Intelligent gas terminal energy-saving control internet of things system and method

Abstract

The application provides a kind of wisdom gas terminal energy-saving control Internet of Things system and method, it is related to Internet of Things technical field, this method is based on the wisdom gas management platform of wisdom gas terminal energy-saving control Internet of Things execution, including: by wisdom gas object platform obtains the gas use data and gas image data of target user;Based on gas use data, gas image data determines combustion state distribution;In response to the combustion state distribution meets preset condition, based on combustion state distribution determines energy-saving parameter;And based on energy-saving parameter determines energy-saving instruction and driven adjustment instruction, to adjust the valve opening of valve control device based on energy-saving instruction and driven adjustment instruction.The combustion state is evaluated, and the energy-saving parameter is adjusted according to the state of combustion, so as to appropriately reduce the gas flow rate, in the case of ensuring that the provided gas flow rate meets the user demand, the effect of energy saving and environmental protection is achieved.

Description

Technical Field

[0001] This specification relates to the field of Internet of Things (IoT) technology, and in particular to an IoT system and method for energy-saving control of a smart gas terminal. Background Technology

[0002] With the development of society and the economy, the application of combustible gases such as natural gas, which are non-renewable energy sources, in people's lives and industrial production is becoming increasingly widespread, and consumption is increasing year by year. While meeting human production and living needs, how to carry out energy-saving management of gas has become an urgent problem to be solved in current gas operations. Due to the differences in gas pipelines, gas-using equipment, and environment among different gas end users, different combustion usage conditions exist. Therefore, energy-saving management of gas requires the formulation of corresponding energy-saving measures and management strategies based on specific circumstances.

[0003] Therefore, it is desirable to provide an intelligent gas terminal energy-saving control IoT system and method, which can help to formulate corresponding gas energy-saving measures and management strategies based on gas combustion. Summary of the Invention

[0004] The invention includes an IoT system for energy-saving control of a smart gas terminal, comprising a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform connected in sequence. The smart gas object platform includes a monitoring sensor and an image acquisition device, both located at the gas terminal. The monitoring sensor is configured to acquire gas usage data of the target user, and the image acquisition device is configured to acquire gas image data of the target user. The smart gas management platform is configured to: acquire the gas usage data and gas image data of the target user through the smart gas object platform; determine the combustion state distribution based on the gas usage data and gas image data; determine energy-saving parameters based on the combustion state distribution in response to preset conditions; and determine energy-saving commands and passive adjustment commands based on the energy-saving parameters, thereby adjusting the valve opening of the valve control device based on the energy-saving commands and passive adjustment commands.

[0005] The invention includes an energy-saving control method for a smart gas terminal, executed by a smart gas management platform, comprising: acquiring gas usage data and gas image data of a target user through a smart gas object platform; determining a combustion state distribution based on the gas usage data and gas image data; determining energy-saving parameters based on the combustion state distribution in response to the combustion state distribution meeting preset conditions; and determining energy-saving instructions and passive adjustment instructions based on the energy-saving parameters, so as to adjust the valve opening of the valve control device based on the energy-saving instructions and passive adjustment instructions.

[0006] Beneficial effects: By evaluating the combustion state and adjusting energy-saving parameters accordingly, the gas flow rate can be appropriately reduced, achieving energy-saving and environmental protection effects while ensuring that the provided gas flow rate meets user needs. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is an exemplary structural diagram of an intelligent gas terminal energy-saving control Internet of Things system according to some embodiments of this specification;

[0009] Figure 2 This is an exemplary flowchart of a method for energy-saving control of a smart gas terminal according to some embodiments of this specification;

[0010] Figure 3 These are exemplary schematic diagrams of state prediction models according to some embodiments of this specification;

[0011] Figure 4 This is an exemplary flowchart illustrating the determination of energy-saving parameters according to some embodiments of this specification. Detailed Implementation

[0012] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0013] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0014] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0016] Figure 1 This is an exemplary structural diagram of an intelligent gas terminal energy-saving control Internet of Things system according to some embodiments of this specification. For example... Figure 1 As shown, the smart gas terminal energy-saving control IoT system 100 includes a smart gas user platform 110, a smart gas service platform 120, a smart gas management platform 130, a smart gas sensor network platform 140, and a smart gas object platform 150. The smart gas object platform 150 includes a monitoring sensor and an image acquisition device, which are installed at the gas terminal.

[0017] The smart gas user platform 110 is an interactive platform directly facing end users. In some embodiments, the smart gas user platform 110 can obtain gas information from the smart gas service platform 120 and display it to the user, such as displaying gas equipment status, gas usage data, and warning information. In some embodiments, the smart gas user platform 110 can also receive user feedback information and send it to the smart gas service platform 120, such as online warranty requests, complaints, suggestions, and service applications. The smart gas user platform 110 and the smart gas service platform 120 are communicatively connected.

[0018] In some embodiments, the smart gas user platform 110 may include at least one user interaction device, such as a mobile phone or computer.

[0019] The smart gas service platform 120 refers to a platform used for receiving and transmitting data and / or information. In some embodiments, the smart gas service platform 120 may be configured as a device such as a communication network or gateway. In some embodiments, the smart gas service platform 120 may engage in bidirectional data interaction with the smart gas user platform 110 and the smart gas management platform 130.

[0020] For example, the smart gas service platform 120 can obtain information such as gas usage data and user feedback data from the smart gas user platform 110. In some embodiments, the smart gas service platform 120 can upload the collected data and other information to the smart gas management platform 130.

[0021] The intelligent gas management platform 130 is a comprehensive management platform that manages and coordinates the connections and collaboration between multiple platforms. Gas companies can use the intelligent gas management platform 130 to digitally monitor and manage gas operations across the entire region. In some embodiments, the intelligent gas management platform 130 can coordinate the connections and collaboration between various functional platforms, gather all information from the Internet of Things, and generate and execute instructions by analyzing and processing the data and information generated during gas operations.

[0022] In some embodiments, the intelligent gas management platform 130 may be configured in a processor and / or server. The processor and / or server may process data and / or information acquired from other platforms. Based on this data, information, and / or processing results, the processor and / or server may execute program instructions to perform one or more functions described in this application.

[0023] The intelligent gas sensor network platform 140 refers to a communication transmission platform that enables bidirectional data interaction between various functional platforms managed by a gas company. The intelligent gas sensor network platform 140 can be configured as a communication device and / or a server.

[0024] In some embodiments, the smart gas sensor network platform 140 can connect to the smart gas management platform 130 and the smart gas object platform 150 to realize the functions of sensing and communication of perception information and sensing and communication of control information.

[0025] The intelligent gas object platform 150 can be a functional platform for generating sensing information. In some embodiments, the intelligent gas object platform 150 can be configured as various sensing devices. For example, the intelligent gas object platform 150 may include monitoring sensing devices, image acquisition devices, sound acquisition devices, gas sampling devices, etc.

[0026] In some embodiments, the smart gas object platform 150 can interact with the smart gas sensor network platform 140. For example, the smart gas object platform 150 can obtain gas operation-related data from gas terminals and upload it to the smart gas management platform 130 via the smart gas sensor network platform 140.

[0027] A gas terminal refers to the terminal equipment used by a user to consume gas. For example, a gas terminal may include a food processing boiler, a metallurgical blast furnace, or a chemical reaction vessel. In some embodiments, the gas terminal may be equipped with monitoring sensors, image acquisition devices, sound acquisition devices, gas sampling devices, etc.

[0028] A monitoring sensor device refers to a sensing device used to monitor / detect the status of gas usage. For example, a monitoring sensor device may include a gas flow meter, a thermometer, a gas detector, etc. In some embodiments, the monitoring sensor device can be used to acquire gas usage data. This gas usage data may include gas flow rate, gas velocity, gas pressure, and gas consumption during the user's usage period.

[0029] An image acquisition device refers to a sensing device used to monitor / detect the combustion state of gas. For example, an image acquisition device may include an optical gas thermal imager. In some embodiments, the image acquisition device can be used to acquire gas image data. This gas image data may include images of the combustion flame, thermal images, etc., during the period when the user is using the gas.

[0030] A sound acquisition device refers to a sensing device used to monitor / detect the sound of gas combustion. For example, a sound acquisition device may include a microphone, an audio analyzer, etc. In some embodiments, the sound acquisition device can be used to acquire gas sound data. This gas sound data may include irregular sounds produced by the combustion of impurities in the gas, or backfire sounds caused by incomplete combustion of the gas, etc.

[0031] A gas sampling device is a sensing device used to detect the composition of gas in gas. For example, a gas sampling device may include a gas analyzer, a gas detector, etc. In some embodiments, the gas sampling device can be used to obtain the composition of gas before and after combustion. The gas composition may include CH4, CO, CO2, etc.

[0032] For more information on gas usage data, gas image data, gas sound data, and gas composition, please refer to [link / reference]. Figures 2-4 The corresponding content. Figure 2 This is an exemplary flowchart of a smart gas terminal energy-saving control method according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by a smart gas management platform.

[0033] Step 210: Obtain gas usage data and gas image data of the target user through the smart gas object platform.

[0034] In some embodiments, the smart gas management platform can acquire gas usage data and gas image data of target users through a smart gas object platform, using monitoring sensors and image acquisition devices, respectively. Target users refer to users who consume gas. For example, target users include enterprises, institutions, and households that consume gas.

[0035] Step 220: Determine the combustion state distribution based on gas usage data and gas image data.

[0036] Gas state distribution can characterize the degree of incomplete combustion of gas. In some embodiments, gas state distribution may include gas impurity content and incomplete combustion value. For example, gas impurity content may include the content of CO2, dust, water, etc. When gas undergoes incomplete combustion, CO is generated along with CO2. The incomplete combustion value refers to the mass percentage of CO in the substances generated after incomplete combustion of gas. For example, incomplete combustion value = CO content / (CO content + CO2 content).

[0037] In some embodiments, the intelligent gas management platform can construct a matching vector based on gas usage data and gas image data. Based on this matching vector, a search is performed in a vector database to obtain the reference vector with the smallest vector distance to the matching vector, which is then used as the target vector. The vector database stores several reference vectors and their corresponding combustion state distributions. The intelligent gas management platform determines the combustion state distribution corresponding to the target vector as the currently required combustion state distribution. This combustion state distribution is obtained based on practical experience and historical data. The reference vectors are constructed based on historical gas usage data and historical gas image data.

[0038] For more information on determining the combustion state distribution, see [link to documentation]. Figure 3 The corresponding content.

[0039] Step 230: In response to the combustion state distribution meeting the preset conditions, determine the energy-saving parameters based on the combustion state distribution.

[0040] The preset conditions may include a combustion incompleteness value greater than a combustion completeness threshold. The combustion completeness threshold refers to a preset value for complete combustion of the fuel gas. For example, the higher the impurity content of the fuel gas, the lower the combustion completeness threshold.

[0041] Energy-saving parameters refer to the target gas flow rate set for adjacent pipelines at the gas-consuming terminal to achieve energy savings. Adjacent pipelines are those that directly supply gas to the target user.

[0042] In some embodiments, the energy-saving parameters can be adjusted based on incomplete combustion values ​​and combustion completeness thresholds. For example, the energy-saving parameters can be obtained based on the following formula (1):

[0043] (1)

[0044] in, This indicates energy-saving parameters (i.e., the gas flow rate in adjacent pipes). This indicates the current flow rate of the gas in the adjacent pipe. 'b' represents the completeness threshold, and 'b' represents the incomplete combustion value.

[0045] For more information on determining energy-saving parameters, please see [link / reference]. Figure 4 The corresponding content.

[0046] Step 240: Determine energy-saving instructions and passive adjustment instructions based on energy-saving parameters, and adjust the valve opening of the valve control device based on the energy-saving instructions and passive adjustment instructions.

[0047] An energy-saving instruction is an instruction to regulate the gas flow rate in an adjacent pipeline. In some embodiments, an energy-saving instruction may include an instruction to regulate the valve opening of at least one valve control device (hereinafter referred to as the target valve) in an adjacent pipeline.

[0048] A passive regulation command is an instruction to regulate the gas flow rate in an upstream pipeline (hereinafter referred to as an auxiliary pipeline) adjacent to the main pipeline. The gas flow direction is from the auxiliary pipeline to the adjacent pipeline. A passive regulation command may include an instruction to adjust the valve opening of at least one valve control device (hereinafter referred to as an auxiliary valve) in the auxiliary pipeline. In some embodiments, the passive regulation command may include step-value regulation or linear slow regulation to reduce the amplitude of gas flow rate changes in the pipeline network, thereby ensuring the flow rate stability of the entire gas pipeline network.

[0049] A valve control device refers to a valve device that regulates the flow rate of gas in a pipeline, and can include electric control valves, pneumatic control valves, etc. Valve opening degree refers to the extent to which the valve control device is open.

[0050] In some embodiments, the intelligent gas management platform can determine the valve opening of a target valve based on energy-saving parameters by querying a preset table. The preset table may include the correspondence between the gas flow rate in adjacent pipelines and the valve opening of the target valve. In some embodiments, the preset table can be obtained experimentally or set manually.

[0051] In some embodiments, the driven adjustment command can be determined based on energy-saving parameters and the distance between the auxiliary valve and the target valve. For example, the change in the opening of the auxiliary valve in the auxiliary pipeline can be obtained based on the following formula (2):

[0052] (2)

[0053] in, B This indicates the range of change in the opening degree of the auxiliary valve. This indicates the current opening degree of the auxiliary valve. The valve opening degree of the target valve after executing the energy-saving command. This indicates the valve opening degree before the target valve executes the energy-saving command. D This indicates the distance between the auxiliary valve and the target valve.

[0054] After determining the change range of the opening of each auxiliary valve, the intelligent gas management platform can determine the adjusted valve opening of each auxiliary valve in the driven adjustment command based on the current opening of each auxiliary valve and its change range. For example, the adjusted valve opening = the current opening of the auxiliary valve + the change range of the auxiliary valve opening. A negative change range in the opening of an auxiliary valve indicates that its opening needs to be reduced to decrease the gas flow rate.

[0055] In some embodiments of this specification, by evaluating the combustion state and adjusting the energy-saving parameters according to the combustion state, the gas flow rate is appropriately reduced, thereby achieving energy-saving and environmental protection effects while ensuring that the provided gas flow rate meets the user's needs.

[0056] Figure 3 This is an exemplary schematic diagram of a state prediction model according to some embodiments of this specification.

[0057] In some embodiments, such as Figure 3 As shown, the intelligent gas management platform determines the combustion state distribution 330 based on gas usage data 311, gas image data 312, and gas sound data 313 through a state prediction model 320.

[0058] For more information on gas usage data, gas image data, and combustion status distribution, please refer to [link / reference]. Figure 2 And related explanations.

[0059] A state prediction model is a model used to predict the distribution of combustion states. In some embodiments, the state prediction model is a machine learning model, such as a neural network (NN) model.

[0060] The inputs to the state prediction model include gas usage data, gas image data, and gas sound data, while the output of the state prediction model includes the combustion state distribution.

[0061] Gas sound data refers to data related to the sound during the gas combustion process. In some embodiments, the smart gas management platform acquires the gas sound data of a target user through a sound acquisition device.

[0062] In some embodiments, the smart gas management platform trains a state prediction model based on a first sample dataset. The first sample dataset includes multiple first training samples with first labels. The smart gas management platform can input these multiple first training samples into the initial state prediction model, construct a loss function based on the output of the initial state prediction model and the first labels, iteratively update the parameters of the initial state prediction model based on the loss function, and terminate the iteration when the iteration completion condition is met, thus obtaining the trained state prediction model. The iterative update method includes, but is not limited to, gradient descent. The iteration completion condition includes the convergence of the loss function or the number of iterations reaching a threshold.

[0063] The first training sample includes sample gas usage data, sample gas image data, and sample gas sound data of the target user. The first training sample can be obtained based on historical data.

[0064] The first label includes the actual combustion state distribution corresponding to the target users of the sample. In some embodiments, some target users (e.g., industrial users, commercial users, and some residential users) are equipped with gas sampling devices. The smart gas management platform uses the gas sampling devices to detect the gas before combustion to obtain the gas impurity content, and to detect the gas produced after combustion to obtain the composition of the post-combustion gas. Based on the composition of the post-combustion gas, the incomplete combustion value is calculated. The gas impurity content and the incomplete combustion value are combined to obtain the actual combustion state distribution corresponding to the target users.

[0065] For more information on gas sampling devices, please see [link / reference]. Figure 1 And related explanations. For more information on fuel gas impurity content and incomplete combustion values, please refer to [link / reference]. Figure 2 And related explanations.

[0066] In some embodiments, for target users who have not installed gas sampling devices, the smart gas management platform samples and tests the gas delivered to the gas terminal to obtain the gas impurity content, conducts a combustion experiment on the sampled gas to obtain the composition of the gas after combustion, calculates the incomplete combustion value based on the composition of the gas after combustion, and combines the gas impurity content and the incomplete combustion value to obtain the actual combustion state distribution corresponding to the target user.

[0067] Some embodiments in this specification determine the combustion state distribution through a state prediction model, which can process and analyze large amounts of data in real time and quickly and accurately determine the combustion state distribution of the target user.

[0068] In some embodiments, such as Figure 3As shown, the state prediction model 320 includes a feature extraction layer 321, a first prediction layer 322, a second prediction layer 323, and a correction layer 324. In some embodiments, the feature extraction layer 321, the first prediction layer 322, the second prediction layer 323, and the correction layer 324 are all machine learning models, for example, the feature extraction layer 321, the first prediction layer 322, the second prediction layer 323, and the correction layer 324 are all neural network (NN) models, etc.

[0069] In some embodiments, the feature extraction layer 321 determines gas usage features 3211 based on gas usage data 311. The first prediction layer 322 determines a first state distribution 3221 based on the gas usage features 3211 and gas image data 312. The second prediction layer 323 determines a second state distribution 3231 based on the gas usage features 3211 and gas sound data 313. The correction layer determines a combustion state distribution 330 based on the gas usage features 3211, the first state distribution 3221, and the second state distribution 3231.

[0070] The feature extraction layer is used to extract gas usage features from gas usage data.

[0071] Gas usage characteristics refer to features related to a target user's gas usage. For example, gas usage characteristics include gas usage time and gas consumption.

[0072] The first prediction layer is used to determine the first state distribution based on gas usage characteristics and gas image data.

[0073] The first state distribution refers to the combustion state distribution predicted based on gas image data.

[0074] The second prediction layer is used to determine the second state distribution based on gas usage characteristics and gas sound data.

[0075] The second state distribution refers to the combustion state distribution predicted based on gas sound data.

[0076] The correction layer is used to correct the first state distribution and the second state distribution to obtain the final combustion state distribution.

[0077] In some embodiments, the state prediction model is trained based on a first sample dataset, which includes multiple first training samples and multiple first labels corresponding to the first training samples. The first sample dataset is obtained based on a first database, a second database, and a third database.

[0078] In some embodiments, the smart gas management platform divides historical data into a first database, a second database, and a third database based on the types of data that can be collected from different target users.

[0079] The first database includes gas usage data, gas image data, and actual combustion state distribution of the target users. The first training sample constructed based on the first database includes sample gas usage data and sample gas image data of the target users, and the first label is the actual combustion state distribution of the target users.

[0080] The second database includes gas usage data, gas sound data, and actual combustion status distribution of the target users. The first training sample constructed based on the second database includes sample gas usage data and sample gas sound data of the target users, with the first label being the actual combustion status distribution of the target users.

[0081] The third database includes gas usage data, gas image data, gas sound data, and actual combustion state distribution of the target users. The first training sample constructed based on the third database includes sample gas usage data, sample gas image data, and sample gas sound data of the target users, with the first label being the actual combustion state distribution of the target users.

[0082] In some embodiments, the intelligent gas management platform jointly trains the feature extraction layer and the first prediction layer based on multiple first training samples with first labels constructed from a first database, thereby obtaining a trained first prediction layer. Specifically, the intelligent gas management platform inputs sample gas usage data into the initial feature extraction layer to obtain gas usage features output by the initial feature extraction layer. It then inputs the gas usage features and sample gas image data into the initial first prediction layer, constructs a loss function based on the output of the initial first prediction layer and the first labels, and iteratively updates the parameters of the initial first prediction layer based on the loss function. The iteration ends when the iteration completion condition is met, resulting in the trained first prediction layer. For more details on iterative updates, please refer to the above.

[0083] After the first prediction layer is trained, the smart gas management platform uses multiple first training samples with first labels built on the second database to jointly train the feature extraction layer and the second prediction layer using the method described above, thus obtaining the trained feature extraction layer and the second prediction layer.

[0084] After the feature extraction layer, the first prediction layer, and the second prediction layer are trained, the smart gas management platform uses multiple first training samples with first labels, constructed based on a third database, to train a correction layer. The smart gas management platform can input sample gas usage data into the feature extraction layer to obtain gas usage features output by the feature extraction layer. It can then input the gas usage features and sample gas image data into the first prediction layer to obtain the first state distribution output by the first prediction layer. Finally, it can input the gas usage data, the first state distribution, and the second state distribution into the initial correction layer. Based on the output of the initial correction layer and the first label, a loss function is constructed. The parameters of the initial correction layer are iteratively updated based on the loss function. The iteration ends when the iteration completion condition is met, resulting in the trained correction layer.

[0085] In some embodiments, the smart gas management platform, in response to the data volume of the first database and / or the second database being less than a data volume threshold, identifies a data-missing device; determines a hardware self-test instruction based on the data volume and the data volume threshold; sends the hardware self-test instruction to the data-missing device to obtain the self-test result; and, in response to the self-test result meeting preset maintenance conditions, generates a device maintenance instruction and sends it to the interactive device to arrange for personnel to maintain the data-missing device.

[0086] The data volume threshold is used to determine whether a data missing device exists. In some embodiments, the data volume threshold can be set based on historical experience. The data volume thresholds for the first database and the second database can be the same or different.

[0087] In some embodiments, the data volume threshold can also be determined based on the required model accuracy; the higher the model accuracy, the larger the data volume threshold.

[0088] A data-missing device is a device that cannot collect data normally. Examples include image acquisition devices and sound sensing devices that cannot collect data normally.

[0089] In some embodiments, in response to the data volume of the first database being less than a data volume threshold, the smart gas management platform identifies the image acquisition device that cannot collect gas image data in the first database as a data missing device. Similarly, in response to the data volume of the second database being less than a data volume threshold, the smart gas management platform identifies the sound acquisition device that cannot collect gas sound data in the second database as a data missing device.

[0090] Hardware self-test commands are instructions used to control devices to perform self-tests. Hardware self-test commands include commands for devices that require self-testing.

[0091] In some embodiments, the smart gas management platform can randomly select a portion of the devices with missing data from all devices with missing data for self-testing.

[0092] In some embodiments, the number of data missing devices requiring self-checking is related to the data volume and data volume threshold of the corresponding database. The smaller the difference between the data volume threshold and the data volume, and the larger the data volume threshold, the fewer data missing devices require self-checking. In some embodiments, the smart gas management platform can calculate the number of data missing devices requiring self-checking for each database using the following formula (3).

[0093] (3)

[0094] in, This represents the number of data missing devices that require self-testing. For data volume threshold, For data volume, Coefficient and .

[0095] In some embodiments, It is related to the time interval between the current moment and the last self-check. The larger the time interval, the better. The larger.

[0096] The self-test result refers to the result of the device performing a self-test. The self-test result includes abnormal function, normal function but not enabled, and normal function enabled.

[0097] In some embodiments, the data loss device responds to receiving a hardware self-test command by performing a self-test according to an internally stored self-test program and obtaining a self-test result.

[0098] In some embodiments, the sound acquisition device includes a sound-emitting component, a data acquisition component, and a microprocessor component. In response to receiving a hardware self-test command, the sound acquisition device generates a test sound wave through the sound-emitting component and simultaneously acquires ambient sound wave data through the data acquisition component. The microprocessor component matches the ambient sound wave data with standard sound wave data to obtain matching information, which is then sent to the smart gas management platform. Based on the matching information, the smart gas management platform determines the self-test result of the sound acquisition device.

[0099] A sound-generating component is a component used to produce sound. For example, sound-generating components include electronic components such as loudspeakers.

[0100] In some embodiments, the sound-generating component is used to generate test sound waves, the frequency of which is close to the frequency of the sound produced when gas is burned.

[0101] A data acquisition component is a device used to convert sound signals into electrical signals. For example, data acquisition components include audio acquisition devices such as microphones.

[0102] Microprocessor components are used to process electrical signals. For example, microprocessor components include central processing units (CPUs) and digital signal processors (DSPs).

[0103] Ambient sound wave data refers to data related to the sound of the environment in which the sound acquisition device is located.

[0104] Matching information reflects the matching status between ambient sound wave data and standard sound wave data. For example, matching information includes the degree of matching between the ambient sound wave data and the standard sound wave data. In some embodiments, the microprocessor determines the degree of matching based on the similarity of the waveforms by comparing the waveforms of the ambient sound wave data and the standard sound wave data; the greater the similarity of the waveforms, the greater the degree of matching.

[0105] Standard acoustic wave data is acoustic wave data pre-stored in the microprocessor. In some embodiments, the microprocessor generates an electrical signal based on the standard acoustic wave data, and the sound-generating component converts the electrical signal into an audio signal, thereby generating a test acoustic wave.

[0106] In some embodiments, the smart gas management platform compares the matching information with a preset matching threshold. In response to a matching degree less than the preset matching threshold, the smart gas management platform determines the self-test result of the sound acquisition device corresponding to the matching information as a functional abnormality.

[0107] In some embodiments, the preset matching threshold is related to the flow rate of the adjacent pipe of the gas terminal corresponding to the matching information. The higher the flow rate of the adjacent pipe, the lower the preset matching threshold.

[0108] The higher the flow velocity in adjacent pipes, the greater the noise in the gas usage environment, which may interfere with the test sound waves. By appropriately reducing the preset matching threshold, the accuracy of determining the self-test results can be improved.

[0109] Preset maintenance conditions are used to determine whether the device needs maintenance. In some embodiments, the preset maintenance conditions are that the self-test result is a functional abnormality or no self-test result is received.

[0110] A maintenance instruction is an order used to schedule personnel to perform maintenance on equipment. Maintenance instructions include the equipment requiring maintenance.

[0111] In some embodiments, after the device is repaired, the smart gas management platform continuously acquires gas image data and / or gas sound data and stores them in the corresponding database.

[0112] In some embodiments of this specification, when the amount of data in the database is less than a data volume threshold, the device controlling the partial data missing performs a self-check, and the device is repaired based on the self-check results. This can increase the amount of data in the database, thereby improving the training effect of the state prediction model.

[0113] In some embodiments, the input to the correction layer further includes user features. The training process of the state prediction model includes: based on the user features corresponding to the first training sample in the first sample dataset, dividing the first sample dataset into a training set and a test set according to a preset rule; training and testing the initial state prediction model based on the training set and the test set to obtain the state prediction model, wherein the learning rate corresponding to each first training sample in the training set is related to the iteration round in which the first training sample is located and the subsequent energy saving magnitude.

[0114] User characteristics refer to features relevant to the target user. For example, user characteristics include user type and average gas consumption. User type includes residential users, commercial users, industrial users, and government users. Average gas consumption can be the target user's daily / weekly / monthly average gas consumption.

[0115] In some embodiments, the smart gas management platform obtains user types through the smart gas service platform and calculates the average gas consumption of the target user based on gas usage data.

[0116] In some embodiments, the smart gas management platform divides the average gas consumption into multiple ranges, combines the average gas consumption of multiple ranges with multiple user types to obtain multiple combination types, and classifies the data in the first sample dataset according to the combination types.

[0117] In some embodiments, the intelligent gas management platform divides the data of each combination type into a training set and a test set according to preset rules. The preset rules can be based on a preset ratio for data division, for example, a preset ratio of 7:3 for the training set and the test set.

[0118] In some embodiments, the intelligent gas management platform updates the model parameters of the initial state prediction model based on the training set, evaluates the performance indicators of the trained initial state prediction model based on the test set, and then determines the final model parameters of the state prediction model.

[0119] In some embodiments, the learning rate corresponding to each first training sample in the training set is negatively correlated with the iteration round in which the first training sample is located, and positively correlated with the subsequent energy saving magnitude.

[0120] The subsequent energy saving margin is used to evaluate the effect of energy-saving adjustment after the sampling time of the first training sample. In some embodiments, the intelligent gas management platform determines energy-saving parameters based on the actual combustion state distribution corresponding to the first training sample, and performs energy-saving adjustment based on the energy-saving parameters. The subsequent energy saving margin can be expressed as the ratio of the difference in average gas consumption before and after energy-saving adjustment to the average gas consumption before energy-saving adjustment.

[0121] In some embodiments described in this specification, the first sample dataset is divided into a training set and a test set based on user characteristics. The initial state prediction model is then trained and tested using the training and test sets, resulting in a more accurate state prediction model. By setting an appropriate learning rate, the convergence rate of the loss function can be improved, thereby enhancing the model training effect.

[0122] Due to hardware limitations, some target users may not be able to collect gas image data or gas sound data. Through the multi-layer design of the state prediction model, it is possible to accurately predict the distribution of combustion state even when data is missing, and the model has a wider range of applications.

[0123] Figure 4 This is an exemplary flowchart illustrating the determination of energy-saving parameters according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by a smart gas management platform.

[0124] Step 410: Determine candidate energy-saving parameters.

[0125] Candidate energy-saving parameters refer to the available energy-saving parameters. For more information on energy-saving parameters, please see [link to relevant documentation]. Figure 2 And related explanations.

[0126] In some embodiments, the intelligent gas management platform identifies the N most frequently used energy-saving parameters from historical data as candidate energy-saving parameters. N can be set based on experience.

[0127] In some embodiments, N is positively correlated with the accuracy of energy-saving regulation.

[0128] Step 420: Determine the estimated calorific value based on candidate energy-saving parameters and combustion state distribution.

[0129] The estimated calorific value refers to the estimated calorific value generated by gas combustion after adjustment according to the candidate energy-saving parameters.

[0130] In some embodiments, the smart gas management platform constructs a reference vector based on historical energy-saving parameters and historical combustion state distribution in historical data, determines the actual heat value after adjustment based on historical energy-saving parameters as the label corresponding to the reference vector, and constructs a reference vector library based on the reference vector and the corresponding label.

[0131] The intelligent gas management platform constructs a target vector based on candidate energy-saving parameters and combustion state distribution. It then searches a reference vector library to obtain the reference vector with the highest similarity to the target vector, and assigns the label corresponding to this reference vector as the estimated calorific value. The similarity can be determined based on vector distance, which includes, but is not limited to, Euclidean distance.

[0132] In some embodiments, the intelligent gas management platform determines the estimated calorific value based on candidate energy-saving parameters and combustion state distribution, using a calorific value prediction model.

[0133] A calorific value prediction model is a model used to determine an estimated calorific value. In some embodiments, the calorific value prediction model is a machine learning model, such as a neural network (NN) model.

[0134] The inputs to the calorific value prediction model include candidate energy-saving parameters and combustion state distribution, and the output of the calorific value prediction model is the estimated calorific value.

[0135] In some embodiments, the heat value prediction model is trained based on a second sample dataset, which includes multiple second training samples and multiple second labels corresponding to the second training samples.

[0136] The second training sample includes sample energy-saving parameters and sample combustion state distribution. The second training sample can be obtained based on historical data.

[0137] The second label represents the actual calorific value of the adjusted gas corresponding to the second training sample. In some embodiments, the smart gas management platform obtains the gas composition of the adjusted gas terminal through a gas sampling device, and calculates the actual calorific value by weighted summation based on the calorific value and proportion of each gas component.

[0138] For more information on gas sampling devices, please see [link / reference]. Figure 1 And related explanations.

[0139] The training process for the calorific value prediction model is similar to that for the state prediction model. For more details, please refer to [link / reference]. Figure 3 And related explanations.

[0140] In some embodiments of this specification, the actual calorific value is determined based on the actual collected gas composition, and the model is trained based on the actual calorific value, resulting in a more accurate calorific value prediction model.

[0141] Step 430: Determine the required calorie value based on user characteristics.

[0142] For more information on user characteristics, please see [link to relevant documentation]. Figure 3 And related explanations.

[0143] The required calorie value refers to the amount of calories needed by the target user.

[0144] In some embodiments, user characteristics further include a gas usage sequence for the target user. The gas usage sequence includes the time the target user uses gas and the corresponding gas consumption. The intelligent gas management platform calculates the gas consumption per unit time for the target user based on the gas usage sequence. Based on the gas consumption per unit time and the gas composition, it calculates the heat generated by the target user's gas usage per unit time and determines this heat as the required heat value.

[0145] In some embodiments, the required heat value is related to the gas consumption in the area where the target user is located during a preset time period.

[0146] In some embodiments, the smart gas management platform determines the gas consumption of a target user's area within a preset time period based on gas usage data.

[0147] In some embodiments, the greater the gas consumption in the area where the target user is located within a preset time period, the greater the required heat value.

[0148] In some embodiments of this specification, the user's required heat value is estimated based on the gas usage of other users near the user, and the obtained required heat value is closer to the actual situation.

[0149] Step 440: Based on the estimated heat value and the required heat value, determine the demand satisfaction of the candidate energy-saving parameters.

[0150] Demand satisfaction reflects the degree to which the estimated caloric value can meet the demand caloric value. In some embodiments, demand satisfaction is the ratio of the estimated caloric value to the demand caloric value.

[0151] Step 450: Determine energy-saving parameters based on demand satisfaction.

[0152] In some embodiments, in response to the existence of a demand satisfaction rate of not less than 100%, the smart gas management platform determines the candidate energy-saving parameter corresponding to the demand satisfaction rate closest to 100% among the demand satisfaction rates of not less than 100% as the final energy-saving parameter used. In response to the absence of a demand satisfaction rate of not less than 100%, the smart gas management platform determines the candidate energy-saving parameter corresponding to the demand satisfaction rate closest to 100% as the final energy-saving parameter used.

[0153] Some embodiments in this specification select appropriate energy-saving parameters based on the degree of demand satisfaction, which can maximize the satisfaction of user needs while saving energy and reducing emissions.

[0154] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0155] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0156] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0157] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0158] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0159] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0160] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart gas terminal energy-saving control Internet of Things system, characterized in that, The system includes a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform connected in sequence. The smart gas target platform includes a monitoring sensor, an image acquisition device, and a sound acquisition device. The monitoring sensor and the image acquisition device are installed at the gas terminal. The monitoring sensor is configured to acquire the gas usage data of the target user, the image acquisition device is configured to acquire the gas image data of the target user, and the sound acquisition device is configured to acquire the gas sound data of the target user. The intelligent gas management platform is configured as follows: The gas usage data and gas image data of the target user are obtained through the smart gas object platform; The combustion state distribution is determined based on the gas usage data and the gas image data. The combustion state distribution includes the gas impurity content and the incomplete combustion value. The incomplete combustion value refers to the mass percentage of CO in the substances generated after incomplete combustion of gas. In response to the combustion state distribution meeting preset conditions, energy-saving parameters are determined based on the combustion state distribution. The preset conditions include the incomplete combustion value being greater than the sufficiency threshold, and the sufficiency threshold being negatively correlated with the fuel gas impurity content. Based on the energy-saving parameters, energy-saving instructions and passive adjustment instructions are determined, and the valve opening of the valve control device is adjusted based on the energy-saving instructions and the passive adjustment instructions. The energy-saving instructions refer to instructions for adjusting the gas flow rate of adjacent pipelines, and the passive adjustment instructions refer to instructions for adjusting the gas flow rate of upstream pipelines of adjacent pipelines. The step of determining the combustion state distribution based on the gas usage data and the gas image data includes: Based on the gas usage data, gas image data, and gas sound data, the combustion state distribution is determined using a state prediction model. This state prediction model is a machine learning model and includes a feature extraction layer, a first prediction layer, a second prediction layer, and a correction layer. Each of these layers is a machine learning model. The feature extraction layer determines gas usage characteristics based on the gas usage data. The first prediction layer determines a first state distribution based on the gas usage characteristics and the gas image data. The second prediction layer determines a second state distribution based on the gas usage characteristics and the gas sound data. The correction layer determines a second state distribution based on the gas usage characteristics and the first prediction layer. The combustion state distribution is determined by a first state distribution, a second state distribution, and user characteristics, wherein the user characteristics include user type and average gas consumption; the training process of the state prediction model includes: based on the user characteristics corresponding to the first training sample in the first sample dataset, dividing the first sample dataset into a training set and a test set according to preset rules; training and testing the initial state prediction model based on the training set and the test set to obtain the state prediction model, wherein the learning rate corresponding to each first training sample in the training set is related to the iteration round in which the first training sample is located and the subsequent energy saving amplitude, wherein the subsequent energy saving amplitude refers to the ratio of the difference between the average gas consumption before and after energy saving adjustment to the average gas consumption before energy saving adjustment.

2. The system as described in claim 1, characterized in that, The intelligent gas management platform is further configured as follows: Determine candidate energy-saving parameters; Based on the candidate energy-saving parameters and the combustion state distribution, the estimated heat value is determined; Determine the required calorie value based on user characteristics; Based on the estimated heat value and the required heat value, the demand satisfaction level of the candidate energy-saving parameters is determined; and, The energy-saving parameters are determined based on the degree of demand satisfaction.

3. The system as described in claim 2, characterized in that, The intelligent gas management platform is further configured as follows: Based on the candidate energy-saving parameters and the combustion state distribution, the estimated calorific value is determined by a calorific value prediction model, which is a machine learning model.

4. A smart gas terminal energy-saving control method, characterized in that, The method is implemented based on the smart gas terminal energy-saving control Internet of Things system as described in claim 1. The system includes a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform connected in sequence. The smart gas target platform includes a monitoring sensor, an image acquisition device, and a sound acquisition device. The monitoring sensor and the image acquisition device are installed at the gas terminal. The monitoring sensor is configured to acquire the gas usage data of the target user, the image acquisition device is configured to acquire the gas image data of the target user, and the sound acquisition device is configured to acquire the gas sound data of the target user. The method is executed by the intelligent gas management platform and includes: The gas usage data and gas image data of the target user are obtained through the smart gas object platform; The combustion state distribution is determined based on the gas usage data and the gas image data. The combustion state distribution includes the gas impurity content and the incomplete combustion value. The incomplete combustion value refers to the mass percentage of CO in the substances generated after incomplete combustion of gas. In response to the combustion state distribution meeting preset conditions, energy-saving parameters are determined based on the combustion state distribution. The preset conditions include the incomplete combustion value being greater than the sufficiency threshold, and the sufficiency threshold being negatively correlated with the fuel gas impurity content. Based on the energy-saving parameters, energy-saving instructions and passive adjustment instructions are determined, and the valve opening of the valve control device is adjusted based on the energy-saving instructions and the passive adjustment instructions. The energy-saving instructions refer to instructions for adjusting the gas flow rate of adjacent pipelines, and the passive adjustment instructions refer to instructions for adjusting the gas flow rate of upstream pipelines of adjacent pipelines. The step of determining the combustion state distribution based on the gas usage data and the gas image data includes: Based on the gas usage data, gas image data, and gas sound data, the combustion state distribution is determined using a state prediction model. This state prediction model is a machine learning model and includes a feature extraction layer, a first prediction layer, a second prediction layer, and a correction layer. Each of these layers is a machine learning model. The feature extraction layer determines gas usage characteristics based on the gas usage data. The first prediction layer determines a first state distribution based on the gas usage characteristics and the gas image data. The second prediction layer determines a second state distribution based on the gas usage characteristics and the gas sound data. The correction layer determines a second state distribution based on the gas usage characteristics and the first prediction layer. The combustion state distribution is determined by a first state distribution, a second state distribution, and user characteristics, wherein the user characteristics include user type and average gas consumption; the training process of the state prediction model includes: based on the user characteristics corresponding to the first training sample in the first sample dataset, dividing the first sample dataset into a training set and a test set according to preset rules; training and testing the initial state prediction model based on the training set and the test set to obtain the state prediction model, wherein the learning rate corresponding to each first training sample in the training set is related to the iteration round in which the first training sample is located and the subsequent energy saving amplitude, wherein the subsequent energy saving amplitude refers to the ratio of the difference between the average gas consumption before and after energy saving adjustment to the average gas consumption before energy saving adjustment.

5. The method as described in claim 4, characterized in that, In response to the combustion state distribution satisfying preset conditions, energy-saving parameters are determined based on the combustion state distribution, including: Determine candidate energy-saving parameters; Based on the candidate energy-saving parameters and the combustion state distribution, the estimated heat value is determined; Determine the required calorie value based on user characteristics; Based on the estimated heat value and the required heat value, the demand satisfaction level of the candidate energy-saving parameters is determined; and, The energy-saving parameters are determined based on the degree of demand satisfaction.

6. The method as described in claim 5, characterized in that, The process of determining the estimated calorific value based on the candidate energy-saving parameters and the combustion state distribution includes: Based on the candidate energy-saving parameters and the combustion state distribution, the estimated calorific value is determined by a calorific value prediction model, which is a machine learning model.

Images