Fly ash treatment equipment operation control system and method based on AI vision

Abstract

The invention discloses a fly ash treatment equipment operation control system and method based on AI vision, and relates to the technical field of fly ash treatment, the system comprises an AI vision detection module, an anomaly detection treatment module, a fly ash treatment module and a parameter regression adjustment module; the AI visual detection module is used for detecting physical and chemical characteristic information of fly ash; the anomaly detection processing module is used for analyzing whether the conditions of humidity anomaly and abnormal agglomeration of fly ash occur or not, and processing the abnormal conditions; the fly ash treatment module is used for controlling fly ash treatment equipment to treat fly ash and adjusting equipment parameters according to a residual amount detection result; the parameter regression adjustment module is used for carrying out regression adjustment on equipment parameters; according to the method, the accuracy of fly ash treatment and the operation efficiency of fly ash treatment equipment are improved through anomaly detection treatment and real-time adjustment of equipment parameters; and through regression adjustment of the equipment parameters, the problem of energy waste caused by higher and higher equipment parameters is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fly ash treatment, and specifically to an AI vision-based fly ash treatment equipment operation control system and method. Background Art

[0002] Fly ash Fly ash (Fly ash) is a hazardous waste generated by industries such as waste incineration, coal-fired power plants, and metallurgy. Its main components are inorganic substances such as SiO2, Al2O3, and CaO, as well as toxic substances such as heavy metals (such as Pb, Cd, and Hg) and dioxins. If improperly handled, it can cause serious environmental pollution and threaten ecological balance and human health. At the same time, with increasingly stringent environmental regulations, companies face tremendous environmental pressure and require efficient and compliant fly ash treatment technologies to meet these requirements. Traditional fly ash treatment methods have limitations, such as low treatment efficiency and low resource recovery rates. In recent years, with the rapid development of artificial intelligence technology, AI has also been introduced to the control of fly ash treatment equipment. However, current technologies still face difficulties in real-time monitoring and precise control of the treatment process. The parameters of fly ash treatment equipment cannot be adjusted based on real-time fly ash data. This inability to flexibly adjust fly ash treatment equipment parameters can lead to problems during the fly ash treatment process. If the equipment parameters of the fly ash treatment equipment are too low, the treatment or separation of different components in the fly ash will not be complete. If the equipment parameters of the fly ash treatment equipment are too high, energy waste and low treatment efficiency will be caused. Summary of the Invention

[0003] The purpose of the present invention is to provide an AI vision-based fly ash processing equipment operation control system and method to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a fly ash treatment equipment operation control method based on AI vision, comprising the following steps: S1. Use high-resolution industrial cameras, infrared sensors, and laser scattering sensors to collect fly ash information and extract fly ash characteristic data; S2. Analyze whether humidity anomalies and fly ash agglomeration abnormalities occur based on the real-time detected humidity data and fly ash particle diameter data, and handle the abnormalities; S3. Process the fly ash using fly ash processing equipment, test the residual amount of components after each processing step, and adjust equipment parameters in real time based on the residual amount test results; S4. Record and store equipment parameter changes in the cloud data processing center, and perform regression adjustments on the equipment parameters of the fly ash processing equipment at a fixed period.

[0005] Furthermore, in step S1: the morphology, color and diameter of fly ash particles are collected by a high-resolution industrial camera and a laser sensor, and the spectral information of different fly ash particles is detected by an infrared sensor; the types of fly ash are analyzed based on the collected particle diameter and spectral information data using a convolutional neural network, and the fly ash particles are classified according to toxic substances, heavy metals, salt components and building material base components; the proportion of each type of fly ash in the total amount of fly ash is detected and calculated, and the proportion of toxic substances is recorded as q d ; The proportion of heavy metals is recorded as q j ; The proportion of salt components is recorded as q y ; The proportion of building material base material components is recorded as q c .

[0006] Furthermore, in step S2: the fly ash particles are subjected to vibration anti-agglomeration treatment by a vibrating screen, and the operating power of the vibrating screen is set to P when the equipment is started. z1 The humidity of fly ash particles is controlled by the dryer to prevent the fly ash particles from getting wet and sticking together. When the equipment is started, the operating power of the dryer is set to P h1 ; According to the detected fly ash characteristic data and the humidity data in the fly ash processing equipment, abnormal conditions are detected and processed; in the abnormal condition detection process, first, the humidity threshold W is set max , the humidity W in the fly ash processing equipment is collected in real time through the humidity sensor, and W is compared with W max Perform comparative analysis to determine in real time whether the humidity in the fly ash processing equipment exceeds the set humidity threshold; if W <W max , judge that the humidity in the fly ash treatment equipment is normal; if W≥W max If the humidity in the fly ash processing equipment is abnormally high, an abnormal humidity warning is issued, and an instruction is issued to increase the operating power of the dryer by ΔP h ; While issuing a command to increase the dryer power for humidity control, the fly ash particle diameter is detected for abnormality; the collected fly ash particle diameter data is used to determine whether abnormal agglomeration occurs; the particle diameters of the fly ash particles detected in real time are {D1, D2, ..., D n}, set the fly ash particle diameter threshold to D max , the detected fly ash particle diameter D i With D max For comparative analysis, if D i <D max , judge that there is no abnormal agglomeration of fly ash particles; if D i ≥D max , to determine if fly ash particles are agglomerated abnormally; where i = 1, 2, ..., n; Different processing solutions are triggered based on the detected anomalies: If W ≥ W max and D i <D max , if it is determined that the humidity of the fly ash processing equipment is abnormally high but the fly ash particles are abnormally agglomerated, only the instruction to increase the dryer power is issued to control the humidity; If W ≥ W max and D i ≥D max , it is judged that the humidity of the fly ash equipment is abnormal and the fly ash particles are abnormally agglomerated; while issuing a command to increase the dryer power for humidity control, it further issues a command to increase the operating power of the vibrating screen by ΔP z , used to vibrate and separate fly ash particles that are abnormally agglomerated; and issue an early warning of abnormal fly ash particle composition detection; and mark the fly ash component ratio detected in step S1 as abnormal data. After the vibrating screen separates the abnormally agglomerated fly ash particles, it issues a command to control the detection equipment to re-detect the composition of the fly ash particles, and the ratio of the amount of each fly ash component calculated by the re-detection to the total amount of fly ash is recorded as q d ′、q j ′、q y ′ and q c ′, the proportion of toxic substances is recorded as q d ′, the proportion of heavy metals is recorded as q j ′, the proportion of salt components is recorded as q y ′, the proportion of building material base material components is recorded as q c '; Real-time monitoring of the humidity data of the fly ash processing equipment and the abnormal agglomeration of fly ash particles can reduce the adhesion of fly ash particles caused by increased humidity and prevent the erroneous monitoring of fly ash composition caused by the agglomeration of fly ash particles.

[0007] Furthermore, in step S3, the fly ash processing equipment processes the fly ash particles according to the following steps: S3-1. Detoxification of toxic substances contained in fly ash by low-temperature pyrolysis; S3-2, removing salt components from fly ash by sedimentation and rinsing; S3-3, removing heavy metals from fly ash by circulating rinsing; S3-4, collecting and storing the building material base material components contained in the treated fly ash for subsequent production of building materials; After each processing step, a component residual amount test is performed and a component residual amount threshold is set to control the component residual amount; the toxic substance residual amount threshold is set to q d0 , set the salt component residual threshold qy0 , set the heavy metal residue threshold to q j0 ; In step S3-1, a low-temperature pyrolysis process with a duration of Δt0 is set to detoxify the toxic substances in the fly ash; after the low-temperature pyrolysis process with a duration of Δt0 is completed, the residual amount of toxic substances in the treated fly ash is detected, and the residual amount of toxic substances in the fly ash is recorded as q d ′′, and q d ′′ is compared with the set toxic substance residual threshold. If q d ′′≤q d0 , it is judged that the residual amount of toxic substances in the fly ash meets the standard, then the process of step S3-2 is entered; if q d ′′>q d0 , it is judged that the residual amount of toxic substances in the fly ash is high, then an instruction is generated to control the processing equipment to increase the pyrolysis treatment time, add a pyrolysis process of Δt, and then perform the toxic substance residual detection until q is detected. d ′′≤q d0 Then enter the process of step S3-2 and record the total time of pyrolysis treatment , where m1 represents the number of times the pyrolysis treatment time is increased, and the first treatment time of the next fly ash pyrolysis treatment is set to Δt′; In step S3-2, chemical additives are added to promote the precipitation of salt components. First, a chemical additive with a mass of s0 is added to perform the precipitation treatment of the salt components. After the first precipitation reaction and filtration, the residual amount of the salt components is detected and recorded as q y ′′, if q y ′′≤q y0 , it is judged that the residual amount of salt components meets the standard, then the process enters step S4-3; if q y ′′>q y0 If it is judged that the residual amount of salt components is high, an instruction is generated to control the processing equipment to add a chemical additive with a mass of Δs to precipitate the salt components again, and then the residual amount of salt components is detected again until q y ′′≤q y0 , then enter the processing process of step S3-3, and record the total mass of the added chemical additives , where m2 represents the number of times the chemical additive with a mass of Δs is added; and the mass of the chemical additive added for the first time during the precipitation and rinsing process of the next fly ash treatment is set to s′; In step S3-3, first, the m0 times of the circulating rinsing process is set to treat the heavy metals contained in the fly ash, and after the m0 times of the circulating rinsing, the residual amount of the heavy metals in the fly ash is detected, and the residual amount of the heavy metals in the fly ash is recorded as q j ′′, and the q j ′′ is compared with the set threshold value of the residual amount of the heavy metals, if q j ′′≤q j0 , it is judged that the residual amount of the heavy metals meets the standard, and then the process in step S3-4 is entered; if q j ′′>q j0 , it is judged that the residual amount of the heavy metals is high, and then an instruction is generated to control the treatment equipment to increase the circulating rinsing to treat the residual heavy metals, and then the residual amount of the heavy metals is detected again until q j ′′≤q j0 , and then the process in step S3-4 is entered, and the final circulating rinsing times m3 is recorded, and the first circulating rinsing times of the fly ash treatment process in the next time is set to m3; The residual amount detection is performed after each fly ash treatment step, which can ensure that the residual amount meets the standard in the fly ash treatment process, and can improve the recovery rate of different components in the fly ash; and when the residual amount is detected to be abnormal each time, the treatment data of the fly ash treatment equipment is updated, and the equipment parameters of the fly ash treatment equipment are adjusted according to the treatment, so that the same residual amount detection and value adjustment process as the present treatment process is not repeated in the next treatment, and the efficiency of the fly ash treatment process is improved while the fly ash treatment process is monitored and controlled in real time.

[0008] Further, in step S4, the number of times of the fly ash treatment η of the fly ash treatment equipment is recorded in the cloud data processing center, and the parameter change of the fly ash treatment equipment in each fly ash treatment process is recorded, and the equipment parameters of each fly ash treatment are recorded as A η ; and the period of the equipment parameter regression adjustment is set to k, and after k times of the fly ash treatment, the cloud data processing center performs the equipment parameter regression adjustment according to the recorded equipment parameter change; in the regression adjustment process of the fly ash equipment treatment parameters, the number of times of the change of the equipment parameters in k times of the fly ash treatment is recorded as k1, and the regression adjustment result of the equipment parameters is calculated by the following formula: ; Wherein, A represents the equipment parameters after the regression adjustment, A0 represents the initial equipment parameters set in the fly ash treatment equipment when the fly ash treatment is not performed; the equipment parameters represent the pyrolysis time, the rinsing times and the mass of the chemical additives; and in the parameter regression adjustment process, if the adjusted parameter is the rinsing times, the calculation result of the equipment parameter regression adjustment is calculated by rounding up; After the cloud data processing center makes regression adjustments to the equipment parameters, it records and stores the number of regression adjustments of the equipment parameters and the equipment parameter values ​​after each regression adjustment; and every time k2 equipment parameter regression adjustments are made, the k2 adjusted equipment parameter adjustment results are compared and analyzed to determine whether the k2 regression adjustment results are the same. If it is detected that the k2 equipment parameter regression adjustment results are the same, an instruction is issued to control the fly ash processing equipment to adjust the equipment parameters to the initial equipment parameter A0; if it is detected that the k2 equipment parameter adjustment results are all the initial equipment parameter A0, an instruction is issued to lower the initial equipment parameter of the fly ash processing equipment and adjust the initial equipment parameter to A0′=p A0, where p is the proportional coefficient set by the system, and 0 <p<1;通过在云端数据处理中心设置固定周期的设备参数回归调整,能够在一个周期的飞灰处理过程后将设备参数进行回归调整,解决了设备参数在设备端根据飞灰处理情况进行实时调整的过程中产生的参数值越来越高的问题,防止因为设备参数始终增高导致的能源浪费问题和处理时间冗长的问题,定期的参数回归提高了飞灰处理设备的工作效率。

[0009] An AI vision-based fly ash treatment equipment operation control system, the system includes an AI vision detection module, an anomaly detection and processing module, a fly ash treatment module, and a parameter regression adjustment module; The AI ​​visual inspection module uses a high-resolution industrial camera, an infrared sensor, and a laser scattering sensor to detect the physical and chemical characteristics of fly ash. The abnormality detection and processing module analyzes whether humidity abnormality and fly ash abnormal agglomeration occur based on the real-time monitored humidity data and fly ash particle diameter data, and processes the abnormality; The fly ash processing module is used to control the fly ash processing equipment to process the fly ash, perform component residual detection after each processing step, and adjust the equipment parameters in real time according to the residual detection results; The parameter regression adjustment module is used to control the cloud data processing center to record and store parameter changes on the equipment side, and to perform regression adjustment on the equipment parameters of the fly ash processing equipment according to a fixed period.

[0010] Furthermore, the AI ​​visual inspection module includes a physical feature detection unit, a chemical feature detection unit and a fly ash composition identification unit; the physical feature detection unit collects the morphology, color and particle diameter of fly ash particles through a high-resolution industrial camera and a laser sensor; the chemical feature detection unit detects the chemical composition of fly ash particles through an infrared sensor; the fly ash composition identification unit uses a convolutional neural network to analyze the composition of fly ash based on the collected fly ash particle data.

[0011] Furthermore, the abnormality detection and processing module includes a humidity abnormality detection unit, a fly ash particle abnormal agglomeration detection unit and an abnormal situation processing unit; the humidity abnormality detection unit collects the humidity in the fly ash processing equipment through a humidity sensor, compares and analyzes the collected humidity data with the set humidity threshold, and determines whether the humidity in the fly ash processing equipment is abnormal; the fly ash particle abnormal agglomeration detection unit compares the fly ash particle diameter with the set fly ash particle diameter threshold to determine whether the fly ash particles are abnormally agglomerated; the abnormal situation processing unit is used to perform abnormal situation processing according to the type of abnormal situation detected.

[0012] Furthermore, the fly ash processing module includes a fly ash processing unit, a residual amount detection unit and an equipment parameter updating unit; the fly ash processing unit detoxifies toxic substances in fly ash through low-temperature pyrolysis, removes salt components in fly ash through sedimentation rinsing, and removes heavy metals in fly ash through circulation rinsing; the residual amount detection unit is used to set a residual amount threshold, and compare the detected residual amount value with the set residual amount threshold, so as to determine whether the residual amount of the treated component meets the standard; the equipment parameter updating unit is used to update the equipment parameters of the fly ash processing equipment in real time.

[0013] Furthermore, the parameter regression adjustment module includes a cloud data storage unit and an equipment parameter regression adjustment unit; the cloud data storage unit is used to record and store the number of fly ash treatments and equipment parameter changes; the equipment parameter regression adjustment unit is used to perform regular regression adjustments on the equipment parameters of the fly ash treatment equipment in the cloud data processing center.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes an operation control system and method for fly ash processing equipment based on AI vision, which collects fly ash particle data through sensors and uses convolutional neural networks to identify fly ash components, thereby improving the efficiency of fly ash component identification; and the present invention performs real-time detection and processing of humidity data and abnormal agglomeration of fly ash particles of fly ash processing equipment, thereby reducing the adhesion of fly ash particles caused by increased humidity and preventing inaccurate fly ash component detection caused by agglomeration of fly ash particles; the present invention performs residual amount detection of the processed components after each fly ash processing step, and each time an abnormal residual amount is detected, the equipment parameters of the fly ash processing equipment are adjusted in real time according to the processing situation. The cloud-based data processing center can be used to adjust the equipment parameters at fixed intervals, thereby improving the resource recovery rate of the fly ash treatment process and eliminating the need to repeat the same residual amount detection and value adjustment process as in the current treatment process during the next treatment, thereby improving the efficiency of fly ash treatment. In addition, by setting a fixed-period equipment parameter regression adjustment in the cloud-based data processing center, the equipment parameters can be adjusted after one cycle of fly ash treatment process, thereby solving the problem of increasingly higher equipment parameter values ​​in the process of real-time adjustment of equipment parameters according to the fly ash treatment situation, and preventing energy waste and lengthy processing time caused by the continuous increase in equipment parameters. Regular parameter regression further improves the working efficiency of fly ash treatment equipment and avoids energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an AI vision-based fly ash treatment equipment operation control method of the present invention; Figure 2 This is a structural schematic diagram of an AI vision-based fly ash processing equipment operation control system of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] like Figure 1-Figure 2 As shown, the present invention provides a technical solution, a fly ash treatment equipment operation control method based on AI vision, such as Figure 1 As shown, the method includes the following steps: S1. Use high-resolution industrial cameras, infrared sensors, and laser scattering sensors to collect fly ash information and extract fly ash characteristic data; S2. Analyze whether humidity anomalies and fly ash agglomeration abnormalities occur based on the real-time detected humidity data and fly ash particle diameter data, and handle the abnormalities; S3. Process the fly ash using fly ash processing equipment, test the residual amount of components after each processing step, and adjust equipment parameters in real time based on the residual amount test results; S4. Record and store equipment parameter changes in the cloud data processing center, and perform regression adjustments on the equipment parameters of the fly ash processing equipment at a fixed period.

[0018] In step S1: the morphology, color and diameter of fly ash particles are collected by high-resolution industrial cameras and laser sensors, and the spectral information of different fly ash particles is detected by infrared sensors; the types of fly ash are analyzed based on the collected particle diameter and spectral information data using a convolutional neural network, and the fly ash particles are classified according to toxic substances, heavy metals, salt components and building material base components; the proportion of each type of fly ash in the total amount of fly ash is detected and calculated, and the proportion of toxic substances is recorded as q d ; The proportion of heavy metals is recorded as q j ; The proportion of salt components is recorded as q y ; The proportion of building material base material components is recorded as q c .

[0019] In step S2: the fly ash particles are vibrated to prevent agglomeration through the vibrating screen, and the operating power of the vibrating screen is set to P when the equipment is started. z1 The humidity of fly ash particles is controlled by the dryer to prevent the fly ash particles from getting wet and sticking together. When the equipment is started, the operating power of the dryer is set to P h1 ; According to the detected fly ash characteristic data and the humidity data in the fly ash processing equipment, abnormal conditions are detected and processed; in the abnormal condition detection process, first, the humidity threshold W is set max , the humidity W in the fly ash processing equipment is collected in real time through the humidity sensor, and W is compared with W max Perform comparative analysis to determine in real time whether the humidity in the fly ash processing equipment exceeds the set humidity threshold; if W <W max , judge that the humidity in the fly ash treatment equipment is normal; if W≥W max If the humidity in the fly ash processing equipment is abnormally high, an abnormal humidity warning is issued, and an instruction is issued to increase the operating power of the dryer by ΔP h ; While issuing a command to increase the dryer power for humidity control, the fly ash particle diameter is detected for abnormality; the collected fly ash particle diameter data is used to determine whether abnormal agglomeration occurs; the particle diameters of the fly ash particles detected in real time are {D1, D2, ..., D n}, set the fly ash particle diameter threshold to D max , the detected fly ash particle diameter D i With D max For comparative analysis, if D i <D max , judge that there is no abnormal agglomeration of fly ash particles; if D i ≥D max , to determine if fly ash particles are agglomerated abnormally; where i = 1, 2, ..., n; Different processing solutions are triggered based on the detected anomalies: If W ≥ W max and D i <D max , if it is determined that the humidity of the fly ash processing equipment is abnormally high but the fly ash particles are abnormally agglomerated, only the instruction to increase the dryer power is issued to control the humidity; If W ≥ W max and D i ≥D max , it is judged that the humidity of the fly ash equipment is abnormal and the fly ash particles are abnormally agglomerated; then, while issuing a command to increase the dryer power for humidity control, a further command is issued to increase the operating power of the vibrating screen by ΔP z , used to vibrate and separate fly ash particles that are abnormally agglomerated; and issue an early warning of abnormal fly ash particle composition detection; and mark the fly ash component ratio detected in step S1 as abnormal data. After the vibrating screen separates the abnormally agglomerated fly ash particles, it issues a command to control the detection equipment to re-detect the composition of the fly ash particles, and the ratio of the amount of each fly ash component calculated by the re-detection to the total amount of fly ash is recorded as q d ′、q j ′、q y ′ and q c ′, the proportion of toxic substances is recorded as q d ′, the proportion of heavy metals is recorded as q j ′, the proportion of salt components is recorded as q y ′, the proportion of building material base material components is recorded as q c '; Real-time monitoring of the humidity data of the fly ash processing equipment and the abnormal agglomeration of fly ash particles can reduce the adhesion of fly ash particles caused by increased humidity and prevent the erroneous monitoring of fly ash composition caused by the agglomeration of fly ash particles.

[0020] In step S3, the fly ash processing equipment processes the fly ash particles according to the following steps: S3-1. Detoxification of toxic substances contained in fly ash by low-temperature pyrolysis; S3-2, removing salt components from fly ash by sedimentation and rinsing; S3-3, removing heavy metals from fly ash by circulating rinsing; S3-4, collecting and storing the building material base material components contained in the treated fly ash for subsequent production of building materials; After each processing step, a component residual amount test is performed and a component residual amount threshold is set to control the component residual amount; the toxic substance residual amount threshold is set to q d0 , set the salt component residual threshold q y0 , set the heavy metal residue threshold to q j0 ; In step S3-1, a low-temperature pyrolysis process with a duration of Δt0 is set to detoxify the toxic substances in the fly ash; after the low-temperature pyrolysis process with a duration of Δt0 is completed, the residual amount of toxic substances in the treated fly ash is detected, and the residual amount of toxic substances in the fly ash is recorded as q d ′′, and q d ′′ is compared with the set toxic substance residual threshold. If q d ′′≤q d0 , it is judged that the residual amount of toxic substances in the fly ash meets the standard, then the process of step S3-2 is entered; if q d ′′>q d0 , it is judged that the residual amount of toxic substances in the fly ash is high, then an instruction is generated to control the processing equipment to increase the pyrolysis treatment time, add a pyrolysis process of Δt, and then perform the toxic substance residual detection until q is detected. d ′′≤q d0 Then enter the process of step S3-2 and record the total time of pyrolysis treatment , where m1 represents the number of times the pyrolysis treatment time is increased, and the first treatment time of the next fly ash pyrolysis treatment is set to Δt′; In step S3-2, chemical additives are added to promote the precipitation of salt components. First, a chemical additive with a mass of s0 is added to perform the precipitation treatment of the salt components. After the first precipitation reaction and filtration, the residual amount of the salt components is detected and recorded as q y ′′, if q y ′′≤q y0 , it is judged that the residual amount of salt components meets the standard, then the process enters step S4-3; if q y ′′>q y0If it is judged that the residual amount of salt components is high, an instruction is generated to control the processing equipment to add a chemical additive with a mass of Δs to precipitate the salt components again, and then the residual amount of salt components is detected again until q y ′′≤q y0 , then enter the processing process of step S3-3, and record the total mass of the added chemical additives , where m2 represents the number of times the chemical additive with a mass of Δs is added; and the mass of the chemical additive added for the first time during the precipitation and rinsing process of the next fly ash treatment is set to s′; In step S3-3, firstly, a rinsing process of m0 times is set to process the heavy metals contained in the fly ash, and the residual amount of heavy metals is detected after m0 times of rinsing, and the residual amount of heavy metals in the fly ash is recorded as q j ′′, change q j ′′ is compared with the set heavy metal residue threshold. If q j ′′≤q j0 , it is judged that the heavy metal residue meets the standard, then the process goes to step S3-4; if q j ′′>q j0 If it is judged that the residual amount of heavy metals is high, an instruction is generated to control the processing equipment to add a cycle rinse to process the residual heavy metals, and then the residual amount of heavy metals is detected again until q j ′′≤q j0 , then enter the processing process of step S3-4, and record the final cycle rinsing number m3, and set the first cycle rinsing number of the next fly ash treatment process to m3; Carrying out residual amount detection after each fly ash treatment step can ensure that the residual amount in the fly ash treatment process meets the standard and can achieve the effect of improving the recovery rate of different components in the fly ash; and each time an abnormal residual amount is monitored, the processing data of the fly ash treatment equipment is updated, and the equipment parameters of the fly ash treatment equipment are adjusted according to the treatment situation, thereby eliminating the need to repeat the same residual amount detection and numerical adjustment process as the current treatment process during the next treatment; realizing real-time monitoring and control of the fly ash treatment process while improving the efficiency of the fly ash treatment process.

[0021] In step S4: the number of times the fly ash treatment equipment performs fly ash treatment η is recorded in the cloud data processing center, and the parameter changes in the fly ash treatment equipment during each fly ash treatment process are recorded, and the equipment parameters of each fly ash treatment are recorded as A ηThe period of equipment parameter regression adjustment is set to k. After every k fly ash treatments, the cloud data processing center performs a regression adjustment of the equipment parameters based on the recorded equipment parameter changes. During the regression adjustment of the fly ash equipment treatment parameters, the number of times the equipment parameters change during the k fly ash treatments is recorded as k1. The regression adjustment result of the equipment parameters is calculated using the following formula: ; Where A represents the equipment parameters after regression adjustment, A0 represents the initial equipment parameters set in the fly ash treatment equipment before fly ash treatment is performed; the equipment parameters represent the pyrolysis time, the number of rinses, and the chemical addition and quality; during the parameter regression adjustment process, if the adjusted parameter is the number of rinses, the calculation result of the equipment parameter regression adjustment is rounded up; After the cloud data processing center makes regression adjustments to the equipment parameters, it records and stores the number of regression adjustments of the equipment parameters and the equipment parameter values ​​after each regression adjustment; and every time k2 equipment parameter regression adjustments are made, the k2 adjusted equipment parameter adjustment results are compared and analyzed to determine whether the k2 regression adjustment results are the same. If it is detected that the k2 equipment parameter regression adjustment results are the same, an instruction is issued to control the fly ash processing equipment to adjust the equipment parameters to the initial equipment parameter A0; if it is detected that the k2 equipment parameter adjustment results are all the initial equipment parameter A0, an instruction is issued to lower the initial equipment parameter of the fly ash processing equipment and adjust the initial equipment parameter to A0′=p A0, where p is the proportional coefficient set by the system, and 0 <p<1; By setting up fixed-period equipment parameter regression adjustments in the cloud data processing center, the equipment parameters can be regressed and adjusted after a cycle of fly ash treatment. This solves the problem of increasingly higher parameter values ​​generated during real-time adjustment of equipment parameters based on the fly ash treatment situation at the equipment end, prevents energy waste and lengthy processing time caused by the continuous increase in equipment parameters, and regular parameter regression improves the working efficiency of fly ash treatment equipment.

[0022] An AI vision-based fly ash treatment equipment operation control system, such as Figure 2 As shown, the system includes an AI visual detection module, an anomaly detection and processing module, a fly ash processing module, and a parameter regression adjustment module; The AI ​​visual inspection module uses high-resolution industrial cameras, infrared sensors, and laser scattering sensors to detect the physical and chemical characteristics of fly ash; The abnormality detection and processing module analyzes whether there are abnormal humidity and abnormal fly ash agglomeration based on the real-time monitored humidity data and fly ash particle diameter data, and handles the abnormal situation; The fly ash processing module is used to control the fly ash processing equipment to process the fly ash, perform component residual detection after each processing step, and adjust the equipment parameters in real time according to the residual detection results; The parameter regression adjustment module is used to control the cloud data processing center to record and store parameter changes on the equipment side, and to perform regression adjustment on the equipment parameters of the fly ash treatment equipment according to a fixed period.

[0023] The AI ​​visual inspection module includes a physical feature detection unit, a chemical feature detection unit and a fly ash composition identification unit; the physical feature detection unit collects the morphology, color and particle diameter of fly ash particles through high-resolution industrial cameras and laser sensors; the chemical feature detection unit detects the chemical composition of fly ash particles through infrared sensors; the fly ash composition identification unit uses a convolutional neural network to analyze the composition of fly ash based on the collected fly ash particle data.

[0024] The abnormality detection and processing module includes a humidity abnormality detection unit, a fly ash particle abnormal agglomeration detection unit and an abnormal situation processing unit; the humidity abnormality detection unit collects the humidity in the fly ash processing equipment through the humidity sensor, compares and analyzes the collected humidity data with the set humidity threshold, and determines whether the humidity in the fly ash processing equipment is abnormal; the fly ash particle abnormal agglomeration detection unit compares the fly ash particle diameter with the set fly ash particle diameter threshold to determine whether the fly ash particles are abnormally agglomerated; the abnormal situation processing unit is used to handle abnormal situations according to the type of abnormal situation detected.

[0025] The fly ash treatment module includes a fly ash treatment unit, a residual amount detection unit and an equipment parameter update unit; the fly ash treatment unit detoxifies toxic substances in fly ash through low-temperature pyrolysis, removes salt components in fly ash through sedimentation rinsing, and removes heavy metals in fly ash through circulation rinsing; the residual amount detection unit is used to set a residual amount threshold, and compare the detected residual amount value with the set residual amount threshold to determine whether the residual amount of the treated component meets the standard; the equipment parameter update unit is used to update the equipment parameters of the fly ash treatment equipment in real time.

[0026] The parameter regression adjustment module includes a cloud data storage unit and an equipment parameter regression adjustment unit; the cloud data storage unit is used to record and store the number of fly ash treatments and equipment parameter changes; the equipment parameter regression adjustment unit is used to regularly regress and adjust the equipment parameters of the fly ash treatment equipment in the cloud data processing center.

[0027] Example 1: In step S1: the morphology, color and diameter of fly ash particles are collected by a high-resolution industrial camera and a laser sensor, and the spectral information of different fly ash particles is detected by an infrared sensor; the types of fly ash are analyzed based on the collected particle diameter and spectral information data using a convolutional neural network, and the fly ash particles are classified according to toxic substances, heavy metals, salt components and building material base components; and the proportion of each type of fly ash in the total amount of fly ash is detected and calculated, and the proportion of the collected toxic substances is recorded as q d =1%; the proportion of heavy metals is recorded as q j =1%; the proportion of salt components is recorded as q y =35%; the proportion of building material base material components is recorded as q c =63%.

[0028] In step S2: the fly ash particles are vibrated to prevent agglomeration through the vibrating screen, and the operating power of the vibrating screen is set to P when the equipment is started. z1 =300W; The humidity of fly ash particles is controlled by the dryer to prevent the fly ash particles from getting wet and sticking together, and the dryer operating power is set to P when the equipment is started. h1 =400W; Set the humidity threshold W max =5%, and the humidity W=4% in the fly ash processing equipment is collected in real time through the humidity sensor, and W is compared with W max Comparative analysis is performed to determine in real time whether the humidity in the fly ash treatment equipment exceeds the set humidity threshold; according to the collected data, W <W max , then it is judged that the humidity in the fly ash processing equipment is normal; While increasing the dryer power to control humidity, the fly ash particle diameter is detected abnormally; the collected fly ash particle diameter data is used to determine whether abnormal agglomeration occurs; the particle diameters of the fly ash particles detected in real time are {D1, D2, ..., D n}, set the fly ash particle diameter threshold to D max =100μm, the diameter of the fly ash particles detected is D i With D max For comparative analysis, if D i <D max , it is judged that there is no abnormal agglomeration of fly ash particles; if D i ≥D max , it is judged that the fly ash particles are abnormally agglomerated; where i=1, 2, ..., n; And according to the detection of different abnormal situations, different processing solutions are triggered: If W ≥ W max , D i <Dmax , it is judged that the humidity of the fly ash processing equipment is abnormally high but the fly ash particles are abnormally agglomerated, and only the instruction to increase the dryer power is issued to control the humidity; If W ≥ W max and D i ≥D max , it is determined that the humidity of the fly ash equipment is abnormal, and the fly ash particles are abnormally agglomerated; while issuing an instruction to increase the dryer power for humidity control, a further instruction to increase the vibrating screen power is issued to vibrate and separate the fly ash particles that are abnormally agglomerated; and an early warning of abnormal fly ash particle composition detection is issued; and the fly ash component ratio detected in step S1 is marked as abnormal data. After the vibrating screen separates the abnormally agglomerated fly ash particles, an instruction is issued to control the detection equipment to re-detect the composition of the fly ash particles, and the ratio of the amount of each fly ash component calculated by the re-detection to the total amount of fly ash is recorded as q d ′、q j ′、q y ′ and q c ′, the proportion of toxic substances is recorded as q d ′, the proportion of heavy metals is recorded as q j ′, the proportion of salt components is recorded as q y ′, the proportion of building material base material components is recorded as q c '; Real-time monitoring of the humidity data of the fly ash processing equipment and the abnormal agglomeration of fly ash particles can reduce the adhesion of fly ash particles caused by increased humidity and prevent the erroneous monitoring of fly ash composition caused by the agglomeration of fly ash particles.

[0029] In step S3, the fly ash particles are processed according to the following steps: S3-1. Detoxification of toxic substances contained in fly ash by low-temperature pyrolysis; S3-2, removing salt components from fly ash by sedimentation and rinsing; S3-3, removing heavy metals from fly ash by circulating rinsing; S3-4, collecting and storing the building material base material components contained in the treated fly ash for subsequent production of building materials; After each processing step, a component residual amount test is performed and a component residual amount threshold is set to control the component residual amount; the toxic substance residual amount threshold is set to q d0 =0.01%, set the salt component residual threshold q y0 =0.1%, set the heavy metal residue threshold to q j0 =0.01%; In step S3-1, a low-temperature pyrolysis process with a duration of Δt0 = 1h is set to detoxify the toxic substances in the fly ash; after the low-temperature pyrolysis process with a duration of Δt0 = 1h is completed, the residual amount of toxic substances in the treated fly ash is detected, and the residual amount of toxic substances in the fly ash is recorded as q d ′′=0.02%, then it can be determined that q d ′′>q d0 , it is judged that the residual amount of toxic substances in the fly ash is high, and an instruction is generated to control the processing equipment to increase the pyrolysis treatment time. The pyrolysis process is increased for a time of Δt=0.5h, and then the residual amount of toxic substances is detected again. If q is detected for the second time d ′′=0.009%, then it can be determined that q d ′′≤q d0 , enter the processing process of step S3-2, and record the total time of pyrolysis treatment , where m1=1, and the first treatment duration of the next fly ash pyrolysis treatment is set to 1.5h; In step S3-2, chemical additives are added to promote the precipitation of salt components. First, a chemical additive with a mass of s0 = 2 kg is added to perform the precipitation treatment of the salt components. After the first precipitation reaction and filtration, the residual amount of the salt components is detected and recorded as q y ′′=0.09%, then we can judge that q y ′′≤q y0 , it is determined that the residual amount of salt components meets the standard, and the process enters step S3-3; In step S3-3, firstly, set m0 = 6 cycles of rinsing process to process the heavy metals contained in the fly ash, and perform heavy metal residual detection after 6 cycles of rinsing, and record the heavy metal residual amount in the fly ash as q j ′′=0.09%, then it can be determined that q j ′′≤q j0 , it is determined that the residual heavy metal content in the fly ash meets the standard, and the processing process enters step S3-4.

[0030] In step S4: the number of times the fly ash treatment equipment performs fly ash treatment η is recorded in the cloud data processing center, and the parameter changes in the fly ash treatment equipment during each fly ash treatment process are recorded, and the equipment parameters of each fly ash treatment are recorded as A η The period of equipment parameter regression adjustment is set to k=4. After every four fly ash treatments, the cloud data processing center performs a regression adjustment of the equipment parameters based on the recorded equipment parameter changes. During the regression adjustment of the fly ash equipment treatment parameters, the number of times the equipment parameters change during the k-th fly ash treatment process is recorded as k1=3. The regression adjustment result of the equipment parameters is calculated using the following formula: ; Among them, A represents the equipment parameters after regression adjustment, A0 represents the initial equipment parameters set in the fly ash treatment equipment when fly ash treatment is not performed; the equipment parameters can represent the pyrolysis time, the number of rinses, and the chemical addition and quality; according to the monitoring results, during the four fly ash treatment processes, the parameter changes of the pyrolysis time were analyzed, A1 (Δt) = 1.5h, A2 (Δt) = 2h, A3 (Δt) = 2h, A4 (Δt) = 2.5h; then it can be calculated that A (Δt) = 1.75h; and in the process of parameter regression adjustment, if the adjusted parameter is the number of rinses, the calculation result of the equipment parameter regression adjustment is rounded up; then the parameter of the number of rinses is calculated, A1 (m3) = 7 times, A2 (m3) = 7 times, A3 (m3) = 8 times, A4 (m3) = 9 times; then A = 7.3125, rounding A up to obtain A (m3) = 8 times; After the equipment parameters are regressed and adjusted in the cloud data processing center, the number of regression adjustments of the equipment parameters and the equipment parameter values ​​after each regression adjustment are recorded and stored; and every time k2=10 equipment parameter regression adjustments are performed, the k2 adjusted equipment parameter adjustment results are compared and analyzed to determine whether the results of the k2 regression adjustments are the same. If it is detected that the k2 equipment parameter regression adjustment results are the same, an instruction is issued to control the fly ash treatment equipment to adjust the equipment parameters to the initial equipment parameters A0; if it is detected that the k2 equipment parameter adjustment results are all the initial equipment parameters, an instruction is issued to lower the initial equipment parameters of the fly ash treatment equipment and adjust the initial equipment parameters to A0′=p A0, where p = 80%; by setting a fixed-period equipment parameter regression adjustment in the cloud data processing center, the equipment parameters can be adjusted after a cycle of fly ash treatment process, solving the problem of increasingly high parameter values ​​generated during real-time adjustment of equipment parameters at the equipment end according to the fly ash treatment situation, and preventing energy waste and lengthy processing time caused by the continuous increase in equipment parameters. Regular parameter regression improves the working efficiency of fly ash treatment equipment.

[0031] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A fly ash treatment equipment operation control method based on AI vision, characterized by: The following steps are involved: S1. Use high-resolution industrial cameras, infrared sensors, and laser scattering sensors to collect fly ash information and extract fly ash characteristic data; S2. Analyze whether humidity anomalies and fly ash agglomeration abnormalities occur based on the real-time detected humidity data and fly ash particle diameter data, and handle the abnormalities; S3. Process the fly ash using fly ash processing equipment, test the residual amount of components after each processing step, and adjust equipment parameters in real time based on the residual amount test results; S4. Record and store equipment parameter changes in the cloud data processing center, and perform regression adjustments on the equipment parameters of the fly ash processing equipment at a fixed period.

2. The AI ​​vision-based fly ash treatment equipment operation control method according to claim 1, characterized in that: In step S1: the morphology, color and diameter of fly ash particles are collected by high-resolution industrial cameras and laser sensors, and the spectral information of different fly ash particles is detected by infrared sensors; the types of fly ash are analyzed based on the collected particle diameter and spectral information data using a convolutional neural network, and the fly ash particles are classified according to toxic substances, heavy metals, salt components and building material base components; the proportion of each type of fly ash in the total amount of fly ash is detected and calculated, and the proportion of toxic substances is recorded as q d ; The proportion of heavy metals is denoted as q j ; The proportion of salt components is recorded as q y ; The proportion of building material base material components is recorded as q c .

3. The fly ash treatment equipment operation control method based on AI vision according to claim 1, characterized in that: In step S2: the fly ash particles are vibrated to prevent agglomeration through the vibrating screen, and the operating power of the vibrating screen is set to P when the equipment is started. z1 ; The humidity of fly ash particles is controlled by the dryer, and the dryer operating power is set to P when the equipment is started. h1 ; According to the detected fly ash characteristic data and the humidity data in the fly ash processing equipment, abnormal conditions are detected and processed; in the abnormal condition detection process, first, the humidity threshold W is set max , the humidity W in the fly ash processing equipment is collected in real time through the humidity sensor, and W is compared with W max Perform comparative analysis to determine in real time whether the humidity in the fly ash processing equipment exceeds the set humidity threshold; if W <W max , judge that the humidity in the fly ash treatment equipment is normal; if W≥W max If the humidity in the fly ash processing equipment is abnormally high, an abnormal humidity warning is issued, and an instruction is issued to increase the operating power of the dryer by ΔP h ; While issuing a command to increase the operating power of the dryer for humidity control, the particle diameter of the fly ash is detected for abnormality; the collected fly ash particle diameter data is used to determine whether abnormal agglomeration occurs; the particle diameter of the fly ash particles detected in real time is {D1, D2, ..., D n }, set the fly ash particle diameter threshold to D max , the detected fly ash particle diameter D i With D max For comparative analysis, if D i <D max , judge that there is no abnormal agglomeration of fly ash particles; if D i ≥D max , to determine if fly ash particles are agglomerated abnormally; where i = 1, 2, ..., n; Different processing solutions are triggered based on the detected anomalies: If W ≥ W max and D i <D max , if it is determined that the humidity of the fly ash processing equipment is abnormally high but there is no abnormal agglomeration of fly ash particles, only an instruction to increase the operating power of the dryer is issued to control the humidity; If W ≥ W max and D i ≥D max , it is judged that the humidity of the fly ash equipment is abnormal and the fly ash particles are abnormally agglomerated; then, while issuing a command to increase the dryer power for humidity control, a further command is issued to increase the operating power of the vibrating screen by ΔP z ; and issue an early warning of abnormal fly ash particle composition detection; The fly ash component ratio detected in step S1 is marked as abnormal data. After the vibrating screen separates the abnormally agglomerated fly ash particles, an instruction is issued to control the detection equipment to re-detect the components of the fly ash particles. The ratio of the amount of each fly ash component calculated by the re-detection to the total amount of fly ash is recorded as q d ′、q j ′、q y ′ and q c ′, the proportion of toxic substances is recorded as q d ′, the proportion of heavy metals is recorded as q j ′, the proportion of salt components is recorded as q y ′, the proportion of building material base material components is recorded as q c ′.

4. The AI ​​vision-based fly ash treatment equipment operation control method according to claim 1, characterized in that: In step S3, the fly ash processing equipment processes the fly ash particles according to the following steps: S3-1. Detoxification of toxic substances contained in fly ash by low-temperature pyrolysis; S3-2, removing salt components from fly ash by sedimentation and rinsing; S3-3, removing heavy metals from fly ash by circulating rinsing; S3-4, collecting and storing the building material base material components contained in the treated fly ash for subsequent production of building materials; After each processing step, a component residual amount test is performed and a component residual amount threshold is set to control the component residual amount; the toxic substance residual amount threshold is set to q d0 , set the salt component residual threshold q y0 , set the heavy metal residue threshold to q j0 ; In step S3-1, a low-temperature pyrolysis process with a duration of Δt0 is set to detoxify the toxic substances in the fly ash; after the low-temperature pyrolysis process with a duration of Δt0 is completed, the residual amount of toxic substances in the treated fly ash is detected, and the residual amount of toxic substances in the fly ash is recorded as q d ′′, and q d ′′ is compared with the set toxic substance residual threshold. If q d ′′≤q d0 If it is determined that the residual amount of toxic substances in the fly ash meets the standard, the process proceeds to step S3-2; If q d ′′>q d0 , it is judged that the residual amount of toxic substances in the fly ash is high, then an instruction is generated to control the processing equipment to increase the pyrolysis treatment time, add a pyrolysis process of Δt, and then perform the toxic substance residual detection until q is detected. d ′′≤q d0 Then enter the process of step S3-2 and record the total time of pyrolysis treatment , where m1 represents the number of times the pyrolysis treatment time Δt is increased, and the first treatment time of the next fly ash pyrolysis treatment is set to Δt′; In step S3-2, chemical additives are added to promote the precipitation of salt components. First, a chemical additive with a mass of s0 is added to perform the precipitation treatment of the salt components. After the first precipitation reaction and filtration, the residual amount of the salt components is detected and recorded as q y ′′, if q y ′′≤q y0 , it is judged that the residual amount of salt components meets the standard, then the process enters step S4-3; if q y ′′>q y0 If it is judged that the residual amount of salt components is high, an instruction is generated to control the processing equipment to add a chemical additive with a mass of Δs to precipitate the salt components again, and then the residual amount of salt components is detected again until q y ′′≤q y0 , then enter the processing process of step S3-3, and record the total mass of the added chemical additives , where m2 represents the number of times the chemical additive with a mass of Δs is added; and the mass of the chemical additive added for the first time during the precipitation and rinsing process of the next fly ash treatment is set to s′; In step S3-3, firstly, a rinsing process of m0 times is set to process the heavy metals contained in the fly ash, and the residual amount of heavy metals is detected after m0 times of rinsing, and the residual amount of heavy metals in the fly ash is recorded as q j '', change q j ′′ is compared with the set heavy metal residue threshold. If q j ′′≤q j0 If it is determined that the residual heavy metal content meets the standard, the process proceeds to step S3-4; If q j ′′>q j0 If it is judged that the residual amount of heavy metals is high, an instruction is generated to control the processing equipment to add a cycle rinse to process the residual heavy metals, and then the residual amount of heavy metals is detected again until q j ′′≤q j0 , then enter the processing process of step S3-4, and record the final cycle rinsing times m3, and set the first cycle rinsing times of the next fly ash treatment process to m3.

5. The AI ​​vision-based fly ash treatment equipment operation control method according to claim 1, characterized in that: In step S4: the number of times the fly ash treatment equipment performs fly ash treatment η is recorded in the cloud data processing center, and the parameter changes in the fly ash treatment equipment during each fly ash treatment process are recorded, and the equipment parameters of each fly ash treatment are recorded as A η The period of equipment parameter regression adjustment is set to k. After every k fly ash treatments, the cloud data processing center performs a regression adjustment of the equipment parameters based on the recorded equipment parameter changes. During the regression adjustment of the fly ash equipment treatment parameters, the number of times the equipment parameters change during the k fly ash treatments is recorded as k1. The regression adjustment result of the equipment parameters is calculated using the following formula: ； Wherein, A represents the equipment parameter after regression adjustment, and A0 represents the initial equipment parameter set in the fly ash treatment equipment before fly ash treatment is performed; during the parameter regression adjustment process, if the adjusted parameter is the number of rinses, the calculation result of the equipment parameter regression adjustment is rounded up; After the cloud data processing center makes regression adjustments to the equipment parameters, it records and stores the number of regression adjustments of the equipment parameters and the equipment parameter values ​​after each regression adjustment; and every time k2 equipment parameter regression adjustments are made, the k2 adjusted equipment parameter adjustment results are compared and analyzed to determine whether the k2 regression adjustment results are the same. If it is detected that the k2 equipment parameter regression adjustment results are the same, an instruction is issued to control the fly ash processing equipment to adjust the equipment parameters to the initial equipment parameter A0; if it is detected that the k2 equipment parameter adjustment results are all the initial equipment parameter A0, an instruction is issued to lower the initial equipment parameter of the fly ash processing equipment and adjust the initial equipment parameter to A0′=p A0, where p is the proportional coefficient set by the system, and 0 <p<1。 6. An AI vision-based fly ash treatment equipment operation control system, characterized by: The system includes: AI visual detection module, anomaly detection and processing module, fly ash processing module, and parameter regression adjustment module; The AI ​​visual inspection module uses a high-resolution industrial camera, an infrared sensor, and a laser scattering sensor to detect the physical and chemical characteristics of fly ash. The abnormality detection and processing module analyzes whether humidity abnormality and fly ash abnormal agglomeration occur based on the real-time monitored humidity data and fly ash particle diameter data, and processes the abnormality; The fly ash processing module is used to control the fly ash processing equipment to process the fly ash, perform component residual detection after each processing step, and adjust the equipment parameters in real time according to the residual detection results; The parameter regression adjustment module is used to control the cloud data processing center to record and store parameter changes on the equipment side, and to perform regression adjustment on the equipment parameters of the fly ash processing equipment according to a fixed period.

7. The AI ​​vision-based fly ash processing equipment operation control system according to claim 6, characterized in that: The AI ​​visual inspection module includes a physical feature detection unit, a chemical feature detection unit and a fly ash composition identification unit; the physical feature detection unit collects the morphology, color and particle diameter of fly ash particles through a high-resolution industrial camera and a laser sensor; the chemical feature detection unit detects the chemical composition of fly ash particles through an infrared sensor; and the fly ash composition identification unit uses a convolutional neural network to analyze the composition of fly ash based on the collected fly ash particle data.

8. The AI ​​vision-based fly ash processing equipment operation control system according to claim 6, characterized in that: The abnormality detection and processing module includes a humidity abnormality detection unit, a fly ash particle abnormal agglomeration detection unit and an abnormal situation processing unit; the humidity abnormality detection unit collects the humidity in the fly ash processing equipment through a humidity sensor, compares and analyzes the collected humidity data with the set humidity threshold, and determines whether the humidity in the fly ash processing equipment is abnormal; the fly ash particle abnormal agglomeration detection unit compares the fly ash particle diameter with the set fly ash particle diameter threshold to determine whether the fly ash particles are abnormally agglomerated; the abnormal situation processing unit is used to perform abnormal situation processing according to the type of abnormal situation detected.

9. The AI ​​vision-based fly ash treatment equipment operation control system according to claim 6, characterized in that: The fly ash processing module includes a fly ash processing unit, a residual amount detection unit and an equipment parameter updating unit; the fly ash processing unit detoxifies toxic substances in fly ash through low-temperature pyrolysis, removes salt components in fly ash through sedimentation rinsing, and removes heavy metals in fly ash through circulation rinsing; the residual amount detection unit is used to set a residual amount threshold, and compare the detected residual amount value with the set residual amount threshold to determine whether the residual amount of the treated component meets the standard; the equipment parameter updating unit is used to update the equipment parameters of the fly ash processing equipment in real time.

10. The AI ​​vision-based fly ash processing equipment operation control system according to claim 6, characterized in that: The parameter regression adjustment module includes a cloud data storage unit and an equipment parameter regression adjustment unit; the cloud data storage unit is used to record and store the number of fly ash treatments and equipment parameter changes; the equipment parameter regression adjustment unit is used to regularly regress and adjust the equipment parameters of the fly ash treatment equipment in the cloud data processing center.

Images