring network, and acquiring oxygen concentration data in each monitoring area;

[0037] A model building module is responsible for processing and analyzing the oxygen concentration data of each monitoring area, obtaining the processed oxygen concentration data, introducing the Markov chain and the deep neural network, and building an oxygen concentration state monitoring model based on the processed oxygen concentration data, the Markov chain and the deep neural network;

[0038] An analysis module is responsible for obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifying and analyzing the oxygen concentration state of each monitoring area to obtain analysis results;

[0039] The control module is responsible for introducing a genetic algorithm, and dynamically controlling the working parameter data of the oxygen supplementation device according to the analysis result through the genetic algorithm.

[0040] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a landfill stock waste stabilization control method program. When the landfill stock waste stabilization control method program is executed by a processor, the steps of any one of the landfill stock waste stabilization control methods are implemented.

[0041] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0042] The present invention arranges wireless sensors in a landfill, constructs a wireless sensor monitoring network, collects data through the wireless sensor monitoring network, obtains oxygen concentration data of each monitoring area, processes and analyzes the oxygen concentration data of each monitoring area, obtains the processed oxygen concentration data, introduces Markov chain and deep neural network, constructs an oxygen concentration state monitoring model based on the processed oxygen concentration data, Markov chain and deep neural network, thereby obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifies and analyzes the oxygen concentration state of each monitoring area to obtain the analysis result, finally introduces a genetic algorithm, and dynamically controls the working parameter data of the oxygen supplement device according to the analysis result through the genetic algorithm. The present invention obtains oxygen concentration data through a wireless sensor monitoring network, thereby dynamically identifying and monitoring the oxygen concentration state by fusing Markov chain and deep neural network, and can dynamically control the oxygen supplement device according to the oxygen concentration state, so that the aerobic decomposition process of the landfill is in a stable state, and the effect of aerobic decomposition is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0044] Figure 1 The overall flow chart of the landfill stock waste stabilization control method is shown;

[0045] Figure 2 A partial flow chart of a landfill stock waste stabilization control method is shown;

[0046] Figure 3 The system block diagram of the landfill stock waste stabilization control system is shown;

[0047] Figure 4 A device schematic diagram of a terminal device is shown. DETAILED DESCRIPTION

[0048] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0050] like Figure 1 As shown, the first aspect of the present invention provides a method for controlling the stabilization of waste in a landfill, comprising the following steps:

[0051] S102: wireless sensors are arranged in the landfill to build a wireless sensor monitoring network, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area;

[0052] S104: Processing and analyzing the oxygen concentration data of each monitoring area to obtain processed oxygen concentration data, introducing a Markov chain and a deep neural network, and constructing an oxygen concentration state monitoring model based on the processed oxygen concentration data, the Markov chain and the deep neural network;

[0053] S106: Obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifying and analyzing the oxygen concentration state of each monitoring area to obtain analysis results;

[0054] S108: Introducing a genetic algorithm, and dynamically controlling the working parameter data of the oxygen supplementation device according to the analysis results through the genetic algorithm.

[0055] It should be noted that the present invention obtains oxygen concentration data through a wireless sensor monitoring network, and then dynamically identifies and monitors the oxygen concentration state by fusing Markov chains and deep neural networks. The oxygen supplementation device can be dynamically controlled according to the oxygen concentration state, so that the aerobic decomposition process of the landfill is stabilized, thereby improving the effect of aerobic decomposition.

[0056] Furthermore, in this method, by arranging wireless sensors in the landfill (such as in the ventilation area, the air pipe, the stabilization area, etc.), a wireless sensor monitoring network is constructed, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area, specifically:

[0057] Acquire area information and geographic location information of the landfill, and initialize the layout location information of the wireless sensor and the layout location information of the communication device based on the area information and geographic location information of the landfill, so as to build a wireless sensor monitoring network;

[0058] The Euclidean distance value is calculated based on the layout location information of the wireless sensor and the layout location information of the communication device, and the Euclidean distance value is used as the communication distance between the wireless sensor and the communication device, and the collection delay data of each wireless sensor in the wireless sensor monitoring network is estimated based on the communication distance;

[0059] Setting a collection delay threshold data, obtaining the collection delay data of each wireless sensor through estimation, and determining whether the collection delay data of each wireless sensor is less than the collection delay threshold data;

[0060] When the acquisition delay data of each wireless sensor is not all less than the acquisition delay threshold data, rearrange the layout position information of the line sensor and the layout position information of the communication device until the acquisition delay data of each wireless sensor is all less than the acquisition delay threshold data;

[0061] When the collection delay data of each wireless sensor is less than the collection delay threshold data, the layout location information of the wireless sensor and the layout location information of the communication equipment are output to form a wireless sensor monitoring network. Data is collected through the wireless sensor monitoring network to obtain the oxygen concentration data of each monitoring area.

[0062] It should be noted that since data transmission is related to distance, the Euclidean distance value between the layout location information of the wireless sensor and the layout location information of the communication device can represent the communication distance between the wireless sensor and the communication device. When the distance becomes larger, the communication delay between the wireless sensor and the communication device becomes larger, which causes the actual collection delay data of the wireless sensor to change.

[0063] Furthermore, in this method, the oxygen concentration data of each monitoring area is processed and analyzed to obtain the processed oxygen concentration data, specifically:

[0064] Obtain oxygen concentration data of each monitoring area at each timestamp, and obtain data collection delay data of each data according to the oxygen concentration data of each monitoring area at each timestamp;

[0065] Determine whether the data collection delay data of each data is less than the collection delay threshold data. When the data collection delay data of each data is less than the collection delay threshold data, the corresponding data is regarded as credible data, and the credible data is output as processed oxygen concentration data;

[0066] When the data collection delay data of each data is not less than the collection delay threshold data, the corresponding data is regarded as unreliable data and is eliminated.

[0067] It should be noted that when the data collection delay data of each data is less than the collection delay threshold data, it means that the data is not the real-time data required, and the data may have a huge delay. This method can be used to identify abnormal data and improve the rationality of oxygen control.

[0068] Furthermore, in this method, a Markov chain and a deep neural network are introduced, and an oxygen concentration state monitoring model is constructed based on the processed oxygen concentration data, the Markov chain and the deep neural network, specifically including:

[0069] An oxygen concentration state monitoring model is constructed based on a deep neural network, oxygen concentration change characteristic data based on a time series is constructed based on the processed oxygen concentration data, and the oxygen concentration data of each timestamp in the oxygen concentration change characteristic data is used as a state value;

[0070] Obtain the state value of each timestamp, construct a state value matrix, introduce a Markov chain, input the state value matrix into the Markov chain for calculation, and obtain the transition probability value of each state value in the state value matrix transferring to another state value;

[0071] When the transition probability value is greater than the preset transition probability threshold, the corresponding state value is updated to another state value. When the transition probability value is not greater than the preset transition probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated.

[0072] The updated state value matrix is ​​obtained, and the updated state value matrix is ​​input into the oxygen concentration state monitoring model for learning. After the training is completed, the oxygen concentration state monitoring model is output.

[0073] It should be noted that, in fact, in a data collection process, the wireless sensor collects a time series of information. However, in this process, the data of each timestamp will change, and the Markov chain describes the model of state change. Since the state will transfer, such as one concentration data is converted to another concentration data, when the transfer probability value is greater than the preset transfer probability threshold, the corresponding state value is updated to another state value. When the transfer probability value is not greater than the preset transfer probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated. This method can update the state value in time.

[0074] Furthermore, in this method, the oxygen concentration state of each monitoring area is obtained according to the oxygen concentration state monitoring model, and the oxygen concentration state of each monitoring area is identified and analyzed to obtain the analysis results, which specifically include:

[0075] Preset the oxygen concentration state threshold, and determine whether the oxygen concentration state of each monitoring area is greater than the oxygen concentration state threshold;

[0076] When the oxygen concentration state of the monitoring area is less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state less than the oxygen concentration state threshold is regarded as an abnormal monitoring area, and an analysis result is generated;

[0077] When the oxygen concentration state of the monitoring area is not less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state not less than the oxygen concentration state threshold is regarded as a normal monitoring area, and an analysis result is generated.

[0078] like Figure 2 As shown, further, in this method, a genetic algorithm is introduced, and the working parameter data of the oxygen supplementation device is dynamically controlled according to the analysis results by the genetic algorithm, specifically:

[0079] S202: When the analysis result is an abnormal monitoring area, a genetic algorithm is introduced, and a genetic algebra is set based on the genetic algorithm to initialize the working parameter data of the oxygen supplementation device to obtain the garbage quality in the landfill;

[0080] S204: Calculate the treatment compliance rate based on the working parameter data of the oxygen supplementation device and the mass of the garbage in the landfill, set a treatment compliance rate threshold, and determine whether the treatment compliance rate is greater than the treatment compliance rate threshold;

[0081] S206: When the governance compliance rate is greater than the governance compliance rate threshold, the working parameter data of the oxygen supplementation device is output, and the oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device;

[0082] S208: When the governance compliance rate is not greater than the governance compliance rate threshold, genetic iteration is performed based on the genetic algebraic pair, the working parameter data of the oxygen supplementation device is adjusted until the governance compliance rate is not greater than the governance compliance rate threshold, the working parameter data of the oxygen supplementation device is output, and the oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device;

[0083] It should be noted that the calculation of the governance compliance rate satisfies the following relationship:

[0084] ;

[0085] in: To stabilize the gas demand of the subunit, is the mass of garbage in the pile, kg; BDM content before restoration; is the BDM content after repair; This is the governance compliance rate, which is taken as 85% this time; is the BDM aerobic load; is the molecular weight of oxygen; is the oxygen utilization rate, which is taken as 100% this time; C is the stabilization safety factor, which is taken as 1 this time.

[0086] It should be noted that BDM is a biodegradable substance, and by integrating genetic algorithms, the optimal oxygen supplementation device can be obtained. Among them, the working parameter data of the oxygen supplementation device include the gas demand of the stabilization subunit, the oxygen supplementation per unit time, etc. The BDM content after repair and the BDM content before repair can be sampled, and the BDM aerobic load can be obtained through the big data network.

[0087] In addition, the method may further comprise the following steps:

[0088] Acquire historical service data of the oxygen supplementation device through big data, build a fault prediction model based on a deep neural network, and input the acquired historical service data of the oxygen supplementation device into the fault prediction model for training;

[0089] Obtaining a trained fault prediction model through training, predicting the fault time information of each oxygen supplementation device through the trained fault prediction model, and obtaining the work task information of each oxygen supplementation device;

[0090] Based on the work task information of each oxygen supplementing device, the working time information of each oxygen supplementing device is obtained, and it is determined whether the fault time information of the oxygen supplementing device is within the working time information of the oxygen supplementing device;

[0091] When the fault time information of the oxygen supplementing device is not within the working time information of the oxygen supplementing device, the oxygen supplementing device whose fault time information is not within the working time information is used for oxygen supplementing.

[0092] It should be noted that, since oxygen replenishment tasks need to be distributed in the landfill, the rationality of oxygen replenishment in the oxygen replenishment process can be improved through this method.

[0093] In addition, the method may further comprise the following steps:

[0094] Obtain data information on aerobic colonies in each landfill, and obtain the survival rate data of each aerobic colony under meteorological environmental characteristics through big data, build a knowledge graph, and use meteorological environmental characteristics as the first node and survival rate data as the second node;

[0095] A topological structure graph is constructed based on the first node and the second node, the topological structure graph is input into an adjacency matrix for storage, and meteorological characteristics of the geographical location of the landfill are obtained, the meteorological characteristics of the geographical location of the landfill are input into the knowledge graph, and the survival rate data of each aerobic bacterial colony under the current meteorological environment characteristics are obtained;

[0096] Based on the survival rate data of each aerobic colony under the current meteorological environment characteristics and the data information of aerobic colonies in each landfill, the survival rate data of aerobic colonies in the landfill under the current meteorological characteristics are obtained, and the concentration data of aerobic colonies in each landfill are estimated based on the survival rate data;

[0097] The oxygen supply amount of the oxygen supply device per unit time is estimated based on the concentration data of aerobic colonies in each landfill, and the maximum oxygen supply amount of each oxygen supply device per unit time is obtained. The number of oxygen supply devices required is calculated based on the maximum oxygen supply amount of the oxygen supply device per unit time and the oxygen supply amount of the oxygen supply device per unit time, and advance planning is carried out according to the number of oxygen supply devices and the oxygen supply amount of the oxygen supply devices per unit time.

[0098] It should be noted that the survival rate of aerobic colonies is inconsistent under different meteorological characteristics (including temperature, humidity, sunny days, rainy days, snowy days, etc.), and excessive oxygen supplementation will lead to increased treatment costs. This method can estimate the number of required oxygen supplementation devices, the amount of oxygen supplemented by the oxygen supplementation device per unit time, etc., and make advance plans according to the number of oxygen supplementation devices, so as to cope with the impact of meteorological characteristics and improve the aerobic decomposition effect.

[0099] like Figure 3 As shown, the second aspect of the present invention provides a landfill stock waste stabilization control system 4, the system 4 includes a memory 41 and a processor 42, the memory 41 includes a landfill stock waste stabilization control method program, when the landfill stock waste stabilization control method program is executed by the processor 42, any step of the landfill stock waste stabilization control method is implemented.

[0100] A third aspect of the present invention provides a terminal device, including:

[0101] The acquisition module 10 is responsible for arranging wireless sensors in the landfill to build a wireless sensor monitoring network, collecting data through the wireless sensor monitoring network, and acquiring oxygen concentration data in each monitoring area;

[0102] The model building module 20 is responsible for processing and analyzing the oxygen concentration data of each monitoring area, obtaining the processed oxygen concentration data, introducing the Markov chain and the deep neural network, and building the oxygen concentration state monitoring model based on the processed oxygen concentration data, the Markov chain and the deep neural network;

[0103] The analysis module 30 is responsible for obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifying and analyzing the oxygen concentration state of each monitoring area to obtain the analysis result;

[0104] The control module 40 is responsible for introducing a genetic algorithm and dynamically controlling the working parameter data of the oxygen supplementation device according to the analysis results through the genetic algorithm.

[0105] Furthermore, in this terminal device, wireless sensors are arranged in the landfill to build a wireless sensor monitoring network, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area, specifically:

[0106] Acquire area information and geographic location information of the landfill, and initialize the layout location information of the wireless sensor and the layout location information of the communication device based on the area information and geographic location information of the landfill, so as to build a wireless sensor monitoring network;

[0107] The Euclidean distance value is calculated based on the layout location information of the wireless sensor and the layout location information of the communication device, and the Euclidean distance value is used as the communication distance between the wireless sensor and the communication device, and the collection delay data of each wireless sensor in the wireless sensor monitoring network is estimated based on the communication distance;

[0108] Setting a collection delay threshold data, obtaining the collection delay data of each wireless sensor through estimation, and determining whether the collection delay data of each wireless sensor is less than the collection delay threshold data;

[0109] When the acquisition delay data of each wireless sensor is not all less than the acquisition delay threshold data, rearrange the layout position information of the line sensor and the layout position information of the communication device until the acquisition delay data of each wireless sensor is all less than the acquisition delay threshold data;

[0110] When the collection delay data of each wireless sensor is less than the collection delay threshold data, the layout location information of the wireless sensor and the layout location information of the communication equipment are output to form a wireless sensor monitoring network. Data is collected through the wireless sensor monitoring network to obtain the oxygen concentration data of each monitoring area.

[0111] Furthermore, in this terminal device, the oxygen concentration data of each monitoring area is processed and analyzed to obtain the processed oxygen concentration data, specifically:

[0112] Obtain oxygen concentration data of each monitoring area at each timestamp, and obtain data collection delay data of each data according to the oxygen concentration data of each monitoring area at each timestamp;

[0113] Determine whether the data collection delay data of each data is less than the collection delay threshold data. When the data collection delay data of each data is less than the collection delay threshold data, the corresponding data is regarded as credible data, and the credible data is output as processed oxygen concentration data;

[0114] When the data collection delay data of each data is not less than the collection delay threshold data, the corresponding data is regarded as unreliable data and is eliminated.

[0115] Furthermore, in this terminal device, a Markov chain and a deep neural network are introduced, and an oxygen concentration state monitoring model is constructed based on the processed oxygen concentration data, the Markov chain and the deep neural network, specifically including:

[0116] An oxygen concentration state monitoring model is constructed based on a deep neural network, oxygen concentration change characteristic data based on a time series is constructed based on the processed oxygen concentration data, and the oxygen concentration data of each timestamp in the oxygen concentration change characteristic data is used as a state value;

[0117] Obtain the state value of each timestamp, construct a state value matrix, introduce a Markov chain, input the state value matrix into the Markov chain for calculation, and obtain the transition probability value of each state value in the state value matrix transferring to another state value;

[0118] When the transition probability value is greater than the preset transition probability threshold, the corresponding state value is updated to another state value. When the transition probability value is not greater than the preset transition probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated.

[0119] The updated state value matrix is ​​obtained, and the updated state value matrix is ​​input into the oxygen concentration state monitoring model for learning. After the training is completed, the oxygen concentration state monitoring model is output.

[0120] Furthermore, in the terminal device, the oxygen concentration state of each monitoring area is obtained according to the oxygen concentration state monitoring model, and the oxygen concentration state of each monitoring area is identified and analyzed to obtain the analysis results, which specifically include:

[0121] Preset the oxygen concentration state threshold, and determine whether the oxygen concentration state of each monitoring area is greater than the oxygen concentration state threshold;

[0122] When the oxygen concentration state of the monitoring area is less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state less than the oxygen concentration state threshold is regarded as an abnormal monitoring area, and an analysis result is generated;

[0123] When the oxygen concentration state of the monitoring area is not less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state not less than the oxygen concentration state threshold is regarded as a normal monitoring area, and an analysis result is generated.

[0124] Furthermore, in this terminal device, a genetic algorithm is introduced to dynamically control the working parameter data of the oxygen supplementation device according to the analysis results, specifically:

[0125] When the analysis result is an abnormal monitoring area, a genetic algorithm is introduced, and the genetic generation is set based on the genetic algorithm to initialize the working parameter data of the oxygen supplementation device and obtain the garbage quality in the landfill;

[0126] The treatment compliance rate is calculated based on the working parameter data of the oxygen supplementation device and the mass of the garbage in the landfill, a treatment compliance rate threshold is set, and it is determined whether the treatment compliance rate is greater than the treatment compliance rate threshold;

[0127] When the control standard achievement rate is greater than the control standard achievement rate threshold, the working parameter data of the oxygen supplement device is output, and the oxygen supplement device is controlled based on the working parameter data of the oxygen supplement device;

[0128] When the governance compliance rate is not greater than the governance compliance rate threshold, genetic iteration is performed based on genetic algebraic pairs to adjust the working parameter data of the oxygen supplementation device until the governance compliance rate is no greater than the governance compliance rate threshold, and the working parameter data of the oxygen supplementation device is output. The oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device.

[0129] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a landfill stock waste stabilization control method program. When the landfill stock waste stabilization control method program is executed by a processor, any step of the landfill stock waste stabilization control method is implemented.

[0130] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0131] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0132] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0133] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0134] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0135] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling the stabilization of waste in a landfill, characterized in that: The following steps are involved: By arranging wireless sensors in the landfill, a wireless sensor monitoring network is constructed, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area; By processing and analyzing the oxygen concentration data of each monitoring area, the processed oxygen concentration data is obtained, a Markov chain and a deep neural network are introduced, and an oxygen concentration state monitoring model is constructed based on the processed oxygen concentration data, the Markov chain and the deep neural network; Acquire the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identify and analyze the oxygen concentration state of each monitoring area to obtain analysis results; Introducing a genetic algorithm, and dynamically controlling the working parameter data of the oxygen supplementation device according to the analysis results through the genetic algorithm; Markov chain and deep neural network are introduced to build an oxygen concentration state monitoring model based on the processed oxygen concentration data, Markov chain and deep neural network, including: Building an oxygen concentration state monitoring model based on a deep neural network, building oxygen concentration change characteristic data based on a time series based on the processed oxygen concentration data, and taking the oxygen concentration data of each timestamp in the oxygen concentration change characteristic data as a state value; Obtaining the state value of each timestamp, constructing a state value matrix, introducing a Markov chain, inputting the state value matrix into the Markov chain for calculation, and obtaining a transition probability value of each state value in the state value matrix transferring to another state value; When the transition probability value is greater than a preset transition probability threshold, the corresponding state value is updated to another state value; when the transition probability value is not greater than the preset transition probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated; Obtaining an updated state value matrix, inputting the updated state value matrix into the oxygen concentration state monitoring model for learning, and outputting the oxygen concentration state monitoring model after training is completed; A genetic algorithm is introduced to dynamically control the working parameter data of the oxygen supplementation device according to the analysis results, specifically: When the analysis result is an abnormal monitoring area, a genetic algorithm is introduced, and a genetic generation is set based on the genetic algorithm to initialize the working parameter data of the oxygen supplementation device to obtain the garbage quality in the landfill; Calculating a treatment compliance rate based on the working parameter data of the oxygen supplementation device and the mass of the garbage in the landfill, setting a treatment compliance rate threshold, and determining whether the treatment compliance rate is greater than the treatment compliance rate threshold; When the control standard achievement rate is greater than the control standard achievement rate threshold, the working parameter data of the oxygen supplementation device is output, and the oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device; When the governance compliance rate is not greater than the governance compliance rate threshold, genetic iteration is performed based on genetic algebraic pairs, the working parameter data of the oxygen supplementation device is adjusted until the governance compliance rate is no greater than the governance compliance rate threshold, the working parameter data of the oxygen supplementation device is output, and oxygen supplementation control is performed on the oxygen supplementation device based on the working parameter data of the oxygen supplementation device.

2. A landfill waste stabilization control method according to claim 1, characterized in that: By arranging wireless sensors in the landfill, a wireless sensor monitoring network is constructed, and data is collected through the wireless sensor monitoring network to obtain oxygen concentration data in each monitoring area, specifically: Acquire area information and geographic location information of the landfill, and initialize the layout location information of the wireless sensor and the layout location information of the communication device based on the area information and geographic location information of the landfill to build a wireless sensor monitoring network; Calculate the Euclidean distance value based on the arrangement location information of the wireless sensor and the arrangement location information of the communication device, use the Euclidean distance value as the communication distance between the wireless sensor and the communication device, and estimate the collection delay data of each wireless sensor in the wireless sensor monitoring network based on the communication distance; Setting a collection delay threshold data, obtaining the collection delay data of each wireless sensor by estimation, and determining whether the collection delay data of each wireless sensor is less than the collection delay threshold data; When the acquisition delay data of each wireless sensor is not all less than the acquisition delay threshold data, rearrange the arrangement position information of the line sensor and the arrangement position information of the communication device until the acquisition delay data of each wireless sensor is all less than the acquisition delay threshold data; When the collection delay data of each wireless sensor is less than the collection delay threshold data, the layout position information of the wireless sensor and the layout position information of the communication device are output to form a wireless sensor monitoring network, and data collection is performed through the wireless sensor monitoring network to obtain the oxygen concentration data of each monitoring area.

3. A method for controlling the stabilization of landfill stock waste according to claim 1, characterized in that: By processing and analyzing the oxygen concentration data of each monitoring area, the processed oxygen concentration data is obtained, specifically: Obtaining oxygen concentration data of each monitoring area in each timestamp, and obtaining data acquisition delay data of each data according to the oxygen concentration data of each monitoring area in each timestamp; Determine whether the data collection delay data of each data is less than the collection delay threshold data, and when the data collection delay data of each data is less than the collection delay threshold data, take the corresponding data as credible data, and output the credible data as processed oxygen concentration data; When the data collection delay data of each data is not less than the collection delay threshold data, the corresponding data is regarded as unreliable data and is eliminated.

4. A method for controlling the stabilization of landfill waste according to claim 1, characterized in that: Obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifying and analyzing the oxygen concentration state of each monitoring area to obtain analysis results, specifically including: Preset an oxygen concentration state threshold, and determine whether the oxygen concentration state of each monitoring area is greater than the oxygen concentration state threshold; When the oxygen concentration state of the monitoring area is less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state less than the oxygen concentration state threshold is regarded as an abnormal monitoring area, and an analysis result is generated; When the oxygen concentration state of the monitoring area is not less than the oxygen concentration state threshold, the monitoring area corresponding to the oxygen concentration state not less than the oxygen concentration state threshold is regarded as a normal monitoring area, and an analysis result is generated.

5. A landfill waste stabilization control system, characterized in that: The system includes a memory and a processor, wherein the memory includes a landfill stock waste stabilization control method program, and when the landfill stock waste stabilization control method program is executed by the processor, the steps of the landfill stock waste stabilization control method as described in any one of claims 1-4 are implemented.

6. A terminal device, characterized in that: include: An acquisition module is responsible for arranging wireless sensors in the landfill to build a wireless sensor monitoring network, collecting data through the wireless sensor monitoring network, and acquiring oxygen concentration data in each monitoring area; A model building module is responsible for processing and analyzing the oxygen concentration data of each monitoring area, obtaining the processed oxygen concentration data, introducing the Markov chain and the deep neural network, and building an oxygen concentration state monitoring model based on the processed oxygen concentration data, the Markov chain and the deep neural network; An analysis module is responsible for obtaining the oxygen concentration state of each monitoring area according to the oxygen concentration state monitoring model, and identifying and analyzing the oxygen concentration state of each monitoring area to obtain analysis results; A control module is responsible for introducing a genetic algorithm and dynamically controlling the working parameter data of the oxygen supplementation device according to the analysis result through the genetic algorithm; Markov chain and deep neural network are introduced to build an oxygen concentration state monitoring model based on the processed oxygen concentration data, Markov chain and deep neural network, including: Building an oxygen concentration state monitoring model based on a deep neural network, building oxygen concentration change characteristic data based on a time series based on the processed oxygen concentration data, and taking the oxygen concentration data of each timestamp in the oxygen concentration change characteristic data as a state value; Obtaining the state value of each timestamp, constructing a state value matrix, introducing a Markov chain, inputting the state value matrix into the Markov chain for calculation, and obtaining a transition probability value of each state value in the state value matrix transferring to another state value; When the transition probability value is greater than a preset transition probability threshold, the corresponding state value is updated to another state value; when the transition probability value is not greater than the preset transition probability threshold, the corresponding state value is maintained, the state value is counted, and the state value matrix is ​​updated; Obtaining an updated state value matrix, inputting the updated state value matrix into the oxygen concentration state monitoring model for learning, and outputting the oxygen concentration state monitoring model after training is completed; A genetic algorithm is introduced to dynamically control the working parameter data of the oxygen supplementation device according to the analysis results, specifically: When the analysis result is an abnormal monitoring area, a genetic algorithm is introduced, and a genetic generation is set based on the genetic algorithm to initialize the working parameter data of the oxygen supplementation device to obtain the garbage quality in the landfill; Calculating a treatment compliance rate based on the working parameter data of the oxygen supplementation device and the mass of the garbage in the landfill, setting a treatment compliance rate threshold, and determining whether the treatment compliance rate is greater than the treatment compliance rate threshold; When the control standard achievement rate is greater than the control standard achievement rate threshold, the working parameter data of the oxygen supplementation device is output, and the oxygen supplementation device is controlled based on the working parameter data of the oxygen supplementation device; When the governance compliance rate is not greater than the governance compliance rate threshold, genetic iteration is performed based on genetic algebraic pairs, the working parameter data of the oxygen supplementation device is adjusted until the governance compliance rate is no greater than the governance compliance rate threshold, the working parameter data of the oxygen supplementation device is output, and oxygen supplementation control is performed on the oxygen supplementation device based on the working parameter data of the oxygen supplementation device.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a landfill stock waste stabilization control method program, and when the landfill stock waste stabilization control method program is executed by a processor, the steps of the landfill stock waste stabilization control method as described in any one of claims 1-4 are implemented.

Images