Chemical production safety early warning system and method based on big data

Abstract

The invention discloses a chemical production safety early warning system and method based on big data, and relates to the technical field of safety early warning, and the method comprises the steps: firstly obtaining electrostatic data and caking data, carrying out the preprocessing, carrying out the comprehensive evaluation, obtaining a chemical material caking evaluation value, and judging whether a chemical material is caked or not; if caking occurs, a first type of early warning is sent out, then the next step is executed, and if not, the next step is directly executed; and then, obtaining blockage data, carrying out primary processing and comprehensive evaluation to obtain a pipeline or tank blockage evaluation value so as to judge whether the pipeline or the tank is blocked or not, if so, sending out a second early warning and prompting maintenance, and meanwhile, obtaining the blockage data in real time until the blockage data is judged to be normal, and if not, continuing detection. When the pipeline or the tank body is judged to be blocked, a second early warning is given out to prompt workers to overhaul, and the situation that early warning cannot be conducted in time due to the fact that static electricity is generated due to friction, chemical materials are caked and block the pipeline or the tank body is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of safety warning, and specifically to a chemical production safety warning system and method based on big data. Background Art

[0002] Chemical production involves a variety of hazardous chemicals and complex technological processes. A slight oversight may trigger accidents such as fires, explosions, and leaks, resulting in casualties, environmental pollution, and significant economic losses. Therefore, chemical production requires safety warnings. By real-time monitoring the operating status of equipment, technological parameters, and the storage and transportation of hazardous chemicals, potential risks can be detected in advance, and measures can be taken in a timely manner to prevent and control them, thereby effectively reducing the probability of accidents, ensuring the safe and stable operation of the production process, and protecting the safety of personnel's lives and the property of enterprises.

[0003] During the production process of chemical materials, it is necessary to put chemical materials into pipelines or tanks. To prevent the blockage of chemical materials in pipelines or tanks, which may cause excessive pressure in the pipelines or tanks and lead to rupture and explosion, affecting production safety, early warnings for pipeline or tank blockages are required.

[0004] For example, a chemical industrial park safety risk warning system and method disclosed in the invention patent with the publication number: CN118747942A includes the following steps: an industrial control system, a chemical industrial park intelligent management and control platform, and a fusion positioning platform. Among them, the industrial control system is used to collect process control data and send it to the chemical industrial park intelligent management and control platform; the chemical industrial park intelligent management and control platform is used to collect chemical industrial park business data, obtain a static risk database and a dynamic risk database based on the process control data and chemical industrial park business data, and determine the regional risk index; the fusion positioning platform is used to perform grid division based on park positioning data to obtain park grid data and obtain a four-color map of regional dynamic risks based on the grid. This application can effectively solve the problems of the lack of a dynamic calculation model for regional risks in chemical industrial parks and risk display based on positioning. At the same time, the regional risk data can provide dynamic regional risk data for each business application module in the park, providing guidance for the daily safety management of chemical industrial parks.

[0005] For example, a chemical gas leakage safety feedback system and method disclosed in the invention patent with the publication number: CN117007247B includes: a control management platform and an operation analysis platform. A server is set in the control management platform, and the server is communicatively connected to a position acquisition unit and a risk prompt unit. A controller is set in the operation analysis platform. The present invention monitors the airtightness by analyzing the states of each bolt on chemical equipment, and monitors the states of each bolt in real time, giving early warnings about the loosening risks of bolts, facilitating relevant personnel to maintain the states of each bolt in advance.

[0006] In the prior art, the problem of timely warning has not been effectively solved, that is, during the loading, unloading and storage of chemical materials in pipelines or tanks, static electricity is generated due to friction, resulting in the caking of chemical materials and blocking of pipelines or tanks. Summary of the Invention

[0007] Technical Problem to be Solved

[0008] In view of the deficiencies of the prior art, the present invention provides a chemical production safety warning system and method based on big data, which solves the problem of lack of warning for caking and blockage caused by frictional static electricity during the loading, unloading and storage of chemical materials in the prior art.

[0009] Technical Solution

[0010] To achieve the above object, the present invention is realized through the following technical solutions: A chemical production safety warning system and method based on big data, including the following specific steps: Step 1: Obtain static electricity data and caking data, preprocess the static electricity data and caking data, and comprehensively evaluate the preprocessed static electricity data and caking data to obtain a chemical material caking evaluation value; Step 2: Judge the caking of chemical materials according to the chemical material caking evaluation value; Step 3: If it is judged that the chemical materials are caked, issue a first warning and execute Step 4; if it is judged that the chemical materials are normal, directly execute Step 4; Step 4: Obtain blockage data, perform preliminary processing on the blockage data, and comprehensively evaluate the preprocessed blockage data to obtain a pipeline or tank blockage evaluation value; Step 5: Judge the blockage of the pipeline or tank according to the pipeline or tank blockage evaluation value; Step 6: If it is judged that the pipeline or tank is blocked, issue a second warning to prompt the staff to repair, and return to Step 4 to obtain blockage data in real time until it is judged that the pipeline or tank is normal; if it is judged that the pipeline or tank is normal, continue the detection.

[0011] Further, in Step 1, the static electricity data includes static electricity voltage and static electricity discharge sound, the caking data includes the current crystal particle size and the current chemical material temperature, and the static electricity data and caking data are subjected to filtering and noise reduction processing; the filtered and noise-reduced static electricity data and caking data are normalized and comprehensively analyzed to obtain a static electricity influence coefficient and a caking severity coefficient; the static electricity influence coefficient and the caking severity coefficient are standardized and comprehensively evaluated to obtain a chemical material caking evaluation value; Among them, JP represents the chemical material caking evaluation value, DY represents the static electricity influence coefficient, k1 represents the slope of the static electricity influence coefficient, and KY represents the caking severity coefficient.

[0012] Further, the specific method for obtaining the static electricity influence coefficient is as follows: Set a voltage presence value. If a static electricity voltage is detected, assign a value to the voltage presence value, and the assigned value is not equal to zero. Statistically analyze the changes in the static electricity voltage to obtain a voltage group, calculate the average value of the voltage group to obtain an average voltage value, calculate the voltage group using the variance method based on the average voltage value to obtain a voltage disorder value. If no static electricity voltage is detected, continue the detection and assign a value to the voltage presence value, and the assigned value is equal to zero. Comprehensively analyze the static electricity discharge sound using big data technology to obtain the number of static electricity discharge sound waveforms. Comprehensively analyze the voltage presence value, the voltage disorder value, and the number of static electricity discharge sound waveforms to obtain the static electricity influence coefficient.

[0013] Further, the specific method for obtaining the number of static electricity discharge sound waveforms is as follows: Convert the static electricity discharge sound into a static electricity discharge waveform, use Fourier transform on the static electricity discharge waveform to transform the static electricity discharge waveform that is chaotic in the time and space domain into a sine or cosine static electricity discharge waveform in the frequency domain. The sine or cosine static electricity discharge waveform includes amplitude and frequency. Group the sine or cosine static electricity discharge waveforms with similar amplitudes and frequencies through big data technology and store them in the sound waveform type database. Classify the sine or cosine static electricity discharge waveforms, count the number of each group of sine or cosine static electricity discharge waveforms, select one of the sine or cosine static electricity discharge waveforms in each group to perform similarity matching with a preset standard sine or cosine static electricity discharge waveform, and arrange them in ascending order of similarity. Select the group with the highest similarity and determine the number to obtain the number of static electricity discharge sound waveforms.

[0014] Further, the specific method for obtaining the severe caking coefficient is as follows: Obtain the standard crystal particle size and the standard chemical material temperature. Comprehensively analyze the current crystal particle size, the standard crystal particle size, the current chemical material temperature, and the standard chemical material temperature to obtain the severe caking coefficient.

[0015] Further, in step two, compare the chemical material caking threshold with the chemical material caking evaluation value in real time. If the chemical material caking evaluation value is greater than or equal to the chemical material caking threshold, it is determined that the chemical material is caked. If the chemical material caking evaluation value is less than the chemical material caking threshold, it is determined that the chemical material is normal.

[0016] Further, in step four, the blockage data includes expansion stress and the temperature inside the pipeline or tank. Perform filtering and noise reduction processing on the blockage data. Perform normalization processing and comprehensive analysis on the blockage data after filtering and noise reduction processing to obtain the blockage severity coefficient. Perform standardization processing and comprehensive evaluation on the blockage severity coefficient and the severe caking coefficient to obtain the pipeline or tank blockage evaluation value.

[0017] Further, the specific method for obtaining the clogging severity coefficient is as follows: When a change in expansion stress is detected, the (m + 1)-th expansion stress is compared with the m-th expansion stress in real time. If the (m + 1)-th expansion stress is greater than the m-th expansion stress, a quantity statistic is performed to obtain the expansion stress quantity. If the (m + 1)-th expansion stress is less than or equal to the m-th expansion stress, the detection continues until the (m + 1)-th expansion stress is equal to or greater than the bearing limit value of the pipeline or tank and then stops; According to the heat transfer principle, the heat dissipation time of the pipeline or tank is set. If the temperature inside the pipeline or tank is greater than the ambient temperature, the temperature inside the pipeline or tank dissipates heat to the surroundings until it equals the ambient temperature and then stops. The heat dissipation time of the pipeline or tank is assigned a value, and the value is the difference between the temperature inside the pipeline or tank and the ambient temperature; If the temperature inside the pipeline or tank is less than or equal to the ambient temperature, the heat dissipation time of the pipeline or tank is assigned a value, and the value is equal to one; The heat dissipation time, the m expansion stresses, the (m + 1)-th expansion stress, and the m-th expansion stress are comprehensively analyzed to obtain the clogging severity coefficient.

[0018] Further, in step five, the clogging threshold of the pipeline or tank is compared with the clogging evaluation value of the pipeline or tank in real time; If the clogging evaluation value of the pipeline or tank is greater than or equal to the clogging threshold of the pipeline or tank, it is determined that the pipeline or tank is clogged; If the clogging evaluation value of the pipeline or tank is less than the clogging threshold of the pipeline or tank, it is determined that the pipeline or tank is normal.

[0019] Further, a data acquisition module is used to acquire electrostatic data, caking data, and clogging data and preprocess them to obtain preprocessed data, and send the preprocessed data to the data analysis module; The data analysis module is used to receive the preprocessed data and analyze the preprocessed data to make judgments on the caking of chemical materials and the clogging of pipelines or tanks, and send the judgment results of the caking of chemical materials and the judgment results of the clogging of pipelines or tanks to the data execution module respectively; The data execution module is used to receive the judgment results of the caking of chemical materials and the judgment results of the clogging of pipelines or tanks, and give early warnings for the judgment results of the caking of chemical materials and the judgment results of the clogging of pipelines or tanks.

[0020] Beneficial effects

[0021] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0022] 1. By acquiring electrostatic data and caking data, preprocessing and comprehensively evaluating them, a caking evaluation value of chemical materials is obtained, improving the accuracy for judging whether chemical materials are caked.

[0023] 2. By acquiring clogging data, preprocessing and comprehensively evaluating them, a clogging evaluation value of the pipeline or tank is obtained, improving the accuracy for judging whether the pipeline or tank is clogged.

[0024] 3. When it is determined that the chemical materials are caked, the first type of warning is issued to promptly remind the staff that there is caking in the pipeline or tank. In order to avoid blockage of the pipeline or tank by the caking, timely treatment is carried out.

[0025] 4. When it is determined that the pipeline or tank is blocked, the second type of warning is issued to prompt the staff to carry out maintenance, so as to avoid the generation of static electricity due to friction, resulting in caking of chemical materials and blockage of the pipeline or tank without timely warning.

[0026] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. Description of the Drawings

[0027] Figure 1 This is for the present invention: Flow chart of the chemical production safety warning method based on big data.

[0028] Figure 2 This is for the present invention: Broken line graph of the influence of static voltage on the temperature in the pipeline or tank.

[0029] Figure 3 This is for the present invention: Structure diagram of the chemical production safety warning system based on big data. Detailed Embodiment

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0032] As Figure 1 shown, the embodiments of the present invention provide a chemical production safety warning method based on big data, which includes the following specific steps:

[0033] Step 1: Set up a charge sensor, a digital microphone, a laser particle size analyzer, a first temperature sensor, a second temperature sensor, and a pressure sensor; obtain electrostatic data in real time through the charge sensor and the digital microphone. Due to the characteristics of high resistivity and dielectric constant differences of chemical materials themselves, static electricity will be generated by friction during the loading and unloading in pipelines or tanks. Static electricity will cause charges to attach to the surface of loose crystal particles in chemical materials, and the particles will approach and aggregate due to the attraction of charges. At the same time, the heat generated by static electricity will cause the local temperature of the crystal particles to rise, accelerating the dissolution and recrystallization process on the crystal surface, making the crystal particles more likely to adhere and form lumps; the electrostatic data includes the electrostatic voltage obtained in real time by the charge sensor and the electrostatic discharge sound obtained in real time by the digital microphone. The electrostatic discharge sound is caused by the air vibration generated by the pressure wave after the static electricity accumulates to a certain extent and discharges.

[0034] Obtain agglomeration data in real time through the laser particle size analyzer and the first temperature sensor. The agglomeration data includes the current crystal particle size obtained in real time by the laser particle size analyzer and the current temperature of the chemical material obtained in real time by the first temperature sensor; the laser particle size analyzer accurately detects the size of the crystal particles of the chemical material. When the chemical material agglomerates, its particle size will increase; the first temperature sensor detects the temperature of the chemical material. After the crystal particles agglomerate, not only the surface area of the chemical material becomes smaller, resulting in a decrease in the heat dissipation ability of the chemical material, but also the electrostatic discharge will release heat. As Figure 2 shown, and then the temperature on the surface of the chemical material will rise after the chemical material agglomerates;

[0035] Table 1 Influence of Electrostatic Voltage on the Temperature in the Pipeline or Tank

[0036] Group Static voltage (V) Temperature inside the pipeline or tank (℃) 1 526 12 2 633 19 3 876 26

[0037] As shown in Table 1, in the relevant experiments studying the influence of electrostatic voltage on the temperature in the pipeline or tank, the following data were obtained; in Group 1, when the electrostatic voltage was 526V, the temperature in the pipeline or tank was 12°C; in Group 2, the electrostatic voltage increased to 633V, and the temperature also rose to 19°C; in Group 3, the electrostatic voltage reached 876V, and at this time the temperature in the pipeline or tank further increased to 26°C; from these data, it can be preliminarily seen that as the electrostatic voltage increases, the temperature in the pipeline or tank shows an upward trend;

[0038] Perform filtering and noise reduction processing on the electrostatic data and the agglomeration data to improve the quality of the electrostatic data and the agglomeration data; perform normalization processing and comprehensive analysis on the electrostatic data and the agglomeration data after filtering and noise reduction processing, eliminate the dimension and improve the calculation efficiency of the electrostatic data and the agglomeration data, and obtain the electrostatic influence coefficient and the agglomeration severity coefficient; perform standardization processing and comprehensive evaluation on the electrostatic influence coefficient and the agglomeration severity coefficient, further eliminate different dimensions and further improve the calculation efficiency of the electrostatic influence coefficient and the agglomeration severity coefficient, and obtain the chemical material agglomeration evaluation value;

[0039]

[0040] Among them, JP represents the evaluation value of chemical material caking, DY represents the static electricity influence coefficient, which reflects whether static electricity affects caking, k1 represents the slope of the static electricity influence coefficient and is an integer greater than one, which reflects the change trend of the static electricity influence coefficient, and KY represents the caking severity coefficient, which reflects the severity of chemical material caking.

[0041] The specific method for obtaining the static electricity influence coefficient is as follows:

[0042] The charge sensor detects in real time and sets a voltage presence value to measure whether there is voltage. If the charge sensor detects a static electricity voltage, the voltage presence value is assigned a value that is not equal to zero, and the change of the static electricity voltage is statistically obtained to form a voltage group. Since the contact area or force of the chemical material with the pipeline or tank body is different in different regions of the pipeline or tank body, the static electricity voltage detected by the charge sensor will change. The average value of the voltage group is calculated to obtain the average voltage value. The larger the average voltage value, the larger the voltage presence value. The voltage group is calculated using the variance method based on the average voltage value to obtain the voltage disorder value. If the charge sensor does not detect a static electricity voltage, the detection continues, and the voltage presence value is assigned a value equal to zero; the static electricity discharge sound is comprehensively analyzed using big data technology to obtain the number of static electricity discharge sound waveforms;

[0043] The voltage presence value, the voltage disorder value, and the number of static electricity discharge sound waveforms are comprehensively analyzed to obtain the static electricity influence coefficient;

[0044]

[0045] Among them, DY represents the static electricity influence coefficient, DC represents the voltage presence value, ensuring that when the average voltage value increases, the static electricity influence coefficient also increases, DW represents the voltage disorder value, which reflects whether the static electricity voltage is disordered. The more disordered the static electricity voltage, the greater the static electricity influence, and YB represents the number of static electricity discharge sound waveforms. The more the number, the greater the static electricity influence.

[0046] The specific method for obtaining the number of static electricity discharge sound waveforms is as follows:

[0047] The digital microphone converts the obtained electrostatic discharge sound into an electrostatic discharge waveform. The Fourier transform is used on the electrostatic discharge waveform to transform the electrostatic discharge waveform that is chaotic in the time - space domain into a sine or cosine electrostatic discharge waveform in the frequency domain. The sine or cosine electrostatic discharge waveform includes amplitude and frequency. Through big data technology, the sine or cosine electrostatic discharge waveforms with similar amplitudes and frequencies are grouped and stored in the sound waveform type database. Since the electrostatic discharge sound obtained by the digital microphone contains noise, it is necessary to classify the sine or cosine electrostatic discharge waveforms, count the quantity of each group of sine or cosine electrostatic discharge waveforms, select one of the sine or cosine electrostatic discharge waveforms in each group for similarity matching with a preset standard sine or cosine electrostatic discharge waveform, arrange them from the lowest to the highest similarity, select the group with the highest similarity and determine the quantity to obtain the quantity of the electrostatic discharge sound waveform.

[0048] The specific method for obtaining the caking severity coefficient is as follows:

[0049] The laser particle size analyzer obtains the standard crystal particle size during the normal detection of chemical engineering material crystal particles, and the first temperature sensor obtains the standard chemical engineering material temperature during the normal detection of chemical engineering material crystal particles; comprehensively analyze the current crystal particle size, the standard crystal particle size, the current chemical engineering material temperature, and the standard chemical engineering material temperature to obtain the caking severity coefficient;

[0050]

[0051] Among them, KY represents the caking severity coefficient, DC represents the current crystal particle size, the larger the current crystal particle size, the more serious the caking of the chemical engineering material, BC represents the standard crystal particle size, DW represents the current chemical engineering material temperature, the higher the current chemical engineering material temperature, the more serious the caking of the chemical engineering material, and BW represents the standard chemical engineering material temperature.

[0052] Step 2: Judge the caking of the chemical engineering material according to the caking evaluation value of the chemical engineering material;

[0053] Compare the caking threshold of the chemical engineering material with the caking evaluation value of the chemical engineering material in real - time; if the caking evaluation value of the chemical engineering material is greater than or equal to the caking threshold of the chemical engineering material, it is judged that the chemical engineering material is caked; if the caking evaluation value of the chemical engineering material is less than the caking threshold of the chemical engineering material, it is judged that the chemical engineering material is normal.

[0054] Step 3: If it is judged that the chemical engineering material is caked, issue the first type of warning and execute Step 4;

[0055] If it is judged that the chemical engineering material is normal, directly execute Step 4.

[0056] Step 4: Obtain the blockage data in real time through the pressure sensor and the second temperature sensor. The blockage data includes the expansion stress obtained in real time by the pressure sensor and the temperature inside the pipeline or tank obtained in real time by the second temperature sensor. The expansion stress is the force that causes the pipeline or tank to have an expansion trend; the caking of chemical materials will cause the pipeline or tank to be blocked and generate a gradually increasing pressure on the inner walls of the pipeline or tank. And when the pipeline or tank is blocked, the air inside it is not circulated, so the temperature inside the pipeline or tank is difficult to dissipate heat. Filter and denoise the blockage data to improve the quality of the blockage data; perform normalization processing and comprehensive analysis on the filtered and denoised blockage data to eliminate the dimension and improve the calculation efficiency of the blockage data, and obtain the blockage severity coefficient. Standardize and comprehensively evaluate the blockage severity coefficient and the caking severity coefficient to further eliminate different dimensions and further improve the calculation efficiency of the blockage severity coefficient and the caking severity coefficient, and obtain the pipeline or tank blockage evaluation value;

[0057]

[0058] Among them, SP represents the pipeline or tank blockage evaluation value, SY represents the blockage severity coefficient, which reflects the severity of the blockage of chemical materials, k2 represents the slope of the blockage severity coefficient and is an integer greater than one, which reflects the change trend of the blockage severity coefficient, and KY represents the caking severity coefficient, which reflects the severity of the caking of chemical materials.

[0059] The specific method for obtaining the blockage severity coefficient is as follows:

[0060] When the pressure sensor detects a change in the expansion stress, the (m + 1)-th expansion stress is compared with the m-th expansion stress in real time. If the (m + 1)-th expansion stress is greater than the m-th expansion stress, then perform quantity statistics to obtain the expansion stress quantity. If the (m + 1)-th expansion stress is less than or equal to the m-th expansion stress, continue the detection until the (m + 1)-th expansion stress is equal to or greater than the bearing limit value of the pipeline or tank and then stop;

[0061] According to the heat transfer principle, heat is transferred from high temperature to low temperature. Set the heat dissipation time of the pipeline or tank. If the temperature inside the pipeline or tank is greater than the ambient temperature, the temperature inside the pipeline or tank dissipates heat to the surroundings until it is equal to the ambient temperature and then stops. Assign a value to the heat dissipation time of the pipeline or tank, and the value is assigned as the difference between the temperature inside the pipeline or tank and the ambient temperature; if the temperature inside the pipeline or tank is less than or equal to the ambient temperature, assign a value to the heat dissipation time of the pipeline or tank, and the value is assigned equal to one;

[0062] Comprehensively analyze the heat dissipation time, m expansion stresses, the (m + 1)-th expansion stress, and the m-th expansion stress to obtain the blockage severity coefficient;

[0063]

[0064] Among them, SY represents the severe blockage coefficient, RS represents the heat dissipation time. The longer the heat dissipation time of the pipeline or tank, the more severe the blockage. m represents the number of expansion stresses. The more the number of expansion stresses, the more severe the blockage. x m+1 represents the (m + 1)-th expansion stress, x m represents the m-th expansion stress.

[0065] Step Five: Judge the blockage of the pipeline or tank according to the pipeline or tank blockage evaluation value;

[0066] Compare the pipeline or tank blockage threshold with the pipeline or tank blockage evaluation value in real time. If the pipeline or tank blockage evaluation value is greater than or equal to the pipeline or tank blockage threshold, it is judged that the pipeline or tank is blocked. If the pipeline or tank blockage evaluation value is less than the pipeline or tank blockage threshold, it is judged that the pipeline or tank is normal.

[0067] Step Six: If it is judged that the pipeline or tank is blocked, issue a second warning to prompt the staff to repair, and return to Step Four to obtain the blockage data in real time until it is judged that the pipeline or tank is normal;

[0068] If it is judged that the pipeline or tank is normal, continue the detection.

[0069] As Figure 3 shown: The chemical production safety warning system based on big data includes:

[0070] A data acquisition module, which is used to acquire static electricity data, caking data and blockage data and preprocess them to obtain preprocessed data, and send the preprocessed data to the data analysis module;

[0071] A data analysis module, which is used to receive the preprocessed data and analyze the preprocessed data, used to judge the caking of chemical materials and the blockage of pipelines or tanks, and send the judgment results of the caking of chemical materials and the blockage of pipelines or tanks to the data execution module respectively;

[0072] A data execution module, which is used to receive the judgment results of the caking of chemical materials and the blockage of pipelines or tanks, and give early warnings for the judgment results of the caking of chemical materials and the blockage of pipelines or tanks.

[0073] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A chemical production safety early warning method based on big data, characterized in that: It includes the following specific steps: Step 1: Obtain static electricity data and caking data, preprocess the static electricity data and caking data, and comprehensively evaluate the preprocessed static electricity data and caking data to obtain a chemical material caking evaluation value; Step 2: Judge the caking of chemical materials according to the chemical material caking evaluation value; Step 3: If it is judged that the chemical materials are caked, issue a first type of warning and execute Step 4; If it is judged that the chemical materials are normal, directly execute Step 4; Step 4: Obtain blockage data, perform preliminary processing on the blockage data, and comprehensively evaluate the preprocessed blockage data to obtain a pipeline or tank blockage evaluation value; Step 5: Judge the blockage of the pipeline or tank according to the pipeline or tank blockage evaluation value; Step 6: If it is judged that the pipeline or tank is blocked, issue a second type of warning to prompt the staff to repair, and return to Step 4 to obtain the blockage data in real time until it is judged that the pipeline or tank is normal; If it is judged that the pipeline or tank is normal, continue the detection.

2. The big data-based chemical production safety warning method according to claim 1, wherein: In Step 1, the static electricity data includes static electricity voltage and static electricity discharge sound, the caking data includes the current crystal particle size and the current chemical material temperature, and the static electricity data and caking data are subjected to filtering and noise reduction processing; The filtered and noise-reduced static electricity data and caking data are normalized and comprehensively analyzed to obtain a static electricity influence coefficient and a caking severity coefficient; the static electricity influence coefficient and the caking severity coefficient are standardized and comprehensively evaluated to obtain a chemical material caking evaluation value; Among them, JP represents the chemical material caking evaluation value, DY represents the static electricity influence coefficient, k1 represents the slope of the static electricity influence coefficient, and KY represents the caking severity coefficient.

3. The chemical production safety warning method based on big data according to claim 2, wherein: The specific method for obtaining the static electricity influence coefficient is as follows: Set a voltage existence value. If the static electricity voltage is detected, assign a value to the voltage existence value, and the assigned value is not equal to zero. Count the change of the static electricity voltage to obtain a voltage group, calculate the average value of the voltage group to obtain a voltage average value, calculate the voltage disorder value for the voltage group using the variance method according to the voltage average value. If the static electricity voltage is not detected, continue the detection and assign a value to the voltage existence value, and the assigned value is equal to zero; Comprehensively analyze the static electricity discharge sound using big data technology to obtain the number of static electricity discharge sound waveforms; Comprehensively analyze the voltage existence value, the voltage disorder value, and the number of static electricity discharge sound waveforms to obtain a static electricity influence coefficient.

4. The chemical production safety warning method based on big data according to claim 3, characterized in that: The specific method for obtaining the number of static electricity discharge sound waveforms is as follows: Convert the electrostatic discharge sound into an electrostatic discharge waveform, and use Fourier transform on the electrostatic discharge waveform to transform the electrostatic discharge waveform that is chaotic in the time - space domain into a sine or cosine electrostatic discharge waveform in the frequency domain. The sine or cosine electrostatic discharge waveform includes amplitude and frequency. Group the sine or cosine electrostatic discharge waveforms with similar amplitudes and frequencies through big data technology, and store them in the sound waveform type database. Classify the sine or cosine electrostatic discharge waveforms, count the quantity of each group of sine or cosine electrostatic discharge waveforms, select one of the sine or cosine electrostatic discharge waveforms in each group to perform similarity matching with a preset standard sine or cosine electrostatic discharge waveform, and arrange them in ascending order of similarity. Select the group with the highest similarity and determine the quantity to obtain the quantity of the electrostatic discharge sound waveform.

5. The chemical production safety early warning method based on big data according to claim 2, characterized in that: The specific method for obtaining the caking severity coefficient is as follows: Obtain the standard crystal particle size and the standard chemical material temperature; comprehensively analyze the current crystal particle size, the standard crystal particle size, the current chemical material temperature, and the standard chemical material temperature to obtain the caking severity coefficient.

6. The method for chemical production safety early warning based on big data according to claim 1, wherein: In step two, compare the chemical material caking threshold with the chemical material caking evaluation value in real - time; if the chemical material caking evaluation value is greater than or equal to the chemical material caking threshold, it is determined that the chemical material is caking; if the chemical material caking evaluation value is less than the chemical material caking threshold, it is determined that the chemical material is normal.

7. The method for chemical production safety early warning based on big data according to claim 1, wherein: In step four, the blockage data includes the expansion stress and the temperature inside the pipeline or tank; perform filtering and noise reduction processing on the blockage data; Perform normalization processing and comprehensive analysis on the blockage data after filtering and noise reduction processing to obtain the blockage severity coefficient. Perform standardization processing and comprehensive evaluation on the blockage severity coefficient and the caking severity coefficient to obtain the pipeline or tank blockage evaluation value.

8. The chemical production safety warning method based on big data according to claim 7, characterized in that: The specific method for obtaining the blockage severity coefficient is as follows: When a change in the expansion stress is detected, the (m + 1) - th expansion stress is compared with the m - th expansion stress in real - time. If the (m + 1) - th expansion stress is greater than the m - th expansion stress, perform quantity statistics to obtain the expansion stress quantity. If the (m + 1) - th expansion stress is less than or equal to the m - th expansion stress, continue the detection until the (m + 1) - th expansion stress is equal to or greater than the bearing limit value of the pipeline or tank and then stop; According to the heat transfer principle, set the heat dissipation time of the pipeline or tank. If the temperature inside the pipeline or tank is greater than the ambient temperature, the temperature inside the pipeline or tank dissipates heat to the surroundings until it equals the ambient temperature and then stops. Assign a value to the heat dissipation time of the pipeline or tank, and the value is the difference between the temperature inside the pipeline or tank and the ambient temperature. If the temperature inside the pipeline or tank is less than or equal to the ambient temperature, assign a value to the heat dissipation time of the pipeline or tank, and the value is equal to one. Comprehensively analyze the heat dissipation time, the m expansion stresses, the (m + 1) - th expansion stress, and the m - th expansion stress to obtain the blockage severity coefficient.

9. The method for chemical production safety early warning based on big data according to claim 1, wherein: In step five, the pipeline or tank blockage threshold is compared with the pipeline or tank blockage evaluation value in real time; if the pipeline or tank blockage evaluation value is greater than or equal to the pipeline or tank blockage threshold, it is determined that the pipeline or tank is blocked; if the pipeline or tank blockage evaluation value is less than the pipeline or tank blockage threshold, it is determined that the pipeline or tank is normal.

10. A chemical production safety early warning system based on big data, which is used to implement the chemical production safety early warning method based on big data according to any one of claims 1-9, characterized in that, The system includes: A data acquisition module, which is used to acquire electrostatic data, caking data, and blockage data and perform preprocessing to obtain preprocessed data, and send the preprocessed data to the data analysis module; A data analysis module, which is used to receive the preprocessed data and analyze the preprocessed data to make judgments on the caking of chemical materials and the blockage of pipelines or tanks, and send the judgment results of the caking of chemical materials and the blockage of pipelines or tanks to the data execution module respectively; A data execution module, which is used to receive the judgment results of the caking of chemical materials and the blockage of pipelines or tanks, and give early warnings for the judgment results of the caking of chemical materials and the blockage of pipelines or tanks.

Images