Method for measuring CO and O2 in hearth flue gas

Abstract

The invention belongs to the field of combustion process monitoring, and particularly discloses a hearth flue gas CO and O2 measuring method which comprises the following steps: S1, acquiring original signals of CO concentration data and O2 concentration data; s2, performing data preprocessing on the obtained original signals of the CO concentration data and the O2 concentration data to generate a standardized electric signal sequence; s3, calculating the concentration of CO and the concentration of O2 through the standardized electric signal sequence; s4, acquiring environment temperature, humidity and concentration data of interference gas in flue gas to obtain a correction data set, and dynamically correcting the calculation results of the CO concentration and the O2 concentration according to the correction data set; according to the method, advanced data preprocessing and an accurate concentration calculation model are combined, the accuracy of CO and O2 concentration measurement is effectively improved, and the stability of a measurement system is enhanced by combining temperature drift compensation of the sensor and dynamic correction of the pre-trained neural network model on the detection concentration.

Description

Technical Field

[0001] The invention belongs to the field of combustion process monitoring, and in particular relates to a method for measuring CO and O2 in furnace flue gas. Background Art

[0002] In industrial production, in many industries involving combustion processes, such as thermal power generation, steel smelting, and chemical industry, the combustion state in the furnace directly affects energy utilization efficiency, production safety, and pollutant emissions. Accurately controlling the CO and O2 concentrations in the furnace flue gas is crucial to achieving optimal control of the combustion process.

[0003] The traditional method for measuring CO and O2 in furnace flue gas does not fully consider the impact of environmental factors and interfering gases in the flue gas on the measurement results, and the measurement accuracy is not ideal. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for measuring CO and O2 in furnace flue gas to solve the problem that the traditional method for measuring CO and O2 in furnace flue gas proposed in the above background technology does not fully consider the influence of environmental factors and interfering gases in the flue gas on the measurement results, and the measurement accuracy is not ideal.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for measuring CO and O2 in furnace flue gas, comprising:

[0007] S1. Obtain the original signals of CO concentration data and O2 concentration data;

[0008] S2. performing data preprocessing on the obtained original signals of the CO concentration data and the O2 concentration data to generate a standardized electrical signal sequence;

[0009] S3. Calculating CO concentration and O2 concentration using the standardized electrical signal sequence;

[0010] S4. Acquire data on ambient temperature, humidity, and concentration of interfering gases in the flue gas to obtain a corrected data set, and dynamically correct the calculated results of the CO concentration and O2 concentration based on the corrected data set;

[0011] S5. Transmitting the corrected CO concentration and O2 concentration calculation results to the combustion control system and storing them in a database.

[0012] Preferably, step S1 obtains the original signal of CO concentration data through a CO sensor, and obtains the original signal of O2 concentration data through an O2 sensor. The CO sensor is a high-sensitivity sensor based on the principle of non-dispersive infrared absorption, and the O2 sensor is an electrochemical high-precision sensor.

[0013] Preferably, the calculating of the CO concentration and the O2 concentration by the standardized electrical signal sequence includes calculating the CO concentration based on the NDIR spectrum absorption model, and the formula is as follows:

[0014]

[0015] Among them, C CO is the calculated CO concentration, K CO is the standardized electrical signal sequence, I 参考 is the infrared reference light intensity, I 测量 To measure light intensity, the infrared reference light intensity and the measured light intensity are obtained through an infrared light source and a detector in a CO2 measurement device.

[0016] Preferably, the calculating of the CO concentration and the O2 concentration by the standardized electrical signal sequence includes calculating the O2 concentration based on an electrochemical current-concentration mapping relationship, and the formula is as follows:

[0017]

[0018] in, is the calculated O2 concentration, is the sensor current, I 零点 is the zero drift compensation value, is the sensor sensitivity, the sensor current is obtained by real-time measurement of the O2 sensor, and the zero drift compensation value and the sensor sensitivity are obtained by sensor calibration.

[0019] Preferably, the dynamically correcting the CO concentration and O2 concentration calculation results according to the corrected data set includes:

[0020] The pre-trained neural network model takes the correction data set as input and outputs the compensation factor ΔC of CO concentration. CO , calculate the corrected CO concentration:

[0021] C CO修正 =C CO +ΔC CO

[0022] Among them, C CO修正 is the corrected CO concentration, ΔC CO is the compensation factor for CO concentration;

[0023] According to the temperature drift characteristics of the O2 sensor, the O2 concentration is corrected using the polynomial fitting formula:

[0024]

[0025] in is the corrected O2 concentration, T is the ambient temperature, and a and b are calibration coefficients.

[0026] Preferably, the corrected data set includes inputting the ambient temperature, humidity and concentration data of interfering gases in the flue gas into an extended Kalman filter through a multi-source data fusion algorithm to generate a joint optimal estimate of CO and O2 concentrations to obtain a corrected data set.

[0027] Preferably, the data preprocessing of the obtained original signals of the CO concentration data and the O2 concentration data includes using an edge computing node to perform real-time processing on the original signals, including:

[0028] The raw signals of the CO concentration data and O2 concentration data are subjected to wavelet transform to eliminate high-frequency noise and perform timestamp alignment to ensure that the synchronization error of the CO and O2 data is ≤10ms. A standardized electrical signal sequence is generated, and historical data is cached at the edge. Local computing and storage are initiated when the network is interrupted.

[0029] Preferably, the pre-trained neural network model is a lightweight convolutional neural network, and the training data includes:

[0030] Combined data of CO, O2, CO2, temperature and humidity under standard laboratory environment;

[0031] Smoke data with noise and interference collected in actual industrial scenarios;

[0032] Dynamically update model weights through transfer learning to adapt to different combustion conditions.

[0033] The present invention further provides a computer, comprising:

[0034] a memory for storing executable instructions;

[0035] The processor is configured to execute the instructions to implement the steps of the above-mentioned method for measuring CO and O2 in furnace flue gas.

[0036] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for measuring CO and O2 in furnace flue gas are implemented.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention effectively improves the accuracy of CO and O2 concentration measurement by adopting a high-sensitivity CO sensor based on the principle of non-dispersive infrared absorption and an electrochemical high-precision O2 sensor, combined with advanced data preprocessing and an accurate concentration calculation model. The temperature drift compensation of the sensor and the dynamic correction of the detected concentration by the pre-trained neural network model enhance the stability of the measurement system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0040] Figure 1 It is a flowchart of the method steps of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0044] As attached Figure 1 As shown:

[0045] Example 1: This example provides a method for measuring CO and O2 in furnace flue gas, including:

[0046] S1. Obtain the original signals of CO concentration data and O2 concentration data;

[0047] Step S1 obtains the original signal of CO concentration data through the CO sensor and obtains the original signal of O2 concentration data through the O2 sensor. The CO sensor is a high-sensitivity sensor based on the principle of non-dispersive infrared absorption, and the O2 sensor is an electrochemical high-precision sensor.

[0048] S2. Preprocessing the original signals of the obtained CO concentration data and O2 concentration data to generate a standardized electrical signal sequence;

[0049] Data preprocessing of the raw signals of the obtained CO concentration data and O2 concentration data includes real-time processing of the raw signals using edge computing nodes, including:

[0050] The raw signals of the obtained CO and O concentration data are subjected to wavelet transform to eliminate high-frequency noise and perform timestamp alignment to ensure that the synchronization error of the CO and O data is ≤10ms. A standardized electrical signal sequence is generated, and historical data is cached at the edge. Local computing and storage are initiated when the network is interrupted.

[0051] The Daubechies4 wavelet basis is used to eliminate high-frequency noise, and the sensor clock is synchronized through the IEEE1588 protocol. When the network is interrupted, calculations can be continued based on historical data, reducing cloud dependence and shortening system response time.

[0052] S3, calculating the CO concentration and O2 concentration through the standardized electrical signal sequence;

[0053] S4. Acquire the ambient temperature, humidity, and concentration data of interfering gases in the flue gas to obtain a corrected data set, and dynamically correct the calculated results of CO concentration and O2 concentration based on the corrected data set;

[0054] Correcting the data set involves inputting ambient temperature, humidity, and concentration data of interfering gases in flue gas into an extended Kalman filter through a multi-source data fusion algorithm to generate a joint optimal estimate of CO and O2 concentrations to obtain a corrected data set;

[0055] By integrating multi-source data such as temperature, pressure, and flow, the CO / O2 concentration estimate is iteratively optimized through the state equation to output a concentration result that is closer to the true value. The measurement error is corrected by integrating environmental parameters to improve robustness.

[0056] S5. The corrected CO concentration and O2 concentration calculation results are transmitted to the combustion control system and stored in the database.

[0057] From the above, we can see that: wavelet denoising is used to eliminate high-frequency interference, timestamp alignment ensures data synchronization, improves signal quality, and avoids calculation errors caused by asynchronous data. The electrical signal is converted into a directly usable concentration value through a standardized electrical signal sequence. The environmental interference (such as temperature, humidity, and CO2 cross-interference) is compensated by the neural network model. The temperature drift is corrected by the polynomial fitting formula, eliminating the influence of non-target factors on the measurement results and improving accuracy.

[0058] Example 2: This example is basically the same as the previous example, except that the CO concentration and O2 concentration are calculated by the standardized electrical signal sequence, including the calculation of the CO concentration based on the NDIR spectrum absorption model, and the formula is as follows:

[0059]

[0060] Among them, C CO is the calculated CO concentration, K CO is the standardized electrical signal sequence, I 参考 is the infrared reference light intensity, I 测量 To measure light intensity, infrared reference light intensity and measurement light intensity are obtained through the infrared light source and detector in the CO measurement device.

[0061] The light intensity ratio eliminates the influence of light source aging and ensures long-term stability.

[0062] Specifically, the CO concentration and O2 concentration are calculated by the standardized electrical signal sequence, including the calculation of the O2 concentration based on the electrochemical current-concentration mapping relationship, and the formula is as follows:

[0063]

[0064] in, is the calculated O2 concentration, is the sensor current, I 零点 is the zero drift compensation value, is the sensor sensitivity. The sensor current is measured in real time by the O2 sensor. The zero drift compensation value and sensor sensitivity are obtained through sensor calibration.

[0065] Linearize electrochemical signals to simplify concentration calculations.

[0066] Specifically, dynamically correcting the CO concentration and O2 concentration calculation results based on the corrected data set includes:

[0067] The pre-trained neural network model takes the correction data set as input and outputs the compensation factor ΔC of CO concentration. CO , calculate the corrected CO concentration:

[0068] C CO修正 =C CO +ΔC CO

[0069] Among them, C CO修正 is the corrected CO concentration, ΔC CO is the compensation factor for CO concentration;

[0070] Eliminate CO2 cross-absorption and temperature and humidity interference to improve accuracy.

[0071] According to the temperature drift characteristics of the O2 sensor, the O2 concentration is corrected using the polynomial fitting formula:

[0072]

[0073] in is the corrected O2 concentration, T is the ambient temperature, and a and b are calibration coefficients.

[0074] The calibration coefficients a and b are obtained by fitting the temperature drift experiment in the laboratory to compensate the temperature drift of the sensor so that the error of O2 measurement is ≤±0.5% in the range of -20℃ to 80℃.

[0075] Specifically, the pre-trained neural network model is a lightweight convolutional neural network, and the training data includes:

[0076] Combined data of CO, O2, CO2, temperature and humidity under standard laboratory environment;

[0077] Smoke data with noise and interference collected in actual industrial scenarios;

[0078] Dynamically update model weights through transfer learning to adapt to different combustion conditions.

[0079] Laboratory data (pure environment) and industrial data (noise) are mixed in a ratio of 3:7 to enhance the generalization of the model. Some network layers are frozen, and only the parameters of the fully connected layer are fine-tuned to adapt to different combustion conditions. This allows the model to maintain high accuracy in scenarios such as coal and gas burning.

[0080] Example 3: Equipment Installation and Preparation: In the furnace flue of a large thermal power plant, a high-sensitivity CO sensor based on non-dispersive infrared absorption, with an accuracy of ±2ppm over a range of 0-1000ppm, was installed 5 meters from the burner outlet. A high-precision electrochemical O2 sensor with an accuracy of ±0.2% was also installed. The sensors were connected to the edge computing node via shielded cables to ensure stable signal transmission. High-precision ambient temperature sensors (accuracy of ±0.5°C), humidity sensors (accuracy of ±2%RH), and interfering gas detection equipment (such as SO2 and NOx) were deployed, with detection accuracies of ±1ppm and ±2ppm, respectively, and the data was connected to the system.

[0081] Measurement process:

[0082] Original signal acquisition: Start the furnace operation equipment. When running at full load, the CO sensor collects data 10 times per second and outputs the original signal of CO concentration data; the O2 sensor collects data at the same frequency and outputs the original signal of O2 concentration data.

[0083] Data preprocessing: Edge computing nodes process the acquired raw signals, using wavelet transforms to remove high-frequency noise, reducing signal noise by 30%. A time synchronization algorithm aligns timestamps to ensure the synchronization error of CO and O2 data is within 5ms. A standardized electrical signal sequence is generated, and the edge caches the last hour of historical data.

[0084] Concentration Calculation: Based on the NDIR spectral absorption model, CO concentration is calculated using a standardized electrical signal sequence, infrared reference light intensity, and measured light intensity, with an accuracy of ±3ppm. O2 concentration is calculated based on the electrochemical current-concentration mapping relationship, combining sensor current, zero drift compensation value, and sensor sensitivity, with an accuracy of ±0.3%.

[0085] Correction Process: Data on ambient temperature (average temperature 120°C), humidity (average humidity 30% RH), and interfering gases in the flue gas (average SO2 concentration 10 ppm, average NOx concentration 20 ppm) are collected and fed into an extended Kalman filter using a multi-source data fusion algorithm. This generates a joint optimal estimate of CO and O2 concentrations, yielding a corrected dataset. This corrected dataset is then fed into a pre-trained lightweight convolutional neural network model, which outputs a compensation factor for CO concentration and corrects the calculated CO concentration. Based on the temperature drift characteristics of the O2 sensor, a polynomial fitting formula is used to correct the O2 concentration. After correction, CO measurement accuracy is improved to ±2 ppm, and O2 measurement accuracy is improved to ±0.2%.

[0086] Data transmission and storage: The corrected CO and O2 concentration calculation results are transmitted once per second to the thermal power plant's combustion control system for real-time adjustment of combustion parameters. Simultaneously, the data is stored in a database with a data transmission delay of less than 10ms.

[0087] Implementation Results: After three months of operational monitoring, this measurement method was able to accurately measure the CO and O2 concentrations in furnace flue gas; compared with traditional measurement methods, measurement accuracy was improved by 30%; after the combustion control system was optimized and adjusted based on the accurate measurement data, the thermal power plant's power generation efficiency increased by 5%, coal consumption decreased by 8%, and nitrogen oxide emissions decreased by 15%.

[0088] In order to achieve the above object, the present invention further provides a computer, comprising:

[0089] a memory for storing executable instructions;

[0090] The processor is configured to execute instructions to implement the steps of the above-mentioned method for measuring CO and O2 in furnace flue gas.

[0091] In order to achieve the above-mentioned object, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for measuring CO and O2 in furnace flue gas are implemented.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course, by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to enter the method described in each embodiment of the present invention.

[0093] It is important to note that the construction and arrangement of the present application shown in a number of different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, as well as parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, directional changes, etc.) without departing substantially from the novel teachings and advantages of the subject matter described in this application. For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of the element may be inverted or otherwise changed, and the nature or number or position of the discrete elements may be altered or changed. Therefore, all such modifications are intended to be included within the scope of the present invention. The order or sequence of any process or method steps may be changed or reordered according to alternative embodiments. In the claims, any "means plus function" clause is intended to cover the structure described herein that performs the function, and is not only structurally equivalent but also equivalent structures. Other replacements, modifications, changes, and omissions may be made in the design, operating conditions, and arrangement of the exemplary embodiments without departing from the scope of the present invention. Therefore, the invention is not limited to the specific embodiments, but extends to various modifications that still fall within the scope of the appended claims.

[0094] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (i.e., those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0095] It will be appreciated that in the development of any actual embodiment, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will, for those of ordinary skill having the benefit of this disclosure, be a routine undertaking of design, fabrication, and production without undue experimentation.

[0096] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for measuring CO and O2 in furnace flue gas, characterized in that: include: S1. Obtain the original signals of CO concentration data and O2 concentration data; S2. performing data preprocessing on the obtained original signals of the CO concentration data and the O2 concentration data to generate a standardized electrical signal sequence; S3. Calculating CO concentration and O2 concentration using the standardized electrical signal sequence; S4. Acquire data on ambient temperature, humidity, and concentration of interfering gases in the flue gas to obtain a corrected data set, and dynamically correct the calculated results of the CO concentration and O2 concentration based on the corrected data set; S5. Transmitting the corrected CO concentration and O2 concentration calculation results to the combustion control system and storing them in a database.

2. A method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The step S1 obtains the original signal of CO concentration data through the CO sensor and obtains the original signal of O2 concentration data through the O2 sensor. The CO sensor is a high-sensitivity sensor based on the principle of non-dispersive infrared absorption, and the O2 sensor is an electrochemical high-precision sensor.

3. The method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The calculation of the CO concentration and the O2 concentration by the standardized electrical signal sequence includes calculating the CO concentration based on the NDIR spectrum absorption model, and the formula is as follows: Among them, C CO is the calculated CO concentration, K CO is the standardized electrical signal sequence, I 参考 is the infrared reference light intensity, I 测量 To measure light intensity, the infrared reference light intensity and the measured light intensity are obtained through an infrared light source and a detector in a CO2 measurement device.

4. The method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The calculation of the CO concentration and the O2 concentration by the standardized electrical signal sequence includes calculating the O2 concentration based on the electrochemical current-concentration mapping relationship, and the formula is as follows: in, is the calculated O2 concentration, is the sensor current, I 零点 is the zero drift compensation value, is the sensor sensitivity, the sensor current is obtained by real-time measurement of the O2 sensor, and the zero drift compensation value and the sensor sensitivity are obtained by sensor calibration.

5. The method for measuring CO and O2 in furnace flue gas according to claim 2, characterized in that: The dynamically correcting the CO concentration and O2 concentration calculation results according to the corrected data set includes: The pre-trained neural network model takes the correction data set as input and outputs the compensation factor ΔC of CO concentration. CO , calculate the corrected CO concentration: C CO修正 =C CO +ΔC CO Among them, C CO修正 is the corrected CO concentration, ΔC CO is the compensation factor for CO concentration; According to the temperature drift characteristics of the O2 sensor, the O2 concentration is corrected using the polynomial fitting formula: in is the corrected O2 concentration, T is the ambient temperature, and a and b are calibration coefficients.

6. The method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The modified data set includes inputting the ambient temperature, humidity and concentration data of interfering gases in the flue gas into an extended Kalman filter through a multi-source data fusion algorithm to generate a joint optimal estimate of CO and O2 concentrations to obtain a modified data set.

7. The method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The data preprocessing of the obtained original signals of the CO concentration data and the O2 concentration data includes real-time processing of the original signals by using an edge computing node, including: The raw signals of the CO concentration data and O2 concentration data are subjected to wavelet transform to eliminate high-frequency noise and perform timestamp alignment to ensure that the synchronization error of the CO and O2 data is ≤10ms. A standardized electrical signal sequence is generated, and historical data is cached at the edge. Local computing and storage are initiated when the network is interrupted.

8. The method for measuring CO and O2 in furnace flue gas according to claim 1, characterized in that: The pre-trained neural network model is a lightweight convolutional neural network, and the training data includes: Combined data of CO, O2, CO2, temperature and humidity under standard laboratory environment; Smoke data with noise and interference collected in actual industrial scenarios; Dynamically update model weights through transfer learning to adapt to different combustion conditions.

9. A computer, characterized in that: The computer comprises: a memory for storing executable instructions; The processor is configured to execute the instructions to implement the steps of the furnace flue gas CO and O2 measurement method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for measuring CO and O2 in furnace flue gas are implemented as described in any one of claims 1 to 8.

Images