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

Abstract

The application discloses a chemical production safety early warning system and method based on big data, and relates to the technical field of safety early warning, which comprises the following steps: firstly, acquiring electrostatic data and caking data; after pretreatment, comprehensively evaluating a chemical material caking evaluation value to determine whether the chemical material is caked; if the chemical material is caked, a first early warning is sent, and then the next step is entered; if the chemical material is not caked, the next step is directly entered; then, acquiring blockage data; after preliminary processing, comprehensively evaluating a pipeline or tank blockage evaluation value to determine whether the pipeline or tank is blocked; if the pipeline or tank is blocked, a second early warning is sent and maintenance is prompted, and meanwhile, the blockage data is acquired in real time until normality is determined; and if the pipeline or tank is normal, detection is continued. When the pipeline or tank is determined to be blocked, the second early warning is sent to prompt the staff to maintain, so that electrostatic generated by friction is avoided, the chemical material is prevented from being caked and blocking the pipeline or tank, and timely early warning is realized.

Description

Technical Field

[0001] This invention relates to the field of safety early warning technology, specifically to a chemical production safety early warning system and method based on big data. Background Technology

[0002] Chemical production involves a variety of hazardous chemicals and complex processes. The slightest carelessness can lead to accidents such as fires, explosions, and leaks, causing casualties, environmental pollution, and significant economic losses. Therefore, chemical production requires safety early warning systems. By monitoring the operating status of equipment, process parameters, and the storage and transportation of hazardous chemicals in real time, potential risks can be identified in advance, and timely measures can be taken to prevent and control them. This can effectively reduce the probability of accidents, ensure the safe and stable operation of the production process, and protect the lives of personnel and the safety of company property.

[0003] In the production process of chemical materials, chemical materials need to be placed into pipes or tanks. In order to prevent the chemical materials from clogging the pipes or tanks, which could cause excessive pressure and lead to rupture and explosion, thus affecting production safety, early warning of pipe or tank blockage is required.

[0004] For example, the invention patent with publication number CN118747942A discloses a safety risk early warning system and method for chemical industrial parks, including the following steps: an industrial control system, an intelligent management and control platform for chemical industrial parks, and a fusion positioning platform. The industrial control system collects process control data and sends it to the intelligent management and control platform for chemical industrial parks. The intelligent management and control platform collects business data from the chemical industrial parks, obtains a static risk database and a dynamic risk database based on the process control data and the business data, and determines the regional risk index. The fusion positioning platform performs grid division based on the park's positioning data to obtain park grid data, resulting in a grid-based regional dynamic risk four-color map. This application effectively solves the problem of the lack of dynamic calculation models and location-based risk display for regional risks in chemical industrial parks. Simultaneously, the regional risk data can provide dynamic regional risk data for various business application modules within the park, providing guidance for the daily safety management of chemical industrial parks.

[0005] For example, the invention patent with publication number CN117007247B discloses a chemical gas leakage safety feedback system and method based on data analysis, including: a control management platform and an operation analysis platform. The control management platform is equipped with a server, and the server is connected to a location acquisition unit and a risk warning unit. The operation analysis platform is equipped with a controller. This invention monitors the airtightness of each bolt on chemical equipment by analyzing its status and monitors the status of each bolt in real time, providing early warning of the risk of bolt loosening, so that relevant personnel can maintain the status of each bolt in advance.

[0006] In the existing technology, there is no effective solution to the problem of timely warning of chemical materials clumping and blocking pipelines or tanks due to static electricity generated by friction during loading, unloading and storage of chemical materials in pipelines or tanks. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a chemical production safety early warning system and method based on big data, which solves the problem of the lack of early warning for the agglomeration and blockage caused by frictional static electricity during the loading, unloading and storage of chemical materials.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solution: a chemical production safety early warning system and method based on big data, comprising the following specific steps: Step 1: Acquire static electricity data and agglomeration data, preprocess the static electricity data and agglomeration data, and comprehensively evaluate the preprocessed static electricity data and agglomeration data to obtain agglomeration assessment value for chemical materials; Step 2: Determine the agglomeration of chemical materials based on the agglomeration assessment value; Step 3: If agglomeration of chemical materials is determined, issue a first type of early warning and proceed to Step 4; if the chemical materials are determined to be normal, proceed directly to Step 4; Step 4: Acquire blockage data, perform initial processing on the blockage data, and comprehensively evaluate the initial processed blockage data to obtain a blockage assessment value for pipelines or tanks; Step 5: Determine the blockage of pipelines or tanks based on the blockage assessment value; Step 6: If a blockage of pipelines or tanks is determined, issue a second type of early warning, prompting personnel to conduct maintenance, and return to Step 4 to acquire blockage data in real time until the pipeline or tank is determined to be normal; if the pipeline or tank is determined to be normal, continue the detection.

[0011] Further, in step one, the electrostatic data includes electrostatic voltage and electrostatic discharge sound, and the agglomeration data includes the current crystal particle size and the current temperature of the chemical material. The electrostatic data and agglomeration data are filtered and noise-reduced. The filtered and noise-reduced electrostatic data and agglomeration data are normalized and comprehensively analyzed to obtain the electrostatic influence coefficient and agglomeration severity coefficient. The electrostatic influence coefficient and agglomeration severity coefficient are standardized and comprehensively evaluated to obtain the agglomeration evaluation value of the chemical material. Where JP represents the chemical material agglomeration assessment value, DY represents the electrostatic influence coefficient, k1 represents the slope of the electrostatic influence coefficient, and KY represents the agglomeration severity coefficient.

[0012] Furthermore, the specific method for obtaining the electrostatic influence coefficient is as follows: A voltage presence value is set. If an electrostatic voltage is detected, a value is assigned to the voltage presence value, and this value is not equal to zero. The changes in electrostatic voltage are statistically analyzed to obtain a voltage group. The voltage group is averaged to obtain the voltage average value. Based on the voltage average value, the voltage group is calculated using the variance method to obtain the voltage disturbance value. If no electrostatic voltage is detected, detection continues, and a value is assigned to the voltage presence value, which is equal to zero. The electrostatic discharge sound is comprehensively analyzed using big data technology to obtain the number of electrostatic discharge sound waveforms. The electrostatic influence coefficient is obtained by comprehensively analyzing the voltage presence value, voltage disturbance value, and the number of electrostatic discharge sound waveforms.

[0013] Furthermore, the specific method for obtaining the number of electrostatic discharge sound waveforms is as follows: The electrostatic discharge sound is converted into an electrostatic discharge waveform. Fourier transform is applied to the electrostatic discharge waveform to transform the spatiotemporally chaotic electrostatic discharge waveform into a sine or cosine electrostatic discharge waveform in the frequency domain. The sine or cosine electrostatic discharge waveform includes amplitude and frequency. Using big data technology, sine or cosine electrostatic discharge waveforms with similar amplitudes and frequencies are grouped and stored in a sound waveform type database. The sine or cosine electrostatic discharge waveforms are classified, and the number of each group of sine or cosine electrostatic discharge waveforms is counted. One of the sine or cosine electrostatic discharge waveforms from each group is selected and matched with a preset standard sine or cosine electrostatic discharge waveform for similarity. The waveforms are then arranged from lowest to highest similarity. The group with the highest similarity is selected, and its number is determined to obtain the number of electrostatic discharge sound waveforms.

[0014] Furthermore, the specific method for obtaining the agglomeration severity coefficient is as follows: obtain the standard crystal particle size and the standard chemical material temperature; perform a comprehensive analysis on the current crystal particle size, the standard crystal particle size, the current chemical material temperature, and the standard chemical material temperature to obtain the agglomeration severity coefficient.

[0015] Furthermore, in step two, the chemical material agglomeration threshold and the chemical material agglomeration evaluation value are compared in real time; if the chemical material agglomeration evaluation value is greater than or equal to the chemical material agglomeration threshold, then the chemical material is determined to be agglomerated; if the chemical material agglomeration evaluation value is less than the chemical material agglomeration threshold, then the chemical material is determined to be normal.

[0016] Furthermore, in step four, the blockage data includes expansion stress and temperature inside the pipe or tank; the blockage data is filtered and noise-reduced; the filtered and noise-reduced blockage data is normalized and comprehensively analyzed to obtain a blockage severity coefficient; the blockage severity coefficient and the agglomeration severity coefficient are standardized and comprehensively evaluated to obtain a blockage assessment value for the pipe or tank.

[0017] Furthermore, the specific method for obtaining the blockage severity coefficient is as follows: When a change in expansion stress is detected, the (m+1)th expansion stress is compared with the mth expansion stress in real time. If the (m+1)th expansion stress is greater than the mth expansion stress, the number of expansion stresses is counted. If the (m+1)th expansion stress is less than or equal to the mth expansion stress, the detection continues until the (m+1)th expansion stress is equal to or greater than the bearing limit of the pipe or tank. According to the principle of heat transfer, a heat dissipation time for the pipe or tank is set. If the temperature inside the pipe or tank is greater than the ambient temperature, the temperature inside the pipe or tank dissipates heat to the surroundings until it equals the ambient temperature, then stops. The heat dissipation time of the pipe or tank is assigned a value, which is the difference between the temperature inside the pipe or tank and the ambient temperature. If the temperature inside the pipe or tank is less than or equal to the ambient temperature, the heat dissipation time of the pipe or tank is assigned a value equal to one. The blockage severity coefficient is obtained by comprehensively analyzing the heat dissipation time, the m expansion stresses, the (m+1)th expansion stress, and the mth expansion stress.

[0018] Furthermore, in step five, the pipe or tank blockage threshold is compared with the pipe or tank blockage assessment value in real time; if the pipe or tank blockage assessment value is greater than or equal to the pipe or tank blockage threshold, the pipe or tank is determined to be blocked; if the pipe or tank blockage assessment value is less than the pipe or tank blockage threshold, the pipe or tank is determined to be normal.

[0019] Furthermore, the data acquisition module is used to acquire and preprocess electrostatic data, agglomeration data, and blockage data to obtain preprocessed data, and then sends the preprocessed data to the data analysis module. The data analysis module is used to receive the preprocessed data and analyze it to make judgments on chemical material agglomeration and pipeline or tank blockage, and sends the judgment results of chemical material agglomeration and pipeline or tank blockage to the data execution module respectively. The data execution module is used to receive the judgment results of chemical material agglomeration and pipeline or tank blockage, and issue early warnings based on the judgment results of chemical material agglomeration and pipeline or tank blockage.

[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 agglomeration data, and performing preprocessing and comprehensive evaluation, agglomeration assessment values ​​for chemical materials are obtained, thereby improving the accuracy of determining whether chemical materials are agglomerating.

[0023] 2. By acquiring blockage data and preprocessing and comprehensively evaluating it, a blockage assessment value for the pipeline or tank is obtained, thereby improving the accuracy of determining whether the pipeline or tank is blocked.

[0024] 3. When it is determined that chemical materials are clumping, the first warning will be issued to promptly remind staff that clumping has occurred in the pipelines or tanks. In order to prevent the clumping from blocking the pipelines or tanks, the clumping will be dealt with in a timely manner.

[0025] 4. When a blockage is detected in a pipeline or tank, a second warning will be issued to prompt staff to conduct maintenance, in order to prevent static electricity generated by friction from causing chemical materials to clump together and block the pipeline or tank, thus preventing the timely warning from being issued.

[0026] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0027] Figure 1 This invention is a flowchart of a big data-based early warning method for chemical production safety.

[0028] Figure 2 This invention provides a line graph illustrating the effect of electrostatic voltage on the temperature inside a pipe or tank.

[0029] Figure 3 This invention is a structural diagram of a big data-based chemical production safety early warning system. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

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

[0032] like Figure 1 As shown, this embodiment of the invention provides a chemical production safety early warning method based on big data, including the following specific steps:

[0033] Step 1: Set up a charge sensor, digital microphone, laser particle size analyzer, first temperature sensor, second temperature sensor, and pressure sensor; acquire electrostatic data in real time through the charge sensor and digital microphone. Due to the high resistivity and dielectric constant differences of chemical materials, static electricity is generated during loading and unloading in pipelines or tanks. Static electricity causes the loose crystal particles in the chemical materials to be charged, and the particles are attracted to each other and aggregate due to the attraction of the charges. At the same time, the heat generated by static electricity will raise the local temperature of the crystal particles, accelerate the dissolution and recrystallization process of the crystal surface, and make the crystal particles more likely to stick together and form agglomerates; the electrostatic data includes the electrostatic voltage acquired in real time by the charge sensor and the electrostatic discharge sound acquired in real time by the digital microphone. The electrostatic discharge sound is caused by the air vibration caused by the pressure wave generated after the static electricity accumulates to a certain level and discharges.

[0034] Agglomeration data is acquired in real time using a laser particle size analyzer and a first temperature sensor. This data includes the current crystal particle size obtained by the laser particle size analyzer and the current temperature of the chemical material obtained by the first temperature sensor. The laser particle size analyzer accurately detects the size of the chemical material's crystal particles; when the chemical material agglomerates, the particle size increases. The first temperature sensor detects the temperature of the chemical material; when crystal particles agglomerate, not only does the surface area of ​​the chemical material decrease, leading to a reduction in its heat dissipation capacity, but electrostatic discharge also releases heat, such as… Figure 2 As shown, the surface temperature will rise when chemical materials agglomerate.

[0035] Table 1. Effects of electrostatic voltage on temperature inside pipes or tanks.

[0036] Group Electrostatic voltage (V) Temperature inside the pipe or tank (°C) 1 526 12 2 633 19 3 876 26

[0037] As shown in Table 1, the following data were obtained in the experiments studying the effect of electrostatic voltage on the temperature inside pipes or tanks: In group 1, when the electrostatic voltage was 526V, the temperature inside the pipe or tank was 12℃; in group 2, when the electrostatic voltage increased to 633V, the temperature also rose to 19℃; and in group 3, when the electrostatic voltage reached 876V, the temperature inside the pipe or tank further increased to 26℃. From these data, it can be preliminarily seen that as the electrostatic voltage increases, the temperature inside the pipe or tank shows an upward trend.

[0038] The electrostatic data and agglomeration data are filtered and denoised to improve their quality. The filtered and denoised data are then normalized and comprehensively analyzed to eliminate dimensions and improve computational efficiency, yielding the electrostatic influence coefficient and agglomeration severity coefficient. Finally, the electrostatic influence coefficient and agglomeration severity coefficient are standardized and comprehensively evaluated to further eliminate different dimensions and improve computational efficiency, resulting in an assessment value for agglomeration of chemical materials.

[0039]

[0040] Wherein, JP represents the chemical material agglomeration assessment value, DY represents the electrostatic influence coefficient, reflecting whether electrostatics affect agglomeration, k1 represents the slope of the electrostatic influence coefficient, and is an integer greater than one, reflecting the changing trend of the electrostatic influence coefficient, and KY represents the agglomeration severity coefficient, reflecting the severity of chemical material agglomeration.

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

[0042] A charge sensor performs real-time detection, setting a voltage presence value to measure the presence of voltage. If the charge sensor detects electrostatic voltage, it assigns a non-zero value to the voltage presence value and statistically analyzes the changes in electrostatic voltage to obtain a voltage group. Since the contact area or force between the chemical material and the pipe or tank varies in different areas, the electrostatic voltage detected by the charge sensor will change. The voltage group is averaged to obtain the average voltage value; the larger the average voltage value, the greater the voltage presence value. Based on the average voltage value, the voltage group is calculated using the variance method to obtain the voltage disturbance value. If the charge sensor does not detect electrostatic voltage, it continues detection and assigns a zero value to the voltage presence value. The electrostatic discharge sound is comprehensively analyzed using big data technology to obtain the number of electrostatic discharge sound waveforms.

[0043] A comprehensive analysis of the voltage presence value, voltage disturbance value, and the number of electrostatic discharge sound waveforms is performed to obtain the electrostatic influence coefficient.

[0044]

[0045] Where DY represents the electrostatic influence coefficient, DC represents the voltage presence value, ensuring that the electrostatic influence coefficient also increases as the average voltage increases, DW represents the voltage disturbance value, reflecting whether the electrostatic voltage is disordered; the more disordered the electrostatic voltage, the greater the electrostatic influence, and YB represents the number of electrostatic discharge sound waveforms; the more waveforms, the greater the electrostatic influence.

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

[0047] The digital microphone converts the acquired electrostatic discharge (ESD) sound into an ESD waveform. Fourier transform is then used to transform the spatiotemporally chaotic ESD waveform into a frequency-domain sine or cosine ESD waveform. This waveform includes both amplitude and frequency. Big data technology is used to group sine or cosine ESD waveforms with similar amplitudes and frequencies and store them in a sound waveform type database. Since the ESD sound acquired by the digital microphone contains noise, the sine or cosine ESD waveforms need to be classified. The number of waveforms in each group is counted. One waveform from each group is selected and compared with a preset standard sine or cosine ESD waveform for similarity matching. These waveforms are then arranged from lowest to highest similarity, and the group with the highest similarity is selected, and its number is determined, thus obtaining the total number of ESD sound waveforms.

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

[0049] The laser particle size analyzer obtains the standard crystal particle size in normal chemical material crystal particle detection, and the first temperature sensor obtains the standard chemical material temperature in normal chemical material crystal particle detection; the current crystal particle size, standard crystal particle size, current chemical material temperature and standard chemical material temperature are comprehensively analyzed to obtain the agglomeration severity coefficient;

[0050]

[0051] Wherein, KY represents the agglomeration severity coefficient, DC represents the current crystal particle size (the larger the current crystal particle size, the more severe the agglomeration of the chemical material), BC represents the standard crystal particle size, DW represents the current chemical material temperature (the higher the current chemical material temperature, the more severe the agglomeration of the chemical material), and BW represents the standard chemical material temperature.

[0052] Step 2: Determine the caking status of chemical materials based on the caking assessment value;

[0053] The chemical material caking threshold and the chemical material caking assessment value are compared in real time. If the chemical material caking assessment value is greater than or equal to the chemical material caking threshold, the chemical material is determined to be caking. If the chemical material caking assessment value is less than the chemical material caking threshold, the chemical material is determined to be normal.

[0054] Step 3: If it is determined that the chemical materials are clumping, issue the first warning and proceed to Step 4;

[0055] If the chemical materials are determined to be normal, proceed directly to step four.

[0056] Step 4: Obtain blockage data in real time using a pressure sensor and a second temperature sensor. This data includes the expansion stress acquired by the pressure sensor and the temperature inside the pipe or tank acquired by the second temperature sensor. Expansion stress is the force that causes the pipe or tank to expand. Agglomeration of chemical materials can lead to blockages in pipes or tanks, gradually increasing pressure on the inner walls. Blockage also prevents airflow, hindering heat dissipation. The blockage data is filtered and noise-reduced to improve its quality. The filtered and noise-reduced data is then normalized and comprehensively analyzed to eliminate dimensions and improve computational efficiency, yielding a blockage severity coefficient. The blockage severity coefficient and agglomeration severity coefficient are then standardized and comprehensively evaluated to further eliminate different dimensions and improve computational efficiency, resulting in a pipe or tank blockage assessment value.

[0057]

[0058] Where SP represents the pipeline or tank blockage assessment value, SY represents the blockage severity coefficient, reflecting the severity of blockage of chemical materials, k2 represents the slope of the blockage severity coefficient, and is an integer greater than one, reflecting the changing trend of the blockage severity coefficient, and KY represents the agglomeration severity coefficient, reflecting the severity of agglomeration of chemical materials.

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

[0060] When the pressure sensor detects a change in expansion stress, the (m+1)th expansion stress is compared with the mth expansion stress in real time. If the (m+1)th expansion stress is greater than the mth expansion stress, the number of expansion stresses is counted. If the (m+1)th expansion stress is less than or equal to the mth expansion stress, the detection continues until the (m+1)th expansion stress is equal to or greater than the bearing limit of the pipe or tank.

[0061] Based on the principle of heat transfer, heat is transferred from high temperature to low temperature. A heat dissipation time is set for the pipe or tank. If the temperature inside the pipe or tank is higher than the ambient temperature, the heat dissipation inside the pipe or tank will continue to spread until it equals the ambient temperature, at which point it will stop. The heat dissipation time of the pipe or tank is assigned a value, which is the difference between the temperature inside the pipe or tank and the ambient temperature. If the temperature inside the pipe or tank is less than or equal to the ambient temperature, the heat dissipation time of the pipe or tank is assigned a value equal to one.

[0062] A comprehensive analysis of heat dissipation time, m expansion stresses, the (m+1)th expansion stress, and the mth expansion stress is used to obtain the blockage severity coefficient.

[0063]

[0064] Where SY represents the severity coefficient of blockage, RS represents the heat dissipation time (the longer the heat dissipation time of the pipe or tank, the more severe the blockage), m represents the amount of expansion stress (the more expansion stress, the more severe the blockage), and x represents the amount of expansion stress. m+1 Let x represent the (m+1)th expansion stress. m This represents the m-th expansion stress.

[0065] Step 5: Determine the blockage of the pipe or tank based on the blockage assessment value;

[0066] The system compares the pipe or tank blockage threshold with the pipe or tank blockage assessment value in real time. If the pipe or tank blockage assessment value is greater than or equal to the pipe or tank blockage threshold, the pipe or tank is determined to be blocked. If the pipe or tank blockage assessment value is less than the pipe or tank blockage threshold, the pipe or tank is determined to be normal.

[0067] Step Six: If a blockage is detected in the pipe or tank, a second warning will be issued to prompt staff to inspect and repair the pipe or tank. The system will then return to Step Four to obtain real-time blockage data until the pipe or tank is determined to be normal.

[0068] If the pipeline or tank is determined to be normal, the inspection continues.

[0069] like Figure 3 As shown: A big data-based chemical production safety early warning system includes:

[0070] The data acquisition module is used to acquire and preprocess electrostatic data, agglomeration data, and blockage data to obtain preprocessed data, and then send the preprocessed data to the data analysis module.

[0071] The data analysis module is used to receive pre-processed data and analyze it to make judgments on chemical material agglomeration and pipeline or tank blockage. The judgment results of chemical material agglomeration and pipeline or tank blockage are sent to the data execution module respectively.

[0072] The data execution module is used to receive the judgment results of chemical material agglomeration and pipeline or tank blockage, and to issue early warnings for the judgment results of chemical material agglomeration and pipeline or tank blockage.

[0073] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for early warning of chemical production safety based on big data, characterized by: The specific steps include the following: Step 1: Obtain electrostatic data and agglomeration data, preprocess the electrostatic data and agglomeration data, and comprehensively evaluate the preprocessed electrostatic data and agglomeration data to obtain the agglomeration evaluation value of chemical materials. The electrostatic data includes electrostatic voltage and electrostatic discharge sound, and the agglomeration data includes the current crystal particle size and the current chemical material temperature. The electrostatic data and agglomeration data are filtered and noise-reduced. The electrostatic data and agglomeration data after filtering and noise reduction are normalized and comprehensively analyzed to obtain the electrostatic influence coefficient and agglomeration severity coefficient; the electrostatic influence coefficient and agglomeration severity coefficient are standardized and comprehensively evaluated to obtain the agglomeration evaluation value of chemical materials. ； in, This indicates the assessment value for agglomeration of chemical materials. Indicates the electrostatic influence coefficient. The slope representing the electrostatic influence coefficient. Indicates the severity coefficient of clumping; Step 2: Determine the caking status of chemical materials based on the caking assessment value; Step 3: If it is determined that the chemical materials are clumping, issue the first warning and proceed to Step 4; If the chemical materials are determined to be normal, proceed directly to step four; Step 4: Obtain blockage data, perform initial processing on the blockage data, and conduct a comprehensive evaluation of the blockage data after initial processing to obtain the blockage evaluation value of the pipeline or tank. Step 5: Determine the blockage of the pipe or tank based on the blockage assessment value; Step Six: If a blockage is detected in the pipe or tank, a second warning will be issued to prompt staff to inspect and repair the pipe or tank. The system will then return to Step Four to obtain real-time blockage data until the pipe or tank is determined to be normal. If the pipeline or tank is determined to be normal, the inspection continues.

2. The method for early warning of chemical production safety based on big data according to claim 1, characterized in that: The specific method for obtaining the electrostatic influence coefficient is as follows: Set a voltage presence value. If electrostatic voltage is detected, assign a value to the voltage presence value, and the assigned value is not equal to zero. Statistically count the changes in electrostatic voltage to obtain a voltage group. Calculate the average voltage value by averaging the voltage group. Calculate the voltage disturbance value by using the variance method based on the average voltage value. If no electrostatic voltage is detected, continue detection and assign a value to the voltage presence value, and the assigned value is equal to zero. The electrostatic discharge sound was comprehensively analyzed using big data technology to obtain the number of electrostatic discharge sound waveforms. A comprehensive analysis of the voltage presence value, voltage disturbance value, and the number of electrostatic discharge sound waveforms is conducted to obtain the electrostatic influence coefficient.

3. The chemical production safety early warning method based on big data according to claim 2, characterized in that: The specific method for obtaining the number of electrostatic discharge sound waveforms is as follows: The electrostatic discharge (ESD) sound is converted into an ESD waveform. Fourier transform is then applied to this waveform to transform the spatiotemporally chaotic ESD waveform into a frequency-domain sine or cosine ESD waveform. This sine or cosine ESD waveform includes amplitude and frequency. Using big data technology, sine or cosine ESD waveforms with similar amplitudes and frequencies are grouped and stored in a sound waveform type database. The sine or cosine ESD waveforms are then classified, and the number of waveforms in each group is counted. One waveform from each group is selected and matched with a preset standard sine or cosine ESD waveform for similarity matching. These waveforms are then arranged from lowest to highest similarity, and the group with the highest similarity is selected and its quantity determined, thus obtaining the total number of ESD sound waveforms.

4. The chemical production safety early warning method based on big data according to claim 1, characterized in that: The specific method for obtaining the clumping severity coefficient is as follows: Obtain the standard crystal particle size and standard chemical material temperature; perform a comprehensive analysis of the current crystal particle size, standard crystal particle size, current chemical material temperature, and standard chemical material temperature to obtain the agglomeration severity coefficient.

5. The chemical production safety early warning method based on big data according to claim 1, characterized in that: In step two, the chemical material clumping threshold and the chemical material clumping assessment value are compared in real time. If the chemical material clumping assessment value is greater than or equal to the chemical material clumping threshold, the chemical material is determined to be clumped. If the chemical material clumping assessment value is less than the chemical material clumping threshold, the chemical material is determined to be normal.

6. The method for early warning of chemical production safety based on big data according to claim 1, characterized in that: In step four, the blockage data includes expansion stress and temperature inside the pipe or tank; the blockage data is then filtered and noise-reduced. The blocked data after filtering and noise reduction is normalized and comprehensively analyzed to obtain the blocked severity coefficient. The blocked severity coefficient and the agglomeration severity coefficient are standardized and comprehensively evaluated to obtain the blocked assessment value of the pipeline or tank.

7. The chemical production safety early warning method based on big data according to claim 6, characterized in that: The specific method for obtaining the congestion severity coefficient is as follows: When a change in expansion stress is detected, the (m+1)th expansion stress is compared with the mth expansion stress in real time. If the (m+1)th expansion stress is greater than the mth expansion stress, the number of expansion stresses is counted. If the (m+1)th expansion stress is less than or equal to the mth expansion stress, the detection continues until the (m+1)th expansion stress is equal to or greater than the bearing limit of the pipe or tank. Based on the principle of heat transfer, a heat dissipation time is set for the pipe or tank. If the temperature inside the pipe or tank is higher than the ambient temperature, the heat dissipation inside the pipe or tank will continue until it equals the ambient temperature, at which point it will stop. The heat dissipation time is assigned a value equal to the difference between the temperature inside the pipe or tank and the ambient temperature. If the temperature inside the pipe or tank is less than or equal to the ambient temperature, the heat dissipation time is assigned a value equal to one. A comprehensive analysis is performed on the heat dissipation time, the mth expansion stress, the (m+1)th expansion stress, and the mth expansion stress to obtain the blockage severity coefficient.

8. The chemical production safety early warning method based on big data according to claim 1, characterized in that: In step five, the pipe or tank blockage threshold is compared with the pipe or tank blockage assessment value in real time. If the pipe or tank blockage assessment value is greater than or equal to the pipe or tank blockage threshold, the pipe or tank is determined to be blocked. If the pipe or tank blockage assessment value is less than the pipe or tank blockage threshold, the pipe or tank is determined to be normal.

9. A big data-based chemical production safety early warning system, used to implement the big data-based chemical production safety early warning method according to any one of claims 1-8, characterized in that, The system includes: The data acquisition module is used to acquire and preprocess electrostatic data, agglomeration data, and blockage data to obtain preprocessed data, and then send the preprocessed data to the data analysis module. The data analysis module is used to receive pre-processed data and analyze it to make judgments on chemical material agglomeration and pipeline or tank blockage. The judgment results of chemical material agglomeration and pipeline or tank blockage are sent to the data execution module respectively. The data execution module is used to receive the judgment results of chemical material agglomeration and pipeline or tank blockage, and to issue early warnings for the judgment results of chemical material agglomeration and pipeline or tank blockage.

Images