Intelligent monitoring method and system for dust concentration in feed processing process

Abstract

The application discloses a kind of feed processing process dust concentration intelligent monitoring method and system, it is related to industrial automation control technical field, including: by intelligent dust concentration sensor obtains the dust concentration data of multiple monitoring points, and corresponding processing process parameter data are synchronously collected.By analyzing the timing relationship of concentration fluctuation moment and process parameter change moment, the process action that causes concentration fluctuation is identified, and process-dust correlation atlas is established.Through the time difference of dust concentration rise moment between monitoring points and the space position reverse tracking dust propagation direction, the position of dust generation source is determined.Combined with prediction analysis, when expected dust concentration increment is about to occur, timely start ventilation device and adjust process execution intensity, effectively control dust concentration change, improve production environment safety and environmental protection.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control technology, specifically to a method and system for intelligent monitoring of dust concentration in feed processing. Background Technology

[0002] Dust pollution has always been a major challenge in feed processing. With the continuous expansion of production scale, traditional dust concentration monitoring methods are no longer sufficient to meet the needs of accurate monitoring and effective control. While existing dust monitoring equipment can acquire real-time dust concentration data for a given area, the lack of a direct temporal correlation between this data collection and processing parameters makes it difficult to accurately identify the intrinsic link between process changes and dust concentration fluctuations. Traditional monitoring methods often fail to effectively predict dust concentration fluctuations and lack the ability to take timely measures to prevent pollution spread. Therefore, the prediction, tracing, and control of dust concentration have become crucial to solving this problem.

[0003] With the development of intelligent sensor technology, utilizing multi-point distributed sensors to acquire dust concentration data at different monitoring points, combined with advanced process parameter acquisition and data analysis technologies, can provide a more accurate and dynamic dust concentration monitoring system. However, how to correlate dust concentration fluctuations with processing actions and achieve timely dust control through predictive analysis remains a challenge in current technology. Accurately tracing the source of dust generation and implementing effective ventilation control measures to improve production safety while ensuring efficient and environmentally friendly process operations remains a pressing technical problem for the industry. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent monitoring method and system for dust concentration in feed processing, aiming to solve at least one of the technical problems existing in the prior art.

[0005] The technical solution of this invention is: a method for intelligent monitoring of dust concentration in feed processing, comprising the following steps: Dust concentration data from multiple monitoring points in the feed processing area are obtained through intelligent dust concentration sensors, and corresponding processing parameter data are collected simultaneously. Identify the temporal correspondence between the time of concentration fluctuation in dust concentration data and the time of parameter change in processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between process action and concentration fluctuation amplitude, and obtain the process-dust correlation map. Extract the time of dust concentration rise at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source. When it is detected that a process action recorded in the process-dust correlation graph is about to be executed, the corresponding correlation strength is obtained and the expected dust concentration increment is calculated. Before the dust concentration data actually increases, the ventilation target area is determined based on the location of the dust generation source, the ventilation intensity is determined based on the expected increase in dust concentration, and the ventilation device in the ventilation target area is activated. At the same time, the execution intensity of the process actions is adjusted.

[0006] Identify the temporal correspondence between the times of dust concentration fluctuations in the data and the times of parameter changes in the process parameter data, determine the process actions that cause the concentration fluctuations, statistically analyze the correlation strength between the process actions and the amplitude of concentration fluctuations, and obtain the process-dust correlation map, including: Extract the concentration fluctuation time from the dust concentration data and the parameter change time from the processing parameter data, calculate the time interval between each concentration fluctuation time and each parameter change time, filter the time intervals where the parameter change time is earlier than the concentration fluctuation time, and establish a time-series correspondence between the parameter change time and the concentration fluctuation time corresponding to the filtered time intervals. Extract the time of parameter change from the time-series correspondence, and determine the process parameter changes that occur at the time of parameter change as the process actions that cause concentration fluctuations; Extract all concentration fluctuation moments corresponding to each process action from the time sequence correspondence, obtain the concentration fluctuation amplitude corresponding to each concentration fluctuation moment, accumulate the concentration fluctuation amplitude corresponding to each process action to obtain the cumulative value of concentration fluctuation amplitude, and calculate the correlation strength between each process action and the concentration fluctuation amplitude based on the cumulative value of concentration fluctuation amplitude. A correlation graph with process actions as nodes is constructed. The correlation strength and cumulative value of concentration fluctuation amplitude corresponding to the process actions are recorded in the nodes. The nodes are connected according to the temporal relationship of the concentration fluctuation time in the temporal correspondence to obtain the process-dust correlation graph.

[0007] Extract the time of dust concentration rise at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction backwards based on the time difference and the spatial location of each monitoring point to obtain the location of the dust generation source, including: Extract the time of dust concentration rise at each monitoring point, sort the monitoring points from morning to night according to the time of dust concentration rise, and obtain the dust arrival sequence. Extract the dust concentration rise time of adjacent monitoring points from the dust arrival sequence, calculate the time difference of the dust concentration rise time between adjacent monitoring points, and obtain the time difference sequence; Obtain the spatial coordinates of each monitoring point in the dust arrival sequence, calculate the spatial distance between adjacent monitoring points, and calculate the propagation speed and direction of dust between adjacent monitoring points based on the time difference sequence and spatial distance to obtain the propagation speed vector sequence. The main propagation direction of dust is obtained by weighted synthesis of the propagation velocity vectors in the propagation velocity vector sequence. The dust source location is determined by extending the tracing path outward from the earliest monitoring point in the dust arrival sequence in the opposite direction of the main dust propagation direction, and determining the intersection of the tracing path and the boundary of the feed processing area.

[0008] Obtain the spatial coordinates of each monitoring point in the dust arrival sequence, calculate the spatial distance between adjacent monitoring points, and calculate the propagation speed and direction of dust between adjacent monitoring points based on the time difference sequence and spatial distance. The resulting propagation speed vector sequence includes: The spatial coordinates of adjacent monitoring points are obtained from the dust arrival sequence, a spatial line is established between adjacent monitoring points, the length of the spatial line is measured to obtain the spatial distance, and the deflection angle of the spatial line relative to the reference coordinate axis is measured to obtain the spatial azimuth. Extract the time difference values ​​corresponding to adjacent monitoring points from the time difference sequence, determine the dust propagation speed based on the spatial distance and time difference values, determine the dust propagation direction angle based on the spatial azimuth angle, and construct a two-dimensional propagation speed vector by combining the propagation speed magnitude and propagation direction angle. The two-dimensional propagation velocity vectors corresponding to each adjacent monitoring point are standardized, and the standardized propagation velocity vectors are arranged and combined according to the temporal relationship of the dust arrival sequence to obtain the propagation velocity vector sequence.

[0009] When a process action recorded in the process-dust correlation graph is about to be executed, the corresponding correlation strength is obtained, and the expected dust concentration increment is calculated, including: Real-time monitoring of the execution status of process actions within the feed processing area; identification of process actions switching from standby to start-up state; extraction of action identifiers for process actions; and querying the correlation strength from the process-dust correlation graph based on the action identifiers. The historical dust concentration change curve is obtained based on the action identifier. The concentration peak value and the concentration baseline value are extracted from the historical dust concentration change curve. The difference between the concentration peak value and the concentration baseline value is calculated to obtain the historical dust concentration increment. Obtain the current ventilation system air volume value at the start of the process action, determine the dust dilution capacity based on the current ventilation system air volume value, and calculate the correlation between the historical dust concentration increment and the dust dilution capacity to obtain the environmentally corrected concentration increment. The correlation strength is used as a weight to weight the concentration increment after environmental correction, so as to obtain the expected dust concentration increment.

[0010] Before the dust concentration actually increases, the target ventilation area is determined based on the location of the dust source. The ventilation intensity is determined based on the expected increase in dust concentration, and the ventilation devices in the target area are activated. At the same time, the execution intensity of process actions is adjusted, including: Obtain the location of the dust source, retrieve the historical dust diffusion trajectory data corresponding to the location of the dust source, extract the spatial area where the dust concentration exceeds the concentration threshold from the historical dust diffusion trajectory data, identify the ventilation device markings deployed in the spatial area, and determine the area corresponding to the ventilation device markings as the ventilation target area based on the location of the dust source. According to the ventilation device identification, obtain the air volume adjustment level information of the ventilation device, obtain the expected dust concentration increment value, match the corresponding level in the air volume adjustment level information according to the expected dust concentration increment value to determine the ventilation intensity and generate a level switching command, send the level switching command to the ventilation device corresponding to the ventilation device identification and start the ventilation device in the ventilation target area. The system acquires historical execution records of process actions, extracts the correspondence between execution parameters and dust generation from these records, finds the upper limit of execution parameters that meet the conditions based on the expected dust concentration increment, and sends it to the process action control unit. Simultaneously, it adjusts the execution intensity of the process actions in conjunction with the activation of ventilation devices in the target ventilation area.

[0011] This invention provides an intelligent monitoring system for dust concentration during feed processing, the system comprising: The data acquisition module is used to acquire dust concentration data from multiple monitoring points in the feed processing area through intelligent dust concentration sensors, and simultaneously acquire corresponding processing parameter data. The correlation analysis module is used to identify the temporal correspondence between the concentration fluctuation time in dust concentration data and the parameter change time in processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between the process action and the concentration fluctuation amplitude, and obtain the process-dust correlation map. The source tracing and positioning module is used to extract the time when the dust concentration rises at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source. The prediction calculation module is used to obtain the corresponding correlation strength and calculate the expected dust concentration increment when it is detected that a process action recorded in the process-dust correlation graph is about to be executed. The collaborative control module is used to determine the ventilation target area based on the location of the dust generation source before the dust concentration data actually increases, determine the ventilation intensity based on the expected dust concentration increase, and start the ventilation device in the ventilation target area, while adjusting the execution intensity of the process actions.

[0012] One technical solution provided in this embodiment of the invention is an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0013] One technical solution provided in this embodiment of the invention is a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the steps in any of the aforementioned methods.

[0014] This invention, through the synchronous acquisition of intelligent dust concentration sensors and processing parameters, can accurately acquire changes in dust concentration in feed processing areas and their correlation with process parameters, improving the real-time performance and accuracy of monitoring. Identifying the temporal relationship between concentration fluctuations and process actions, and statistically analyzing the correlation strength, can effectively determine the source and pattern of dust concentration fluctuations, providing a basis for subsequent pollution control. By tracing the dust propagation direction in reverse, the location of dust generation sources can be accurately pinpointed, thereby achieving precise source control. Based on the process-dust correlation map, the trend of dust concentration changes can be predicted, and ventilation devices can be activated and process intensity adjusted in a timely manner before the dust concentration rises, effectively preventing dust pollution diffusion and improving the safety and environmental protection of the production environment. Attached Figure Description

[0015] Figure 1 A flowchart of an intelligent monitoring method for dust concentration in a feed processing process provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent dust concentration monitoring system for feed processing according to an embodiment of the present invention. Detailed Implementation

[0016] like Figure 1 As shown, Figure 1 A flowchart of an intelligent monitoring method for dust concentration in a feed processing process provided by an embodiment of the present invention, the method comprising the following steps: Step 101: Obtain dust concentration data from multiple monitoring points in the feed processing area using an intelligent dust concentration sensor, and simultaneously collect corresponding processing parameter data.

[0017] Step 102: Identify the temporal correspondence between the concentration fluctuation time in the dust concentration data and the parameter change time in the processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between the process action and the concentration fluctuation amplitude, and obtain the process-dust correlation map.

[0018] In some embodiments of the present invention, step 102 may specifically include the following sub-steps: Sub-step 1021: Extract the concentration fluctuation time from the dust concentration data and the parameter change time from the processing parameter data, calculate the time interval between each concentration fluctuation time and each parameter change time, filter the time intervals where the parameter change time is earlier than the concentration fluctuation time, and establish a time sequence correspondence between the parameter change time corresponding to the filtered time interval and the concentration fluctuation time. Sub-step 1022: Extract the parameter change time from the time sequence correspondence, and determine the process parameter change that occurs at the parameter change time as the process action that causes concentration fluctuation; Sub-step 1023: Extract all concentration fluctuation times corresponding to each process action from the time sequence correspondence, obtain the concentration fluctuation amplitude corresponding to each concentration fluctuation time, accumulate the concentration fluctuation amplitudes corresponding to each process action to obtain the cumulative value of concentration fluctuation amplitude, and calculate the correlation strength between each process action and the concentration fluctuation amplitude based on the cumulative value of concentration fluctuation amplitude. Sub-step 1024: Construct a correlation graph with process actions as nodes, record the correlation strength and cumulative value of concentration fluctuation amplitude corresponding to the process actions in the nodes, and connect the nodes according to the temporal relationship of the concentration fluctuation time in the temporal correspondence to obtain the process-dust correlation graph.

[0019] First, intelligent dust concentration sensors are deployed in the feed processing area, with multiple monitoring points set up at different key locations on the processing line, including the raw material inlet, the vicinity of the crusher, the area near the mixer, and the area around the pellet mill. These sensors collect dust concentration data from each monitoring point in real time, with the data collection frequency set to once per second to ensure that instantaneous concentration changes can be captured. Simultaneously collected processing parameters include equipment on / off status, raw material input rate, crusher speed, mixer stirring speed, and pellet mill pressure, which are also recorded once per second.

[0020] The collected data is analyzed and processed to extract the concentration fluctuation moments from the dust concentration data. The concentration fluctuation moment is defined as the time point when the dust concentration value changes by more than a preset threshold (e.g., 10%) within a short period of time (3 seconds). At the same time, the parameter change moments from the processing parameter data are extracted, that is, the time points when each process parameter changes significantly, such as the time when the equipment changes from a stopped state to a running state, the speed is adjusted, or the pressure value suddenly changes.

[0021] Calculate the time interval between each concentration fluctuation moment and each parameter change moment. Assuming a parameter change occurs at time point t1 and a concentration fluctuation is observed at time point t2, the time interval Δt = t2 - t1 is calculated. Select all time intervals where Δt is greater than 0 and less than the preset maximum response time (e.g., 30 seconds). This means retaining data pairs where the parameter change moment precedes the concentration fluctuation moment and the time interval is within a reasonable range. These data pairs constitute the temporal correspondence between parameter changes and concentration fluctuations.

[0022] The parameter change moments are extracted from the established time-series correspondence, and the process parameter changes occurring at these moments are identified as the process actions that cause concentration fluctuations. For example, if the pulverizer speed increases from 1200 rpm to 1500 rpm at a certain moment, and a subsequent increase in dust concentration is observed, then "increased pulverizer speed" is identified as a process action. Similarly, multiple process actions such as "opening of the raw material feeding door," "starting of the mixer," and "increased pressure in the granulator" can be identified.

[0023] For each identified process action, extract all corresponding concentration fluctuation moments from the time-series correspondence, and obtain the concentration fluctuation amplitude corresponding to these concentration fluctuation moments. The concentration fluctuation amplitude is calculated as the difference or percentage change in concentration value before and after the fluctuation. Accumulate all concentration fluctuation amplitudes caused by the same process action to obtain the cumulative concentration fluctuation amplitude corresponding to that process action.

[0024] The correlation strength between each process action and the concentration fluctuation amplitude is calculated based on the cumulative value of the concentration fluctuation amplitude. This correlation strength can be obtained by dividing the cumulative value of the concentration fluctuation amplitude by the total number of times the process action occurs, i.e., the average concentration fluctuation amplitude caused by each process action. Alternatively, it can be obtained by dividing the cumulative value of the concentration fluctuation amplitude by the total observation time, representing the average concentration fluctuation contribution caused by the process action per unit time.

[0025] A process-dust correlation graph is constructed with process actions as nodes. Each node represents a process action, and its size indicates the correlation strength. Nodes record detailed information about the process action, its correlation strength value, and the cumulative concentration fluctuation amplitude. Nodes are connected by directed edges based on the chronological order of concentration fluctuations. If a concentration fluctuation caused by process action A is immediately followed by a concentration fluctuation caused by process action B, a connection is established from node A to node B. This process-dust correlation graph visually demonstrates the impact of each process action on dust concentration and their temporal relationships.

[0026] The correlation map can be further refined by using different colors to distinguish different types of process actions. The thickness of the connection between nodes can indicate the frequency of two process actions occurring consecutively. The thicker the connection, the more frequently the two process actions occur consecutively.

[0027] This invention enables precise identification and quantitative analysis of the relationship between dust concentration changes and process parameters during feed processing, clarifying the contribution and temporal correlation of different process actions to dust generation. This method does not rely on complex physical models but is based on correlation analysis using measured data, exhibiting strong adaptability and practicality. Through the process-dust correlation graph, production managers can intuitively understand the main sources and propagation paths of dust generation, providing a scientific basis for developing targeted dust control measures, thereby achieving accurate prediction and effective control of dust concentration.

[0028] Step 103: Extract the time of dust concentration rise at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source.

[0029] In some embodiments of the present invention, step 103 may specifically include the following sub-steps: Sub-step 1031: Extract the dust concentration rise time of each monitoring point, sort the monitoring points from morning to night according to the dust concentration rise time, and obtain the dust arrival sequence. Sub-step 1032: Extract the dust concentration rise time of adjacent monitoring points from the dust arrival sequence, calculate the time difference of dust concentration rise time between adjacent monitoring points, and obtain the time difference sequence. Sub-step 1033: Obtain the spatial coordinates of each monitoring point in the dust arrival sequence, calculate the spatial distance between adjacent monitoring points, and calculate the propagation speed and direction of dust between adjacent monitoring points based on the time difference sequence and spatial distance to obtain the propagation speed vector sequence; Sub-step 1034: Weighted synthesis of each propagation velocity vector in the propagation velocity vector sequence to obtain the main propagation direction of dust; Sub-step 1035: Extend the tracing path outward from the earliest arrival monitoring point in the dust arrival sequence in the opposite direction of the main dust propagation direction, and determine the intersection of the tracing path and the boundary of the feed processing area as the dust generation source location.

[0030] Extracting the moment when dust concentration rises at each monitoring point requires analyzing and processing the dust concentration data. The continuously collected dust concentration data is arranged in a time series, and the concentration rise phase is determined by calculating the concentration difference between adjacent time points. When the concentration difference between three consecutive time points exceeds a preset threshold, it is determined that the dust concentration has begun to rise, and this moment is recorded as the dust concentration rise moment for that monitoring point. Multiple monitoring points deployed in the feed processing workshop will detect dust concentration rises at different times. Based on the recorded rise moments, these monitoring points are sorted according to the order in which the dust arrived, forming a dust arrival sequence.

[0031] When extracting the dust concentration rise times of adjacent monitoring points from the dust arrival sequence, two adjacent monitoring points in the sequence are considered as a pair, and the difference in dust concentration rise times between them is calculated. For example, assuming the dust concentration rise times of monitoring points A, B, and C are 10:15:20, 10:15:45, and 10:16:10 respectively, then the time difference between A and B is 25 seconds, and the time difference between B and C is also 25 seconds, thus obtaining the time difference sequence.

[0032] The spatial coordinates of each monitoring point in the dust arrival sequence are obtained through pre-defined monitoring point location information. Each monitoring point has clear three-dimensional coordinates within the feed processing area, which can be used to calculate the spatial distance between monitoring points. With the coordinates of monitoring point A as (2.5, 3.0, 1.8) and monitoring point B as (5.5, 3.5, 1.8), the spatial distance between the two points can be calculated as a straight-line distance. Based on the time difference and spatial distance, the propagation speed of dust between adjacent monitoring points is calculated, and the propagation direction is the direction from the earlier-arriving monitoring point to the later-arriving monitoring point. The propagation speed between A and B is the distance between the two points divided by the time difference, and the propagation direction is a vector from A to B. The propagation speed and propagation direction of all adjacent monitoring point pairs in the sequence are calculated sequentially to form a propagation speed vector sequence.

[0033] When weighting and synthesizing the propagation velocity vectors in the propagation velocity vector sequence, a weighting method based on the reliability of monitoring points is adopted, taking into account the importance of different monitoring point locations and the differences in measurement reliability. The reliability of monitoring points can be comprehensively evaluated by factors such as the accuracy of historical data and equipment status. Each propagation velocity vector is multiplied by its corresponding weighting coefficient and then synthesized to obtain a comprehensive vector representing the main dust propagation direction. In a dust monitoring exercise conducted in a processing workshop, the weighted synthesis of the propagation velocity vectors determined that the dust primarily propagated in a northwest direction.

[0034] When extending the tracing path outward from the earliest monitoring point in the dust arrival sequence in the opposite direction of the main dust propagation direction, the starting point is the monitoring point where the dust concentration increase was first detected, and the path is extended in a straight line in the reverse direction of the calculated main propagation direction. During the extension process, the internal layout of the workshop needs to be considered to avoid areas where dust sources are unlikely to exist. When the tracing path intersects with the boundary of the feed processing area, this intersection point is the potential dust source location. If the tracing path intersects with multiple boundary points, the intersection point closest to the earliest detection point is selected as the final dust source location. For example, if the tracing path intersects with the boundary of a crushing equipment in the southeast corner of the processing area, this location is determined to be the source of this dust event.

[0035] Once the dust source is located, the specific causes of dust generation can be further analyzed by combining the equipment distribution diagram and work logs, such as poor equipment sealing or improper operation, to provide targeted guidance for subsequent dust prevention measures.

[0036] This invention achieves rapid and accurate location of dust sources through precise monitoring and spatiotemporal analysis of dust concentration changes. Compared with traditional methods relying on manual inspections, the location accuracy is significantly improved, the location time is greatly shortened, and the risk of workers being exposed to high-concentration dust environments is reduced. Precise dust source location also provides technical support for feed processing enterprises to implement targeted dust control measures, effectively reducing the frequency and severity of dust pollution incidents and improving the safety and health level of the production environment.

[0037] In sub-step 1033, the spatial coordinates of each monitoring point in the dust arrival sequence are obtained, the spatial distance between adjacent monitoring points is calculated, and the propagation speed and direction of dust between adjacent monitoring points are calculated based on the time difference sequence and spatial distance to obtain the propagation speed vector sequence. This also includes: The spatial coordinates of adjacent monitoring points are obtained from the dust arrival sequence, a spatial line is established between adjacent monitoring points, the length of the spatial line is measured to obtain the spatial distance, and the deflection angle of the spatial line relative to the reference coordinate axis is measured to obtain the spatial azimuth. Extract the time difference values ​​corresponding to adjacent monitoring points from the time difference sequence, determine the dust propagation speed based on the spatial distance and time difference values, determine the dust propagation direction angle based on the spatial azimuth angle, and construct a two-dimensional propagation speed vector by combining the propagation speed magnitude and propagation direction angle. The two-dimensional propagation velocity vectors corresponding to each adjacent monitoring point are standardized, and the standardized propagation velocity vectors are arranged and combined according to the temporal relationship of the dust arrival sequence to obtain the propagation velocity vector sequence.

[0038] The spatial coordinates of adjacent monitoring points are obtained from the dust arrival sequence. The spatial position of each monitoring point is stored in the system in three-dimensional coordinates, including east-west coordinates, north-south coordinates, and altitude coordinates. Assume two adjacent monitoring points A and B in the dust arrival sequence, and their spatial coordinates are known. Establish a spatial line connecting these two adjacent monitoring points; this line represents the path of dust propagation from monitoring point A to monitoring point B.

[0039] Spatial distance calculation employs a three-dimensional method for calculating the distance between two points. The coordinates of the two points are substituted into the distance formula to calculate the actual spatial path of dust propagation between the two monitoring points. Taking two adjacent monitoring points in a feed processing workshop as an example, if monitoring point A is located in the raw material unloading area with coordinates of 5 meters, 8 meters, and 2.5 meters, and monitoring point B is located in the crushing area with coordinates of 12 meters, 10 meters, and 2.8 meters, the calculated spatial distance between the two points is approximately 7.3 meters.

[0040] The spatial azimuth is obtained by measuring the deflection angle of the spatial line relative to the reference coordinate axis. In the horizontal plane, the azimuth is calculated as the angle between the projection of the line onto the horizontal plane and the due east direction. For the two points mentioned above, the angle between the projection of the line onto the horizontal plane and the due east direction is approximately 16.7 degrees. In the vertical direction, the elevation angle is calculated as the angle between the line and the horizontal plane. For the two points mentioned above, the angle between the line and the horizontal plane is approximately 2.4 degrees. The spatial azimuth is determined by both the azimuth and elevation angles, thus fully describing the three-dimensional orientation of the spatial line.

[0041] Extract the time difference values ​​corresponding to adjacent monitoring points from the time difference sequence, which represents the time required for dust to propagate from monitoring point A to monitoring point B. If the dust concentration rises at monitoring point A at 10:15:30 and at monitoring point B at 10:15:37, the time difference is 7 seconds. Based on the spatial distance of 7.3 meters and the time difference of 7 seconds, the dust propagation speed is calculated to be 1.04 m / s.

[0042] Considering that dust primarily propagates in the horizontal plane in practical applications, the three-dimensional problem can be simplified into a two-dimensional problem, focusing mainly on the horizontal azimuth angle. A two-dimensional propagation velocity vector is constructed by combining the propagation velocity magnitude of 1.04 m / s with the propagation direction angle of 16.7 degrees. This vector can be decomposed into east-west and north-south components. In the example above, the east-west component is 1.0 m / s, and the north-south component is 0.3 m / s.

[0043] The two-dimensional propagation velocity vectors corresponding to each adjacent monitoring point are standardized. Standardization aims to eliminate the impact of distance differences between monitoring points on subsequent analysis and ensure consistent weights for each propagation direction. In the example above, the standardized propagation velocity vector has an east-west component of 0.96 and a north-south component of 0.28. Standardization ensures consistent representation across propagation directions, facilitating subsequent composite analysis.

[0044] The standardized propagation velocity vectors are arranged according to the temporal relationship of the dust arrival sequence to obtain a propagation velocity vector sequence. If the dust arrival sequence is monitoring points A, B, C, and D, then the propagation velocity vector sequence includes three vectors: A to B, B to C, and C to D. These vectors sequentially describe the changes in the speed and direction of dust propagation. In practical applications, the quality of dust concentration data collected at each monitoring point can be assessed, and the propagation velocity vectors corresponding to monitoring points with higher data quality can be given greater weight.

[0045] If the time difference between certain monitoring points is too small, such as less than the system's time resolution, or the spatial distance is too large, resulting in an unreasonable calculated propagation speed, these abnormal data can be filtered or corrected. For example, when the calculated propagation speed exceeds 10 m / s, considering the normal diffusion speed of dust in the air, there may be measurement errors. This speed can be set to a reasonable upper limit or its weight can be reduced in subsequent analyses.

[0046] By utilizing propagation velocity vector sequences, the propagation path and directional trend of dust throughout the entire feed processing area can be visually presented. Through visualization, staff can quickly understand the dynamic process of dust propagation, providing an intuitive basis for the accurate tracing of dust source locations.

[0047] This invention achieves effective tracking of dust propagation paths by precisely characterizing the speed and direction of dust transmission, providing a scientific basis for locating dust sources. Compared with traditional dust monitoring methods, this method utilizes spatiotemporal data fusion analysis, significantly improving the accuracy and response speed of dust source location. By accurately grasping the laws of dust propagation, it can guide feed processing enterprises to optimize dust control measures, make targeted improvements to process flows and equipment design, reduce dust generation at the source, and improve the safety of the production environment and the health of employees.

[0048] Step 104: When it is detected that a process action recorded in the process-dust correlation graph is about to be executed, obtain the corresponding correlation strength and calculate the expected dust concentration increment.

[0049] In some embodiments of the present invention, step 104 may specifically include the following sub-steps: Sub-step 1041: Real-time monitoring of the execution status of process actions in the feed processing area, identification of process actions switching from standby to start state, extraction of action identifiers of process actions, and querying of correlation strength from the process-dust correlation graph based on the action identifiers; Sub-step 1042: Obtain the historical dust concentration change curve based on the action identifier, extract the concentration peak value and the concentration reference value from the historical dust concentration change curve, calculate the difference between the concentration peak value and the concentration reference value, and obtain the historical dust concentration increment. Sub-step 1043: Obtain the current ventilation system air volume value at the start time of the process action, determine the dust dilution capacity based on the current ventilation system air volume value, and perform correlation calculation between the historical dust concentration increment and the dust dilution capacity to obtain the environmentally corrected concentration increment. Sub-step 1044: The correlation strength is used as a weight to weight the concentration increment after environmental correction, so as to obtain the expected dust concentration increment.

[0050] The system monitors the execution status of process actions within the feed processing area in real time, collecting operational status signals from each processing device using an equipment operation parameter acquisition module. Feed processing equipment typically includes grinders, mixers, and pellet mills. The start-up and shutdown status of these devices can be determined using current signals, speed signals, and vibration signals. A status judgment threshold is set; when a signal value changes from below the threshold to above the threshold, it is identified as a process action switching from standby to start-up. For grinders, the motor current value can be monitored; when the current value increases from 2A to 10A, the grinder is considered to have started. For mixers, the stirring shaft speed can be monitored; when the speed increases from 0 r / min to 60 r / min, the mixer is considered to have started.

[0051] After a process action is initiated, its action identifier is extracted. This action identifier is a unique code for the process action, composed of a combination of an equipment type code and an action type code. The equipment type code corresponds to different processing equipment; for example, a crusher corresponds to code "CR", a mixer to code "MX", and a granulator to code "PL". The action type code corresponds to different operations of the equipment; for example, starting corresponds to code "01", stopping corresponds to code "02", and feeding corresponds to code "03". A complete action identifier is formed by connecting the equipment type code and the action type code; for example, the action identifier for starting a crusher is "CR01".

[0052] Based on the extracted action identifiers, the correlation strength is queried from the process-dust correlation graph. The process-dust correlation graph is a data structure that stores the relationship between process actions and dust generation, recording the degree of influence of each process action on dust concentration. The correlation strength is a value between 0 and 1, representing the correlation between the process action and dust generation; the higher the value, the stronger the correlation. For typical process actions in feed processing, the correlation strength for crusher startup is 0.85, for mixer startup it is 0.6, for pellet mill startup it is 0.7, and for raw material unloading it is 0.9.

[0053] Historical dust concentration variation curves are obtained based on the action identifier. These curves record historical data on dust concentration changes over time during the execution of the same process action. Historical records matching the current process action identifier are retrieved from the database, yielding the dust concentration variation curves for the last 10 executions of this process action. Peak and baseline concentration values ​​are extracted from these historical curves. The peak concentration is the highest dust concentration reached after the process action, while the baseline concentration is the ambient dust concentration before the process action. The difference between the peak and baseline concentration values ​​for each curve is calculated to obtain the historical dust concentration increment. For the pulverizer start-up action, the possible historical increment is 3.5 mg / m³. 3 4.2 mg / m 3 3.8 mg / m 3 The average value was 4.0 mg / m². 3 As a historical increase in dust concentration.

[0054] The current ventilation system airflow value is obtained at the moment the process starts. Ventilation system airflow is a crucial factor affecting dust diffusion and settling. The actual airflow is calculated by real-time monitoring of the outlet velocity of the ventilation equipment using airflow sensors and combining this with the duct cross-sectional area. The dust dilution capacity is determined based on the current ventilation system airflow value. Dust dilution capacity is directly proportional to the ventilation system airflow; the larger the airflow, the stronger the dilution capacity. The dilution capacity under a standard airflow is set to 1; the ratio of the current airflow to the standard airflow is the current dilution capacity coefficient. If the standard airflow is 10000 m³ / s... 3 / h, current air volume is 12000m³ / h 3 If / h, then the current dilution capacity coefficient is 1.2.

[0055] The historical dust concentration increment is correlated with the dust dilution capacity to obtain the environmentally corrected concentration increment, which is calculated as: historical dust concentration increment / current dilution capacity coefficient. If the historical dust concentration increment is 4.0 mg / m³... 3 Given a current dilution capacity factor of 1.2, the environmentally corrected concentration increment is 4.0 / 1.2 = 3.33 mg / m³. 3 .

[0056] The correlation strength is used as a weight to weight the environmentally corrected concentration increment, resulting in the expected dust concentration increment: Expected dust concentration increment = Environmentally corrected concentration increment × Correlation strength. If the environmentally corrected concentration increment is 3.33 mg / m³... 3 If the correlation strength is 0.85, then the expected increase in dust concentration is 3.33 × 0.85 = 2.83 mg / m³. 3The expected dust concentration increment is a prediction of the possible change in dust concentration after the execution of a process action. It can be used for early warning and triggering control measures. The expected dust concentration increment can be compared with a preset warning threshold. When the expected increment exceeds the warning threshold, a warning signal is triggered to remind operators to take appropriate protective measures.

[0057] This invention, through its method for calculating expected dust concentration increments, enables accurate prediction of dust concentration changes during feed processing, providing forward-looking technical support for dust concentration control. By analyzing the correlation between process actions and dust generation, and combining historical data with corrective calculations based on environmental conditions, it overcomes the shortcomings of traditional monitoring methods that suffer from delayed responses, improving the real-time nature and predictability of dust concentration monitoring. This provides feed processing enterprises with an effective tool for implementing proactive dust control, significantly enhancing the safety and health protection level of the production environment.

[0058] Step 105: Before the dust concentration data actually increases, determine the ventilation target area based on the location of the dust generation source, determine the ventilation intensity based on the expected dust concentration increase, and start the ventilation device in the ventilation target area. At the same time, adjust the execution intensity of the process actions.

[0059] In some embodiments of the present invention, step 105 may specifically include the following sub-steps: Sub-step 1051: Obtain the location of the dust source, retrieve the historical dust diffusion trajectory data corresponding to the location of the dust source, extract the spatial area where the dust concentration exceeds the concentration threshold from the historical dust diffusion trajectory data, identify the ventilation device markers deployed in the spatial area, and determine the area corresponding to the ventilation device markers as the ventilation target area based on the location of the dust source. Sub-step 1052: Obtain the airflow adjustment level information of the ventilation device according to the ventilation device identifier, obtain the expected dust concentration increment value, match the corresponding level in the airflow adjustment level information according to the expected dust concentration increment value to determine the ventilation intensity and generate a level switching command, send the level switching command to the ventilation device corresponding to the ventilation device identifier and start the ventilation device in the ventilation target area. Sub-step 1053: Obtain the historical execution records of the process actions, extract the correspondence between the execution parameters and the amount of dust generated from the historical execution records, find the upper limit value of the execution parameters that meet the conditions from the correspondence based on the expected dust concentration increment value, and send it to the process action control unit, and adjust the execution intensity of the process action at the same time as starting the ventilation device in the ventilation target area.

[0060] The location of dust sources is determined using the aforementioned dust propagation direction tracing method, accurate to three-dimensional spatial coordinates. For typical dust sources in feed processing, such as the feed inlet of a crusher, the coordinates might be (15m, 8m, 2.5m). Based on this coordinate information, historical dust diffusion trajectory data corresponding to that location is retrieved from the database. This historical dust diffusion trajectory data records the process of dust spreading from the source location to the surrounding space, including timestamps, spatial locations, and corresponding dust concentration values.

[0061] Extract spatial regions where dust concentration exceeds a threshold from historical dust dispersion trajectory data, and set the dust concentration threshold at 8 mg / m³. 3 The system filters out all historical data points with concentration values ​​greater than or equal to a threshold. These data points are then visualized in three-dimensional space to form high-concentration dust distribution areas. Using spatial clustering methods, adjacent high-concentration data points are merged to obtain several consecutive high-risk spatial regions. These spatial regions represent locations where dust may reach high concentrations after diffusing from its source.

[0062] Multiple ventilation devices are typically installed within the feed processing area, each with a unique identification code consisting of the installation location area code and the equipment serial number. For example, the fan installed on the first piece of equipment in the grinding area has the identification code "CR-F01"; the fan installed on the third piece of equipment in the pelleting area has the identification code "PL-F03". Spatial coordinate matching is used to determine which ventilation devices are located in or near high-risk areas. If the distance between the installation coordinates of a ventilation device and a high-risk area is less than a set threshold (e.g., 3m), that ventilation device is added to the candidate list.

[0063] Based on the location of the dust source and the spatial relationship between the candidate ventilation devices and the source, the final ventilation target area is determined. The straight-line distance from each candidate ventilation device to the dust source is calculated, taking into account the coverage and ventilation efficiency of the devices. Ventilation devices with a moderate distance (neither too far nor too close) and whose coverage includes high-risk areas are given priority. For example, for a dust source such as the feed inlet of a crusher, the area covered by two ventilation devices with identification codes "CR-F01" and "CR-F02" might be identified as the ventilation target area.

[0064] Obtain the airflow adjustment level information of the ventilation device based on its label. This information includes the adjustment level, corresponding airflow, and applicable dust concentration range. For example, a ventilation device may have four settings: Level 1 has an airflow of 1000 m³ / h. 3 / h, applicable when the expected dust concentration increase is less than 2mg / m³ 3 The second fan speed is 2000m³ / h. 3 / h, applicable when the expected dust concentration increase is 2-5mg / m³3 The situation is as follows: the third fan speed is 3000m³ / h. 3 / h, applicable when the expected dust concentration increase is 5-8 mg / m³ 3 The situation is as follows: the fourth fan speed is 4000m³ / h. 3 / h, applicable when the expected dust concentration increase is greater than 8mg / m³ 3 The situation.

[0065] Obtain the expected dust concentration increment value, which has already been calculated in the aforementioned dust concentration increment prediction step. Match the expected dust concentration increment value with the applicable dust concentration range in the ventilation device's setting information to determine the required ventilation intensity. If the expected dust concentration increment is 6.5 mg / m³... 3 Then it will be matched to the third speed, with an air volume of 3000m³ / h. 3 / h. Based on this, a gear shifting command is generated, which includes the ventilation device identifier, the target gear level, and the execution time. The gear shifting command is sent to the corresponding ventilation device controller via the communication network. After receiving the command, the controller performs the gear adjustment and starts the ventilation device.

[0066] Obtain historical execution records of process actions and extract the correspondence between execution parameters and dust generation. Execution parameters include equipment operating speed, material processing volume, and equipment load, and these parameters have a quantitative relationship with dust generation. Establish a mapping table between execution parameters and dust generation, such as the relationship between crusher speed and dust generation: at a speed of 900 r / min, the dust generation is 10 mg / m³. 3 At a rotation speed of 750 r / min, the dust generation is 7 mg / m³. 3 At a rotation speed of 600 r / min, the dust generation is 5 mg / m³. 3 .

[0067] Based on the expected increase in dust concentration, find the upper limit value of the execution parameter that meets the conditions from the correspondence between the execution parameters and the amount of dust generated. If the expected increase in dust concentration is 6.5 mg / m³, then... 3 By consulting tables or interpolating, the upper limit of the corresponding crusher speed is determined to be 720 r / min. This upper limit of the execution parameter is then sent to the process control unit. After receiving the upper limit, the control unit adjusts the equipment's operating parameters to ensure that the actual operating parameters do not exceed the set upper limit. This is synchronized with the activation of ventilation devices in the target ventilation area, achieving dual control of enhanced ventilation and reduced dust source.

[0068] This invention employs pre-emptive dust control technology to intervene in dust concentration during feed processing. By precisely locating dust sources, rationally allocating ventilation resources, and optimizing process parameters, a complete intelligent dust concentration control system is constructed. This technology breaks away from the traditional passive response mode, moving dust control forward to before dust is actually generated and dispersed, effectively preventing dust concentration from exceeding standards, significantly improving air quality in the feed processing environment, reducing dust exposure risks for operators, and enhancing the safety and health protection level of the production process.

[0069] like Figure 2 As shown, Figure 2 This is a schematic diagram of a smart dust concentration monitoring system for feed processing provided in an embodiment of the present invention. The system includes: Data acquisition module 201 is used to acquire dust concentration data from multiple monitoring points in the feed processing area through an intelligent dust concentration sensor, and simultaneously acquire corresponding processing parameter data. The correlation analysis module 202 is used to identify the temporal correspondence between the concentration fluctuation time in the dust concentration data and the parameter change time in the processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between the process action and the concentration fluctuation amplitude, and obtain the process-dust correlation map. The source tracing and positioning module 203 is used to extract the time when the dust concentration rises at each monitoring point, calculate the time difference between the times when the dust concentration rises at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source. The prediction calculation module 204 is used to obtain the corresponding correlation strength and calculate the expected dust concentration increment when it is detected that a process action recorded in the process-dust correlation map is about to be executed. The collaborative control module 205 is used to determine the ventilation target area based on the location of the dust generation source before the dust concentration data actually increases, determine the ventilation intensity based on the expected dust concentration increase, and start the ventilation device in the ventilation target area, while adjusting the execution intensity of the process actions.

[0070] One technical solution provided in this embodiment of the invention is an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0071] One technical solution provided in this embodiment of the invention is a computer-readable storage medium storing a computer program, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0072] The specific embodiments described above are preferred embodiments of the present invention and are not intended to limit the specific scope of the present invention. The scope of the present invention includes, but is not limited to, these specific embodiments. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of dust concentration in feed processing, characterized in that, Includes the following steps: Dust concentration data from multiple monitoring points in the feed processing area are obtained through intelligent dust concentration sensors, and corresponding processing parameter data are collected simultaneously. Identify the temporal correspondence between the time of concentration fluctuation in dust concentration data and the time of parameter change in processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between process action and concentration fluctuation amplitude, and obtain the process-dust correlation map. Extract the time of dust concentration rise at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source. When it is detected that a process action recorded in the process-dust correlation graph is about to be executed, the corresponding correlation strength is obtained and the expected dust concentration increment is calculated. Before the dust concentration data actually increases, the ventilation target area is determined based on the location of the dust generation source, the ventilation intensity is determined based on the expected increase in dust concentration, and the ventilation device in the ventilation target area is activated. At the same time, the execution intensity of the process actions is adjusted.

2. The method according to claim 1, characterized in that, Identify the temporal correspondence between the times of dust concentration fluctuations in the data and the times of parameter changes in the process parameter data, determine the process actions that cause the concentration fluctuations, statistically analyze the correlation strength between the process actions and the amplitude of concentration fluctuations, and obtain the process-dust correlation map, including: Extract the concentration fluctuation time from the dust concentration data and the parameter change time from the processing parameter data, calculate the time interval between each concentration fluctuation time and each parameter change time, filter the time intervals where the parameter change time is earlier than the concentration fluctuation time, and establish a time-series correspondence between the parameter change time and the concentration fluctuation time corresponding to the filtered time intervals. Extract the time of parameter change from the time-series correspondence, and determine the process parameter changes that occur at the time of parameter change as the process actions that cause concentration fluctuations; Extract all concentration fluctuation moments corresponding to each process action from the time sequence correspondence, obtain the concentration fluctuation amplitude corresponding to each concentration fluctuation moment, accumulate the concentration fluctuation amplitude corresponding to each process action to obtain the cumulative value of concentration fluctuation amplitude, and calculate the correlation strength between each process action and the concentration fluctuation amplitude based on the cumulative value of concentration fluctuation amplitude. A correlation graph with process actions as nodes is constructed. The correlation strength and cumulative value of concentration fluctuation amplitude corresponding to the process actions are recorded in the nodes. The nodes are connected according to the temporal relationship of the concentration fluctuation time in the temporal correspondence to obtain the process-dust correlation graph.

3. The method according to claim 1, characterized in that, Extract the time of dust concentration rise at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction backwards based on the time difference and the spatial location of each monitoring point to obtain the location of the dust generation source, including: Extract the time of dust concentration rise at each monitoring point, sort the monitoring points from morning to night according to the time of dust concentration rise, and obtain the dust arrival sequence. Extract the dust concentration rise time of adjacent monitoring points from the dust arrival sequence, calculate the time difference of the dust concentration rise time between adjacent monitoring points, and obtain the time difference sequence; Obtain the spatial coordinates of each monitoring point in the dust arrival sequence, calculate the spatial distance between adjacent monitoring points, and calculate the propagation speed and direction of dust between adjacent monitoring points based on the time difference sequence and spatial distance to obtain the propagation speed vector sequence. The main propagation direction of dust is obtained by weighted synthesis of the propagation velocity vectors in the propagation velocity vector sequence. The dust source location is determined by extending the tracing path outward from the earliest monitoring point in the dust arrival sequence in the opposite direction of the main dust propagation direction, and determining the intersection of the tracing path and the boundary of the feed processing area.

4. The method according to claim 3, characterized in that, Obtain the spatial coordinates of each monitoring point in the dust arrival sequence, calculate the spatial distance between adjacent monitoring points, and calculate the propagation speed and direction of dust between adjacent monitoring points based on the time difference sequence and spatial distance. The resulting propagation speed vector sequence includes: The spatial coordinates of adjacent monitoring points are obtained from the dust arrival sequence, a spatial line is established between adjacent monitoring points, the length of the spatial line is measured to obtain the spatial distance, and the deflection angle of the spatial line relative to the reference coordinate axis is measured to obtain the spatial azimuth. Extract the time difference values ​​corresponding to adjacent monitoring points from the time difference sequence, determine the dust propagation speed based on the spatial distance and time difference values, determine the dust propagation direction angle based on the spatial azimuth angle, and construct a two-dimensional propagation speed vector by combining the propagation speed magnitude and propagation direction angle. The two-dimensional propagation velocity vectors corresponding to each adjacent monitoring point are standardized, and the standardized propagation velocity vectors are arranged and combined according to the temporal relationship of the dust arrival sequence to obtain the propagation velocity vector sequence.

5. The method according to claim 1, characterized in that, When a process action recorded in the process-dust correlation graph is about to be executed, the corresponding correlation strength is obtained, and the expected dust concentration increment is calculated, including: Real-time monitoring of the execution status of process actions within the feed processing area; identification of process actions switching from standby to start-up state; extraction of action identifiers for process actions; and querying the correlation strength from the process-dust correlation graph based on the action identifiers. The historical dust concentration change curve is obtained based on the action identifier. The concentration peak value and the concentration baseline value are extracted from the historical dust concentration change curve. The difference between the concentration peak value and the concentration baseline value is calculated to obtain the historical dust concentration increment. Obtain the current ventilation system air volume value at the start of the process action, determine the dust dilution capacity based on the current ventilation system air volume value, and calculate the correlation between the historical dust concentration increment and the dust dilution capacity to obtain the environmentally corrected concentration increment. The correlation strength is used as a weight to weight the concentration increment after environmental correction, so as to obtain the expected dust concentration increment.

6. The method according to claim 1, characterized in that, Before the dust concentration actually increases, the target ventilation area is determined based on the location of the dust source. The ventilation intensity is determined based on the expected increase in dust concentration, and the ventilation devices in the target area are activated. At the same time, the execution intensity of process actions is adjusted, including: Obtain the location of the dust source, retrieve the historical dust diffusion trajectory data corresponding to the location of the dust source, extract the spatial area where the dust concentration exceeds the concentration threshold from the historical dust diffusion trajectory data, identify the ventilation device markings deployed in the spatial area, and determine the area corresponding to the ventilation device markings as the ventilation target area based on the location of the dust source. According to the ventilation device identification, obtain the air volume adjustment level information of the ventilation device, obtain the expected dust concentration increment value, match the corresponding level in the air volume adjustment level information according to the expected dust concentration increment value to determine the ventilation intensity and generate a level switching command, send the level switching command to the ventilation device corresponding to the ventilation device identification and start the ventilation device in the ventilation target area. The system acquires historical execution records of process actions, extracts the correspondence between execution parameters and dust generation from these records, finds the upper limit of execution parameters that meet the conditions based on the expected dust concentration increment, and sends it to the process action control unit. Simultaneously, it adjusts the execution intensity of the process actions in conjunction with the activation of ventilation devices in the target ventilation area.

7. An intelligent monitoring system for dust concentration in feed processing, used to implement the method described in any one of claims 1-6, characterized in that, The system includes: The data acquisition module is used to acquire dust concentration data from multiple monitoring points in the feed processing area through intelligent dust concentration sensors, and simultaneously acquire corresponding processing parameter data. The correlation analysis module is used to identify the temporal correspondence between the concentration fluctuation time in dust concentration data and the parameter change time in processing parameter data, determine the process action that causes the concentration fluctuation, statistically analyze the correlation strength between the process action and the concentration fluctuation amplitude, and obtain the process-dust correlation map. The source tracing and positioning module is used to extract the time when the dust concentration rises at each monitoring point, calculate the time difference between the dust concentration rise times at each monitoring point, and trace the dust propagation direction in reverse based on the time difference and the spatial location of each monitoring point to obtain the location of the dust source. The prediction calculation module is used to obtain the corresponding correlation strength and calculate the expected dust concentration increment when it is detected that a process action recorded in the process-dust correlation graph is about to be executed. The collaborative control module is used to determine the ventilation target area based on the location of the dust generation source before the dust concentration data actually increases, determine the ventilation intensity based on the expected dust concentration increase, and start the ventilation device in the ventilation target area, while adjusting the execution intensity of the process actions.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 6.

Images