A risk monitoring and early warning system for the entire production cycle of fireworks and firecrackers

Abstract

The present invention discloses a risk monitoring and early warning system for the whole cycle of fireworks and firecrackers production, which relates to the technical field of fireworks and firecrackers production, including an initial conveying rate setting module, a real-time monitoring module, a data extraction module, a feature analysis module, an intelligent prediction module, an early warning trigger module and a dynamic adjustment module; the initial conveying rate setting module sets the initial conveying rate of the screw conveyor according to historical conveying experience and the physical properties of gunpowder. The present invention uses sensors to capture anomalies in real time and combines machine learning models to predict the trend of fluidity degradation, promptly issues early warning signals and guides operators to intervene. The conveying rate of the screw conveyor is dynamically adjusted according to the prediction results, effectively alleviating the problems of frictional heat, pressure accumulation, blockage and uneven filling caused by decreased fluidity, significantly reducing the risk of spontaneous combustion or explosion of gunpowder, and comprehensively improving the safety and stability of the conveying process, providing safe and efficient technical support for the production of fireworks and firecrackers.

Description

Technical Field

[0001] The present invention relates to the technical field of fireworks and firecrackers production, and in particular to a full-cycle risk monitoring and early warning system for fireworks and firecrackers production. Background Art

[0002] Risk monitoring and early warning for the entire production cycle of fireworks and firecrackers refers to comprehensive risk monitoring and early warning management of all links in the production process of fireworks and firecrackers, from raw material procurement, production and manufacturing, storage, transportation to final sales. This process involves the use of various technical means, such as sensors, data acquisition systems, Internet of Things technology and big data analysis, to monitor potential risk factors in real time, such as fire, explosion, chemical leakage, equipment failure, etc., and timely predict possible risk events through data analysis. When an abnormal situation is detected, the system will automatically issue an early warning to remind relevant personnel to take preventive measures or emergency treatment to ensure the safety of the entire production process. The ultimate goal is to minimize the probability of accidents and ensure production safety and the safety of life and property through full-cycle risk management.

[0003] In the production process of fireworks and firecrackers, screw conveyors are usually used in the gunpowder filling process to ensure that the gunpowder is accurately loaded into the shell of the fireworks and firecrackers. Screw conveyors are particularly suitable for the transportation of granular or powdered materials. They can efficiently handle gunpowder of different types and particle sizes, especially for fine particles of gunpowder. It can effectively avoid blockage and ensure a smooth and stable conveying process. The advantage of this equipment lies in its good adaptability to the flow characteristics of gunpowder and its high conveying accuracy, thereby ensuring that the gunpowder filling amount of each firework or firecracker is accurate.

[0004] However, the existing technology usually uses a constant delivery rate to transport gunpowder. When the gunpowder is affected by the external environment and its fluidity deteriorates, it may cause excessive friction heat or static electricity accumulation. If the gunpowder is blocked or unevenly loaded during transportation, it may be subjected to excessive pressure, causing spontaneous combustion or explosion, especially when the gunpowder contains flammable substances or chemically reactive components. Continuous pressure and heat may cause serious safety accidents, endangering the safety of personnel and equipment.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a risk monitoring and early warning system for the entire production cycle of fireworks and firecrackers, which can capture anomalies in real time through sensors and predict the trend of fluidity degradation in combination with machine learning models, issue early warning signals in a timely manner and guide operators to intervene. The conveying rate of the screw conveyor is dynamically adjusted according to the prediction results, effectively alleviating the friction heat, pressure accumulation, blockage and uneven filling problems caused by decreased fluidity, significantly reducing the risk of spontaneous combustion or explosion of gunpowder, comprehensively improving the safety and stability of the conveying process, and ensuring production efficiency at the same time, providing safe and efficient technical support for the production of fireworks and firecrackers to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a risk monitoring and early warning system for the whole cycle of fireworks and firecrackers production, comprising an initial delivery rate setting module, a real-time monitoring module, a data extraction module, a feature analysis module, an intelligent prediction module, an early warning trigger module and a dynamic adjustment module;

[0008] The initial conveying rate setting module sets the initial conveying rate of the screw conveyor according to historical conveying experience and the physical properties of gunpowder, and accurately loads the gunpowder to be filled into the shell of fireworks and firecrackers;

[0009] The real-time monitoring module deploys sensors at key locations in the conveying pipeline while the screw conveyor is running to monitor the conveying status of the gunpowder in real time and promptly capture changes in the flow status of the gunpowder;

[0010] The data extraction module sorts and processes the raw data obtained by the sensor to extract key feature information related to the decrease in gunpowder fluidity;

[0011] The feature analysis module analyzes the extracted key information in the monitoring window and preliminarily quantifies the deterioration of the fluidity of the gunpowder during transportation;

[0012] The intelligent prediction module sends the analysis results as input data to a pre-trained machine learning model, and uses the machine learning model to make intelligent predictions on gunpowder fluidity;

[0013] The early warning trigger module automatically sends out an early warning signal when the machine learning model predicts that the fluidity of the gunpowder has deteriorated, ensuring that operators remain highly alert to potential risks in the gunpowder delivery process, understand abnormal changes in the fluidity of the gunpowder in a timely manner, and take further intervention measures;

[0014] The dynamic adjustment module dynamically adjusts the conveying rate of the screw conveyor according to the real-time feedback prediction results and warning signals to cope with the changes in the fluidity of the gunpowder. By timely lowering the conveying rate, it ensures that the screw conveyor can still complete the conveying task efficiently and safely when the fluidity of the gunpowder changes.

[0015] Preferably, the initial conveying rate of the screw conveyor is set according to historical conveying experience and the physical properties of gunpowder, and the specific steps are as follows:

[0016] First, we collected and analyzed the transportation data from previous production processes to understand the transportation performance of different types of gunpowder in different production environments;

[0017] Based on the collected historical data, the characteristics of the gunpowder to be transported are analyzed;

[0018] According to the characteristics of gunpowder and historical delivery experience, select a suitable initial delivery rate to ensure smooth delivery of gunpowder under normal production conditions, while avoiding gunpowder accumulation, blockage or uneven loading caused by too fast or too slow delivery rate.

[0019] Preferably, key feature information related to the decrease in fluidity of gunpowder is extracted, wherein the extracted features include the uniformity of gunpowder particles and the degree to which the gunpowder becomes denser due to compression during transportation. Under the monitoring window, the uniformity of the extracted gunpowder particles and the degree to which the gunpowder becomes denser due to compression during transportation are analyzed, and a particle size distribution reference value and a compaction reference value are generated respectively. The particle size distribution reference value and the compaction reference value are used to preliminarily quantify the deterioration in fluidity of gunpowder during transportation.

[0020] Preferably, the particle size distribution reference value and compaction reference value generated by analyzing the uniformity of the gunpowder particles and the degree to which the gunpowder becomes denser due to compression during transportation are sent as input data to a pre-trained machine learning model, and a fluidity degradation index is generated by the machine learning model. Based on the fluidity degradation index, an intelligent prediction is made on the deterioration of the fluidity of the gunpowder.

[0021] Preferably, the fluidity degradation index generated when the fluidity of gunpowder is intelligently predicted by a pre-trained machine learning model under the monitoring window is compared and analyzed with a preset reference threshold of the fluidity degradation index, so as to intelligently sense the deterioration of the fluidity of gunpowder. The specific steps are as follows:

[0022] If the fluidity degradation index is greater than the reference threshold of the fluidity degradation index, a high-risk signal is generated, and an early warning is automatically issued for the generated high-risk signal, ensuring that operators remain highly alert to potential risks in the process of gunpowder transportation, understand abnormal changes in gunpowder fluidity in a timely manner, and take further intervention measures;

[0023] If the fluidity degradation index is less than or equal to the fluidity degradation index reference threshold, a risk-free signal is generated, indicating that the gunpowder to be loaded can be efficiently transported by the screw conveyor at this time, and no signal is generated, and the gunpowder continues to be transported.

[0024] Preferably, under the monitoring window, the specific steps of analyzing the uniformity of the extracted gunpowder particles to generate a reference value of particle size distribution are as follows:

[0025] The particle size data of the gunpowder particles are obtained, and the cumulative distribution function of the gunpowder particles is calculated using the obtained particle size data. The cumulative distribution function is a function that reflects the proportion of particles in different particle size ranges, and its calculation expression is:

[0026] ,

[0027] Where: d represents the particle size, is the cumulative distribution function, which describes the proportion of particles with a size less than or equal to d, and reflects the particle size distribution of gunpowder particles. represents the number of particles with a particle size less than or equal to d, is the total number of particles in the sample;

[0028] The cumulative distribution function is used to subdivide the particle size range of the gunpowder particles. The particle size distribution reference value is generated by weighting the cumulative proportion change of particles in different particle size ranges to reflect the uniformity of the gunpowder particles. The calculation expression of the particle size distribution reference value is:

[0029] ,

[0030] in: and is the particle size range The cumulative proportion within the range, i is an index variable used to indicate the number of the particle size interval. Specifically, i is used to traverse and identify the particle size data of different particle size intervals in the cumulative distribution function, k represents the number of particle size intervals, and are the minimum and maximum particle sizes in the sample, respectively. is the interval weight factor, reflecting the sensitivity of different particle size intervals to fluidity changes. is an adjustment factor used to adjust the importance of each particle size interval in the entire distribution. Indicates the reference value of particle size distribution.

[0031] Preferably, under the monitoring window, the specific steps of analyzing the degree to which the extracted gunpowder becomes more compact due to compression during the transportation process to generate a compaction reference value are as follows:

[0032] Firstly, a high-precision sensor is used to monitor the density change of gunpowder in the delivery pipeline in real time. By measuring the volume density of gunpowder at different delivery positions, the initial density of gunpowder and the final density under compression are obtained.

[0033] A "compactness factor" is defined to reflect the degree to which the gunpowder particles become more compact due to compression during transportation. The calculation expression of the compactness factor is:

[0034] ,

[0035] in: is the compaction factor, is the final density of gunpowder during transportation, is the initial density of gunpowder, It is the pressure change during the gunpowder transportation process, indicating the compression force of the gunpowder caused by external force. is the pressure response index, which characterizes the sensitivity of gunpowder particles to pressure changes;

[0036] The compaction factor is combined with the gunpowder fluidity index to obtain a comprehensive compaction reference value, which accurately reflects the fluidity changes of gunpowder during transportation. The calculation expression of the compaction reference value is:

[0037] ,

[0038] in: is the compaction factor at time t, is the volume change rate at the tth moment, reflecting the volume shrinkage of gunpowder during transportation. is the pressure change at moment t, , are the weighted coefficients of the powder fluidity adjustment coefficient and the pressure sensitivity coefficient, respectively, which control the influence weight of each parameter on the compaction reference value. n represents the total number of time points in the monitoring window. Indicates the compaction reference value.

[0039] Preferably, according to the real-time feedback prediction results and warning signals, the conveying rate of the screw conveyor is dynamically adjusted to cope with the change of the fluidity of the gunpowder. The specific steps are as follows:

[0040] Before dynamically adjusting the conveying rate of the screw conveyor, an adjustment coefficient is first calculated to quantify the correlation between the current degree of gunpowder fluidity degradation and the conveying rate adjustment. The calculation expression of the adjustment coefficient is:

[0041] ,

[0042] in: It is a real-time feedback fluidity degradation index, reflecting the current state of gunpowder fluidity degradation. It is the preset reference threshold of liquidity degradation index, which is used to judge whether liquidity is abnormal. is the rate adjustment factor, which controls the sensitivity of the adjustment amplitude. is the current transmission rate, is the initial transport rate, is the adjustment factor;

[0043] The adjusted delivery rate is dynamically calculated based on the adjustment coefficient to ensure that the delivery rate can adapt to the changes in the fluidity of the gunpowder. The calculation expression of the adjusted delivery rate is:

[0044] ,

[0045] in: is the adjusted delivery rate, It is a dynamic adjustment factor that controls the weight of the downward adjustment range and is set according to the type of gunpowder and transportation conditions.

[0046] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0047] Through the risk monitoring and early warning system for the entire production cycle of fireworks and firecrackers, all-round dynamic monitoring and intelligent management of the gunpowder transportation process are achieved. When the fluidity of gunpowder changes due to environmental influences, it can capture anomalies in real time and intelligently predict the fluidity degradation trend through machine learning models, issue early warning signals in time, and guide operators to take effective intervention measures. At the same time, the conveying rate of the screw conveyor is dynamically adjusted according to the prediction results, effectively alleviating the friction heat and pressure accumulation caused by the decrease in fluidity, avoiding blockage and uneven filling, and significantly reducing the risk of spontaneous combustion or explosion of gunpowder. It not only improves the safety and stability of the transportation process, but also ensures the continuity of production efficiency, providing safe and efficient technical support for the production process of fireworks and firecrackers. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 This is a module schematic diagram of a full-cycle risk monitoring and early warning system for fireworks and firecrackers production according to the present invention. DETAILED DESCRIPTION

[0050] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0051] The present invention provides Figure 1 A risk monitoring and early warning system for the whole cycle of fireworks and firecrackers production is shown, comprising an initial delivery rate setting module, a real-time monitoring module, a data extraction module, a feature analysis module, an intelligent prediction module, an early warning trigger module and a dynamic adjustment module;

[0052] The initial conveying rate setting module, in the process of fireworks and firecrackers production, first sets the initial conveying rate of the screw conveyor according to historical conveying experience and the physical properties of gunpowder, and accurately loads the gunpowder to be filled into the shell of fireworks and firecrackers;

[0053] This step is based on the fluidity analysis of different types of gunpowder (such as particle size, humidity, density, etc.), and selects a suitable initial delivery rate. This rate will ensure that the gunpowder can be smoothly delivered to the shell of the fireworks and firecrackers, and the loading amount of gunpowder is accurate. By setting a reasonable initial delivery rate, the stability of gunpowder delivery can be maintained in most cases, and the standard loading requirements in the production process can be met. Avoid the fluidity problem of gunpowder caused by too fast or too slow delivery rate.

[0054] The initial conveying rate of the screw conveyor is set according to historical conveying experience and the physical properties of gunpowder. The specific steps are as follows:

[0055] First, collect and analyze the transportation data from previous production processes to understand the transportation performance of different types of gunpowder (such as particle size, moisture, density, fluidity, etc.) in different production environments. These data can come from production records, experimental results or historical feedback.

[0056] Based on the historical data collected, the characteristics of the gunpowder to be transported are analyzed. The focus is on evaluating factors such as the gunpowder particle size, humidity, viscosity, specific gravity, etc., which all affect the flowability of the gunpowder. The flowability of the gunpowder generally determines its behavior during transportation, especially whether it is prone to blockage or uneven flow.

[0057] According to the characteristics of the gunpowder and historical delivery experience, select a suitable initial delivery rate. This rate should ensure smooth delivery of the gunpowder under normal production conditions, while avoiding gunpowder accumulation, blockage or uneven filling caused by too fast or too slow delivery rates.

[0058] The purpose of this step is to set a reasonable starting speed for the screw conveyor to ensure that the gunpowder can be smoothly transported under normal production conditions and avoid problems in production such as blockage or overload caused by improper speed setting.

[0059] The real-time monitoring module deploys sensors at key locations in the conveying pipeline while the screw conveyor is running to monitor the conveying status of the gunpowder in real time and promptly capture changes in the flow status of the gunpowder;

[0060] During the operation of the screw conveyor, the deployed sensors include pressure sensors, temperature sensors, humidity sensors, flow sensors, and vibration sensors. The pressure sensor is used to monitor the pressure changes in the conveying pipeline to help identify whether the gunpowder is blocked or flowing unevenly; the temperature sensor monitors the temperature changes of the gunpowder during the conveying process to avoid overheating caused by friction or environmental changes; the humidity sensor is used to detect the humidity level of the gunpowder to help evaluate whether the fluidity of the gunpowder is affected by moisture; the flow sensor monitors the flow rate of the gunpowder in real time to ensure that it meets the preset standards; the vibration sensor helps detect whether the equipment has abnormal vibrations and further analyzes the stability of the gunpowder flow state.

[0061] Key locations include the feed end, the middle section of the conveyor, and the discharge end of the screw conveyor. At the feed end, sensors can monitor the initial flow state and loading status of the gunpowder; in the middle section of the conveyor, sensors can capture the dynamic changes of the gunpowder during the conveying process in real time to determine whether there are problems such as blockage, reduced fluidity, or friction overheating; at the discharge end, sensors are used to monitor the final delivery effect of the gunpowder, ensure accurate loading, and promptly feedback any abnormalities during the conveying process. By monitoring these key locations, the delivery status of the gunpowder can be fully grasped and potential risks can be effectively prevented.

[0062] The data extraction module sorts and processes the raw data obtained by the sensor to extract key feature information related to the decrease in gunpowder fluidity;

[0063] The feature analysis module analyzes the extracted key information in the monitoring window and preliminarily quantifies the deterioration of the fluidity of the gunpowder during transportation;

[0064] The intelligent prediction module sends the analysis results as input data to a pre-trained machine learning model, and uses the machine learning model to make intelligent predictions on gunpowder fluidity;

[0065] The process of combing and preprocessing raw data includes several key steps:

[0066] First, the data acquired by the sensor is denoised to remove outliers and noise caused by sensor errors or external interference;

[0067] Then, the data is normalized or standardized to ensure that various data parameters (such as temperature, pressure, humidity, etc.) have a unified dimension and scale for subsequent analysis and processing;

[0068] Next, fill in missing values ​​or interpolate the data to ensure data integrity;

[0069] Finally, the data is smoothed through methods such as sliding windows to eliminate short-term fluctuations and ensure the continuity and stability of the data over time.

[0070] Through this series of combing and preprocessing, we ensure that the data input into subsequent analysis and machine learning models is accurate, reliable and of high quality.

[0071] Key feature information related to the decrease in fluidity of gunpowder is extracted, wherein the extracted features include the uniformity of gunpowder particles and the degree to which the gunpowder becomes denser due to compression during transportation. Under the monitoring window, the uniformity of the extracted gunpowder particles and the degree to which the gunpowder becomes denser due to compression during transportation are analyzed, and particle size distribution reference values ​​and compaction reference values ​​are generated respectively. The particle size distribution reference values ​​and compaction reference values ​​are used to preliminarily quantify the deterioration in fluidity of gunpowder during transportation.

[0072] When the uniformity of the gunpowder particles is poor, it usually indicates that the flowability of the gunpowder is deteriorating. Poor uniformity of gunpowder particles may mean that the particles are of different sizes, some particles may be too large or too small, or even aggregated, which will cause the gunpowder to flow erratically during delivery. Larger particles may get stuck or block the delivery pipeline, while smaller particles may have a strong surface adhesion, resulting in reduced flowability. In addition, the unevenness of the particles may increase friction and compaction, making the delivery process more difficult, further affecting the filling accuracy and efficiency of the gunpowder. Therefore, poor particle uniformity is a clear indicator of reduced gunpowder flowability.

[0073] Under the monitoring window, the specific steps for analyzing the uniformity of the extracted gunpowder particles and generating a reference value for the particle size distribution are as follows:

[0074] The particle size data of gunpowder particles are obtained through image processing or sensors such as particle size analyzers. These data are obtained through multiple measurements and reflect the distribution of gunpowder particles at different sizes. Then, using these particle size data, the cumulative distribution function of gunpowder particles is calculated. The cumulative distribution function is a function that reflects the proportion of particles in different particle size ranges. Its calculation expression is:

[0075] ,

[0076] Where: d represents the particle size, is the cumulative distribution function, which describes the proportion of particles with a size less than or equal to d, and reflects the particle size distribution of gunpowder particles. represents the number of particles with a particle size less than or equal to d, is the total number of particles in the sample;

[0077] The cumulative distribution function represents the cumulative proportion of particles below a certain particle size threshold. When the fluidity of the gunpowder particles is good, the cumulative distribution function Usually smooth and uniform; when liquidity is poor, the cumulative distribution function The purpose of this step is to provide basic data for the subsequent generation of particle size distribution reference values, reflecting the distribution of particles.

[0078] The cumulative distribution function is used to subdivide the particle size range of the gunpowder particles. The particle size distribution reference value is generated by weighting the cumulative proportion change of particles in different particle size ranges to reflect the uniformity of the gunpowder particles. The calculation expression of the particle size distribution reference value is:

[0079] ,

[0080] in: and is the particle size range The cumulative proportion within the range, i is an index variable used to indicate the number of the particle size interval. Specifically, i is used to traverse and identify the particle size data of different particle size intervals in the cumulative distribution function, k represents the number of particle size intervals, and are the minimum and maximum particle sizes in the sample, respectively. is the interval weight factor, which reflects the sensitivity of different particle size intervals to changes in fluidity. Larger particles or very fine particles may have a greater impact on fluidity, so their weight factors are relatively high. It is an adjustment factor used to adjust the importance of each particle size range in the entire distribution. It is usually adjusted according to experimental data. Indicates the reference value of particle size distribution;

[0081] By analyzing the changes in particle distribution within different particle size ranges, the uniformity of the particles can be quantified. The larger the value of the particle size distribution reference value, the more uneven the particle distribution and the poorer the fluidity; the smaller the value of the particle size distribution reference value, the more uniform the particle distribution and the better the fluidity. This method can accurately judge the fluidity of gunpowder particles and provide real-time early warning information.

[0082] It can be seen from the particle size distribution reference value that, under the monitoring window, the larger the performance value of the particle size distribution reference value generated by analyzing the uniformity of the extracted gunpowder particles, the more uneven the distribution of the particles, the worse the fluidity of the gunpowder, and the greater the risk in the transportation process. Specifically, when the particle size distribution is uneven, there may be larger particles or too fine particles, which may cause blockages, excessive friction, pressure concentration and other problems during transportation, thereby increasing the risk of spontaneous combustion or explosion. Therefore, the larger the value of the particle size distribution reference value, the more significant the difference between the particles, and the higher the possibility and risk of poor fluidity. When the particle size distribution is more uniform, the value of the particle size distribution reference value is lower, the fluidity of the particles is better, the transportation process is smoother and more stable, and the risk of poor fluidity is relatively small.

[0083] The degree to which gunpowder becomes denser due to compression during delivery is usually a sign that the flowability of the gunpowder is deteriorating. Compression causes the gaps between gunpowder particles to decrease, which increases the mutual friction between the particles and hinders their free flow. When the flowability of gunpowder decreases, the particles are more likely to be tightly bound or compacted, causing the gunpowder in the delivery pipeline to become more agglomerated, increasing the pressure and friction during delivery. This situation may cause blockages, uneven loading or unstable delivery processes, further affecting the precise loading of gunpowder and increasing the risk of spontaneous combustion or explosion of gunpowder. Therefore, monitoring changes in the compaction of gunpowder can be used as an important indicator to identify decreased flowability.

[0084] Under the monitoring window, the specific steps for analyzing the degree to which the extracted gunpowder becomes more compact due to compression during the transportation process to generate a compaction reference value are as follows:

[0085] Firstly, high-precision sensors (such as pressure sensors, laser ranging sensors, etc.) are used to monitor the density changes of gunpowder in the delivery pipeline in real time. By measuring the volume density of gunpowder at different delivery positions, the initial density of gunpowder and the final density under compression are obtained.

[0086] By installing sensors at different positions of the screw conveyor, the volume density changes of gunpowder at each position during the conveying process are measured in real time. The initial density refers to the density of the gunpowder when it enters the conveying pipeline, which is usually in a loose state; while the final density is the density of the gunpowder after it becomes more compact due to compression during the conveying process. During the conveying process, the gunpowder is affected by factors such as pressure and friction, and the particles may shrink, resulting in an increase in its density. This change in density reflects the degree of compaction of the gunpowder, which helps to analyze the fluidity of the gunpowder and possible flow problems (such as blockage).

[0087] A "compactness factor" is defined to reflect the degree to which the gunpowder particles become more compact due to compression during transportation. The calculation expression of the compactness factor is:

[0088] ,

[0089] in: is the compaction factor, is the final density of gunpowder during transportation, is the initial density of gunpowder, It is the pressure change during the gunpowder transportation process, indicating the compression force of the gunpowder caused by external force. is the pressure response index, which characterizes the sensitivity of gunpowder particles to pressure changes;

[0090] By combining pressure change and density ratio to measure the compaction degree of gunpowder, we ensure that the compaction factor not only takes into account the density change, but also reflects the reaction characteristics of gunpowder under different pressures. Through this step, we can quantify the change in density of gunpowder during transportation, reveal the decrease in fluidity of gunpowder due to compression, and provide basic data for subsequent steps.

[0091] The compaction factor is combined with the fluidity index of gunpowder (such as friction, relative movement between particles, etc.) to obtain a comprehensive compaction reference value, which accurately reflects the fluidity change of gunpowder during transportation. The calculation expression of the compaction reference value is:

[0092] ,

[0093] in: is the compaction factor at time t, is the volume change rate at the tth moment, reflecting the volume shrinkage of gunpowder during transportation. is the pressure change at moment t, , are the weighted coefficients of the powder fluidity adjustment coefficient and the pressure sensitivity coefficient, respectively, which control the influence weight of each parameter on the compaction reference value. n represents the total number of time points in the monitoring window. Indicates the compaction reference value;

[0094] Combining the compaction factor with factors such as pressure and volume change to form a comprehensive compaction reference value can more accurately reflect the degree of compaction of gunpowder during transportation and its impact on fluidity. Through multi-dimensional analysis of compaction, a comprehensive compaction reference value is provided, making it possible to accurately monitor changes in gunpowder fluidity, identify signs of decreased fluidity in a timely manner, and take appropriate measures.

[0095] It can be seen from the compaction reference value that, under the monitoring window, the larger the performance value of the compaction reference value generated by analyzing the degree to which the extracted gunpowder becomes tighter due to compression during transportation, the greater the risk of poor fluidity as the gunpowder becomes tighter due to compression during transportation. This usually indicates that the gunpowder is subjected to a greater compression force in the transportation pipeline, the gap between the particles is reduced, and the fluidity is poor, which may lead to blockage or uneven loading, thereby increasing the risk of spontaneous combustion or explosion of the gunpowder. On the contrary, when the compaction reference value is low, it means that the gaps between the gunpowder particles are larger, the fluidity is better, the transportation process is smoother, and the risk is relatively small. Therefore, the compaction reference value can effectively reflect the potential risk of decreased fluidity of gunpowder.

[0096] The particle size distribution reference value and compaction reference value generated by analyzing the uniformity of gunpowder particles and the degree to which gunpowder becomes denser due to compression during transportation are sent as input data to a pre-trained machine learning model. The fluidity degradation index is generated by the machine learning model, and the deterioration of gunpowder fluidity is intelligently predicted based on the fluidity degradation index.

[0097] A pre-trained machine learning model refers to a mathematical model used to predict changes in gunpowder fluidity during the gunpowder delivery process, which is obtained through algorithm training based on historical data and pre-set rules. The core of this model is that it captures the characteristics and changing patterns related to gunpowder fluidity by learning a large amount of experimental data and actual operation records. For example, during the training process, the model learns how gunpowder fluidity changes with time, environment, and external operating factors under different circumstances by inputting features such as particle size distribution reference values ​​and compaction reference values. With these data, the machine learning model can make intelligent predictions about future fluidity changes based on what it has learned when encountering new data.

[0098] During the gunpowder delivery process, the application of machine learning models can capture abnormal changes in gunpowder fluidity in real time. By inputting real-time monitoring data (such as particle size distribution reference values ​​and compaction reference values), the model can accurately identify whether the gunpowder fluidity has degraded. When these input data change, the trained model will predict the trend of possible deterioration of gunpowder fluidity based on the rules it has learned, and generate a fluidity degradation index. As a predictive tool, this degradation index can send out early warning signals at critical moments in the gunpowder delivery process, guiding operators to adjust the delivery rate or take other remedial measures in a timely manner to ensure the safety of the production process and the accuracy of gunpowder loading.

[0099] In order for the machine learning model to make predictions efficiently and accurately, data collection and processing are first required. These data include various sensor data during the gunpowder transportation process, such as particle size distribution, compaction, humidity, temperature, etc., as well as historical gunpowder fluidity data, pressure changes in the transportation pipeline, friction of gunpowder particles and other multi-dimensional feature data. By collecting and processing these data, the model can learn the laws of gunpowder fluidity changes and its sensitivity to external conditions (such as humidity, temperature changes, transportation speed, etc.). Next, by selecting appropriate machine learning algorithms (such as random forests, support vector machines, neural networks, etc.), these data are trained to obtain an accurate prediction model.

[0100] The training of machine learning models depends not only on historical input data, but also on accurate data labeling. Data labeling refers to associating historical data with actual liquidity changes so that the model can learn the specific impact of different features on liquidity. For example, by labeling the specific scenarios of gunpowder liquidity degradation (for example, gunpowder liquidity degradation is greater or less), the model can gradually optimize its prediction ability through supervised learning. During the training process, the model continuously adjusts its internal parameters, and ultimately can accurately map the relationship between input features and gunpowder liquidity degradation. After sufficient training, the machine learning model can not only predict the liquidity degradation index based on new sensor data, but also optimize itself based on historical data, so that the accuracy and reliability of its predictions continue to improve.

[0101] The machine learning model is not specifically limited here, and can achieve the particle size distribution reference value and compaction reference value Conduct comprehensive analysis to generate a liquidity degradation index In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the liquidity degradation index The resulting calculation formula is:

[0102] ,

[0103] In the formula, , are the reference values ​​of particle size distribution and compaction reference value The weight factor of , are all greater than 0. Weight factor ( and ) are used in the formula to balance and adjust the influence of the particle size distribution reference value and the compaction reference value on the fluidity degradation index. They reflect the relative importance of each index in the fluidity degradation assessment. For example, when the unevenness of particle size distribution is the main cause of fluidity degradation, you can set , giving a higher weight to the particle size distribution reference value; and when the compaction degree has a more significant effect on fluidity, By dynamically adjusting the weight factor, it can adapt to different gunpowder characteristics or transportation conditions, making the calculation results more accurate and in line with actual needs. At the same time, the normalization processing in the denominator ( ) ensures that the calculated liquidity degradation index has a uniform dimension and range, thereby improving the flexibility and robustness of the model.

[0104] It can be seen from the fluidity degradation index that, under the monitoring window, the larger the performance value of the particle size distribution reference value generated by analyzing the uniformity of the extracted gunpowder particles, the larger the performance value of the compaction reference value generated by analyzing the degree to which the extracted gunpowder becomes denser due to compression during the transportation process. That is, the larger the fluidity degradation index generated when the fluidity of gunpowder is intelligently predicted by a pre-trained machine learning model under the monitoring window, the greater the risk of deterioration in fluidity during gunpowder transportation, and vice versa.

[0105] The early warning trigger module automatically sends out an early warning signal when the machine learning model predicts that the fluidity of the gunpowder has deteriorated, ensuring that operators remain highly alert to potential risks in the gunpowder delivery process, understand abnormal changes in the fluidity of the gunpowder in a timely manner, and take further intervention measures;

[0106] The fluidity degradation index generated by intelligently predicting the fluidity of gunpowder under the monitoring window through the pre-trained machine learning model is compared and analyzed with the pre-set reference threshold of the fluidity degradation index to intelligently perceive the deterioration of gunpowder fluidity. The specific steps are as follows:

[0107] If the fluidity degradation index is greater than the reference threshold of the fluidity degradation index, a high-risk signal is generated, and an early warning is automatically issued for the generated high-risk signal, ensuring that operators remain highly alert to potential risks in the process of gunpowder transportation, understand abnormal changes in gunpowder fluidity in a timely manner, and take further intervention measures;

[0108] If the fluidity degradation index is less than or equal to the fluidity degradation index reference threshold, a risk-free signal is generated, indicating that the gunpowder to be loaded can be efficiently transported by the screw conveyor at this time, and no signal is generated, and the gunpowder continues to be transported.

[0109] Early warnings can be sent to relevant personnel through alarms, interface prompts, text messages or emails. Early warning signals usually include the type of change in gunpowder fluidity, the time of occurrence and the possible risk level, ensuring that operators can be aware of the problem in time and take necessary countermeasures.

[0110] The dynamic adjustment module dynamically adjusts the conveying rate of the screw conveyor according to the real-time feedback prediction results and warning signals to cope with the changes in the fluidity of the gunpowder. By timely lowering the conveying rate, it ensures that the screw conveyor can still complete the conveying task efficiently and safely when the fluidity of the gunpowder changes, effectively reducing the friction heat and pressure generated during the conveying process, avoiding gunpowder blockage or uneven filling, and reducing the risk of gunpowder spontaneous combustion or explosion;

[0111] According to the real-time feedback prediction results and early warning signals, the conveying rate of the screw conveyor is dynamically adjusted to cope with the changes in the fluidity of the gunpowder. The specific steps are as follows:

[0112] Before dynamically adjusting the conveying rate of the screw conveyor, an adjustment coefficient is first calculated to quantify the correlation between the current degree of gunpowder fluidity degradation and the conveying rate adjustment. The calculation expression of the adjustment coefficient is:

[0113] ,

[0114] in: It is a real-time feedback fluidity degradation index, reflecting the current state of gunpowder fluidity degradation. It is the preset reference threshold of liquidity degradation index, which is used to judge whether liquidity is abnormal. is the rate adjustment factor, which controls the sensitivity of the adjustment range and is set according to production experience (such as 0.5-1.0). is the current transmission rate, is the initial transport rate, is the adjustment factor;

[0115] This step takes into account both the degree of fluidity degradation and the ratio of the current delivery rate to the initial rate, ensuring that the adjustment process is highly sensitive to changes in the powder state. The effect of fluidity degradation on the delivery rate is quantified by the adjustment coefficient, providing a clear calculation basis for subsequent adjustments.

[0116] The adjusted delivery rate is dynamically calculated based on the adjustment coefficient to ensure that the delivery rate can adapt to the changes in the fluidity of the gunpowder. The calculation expression is:

[0117] ,

[0118] in: is the adjusted delivery rate, It is a dynamic adjustment factor that controls the weight of the downward adjustment range, usually between 0.1-0.5, and is set according to the type of gunpowder and delivery conditions;

[0119] The core of this step is to use the adjustment coefficient to directly correct the current delivery rate. If the fluidity degradation index is significantly higher than the reference threshold of the fluidity degradation index, the adjustment coefficient increases, thereby reducing the delivery rate to a greater extent. The dynamically adjusted delivery rate can effectively reduce friction heat and pressure, and avoid blockage or compression caused by decreased fluidity of gunpowder.

[0120] Through the above-mentioned risk monitoring and early warning system for the entire production cycle of fireworks and firecrackers, all-round dynamic monitoring and intelligent management of the gunpowder transportation process are realized. When the fluidity of gunpowder changes due to environmental influences, it can capture anomalies in real time and intelligently predict the fluidity degradation trend through machine learning models, issue early warning signals in time, and guide operators to take effective intervention measures. At the same time, the system can dynamically adjust the conveying rate of the screw conveyor according to the prediction results, effectively alleviate the friction heat and pressure accumulation caused by the decrease in fluidity, avoid blockage and uneven filling, and significantly reduce the risk of spontaneous combustion or explosion of gunpowder. The overall solution not only improves the safety and stability of the transportation process, but also ensures the continuity of production efficiency, providing safe and efficient technical support for the production process of fireworks and firecrackers.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0123] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A risk monitoring and early warning system for the entire production cycle of fireworks and firecrackers, characterized in that: It includes an initial delivery rate setting module, a real-time monitoring module, a data extraction module, a feature analysis module, an intelligent prediction module, an early warning trigger module and a dynamic adjustment module; The initial conveying rate setting module sets the initial conveying rate of the screw conveyor according to historical conveying experience and the physical characteristics of gunpowder, and accurately loads the gunpowder to be filled into the shell of fireworks and firecrackers; The real-time monitoring module deploys sensors at key locations in the conveying pipeline while the screw conveyor is running to monitor the conveying status of the gunpowder in real time and promptly capture changes in the flow status of the gunpowder; The data extraction module sorts and processes the raw data obtained by the sensor to extract key feature information related to the decrease in gunpowder fluidity; Extract key feature information related to the decrease in fluidity of gunpowder, wherein the extracted features include the uniformity of gunpowder particles and the degree to which the gunpowder becomes more compact due to compression during transportation. Under the monitoring window, analyze the uniformity of the extracted gunpowder particles and the degree to which the gunpowder becomes more compact due to compression during transportation, and generate a particle size distribution reference value and a compactness reference value respectively. The particle size distribution reference value and the compactness reference value are used to preliminarily quantify the deterioration of fluidity during gunpowder transportation. Under the monitoring window, the specific steps for analyzing the uniformity of the extracted gunpowder particles and generating a reference value for the particle size distribution are as follows: Obtaining particle size data of gunpowder particles, and calculating a cumulative distribution function of the gunpowder particles using the obtained particle size data; The cumulative distribution function is used to subdivide the particle size range of the gunpowder particles. The particle size distribution reference value is generated by weighting the cumulative proportion change of particles in different particle size ranges to reflect the uniformity of the gunpowder particles. Under the monitoring window, the specific steps for analyzing the degree to which the extracted gunpowder becomes more compact due to compression during the transportation process to generate a compaction reference value are as follows: Firstly, a high-precision sensor is used to monitor the density change of gunpowder in the delivery pipeline in real time. By measuring the volume density of gunpowder at different delivery positions, the initial density of gunpowder and the final density under compression are obtained. Define a "compactness factor" to reflect the degree to which the gunpowder particles become more compact due to compression during transportation; The compaction factor is combined with the gunpowder fluidity index to obtain a comprehensive compaction reference value, which accurately reflects the fluidity changes of gunpowder during transportation. The feature analysis module analyzes the extracted key information in the monitoring window and preliminarily quantifies the deterioration of the fluidity of the gunpowder during transportation; The intelligent prediction module sends the analysis results as input data to a pre-trained machine learning model, and uses the machine learning model to make intelligent predictions on gunpowder fluidity; The early warning trigger module automatically sends out an early warning signal when the machine learning model predicts that the fluidity of the gunpowder has deteriorated, ensuring that operators remain highly alert to potential risks in the gunpowder delivery process, understand abnormal changes in the fluidity of the gunpowder in a timely manner, and take further intervention measures; The dynamic adjustment module dynamically adjusts the conveying rate of the screw conveyor according to the real-time feedback prediction results and warning signals to cope with the changes in the fluidity of the gunpowder. By timely lowering the conveying rate, it ensures that the screw conveyor can still complete the conveying task efficiently and safely when the fluidity of the gunpowder changes.

2. A fireworks and firecracker production full cycle risk monitoring and early warning system according to claim 1, characterized in that: The initial conveying rate of the screw conveyor is set according to historical conveying experience and the physical properties of gunpowder. The specific steps are as follows: First, we collected and analyzed the transportation data from previous production processes to understand the transportation performance of different types of gunpowder in different production environments; Based on the collected historical data, the characteristics of the gunpowder to be transported are analyzed; According to the characteristics of gunpowder and historical delivery experience, select a suitable initial delivery rate to ensure smooth delivery of gunpowder under normal production conditions, while avoiding gunpowder accumulation, blockage or uneven loading caused by too fast or too slow delivery rate.

3. A fireworks and firecracker production full cycle risk monitoring and early warning system according to claim 1, characterized in that: The particle size distribution reference value and compaction reference value generated by analyzing the uniformity of gunpowder particles and the degree to which gunpowder becomes denser due to compression during transportation are sent as input data to a pre-trained machine learning model. The fluidity degradation index is generated by the machine learning model, and the deterioration of gunpowder fluidity is intelligently predicted based on the fluidity degradation index.

4. A fireworks and firecracker production full cycle risk monitoring and early warning system according to claim 3, characterized in that: The fluidity degradation index generated by intelligently predicting the fluidity of gunpowder under the monitoring window through the pre-trained machine learning model is compared and analyzed with the pre-set reference threshold of the fluidity degradation index to intelligently perceive the deterioration of gunpowder fluidity. The specific steps are as follows: If the fluidity degradation index is greater than the reference threshold of the fluidity degradation index, a high-risk signal is generated, and an early warning is automatically issued for the generated high-risk signal, ensuring that operators remain highly alert to potential risks in the process of gunpowder transportation, understand abnormal changes in gunpowder fluidity in a timely manner, and take further intervention measures; If the fluidity degradation index is less than or equal to the fluidity degradation index reference threshold, a risk-free signal is generated, indicating that the gunpowder to be loaded can be efficiently transported by the screw conveyor at this time, and no signal is generated, and the gunpowder continues to be transported.

5. The risk monitoring and early warning system for the whole cycle of fireworks and firecrackers production according to claim 1 is characterized in that: Under the monitoring window, the specific steps for analyzing the uniformity of the extracted gunpowder particles and generating a reference value for the particle size distribution are as follows: The particle size data of the gunpowder particles are obtained, and the cumulative distribution function of the gunpowder particles is calculated using the obtained particle size data. The cumulative distribution function is a function that reflects the proportion of particles in different particle size ranges, and its calculation expression is: ， in: d represents the particle size, is the cumulative distribution function, which describes the proportion of particles with a size less than or equal to d, and reflects the particle size distribution of gunpowder particles. represents the number of particles with a particle size less than or equal to d, is the total number of particles in the sample; The cumulative distribution function is used to subdivide the particle size range of the gunpowder particles. The particle size distribution reference value is generated by weighting the cumulative proportion change of particles in different particle size ranges to reflect the uniformity of the gunpowder particles. The calculation expression of the particle size distribution reference value is: ， in: and is the particle size range The cumulative proportion within i is an index variable used to indicate the number of the particle size interval. Specifically, i Used to traverse and identify the particle size data of different particle size intervals in the cumulative distribution function. k represents the number of particle size intervals, and are the minimum and maximum particle sizes in the sample, respectively. is the interval weight factor, reflecting the sensitivity of different particle size intervals to fluidity changes. is an adjustment factor used to adjust the importance of each particle size interval in the entire distribution. Indicates the reference value of particle size distribution.

6. The risk monitoring and early warning system for the whole cycle of fireworks and firecrackers production according to claim 1 is characterized in that: Under the monitoring window, the specific steps for analyzing the degree to which the extracted gunpowder becomes more compact due to compression during the transportation process to generate a compaction reference value are as follows: Firstly, a high-precision sensor is used to monitor the density change of gunpowder in the delivery pipeline in real time. By measuring the volume density of gunpowder at different delivery positions, the initial density of gunpowder and the final density under compression are obtained. A "compactness factor" is defined to reflect the degree to which the gunpowder particles become more compact due to compression during transportation. The calculation expression of the compactness factor is: ， in: is the compaction factor, is the final density of gunpowder during transportation, is the initial density of gunpowder, It is the pressure change during the gunpowder transportation process, indicating the compression force of the gunpowder caused by external force. is the pressure response index, which characterizes the sensitivity of gunpowder particles to pressure changes; The compaction factor is combined with the gunpowder fluidity index to obtain a comprehensive compaction reference value, which accurately reflects the fluidity changes of gunpowder during transportation. The calculation expression of the compaction reference value is: ， in: is the compaction factor at time t, is the volume change rate at the tth moment, reflecting the volume shrinkage of gunpowder during transportation. is the pressure change at moment t, , are the weighted coefficients of the gunpowder fluidity adjustment coefficient and the pressure sensitivity coefficient, respectively, which control the influence weight of each parameter on the compaction reference value. n Indicates the total number of time points under the monitoring window. Indicates the compaction reference value.

7. A fireworks and firecracker production full cycle risk monitoring and early warning system according to claim 4, characterized in that: According to the real-time feedback prediction results and early warning signals, the conveying rate of the screw conveyor is dynamically adjusted to cope with the changes in the fluidity of the gunpowder. The specific steps are as follows: Before dynamically adjusting the conveying rate of the screw conveyor, an adjustment coefficient is first calculated to quantify the correlation between the current degree of gunpowder fluidity degradation and the conveying rate adjustment. The calculation expression of the adjustment coefficient is: ， in: It is a real-time feedback fluidity degradation index, reflecting the current state of gunpowder fluidity degradation. It is the preset reference threshold of liquidity degradation index, which is used to judge whether liquidity is abnormal. is the rate adjustment factor, which controls the sensitivity of the adjustment amplitude. is the current transmission rate, is the initial transport rate, is the adjustment factor; The adjusted delivery rate is dynamically calculated based on the adjustment coefficient to ensure that the delivery rate can adapt to the changes in the fluidity of the gunpowder. The calculation expression of the adjusted delivery rate is: ， in: is the adjusted delivery rate, It is a dynamic adjustment factor that controls the weight of the downward adjustment range and is set according to the type of gunpowder and transportation conditions.

Images