An AI-driven enterprise economic cost intelligent management and control method and system

Abstract

This application relates to an AI-driven intelligent management method and system for enterprise economic costs. The method includes acquiring combustion parameters of a mixture in a fixed area on a transport line, including moisture content, combustible composition, ash content, and density. The method calculates the calorific value of the mixture in the corresponding fixed area using these parameters, obtaining a reference calorific value. It then calculates an adjustment ratio based on the set and reference calorific values, calculates supplementary materials and their dosage based on the adjustment ratio, and delivers the determined amount of supplementary materials to the corresponding fixed area on the transport line. This AI-driven intelligent management method and system for enterprise economic costs, by determining the composition and volume of waste fed into the incinerator, more accurately calculates the calorific value, thereby ensuring stable incineration and achieving better economic benefits.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an AI-driven intelligent management method and system for enterprise economic costs. Background Technology

[0002] AI-driven intelligent management of enterprise economic costs is based on using full-domain data, predictive algorithms, and real-time decision-making to transform cost management from "post-event accounting" into a closed loop of "pre-event prediction, in-event control, and post-event optimization." Taking waste incineration as an example, through automated control of the incineration process, it is possible to solve problems such as large fluctuations in the calorific value of waste, difficulty in controlling combustion, and high consumption of environmental protection materials. This can lead to increased power generation per ton of waste, reduced material consumption, reduced plant power consumption, and reduced labor costs.

[0003] Specifically, the core problem of waste incineration lies in the instability of the combustion parameters (calorific value, moisture, non-combustible materials, etc.) of the fed waste. This leads to unstable furnace temperature when using experience-based control. At the same time, experience-based control also has a certain lag, which can easily cause system fluctuations due to excessive adjustment. How to solve this problem requires further research. Summary of the Invention

[0004] This application provides an AI-driven intelligent management method and system for enterprise economic costs. By determining the composition and calculating the volume of the waste fed into the furnace, the calorific value of combustion can be calculated more accurately, thereby ensuring the stability of the incineration process and achieving better economic benefits.

[0005] The above-mentioned objective of this application is achieved through the following technical solution: Firstly, this application provides an AI-driven intelligent management and control method for enterprise economic costs, including: The combustion parameters of the mixture in a fixed area on the transport line are obtained. The combustion parameters include moisture content, combustible composition, ash content and density. The calorific value of the mixture in the corresponding fixed division area is calculated using the combustion parameters of the mixture to obtain the reference calorific value; The adjustment ratio is calculated based on the set calorific value and the reference calorific value; Calculate the supplement and its usage based on the adjustment ratio, and then place the determined amount of supplement into the corresponding fixed area on the transport line.

[0006] In one possible implementation of the first aspect, determining the density parameter among the combustion parameters includes: Acquire an image of the transportation line, and denote it as the analysis image; The transport lines in the image are extracted and divided to obtain fixed division regions; Calculate the height distribution parameter set of a fixed region; The volume parameters of the fixed-division region are calculated using the height distribution parameter set of the fixed-division region, and the density parameters are calculated based on the volume parameters and weight parameters. The calculation of the height distribution parameter set of the fixed division region also includes removing floating dust interference.

[0007] In one possible implementation of the first aspect, removing dust interference includes: Calculate the position coordinates of the reflection point based on the transmission and reception parameters; The position coordinates of the reflection point are filtered once using a predetermined height area to obtain the first filtered position coordinates; The coordinates of the first-stage selection are filtered using the intensity parameter to obtain the coordinates of the second-stage selection. The coordinates of the secondary selection are filtered using an adaptive distance parameter to obtain the coordinates of the tertiary selection.

[0008] In one possible implementation of the first aspect, using intensity parameters to filter the primary screening location coordinates and obtain the secondary screening coordinates includes: Divide the altitude into multiple altitude zones; Calculate the first average signal reflection intensity for each height range; When the difference between the first average signal reflection intensity of two adjacent height intervals is greater than the set reference value, the height interval with the smaller first average signal reflection intensity is discarded.

[0009] In one possible implementation of the first aspect, when discarding the height range with a lower first average signal reflection intensity, the method further includes: Divide the height range where the first average signal reflection intensity is relatively low into unit spaces: Calculate the second average signal reflection intensity for each unit space; Calculate the dispersion of the second average signal reflection intensity and obtain the dispersion result; The unit space is partially preserved based on the dispersion results.

[0010] In one possible implementation of the first aspect, using an adaptive distance parameter to filter the secondary selection location coordinates and obtain the tertiary selection coordinates includes: By statistically analyzing the average distance values ​​of the secondary selection location coordinates, a distance distribution parameter set is obtained; The secondary screening location coordinates are grouped according to the distance distribution parameter group to obtain multiple secondary screening location coordinate groups; Use secondary filtering of location coordinates to group and construct the height distribution of corresponding fixed division regions; Obtain the surface image of the fixed-division region; The surface images and height distributions of the fixed-division regions are compared to obtain the comparison results; Get all comparison results; Use one or more distance distribution parameter sets corresponding to the smallest comparison result as the coordinates for the third selection.

[0011] In one possible implementation of the first aspect, comparing the surface image of the fixed-division region and the height distribution of the fixed-division region includes: Determine the first peak point corresponding to the height distribution of the fixed division region. The first peak point includes the first peak point and the first valley point. Determine the second peak point corresponding to the surface image of the fixed division region. The second peak point includes the second peak point and the second valley point. Calculate the average distance difference between the first peak and the second peak.

[0012] Secondly, this application provides an AI-driven intelligent management and control device for enterprise economic costs, comprising: The data acquisition unit is used to acquire the combustion parameters of the mixture in a fixedly divided area on the transport line. The combustion parameters include moisture content parameters, combustible composition parameters, ash content parameters, and density parameters. The first calculation and processing unit is used to calculate the calorific value of the mixture in a corresponding fixed division area using the combustion parameters of the mixture, and obtain a reference calorific value; The second calculation and processing unit is used to calculate the adjustment ratio value based on the set calorific value and the reference calorific value; The adjustment unit is used to calculate the supplement and the amount of supplement based on the adjustment ratio and to deliver the determined amount of supplement to the corresponding fixed area on the transport line.

[0013] Thirdly, this application provides an AI-driven intelligent management and control system for enterprise economic costs, the system comprising: One or more memories for storing instructions; and One or more processors are configured to call and execute the instructions from the memory to perform the methods described in the first aspect and any possible implementation thereof.

[0014] Fourthly, this application provides a computer-readable storage medium, the computer-readable storage medium comprising: The program, when run by a processor, is executed as described in the first aspect and any possible implementation thereof.

[0015] Fifthly, this application provides a computer program product, including program instructions that, when run by a computing device, execute the method described in the first aspect and any possible implementation thereof.

[0016] Sixthly, this application provides a chip system including a processor for implementing the functions involved in the foregoing aspects, such as generating, receiving, transmitting, or processing the data and / or information involved in the foregoing methods.

[0017] This chip system can consist of chips or include chips and other discrete components.

[0018] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means, or the processor and the memory can be coupled to the same device. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of an AI-driven intelligent management and control method for enterprise economic costs provided in this application.

[0020] Figure 2 This is a schematic diagram illustrating the adjustment of calorific value over time, as provided in this application.

[0021] Figure 3 This is a schematic diagram of a fixed division of regions provided in this application.

[0022] Figure 4 This is a comparative schematic diagram of a predicted surface and an actual surface provided in this application.

[0023] Figure 5 This is a schematic diagram illustrating the principle of calculating the position coordinates of a reflection point based on transmission and reception parameters, as provided in this application.

[0024] Figure 6 This is a schematic diagram of the location of a height-limiting scraper provided in this application.

[0025] Figure 7 This is a schematic diagram of a method for filtering position coordinates using intensity parameters, as provided in this application.

[0026] Figure 8 This is a schematic diagram of a region division along the same height direction provided in this application.

[0027] Figure 9 This is a schematic diagram illustrating a further division of a rectangle as provided in this application. Detailed Implementation

[0028] The technical solutions in this application will be further described in detail below with reference to the accompanying drawings.

[0029] This application discloses an AI-driven intelligent management and control method for enterprise economic costs. Please refer to [link / reference]. Figure 1 In some examples, the AI-driven intelligent management and control method for enterprise economic costs disclosed in this application includes the following steps: S101, Obtain the combustion parameters of the mixture in the fixedly divided area on the transport line. The combustion parameters include moisture content parameters, combustible composition parameters, ash content parameters, and density parameters. S102, use the combustion parameters of the mixture to calculate the calorific value of the mixture in the corresponding fixed division area to obtain the reference calorific value; S103, calculate and adjust the ratio value based on the set calorific value and the reference calorific value; S104, calculate the supplement and the amount of supplement based on the adjustment ratio, and place the supplement with the determined amount into the corresponding fixed area on the transport line.

[0030] First, it needs to be clarified that the intelligent management and control of enterprise economic costs here refers to determining the combustion parameters of the waste fed into the waste incinerator during waste incineration, and then formulating appropriate management and control methods. Specifically, waste as fuel has an extremely complex and unstable composition. The goal of management and control is to make the actual calorific value of the fuel fed into the furnace infinitely close to the set calorific value required for the optimal operating conditions of the waste incinerator.

[0031] In traditional models, excessive amounts of auxiliary fuels such as oil or natural gas are often added to ensure combustion. AI, by accurately calculating the "replenishment usage," enables on-demand addition, avoiding waste of auxiliary fuels and significantly reducing operating costs.

[0032] The main disadvantages of the traditional model are unstable calorific value (in order to ensure furnace temperature, a large amount of auxiliary fuels such as fuel oil or natural gas are often required, which not only significantly increases the operating costs of enterprises, but also directly reduces the net energy recovery efficiency of incineration power generation; when the calorific value is too high or fluctuates drastically, it is easy to cause local overheating and coking in the furnace, affecting the safe and stable operation of the equipment) and high emission risk (dioxins are most likely to be generated in the temperature range of 200℃-400℃ and when combustion is incomplete; unstable furnace temperature control or local oxygen deficiency and smoldering increase the probability of the formation of highly toxic substances such as dioxins; when combustion is incomplete, the gasification and migration of heavy metals leads to excessive exhaust gas) and serious equipment wear (the sudden change in furnace temperature, coking and corrosion caused by combustion fluctuations will significantly increase the failure rate of the equipment).

[0033] As can be seen from the above, it is impossible to ensure the stable operation of the combustion process by simply adjusting the amount of waste input. At the same time, it is also difficult to ensure the stability of the calorific value of the waste through waste sorting, because waste sorting will increase the upfront costs, storage costs and transportation costs of waste treatment.

[0034] The solution used in this application is to calculate the calorific value of the mixture on the transport line by means of combustion parameters, then calculate the adjustment ratio value based on the set calorific value and the reference calorific value, and finally calculate the supplement and the amount of supplement based on the adjustment ratio value and put the determined amount of supplement into the corresponding fixed division area on the transport line.

[0035] The advantage of this method is that, without adjusting the way the mixture is fed into the waste incinerator, the calorific value of the mixture on the transport line can be specifically adjusted to ensure the stability of the calorific value. A stable calorific value will lead to a stable incineration process in the waste incinerator.

[0036] like Figure 2 As shown, when the calorific value of the mixture is insufficient, it is supplemented by adding high-calorific-value waste, auxiliary fuel, or combustion improver to the mixture on the transport line. When the calorific value of the mixture is too high, the mixing speed is appropriately reduced to bring the calorific value back to the required value.

[0037] Specifically, in step S101, firstly, the combustion parameters of the mixture in the fixedly divided area on the transport line are obtained. The combustion parameters are moisture content parameters, combustible composition parameters, ash content parameters, and density parameters. Specifically: Moisture content parameter refers to the proportion of water in a mixture. Since water is an ineffective component in fuel, it will reduce the calorific value of the mixture. This is because the higher the moisture content, the more latent heat the fuel consumes to evaporate the water during combustion, and the lower the effective calorific value that can actually be used to do work.

[0038] Combustible composition parameters refer to the proportion of combustibles, which are the decisive parameters that determine the theoretical calorific value of a mixture.

[0039] Ash content refers to the non-combustible components in a mixture. A higher ash content means less combustible material per unit mass of fuel, and the calorific value decreases inversely. It is a negative weight that must be deducted when calculating the calorific value.

[0040] Density is an important reference value for calculations because calorific value is usually measured in "unit mass" (e.g., kJ / kg), and mass calculations are performed using density.

[0041] Moisture content parameters are obtained using microwave moisture sensors or infrared moisture sensors.

[0042] The working principle of microwave moisture sensors is based on the high dielectric constant of water (the dielectric constant of water is about 75, which is much higher than that of ordinary fiber or coal, which is about 2.5). When microwaves penetrate the material, the proportion of moisture in the material will strongly affect the overall dielectric constant.

[0043] The working principle of an infrared moisture sensor is based on the principle of infrared absorption. In the near-infrared spectral region, infrared radiation energy of specific wavelengths is selectively absorbed by water molecules, while radiation energy of the central wavelength is hardly absorbed. The sensor characterizes the moisture content of a material by measuring the difference in energy absorbed when infrared light passes through it.

[0044] Combustible material composition parameters are acquired using spectral sensors (such as near-infrared spectroscopy (NIRS) and laser-induced breakdown spectroscopy (LIBS). These sensors operate on the principle of the interaction between matter and light; when a light source illuminates a sample, different chemical components produce unique absorption, reflection, or emission spectra for specific wavelengths of light. After capturing these spectral characteristics, the detector can quantitatively analyze the concentration of each component in the mixture.

[0045] For example, the composition of a combustible material is used to obtain the concentrations of carbon, hydrogen, and oxygen, and then the calorific value is calculated based on these concentrations.

[0046] The ash content parameter is obtained by X-ray transmission and natural gamma sensor. The working principle is that the average atomic number of combustible organic matter is low (about 6), while the average atomic number of ash (oxides of silicon, aluminum, calcium, iron, etc.) is high (greater than 12).

[0047] The material is irradiated with dual gamma rays, namely a low-energy americium (Am) source and a medium-energy cesium (Cs) source. The low-energy rays are sensitive to ash content, while the medium-energy rays are used to eliminate the influence of material thickness and density. The ash content can be linearly derived by calculating the ratio of characteristic parameters after dual-source absorption.

[0048] In step S102, the calorific value of the mixture in the corresponding fixed division area is calculated using the combustion parameters of the mixture to obtain a reference calorific value. The formula for the reference calorific value is as follows: Reference calorific value = calorific value of combustible material - heat consumption for moisture evaporation - heat consumption for ash temperature rise - heat consumption for hydrogen combustion to produce water evaporation.

[0049] In step S103, an adjustment ratio value is calculated based on the set calorific value and the reference calorific value, such as... Figure 2 As shown, when the added calorific value is insufficient, it is supplemented; when the added calorific value is too high, the addition rate of the mixture is appropriately reduced to bring the added calorific value back to the required calorific value.

[0050] Finally, in step S104, the supplement and the amount of supplement are calculated according to the adjustment ratio, and the supplement with the determined amount is placed in the corresponding fixed area on the transport line. The supplement here is generally high-calorific-value waste that has been screened separately. Of course, it is also possible to choose to inject combustion oil into the combustion furnace for supplementation.

[0051] It should be added that there are generally 2-3 detection points for each parameter (moisture content, combustible composition, ash content), and one corresponding sensor is deployed at each detection point for detection.

[0052] In some cases, the density parameter in the combustion parameters is determined in the following ways: S201, acquire an image of the transport line, denoted as the analysis image; S202, Extract and analyze the transport lines in the image and divide the transport lines to obtain fixed division regions; S203, Calculate the height distribution parameter set of the fixed division region; S204, use the height distribution parameter set of the fixed division region to calculate the volume parameter of the fixed division region and calculate the density parameter based on the volume parameter and weight parameter; The calculation of the height distribution parameter set of the fixed division region also includes removing floating dust interference.

[0053] Combination Figure 3 Here, the transport line is divided using image analysis to obtain fixed division regions. After obtaining the fixed division regions, the height distribution parameter set of the fixed division regions is calculated, and the density parameter is calculated using the height distribution parameter set and the composition.

[0054] Extract and analyze transport lines from the image, as follows: Image enhancement: First, the acquired analysis images are converted to grayscale, adaptive histogram equalization (to improve contrast), and noise reduction is performed to eliminate uneven lighting or dust interference.

[0055] ROI extraction: By using the approximate location information of a fixed track and the YOLO segmentation model to classify the image, the "transportation line region" is accurately cropped out, and the surrounding irrelevant background environment is blocked out.

[0056] Next, the height distribution parameter set of the fixed division area is calculated. The height distribution parameter set refers to the set of height values ​​at different locations on the fixed division area. These height values ​​represent the different height values ​​at various locations on the fixed division area.

[0057] Finally, the volume parameters of the fixed division area are calculated using the height distribution parameter set of the fixed division area, and the density parameters are calculated based on the volume parameters and weight parameters. The weight parameters are obtained by the sensors on the overhead crane. The weight of the garbage grabbed each time the overhead crane is working is known, so the density parameters can be calculated using the volume parameters and weight parameters.

[0058] Density parameter = weight parameter / volume parameter.

[0059] When calculating the height distribution parameter set of a fixed region, it is necessary to remove dust interference. This is because obtaining the height distribution parameter set requires the use of a lidar system, and the detection signal emitted by the lidar will be reflected when it encounters dust. Figure 4 As shown, this situation can lead to the generation of an incorrect set of height distribution parameters.

[0060] In some cases, the methods for removing dust interference are as follows: Calculate the position coordinates of the reflection point based on the transmission and reception parameters; The position coordinates of the reflection point are filtered once using a predetermined height area to obtain the first filtered position coordinates; The coordinates of the first-stage selection are filtered using the intensity parameter to obtain the coordinates of the second-stage selection. The coordinates of the secondary selection are filtered using an adaptive distance parameter to obtain the coordinates of the tertiary selection.

[0061] The method for calculating the position coordinates of the reflection point based on the transmission and reception parameters is as follows: Figure 5 As shown, the transmission and reception times of the detection signal are known, therefore the propagation time of the detection signal is the reception time minus the transmission time; the propagation speed of the detection signal is also known, and the propagation distance R can be calculated. ; The launch parameters used include the physical spatial coordinates of the launch point, the horizontal launch angle (azimuth α), and the vertical launch angle (elevation β).

[0062] Using the conversion formula from spherical coordinates to rectangular coordinates, the three-dimensional position of the reflection point relative to the sensor coordinate system can be calculated: X-axis coordinate: X=X0+R×cos(β)×cos(α)X= X0+R×cos(β)×cos(α); Y-axis coordinate: Y=Y0+R×cos(β)×sin(α)Y= Y0+R×cos(β)×sin(α); Z-axis coordinate: Z = Z0 + R × sin(β) X0, Y0, Z0 are the known absolute coordinates of the sensor's emission point in space. Finally, using a pre-calibrated rotation matrix and translation vector, the coordinates (X, Y, Z) of the reflection point in the sensor coordinate system are converted into absolute coordinates in the physical coordinate system of the transport line.

[0063] Then the obtained position coordinates are filtered. The filtering is done in three steps. The first step is to use a predetermined height area to filter the position coordinates of the reflection point to obtain the first set of filtered position coordinates. The predetermined height area here refers to the maximum height of the mixture on the transport line. This maximum height is controlled by a height-limiting scraper. When the mixture on the transport line passes the height-limiting scraper, any portion exceeding the scraper will be blocked and moved backward on the transport line (opposite to the working direction). The relevant content regarding using the predetermined height area to filter the position coordinates of the reflection point is as follows... Figure 6 As shown, the portion above the dashed line is outside the predetermined height area and is directly discarded.

[0064] Next, the intensity parameter is used to filter the coordinates of the first-stage filter to obtain the coordinates of the second-stage filter. The specific method is as follows: Divide the altitude into multiple altitude zones; Calculate the first average signal reflection intensity for each height range; When the difference between the first average signal reflection intensity of two adjacent height intervals is greater than the set reference value, the height interval with the smaller first average signal reflection intensity is discarded.

[0065] The specific principle behind this method is that there is a difference in physical density between floating dust and real materials, which leads to a significant discontinuity in the intensity of reflected signals. Real materials have a strong ability to reflect signals, resulting in high intensity of reflected signals. For floating dust, most signals will penetrate or undergo diffuse reflection, resulting in extremely low intensity of reflected signals.

[0066] The purpose of dividing the vertical space (from the ground to the highest point) into multiple height intervals is to divide the vertical space detected by the sensor into several horizontal "slices" or "thin layers", which is equivalent to establishing a Z-axis coordinate system for space.

[0067] Calculating the average intensity of all reflection points within each "slice" smooths the data, eliminates random errors caused by individual noise points, and reflects the overall material density characteristics of that height layer.

[0068] On top of a real material pile, there is usually a layer of dust. When the system scans from bottom to top (or from top to bottom), it will inevitably go through a transition from "high-density material" to "low-density dust". When the intensity difference between two adjacent layers suddenly increases (greater than the set reference value), it means that this is the physical boundary between the material surface and the dust layer.

[0069] The layer with lower intensity above (or below, depending on the scanning direction) the boundary line is judged by the system as a pure dust layer and is directly removed, such as... Figure 7 As shown.

[0070] In actual work, areas are also divided along the same vertical axis, specifically as follows: Figure 8 As shown, each fixed division area is divided into multiple (MxN) rectangles, which can be viewed as these rectangles moving in the height direction.

[0071] The reason for dividing the mixture into multiple (MxN) rectangles is that the surface height distribution of the mixture is uneven, meaning that it cannot be described using a single height value.

[0072] When calculating the first average signal reflection intensity for each height interval, it is necessary to divide the data into multiple (MxN) rectangles for the calculation. The height of the height interval is controlled between 1-3cm, and the rectangles are generally squares with a side length controlled between 2-4cm.

[0073] When discarding height ranges with relatively low first average signal reflection intensity, the following additional steps were added: Divide the height range where the first average signal reflection intensity is relatively low into unit spaces: Calculate the second average signal reflection intensity for each unit space; Calculate the dispersion of the second average signal reflection intensity and obtain the dispersion result; The unit space is partially preserved based on the dispersion results.

[0074] Specifically, in the previous steps, the interface between dust and material was found by looking for the "intensity cliff" (the difference is greater than the reference value), and the area with the lower overall intensity was identified as the "suspected dust area".

[0075] In reality, the dust zone is often not pure dust, but a transitional zone where dust and real materials are mixed. If it is completely discarded, it is easy to accidentally delete the real material surface.

[0076] Dispersion represents the "uniformity" or "fluctuation" of matter density within a space; specifically: Pure dust region: The particles are small and evenly distributed, the signal strength is extremely stable, and the dispersion is extremely low.

[0077] Material and dust mixing area / real material area: Due to the presence of material blocks of varying sizes, pores, or surface undulations, the signal strength fluctuates and has a high degree of dispersion.

[0078] By setting a dispersion threshold, units with dispersion higher than the threshold are retained, while units with dispersion too low are removed, thus accurately removing pure dust and retaining the real material.

[0079] This mechanism successfully filters out pure dust interference that, although located in the material area, has a weak and stable signal, while retaining the actual material surface points where the signal is generally weak but exhibits significant local intensity fluctuations. Here, we take... Figure 8 and Figure 9 For reference, this involves further subdividing the rectangle, typically retaining only points, with the area of ​​each point controlled between 0.1-0.2 cm². 2 The heights of these points can be directly added to the height distribution parameter set.

[0080] In some examples, the adaptive distance parameter is used to filter the secondary selection coordinates and obtain the tertiary selection coordinates as follows: By statistically analyzing the average distance values ​​of the secondary selection location coordinates, a distance distribution parameter set is obtained; The secondary screening location coordinates are grouped according to the distance distribution parameter group to obtain multiple secondary screening location coordinate groups; Use secondary filtering of location coordinates to group and construct the height distribution of corresponding fixed division regions; Obtain the surface image of the fixed-division region; The surface images and height distributions of the fixed-division regions are compared to obtain the comparison results; Get all comparison results; Use one or more distance distribution parameter sets corresponding to the smallest comparison result as the coordinates for the third selection.

[0081] It should be noted that in the previous steps, most of the pure dust and obvious noise have been removed through "intensity cliff" and "dispersion analysis", resulting in "secondary screening coordinates". However, at this point, some extremely difficult-to-distinguish floating dust or dust may still be attached near the material surface. If a fixed distance threshold is continued to be used, it is very easy to cause misjudgment due to the fluctuations of the material itself.

[0082] Therefore, surface images are introduced here, and the distance parameters are dynamically adjusted in reverse through cross-validation of vision and point clouds. The specific process of calculating the average distance between the coordinates of the secondary screening locations and obtaining the distance distribution parameter set is as follows: First, calculate the average distance between a certain secondary screening location coordinate and its surrounding adjacent secondary screening location coordinates. Then, group these average distance values ​​to obtain the distance distribution parameter set. This distance distribution parameter set is obtained based on the actual situation (adaptive), as follows: The coordinates of the secondary selection locations corresponding to a set of distance distribution parameters are such that the average distance between these secondary selection location coordinates and their surrounding neighboring secondary selection location coordinates is within a predetermined range. The K-Means clustering algorithm is typically used here, and the steps are as follows: 1. Randomly initialize K centroids; 2. Assign each random number to the nearest centroid (forming K groups); 3. Recalculate the average of all numbers within each group, and use it as the new centroid; 4. Repeat steps 2 and 3 until the centroid no longer changes significantly (convergence).

[0083] The specific method for comparing the surface image and the height distribution of a fixed region is as follows: Determine the first peak point corresponding to the height distribution of the fixed division region. The first peak point includes the first peak point and the first valley point. Determine the second peak point corresponding to the surface image of the fixed division region. The second peak point includes the second peak point and the second valley point. Calculate the average distance difference between the first peak and the second peak.

[0084] This section compares the first peak point (peak point) and the first valley point (valley point) existing in a fixed division region with the second peak point (peak point) and the second valley point (valley point) existing on the surface image. The comparison includes two types: horizontal (XY plane) comparison and vertical (XZ plane) comparison.

[0085] The height distribution of the corresponding fixed division area is constructed by using secondary filtering of position coordinate grouping. A three-dimensional surface is constructed using secondary filtering of position coordinate grouping. This surface has a first peak point and a first valley point.

[0086] The second peak point corresponding to the surface image is obtained as follows: Extreme value detection method: On the extracted one-dimensional contour line or gray-scale curve, find local maxima, that is, satisfy the condition: the gray value (or height value) of the center pixel is greater than the value of its adjacent left and right neighboring pixels.

[0087] Gradient analysis method: Calculate the first derivative of the image contour. The point where the derivative changes from positive to negative (crosses zero) is the potential peak point.

[0088] The second peak and valley points corresponding to the surface image are obtained as follows: Minimum detection method: Find local minima on the contour curve. That is, the gray value (or height value) of the center pixel is less than the value of its neighboring pixels.

[0089] Gradient backpropagation: Calculate the first derivative, and the position where the derivative changes from negative to positive (passes through zero) is the potential peak and valley point.

[0090] The first peak and the second peak are matched according to a distance matching method, that is, the distance between the matched first peak and the corresponding second peak is minimized, and the distance between the first valley and the corresponding second valley is minimized.

[0091] Finally, calculate the average distance difference between the first peak point and the second peak point, which is the average of the average distance difference between the first peak point and the corresponding second peak point and the average distance difference between the first valley point and the corresponding second valley point.

[0092] The mean distance difference obtained at this point is a comparison result, which corresponds to one or more distance distribution parameter sets. Continuing the above process, all comparison results are obtained. Each comparison result corresponds to one or more distance distribution parameter sets, and at least one of the distance distribution parameter sets corresponding to any two comparison results is different.

[0093] The above method can obtain all comparison results. Among these comparison results, the one or more distance distribution parameter sets corresponding to the smallest comparison result are used as the three-stage screening coordinates.

[0094] A surface can be constructed using cubic sieving coordinates, and the volume of the region below this surface can be calculated. The density can then be calculated using the volume and weight. The reason for calculating the density here is that the density of the mixture directly reflects the compactness and porosity of its internal substances.

[0095] The calorific value estimation formula uses the mass percentage of combustible elements (carbon, hydrogen, oxygen, and sulfur) in the fuel to estimate the higher heating value (GCV): GCV (kcal / kg) = 8080 × C + 34500 × (H - O / 8) + 2240 × S. The moisture content parameter also determines the conversion from higher heating value (GCV) to lower heating value (NCV): NCV = GCV - heat of condensation of water vapor. Finally, the heat loss due to ash content must be subtracted.

[0096] This can be summarized as follows: Net calorific value = Theoretical calorific value - Coefficient 1 × Ash content - Coefficient 2 × Moisture content

[0097] Density is used for correction, as follows: Corrected net calorific value = (theoretical calorific value - coefficient 1 × ash content - coefficient 2 × moisture content) × (1 + k × (ρ - ρ0)); in: ρ: The actual density of the mixture as measured in real time by the sensor; ρ0: Standard reference density (baseline density); K: Density correction coefficient, obtained through regression fitting of historical data.

[0098] This application also provides an AI-driven intelligent management and control device for enterprise economic costs, comprising: The data acquisition unit is used to acquire the combustion parameters of the mixture in a fixedly divided area on the transport line. The combustion parameters include moisture content parameters, combustible composition parameters, ash content parameters, and density parameters. The first calculation and processing unit is used to calculate the calorific value of the mixture in a corresponding fixed division area using the combustion parameters of the mixture, and obtain a reference calorific value; The second calculation and processing unit is used to calculate the adjustment ratio value based on the set calorific value and the reference calorific value; The adjustment unit is used to calculate the supplement and the amount of supplement based on the adjustment ratio and to deliver the determined amount of supplement to the corresponding fixed area on the transport line.

[0099] Furthermore, determining the density parameter in the combustion parameters includes: Acquire an image of the transportation line, and denote it as the analysis image; The transport lines in the image are extracted and divided to obtain fixed division regions; Calculate the height distribution parameter set of a fixed region; The volume parameters of the fixed-division region are calculated using the height distribution parameter set of the fixed-division region, and the density parameters are calculated based on the volume parameters and weight parameters. The calculation of the height distribution parameter set of the fixed division region also includes removing floating dust interference.

[0100] Furthermore, removing dust interference includes: Calculate the position coordinates of the reflection point based on the transmission and reception parameters; The position coordinates of the reflection point are filtered once using a predetermined height area to obtain the first filtered position coordinates; The coordinates of the first-stage selection are filtered using the intensity parameter to obtain the coordinates of the second-stage selection. The coordinates of the secondary selection are filtered using an adaptive distance parameter to obtain the coordinates of the tertiary selection.

[0101] Furthermore, the intensity parameters are used to filter the primary selection location coordinates to obtain the secondary selection coordinates, including: Divide the altitude into multiple altitude zones; Calculate the first average signal reflection intensity for each height range; When the difference between the first average signal reflection intensity of two adjacent height intervals is greater than the set reference value, the height interval with the smaller first average signal reflection intensity is discarded.

[0102] Furthermore, when discarding height ranges with relatively low first average signal reflection intensity, the process also includes: Divide the height range where the first average signal reflection intensity is relatively low into unit spaces: Calculate the second average signal reflection intensity for each unit space; Calculate the dispersion of the second average signal reflection intensity and obtain the dispersion result; The unit space is partially preserved based on the dispersion results.

[0103] Furthermore, the adaptive distance parameter is used to filter the secondary selection location coordinates to obtain the tertiary selection coordinates, including: By statistically analyzing the average distance values ​​of the secondary selection location coordinates, a distance distribution parameter set is obtained; The secondary screening location coordinates are grouped according to the distance distribution parameter group to obtain multiple secondary screening location coordinate groups; Use secondary filtering of location coordinates to group and construct the height distribution of corresponding fixed division regions; Obtain the surface image of the fixed-division region; The surface images and height distributions of the fixed-division regions are compared to obtain the comparison results; Get all comparison results; Use one or more distance distribution parameter sets corresponding to the smallest comparison result as the coordinates for the third selection.

[0104] Furthermore, comparing the surface image and the height distribution of the fixed-division region includes: Determine the first peak point corresponding to the height distribution of the fixed division region. The first peak point includes the first peak point and the first valley point. Determine the second peak point corresponding to the surface image of the fixed division region. The second peak point includes the second peak point and the second valley point. Calculate the average distance difference between the first peak and the second peak.

[0105] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0106] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0107] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0108] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] It should also be understood that in the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, a first time window and a second time window are only to indicate different time windows. They should not have any effect on the time windows themselves, and the aforementioned terms "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0113] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0114] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] This application also provides an AI-driven intelligent management and control system for enterprise economic costs, the system comprising: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory, performing the methods described above.

[0116] This application also provides a computer program product including instructions that, when executed, cause the terminal device and the network device to perform operations corresponding to the methods described above.

[0117] This application also provides a chip system including a processor for implementing the functions involved in the above description, such as generating, receiving, transmitting, or processing the data and / or information involved in the above methods.

[0118] This chip system can consist of chips or include chips and other discrete components.

[0119] The processor mentioned above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits that execute a program to control the method of transmitting the feedback information described above.

[0120] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can also be coupled to the same device.

[0121] Optionally, the computer instructions are stored in memory.

[0122] Optionally, the memory can be a storage unit within the chip, such as a register or cache. Alternatively, the memory can be a storage unit located outside the chip within the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, such as RAM.

[0123] It is understood that the memory in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0124] Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0125] Volatile memory can be RAM, which is used as an external cache. There are many different types of RAM, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory.

[0126] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An AI-driven intelligent management and control method for enterprise economic costs, characterized in that, include: The combustion parameters of the mixture in a fixed area on the transport line are obtained. The combustion parameters include moisture content, combustible composition, ash content and density. The calorific value of the mixture in the corresponding fixed division area is calculated using the combustion parameters of the mixture to obtain the reference calorific value; The adjustment ratio is calculated based on the set calorific value and the reference calorific value; Calculate the supplement and its usage based on the adjustment ratio, and then place the determined amount of supplement into the corresponding fixed area on the transport line.

2. The AI-driven intelligent management and control method for enterprise economic costs according to claim 1, characterized in that, The density parameter in determining combustion parameters includes: Acquire an image of the transportation line, and denote it as the analysis image; The transport lines in the image are extracted and divided to obtain fixed division regions; Calculate the height distribution parameter set of a fixed region; The volume parameters of the fixed-division region are calculated using the height distribution parameter set of the fixed-division region, and the density parameters are calculated based on the volume parameters and weight parameters. The calculation of the height distribution parameter set of the fixed division region also includes removing floating dust interference.

3. The AI-driven intelligent management and control method for enterprise economic costs according to claim 2, characterized in that, Removing dust interference includes: Calculate the position coordinates of the reflection point based on the transmission and reception parameters; The position coordinates of the reflection point are filtered once using a predetermined height area to obtain the first filtered position coordinates; The coordinates of the first-stage selection are filtered using the intensity parameter to obtain the coordinates of the second-stage selection. The coordinates of the secondary selection are filtered using an adaptive distance parameter to obtain the coordinates of the tertiary selection.

4. The AI-driven intelligent management and control method for enterprise economic costs according to claim 3, characterized in that, The coordinates of the primary selection location are filtered using intensity parameters, and the coordinates of the secondary selection are obtained, including: Divide the altitude into multiple altitude zones; Calculate the first average signal reflection intensity for each height range; When the difference between the first average signal reflection intensity of two adjacent height intervals is greater than the set reference value, the height interval with the smaller first average signal reflection intensity is discarded.

5. The AI-driven intelligent management and control method for enterprise economic costs according to claim 4, characterized in that, When discarding height ranges with low first average signal reflection intensity, the process also includes: Divide the height range where the first average signal reflection intensity is relatively low into unit spaces: Calculate the second average signal reflection intensity for each unit space; Calculate the dispersion of the second average signal reflection intensity and obtain the dispersion result; The unit space is partially preserved based on the dispersion results.

6. The AI-driven intelligent management and control method for enterprise economic costs according to claim 3, characterized in that, The coordinates of the secondary selection are filtered using adaptive distance parameters, resulting in the coordinates of the tertiary selection, which include: By statistically analyzing the average distance values ​​of the secondary selection location coordinates, a distance distribution parameter set is obtained; The secondary screening location coordinates are grouped according to the distance distribution parameter group to obtain multiple secondary screening location coordinate groups; Use secondary filtering of location coordinates to group and construct the height distribution of corresponding fixed division regions; Obtain the surface image of the fixed-division region; The surface images and height distributions of the fixed-division regions are compared to obtain the comparison results; Get all comparison results; Use one or more distance distribution parameter sets corresponding to the smallest comparison result as the coordinates for the third selection.

7. The AI-driven intelligent management and control method for enterprise economic costs according to claim 6, characterized in that, The comparison of surface images and height distributions of fixed-region divisions includes: Determine the first peak point corresponding to the height distribution of the fixed division region. The first peak point includes the first peak point and the first valley point. Determine the second peak point corresponding to the surface image of the fixed division region. The second peak point includes the second peak point and the second valley point. Calculate the average distance difference between the first peak and the second peak.

8. An AI-driven intelligent management and control device for enterprise economic costs, characterized in that, include: The data acquisition unit is used to acquire the combustion parameters of the mixture in a fixedly divided area on the transport line. The combustion parameters include moisture content parameters, combustible composition parameters, ash content parameters, and density parameters. The first calculation and processing unit is used to calculate the calorific value of the mixture in a corresponding fixed division area using the combustion parameters of the mixture, and obtain a reference calorific value; The second calculation and processing unit is used to calculate the adjustment ratio value based on the set calorific value and the reference calorific value; The adjustment unit is used to calculate the supplement and the amount of supplement based on the adjustment ratio and to deliver the determined amount of supplement to the corresponding fixed area on the transport line.

9. An AI-driven intelligent management and control system for enterprise economic costs, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by a processor, executes the method as described in any one of claims 1 to 7.

Images