Carbon emission activity level checking method and device based on Internet of Things technology

Abstract

The invention belongs to the technical field of production checking, and discloses a carbon emission activity level checking method and device based on the Internet of Things technology. The method comprises the following steps: monitoring vibration data of equipment based on a non-invasive deployed vibration sensor, and correspondingly monitoring voltage data and current data of the equipment based on a voltage sensor and a current sensor; when it is judged that a preset checking period is reached, inputting a section of vibration data which is traced forward from the current time point for a preset duration into a pre-trained LSTM neural network model and a CNN neural network model to obtain predicted equipment working time and equipment energy consumption rate of a corresponding time period; calculating arithmetic average values based on the voltage data and the current data in the corresponding time periods to obtain average voltage data and average current data; and inputting the data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding time period. According to the invention, the checking difficulty of the carbon emission activity level is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of production verification, and in particular to a method and device for verifying carbon emission activity levels based on Internet of Things technology. Background Art

[0002] Carbon emission activity level refers to the carbon emission activity level generated by a specific region, organization or individual per unit time. This concept is usually used to measure the amount of carbon dioxide or other greenhouse gases released into the atmosphere by a specific entity (such as a company or individual) in its daily activities. The measurement of carbon emission activity level can involve many aspects, including industrial production, transportation, energy consumption, agricultural activities and other activities that affect greenhouse gas emissions.

[0003] For countries or regions, calculating carbon emission activity levels is an important basis for assessing their contribution to global climate change and countermeasures. At the corporate level, understanding carbon emission activity levels helps identify and implement strategies to reduce carbon footprints in order to comply with environmental regulations and social responsibility requirements. For individuals, paying attention to personal carbon emission activity levels can reduce the negative impact of climate change by changing lifestyles and consumption habits.

[0004] Based on this, it is of great practical significance to effectively monitor the level of carbon emission activities. Specifically, the "Carbon Emission Trading Management Measures (Trial)" issued by the Ministry of Ecology and Environment has been implemented since February 1, 2021, which stipulates carbon verification: Provincial ecological and environmental authorities shall organize the verification of greenhouse gas emission reports of key emission units, and inform key emission units of the verification results, and the verification results shall be used as the basis for the settlement of carbon emission quotas of key emission units; provincial ecological and environmental authorities may entrust technical service agencies to provide verification services through government procurement services.

[0005] There are two methods for third-party verification agencies to verify carbon emission levels: one is to directly monitor the amount of gas emitted, but this method is affected by the gas form and has the defect of low accuracy. The other is to first obtain the relevant equipment parameters, and then use the relevant accounting formula to calculate the carbon emission activity level. Among them, the second method has relatively high accuracy, so it is often used to verify carbon emission levels. However, the inventors found that during the operation of the second method, in order to obtain the relevant equipment parameters, it is necessary to install the corresponding monitoring equipment in an invasive manner, which is not only difficult to install, but also may affect the normal operation of the equipment. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for verifying carbon emission activity levels based on Internet of Things technology, so as to improve the technical problem of difficulty in obtaining relevant equipment parameters during the operation process of calculating carbon emission activity levels using calculation formulas.

[0007] To achieve the above object, the present invention proposes the following technical solutions:

[0008] In the first aspect, this technical solution provides a method for verifying carbon emission activity levels based on Internet of Things technology. It includes:

[0009] Vibration data of the equipment is monitored based on non-invasively deployed vibration sensors, and voltage data and current data of the equipment are monitored based on pre-deployed voltage sensors and current sensors;

[0010] The vibration sensor is deployed at a position in the device that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the device; the voltage sensor and the current sensor are both deployed on the power supply circuit of the device drive motor, and the voltage data and the current data are both input end data;

[0011] When it is determined that the preset verification cycle has been reached, a section of vibration data from the current time point with a preset length of time is input into the pre-trained LSTM neural network model based on the Internet of Things technology to obtain the predicted equipment working time of the corresponding period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period;

[0012] The LSTM neural network model is used to extract the long-term time dependency in the vibration data. In the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, the deep features of the input are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training;

[0013] Calculate the arithmetic mean values ​​based on the voltage data and the current data in the corresponding time period to obtain the average voltage data and the average current data;

[0014] Inputting the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding period;

[0015] Among them, the carbon emission activity level calculation formula is: Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor; where P=U×I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

[0016] Furthermore, when the judgment reaches a preset verification cycle, based on the Internet of Things technology, a section of vibration data traced back to a preset time from the current time point is input into a pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding period; at the same time, the section of vibration data is input into a pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period; including:

[0017] Acquire sensor data based on a pre-deployed data acquisition gateway, and simultaneously acquire a check code corresponding to the sensor data; wherein the sensor data includes the vibration data, the current data and the voltage data, and is compressed data compressed by the LORA module of each corresponding sensor data acquisition terminal;

[0018] Decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data;

[0019] After the standard sensor data is packaged in JSON format, the standard sensor data is sent to the cloud platform based on the MQTT protocol and then decompressed and stored; wherein a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection;

[0020] When it is determined that the preset verification cycle has been reached, the standard vibration data in the standard sensor data of the corresponding time period is analyzed and sent to the LSTM neural network model and the CNN neural network model.

[0021] Furthermore, the vibration sensor based on non-invasive deployment monitors the vibration data of the equipment; including:

[0022] Real-time display of relevant data of vibration sensors based on the display terminal integrated in the data acquisition gateway;

[0023] The relevant data include: acceleration value, velocity value, displacement value and spectrum diagram of each axis of the vibration sensor; the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in the corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in the corresponding time period;

[0024] The vibration data is time domain data, and the acquisition of the spectrum diagram includes: first, denoising the time domain data, then converting the denoised time domain data into frequency domain data based on the FFT algorithm, and calculating the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies; finally, drawing the spectrum diagram with the frequency as the horizontal axis and the vibration amplitude as the vertical axis;

[0025] When it is determined that the relevant data shows an abnormality, an early warning message is sent to the maintenance end; wherein the early warning message includes: abnormal data, abnormal time period and abnormal data source.

[0026] Furthermore,

[0027] The CNN neural network model is composed of an input layer, a convolutional layer, a batch normalization layer, an activation layer, a discard layer, and a fully connected layer in sequence, and performs gradient back propagation to update parameters;

[0028] Among them, the corresponding loss function is: Among them, x i is the predicted value, y i is the true value, and N is the number of samples.

[0029] Furthermore, after simultaneously inputting the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into the carbon emission activity level calculation formula to obtain the carbon emission activity level of the corresponding period; it includes:

[0030] When it is determined that the carbon emission activity level in any period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is less than the first emission difference, or when the total carbon emission activity level in a number of consecutive periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is less than the second emission difference; send the first over-regulation information to the enterprise end;

[0031] When it is determined that the carbon emission activity level in any period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is greater than the first emission difference, or when the total carbon emission activity level in a number of consecutive periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is greater than the second emission difference; send the second over-regulation information to the enterprise end and the verification end;

[0032] Among them, the first out-of-specification information is used to remind the enterprise to optimize relevant production parameters, and the second out-of-specification information is used to require the enterprise to suspend relevant production within a preset downtime period; the first out-of-specification information and the second out-of-specification information both include: out-of-specification equipment, out-of-specification time period and out-of-specification carbon emission activity level.

[0033] In the second aspect, this technical solution provides a carbon emission activity level verification device based on Internet of Things technology. It includes:

[0034] A monitoring module, used to monitor the vibration data of the equipment based on the non-invasively deployed vibration sensor, and to monitor the voltage data and current data of the equipment based on the pre-deployed voltage sensor and current sensor;

[0035] The vibration sensor is deployed at a position in the device that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the device; the voltage sensor and the current sensor are both deployed on the power supply circuit of the device drive motor, and the voltage data and the current data are both input end data;

[0036] The prediction module is used to determine when the preset verification cycle has arrived. Based on the Internet of Things technology, a section of vibration data traced back to a preset time from the current time point is input into the pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period;

[0037] The LSTM neural network model is used to extract the long-term time dependency in the vibration data. In the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, the deep features of the input are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training;

[0038] A calculation module, used for respectively calculating arithmetic averages based on the voltage data and the current data in the corresponding time period to obtain average voltage data and average current data;

[0039] A verification module, used to input the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding period;

[0040] Among them, the carbon emission activity level calculation formula is: Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor; where P=U×I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

[0041] Furthermore, the prediction module includes:

[0042] An acquisition unit, used to acquire sensor data based on a pre-deployed data acquisition gateway, and at the same time acquire a check code corresponding to the sensor data; wherein the sensor data includes the vibration data, the current data and the voltage data, and is compressed data compressed by the LORA module of each corresponding sensor data acquisition terminal;

[0043] A processing unit is used to decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data;

[0044] A storage unit, used for packaging the standard sensor data in JSON format, sending the standard sensor data to the cloud platform based on the MQTT protocol, and then decompressing and storing the data; wherein a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection;

[0045] The sending unit is used to determine when a preset verification cycle has been reached, parse the standard vibration data in the standard sensor data of the corresponding time period, and send the data to the LSTM neural network model and the CNN neural network model.

[0046] Further, including:

[0047] A display module, used for displaying relevant data of the vibration sensor in real time based on a display terminal integrated on the data acquisition gateway;

[0048] The relevant data include: acceleration value, velocity value, displacement value and spectrum diagram of each axis of the vibration sensor; the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in the corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in the corresponding time period;

[0049] The vibration data is time domain data, and the acquisition of the spectrum diagram includes: first, denoising the time domain data, then converting the denoised time domain data into frequency domain data based on the FFT algorithm, and calculating the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies; finally, drawing the spectrum diagram with the frequency as the horizontal axis and the vibration amplitude as the vertical axis;

[0050] The abnormality processing module is used to send an early warning message to the maintenance end when it is determined that the relevant data shows an abnormality; wherein the early warning message includes: abnormal data, abnormal time period and abnormal data source.

[0051] In a third aspect, the technical solution provides an electronic device, comprising at least one processor, the processor being coupled to a memory, the memory storing a computer program, and the computer program being configured to execute the method when executed by the processor.

[0052] In a fourth aspect, the technical solution provides a computer-readable storage medium, on which a computer program is stored, and the computer program is used to execute the method described.

[0053] Beneficial effects:

[0054] It can be seen from the above technical solutions that the technical solution of the present invention provides a carbon emission activity level verification method based on Internet of Things technology to improve the defect of high technical difficulty in the operation process of calculating carbon emission activity levels using accounting formulas.

[0055] The method includes: first, monitoring the vibration data of the equipment based on a non-invasively deployed vibration sensor, and correspondingly monitoring the voltage data and current data of the equipment based on a pre-deployed voltage sensor and current sensor. Specifically, the vibration sensor is deployed at a position in the equipment that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the equipment; the voltage sensor and the current sensor are both deployed on the power supply circuit of the equipment drive motor, and the voltage data and the current data are both input data. Secondly, when it is judged that a preset verification cycle has been reached, a section of vibration data with a preset length of time from the current time point is input into the pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding time period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding time period. Specifically, the LSTM neural network model is used to extract the long-term time dependency in the vibration data. During the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, and the input deep features are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training; then, the arithmetic mean is calculated based on the voltage data and current data in the corresponding time period to obtain the average voltage data and the average current data. Finally, the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data are simultaneously input into the carbon emission activity level calculation formula to obtain the carbon emission activity level of the corresponding time period.

[0056] It can be seen that by using vibration data for prediction, real-time prediction of equipment working time and equipment energy consumption rate of the production process can be achieved. The collection of vibration data is a non-invasive method that does not require any physical changes to the production equipment. This makes the acquisition of vibration data relatively simple and does not affect the normal operation of the equipment. At this point, through precise signal processing and neural network model prediction, a relatively accurate calculation of carbon emission activity levels can be achieved.

[0057] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, may be considered to be part of the inventive subject matter of the present disclosure, provided such concepts are not mutually inconsistent.

[0058] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings, in which:

[0060] Figure 1 This is a flow chart of the carbon emission activity level verification method based on the Internet of Things technology described in this embodiment;

[0061] Figure 2 A flow chart showing real-time display of vibration sensor related data in this embodiment;

[0062] Figure 3 A flowchart for obtaining the spectrum diagram in this embodiment;

[0063] Figure 4 Flowchart of vibration data acquisition for neural network model;

[0064] Figure 5 Flowchart for the processing of verification results;

[0065] Figure 6 This is a structural block diagram of the carbon emission activity level verification device based on the Internet of Things technology described in this embodiment;

[0066] Figure 7 is a structural block diagram of the electronic device described in this embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be the common meaning understood by people with general skills in the field to which the present invention belongs.

[0068] The words "first", "second" and similar words used in the specification and claims of this application do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular form of "a", "an" or "the" and other similar words do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before "include" or "comprise" cover the features, wholes, steps, operations, elements and / or components listed after "include" or "comprise", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0069] In the prior art, the general method for third-party verification agencies to verify carbon emission levels is: first, obtain relevant equipment parameters, and then use relevant calculation formulas to calculate carbon emission activity levels. However, in this process, in order to obtain relevant equipment parameters, it is necessary to install corresponding monitoring equipment in an intrusive manner, which is not only difficult to install, but also may affect the normal operation of the equipment. Based on this, this embodiment aims to provide a carbon emission activity level verification method based on Internet of Things technology to improve the above technical defects.

[0070] The following is a detailed introduction to the carbon emission activity level verification method based on the Internet of Things technology described in this embodiment with reference to the accompanying drawings.

[0071] like Figure 1 As shown, the method includes:

[0072] Step S102: monitoring vibration data of the device based on the non-invasively deployed vibration sensor, and correspondingly monitoring voltage data and current data of the device based on the pre-deployed voltage sensor and current sensor.

[0073] The equipment described in this embodiment can be a ball mill, a vibrating screen, a hydraulic press, etc.

[0074] In order to improve the accuracy of the monitored vibration data, the vibration sensor is deployed in a position in the equipment that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the equipment.

[0075] The voltage sensor and the current sensor are both deployed on the power supply circuit of the device driving motor, thereby ensuring that they are both installed upstream of the power coil. At this time, the voltage data and the current data are both input end data.

[0076] As a specific implementation method, in order to facilitate the monitoring of the vibration data, to ensure the effectiveness of the monitoring of the vibration situation, and to ensure the stable operation of the equipment, and then to ensure the effective monitoring of the subsequent prediction process and carbon emission activity level. Figure 2 As shown, it also includes:

[0077] Step S103.2: Display relevant data of the vibration sensor in real time based on the display terminal integrated in the data acquisition gateway.

[0078] Specifically, before displaying the data on the display, the LORA module on the data acquisition gateway is responsible for decoding and parsing the received data packets, restoring them to the original sensor data, and performing verification and validation to ensure data accuracy.

[0079] In this embodiment, the relevant data includes: acceleration values, velocity values, displacement values ​​and frequency spectrum of each axis of the vibration sensor.

[0080] Specifically, the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in a corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in a corresponding time period.

[0081] Furthermore, the vibration data is time domain data, combined with Figure 3 As shown, the acquisition of the spectrum diagram includes:

[0082] Step S103.20, denoising the time domain data.

[0083] Step S103.22: convert the denoised time domain data into frequency domain data based on the FFT algorithm, and calculate the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies.

[0084] Step S103.22, draw the spectrum diagram with the frequency as the horizontal axis and the vibration amplitude as the vertical axis.

[0085] Step S103.4: When it is determined that the relevant data shows abnormality, an early warning message is sent to the maintenance terminal.

[0086] In this step, the warning information includes: abnormal data, abnormal time period and abnormal data source.

[0087] At this time, the relevant data of the vibration sensor can be monitored in real time based on steps S103.2 to S103.4, on the one hand, to ensure the stable operation of the equipment, and on the other hand, to ensure the validity of the vibration data.

[0088] Step S104: When it is determined that the preset verification cycle has been reached, a section of vibration data with a preset length of time from the current time point is input into the pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding time period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding time period.

[0089] In this embodiment, the verification cycle is 1 hour, that is, a period of vibration data traced back 1 hour from the current time point is input into the corresponding neural network model.

[0090] Specifically, the LSTM neural network model is used to predict the equipment working time. Vibration signal data usually contains complex time dependencies, and the LSTM neural network model can effectively capture and process long-term time dependencies. The LSTM neural network has memory units that can effectively remember and utilize historical information in vibration signal data; this enables the LSTM neural network to better understand the patterns and laws in the vibration signal data, thereby improving the ability to predict the equipment running time.

[0091] For the equipment energy consumption rate, a CNN neural network model is used for prediction. The CNN convolutional neural network in this embodiment is composed of an input layer, a convolution layer, a batch normalization layer, an activation layer, a discard layer, and a fully connected layer. Among them, during the training process of the CNN neural network model, the activation layer uses a ReLU activation function to increase the nonlinearity of the network. After extracting the deep features of the data through the convolution layer, the risk of overfitting is reduced through the discard layer. The fully connected layer performs a weighted operation on the input features, maps the features to the sample label space, and compares them with the true value for iterative training.

[0092] At the same time, the gradient is back-propagated to update the parameters. The corresponding loss function is:

[0093]

[0094] Among them, x i is the predicted value, y i is the true value, and N is the number of samples.

[0095] As a specific implementation method, Figure 4 As shown, each vibration data is input into the corresponding neural network model in the following way:

[0096] Step S104.2: Acquire sensor data based on the pre-deployed data acquisition gateway, and simultaneously acquire a verification code corresponding to the sensor data.

[0097] In this embodiment, the sensor data includes the vibration data, the current data and the voltage data; and is compressed data compressed by the LORA module of each corresponding sensor data acquisition end.

[0098] Step S104.4: decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data.

[0099] Step S104.6: After the standard sensor data is packaged in JSON format, the standard sensor data is sent to the cloud platform based on the MQTT protocol and then decompressed and stored.

[0100] In this embodiment, a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection.

[0101] Step S104.8: When it is determined that the preset verification cycle has been reached, the standard vibration data in the standard sensor data of the corresponding time period is analyzed and sent to the LSTM neural network model and the CNN neural network model.

[0102] At this time, based on steps S104.2 to S104.8, this embodiment introduces a data acquisition gateway and a cloud platform in the data transmission process, thereby ensuring the effective transmission and storage of massive data, and ensuring the smooth progress of the model prediction at this time.

[0103] Step S106 , calculating arithmetic averages based on the voltage data and the current data in the corresponding time period to obtain average voltage data and average current data.

[0104] Step S108: input the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding time period.

[0105] In this embodiment, the carbon emission activity level calculation formula is:

[0106] Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor. Among them, P = U × I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

[0107] As a further embodiment, in combination Figure 5 As shown, the verification results are processed in the following way:

[0108] Step S110.2: When it is determined that the carbon emission activity level in any time period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is less than the first emission difference, or when the total carbon emission activity level in several consecutive time periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is less than the second emission difference; send the first excess information to the enterprise end.

[0109] Step S110.4: When it is determined that the carbon emission activity level in any time period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is greater than the second emission difference, or when the total carbon emission activity level for several consecutive time periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is greater than the second emission difference; send the second excess information to the enterprise end and the verification end.

[0110] Specifically, the first out-of-specification information is used to remind the enterprise to optimize relevant production parameters, and the second out-of-specification information is used to require the enterprise to suspend relevant production within a preset downtime period; the first out-of-specification information and the second out-of-specification information both include: out-of-specification equipment, out-of-specification time period and out-of-specification carbon emission activity level.

[0111] At this time, based on steps S110.2 to S110.4, the verification results can be classified and processed, thereby improving the feasibility of the verification process.

[0112] In summary, the method described in this embodiment has the following technical advantages: (1) Vibration data is used to predict the equipment operation time and energy consumption rate of the production process in real time. At the same time, enterprises can use vibration data to promptly discover and solve potential faults or problems, thereby improving the reliability and operating efficiency of the equipment. (2) The collection of vibration data is a non-invasive method that does not require any physical changes to the production equipment. This makes the acquisition of vibration data relatively simple and does not affect the normal operation of the equipment. (3) The vibration signal measurement method can infer the working status and energy consumption rate of the production equipment by analyzing the characteristic parameters such as the frequency and amplitude of the vibration signal. Through precise signal processing and algorithm optimization, a more accurate calculation of the carbon emission activity level can be achieved. (4) The vibration signal measurement method is applicable to various types of industrial equipment and can measure the carbon emission levels of different types of equipment, such as ball mills, vibrating screens, and hydraulic presses. Whether in the fields of industry, metallurgy, mining, chemical industry, or in the transportation, logistics and other industries, the vibration signal measurement method can be used to monitor and control the carbon emission activity level of equipment.

[0113] The above program can be run in the processor, or it can be stored in the memory (or computer-readable storage medium), which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include temporary computer-readable media, such as modulated data signals and carrier waves.

[0114] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes can be implemented by different modules corresponding to different steps.

[0115] Based on this, this embodiment also provides a carbon emission activity level verification device based on Internet of Things technology. Figure 6 As shown, the device comprises:

[0116] The monitoring module is used to monitor the vibration data of the equipment based on the non-invasively deployed vibration sensor, and to monitor the voltage data and current data of the equipment based on the pre-deployed voltage sensor and current sensor.

[0117] Among them, the vibration sensor is deployed at a position in the equipment that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the equipment; the voltage sensor and the current sensor are both deployed on the power supply circuit of the equipment drive motor, and the voltage data and the current data are both input end data.

[0118] The prediction module is used to determine when the preset verification cycle has arrived, and input a section of vibration data of a preset time length from the current time point into the pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding period; at the same time, the vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period.

[0119] Among them, the LSTM neural network model is used to extract the long-term time dependency in the vibration data. During the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, the deep features of the input are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training.

[0120] The calculation module is used to calculate the arithmetic mean values ​​based on the voltage data and the current data in the corresponding time period to obtain the average voltage data and the average current data.

[0121] The verification module is used to input the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into the carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding time period.

[0122] Among them, the carbon emission activity level calculation formula is: Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor; where P=U×I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

[0123] The device is used to implement the steps of the above method, so what has been described has not been repeated here.

[0124] For example, the prediction module specifically includes:

[0125] An acquisition unit, used to acquire sensor data based on a pre-deployed data acquisition gateway, and at the same time acquire a check code corresponding to the sensor data; wherein the sensor data includes the vibration data, the current data and the voltage data, and is compressed data compressed by the LORA module of each corresponding sensor data acquisition terminal;

[0126] A processing unit is used to decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data;

[0127] A storage unit, used for packaging the standard sensor data in JSON format, sending the standard sensor data to the cloud platform based on the MQTT protocol, and then decompressing and storing the data; wherein a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection;

[0128] The sending unit is used to determine when a preset verification cycle has been reached, parse the standard vibration data in the standard sensor data of the corresponding time period, and send the data to the LSTM neural network model and the CNN neural network model.

[0129] For another example, the device further includes:

[0130] The display module is used to display the relevant data of the vibration sensor in real time based on the display terminal integrated on the data acquisition gateway.

[0131] Among them, the relevant data include: acceleration value, velocity value, displacement value and spectrum diagram of each axis of the vibration sensor; the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in the corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in the corresponding time period.

[0132] The vibration data is time domain data, and the acquisition of the spectrum diagram includes: first, denoising the time domain data, then converting the denoised time domain data into frequency domain data based on the FFT algorithm, and calculating the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies; finally, drawing the spectrum diagram with frequency as the horizontal axis and vibration amplitude as the vertical axis.

[0133] The abnormality processing module is used to send an early warning message to the maintenance end when it is determined that the relevant data shows an abnormality; wherein the early warning message includes: abnormal data, abnormal time period and abnormal data source.

[0134] Combination Figure 7 As shown, this embodiment further provides an electronic device, comprising at least one processor, the processor being coupled to a memory, the memory storing a computer program, and the computer program being configured to execute the method when being executed by the processor.

[0135] Meanwhile, this embodiment also provides a computer-readable storage medium, on which a computer program is stored, and the computer program is used to execute the method described.

[0136] Since the device, electronic device and storage medium are all constructed based on the method, they also have the technical advantage of convenient and reliable acquisition of carbon emission activity levels during actual operation.

[0137] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. A method for verifying carbon emission activity levels based on Internet of Things technology, characterized in that: include: Vibration data of the equipment is monitored based on non-invasively deployed vibration sensors, and voltage data and current data of the equipment are monitored based on pre-deployed voltage sensors and current sensors; The vibration sensor is deployed at a position in the device that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the device; the voltage sensor and the current sensor are both deployed on the power supply circuit of the device drive motor, and the voltage data and the current data are both input end data; When it is determined that the preset verification cycle has been reached, a section of vibration data from the current time point with a preset length of time is input into the pre-trained LSTM neural network model based on the Internet of Things technology to obtain the predicted equipment working time of the corresponding period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period; The LSTM neural network model is used to extract the long-term time dependency in the vibration data. In the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, the deep features of the input are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training; Calculate the arithmetic mean values ​​based on the voltage data and the current data in the corresponding time period to obtain the average voltage data and the average current data; Inputting the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding period; Among them, the carbon emission activity level calculation formula is: Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor; where P=U×I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

2. The carbon emission activity level verification method based on Internet of Things technology according to claim 1 is characterized in that: When the judgment reaches the preset verification cycle, based on the Internet of Things technology, a period of vibration data traced back to a preset time from the current time point is input into a pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding period; At the same time, the vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate for the corresponding period; including: Acquire sensor data based on a pre-deployed data acquisition gateway, and simultaneously acquire a check code corresponding to the sensor data; wherein the sensor data includes the vibration data, the current data and the voltage data, and is compressed data compressed by the LORA module of each corresponding sensor data acquisition terminal; Decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data; After the standard sensor data is packaged in JSON format, the standard sensor data is sent to the cloud platform based on the MQTT protocol and then decompressed and stored; wherein a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection; When it is determined that the preset verification cycle has been reached, the standard vibration data in the standard sensor data of the corresponding time period is analyzed and sent to the LSTM neural network model and the CNN neural network model.

3. The carbon emission activity level verification method based on Internet of Things technology according to claim 1 is characterized in that: The vibration sensor based on non-invasive deployment monitors the vibration data of the equipment; comprising: Real-time display of relevant data of vibration sensors based on the display terminal integrated in the data acquisition gateway; The relevant data include: acceleration value, velocity value, displacement value and spectrum diagram of each axis of the vibration sensor; the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in the corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in the corresponding time period; The vibration data is time domain data, and the acquisition of the spectrum diagram includes: first, denoising the time domain data, then converting the denoised time domain data into frequency domain data based on the FFT algorithm, and calculating the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies; finally, drawing the spectrum diagram with the frequency as the horizontal axis and the vibration amplitude as the vertical axis; When it is determined that the relevant data shows an abnormality, an early warning message is sent to the maintenance end; wherein the early warning message includes: abnormal data, abnormal time period and abnormal data source.

4. The carbon emission activity level verification method based on Internet of Things technology according to claim 1 is characterized in that: The CNN neural network model is composed of an input layer, a convolutional layer, a batch normalization layer, an activation layer, a discard layer, and a fully connected layer in sequence, and performs gradient back propagation to update parameters; Among them, the corresponding loss function is: Among them, x i is the predicted value, y i is the true value, and N is the number of samples.

5. The carbon emission activity level verification method based on Internet of Things technology according to claim 1 is characterized in that: After simultaneously inputting the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into the carbon emission activity level calculation formula to obtain the carbon emission activity level of the corresponding period; comprising: When it is determined that the carbon emission activity level in any period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is less than the first emission difference, or when the total carbon emission activity level in a number of consecutive periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is less than the second emission difference; send the first over-regulation information to the enterprise end; When it is determined that the carbon emission activity level in any period exceeds the first emission activity level, and the difference between the carbon emission activity level and the first emission activity level is greater than the first emission difference, or when the total carbon emission activity level in a number of consecutive periods exceeds the second emission activity level, and the difference between the carbon emission activity level and the second emission activity level is greater than the second emission difference; send the second over-regulation information to the enterprise end and the verification end; Among them, the first out-of-specification information is used to remind the enterprise to optimize relevant production parameters, and the second out-of-specification information is used to require the enterprise to suspend relevant production within a preset downtime period; the first out-of-specification information and the second out-of-specification information both include: out-of-specification equipment, out-of-specification time period and out-of-specification carbon emission activity level.

6. A carbon emission activity level verification device based on Internet of Things technology, characterized in that: include: A monitoring module, used to monitor the vibration data of the equipment based on the non-invasively deployed vibration sensor, and to monitor the voltage data and current data of the equipment based on the pre-deployed voltage sensor and current sensor; The vibration sensor is deployed at a position in the device that operates stably and is easy to observe; the position is cleaned before installation to confirm that the sensing area of ​​the vibration sensor is flat and free of impurities, and the Z-axis direction of the vibration sensor is consistent with the main vibration direction of the device; the voltage sensor and the current sensor are both deployed on the power supply circuit of the device drive motor, and the voltage data and the current data are both input end data; The prediction module is used to determine when the preset verification cycle has arrived. Based on the Internet of Things technology, a section of vibration data traced back to a preset time from the current time point is input into the pre-trained LSTM neural network model to obtain the predicted equipment working time of the corresponding period; at the same time, the section of vibration data is input into the pre-trained CNN neural network model to obtain the predicted equipment energy consumption rate of the corresponding period; The LSTM neural network model is used to extract the long-term time dependency in the vibration data. In the training process of the CNN neural network model, the deep features of the vibration data are extracted through the convolution layer, the risk of overfitting is reduced through the discard layer, the deep features of the input are weighted through the fully connected layer, and the features are mapped to the sample label space for comparison with the true value for iterative training; A calculation module, used for respectively calculating arithmetic averages based on the voltage data and the current data in the corresponding time period to obtain average voltage data and average current data; A verification module, used to input the equipment working time, the equipment energy consumption rate, the average voltage data and the average current data into a carbon emission activity level calculation formula at the same time to obtain the carbon emission activity level of the corresponding period; Among them, the carbon emission activity level calculation formula is: Where P is the electrical power, is the equipment energy consumption rate, t is the equipment working time, and k is the carbon emission factor; where P=U×I, U is the average voltage data, I is the average current data, and the carbon emission factor is determined based on the energy structure and power generation method of the area where the equipment is located.

7. The carbon emission activity level verification device based on Internet of Things technology according to claim 6 is characterized in that: The prediction module comprises: An acquisition unit, used to acquire sensor data based on a pre-deployed data acquisition gateway, and at the same time acquire a check code corresponding to the sensor data; wherein the sensor data includes the vibration data, the current data and the voltage data, and is compressed data compressed by the LORA module of each corresponding sensor data acquisition terminal; A processing unit is used to decompress the sensor data based on the LORA module in the data acquisition gateway, and calculate and compare the verification code based on the single-chip microcomputer to perform data verification; thereby obtaining standard sensor data; A storage unit, used for packaging the standard sensor data in JSON format, sending the standard sensor data to the cloud platform based on the MQTT protocol, and then decompressing and storing the data; wherein a communication channel is established between the corresponding MQTT client and the MQTT proxy server of the cloud platform through a TCP connection; The sending unit is used to determine when a preset verification cycle has been reached, parse the standard vibration data in the standard sensor data of the corresponding time period, and send the data to the LSTM neural network model and the CNN neural network model.

8. The carbon emission activity level verification device based on Internet of Things technology according to claim 6 is characterized in that: include: A display module, used for displaying relevant data of the vibration sensor in real time based on a display terminal integrated on the data acquisition gateway; The relevant data include: acceleration value, velocity value, displacement value and spectrum diagram of each axis of the vibration sensor; the acceleration value is vibration data, the velocity value is obtained by calculating the definite integral of the acceleration value in the corresponding time period, and the displacement value is obtained by calculating the definite integral of the velocity value in the corresponding time period; The vibration data is time domain data, and the acquisition of the spectrum diagram includes: first, denoising the time domain data, then converting the denoised time domain data into frequency domain data based on the FFT algorithm, and calculating the amplitude value of each frequency point in the frequency domain data to obtain the energy distribution of the vibration data at different frequencies; finally, drawing the spectrum diagram with the frequency as the horizontal axis and the vibration amplitude as the vertical axis; The abnormality processing module is used to send an early warning message to the maintenance end when it is determined that the relevant data shows an abnormality; wherein the early warning message includes: abnormal data, abnormal time period and abnormal data source.

9. An electronic device, characterized in that: The method comprises at least one processor, wherein the processor is coupled to a memory, wherein a computer program is stored in the memory, and wherein the computer program is configured to execute the method according to any one of claims 1 to 5 when executed by the processor.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to execute the method according to any one of claims 1 to 5.

Images