An Internet of Things monitoring method and system for mercury-containing waste treatment

Abstract

The present invention discloses an Internet of Things monitoring method and system for the treatment of mercury-containing wastes, the method comprising: mercury-containing waste data collection, mercury-containing waste data transmission, real-time monitoring and early warning, waste treatment report generation and data sharing. The present invention belongs to the field of waste treatment technology, and specifically refers to an Internet of Things monitoring method and system for the treatment of mercury-containing wastes. The scheme adopts a structural similarity index to calculate the mean absolute error of mercury-containing waste data collection in each local control area, and improves the specific arrangement of sensors according to the information reflected by the objective function; determines the correct number of blocks in the blockchain, calculates the entropy and reward function of the blockchain, calculates the data transmission rate, and optimizes the performance of data transmission of mercury-containing wastes; trains a basic model, defines the color of leaves according to the ratio of abnormal points and normal points in the leaves, and gives a piecewise linear supervised depth function to assist in judging the degree of abnormality of mercury-containing waste data.

Description

Technical Field

[0001] The present invention belongs to the technical field of waste treatment, and in particular relates to an Internet of Things monitoring method and system for mercury-containing waste treatment. Background Art

[0002] The IoT monitoring method for mercury-containing waste treatment is a method that uses IoT technology to collect and process various types of data on site in real time, detect abnormal situations in a timely manner and issue early warnings, so as to quickly take countermeasures to avoid the spread of mercury pollution. It aims to achieve more real-time, accurate and comprehensive monitoring and management of the mercury-containing waste treatment process, which is conducive to effective supervision and management by relevant departments. However, the existing IoT monitoring method for mercury-containing waste treatment has technical problems such as inaccurate data collection of mercury-containing waste, difficulty in quantitative processing, large errors in sensor deployment positions, and more difficult data collection; a large amount of mercury-containing waste data is not transmitted quickly, which makes it difficult to achieve more accurate and effective data transmission planning, affects the real-time grasp of the treatment status of mercury-containing waste, and thus makes environmental pollution control difficult; there are abnormal points in the mercury-containing waste data, resulting in inaccurate assessment of the actual situation of mercury-containing waste, interfering with the understanding of the overall progress of treatment work, affecting the rational allocation and management of resources, and increasing environmental risks. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an Internet of Things monitoring method and system for mercury-containing waste treatment. In view of the technical problems that the data collection of mercury-containing waste is inaccurate, it is difficult to quantify it, and the error of sensor deployment position is large, which makes data collection more difficult, a structural similarity index is used to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, and the average absolute error of mercury-containing waste data collection in each local control area is calculated. The specific arrangement of sensors is improved according to the information reflected by the objective function; in view of the fact that a large amount of mercury-containing waste data is not transmitted quickly, which makes it difficult to achieve more accurate and effective data transmission planning, affecting the real-time control of the mercury-containing waste treatment status. In order to solve the technical problem of difficulty in controlling environmental pollution, a method is used to determine the correct number of blocks in the blockchain, calculate the entropy and reward function of the blockchain, exchange blockchain data and calculate the data transmission rate, so as to optimize the data transmission performance of mercury-containing waste; in order to solve the technical problem that there are abnormal points in the mercury-containing waste data, which leads to inaccurate assessment of the actual situation of mercury-containing waste, interferes with the understanding of the progress of the overall treatment work, affects the rational allocation and management of resources, and increases environmental risks, a training basic model is used to judge the abnormal score, calculate the abnormal score value, define the leaf color according to the ratio of abnormal points to normal points in the leaf, give a piecewise linear supervised depth function, calculate the point with the highest abnormal score, and assist in judging the degree of abnormality of the mercury-containing waste data.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides an Internet of Things monitoring method for mercury-containing waste treatment, the method comprising the following steps:

[0005] Step S1: mercury-containing waste data collection, specifically using the structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculating the average absolute error of mercury-containing waste data collection in each local control area, and improving the specific layout of sensors based on the information reflected by the objective function;

[0006] Step S2: Transmission of mercury-containing waste data, specifically determining the correct number of blocks in the blockchain, calculating the entropy and reward function of the blockchain, performing blockchain data exchange and calculating the data transmission rate, and optimizing the performance of mercury-containing waste data transmission;

[0007] Step S21: determining the correct number of blocks in the blockchain, taking into account the security, efficiency and scalability of the blockchain, and obtaining the number of blocks in the blockchain through the consensus mechanism of network nodes, the block generation speed and the data transmission requirements of mercury-containing waste;

[0008] Step S3: Real-time monitoring and early warning, specifically training the basic model, performing anomaly score judgment, calculating the anomaly score value, defining the leaf color according to the ratio of abnormal points to normal points in the leaf, giving a piecewise linear supervised depth function, calculating the point with the highest anomaly score, and assisting in judging the degree of abnormality of the mercury-containing waste data;

[0009] Step S31: training the basic model. During the training process, a series of isolation trees are constructed by randomly sampling data points, and random partitioning is continuously performed to make abnormal data points easier to be isolated by random partitioning;

[0010] Step S4: generating a waste treatment report, specifically recording the mercury-containing waste treatment process;

[0011] Step S5: Data sharing, specifically determining the data sharing scope, setting access rights, and sharing the mercury-containing waste data.

[0012] Furthermore, in step S1, the mercury-containing waste data collection includes the following steps:

[0013] Step S11: Installing sensors. Select appropriate locations to install sensors based on monitoring requirements and characteristics of the target area to ensure that representative mercury-containing waste data is collected;

[0014] Step S12: Calculate the maximum similarity value to ensure the reliability of data collection. Use the structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status. The formula used is as follows:

[0015] ;

[0016] In the formula, It represents the maximum value of the similarity index under the sensor configuration, SSIM represents the structural similarity index function, C represents the sensor configuration, and sim is an index used to measure the similarity between two sets of data. It shows the data collection of mercury-containing waste under the sensor configuration. Represent the true status of mercury-containing waste;

[0017] Step S13: Calculate the mean absolute error. In order to quantify the accuracy of the regional average mercury-containing waste data collection, the mean absolute error of the mercury-containing waste data collection in each local control area is calculated. The formula used is as follows:

[0018] ;

[0019] In the formula, represents the mean absolute error of mercury-containing waste data collection in the jth local control area, j represents the local control area index, Represents the data collection of mercury-containing waste in the local control area under the sensor configuration, represents the actual mercury-containing waste data of the jth local control area, average() represents the function for calculating the average value of the elements in brackets;

[0020] Step S14: Optimize the sensor deployment, calculate the objective function of the MAE aggregation of all areas, and improve the specific layout of the sensors based on the information reflected by the objective function. The formula used is as follows:

[0021] ;

[0022] In the formula, represents the objective function, which is used to express the comprehensive evaluation value related to the mercury content level. Indicates the total number of local control areas.

[0023] Furthermore, in step S2, the transmission of mercury-containing waste data further includes the following steps:

[0024] Step S22: Calculate the entropy of the blockchain to evaluate the stability of the blockchain system. The formula used is as follows:

[0025] ;

[0026] In the formula, H represents the entropy of the blockchain, represents the number of blocks in the blockchain, i represents the index of the blockchain, represents a standardized reputation score metric;

[0027] Step S23: Calculate the reward function to reasonably allocate reward resources and guide the blockchain to improve in the direction of increasing rewards. The formula used is as follows:

[0028] ;

[0029] In the formula, represents the reward function, represents the reward factor, represents the power associated with the hash function, represents the power related to the data rate, represents the power related to connectivity, K represents the number of consensus requests, represents the consensus delay, Indicates the node update delay, Indicates the traffic offloading delay, represents the computational delay, and R represents the data rate;

[0030] Step S24: Blockchain data exchange. Data exchange is carried out between the terminal and cache node belonging to the blockchain. Before establishing a secure communication link between edge nodes, all edge nodes are carefully reviewed at the blockchain level to ensure that only real nodes can participate in data transmission, thereby maximizing the security and authenticity of data exchange in the blockchain network.

[0031] Step S25: Calculate the data rate. Considering various parameters comprehensively, calculate the data transmission rate between nodes, which is helpful to evaluate and optimize data transmission performance and plan network resources. The formula used is as follows:

[0032] ;

[0033] In the formula, represents the data rate between node x and node y, n represents the index of the subchannel, which is used to distinguish different subchannels, and M represents the total number of subchannels. represents the time that edge node x occupies the nth subchannel, represents the bandwidth associated with the subchannel, represents the transmission power of node x on the nth subchannel, represents the channel gain from node x to node y on the nth subchannel, represents the distance from node x to node y on the nth subchannel, α represents the path loss exponent, represents the number of connections of node x, represents the transmission power of node j on the nth subchannel, represents the channel gain from node j to node y on the nth subchannel, represents the distance from node j to node y on the nth subchannel, Indicates the time that node y occupies the nth subchannel.

[0034] Furthermore, in step S3, the real-time monitoring and early warning further includes the following steps:

[0035] Step S32: abnormal score judgment, a low score means that the data point behaves similarly to the normal data pattern in the structure of the isolation forest and is regarded as a normal point; a high score means that the data point exhibits characteristics different from normal data in the process of building the isolation forest and is more likely to be isolated and regarded as an abnormal point; when it is close to the normalization factor, the behavior characteristics of the data point are close to most normal data and there is no obvious abnormal factor;

[0036] Step S33: Calculate the anomaly score value. After the training is completed, the anomaly score of the data point is determined. The anomaly score is based on the depth of the leaf into which the data point falls in the isolation forest. The depth of the leaf reflects the difficulty of isolating the data point in the tree structure. Anomalies are more likely to appear in shallower leaves, so the anomaly score corresponding to shallower depth will be higher. By calculating the score corresponding to the leaf depth of the data point on each tree, these scores are averaged over all trees. The purpose is to make a comprehensive judgment on multiple trees to make the anomaly score more reliable. The average is taken over all trees in the forest. The formula used is as follows:

[0037] ;

[0038] In the formula, represents the anomaly score of point x, is the normalization factor, T represents the trees in the forest, F represents the forest, represents the depth of the leaf of a particular tree T that contains the data point x, It means taking the average value over all trees T in the forest F;

[0039] Step S34: Calculate the leaf color, and define the leaf color according to the ratio of abnormal points to normal points contained therein, and the formula used is as follows:

[0040] ;

[0041] In the formula, Indicates the leaf color, is the number of labeled normal points contained in the leaf, is the number of anomalies marked in the leaf. The color of the leaf determines the internal structure of the leaf and is used to represent the probability of data anomalies.

[0042] Step S35: Calculate the piecewise linear supervision depth function to assist in determining the degree of abnormality of the mercury-containing waste data. The formula used is as follows:

[0043] ;

[0044] In the formula, represents the piecewise linear supervision depth function value of the leaf, is the maximum depth of the isolation forest computed during unsupervised training, It is the minimum depth of the isolation forest calculated during unsupervised training. The depth indicates the number of divisions from the root node to a certain node. A shallower depth means that the data point is isolated faster, and a deeper depth means that the data point is separated from other data after multiple divisions.

[0045] Step S36: Calculate the marked point, which is the point with the highest anomaly score in the current iteration. Update and mark the anomaly point in real time so that the monitoring system can dynamically adapt to changes in mercury-containing waste data. The formula used is as follows:

[0046] ;

[0047] In the formula, Indicates the points selected to be marked. Indicates the value of the data point x that corresponds to the maximum value of the following expression in the data point set X.

[0048] Furthermore, in step S4, the waste treatment report is generated, specifically recording the source of mercury-containing waste according to the real-time monitoring content, describing the waste characteristics, recording the method of treating the mercury-containing waste and determining whether the mercury concentration meets the safe emission standard, evaluating the potential impact on the environment during the treatment process, and taking corresponding protective measures.

[0049] Furthermore, in step S5, the data sharing includes the following steps:

[0050] Step S51: Determine the scope of data sharing and clarify the specific types of mercury-containing waste data to be shared, including waste treatment volume, treatment methods and monitoring data, and establish a safe and reliable data sharing platform to enable relevant departments to timely understand the overall situation of mercury-containing waste and effectively carry out planning, decision-making and resource allocation;

[0051] Step S52: Set access rights. According to different user needs and levels, set corresponding access rights. After uploading the sorted mercury-containing waste data to the data platform, perform regular updates and maintenance, continuously monitor the security of the mercury-containing waste data sharing process, and take necessary security measures to prevent data leakage.

[0052] The present invention provides an Internet of Things monitoring system for the treatment of mercury-containing wastes, including a mercury-containing waste data collection module, a mercury-containing waste data transmission module, a real-time monitoring and early warning module, a waste treatment report generation module and a data sharing module;

[0053] The mercury-containing waste data collection module specifically uses a structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculates the average absolute error of the mercury-containing waste data collection in each local control area, and improves the specific arrangement of sensors according to the information reflected by the objective function;

[0054] The mercury-containing waste data transmission module specifically determines the correct number of blocks in the blockchain, calculates the entropy and reward function of the blockchain, performs blockchain data exchange and calculates the data transmission rate, and optimizes the performance of mercury-containing waste data transmission;

[0055] The real-time monitoring and early warning module specifically trains a basic model, performs anomaly score judgment, calculates anomaly score values, defines leaf color according to the ratio of abnormal points to normal points in the leaves, gives a piecewise linear supervised depth function, calculates the point with the highest anomaly score, and assists in judging the degree of abnormality of mercury-containing waste data;

[0056] The waste treatment report generation module is specifically used to record the mercury-containing waste treatment process;

[0057] The data sharing module is specifically used to determine the data sharing scope, set access rights, and share the mercury-containing waste data.

[0058] The beneficial results achieved by the present invention using the above scheme are as follows:

[0059] (1) In order to address the technical issues of inaccurate data collection on mercury-containing waste, which makes it difficult to quantify the data, and large errors in the location of sensor deployment, which makes data collection more difficult, a structural similarity index is used to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste situation, and the average absolute error of mercury-containing waste data collection in each local control area is calculated. The specific layout of sensors is improved based on the information reflected by the objective function;

[0060] (2) In order to solve the technical problem that a large amount of mercury-containing waste data is not transmitted quickly, which makes it difficult to achieve more accurate and effective data transmission planning, affects the real-time grasp of the treatment status of mercury-containing waste, and thus makes environmental pollution control difficult, a method is adopted to determine the correct number of blocks in the blockchain, calculate the entropy and reward function of the blockchain, exchange blockchain data and calculate the data transmission rate, so as to optimize the performance of mercury-containing waste data transmission;

[0061] (3) In order to solve the technical problem that the existence of abnormal points in the mercury-containing waste data leads to inaccurate assessment of the actual situation of mercury-containing waste, interferes with the understanding of the progress of the overall treatment work, affects the rational allocation and management of resources, and increases environmental risks, a training basic model is used to judge the abnormal score and calculate the abnormal score value. The leaf color is defined according to the ratio of abnormal points to normal points in the leaf. A piecewise linear supervised depth function is given to calculate the point with the highest abnormal score to assist in judging the degree of abnormality of the mercury-containing waste data. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic flow chart of an Internet of Things monitoring method for mercury-containing waste treatment provided by the present invention;

[0063] Figure 2 A schematic diagram of an Internet of Things monitoring system for mercury-containing waste treatment provided by the present invention;

[0064] Figure 3 is a schematic flow chart of step S1;

[0065] Figure 4 is a schematic flow chart of step S2;

[0066] Figure 5 It is a schematic diagram of the process of step S3.

[0067] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0069] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0070] Example 1, see Figure 1 The present invention provides an Internet of Things monitoring method for mercury-containing waste treatment, the method comprising the following steps:

[0071] Step S1: mercury-containing waste data collection, specifically using the structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculating the average absolute error of mercury-containing waste data collection in each local control area, and improving the specific layout of sensors based on the information reflected by the objective function;

[0072] Step S2: Transmission of mercury-containing waste data, specifically determining the correct number of blocks in the blockchain, calculating the entropy and reward function of the blockchain, performing blockchain data exchange and calculating the data transmission rate, and optimizing the performance of mercury-containing waste data transmission;

[0073] Step S21: determining the correct number of blocks in the blockchain, taking into account the security, efficiency and scalability of the blockchain, and obtaining the number of blocks in the blockchain through the consensus mechanism of network nodes, the block generation speed and the data transmission requirements of mercury-containing waste;

[0074] Step S3: Real-time monitoring and early warning, specifically training the basic model, performing anomaly score judgment, calculating the anomaly score value, defining the leaf color according to the ratio of abnormal points to normal points in the leaf, giving a piecewise linear supervised depth function, calculating the point with the highest anomaly score, and assisting in judging the degree of abnormality of the mercury-containing waste data;

[0075] Step S31: training the basic model. During the training process, a series of isolation trees are constructed by randomly sampling data points, and random partitioning is continuously performed to make abnormal data points easier to be isolated by random partitioning;

[0076] Step S4: generating a waste treatment report, specifically recording the mercury-containing waste treatment process;

[0077] Step S5: Data sharing, specifically determining the data sharing scope, setting access rights, and sharing the mercury-containing waste data.

[0078] Example 2, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S1, the mercury-containing waste data collection includes the following steps:

[0079] Step S11: Installing sensors. Select appropriate locations to install sensors based on monitoring requirements and characteristics of the target area to ensure that representative mercury-containing waste data is collected;

[0080] Step S12: Calculate the maximum similarity value to ensure the reliability of data collection. Use the structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status. The formula used is as follows:

[0081] ;

[0082] In the formula, It represents the maximum value of the similarity index under the sensor configuration, SSIM represents the structural similarity index function, C represents the sensor configuration, and sim is an index used to measure the similarity between two sets of data. It shows the data collection of mercury-containing waste under the sensor configuration. Represent the true status of mercury-containing waste;

[0083] Step S13: Calculate the mean absolute error. In order to quantify the accuracy of the regional average mercury-containing waste data collection, the mean absolute error of the mercury-containing waste data collection in each local control area is calculated. The formula used is as follows:

[0084] ;

[0085] In the formula, represents the mean absolute error of mercury-containing waste data collection in the jth local control area, j represents the local control area index, Represents the data collection of mercury-containing waste in the local control area under the sensor configuration, represents the actual mercury-containing waste data of the jth local control area, average() represents the function for calculating the average value of the elements in brackets;

[0086] Step S14: Optimize the sensor deployment, calculate the objective function of the MAE aggregation of all areas, and improve the specific layout of the sensors based on the information reflected by the objective function. The formula used is as follows:

[0087] ;

[0088] In the formula, represents the objective function, which is used to express the comprehensive evaluation value related to the mercury content level. Indicates the total number of local control areas.

[0089] By performing the above operations, the structural similarity index is used to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, and the average absolute error of mercury-containing waste data collection in each local control area is calculated. The specific layout of the sensor is improved based on the information reflected by the objective function, which solves the technical problems of inaccurate mercury waste data collection, difficulty in quantification, and large errors in sensor deployment positions, which make data collection more difficult.

[0090] Example 3, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S2, the mercury-containing waste data transmission further includes the following steps:

[0091] Step S22: Calculate the entropy of the blockchain to evaluate the stability of the blockchain system. The formula used is as follows:

[0092] ;

[0093] In the formula, H represents the entropy of the blockchain, represents the number of blocks in the blockchain, i represents the index of the blockchain, represents a standardized reputation score metric;

[0094] Step S23: Calculate the reward function to reasonably allocate reward resources and guide the blockchain to improve in the direction of increasing rewards. The formula used is as follows:

[0095] ;

[0096] In the formula, represents the reward function, represents the reward factor, represents the power associated with the hash function, represents the power related to the data rate, represents the power related to connectivity, K represents the number of consensus requests, represents the consensus delay, Indicates the node update delay, Indicates the traffic offloading delay, represents the computational delay, and R represents the data rate;

[0097] Step S24: Blockchain data exchange. Data exchange is carried out between the terminal and cache node belonging to the blockchain. Before establishing a secure communication link between edge nodes, all edge nodes are carefully reviewed at the blockchain level to ensure that only real nodes can participate in data transmission, thereby maximizing the security and authenticity of data exchange in the blockchain network.

[0098] Step S25: Calculate the data rate. Considering various parameters comprehensively, calculate the data transmission rate between nodes, which is helpful to evaluate and optimize data transmission performance and plan network resources. The formula used is as follows:

[0099] ;

[0100] In the formula, represents the data rate between node x and node y, n represents the index of the subchannel, which is used to distinguish different subchannels, and M represents the total number of subchannels. represents the time that edge node x occupies the nth subchannel, represents the bandwidth associated with the subchannel, represents the transmission power of node x on the nth subchannel, represents the channel gain from node x to node y on the nth subchannel, represents the distance from node x to node y on the nth subchannel, α represents the path loss exponent, represents the number of connections of node x, represents the transmission power of node j on the nth subchannel, represents the channel gain from node j to node y on the nth subchannel, represents the distance from node j to node y on the nth subchannel, Indicates the time that node y occupies the nth subchannel.

[0101] By executing the above operations, the correct number of blocks in the blockchain is determined, the entropy and reward function of the blockchain are calculated, blockchain data is exchanged and the data transmission rate is calculated, the data transmission performance of mercury-containing waste is optimized, and the technical problem of slow data transmission of a large amount of mercury-containing waste, which makes it difficult to achieve more accurate and effective data transmission planning, affects the real-time grasp of the treatment status of mercury-containing waste, and thus makes environmental pollution control difficult is solved.

[0102] Example 4, see Figure 1 and Figure 5 This embodiment is based on the above embodiment. In step S3, the real-time monitoring and early warning further includes the following steps:

[0103] Step S32: abnormal score judgment, a low score means that the data point behaves similarly to the normal data pattern in the structure of the isolation forest and is regarded as a normal point; a high score means that the data point exhibits characteristics different from normal data in the process of building the isolation forest and is more likely to be isolated and regarded as an abnormal point; when it is close to the normalization factor, the behavior characteristics of the data point are close to most normal data and there is no obvious abnormal factor;

[0104] Step S33: Calculate the anomaly score value. After the training is completed, the anomaly score of the data point is determined. The anomaly score is based on the depth of the leaf into which the data point falls in the isolation forest. The depth of the leaf reflects the difficulty of isolating the data point in the tree structure. Anomalies are more likely to appear in shallower leaves, so the anomaly score corresponding to shallower depth will be higher. By calculating the score corresponding to the leaf depth of the data point on each tree, these scores are averaged over all trees. The purpose is to make a comprehensive judgment on multiple trees to make the anomaly score more reliable. The average is taken over all trees in the forest. The formula used is as follows:

[0105] ;

[0106] In the formula, represents the anomaly score of point x, is the normalization factor, T represents the trees in the forest, F represents the forest, represents the depth of the leaf of a particular tree T that contains the data point x, It means taking the average value over all trees T in the forest F;

[0107] Step S34: Calculate the leaf color, and define the leaf color according to the ratio of abnormal points to normal points contained therein, and the formula used is as follows:

[0108] ;

[0109] In the formula, Indicates the leaf color, is the number of labeled normal points contained in the leaf, is the number of anomalies marked in the leaf. The color of the leaf determines the internal structure of the leaf and is used to represent the probability of data anomalies.

[0110] Step S35: Calculate the piecewise linear supervision depth function to assist in determining the degree of abnormality of the mercury-containing waste data. The formula used is as follows:

[0111] ;

[0112] In the formula, represents the piecewise linear supervision depth function value of the leaf, is the maximum depth of the isolation forest computed during unsupervised training, It is the minimum depth of the isolation forest calculated during unsupervised training. The depth indicates the number of divisions from the root node to a certain node. A shallower depth means that the data point is isolated faster, and a deeper depth means that the data point is separated from other data after multiple divisions.

[0113] Step S36: Calculate the marked point, which is the point with the highest anomaly score in the current iteration. Update and mark the anomaly point in real time so that the monitoring system can dynamically adapt to changes in mercury-containing waste data. The formula used is as follows:

[0114] ;

[0115] In the formula, Indicates the points selected to be marked. Indicates the value of the data point x that corresponds to the maximum value of the following expression in the data point set X.

[0116] By executing the above operations, the training basic model is used to judge the anomaly score, calculate the anomaly score value, define the leaf color according to the ratio of abnormal points to normal points in the leaf, give a piecewise linear supervised depth function, calculate the point with the highest anomaly score, and assist in judging the degree of abnormality of the mercury-containing waste data. The technical problem that the existence of abnormal points in the mercury-containing waste data leads to inaccurate assessment of the actual situation of mercury-containing waste, interferes with the understanding of the progress of the overall treatment work, affects the rational allocation and management of resources, and increases environmental risks is solved.

[0117] Example 5, see Figure 1 This embodiment is based on the above embodiment. In step S4, the waste treatment report is generated, specifically recording the source of mercury-containing waste according to real-time monitoring content, describing the waste characteristics, recording the method of treating mercury-containing waste and judging whether the mercury concentration reaches the safe emission standard, evaluating the potential impact on the environment during the treatment process, and taking corresponding protective measures.

[0118] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the data sharing includes the following steps:

[0119] Step S51: Determine the scope of data sharing and clarify the specific types of mercury-containing waste data to be shared, including waste treatment volume, treatment methods and monitoring data, and establish a safe and reliable data sharing platform to enable relevant departments to timely understand the overall situation of mercury-containing waste and effectively carry out planning, decision-making and resource allocation;

[0120] Step S52: Set access rights. According to different user needs and levels, set corresponding access rights. After uploading the sorted mercury-containing waste data to the data platform, perform regular updates and maintenance, continuously monitor the security of the mercury-containing waste data sharing process, and take necessary security measures to prevent data leakage.

[0121] Embodiment 7, see Figure 2 , this embodiment is based on the above embodiment, and the present invention provides an Internet of Things monitoring system for mercury-containing waste treatment, including a mercury-containing waste data collection module, a mercury-containing waste data transmission module, a real-time monitoring and early warning module, a waste treatment report generation module and a data sharing module;

[0122] The mercury-containing waste data collection module specifically uses a structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculates the average absolute error of the mercury-containing waste data collection in each local control area, and improves the specific arrangement of sensors according to the information reflected by the objective function;

[0123] The mercury-containing waste data transmission module specifically determines the correct number of blocks in the blockchain, calculates the entropy and reward function of the blockchain, performs blockchain data exchange and calculates the data transmission rate, and optimizes the performance of mercury-containing waste data transmission;

[0124] The real-time monitoring and early warning module specifically trains a basic model, performs anomaly score judgment, calculates anomaly score values, defines leaf color according to the ratio of abnormal points to normal points in the leaves, gives a piecewise linear supervised depth function, calculates the point with the highest anomaly score, and assists in judging the degree of abnormality of mercury-containing waste data;

[0125] The waste treatment report generation module is specifically used to record the mercury-containing waste treatment process;

[0126] The data sharing module is specifically used to determine the data sharing scope, set access rights, and share the mercury-containing waste data.

[0127] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0128] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0129] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An Internet of Things monitoring method for mercury-containing waste treatment, Features: The method comprises the following steps: Step S1: mercury-containing waste data collection, specifically using the structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculating the average absolute error of mercury-containing waste data collection in each local control area, and improving the sensor layout according to the information reflected by the objective function; Step S2: Transmission of mercury-containing waste data, specifically calculating the entropy and reward function of the blockchain, performing blockchain data exchange and calculating the data transmission rate; Step S21: comprehensively considering the security, efficiency and scalability of the blockchain, and obtaining the number of blocks of the blockchain through the consensus mechanism of network nodes, the block generation speed and the data transmission requirements of mercury-containing waste; Step S3: Real-time monitoring and early warning, specifically training the basic model, calculating the anomaly score value, defining the leaf color according to the ratio of abnormal points to normal points in the leaf, giving a piecewise linear supervised depth function, calculating the point with the highest anomaly score, and assisting in judging the degree of abnormality of the mercury-containing waste data; Step S31: training the basic model. During the training process, a series of isolation trees are constructed by randomly sampling data points, and random segmentation is continuously performed so that abnormal data points are isolated by random partitions. Step S32: abnormal score determination; Step S33: Calculate the abnormal score value, the formula used is as follows: ； In the formula, represents the anomaly score of point x, is the normalization factor, T represents the trees in the forest, F represents the forest, represents the depth of the leaf of a particular tree T that contains the data point x, It means taking the average value over all trees T in the forest F; Step S34: Calculate the leaf color, and define the leaf color according to the ratio of abnormal points to normal points contained therein, and the formula used is as follows: ； In the formula, Indicates the leaf color, is the number of labeled normal points contained in the leaf, is the number of abnormalities marked in the leaf; Step S35: Calculate the piecewise linear supervision depth function to assist in determining the degree of abnormality of the mercury-containing waste data. The formula used is as follows: ； In the formula, represents the piecewise linear supervision depth function value of the leaf, is the maximum depth of the isolation forest computed during unsupervised training, is the minimum depth of the isolation forest computed during unsupervised training; Step S36: Calculate the marked point, which is the point with the highest anomaly score in the current iteration, using the following formula: ； In the formula, Indicates the points selected to be marked. Indicates the value of the data point x corresponding to the maximum value of the following expression in the data point set X; Step S4: generating a waste treatment report, specifically recording the mercury-containing waste treatment process; Step S5: Data sharing, specifically determining the data sharing scope and setting access permissions.

2. The Internet of Things monitoring method for mercury-containing waste treatment according to claim 1, Features: In step S1, the mercury-containing waste data collection includes the following steps: Step S11: installing the sensor; Step S12: Calculate the maximum similarity value, the formula used is as follows: ； In the formula, It represents the maximum value of the similarity index under the sensor configuration, SSIM represents the structural similarity index function, C represents the sensor configuration, and sim is an index used to measure the similarity between two sets of data. It shows the data collection of mercury-containing waste under the sensor configuration. Represent the true status of mercury-containing waste; Step S13: Calculate the mean absolute error, that is, calculate the mean absolute error of the mercury-containing waste data collection in each local control area, using the following formula: ； In the formula, represents the mean absolute error of mercury-containing waste data collection in the jth local control area, j represents the local control area index, Represents the mercury waste data collection in the control area under the sensor configuration, represents the actual mercury-containing waste data of the jth local control area, average() represents the function for calculating the average value of the elements in brackets; Step S14: Optimize the sensor deployment, and improve the specific arrangement of the sensors according to the information reflected by the objective function. The formula used is as follows: ； In the formula, represents the objective function, which is used to express the comprehensive evaluation value related to the mercury content level. Represents the total number of local control areas.

3. The Internet of Things monitoring method for mercury-containing waste treatment according to claim 1, Features: In step S2, the transmission of mercury-containing waste data further includes the following steps: Step S22: Calculate the entropy of the blockchain to evaluate the stability of the blockchain system. The formula used is as follows: ； In the formula, H represents the entropy of the blockchain, represents the number of blocks in the blockchain, i represents the index of the blockchain, represents a standardized reputation score metric; Step S23: Calculate the reward function to reasonably allocate reward resources and guide the blockchain to improve in the direction of increasing rewards. The formula used is as follows: ； In the formula, represents the reward function, represents the reward factor, represents the power associated with the hash function, represents the power related to the data rate, represents the power related to connectivity, K represents the number of consensus requests, represents the consensus delay, Indicates the node update delay, Indicates the traffic offloading delay, represents the computational delay, and R represents the data rate; Step S24: Blockchain data exchange. Data exchange is carried out between the terminal and cache nodes belonging to the blockchain. Before establishing a secure communication link between edge nodes, all edge nodes are carefully reviewed at the blockchain level to ensure that only authentic nodes can participate in data transmission. Step S25: Calculate the data rate. Consider various parameters comprehensively to calculate the data transmission rate between nodes. The formula used is as follows: ； In the formula, represents the data rate between node x and node y, n represents the index of the subchannel, which is used to distinguish different subchannels, and M represents the total number of subchannels. represents the time that edge node x occupies the nth subchannel, represents the bandwidth associated with the subchannel, represents the transmission power of node x on the nth subchannel, represents the channel gain from node x to node y on the nth subchannel, represents the distance from node x to node y on the nth subchannel, α represents the path loss exponent, represents the number of connections of node x, represents the transmission power of node j on the nth subchannel, represents the channel gain from node j to node y on the nth subchannel, represents the distance from node j to node y on the nth subchannel, Indicates the time that node y occupies the nth subchannel.

4. The Internet of Things monitoring method for mercury-containing waste treatment according to claim 1, Features: In step S4, the waste treatment report is generated, specifically recording the source of mercury-containing waste according to the real-time monitoring content, describing the waste characteristics, recording the method of treating the mercury-containing waste and determining whether the mercury concentration meets the safe emission standard, evaluating the potential impact on the environment during the treatment process, and taking corresponding protective measures.

5. The Internet of Things monitoring method for mercury-containing waste treatment according to claim 1, Features: In step S5, the data sharing includes the following steps: Step S51: Determine the scope of data sharing, clarify the specific types of mercury-containing waste treatment data to be shared, establish a safe and reliable data sharing platform, and effectively carry out planning, decision-making and resource allocation; Step S52: Set access rights. According to different user needs and levels, set corresponding access rights. After uploading the sorted mercury-containing waste treatment data to the data platform, perform regular updates and maintenance, continuously monitor the security of the mercury-containing waste data sharing process, and take security measures to prevent data leakage.

6. An Internet of Things monitoring system for mercury-containing waste treatment, used to implement an Internet of Things monitoring method for mercury-containing waste treatment as claimed in any one of claims 1 to 5, Features: It includes a mercury-containing waste data collection module, a mercury-containing waste data transmission module, a real-time monitoring and early warning module, a waste treatment report generation module and a data sharing module.

7. The Internet of Things monitoring system for mercury-containing waste treatment according to claim 6, Features: The mercury-containing waste data collection module specifically uses a structural similarity index to measure the similarity between the collected mercury-containing waste data and the actual mercury-containing waste status, calculates the average absolute error of the mercury-containing waste data collection in each local control area, and improves the specific arrangement of sensors according to the information reflected by the objective function; The mercury-containing waste data transmission module specifically calculates the entropy and reward function of the blockchain, performs blockchain data exchange and calculates the data transmission rate, and optimizes the performance of mercury-containing waste data transmission; The real-time monitoring and early warning module specifically trains a basic model, performs anomaly score judgment, calculates anomaly score values, defines leaf color according to the ratio of abnormal points to normal points in the leaves, gives a piecewise linear supervised depth function, calculates the point with the highest anomaly score, and assists in judging the degree of abnormality of mercury-containing waste data; The waste treatment report generation module is specifically used to record the mercury-containing waste treatment process; The data sharing module is specifically used to determine the data sharing scope, set access rights, and share the mercury-containing waste treatment data.

Images