Dust removal control method, system and equipment and storage medium

Abstract

The invention relates to the technical field of industrial dust removal, and discloses a dust removal control method, system and equipment and a storage medium. The method comprises the following steps: using a first model to identify the operation category of the dust removal equipment, adjusting the monitoring strategy of the dust removal equipment based on the operation category, collecting the dust concentration of a primary production area, transmitting the collected dust concentration to a remote control unit through a plurality of intermediate nodes, and controlling the remote control unit based on the dust concentration monitored in real time. Comparing the change of the dust concentration before and after the operation of the dust removal equipment, calculating the dust removal effect, adjusting the dust removal intensity based on the dust removal effect, generating a second model corresponding to each data value in the operation data, obtaining the prediction data of each data value in the operation data by using the second model, calculating the difference value between the prediction data and the actual data value, and calculating the dust removal effect. And calculating the sum of difference values of all the data values, and judging whether fault early warning needs to be sent out based on the sum of difference values. The dust removal intensity of the dust removal equipment can be automatically adjusted, and the efficient dust removal effect is achieved.

Description

Technical Field

[0001] This application relates to the technical field of industrial dust removal, and particularly to a dust removal control method, system, device, and storage medium. Background Art

[0002] During industrial production processes, especially in fields such as flux production, welding workshops, and metal processing, a large amount of dust and smoke are generated. These dusts not only pollute the working environment but may also pose hazards to human health. Traditional dust removal equipment usually adopts manual control or simple timing control methods, and cannot accurately adjust according to the actual dust concentration and production conditions, resulting in unstable dust removal effects, serious energy waste, and relatively high equipment maintenance costs.

[0003] A similar prior art Chinese patent application with the publication number CN109507929A provides a dust removal control method, including: based on the dust generation situation in different areas of conveying devices such as conveyor belts, through the signals detected by sensors, and performing separate control according to different flow rates. When the flow rate is large, the amount of dust generated is greater than that when the flow rate is small. When there is no material passing through, no dust is generated. Through the data signals detected by sensors, by comparing with the basic data stored in the learning process by the controller, different situations are separately controlled. However, this dust removal control is mainly based on a simple comparison of the material flow rate and the amount of dust generated, and realizes control by adjusting the current of the vacuum dust collector and the opening degree of the dust suction port. This control mode is relatively single and cannot be finely adjusted according to different working conditions.

[0004] Another similar prior art is the Chinese patent application with the publication number CN113777972A, which provides a preform dust removal control method and a bottle production system, including obtaining the preform signal; obtaining the movement information of the preform; determining the initial preform position information based on the preform signal and the movement information; determining whether the initial preform is in a preset starting position based on the initial preform position information, where the distance between the preset starting position and the feeding station is less than the distance between the preform station and the feeding station; if so, controlling the dust removal mechanism to start. However, the control strategy of this method mainly starts and stops the dust removal mechanism based on the position information of the preform, and the control method is relatively simple and cannot be dynamically optimized according to the actual working conditions.

[0005] Therefore, the present invention provides a dust removal control method, system, device, and storage medium. Summary of the Invention

[0006] This application provides a dust removal control method, system, device, and storage medium, which are used to automatically adjust the operating parameters of dust removal equipment to achieve efficient and energy-saving dust removal effects.

[0007] In a first aspect, the present application provides a dust removal control method, the method comprising: Step S1: Divide the operating states of the dust removal equipment into multiple operating categories, set different monitoring strategies for each operating category, train a first model based on the operating data of the dust removal equipment and the corresponding operating category to identify the operating state of the dust removal equipment. After the dust removal equipment is turned on, use the first model to identify the operating category of the dust removal equipment, and adjust the monitoring strategy of the dust removal equipment based on the operating category; Step S2: Install dust removal equipment and high-precision sensors in the production area, set a fixed first time interval for the high-precision sensors, collect the dust concentration in the production area every first time interval, and transmit the collected dust concentration to the remote control unit through multiple intermediate nodes; Step S3: Based on the real-time monitored dust concentration, compare the change in the dust concentration before and after the operation of the dust removal equipment, calculate the dust removal effect, and adjust the dust removal intensity based on the dust removal effect; Step S4: Obtain the historical operating data of the dust removal equipment, analyze each piece of historical operating data, obtain the correlation between the data values in the operating data, generate a second model for each data value, obtain the operating data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operating data, calculate the difference between the predicted data and the actual data value. When the difference is greater than the first threshold, analyze the corresponding operating data to obtain the abnormal value in the operating data, and use the equipment part corresponding to the abnormal value as the first equipment part. Calculate the corresponding predicted value based on the second model of each data value, and calculate the difference between each data value and the corresponding predicted value. Add up the differences of all data values to obtain the total difference. If the total difference is greater than the preset second threshold, issue a fault warning.

[0008] Combined with the first aspect, in the first implementation manner of the first aspect of the present application, comparing the change in the dust concentration before and after the operation of the dust removal equipment includes: Step S31: Before the dust removal equipment operates, obtain multiple dust concentrations collected within the first time period, which are called the first dust concentrations. Divide the first dust concentrations into the first number of groups, preset the first number of first weight values with different magnitudes, obtain the collection time of each group of first dust concentrations, and set different first weight values for different groups of first environmental information according to the sequence of the collection time; Step S32: Preset the first different change rate ranges, set the corresponding weight values for each change rate range, and also calculate the change rates of each group of first dust concentrations to obtain multiple different change rates. Set different second weight values for each group of first dust concentrations based on the change rate range to which the change rate belongs; Step S33: Calculate the average weight value of the first weight value and the second weight value corresponding to each group of first dust concentrations, calculate the average dust concentration of each group of first dust concentrations, and multiply the average dust concentration of each group of first dust concentrations by the corresponding average weight value to obtain the weighted dust concentration of each group of first dust concentrations; Step S34: Add up the weighted dust concentrations of all the first dust concentrations to obtain a first result value, add up the average weight values of each group of first dust concentrations to obtain a second result value, divide the second result value by the first result value to obtain a third result value, use the third result value as the weighted average dust concentration before the dust removal equipment operates, and use the weighted average dust concentration before the dust removal equipment operates as the first concentration; Step S35: After the dust removal equipment operates, repeat Steps S31 - S34, calculate the weighted average dust concentration after the dust removal equipment operates, use the weighted average dust concentration after the dust removal equipment operates as the second concentration, and calculate the dust removal effect based on the first concentration and the second concentration.

[0009] Combined with the first aspect, in the second implementation manner of the first aspect of the present application, calculating the dust removal effect based on the first concentration and the second concentration includes: Obtain the concentration difference between the first concentration and the second concentration, then calculate the ratio of the concentration difference to the first concentration, use the ratio as the dust removal effect. If the dust removal effect is greater than a preset second threshold, reduce the dust removal intensity. If the dust removal effect is less than or equal to a preset third threshold, increase the dust removal intensity.

[0010] Combined with the first aspect, in the third implementation manner of the first aspect of the present application, generating a second model corresponding to each data value includes: Step S41: Select one of the data values from the operation data as the target value, and the other data values as variable values. Use multiple different correlation analysis methods to obtain multiple relationship models between the target value and the variable values; Step S42: Obtain the variable values in the operation data, calculate the result values of the target value based on the variable values respectively using multiple relationship models, compare the differences between the multiple result values and the corresponding actual target values, obtain multiple differences corresponding to each relationship model, and calculate the standard deviation of the multiple differences; Step S43: Compare the standard deviations corresponding to each relationship model, use the relationship model corresponding to the smallest standard deviation as the second model of the target value. After generating the second model, associate and save the target value, the second model, and the standard deviation of the second model, and use the standard deviation as the first threshold; Step S44: Use the other data values in the operation data as the target value, and repeat Steps S41 - S43 to train the second models of the other data values in the operation data.

[0011] In combination with the first aspect, in the fourth implementation manner of the first aspect of the present application, after taking the equipment part corresponding to the outlier as the first equipment part, it includes: When it is monitored that the first equipment part appears, input the corresponding operation data into the first model to obtain the corresponding operation category, obtain the first historical data of the corresponding operation category based on the operation category, obtain the corresponding variable value and target value from the first historical data, input the variable value into the first model to obtain the corresponding predicted value, calculate the difference between the predicted value and the target value. When the difference is less than the first threshold, mark the corresponding first equipment part as a faulty part. When the difference is greater than or equal to the first threshold, mark the corresponding first equipment part as a normal part.

[0012] In combination with the first aspect, in the fifth implementation manner of the first aspect of the present application, transmitting the collected dust concentration to the remote control unit through multiple intermediate nodes includes: Divide the dust concentration into multiple data groups, obtain the data position of each data group in the dust concentration, and also generate check data for each data group. Pack the data group, data position, and check data to generate a data packet and send it to the intermediate node. After receiving the data packet, the intermediate node checks whether the data group has an error based on the check data. When it is detected that an error has occurred, send a first message to the next node of the intermediate node. After a preset second time interval, if the corresponding error data packet is still not received, send the data position corresponding to the error data packet to the previous node.

[0013] In combination with the first aspect, in the sixth implementation manner of the first aspect of the present application, after the previous node receives the corresponding data position, it includes:

[0014] Judge whether the data packet received by itself is the data packet corresponding to the data position. If so, send the data packet to the next node. If not, send the data position to the previous node until the data sender receives the data position, and the data sender resends the data packet corresponding to the data position.

[0015] In the second aspect, the present application provides a dust removal control system, and the system includes: A monitoring and adjustment unit, configured to divide the operating state of the dust removal equipment into multiple operating categories, set different monitoring strategies for each operating category, train a first model based on the operating data of the dust removal equipment and the corresponding operating category to identify the operating state of the dust removal equipment. After the dust removal equipment is started, use the first model to identify the operating category of the dust removal equipment, and adjust the monitoring strategy of the dust removal equipment based on the operating category; A data acquisition unit is configured to install dust removal equipment and high-precision sensors in a production area, set a fixed first time interval for the high-precision sensors, collect the dust concentration in the production area every first time interval, and transmit the collected dust concentration to a remote control unit through multiple intermediate nodes; The remote control unit is configured to compare the change in the dust concentration before and after the operation of the dust removal equipment based on the real-time monitored dust concentration, calculate the dust removal effect, and adjust the dust removal intensity based on the dust removal effect; A fault warning unit is configured to obtain the historical operation data of the dust removal equipment, analyze each piece of historical operation data, obtain the correlation between the data values in the operation data, generate a second model corresponding to each data value, obtain the operation data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operation data, calculate the difference between the predicted data and the actual data value, when the difference is greater than a first threshold, analyze the corresponding operation data to obtain the abnormal value in the operation data, and use the equipment part corresponding to the abnormal value as the first equipment part, calculate the corresponding predicted value based on the second model of each data value, calculate the difference between each data value and the corresponding predicted value, add up the differences of all data values to obtain the total difference, if the total difference is greater than a preset second threshold, issue a fault warning.

[0016] In a third aspect, the present application provides a dust removal control device, including: A memory and at least one processor, wherein instructions are stored in the memory; the at least one processor invokes the instructions in the memory to cause the dust removal control device to execute the above-mentioned dust removal control method.

[0017] The third aspect of the present application provides a computer-readable storage medium, in which instructions are stored, and when it runs on a computer, it causes the computer to execute the above-mentioned dust removal control method.

[0018] Compared with the prior art, the beneficial effects of the present invention are at least as follows: In the technical solution provided by this application, by monitoring the dust concentration in real time and automatically adjusting the dust removal intensity of the dust removal equipment, it is ensured that the dust removal effect is always in the best state. This not only improves the dust removal efficiency but also reduces energy waste; the operation status of the dust removal equipment is identified using the first model, and the monitoring strategy is adjusted according to different operation categories, realizing intelligent operation management and fault prediction; by generating the second model corresponding to each data value, the operation data is obtained in real time, and the difference between the predicted data and the actual data value is calculated, realizing accurate prediction and rapid positioning of equipment faults, and improving the reliability and maintenance efficiency of the system; when an abnormal value is detected, by analyzing historical data and intelligent models, the fault status of equipment parts is further confirmed, reducing misjudgment and improving the accuracy of maintenance; by dividing the dust concentration into multiple data groups and generating verification data, the accuracy and integrity of data during transmission are ensured, improving the data transmission reliability of the system; when a data transmission error is detected, through the error handling mechanism of the intermediate node, the data is resent in a timely manner to ensure the integrity and accuracy of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a schematic diagram of an embodiment of a dust removal control method in an embodiment of this application; Figure 2 It is the step flow chart for calculating the dust removal effect in an embodiment of this application Figure 1 an embodiment schematic diagram; Figure 3 It is a schematic diagram of an embodiment of the step flow chart for generating the second model in an embodiment of this application; Figure 4 It is a schematic diagram of an embodiment of a dust removal control system in an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Embodiments of the present application provide a dust removal control method, system, device, and storage medium. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and the above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0022] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 One embodiment of a dust removal control method in the embodiments of the present application includes: Step S1: Divide the operating states of the dust removal device into multiple operating categories, set different monitoring strategies for each operating category, train a first model based on the operating data of the dust removal device and the corresponding operating category to identify the operating state of the dust removal device. After the dust removal device is started, use the first model to identify the operating category of the dust removal device and adjust the monitoring strategy of the dust removal device based on the operating category.

[0023] Specifically, based on the operating characteristics of the dust removal device, divide the operating states of the dust removal device into multiple operating categories. For example, the start-up stage of the dust removal device from a stationary state to a normal operating state, the stable stage of the device in the normal operating state, the stage where the operating mode of the device changes, such as switching from low-speed operation to high-speed operation, the stop stage of the device from the normal operating state to the stationary state. Set different monitoring strategies for each operating category, including monitoring frequency, monitoring parameters, etc. For example, increase the monitoring frequency during the start-up stage and focus on key parameters such as current and voltage during the start-up process. During the stable stage, maintain the regular monitoring frequency and pay attention to long-term operating parameters of the dust removal device such as temperature and current. Adjust the monitoring parameters during the mode change stage and focus on abnormal parameters that may occur during the mode change, such as vibration and differential pressure. Reduce the monitoring frequency during the stop stage and focus on key parameters such as current and temperature during the stop process of the dust removal device. Develop a first model to identify the operating state based on the operating data and automatically switch to the corresponding monitoring strategy based on the identified operating state.

[0024] Step S2: Install dust removal equipment and high-precision sensors in the production area. Set a fixed first time interval for the high-precision sensors, and collect the dust concentration in the production area every first time interval. Transmit the collected dust concentration to the remote control unit through multiple intermediate nodes.

[0025] Specifically, in order to remove the dust generated during the production of the flux, install dust removal equipment in the production area (flux production workshop), and also install high-precision sensors in the production area to monitor the dust concentration in the production area. In order to continuously monitor the dust concentration in the production area, set a fixed first time interval for the high-precision sensors, such as half a minute or 1 minute, to collect the dust concentration once. Since the high-precision sensors are installed in the production area and there are usually multiple production areas, it is possible that multiple high-precision sensors will transmit the collected dust concentration to the remote control unit at the same time. The remote control unit is usually set in a remote server and has a certain distance from the high-precision sensors. Therefore, multiple intermediate nodes need to be set as the transmission relay nodes for the dust concentration to ensure that the dust concentration can be effectively transmitted to the remote control unit. The specific transmission process will be explained in detail later.

[0026] Step S3: Based on the real-time monitored dust concentration, compare the change in the dust concentration before and after the operation of the dust removal equipment, calculate the dust removal effect, and adjust the dust removal intensity based on the dust removal effect.

[0027] Specifically, in order to achieve an efficient and energy-saving dust removal effect and ensure that the dust removal effect is always in the best state, based on the real-time monitored dust concentration, compare the change in the dust concentration before and after the operation of the dust removal equipment, calculate the dust removal effect. The specific method for calculating the dust removal effect will be explained in detail later. Adjust the dust removal intensity based on the dust removal effect.

[0028] Step S4: Obtain the historical operation data of the dust removal equipment, analyze each piece of historical operation data, obtain the correlation between the data values in the operation data, generate a second model for each data value, obtain the operation data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operation data, calculate the difference between the predicted data and the actual data value. When the difference is greater than the first threshold, analyze the corresponding operation data to obtain the abnormal value in the operation data, and take the equipment part corresponding to the abnormal value as the first equipment part. Calculate the corresponding predicted value based on the second model of each data value, and calculate the difference between each data value and the corresponding predicted value. Add up the differences of all data values to get the total difference. If the total difference is greater than the preset second threshold, issue a fault warning.

[0029] Specifically, in order to ensure that the dust removal equipment in the flux production workshop is always in a normal state, fault prediction is carried out on the dust removal equipment. In order to achieve accurate prediction and rapid positioning of the fault symptoms of the dust removal equipment, multiple sensors are installed at key parts of the dust removal equipment, such as the fan, filter bag, ash hopper, inlet and outlet, etc., for measuring the operation data of the dust removal equipment, such as pressure, temperature, flow rate, vibration, current, etc., and the measurement data of each sensor are collected in real time through the sensors.

[0030] Obtain the historical operation data measured historically, analyze the historical operation data to obtain the correlation between each data value, generate the corresponding second model, then obtain the operation data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operation data, obtain the difference between the predicted data and the corresponding actual data value. If the difference is greater than the preset first threshold, it is judged that some equipment parts or equipment parts have fault symptoms, obtain the corresponding operation data, analyze these operation data to obtain the corresponding abnormal values, and take the equipment parts (or fault parts) corresponding to the abnormal values as the first equipment parts. In the case of judging that a equipment part or part has a fault symptom, there may be a misjudgment. Therefore, calculate the total sum of the differences of all data values. In the case where the total sum of the differences is greater than the preset second threshold, it means that multiple equipment parts may have fault symptoms, and the possibility of judging that the corresponding dust removal equipment has a fault will increase greatly. At this time, the possibility of misjudgment is greatly reduced, so a fault warning is issued.

[0031] In a specific embodiment, compare the change in dust concentration before and after the operation of the dust removal equipment, calculate the dust removal effect, and also perform the following steps: Step S31: Before the operation of the dust removal equipment, obtain a plurality of dust concentrations collected in the first time period, which are called the first dust concentrations. Divide the first dust concentrations into the first number of groups, preset the first number of first weight values with different sizes, obtain the collection time of each group of first dust concentrations, and set different first weight values for different groups of first environmental information according to the sequence of the collection time. Step S32: Preset the first different change rate ranges, set the corresponding weight values for each change rate range, and also calculate the change rates of each group of first dust concentrations to obtain a plurality of different change rates, and set different second weight values for each group of first dust concentrations based on the change rate range to which the change rate belongs. Step S33: Calculate the average weight value of the first weight value and the second weight value corresponding to each group of first dust concentrations, calculate the average dust concentration of each group of first dust concentrations, and multiply the average dust concentration of each group of first dust concentrations by the corresponding average weight value to obtain the weighted dust concentration of each group of first dust concentrations. Step S34: Add up the weighted dust concentrations of all the first dust concentrations to obtain a first result value, add up the average weight values of each group of the first dust concentrations to obtain a second result value, divide the second result value by the first result value to obtain a third result value, use the third result value as the weighted average dust concentration before the dust removal equipment operates, and use the weighted average dust concentration before the dust removal equipment operates as the first concentration; Step S35: After the dust removal equipment operates, repeat Steps S31 - S34, calculate the weighted average dust concentration after the dust removal equipment operates, use the weighted average dust concentration after the dust removal equipment operates as the second concentration, and calculate the dust removal effect based on the first concentration and the second concentration.

[0032] Specifically, as Figure 2 shown in the flowchart of the steps for calculating the dust removal effect, assume that the high-precision sensor collects the dust concentration in the production area every half minute, and 30 dust concentrations are obtained within 15 minutes before the dust removal equipment is turned on. The 30 collected dust concentrations are collectively referred to as the first dust concentrations. Divide the first dust concentrations collected every three times into one group, and a total of 10 groups are formed. The first quantity is 10. Assume that 10 preset weight values of different sizes are 1, 2, 3,..., 10 respectively. Set the corresponding weight values for the 10 groups of first dust concentrations according to the chronological order of the collection time of each group of data. For example, the first group is collected earliest, and the weight value of the first group is set to 1, the weight value of the second group is set to 2, and so on. The weight value of the tenth group is set to 10.

[0033] Also calculate the change rate of each group of the first dust concentrations to obtain multiple different change rates. Assume that the three first dust concentrations of the first group are 30, 35, and 40 respectively. Then the change rate of the first group is (40 - 30) / 30 = 0.33. After calculating 10 different change rates, set different second weight values for different change rate ranges in advance. For example, for the change rate between 0 - 0.1, the second weight value is set to 1; for the change rate between 0.1 - 0.2, the second weight value is set to 2; and so on. For the change rate between 0.9 - 1, the second weight value is set to 10. Set the corresponding second weight value for each group of the first dust concentrations based on the change rate of each group of the first dust concentrations. The change rate of the first group is 0.33, which belongs to the range of 0.3 - 0.4, and set the corresponding second weight value 4 for the first group.

[0034] After calculating the first weight value and the second weight value of each group of the first dust concentrations, calculate the average of the first weight value and the second weight value, use the average as the average weight value of the corresponding group of the first dust concentrations, then calculate the average dust concentration of each group of the first dust concentrations, and multiply the average weight value and the average dust concentration to obtain the weighted dust concentration of each group of the first dust concentrations.

[0035] Add the weighted dust concentrations of all groups to obtain a first result value, then add the average weight values of each group to obtain a second result value, divide the second result value by the first result value to obtain a third result value, use the third result value as the weighted average dust concentration before the dust removal equipment operates, and use the weighted average dust concentration of the dust before the dust removal equipment operates as the first concentration.

[0036] After the dust removal equipment operates, repeat steps S31 - S34, calculate the weighted average dust concentration after the dust removal equipment operates, use the weighted average dust concentration after the dust removal equipment operates as the second concentration, and calculate the dust removal effect based on the first concentration and the second concentration. The specific calculation method will be explained in detail later.

[0037] The above method evaluates the dust removal effect by comparing the weighted average values before and after the dust removal equipment operates. If the weighted average value after operation is significantly lower than the value before operation, it indicates that the dust removal effect is good; if the change is not significant, it indicates that the dust removal effect needs to be further optimized. Through the above steps, the weighted algorithm can comprehensively consider the time factor and data change situation to more accurately evaluate the dust removal effect.

[0038] In a specific embodiment, calculating the dust removal effect based on the first concentration and the second concentration specifically includes the following steps: Obtain the concentration difference between the first concentration and the second concentration, then calculate the ratio of the concentration difference to the first concentration, use the ratio as the dust removal effect. If the dust removal effect is greater than a preset second threshold, reduce the dust removal intensity. If the dust removal effect is less than or equal to a preset third threshold, increase the dust removal intensity.

[0039] Specifically, obtain the concentration difference between the first concentration and the second concentration, then calculate the ratio of the concentration difference to the first concentration, use the ratio as the dust removal effect. If the dust removal effect is greater than the second threshold, it indicates that the dust removal effect is good, and reduce the dust removal intensity. For example, the fan speed of the dust removal equipment can be reduced, the air volume can be reduced, or the dust cleaning frequency can be reduced. If the dust removal effect is less than or equal to the preset third threshold, it indicates that the dust removal effect is not good, and the dust removal intensity needs to be increased. For example, the fan speed of the dust removal equipment can be increased, the air volume can be increased, or the dust cleaning frequency can be increased. If the dust removal effect is greater than the third threshold and less than or equal to the second threshold, it indicates that the dust removal effect is within a suitable range and the dust removal intensity does not need to be modified. By adjusting the dust removal intensity through this method, the dust removal equipment can ensure the dust removal effect while reducing energy consumption.

[0040] In a specific embodiment, generating a second model corresponding to each data value includes the following steps: Step S41: Select one of the data values from the operation data as the target value, and the other data values as variable values, and use multiple different correlation analysis methods to obtain multiple relationship models between the target value and the variable values; Step S42: Obtain the variable values in the operation data, calculate the result values of the target values respectively based on multiple relational models, compare the differences between the multiple result values and the corresponding actual target values, obtain the multiple differences corresponding to each relational model, and calculate the standard deviation of the multiple differences. Step S43: Compare the standard deviations corresponding to each relational model, use the relational model corresponding to the smallest standard deviation as the second model of the target value. After generating the second model, associate and save the target value, the second model, and the standard deviation of the second model, and use the standard deviation as the first threshold. Step S44: Use the other data values in the operation data as the target values, and repeat steps S41 - S43 to train the second model of the other data values in the operation data.

[0041] Specifically, as Figure 3 shown in the flowchart of the steps for generating the second model. To generate a second model that can accurately predict, select one of the data values from the operation data as the target value, and the other data values as variable values, and use multiple different correlation analysis methods for analysis. Multiple correlation analysis methods include, for example, linear regression, Pearson correlation coefficient, random forest, deep learning, etc. Obtain multiple relational models between the target value and the variable values, obtain the corresponding variable values from multiple sets of operation data, calculate the result values of the target values respectively based on the multiple relational models, compare the differences between the result values and the actual target values, compare the differences obtained by multiple relational models, calculate the standard deviation of the multiple differences, compare the standard deviations corresponding to each relational model, use the relational model corresponding to the smallest standard deviation as the second model of the corresponding target value. After generating the second model, associate and save the target value, the second model, and the standard deviation of the second model, and also use the standard deviation as the first threshold, which is used as the threshold for subsequent abnormal symptom judgment.

[0042] In a specific embodiment, after taking the equipment part corresponding to the outlier as the first equipment part, the following steps are further performed: When it is monitored that the first equipment part appears, input the corresponding operation data into the first model to obtain the corresponding operation category, obtain the first historical data of the corresponding operation category based on the operation category, obtain the corresponding variable values and target values from the first historical data, input the variable values into the first model to obtain the corresponding predicted values, calculate the difference between the predicted values and the target values. When the difference is less than the first threshold, mark the corresponding first equipment part as a faulty part; when the difference is greater than or equal to the first threshold, mark the corresponding first equipment part as a normal part.

[0043] Specifically, when the first equipment part is detected, it indicates that there may be signs of a fault in the first equipment part. However, there may also be abnormal monitoring. For example, in certain specific situations, an abnormal value may appear in the equipment part, but it is actually not a sign of a part fault. To further determine whether the first equipment part has abnormal signs, a corresponding set of operation data is obtained. The operation data is input into the first model to obtain the corresponding operation category. Based on the operation category, the first historical data of the corresponding operation category is obtained from the database. The historical data stored in the database is the historical data of the dust removal equipment in the normal operation state. The corresponding variable value and target value are obtained from the first historical data. The variable value is input into the first model to obtain the corresponding predicted value. The difference between the predicted value and the target value is calculated. When the difference is less than the first threshold, it indicates that the first historical data is normal, while the difference obtained using the current operation data is greater than or equal to the first threshold. Therefore, it indicates that the current operation data is abnormal. So, the corresponding first equipment part is marked as a faulty part. By marking the faulty part, it helps the maintenance personnel quickly locate the faulty part and quickly repair the corresponding faulty part, thus ensuring the normal operation of the dust removal equipment. When the difference is greater than or equal to the first threshold, it indicates that a similar situation also occurred in the historical operation condition, and the corresponding historical operation state was normal. Therefore, it is determined that the current situation where the difference is greater than the first threshold is also normal. Thus, the first equipment part is marked as a normal part.

[0044] In a specific embodiment, the collected dust concentration is transmitted to the remote control unit through multiple intermediate nodes, which specifically includes the following steps: The dust concentration is divided into multiple data groups, the data position of each data group in the dust concentration is obtained, and check data is also generated for each data group. The data group, data position, and check data are packed into a data packet and sent to the intermediate node. After receiving the data packet, the intermediate node checks whether the data group has an error based on the check data. When it is detected that an error has occurred, a first message is sent to the next node of the intermediate node. After a preset second time interval, if the corresponding error data packet is still not received, the data position corresponding to the error data packet is sent to the previous node.

[0045] Specifically, to ensure that the dust concentration can be quickly and correctly transmitted to the remote control unit, the dust concentration is first divided into multiple data groups, and the data positions of each data group in the dust concentration are obtained, which facilitates subsequent sending of incorrect or lost data based on the data positions. Check data is also generated for each data group, and the check data facilitates error checking of the received data groups by the nodes receiving the data. The data groups, data positions, and check data are packed to generate data packets and sent to the intermediate node. After receiving the data packets, the intermediate node checks whether the corresponding data groups are sent incorrectly based on the check data. In the case of detecting an error, a first message is sent to the next node of the intermediate node. The next node is the downstream node of the intermediate node, which may be an intermediate node or the remote control unit. The purpose of sending the first message is to notify the downstream node that a data error has been detected, and it is not necessary for the downstream node to repeatedly send the first message to the upstream node. After a preset second time interval, if the corresponding error data packet is still not received, the data position corresponding to the error data packet is sent to the upstream node of the current node (which may be an intermediate node or the remote control unit), that is, the previous node. Waiting for the second time interval is to prevent the upstream node of itself from having already sent this data position to the upstream node, preventing repeated sending of the first message to the data generation end and wasting communication resources.

[0046] In a specific embodiment, after the previous node receives the corresponding data position, it specifically includes the following steps: Determine whether the data packet received by itself is the data packet corresponding to the data position. If so, send the data packet to the next node; if not, send the data position to the previous node until the data sender receives the data position, and the data sender resends the data packet corresponding to the data position.

[0047] Specifically, after the previous node receives the data position, it may have already received the corresponding data packet. First, determine whether the data packet received by itself is the data packet corresponding to the data position. If so, send the data packet to the next node; if not, continue to send the data position to the previous node, that is, the upstream node, until the data generation end receives the data position, and the data generation end resends the corresponding data packet to the remote control unit. The data generation end refers to the high-precision sensor.

[0048] Through the above method, it can be ensured that the remote control unit efficiently receives the dust concentration while ensuring the accurate reception of the dust concentration.

[0049] Specifically, to ensure that the remote control unit obtains the complete dust concentration and to ensure the accuracy of the environmental information during transmission, the acquisition unit transmits the collected dust concentration to the remote control unit through multiple intermediate nodes. The specific transmission process will be explained in detail later.

[0050] The above describes a dust removal control method in an embodiment of the present application. Next, a dust removal control system in an embodiment of the present application will be described. Please refer to Figure 4 , an embodiment of a dust removal control system in an embodiment of the present application includes: A monitoring and adjustment unit, configured to classify the operating states of the dust removal equipment into multiple operating categories, set different monitoring strategies for each operating category, train a first model based on the operating data of the dust removal equipment and the corresponding operating category to identify the operating state of the dust removal equipment, after the dust removal equipment is turned on, use the first model to identify the operating category of the dust removal equipment, and adjust the monitoring strategy of the dust removal equipment based on the operating category; A data acquisition unit, configured to install dust removal equipment and high-precision sensors in the production area, set a fixed first time interval for the high-precision sensors, collect the dust concentration in the production area every first time interval, and transmit the collected dust concentration to the remote control unit through multiple intermediate nodes; A remote control unit, configured to compare the change in the dust concentration before and after the operation of the dust removal equipment based on the real-time monitored dust concentration, calculate the dust removal effect, and adjust the dust removal intensity based on the dust removal effect; A fault warning unit, configured to obtain the historical operating data of the dust removal equipment, analyze each piece of historical operating data, obtain the correlation between the data values in the operating data, generate a second model corresponding to each data value, obtain the operating data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operating data, calculate the difference between the predicted data and the actual data value, when the difference is greater than the first threshold, analyze the corresponding operating data to obtain the abnormal value in the operating data, and use the equipment part corresponding to the abnormal value as the first equipment part, calculate the corresponding predicted value based on the second model of each data value, calculate the difference between each data value and the corresponding predicted value, add up the differences of all data values to obtain the total difference, if the total difference is greater than the preset second threshold, issue a fault warning.

[0051] The present application also provides a dust removal control device. The dust removal control device includes a memory and a processor. When the computer-readable instructions stored in the memory are executed by the processor, the processor executes the steps of the dust removal control method in the above embodiments.

[0052] The present application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium, and the computer-readable storage medium can also be a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on the computer, the computer executes the steps of a dust removal control method.

[0053] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0054] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0055] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A dust removal control method, characterized in that: The method comprises: Step S1, dividing the operation status of the dust removal equipment into multiple operation categories, setting different monitoring strategies for each operation category, training a first model based on the operation data of the dust removal equipment and the corresponding operation category to identify the operation status of the dust removal equipment, after the dust removal equipment is turned on, using the first model to identify the operation category of the dust removal equipment, and adjusting the monitoring strategy of the dust removal equipment based on the operation category; Step S2: installing dust removal equipment and high-precision sensors in the production area, setting a fixed first time interval for the high-precision sensors, collecting dust concentration in the production area once every first time interval, and transmitting the collected dust concentration to the remote control unit through multiple intermediate nodes; Step S3: based on the real-time monitored dust concentration, compare the change of dust concentration before and after the dust removal equipment is operated, calculate the dust removal effect, and adjust the dust removal intensity based on the dust removal effect; Step S4, obtain the historical operation data of the dust removal equipment, analyze each historical operation data, obtain the correlation between each data value in the operation data, generate a second model corresponding to each data value, obtain the operation data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operation data, calculate the difference between the predicted data and the actual data value, when the difference is greater than the first threshold, analyze the corresponding operation data to obtain the abnormal value in the operation data, and use the equipment part corresponding to the abnormal value as the first equipment part, calculate the corresponding predicted value based on the second model of each data value, and calculate the difference between each data value and the corresponding predicted value, add the differences of all data values ​​to obtain the total difference, if the total difference is greater than the preset second threshold, issue a fault warning.

2. The method according to claim 1, characterized in that Compare the changes in dust concentration before and after the dust removal equipment is operated and calculate the dust removal effect, including: Step S31: before the dust removal equipment is operated, a plurality of dust concentrations collected in a first time period are obtained, referred to as first dust concentrations, the first dust concentrations are divided into a first number of groups, a first number of first weight values ​​of different sizes are preset, the collection time of each group of first dust concentrations is obtained, and different first weight values ​​are set for first environmental information of different groups according to the order of collection time; Step S32: presetting a first different change rate range, setting a corresponding weight value for each change rate range, further calculating the change rate of each group of first dust concentrations to obtain a plurality of different change rates, and setting a different second weight value for each group of first dust concentrations based on the change rate range to which the change rate belongs; Step S33, calculating the average weight value of the first weight value and the second weight value corresponding to each group of first dust concentrations, calculating the average dust concentration of each group of first dust concentrations, and multiplying the average dust concentration of each group of first dust concentrations by the corresponding average weight value to obtain the weighted dust concentration of each group of first dust concentrations; Step S34, adding the weighted dust concentrations of all first dust concentrations to obtain a first result value, adding the average weighted values ​​of each group of first dust concentrations to obtain a second result value, dividing the second result value by the first result value to obtain a third result value, and using the third result value as the weighted average value of the dust concentration before the dust removal equipment is operated, and using the weighted average value of the dust concentration before the dust removal equipment is operated as the first concentration; Step S35: After the dust removal equipment is running, repeat steps S31-S34 to calculate the weighted average value of the dust concentration after the dust removal equipment is running, and use the weighted average value of the dust concentration after the dust removal equipment is running as the second concentration, and calculate the dust removal effect based on the first concentration and the second concentration.

3. The method according to claim 2, characterized in that Calculating the dust removal effect based on the first concentration and the second concentration includes: Obtain the concentration difference between the first concentration and the second concentration, then calculate the ratio of the concentration difference to the first concentration, and use the ratio as the dust removal effect. If the dust removal effect is greater than a preset second threshold, reduce the dust removal intensity; if the dust removal effect is less than or equal to a preset third threshold, increase the dust removal intensity.

4. The method according to claim 1, characterized in that Generate a second model corresponding to each data value, including: Step S41: Select one of the data values ​​from the running data as the target value and the other data values ​​as variable values, and use multiple different correlation analysis methods to obtain multiple relationship models between the target value and the variable values; Step S42, obtaining variable values ​​in the operation data, calculating the result values ​​of the target values ​​based on the variable values ​​based on the multiple relationship models, comparing the differences between the multiple result values ​​and the corresponding actual target values, obtaining multiple difference values ​​corresponding to each relationship model, and calculating the standard deviation of the multiple difference values; Step S43, comparing the standard deviations corresponding to each relationship model, taking the relationship model corresponding to the smallest standard deviation as the second model of the target value, and after generating the second model, associating and saving the target value, the second model, and the standard deviation of the second model, and taking the standard deviation as the first threshold; Step S44: Use other data values ​​in the running data as target values, repeat steps S41 to S43, and train a second model for other data values ​​in the running data.

5. The method according to claim 1, characterized in that After taking the device part corresponding to the abnormal value as the first device part, the following is also executed: When the occurrence of a first equipment part is monitored, the corresponding operating data is input into the first model to obtain the corresponding operating category, first historical data of the corresponding operating category is obtained based on the operating category, corresponding variable values ​​and target values ​​are obtained from the first historical data, the variable values ​​are input into the first model to obtain corresponding predicted values, the difference between the predicted value and the target value is calculated, and when the difference is less than a first threshold, the corresponding first equipment part is marked as a faulty part, and when the difference is greater than or equal to the first threshold, the corresponding first equipment part is marked as a normal part.

6. The method according to claim 1, characterized in that The collected dust concentration is transmitted to the remote control unit through multiple intermediate nodes, including: The dust concentration is divided into multiple data groups, the data position of each data group in the dust concentration is obtained, and verification data is generated for each data group. The data group, data position and verification data are packaged to generate a data packet and sent to the intermediate node. After receiving the data packet, the intermediate node verifies whether an error occurs in the data group based on the verification data. If an error is detected, a first message is sent to the next node of the intermediate node. After a preset second time interval, if the corresponding error data packet is still not received, the data position corresponding to the error data packet is sent to the previous node.

7. The method according to claim 6, characterized in that After receiving the corresponding data location, the previous node also executes: Determine whether the data packet received is the data packet corresponding to the data position. If yes, send the data packet to the next node. If not, send the data position to the previous node until the data sender receives the data position and resends the data packet corresponding to the data position.

8. A dust removal control system, used to implement a dust removal control method as claimed in any one of claims 1 to 7, characterized in that: The system comprises: A monitoring and adjustment unit, configured to classify the operation status of the dust removal device into a plurality of operation categories, set a different monitoring strategy for each operation category, train a first model based on the operation data of the dust removal device and the corresponding operation category for identifying the operation status of the dust removal device, use the first model to identify the operation category of the dust removal device after the dust removal device is turned on, and adjust the monitoring strategy of the dust removal device based on the operation category; A data collection unit is used to install dust removal equipment and a high-precision sensor in the production area, set a fixed first time interval for the high-precision sensor, collect dust concentration in the production area every first time interval, and transmit the collected dust concentration to the remote control unit through multiple intermediate nodes; A remote control unit, for comparing the change in dust concentration before and after the operation of the dust removal equipment based on the real-time monitored dust concentration, calculating the dust removal effect, and adjusting the dust removal intensity based on the dust removal effect; A fault warning unit is used to obtain historical operating data of the dust removal equipment, analyze each historical operating data, obtain the correlation between each data value in the operating data, generate a second model corresponding to each data value, obtain the operating data of the dust removal equipment in real time, use the second model to obtain the predicted data of each data value in the operating data, calculate the difference between the predicted data and the actual data value, and when the difference is greater than a first threshold, analyze the corresponding operating data to obtain the abnormal value in the operating data, and use the equipment part corresponding to the abnormal value as the first equipment part, calculate the corresponding predicted value based on the second model of each data value, and calculate the difference between each data value and the corresponding predicted value, add the differences of all data values ​​to obtain the total difference, and if the total difference is greater than the preset second threshold, issue a fault warning.

9. A dust removal control device, characterized in that: The dust removal control device comprises: A memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory so that the dust removal control device executes a dust removal control method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, a dust removal control method as described in any one of claims 1-7 is implemented.

Images