A furnace working state monitoring management system and method

Abstract

The present invention discloses a furnace working state monitoring management system and method, which relates to the technical field of furnace data processing. The method comprises the following steps: arranging multiple sensors in the furnace to obtain multiple sets of sensor data of the furnace; the sensor data comprises: temperature data and pressure data; performing weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data comprises: temperature fusion data and pressure fusion data; inputting the sensor fusion data into a neural network model; the neural network model analyzes the sensor fusion data and outputs the working state of the furnace. The present invention improves the accuracy of the furnace data by acquiring temperature data and pressure data, performing fusion processing on the temperature data and pressure data, inputting the fusion data into the neural network model for analysis, obtaining the working state of the furnace, and improving the accuracy of the furnace working state analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of furnace data processing, and in particular to a furnace working state monitoring management system and method. Background Art

[0002] The working state of the furnace needs to be evaluated according to the various physical and chemical conditions of the furnace during its operation, as well as the operating efficiency, energy consumption and quality of the furnace under these conditions. When the working state of the furnace is abnormal, it will cause the reaction rate of the furnace to decrease, damage the environmental protection, and reduce the product quality. Therefore, monitoring the working state of the furnace and adjusting it in time is of great significance to the production safety, product quality and energy consumption of the furnace.

[0003] The existing furnace working state monitoring obtains physical data in the furnace and analyzes the working state of the furnace through single physical data. This method has the problem of inaccurate data in the process of obtaining data, and at the same time, the data analysis process cannot accurately determine the working state of the furnace. Summary of the invention

[0004] The purpose of the present invention is to provide a furnace working status monitoring management system and method. The present invention obtains temperature data and pressure data, fuses the temperature data and pressure data, improves the accuracy of the furnace data, inputs the fused data into a neural network model for analysis, obtains the furnace working status, and improves the accuracy of the furnace working status analysis.

[0005] The purpose of the present invention is achieved by the following technical means:

[0006] In a first aspect, the present invention provides a method for monitoring and managing a furnace working state, comprising the following steps:

[0007] Arrange multiple sensors in the furnace to obtain multiple sets of sensor data of the furnace; the sensor data includes: temperature data and pressure data;

[0008] Performing weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data;

[0009] inputting the sensor fusion data into a neural network model;

[0010] The neural network model analyzes the sensor fusion data and outputs the working status of the furnace.

[0011] Preferably, performing weighted average fusion processing on the sensor data to obtain sensor fusion data comprises the following steps:

[0012] Calculating the variance of the sensor based on the multiple sets of sensor data;

[0013] Calculating the weight of the sensor according to the variance of the sensor;

[0014] Calculating the sensor fusion data according to the weights of the sensors;

[0015] The calculation formula of the sensor weight is as follows:

[0016] ,

[0017] in, is the weight of the sensor, is the variance of the sensor, For the The variance of each sensor;

[0018] The calculation formula of the sensor fusion data is as follows:

[0019] ,

[0020] in, For sensor fusion data, For the Sensor data from sensors, For the The weight of the sensor.

[0021] Preferably, before inputting the sensor fusion data into the neural network model, the method further includes the following steps:

[0022] The sensor fusion data is preprocessed.

[0023] Preferably, the preprocessing of the sensor fusion data comprises the following steps:

[0024] Obtaining the data volume of the sensor fusion data;

[0025] Normalizing the sensor fusion data according to the data volume;

[0026] The formula for the normalization process is expressed as follows:

[0027] ,

[0028] in, For the normalized sensor fusion data, is the amount of data, For the The input layer Sensor fusion data.

[0029] Preferably, before the neural network model analyzes the sensor fusion data and outputs the working status of the furnace, it also includes the following steps:

[0030] Obtain historical temperature data and historical pressure data as input data, and work status as output data to construct a training sample set;

[0031] The neural network model is trained according to the training sample set.

[0032] Preferably, the training of the neural network model according to the training sample set comprises the following steps:

[0033] According to the training sample set, an input data matrix is ​​obtained;

[0034] Obtaining the number of samples in the training sample set;

[0035] Calculating a first weight matrix according to the sample quantity;

[0036] According to the working threshold, a second weight matrix is ​​obtained;

[0037] Calculating a target matrix according to the input data matrix, the first weight matrix and the second weight matrix;

[0038] Calculating a loss function based on the input data matrix and the target matrix;

[0039] Resetting the working threshold and calculating the second weight matrix;

[0040] Calculating the loss function according to the recalculated second weight matrix until the loss function is minimized;

[0041] The calculation formula of the loss function is as follows:

[0042] ,

[0043] in, is the loss function, The input data matrix is Line The value of the column, The target matrix Line The value of the column.

[0044] Preferably, after the neural network model analyzes the sensor fusion data and outputs the working status of the furnace, it further includes the following steps:

[0045] When the working state is abnormal, an abnormal alarm is issued.

[0046] In a second aspect, the present invention provides a furnace working state monitoring and management system, which applies the above-mentioned furnace working state monitoring and management method, including: a sensor data acquisition module, a sensor data fusion module and a sensor data analysis module;

[0047] The sensor data acquisition module is used to set a plurality of sensors in the furnace to acquire a plurality of sets of sensor data of the furnace; the sensor data includes: temperature data and pressure data;

[0048] The sensor data fusion module is used to perform weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data;

[0049] The sensor data analysis module is used to input the sensor fusion data into a neural network model; the neural network model analyzes the sensor fusion data and outputs the working status of the furnace.

[0050] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the above-mentioned method for monitoring and managing the working status of a furnace.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the above-mentioned method for monitoring and managing the working status of a furnace.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention obtains temperature data and pressure data, fuses the temperature data and pressure data, improves the accuracy of furnace data, inputs the fused data into a neural network model for analysis, obtains the working state of the furnace, and improves the accuracy of furnace working state analysis;

[0054] The present invention calculates the weight of each sensor through the variance of each sensor, fuses the sensor data according to the weight, and improves the accuracy of the furnace data;

[0055] The present invention improves the accuracy of furnace working status analysis by normalizing sensor fusion data;

[0056] The present invention obtains the first weight matrix and the second weight matrix according to the number of training sample sets and the working threshold, calculates the target matrix, calculates the loss function according to the input data matrix and the target matrix, continuously optimizes the loss function, and improves the accuracy of the furnace working state analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0059] Figure 1 A flow chart of a furnace working status monitoring and management method provided in this embodiment;

[0060] Figure 2 Step S3 provided in this embodiment is a flow chart of performing weighted average fusion processing on sensor data to obtain sensor fusion data;

[0061] Figure 3 Step S4 provided in this embodiment is a flow chart of preprocessing sensor fusion data;

[0062] Figure 4 Step S62 provided in this embodiment is a flow chart of training a neural network model according to a training sample set;

[0063] Figure 5 A schematic diagram of the structure of a furnace working status monitoring and management system provided in this embodiment;

[0064] Figure 6 A schematic diagram of the structure of an electronic device provided in this embodiment. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0067] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0068] Embodiment 1

[0069] This embodiment provides a method for monitoring and managing the working status of a furnace. Figure 1 As shown, the following steps are included:

[0070] S1, setting a plurality of sensors in the furnace to obtain a plurality of sets of sensor data of the furnace; the sensor data includes: temperature data and pressure data;

[0071] S3, performing weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data;

[0072] S5, inputs the sensor fusion data into the neural network model;

[0073] S7, the neural network model analyzes the sensor fusion data and outputs the working status of the furnace.

[0074] It should be noted that the multiple sensors installed in the furnace include multiple temperature sensors and multiple pressure sensors. The multiple groups of sensors collect multiple data in a short time through the pre-set sampling times to measure the temperature and pressure data of the furnace at that time point. In the process of data collection, due to the interference of the environment in which the furnace is located and the performance of the sensor itself, the actual measurement data of each sensor may have deviations. Therefore, before the temperature data and pressure data are input into the neural network model for working state analysis, the temperature data and pressure data are first subjected to weighted average fusion processing. In some embodiments, the working state of the furnace includes normal and abnormal. When the acquired temperature and pressure multi-source data meet the working threshold of the furnace, the neural network model will output a normal working state, and when there is abnormal data, the neural network model will output an abnormal working state.

[0075] In this embodiment, temperature data and pressure data are acquired and fused to improve the accuracy of furnace data. The fused data is input into a neural network model for analysis to obtain the working status of the furnace, thereby improving the accuracy of furnace working status analysis.

[0076] In some embodiments, step S3 performs weighted average fusion processing on the sensor data to obtain sensor fusion data, such as Figure 2 As shown, the following steps are included:

[0077] S31, calculating the variance of the sensor according to the multiple sets of sensor data;

[0078] S32, calculating the weight of the sensor according to the variance of the sensor;

[0079] S33, calculating sensor fusion data according to the weight of the sensor;

[0080] The sensor weight is calculated as follows:

[0081] ,

[0082] in, is the weight of the sensor, is the variance of the sensor, For the The variance of each sensor;

[0083] The calculation formula for sensor fusion data is as follows:

[0084] ,

[0085] in, For sensor fusion data, For the Sensor data from sensors, For the The weight of the sensor.

[0086] It should be noted that the fusion processing of sensor data is for data of sensors of the same type. Specifically, taking the temperature sensor as an example, if the number of temperature sensors is 10, the number of temperature data collected by each temperature sensor is 30. According to the 30 temperature data collected by each temperature sensor, the variance of each sensor is calculated respectively, and the weight of each temperature sensor is calculated based on the variance. The temperature data is fused according to the sum and weight of the 30 temperature data of each temperature sensor data to obtain temperature fusion data. Similarly, pressure fusion data can be obtained. That is, multiple groups of temperature sensor data and multiple groups of pressure sensor data are fused into one temperature fusion data and one pressure fusion data.

[0087] In this embodiment, the weight of each sensor is calculated through the variance of each sensor, and the sensor data is fused according to the weight, thereby improving the accuracy of the furnace data.

[0088] In some embodiments, before step S5, inputting the sensor fusion data into the neural network model, the following steps are also included:

[0089] S4, preprocessing the sensor fusion data.

[0090] Specifically, step S4 pre-processes the sensor fusion data, such as Figure 3 As shown, the following steps are included:

[0091] S41, obtaining the data volume of sensor fusion data;

[0092] S42, normalizing the sensor fusion data according to the data volume;

[0093] The formula for normalization is as follows:

[0094] ,

[0095] in, For the normalized sensor fusion data, is the amount of data, For the The input layer Sensor fusion data.

[0096] It should be noted that when the neural network model is analyzed, the fusion data of each sensor needs to be input. After the fusion process, the fusion data of each sensor is summed and weighted, and there will be certain differences in the order of magnitude, which will lead to certain errors in the results during analysis. Therefore, the fusion data of the sensor needs to be normalized.

[0097] In this embodiment, the accuracy of the furnace working status analysis is improved by normalizing the sensor fusion data.

[0098] In some embodiments, in step S7, before the neural network model analyzes the sensor fusion data and outputs the working status of the furnace, the following steps are also included:

[0099] S61, acquiring historical temperature data and historical pressure data as input data, and the working status as output data to construct a training sample set;

[0100] S62, training the neural network model according to the training sample set.

[0101] In some embodiments, step S62, the neural network model is trained according to the training sample set, such as Figure 4 As shown, the following steps are included:

[0102] S621, obtaining an input data matrix according to the training sample set;

[0103] S622, obtaining the number of samples in the training sample set;

[0104] S623, calculating the first weight matrix according to the number of samples;

[0105] S624, obtaining a second weight matrix according to the working threshold;

[0106] S625, calculating a target matrix according to the input data matrix, the first weight matrix and the second weight matrix;

[0107] S626, calculating a loss function according to the input data matrix and the target matrix;

[0108] S627, resetting the working threshold and calculating the second weight matrix;

[0109] S628, calculating a loss function according to the recalculated second weight matrix until the loss function is minimized;

[0110] The loss function is calculated as follows:

[0111] ,

[0112] in, is the loss function, The input data matrix is Line The value of the column, The target matrix Line The value of the column.

[0113] In some embodiments, the neural network model is provided with two input layers, which respectively input temperature fusion data and pressure fusion data, the number of intermediate layers is five, the number of output layers is one, and the working status is output. The first weight matrix is ​​calculated according to the number of samples as the weight matrix of the input data to perform weight calculation to obtain the intermediate layer matrix. Specifically, the first weight matrix is ​​obtained by random given by the neural network model, and the rank of the transposed matrix of the intermediate layer matrix after weight calculation needs to be equal to the number of samples in the training sample set. That is, the first weight matrix needs to satisfy the following formula:

[0114] ,

[0115] in, For the rank operation, is the transposed matrix of the intermediate layer matrix, is the number of samples in the training sample set, is the middle layer matrix, is the first weight matrix, is the input data matrix;

[0116] The working threshold is used to judge the working state of the furnace, and is continuously selected and updated through the neural network model. The second weight matrix is ​​calculated according to the working threshold as the weight matrix of the intermediate layer data to perform weight calculation and obtain the target matrix. Specifically, the calculation formula of the target matrix is ​​as follows:

[0117] ,

[0118] in, is the target matrix, is the second weight matrix, is the middle layer matrix.

[0119] In this embodiment, the first weight matrix and the second weight matrix are obtained according to the number of training sample sets and the working threshold, the target matrix is ​​calculated, the loss function is calculated according to the input data matrix and the target matrix, and the loss function is continuously optimized to improve the accuracy of the furnace working status analysis.

[0120] In some embodiments, in step S7, after the neural network model analyzes the sensor fusion data and outputs the working status of the furnace, the following steps are also included:

[0121] S8: When the working status is abnormal, an abnormal alarm is issued.

[0122] Embodiment 2

[0123] This embodiment provides a furnace working state monitoring and management system, which applies the above-mentioned furnace working state monitoring and management method, such as Figure 5As shown, it includes: a sensor data acquisition module, a sensor data fusion module and a sensor data analysis module;

[0124] The sensor data acquisition module is used to set a plurality of sensors in the furnace to acquire a plurality of sets of sensor data of the furnace; the sensor data includes: temperature data and pressure data;

[0125] The sensor data fusion module is used to perform weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data;

[0126] The sensor data analysis module is used to input the sensor fusion data into the neural network model; the neural network model analyzes the sensor fusion data and outputs the working status of the furnace.

[0127] In this embodiment, temperature data and pressure data are acquired and fused to improve the accuracy of furnace data. The fused data is input into a neural network model for analysis to obtain the working status of the furnace, thereby improving the accuracy of furnace working status analysis.

[0128] It should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of the above modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, each functional module can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0129] Embodiment 3

[0130] This embodiment provides an electronic device 2, such as Figure 6 As shown, a processor 21 and a memory 22, the memory 22 is used to store computer program codes, the computer program codes include computer instructions, when the processor 21 executes the computer instructions, the electronic device executes the above-mentioned method for monitoring and managing the working status of a furnace.

[0131] The electronic device 2 includes a processor 21, a memory 22, an output device 23, and an input device 24. The processor 21, the memory 22, the output device 23, and the input device 24 are coupled via a connector, and the connector includes various interfaces, transmission lines, or buses, etc., which are not limited in the embodiments of the present invention. It should be understood that in various embodiments of the present invention, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

[0132] The processor 21 may be one or more graphics processing units (GPUs). When the processor 21 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. Optionally, the processor 21 may be a processor group consisting of multiple GPUs, and the multiple processors are coupled to each other via one or more buses. Optionally, the processor 21 may also be other types of processors, etc., which are not limited in the embodiments of the present invention.

[0133] The memory 22 can be used to store computer program instructions and various computer program codes including program codes for executing the scheme of the present invention. Optionally, the memory 22 includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read only memory (CD-ROM), and the memory 22 is used for related instructions and data.

[0134] The input device 24 is used to input data and / or signals, and the output device 23 is used to output data and / or signals. The output device 23 and the input device 24 can be independent devices or an integrated device.

[0135] This embodiment provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the above-mentioned method for monitoring and managing the working status of a furnace.

[0136] The above are only specific embodiments of the present invention, which enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for monitoring and managing the working status of a furnace, characterized in that: The following steps are involved: A plurality of sensors are arranged in the furnace to obtain a plurality of sets of sensor data of the furnace; The sensor data includes: temperature data and pressure data; Performing weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data; inputting the sensor fusion data into a neural network model; The neural network model analyzes the sensor fusion data and outputs the working status of the furnace; The sensor data is subjected to weighted average fusion processing to obtain sensor fusion data, including the following steps: Calculating the variance of the sensor based on the multiple sets of sensor data; Calculating the weight of the sensor according to the variance of the sensor; Calculating the sensor fusion data according to the weights of the sensors; The calculation formula of the sensor weight is as follows: ， in, is the weight of the sensor, is the variance of the sensor, For the The variance of each sensor; The calculation formula of the sensor fusion data is as follows: ， in, For sensor fusion data, For the Sensor data from sensors, For the The weight of the sensor.

2. A method for monitoring and managing furnace working status according to claim 1, characterized in that: Before inputting the sensor fusion data into the neural network model, the following steps are also included: The sensor fusion data is preprocessed.

3. A method for monitoring and managing furnace working status according to claim 2, characterized in that: The preprocessing of the sensor fusion data comprises the following steps: Obtaining the data volume of the sensor fusion data; Normalizing the sensor fusion data according to the data volume; The formula for the normalization process is as follows: ， in, For the normalized sensor fusion data, is the amount of data, For the The input layer Sensor fusion data.

4. A method for monitoring and managing furnace working status according to claim 1, characterized in that: The neural network model analyzes the sensor fusion data and outputs the working status of the furnace, and further includes the following steps: Obtain historical temperature data and historical pressure data as input data, and work status as output data to construct a training sample set; The neural network model is trained according to the training sample set.

5. A method for monitoring and managing furnace working status according to claim 4, characterized in that: The training of the neural network model according to the training sample set comprises the following steps: According to the training sample set, an input data matrix is ​​obtained; Obtaining the number of samples in the training sample set; Calculating a first weight matrix according to the sample quantity; According to the working threshold, a second weight matrix is ​​obtained; Calculating a target matrix according to the input data matrix, the first weight matrix and the second weight matrix; Calculating a loss function based on the input data matrix and the target matrix; Resetting the working threshold and calculating the second weight matrix; Calculating the loss function according to the recalculated second weight matrix until the loss function is minimized; The calculation formula of the loss function is as follows: ， in, is the loss function, The input data matrix is Line The value of the column, The target matrix Line The value of the column.

6. A method for monitoring and managing furnace working status according to claim 1, characterized in that: After the neural network model analyzes the sensor fusion data and outputs the working status of the furnace, the following steps are also included: When the working state is abnormal, an abnormal alarm is issued.

7. A furnace working state monitoring and management system, using a furnace working state monitoring and management method as claimed in any one of claims 1 to 6, characterized in that: include: Sensor data acquisition module, sensor data fusion module and sensor data analysis module; The sensor data acquisition module is used to set a plurality of sensors in the furnace to acquire a plurality of sets of sensor data of the furnace; the sensor data includes: temperature data and pressure data; The sensor data fusion module is used to perform weighted average fusion processing on the sensor data to obtain sensor fusion data; the sensor fusion data includes: temperature fusion data and pressure fusion data; The sensor data analysis module is used to input the sensor fusion data into a neural network model; the neural network model analyzes the sensor fusion data and outputs the working status of the furnace.

8. An electronic device, characterized in that: It includes a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes a furnace working status monitoring and management method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a furnace working status monitoring and management method as described in any one of claims 1 to 6.

Images