Method and equipment for identifying small strip printing problem of environment monitoring equipment and medium

Abstract

The invention relates to an environment monitoring equipment small strip printing problem identification method, equipment and a medium, and belongs to the technical field of environment monitoring. The method comprises the steps of obtaining a digital image of a small printing strip of environment monitoring equipment; performing feature extraction on the digital image to obtain to-be-checked data; calling a pre-established knowledge base and an algorithm base; standard data related to environmental monitoring are stored in the knowledge base, and the algorithm library comprises a plurality of calculation methods and logic inspection methods for checking and problem identification of printed small data; performing fitting calculation on the to-be-checked data by adopting a convolutional neural network, comparing an obtained calculation result with standard data in a knowledge base, and generating a checking result of whether the environment monitoring equipment printing strip is abnormal or not based on a comparison result; and feeding back the verification result to the user. According to the method and the device, the problem in the manually monitored printed small strip is automatically checked, and the problem identification capability and efficiency of the monitoring data are improved.

Description

Technical Field

[0001] The present application belongs to the field of environmental monitoring technology, and specifically relates to a method, device and medium for identifying problems with printed strips of environmental monitoring equipment. Background Art

[0002] In previous inventions in professional fields, it is common to use programs implanted in mobile terminals to identify general text anomalies, which can be roughly applied to conventional parameters in some key industries such as steel, coking, etc. However, it lacks effective problem identification capabilities for complex processes and data texts from other industries. On the other hand, the judgment of different formats and professional terms is usually slow in recognition efficiency and poor in accuracy.

[0003] Therefore, how to refine, effectively and accurately identify the logical distinctions brought about by different industries and adapt to complex scenarios such as multi-process, multi-parameter and multi-sample is a topic worthy of study. Summary of the invention

[0004] In view of the above analysis, the embodiments of the present invention aim to provide a method, device and medium for identifying problems in print strips of environmental monitoring equipment, so as to realize automatic verification of problems in manual monitoring print strips and improve the problem identification capability and efficiency of monitoring data.

[0005] In a first aspect of the present application, a method for identifying problems with printed strips of environmental monitoring equipment is provided, comprising:

[0006] Acquire a digital image of a strip printed by an environmental monitoring device;

[0007] Extracting features from the digital image to obtain data to be verified;

[0008] Calling a pre-established knowledge base and algorithm base; the knowledge base stores standard data related to environmental monitoring, the standard data including print strip format requirements, basic information judgment rules, a calculation model group consisting of industry specifications, and theoretical thresholds based on industry characteristics; the algorithm base includes a variety of calculation methods and logic checking methods for checking and identifying problems in print strip data;

[0009] Based on the calculation method and logic checking method in the algorithm library, a convolutional neural network is used to perform fitting calculation on the data to be verified, and the obtained calculation result is compared with the standard data in the knowledge base, and a verification result of whether there is an abnormality in the print strip of the environmental monitoring equipment is generated based on the comparison result;

[0010] The verification result is fed back to the user.

[0011] Optionally, the standard format requirements for the printed strips include text font, standard line spacing, and numbering rules;

[0012] The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including:

[0013] The printed strips are reviewed for standard format and numbering issues through a convolutional neural network. If the format does not meet the standard format requirements, the number of digits is different, the number order is disordered, or there are problems with the same number, the printed strips are judged to be forged and a verification result indicating that the printed strips are abnormal is generated.

[0014] Optionally, the basic information judgment rules include sampling point information, time rules, personnel arrangement rules, and signature authentication standards;

[0015] The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including:

[0016] Analyze the time and point data on each printed strip to check whether there are repeated sampling records or adjacent sampling records; check the personnel schedule in the knowledge base according to the operators and time recorded on the printed strip to detect whether there are logical conflicts; check whether the signature on the printed strip meets the preset validity standards: including the style and position of the signature and whether it contains authentication elements; generate verification results based on the comparison results to determine whether there are any abnormalities in the printed strips of environmental monitoring equipment.

[0017] Optionally, the calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation result is compared with the standard data in the knowledge base, and the verification result of whether the printed strip of the environmental monitoring device is abnormal is generated based on the comparison result, including:

[0018] The flow rate is calculated according to the sampling flow rate calculation formula in the algorithm library. The flow rate calculation formula used is:

[0019]

[0020] Among them, V s Indicates the gas velocity of wet exhaust gas, in m / s; V a Indicates the air velocity in the ventilation duct at normal temperature and pressure, in m / s; B a Indicates atmospheric pressure, in Pa; K p Indicates the Pitot tube correction factor; P dIndicates exhaust dynamic pressure, unit is Pa; P s Indicates the exhaust static pressure, in Pa; ρ s Indicates the density of wet exhaust gas in kg / m 3 ;M s Indicates the molecular weight of wet exhaust gas, in kg / kmol; t s Indicates the exhaust temperature in °C; compares the calculated flow rate with the theoretical flow rate threshold in the knowledge base, and if it exceeds the theoretical flow rate threshold, it is determined that an abnormality exists, and generates a verification result that the environmental monitoring device prints an abnormality in the strip;

[0021] Based on the sampling nozzle diameter, sampling flow rate, and sampling duration, the sampling volume is calculated according to the sampling volume calculation formula in the algorithm library, and the calculated sampling volume is compared with the sampling volume theoretical threshold in the knowledge base. If the sampling volume theoretical threshold is exceeded, it is determined that an abnormality exists, and a verification result that the environmental monitoring device prints an abnormality is generated;

[0022] The pre-meter pressure is obtained to determine whether the pre-meter pressure exceeds the theoretical threshold of the pre-meter pressure. If so, it is determined that an abnormality exists, and a verification result indicating that an abnormality exists in the print strip of the environmental monitoring device is generated.

[0023] Optionally, extracting features from the digital image to obtain data to be verified includes:

[0024] Extracting text data from the digital image using optical character recognition technology, parsing the text data to identify key parameters, and obtaining data to be verified; the data to be verified includes oxygen content, flow rate, smoke temperature and humidity;

[0025] The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including:

[0026] Perform numerical analysis on the data to be verified, calculate the average value, standard deviation and other statistical indicators of multiple samples at the same point; perform anomaly detection on each parameter, and compare the parameter value of each sample with the set threshold or average value; if the parameter value of the sample exceeds the set threshold or average value, it is determined that an anomaly exists, and generate a verification result indicating that an abnormality exists in the print strip of the environmental monitoring equipment.

[0027] Optionally, the calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation result is compared with the standard data in the knowledge base, and the verification result of whether the printed strip of the environmental monitoring device is abnormal is generated based on the comparison result, including:

[0028] Collect sampling flow rate data at each sampling point from the printed strips of environmental monitoring equipment;

[0029] Conduct statistical analysis on the collected sampling flow rate data and calculate the mean value, standard deviation and deviation rate;

[0030] According to the deviation rate threshold set in the knowledge base, the calculated deviation rate is compared with the deviation rate threshold to determine whether it meets the requirements of constant-speed tracking sampling. If it does not meet the requirements, it is determined that there is an abnormality and a verification result is generated that the environmental monitoring equipment prints an abnormality in the strip.

[0031] Optionally, before acquiring the digital image of the small strip printed by the environment monitoring device, the method further includes:

[0032] Obtaining input information on the industry type, process, and working conditions of the environmental monitoring equipment printing strip;

[0033] Based on the industry type, process, and working conditions to which the small strip printed by the environmental monitoring equipment belongs, corresponding data is loaded from the knowledge base and algorithm library.

[0034] Optionally, after obtaining the digital image of the small strip printed by the environment monitoring device, the method further includes:

[0035] The digital image is subjected to image preprocessing, wherein the image preprocessing includes grayscale processing, binarization processing, and noise removal processing on the digital image.

[0036] According to a second aspect of the present application, there is provided a device for identifying problems with small print strips in an environmental monitoring device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, a method for identifying problems with small print strips in an environmental monitoring device is implemented according to any one of the above-described methods.

[0037] According to a third aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for identifying problems of printing small strips of environmental monitoring equipment according to any one of the above-mentioned methods is implemented.

[0038] The method for identifying problems of printed strips of environmental monitoring equipment provided in the present application obtains a digital image of a printed strip of environmental monitoring equipment; extracts features from the digital image to obtain data to be checked; calls a pre-established knowledge base and algorithm library; based on the calculation method and logic check method in the algorithm library, a convolutional neural network is used to fit the data to be checked, and the obtained calculation result is compared with the standard data in the knowledge base, and a verification result of whether there is an abnormality in the printed strip of the environmental monitoring equipment is generated based on the comparison result; and the verification result is fed back to the user. The present application significantly reduces the time for manual input and analysis of data through automated image processing and data recognition, and realizes rapid extraction and processing of data from printed strips. The convolutional neural network is used to accurately identify the text and symbols on the printed strip, reducing the misunderstandings or errors that may occur in traditional manual reading. By comparing with the standard data in the knowledge base, it is ensured that all data is processed and interpreted according to unified standards, and the consistency and reliability of the data are improved. The present application realizes automatic verification of problems in manual monitoring printed strips, and improves the problem identification ability and efficiency of monitoring data.

[0039] In addition, the present application also provides an environmental monitoring equipment printing strip problem identification device and medium with the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of this specification 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, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 A flowchart of a specific implementation method of the method for identifying problems with printed strips of environmental monitoring equipment provided in this application;

[0042] Figure 2 A schematic diagram of another specific implementation of the method for identifying problems with printed strips of environmental monitoring equipment provided in the present application;

[0043] Figure 3 The structural frame of the small strip problem identification device for the environmental monitoring equipment provided in this application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. It should be noted that, in the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0045] The terms used here are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used here, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "said (the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but it is not excluded that there are or add one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups. It should also be noted that, as used here, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0046] Environmental monitoring equipment printouts are output in the form of record strips generated by relevant equipment during the environmental monitoring process. These strips record monitoring data and related information and are usually used to display and record quality parameters of environmental factors such as air, water quality, and soil.

[0047] The printed strips of environmental monitoring equipment usually have the following data and characteristics:

[0048] (1) Data content: The strips printed by environmental monitoring equipment usually contain key monitoring indicators, such as temperature, humidity, chemical concentration, noise level, radiation level, etc. In addition, they can also include timestamps, equipment identification, location information, etc. to ensure the traceability and accuracy of the data.

[0049] (2) Format: The format of the printed strips is usually paper strips or rolls, on which the data is printed directly by the printer. The format should be easy to read and archive, and common ones include tabular form or continuous time series records.

[0050] Printed strips provide an immediate physical record of environmental monitoring data for subsequent review and comparison. If the monitored data is outside the normal range, the abnormal reading on the printed strip can quickly alert the operator to check or take action. The printed strip can also be used to compare with electronic records to verify the consistency and accuracy of the data.

[0051] The printed strips of environmental monitoring equipment are an important part of environmental monitoring and management. They provide a fast and intuitive way to record data, and are important for ensuring environmental safety and responding to environmental changes. This application is based on the characteristics and content of environmental monitoring printed strips. It uses OCR technology, grayscale, binarization and other technologies as data capture methods, adds knowledge bases and algorithm libraries as the basic foundation, and combines convolutional neural network CNN technology to identify basic parameters such as oxygen content, operating flow rate, flow rate, and verify the fitting calculation results. It forms problem recognition logic and algorithms for format review, sampling period review, flow rate and gas volume calculation for professional printed strips, and realizes rapid diagnosis of environmental monitoring printed strips in different industries and processes.

[0052] A flowchart of a specific implementation method of the method for identifying small strip problems of environmental monitoring equipment provided in this application is as follows: Figure 1 As shown, the method includes:

[0053] S101: Acquire a digital image of a small strip printed by an environmental monitoring device.

[0054] Specifically, a scanner or high-resolution camera can be used to capture the image of the printed strip, so that the captured image is clear and all text and graphics are recognizable. The image format can be saved in a high-quality digital format such as JPEG, PNG or TIFF for subsequent processing.

[0055] S102: Extract features from the digital image to obtain data to be verified.

[0056] This step can specifically use optical character recognition (OCR) technology to extract data from the printed strip and convert the extracted data into editable text content as the data to be verified. This step can convert the text in the image into text data that can be processed by the machine, providing a basis for the next step of feature comparison.

[0057] Before this step, the digital image may be preprocessed, including but not limited to grayscale, binarization, and image denoising and enhancement, in order to improve the image quality and highlight key information.

[0058] Optionally, after feature extraction, data may also be parsed to obtain key information as data to be verified.

[0059] S103: Calling a pre-established knowledge base and algorithm library.

[0060] The knowledge base stores standard data related to environmental monitoring, including printing strip format requirements, basic information judgment rules, a calculation model group consisting of industry specifications, and theoretical thresholds based on industry characteristics; the algorithm library includes a variety of calculation methods and logic checking methods for verifying and identifying problems in printing strip data.

[0061] In this application, the knowledge base stores industry experience and specification summaries. The knowledge base may include, but is not limited to: field query, environmental monitoring specifications, industry experience. Algorithms are used to analyze the extracted data as a method of identifying possible deviations and anomalies. The algorithm library may include, but is not limited to: format review, sampling period verification, flow calculation, and gas volume calculation.

[0062] S104: Based on the calculation method and logic check method in the algorithm library, a convolutional neural network is used to perform fitting calculation on the data to be verified, and the obtained calculation result is compared with the standard data in the knowledge base, and a verification result is generated based on the comparison result to determine whether there is an abnormality in the print strip of the environmental monitoring device.

[0063] This step uses feature comparison to identify the text in the printed strip to be reviewed, combines the knowledge base and algorithm library, and uses convolutional neural network technology to perform deep learning to achieve automatic detection of logical problems in printed strips of manual monitoring equipment in the field of environmental monitoring.

[0064] It is understood that this step not only compares the text extracted by OCR, but also compares this data with preset environmental monitoring specifications and industry experience to identify possible anomalies. Feature comparison may include but is not limited to comparing the logical consistency of the data, format correctness, and consistency with historical data or industry standards.

[0065] In this process, a convolutional neural network (CNN) is used as an anomaly recognition algorithm. The model corresponding to this convolutional neural network is suitable for processing structured text and image data. The model can learn and recognize complex patterns and associations from data.

[0066] Convolutional Neural Network Network Architecture: A CNN architecture that includes convolutional layers, pooling layers, and fully connected layers. Convolutional layers are used to extract local features in an image, pooling layers are used to reduce the spatial size of features (reduce computational effort), and fully connected layers are used to output classification or regression results. During model training, the CNN model is trained using historical data and annotated samples. This includes samples of both normal and abnormal situations to improve the accuracy and robustness of the model.

[0067] Input the data to be verified into the trained CNN model to obtain the prediction results. Compare the output of CNN with the standard data in the knowledge base. Check whether the format requirements are met and whether the values ​​are within the allowed threshold range. If the data deviates from the preset standard, mark it as an anomaly. Furthermore, the specific anomaly type and possible causes can also be recorded.

[0068] S105: Feedback the verification result to the user.

[0069] Specifically, the verification results can be divided into two conditions: "no abnormality" and "abnormality". If "no abnormality" is displayed, it is considered to have passed the verification; if "abnormality" is displayed, an alarm prompt will appear, indicating that the verification has not passed. After obtaining the verification results, they can be further fed back to the user through a visual display interface. The displayed items can include all detailed information to be verified and any abnormalities identified.

[0070] This application significantly reduces the time for manual input and analysis of data through automated image processing and data recognition, and realizes the rapid extraction and processing of data from printed strips. The use of convolutional neural networks to accurately identify text and symbols on printed strips reduces the misunderstandings or errors that may occur in traditional manual reading. By comparing with standard data in the knowledge base, it ensures that all data is processed and interpreted according to unified standards, thereby improving the consistency and reliability of the data. It can be seen that this application realizes the automatic verification of problems in manually monitored printed strips, and improves the problem identification ability and efficiency of monitoring data.

[0071] In order to achieve rapid diagnosis of environmental monitoring print strips, the embodiments provided in this application can construct a comprehensive system that uses OCR technology, image processing technology (such as grayscale, binarization), knowledge base, algorithm library and convolutional neural network (CNN) to achieve automatic data verification and problem identification. Figure 2 A schematic diagram showing another specific implementation of the method for identifying problems with printed strips of environmental monitoring equipment provided by the present application, in combination with the attached Figure 2 The specific implementation process of this process is:

[0072] Raw data acquisition, which usually involves scanning or photographing small strips of manually monitored print to obtain a digital image.

[0073] After acquiring the digital image, the image can be preprocessed, including grayscale processing to convert the color image into a grayscale image to reduce the complexity of processing; binarization processing to convert the image into black and white to highlight the contrast between the text and the background, which is convenient for subsequent text recognition; noise removal is used to clean up the interference elements in the image. The preprocessing operation helps to clearly display the text in the image, which is convenient for subsequent OCR technology to perform text recognition. The main purpose of this step is to optimize the image quality and improve the accuracy of text recognition. Use OCR technology to extract text data from the optimized image. These text data will be used for subsequent data comparison and analysis, which is the key link in data processing, converting image data into an operable text format.

[0074] Parse the text extracted by OCR to identify key parameters, such as oxygen content, operating flow, flow rate, etc. In this step, a parsing algorithm can be used to identify and extract numbers and their units. Use convolutional neural network (CNN) technology to perform deep learning analysis on the extracted text and compare the data in the knowledge base and algorithm library. The core of this step is to use machine learning technology to automatically analyze data and detect anomalies and errors in the data.

[0075] Among them, the format review can check whether the data on the environmental monitoring printout meets the industry standards. The sampling period review can verify whether the time of data collection meets the specified sampling period. The flow and gas volume calculation is used to calculate and verify whether the flow and gas collection volume are accurate.

[0076] The analysis results are classified as normal or abnormal, with normal data displayed as passed and abnormal data triggering an alarm. The final results can be used for real-time monitoring or archived for future review or further analysis.

[0077] All components in the system can be integrated into a user-friendly interface, ensuring that all operations can be performed with simple operations.

[0078] As a specific implementation, the standard format requirements for printed strips include text fonts, standard line spacing, and numbering rules. Through convolutional neural networks, the standard format of printed strips can be reviewed to identify problems such as different number digits, disordered or identical numbering, and thus identify problems such as fake printed strips.

[0079] In this embodiment, based on the calculation method and logic check method in the algorithm library, a convolutional neural network is used to perform fitting calculations on the data to be verified, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, a verification result of whether there is an abnormality in the printed strips of the environmental monitoring equipment is generated, including: using a convolutional neural network to review the standard format and verify the numbering problems of the printed strips. When there are problems such as the format not meeting the standard format requirements, different number of digits, disordered number sorting or the same numbers, it is determined that the printed strips are forged, and a verification result indicating that the printed strips are abnormal is generated.

[0080] Among them, the basic information judgment rules include sampling point information, time rules, personnel arrangement rules, and signature authentication standards. Sampling point information: used to record the standard operation and historical data of each sampling point. Time rules: used to record the provisions of sampling time intervals and time windows to determine whether there are time conflicts or duplications. Personnel arrangement rules: used to record the person in charge of each sampling point and his or her work schedule to detect personnel logic conflicts. Signature authentication standards: used to record what kind of signature is considered valid, including the format of the signature and the required authentication information.

[0081] The calculation method and logic checking method based on the algorithm library adopt a convolutional neural network to perform fitting calculation on the data to be verified, compare the obtained calculation result with the standard data in the knowledge base, and generate the verification result of whether there is an abnormality in the printed strip of the environmental monitoring equipment based on the comparison result, including: comparing the time and point data on each printed strip with the rules in the knowledge base to check whether there are repeated sampling records at or within adjacent times; checking the personnel schedule in the knowledge base according to the operator and time recorded on the printed strip to detect whether there is a logical conflict (for example, the same person takes samples at different locations at the same time); checking whether the signature on the printed strip meets the preset validity standard: including the style and position of the signature and whether it contains necessary authentication elements (such as date and timestamp); generating the verification result of whether there is an abnormality in the printed strip of the environmental monitoring equipment based on the comparison result.

[0082] As a specific implementation method, the knowledge base may include a calculation model group composed of industry specifications such as HJ / T397-2007 and GB / T16157-1996, such as sampling flow rate calculation formulas, sampling volume calculation formulas, and theoretical thresholds based on industry characteristics, such as the benchmark oxygen content of coke oven chimneys after the implementation of ultra-low oxygen in the coking industry is 8%, the benchmark oxygen content in the exhaust gas of oxidized kilns in industrial kilns is 8%, the benchmark oxygen content in the exhaust gas of reduced kilns is 5%, the exhaust gas of cement kilns and kiln tail waste heat utilization systems is 10, the exhaust gas of drying equipment using an independent heat source is 8, the benchmark oxygen content of non-pure oxygen combustion glass melting furnace flue gas is 8%, the benchmark oxygen content of thermal power coal-fired boilers is 6%, and the benchmark oxygen content of the ceramic industry is 18.

[0083] The algorithm library can also include time, flow, and volume calculation methods other than the standard models required in the knowledge base, and check the key parameters such as sampling time, sampling number, sampling frequency, and sampling volume with the standard requirements of the knowledge base. For example, HJ / T 397-2007 stipulates that for boiler particulate matter sampling, multi-point sampling is required. In principle, the sampling time of each point should not be less than 3 minutes, and the sampling time of each point should be equal or the total gas volume collected by each boiler during the measurement should not be less than 1m. At least 3 samples should be collected for each sampling, and the average value should be taken.

[0084] The algorithm library includes sampling flow rate and sampling flow calculation. The sampling flow rate is calculated by dynamic pressure, static pressure, and Pitot tube correction coefficient. The calculation result is compared with the printed strip value. If the deviation rate exceeds a certain value, it is considered abnormal. Based on the calculation method and logic check method in the algorithm library, a convolutional neural network is used to fit the data to be checked, and the calculated result is compared with the standard data in the knowledge base. Based on the comparison result, the verification result of whether there is an abnormality in the printed strip of the environmental monitoring equipment is generated, including:

[0085] The flow rate is calculated according to the sampling flow rate calculation formula in the algorithm library. The flow rate calculation formula used is:

[0086]

[0087] Among them, V s Indicates the gas velocity of wet exhaust gas, in m / s; V a Indicates the air velocity in the ventilation duct at normal temperature and pressure, in m / s; B a Indicates atmospheric pressure, in Pa; K p Indicates the Pitot tube correction factor; P d Indicates exhaust dynamic pressure, unit is Pa; P s Indicates exhaust static pressure, in Pa; ρ s Indicates the density of wet exhaust gas in kg / m 3 ;M s Indicates the molecular weight of wet exhaust gas, in kg / kmol; t s Indicates the exhaust temperature in °C; compares the calculated flow rate with the theoretical flow rate threshold in the knowledge base. If it exceeds the theoretical flow rate threshold, it is determined that an abnormality exists, and generates a verification result that the environmental monitoring device prints an abnormal strip.

[0088] Based on the sampling nozzle diameter, sampling flow rate, and sampling time, the sampling volume is calculated according to the sampling volume calculation formula in the algorithm library, and the calculated sampling volume is compared with the sampling volume theoretical threshold in the knowledge base. If the sampling volume theoretical threshold is exceeded, it is determined that an abnormality exists, and a verification result is generated that indicates that an abnormality exists in the printed strip of the environmental monitoring device.

[0089] The algorithm library may also include pre-meter pressure threshold recognition. The process includes: obtaining the pre-meter pressure, determining whether the pre-meter pressure exceeds the pre-meter pressure theoretical threshold, and if so, determining that there is an abnormality, and generating a verification result that the environmental monitoring device prints a small strip with an abnormality.

[0090] As a specific implementation, the algorithm library may include anomaly recognition for oxygen content, flow rate, smoke temperature, oxygen content, and humidity differences of multiple samples at the same point exceeding a certain limit. In this embodiment, feature extraction is performed on the digital image to obtain the data to be verified, including: extracting text data from the digital image using optical character recognition technology, parsing the text data to identify key parameters, and obtaining the data to be verified; the data to be verified includes oxygen content, flow rate, smoke temperature, and humidity. Normal ranges or specific thresholds for various environmental parameters (such as oxygen content, flow rate, smoke temperature, and humidity) are predefined. These threshold values ​​are formulated based on industry standards, historical data analysis, or expert opinions.

[0091] The calculation method and logic checking method based on the algorithm library use a convolutional neural network to perform fitting calculation on the data to be verified, compare the obtained calculation result with the standard data in the knowledge base, and generate a verification result of whether there is an abnormality in the small strip printed by the environmental monitoring device based on the comparison result, including: performing numerical analysis on the data to be verified, calculating the average value, standard deviation and other statistical indicators of multiple samples at the same point; performing anomaly detection on each parameter, comparing the parameter value of each sample with a set threshold or average value; if the parameter value of the sample exceeds the set threshold or average value, it is determined that there is an abnormality, and a verification result of whether there is an abnormality in the small strip printed by the environmental monitoring device is generated.

[0092] The algorithm library includes constant speed tracking sampling review. When the sampling flow rate deviation rate of different printed strips at the same point is less than a certain value, it is judged as constant flow sampling, that is, constant speed tracking sampling that does not meet the specification requirements. In this embodiment, based on the calculation method and logic inspection method in the algorithm library, a convolutional neural network is used to fit the data to be verified, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether there are abnormalities in the printed strips of the environmental monitoring equipment are generated, including:

[0093] Collect sampling flow rate data at each sampling point from the printed strips of environmental monitoring equipment;

[0094] Conduct statistical analysis on the collected sampling flow rate data and calculate the mean value, standard deviation and deviation rate;

[0095] According to the deviation rate threshold set in the knowledge base, the calculated deviation rate is compared with the deviation rate threshold to determine whether it meets the requirements of constant-speed tracking sampling. If it does not meet the requirements, it is determined that there is an abnormality and a verification result is generated that the environmental monitoring equipment prints an abnormality in the strip.

[0096] In any of the above embodiments, before obtaining the digital image of the environmental monitoring equipment print strip, the process of solidifying the industry and parameters of the environmental monitoring equipment print strip may also be included. Industry and parameter solidification refers to specific print strip indicators brought about by industry and process characteristics, including indicator types, types, threshold ranges, calculation formulas, unit conversions, etc., which are used to preset format review and judgment logic functions to prevent interference from other industry judgments. Industry and parameter solidification can be manually input by the knowledge base and the algorithm library. By selecting industries and processes to solidify the parameters to be reviewed with industry characteristics, the knowledge base and algorithm library used for feature comparison can be used.

[0097] The specific implementation of this process can be: obtaining input information on the industry type, process, and operating conditions of the environmental monitoring equipment print strip; loading corresponding data from the knowledge base and algorithm library based on the industry type, process, and operating conditions of the environmental monitoring equipment print strip.

[0098] By presetting industry-specific parameters and standards, the system can interpret the data on the printed strip more accurately and avoid misunderstandings caused by differences in standards between industries. Specific parameters and standards make it unnecessary for the system to determine the meaning and processing method of each parameter from scratch when processing data, thereby speeding up the data processing process. It also ensures that the analysis will not be interfered by irrelevant industry standards, because each industry may have different monitoring standards and environmental factors of concern.

[0099] After obtaining the digital image of the printed strip of the environmental monitoring device, the method further includes: performing image preprocessing on the digital image, wherein the image preprocessing includes grayscale processing, binarization processing, and noise removal processing on the digital image. The preprocessing operation can reduce the data dimension, provide better contrast and brightness information, and make the image features easier to analyze and identify, thereby quickly identifying the printed strip data and standardizing the data.

[0100] In addition, the present application also provides a device for identifying problems of printing small strips of environmental monitoring equipment, such as Figure 3As shown in the structural block diagram of the device for identifying small print strip problems of environmental monitoring equipment provided in the present application, the device includes a memory 31 and a processor 32, and the memory 31 stores a computer program. When the computer program is executed by the processor 32, it implements the method for identifying small print strip problems of environmental monitoring equipment according to any of the above-mentioned methods.

[0101] The device for identifying problems in printing small strips of environmental monitoring equipment provided in the present application corresponds to the method for identifying problems in printing small strips of environmental monitoring equipment mentioned above. The corresponding contents can be referred to the above introduction and will not be repeated here.

[0102] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for identifying problems with printing small strips of environmental monitoring equipment according to any of the above-mentioned methods is implemented.

[0103] Computer readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0104] The professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0105] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0106] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for identifying problems with printed strips of environmental monitoring equipment, characterized in that: include: Acquire a digital image of a strip printed by an environmental monitoring device; Extracting features from the digital image to obtain data to be verified; Calling a pre-established knowledge base and algorithm base; the knowledge base stores standard data related to environmental monitoring, the standard data including print strip format requirements, basic information judgment rules, a calculation model group consisting of industry specifications, and theoretical thresholds based on industry characteristics; the algorithm base includes a variety of calculation methods and logic checking methods for checking and identifying problems in print strip data; Based on the calculation method and logic checking method in the algorithm library, a convolutional neural network is used to perform fitting calculation on the data to be verified, and the obtained calculation result is compared with the standard data in the knowledge base, and a verification result of whether there is an abnormality in the print strip of the environmental monitoring equipment is generated based on the comparison result; The verification result is fed back to the user.

2. The method for identifying problems with printed strips of environmental monitoring equipment according to claim 1, characterized in that: The standard format requirements for printing strips include text fonts, standard line spacing, and numbering rules; The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including: The printed strips are reviewed for standard format and numbering issues through a convolutional neural network. If the format does not meet the standard format requirements, the number of digits is different, the number order is disordered, or there are problems with the same number, the printed strips are judged to be forged and a verification result indicating that the printed strips are abnormal is generated.

3. The method for identifying problems with printed strips of environmental monitoring equipment according to claim 1, characterized in that: The basic information judgment rules include sampling point information, time rules, personnel arrangement rules, and signature authentication standards; The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including: Analyze the time and point data on each printed strip to check whether there are repeated sampling records or adjacent sampling records; check the personnel schedule in the knowledge base according to the operators and time recorded on the printed strip to detect whether there are logical conflicts; check whether the signature on the printed strip meets the preset validity standards: including the style and position of the signature and whether it contains authentication elements; generate verification results based on the comparison results to determine whether there are any abnormalities in the printed strips of environmental monitoring equipment.

4. The method for identifying problems with printed strips of environmental monitoring equipment according to any one of claims 1 to 3, characterized in that: The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including: The flow rate is calculated according to the sampling flow rate calculation formula in the algorithm library. The flow rate calculation formula used is: Among them, V s Indicates the gas velocity of wet exhaust gas, in m / s; V a Indicates the air velocity in the ventilation duct at normal temperature and pressure, in m / s; B a Indicates atmospheric pressure, in Pa; K p Indicates the Pitot tube correction factor; P d Indicates exhaust dynamic pressure, unit is Pa; P s Indicates exhaust static pressure, in Pa; ρ s Indicates the density of wet exhaust gas in kg / m 3 ;M s Indicates the molecular weight of wet exhaust gas, in kg / kmol; t s Indicates the exhaust temperature in °C; compares the calculated flow rate with the theoretical flow rate threshold in the knowledge base, and if it exceeds the theoretical flow rate threshold, it is determined that an abnormality exists, and generates a verification result that the environmental monitoring device prints an abnormality in the strip; Based on the sampling nozzle diameter, sampling flow rate, and sampling duration, the sampling volume is calculated according to the sampling volume calculation formula in the algorithm library, and the calculated sampling volume is compared with the sampling volume theoretical threshold in the knowledge base. If the sampling volume theoretical threshold is exceeded, it is determined that an abnormality exists, and a verification result that the environmental monitoring device prints an abnormality is generated; The pre-meter pressure is obtained to determine whether the pre-meter pressure exceeds the theoretical threshold of the pre-meter pressure. If so, it is determined that an abnormality exists, and a verification result indicating that an abnormality exists in the print strip of the environmental monitoring device is generated.

5. The method for identifying problems of printed strips of environmental monitoring equipment according to claim 4, characterized in that: The extracting features of the digital image to obtain the data to be verified comprises: Extracting text data from the digital image using optical character recognition technology, parsing the text data to identify key parameters, and obtaining data to be verified; the data to be verified includes oxygen content, flow rate, smoke temperature and humidity; The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including: Perform numerical analysis on the data to be verified, calculate the average value, standard deviation and other statistical indicators of multiple samples at the same point; perform anomaly detection on each parameter, and compare the parameter value of each sample with the set threshold or average value; if the parameter value of the sample exceeds the set threshold or average value, it is determined that an anomaly exists, and generate a verification result indicating that an abnormality exists in the print strip of the environmental monitoring equipment.

6. The method for identifying problems with printed strips of environmental monitoring equipment according to claim 4, characterized in that: The calculation method and logic checking method in the algorithm library are used to fit the data to be checked using a convolutional neural network, and the obtained calculation results are compared with the standard data in the knowledge base. Based on the comparison results, the verification results of whether the printed strip of the environmental monitoring equipment is abnormal are generated, including: Collect sampling flow rate data at each sampling point from the printed strips of environmental monitoring equipment; Conduct statistical analysis on the collected sampling flow rate data and calculate the mean value, standard deviation and deviation rate; According to the deviation rate threshold set in the knowledge base, the calculated deviation rate is compared with the deviation rate threshold to determine whether it meets the requirements of constant-speed tracking sampling. If it does not meet the requirements, it is determined that there is an abnormality and a verification result is generated that the environmental monitoring equipment prints an abnormality in the strip.

7. The method for identifying problems with printed strips of environmental monitoring equipment according to any one of claims 1 to 3, characterized in that: Before obtaining the digital image of the small strip printed by the environment monitoring device, the method further includes: Obtaining input information on the industry type, process, and working conditions of the environmental monitoring equipment printing strip; Based on the industry type, process, and working conditions to which the small strip printed by the environmental monitoring equipment belongs, corresponding data is loaded from the knowledge base and algorithm library.

8. The method for identifying problems with printed strips of environmental monitoring equipment according to claim 7, characterized in that: After obtaining the digital image of the printed strip of the environmental monitoring device, the method further includes: The digital image is subjected to image preprocessing, wherein the image preprocessing includes grayscale processing, binarization processing, and noise removal processing on the digital image.

9. A device for identifying problems in printing strips of environmental monitoring equipment, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying print strip problems of an environmental monitoring device according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for identifying problems of printing small strips of environmental monitoring equipment according to any one of claims 1-8 is implemented.

Images