A power generation by-product sales supervision system and method based on artificial intelligence

Abstract

The invention discloses a power generation byproduct sales supervision system and method based on artificial intelligence, which relates to the field of artificial intelligence technology. The invention relates to the field of artificial intelligence technology. The invention retrieves the power generation demand data and the sampling data of the coal material to be burned by the enterprise through setting up an access channel. The basic ash data of the fuel is analyzed according to the retrieved sampling data of the coal material to be burned. The ash output of the power generation on the next day is predicted and analyzed by combining the power generation demand data of the enterprise with the basic ash analysis results of the coal material to be burned. The real-time ash bin material level data is obtained based on the prediction data of the power generation ash output on the next day, and the ash bin material level is predicted and analyzed. The customer information matrix is ​​constructed by combining the customer's historical transaction data, the allocation weight of the corresponding customer is obtained, and the allocation amount of the coal ash of each customer on the next day is analyzed. Based on the analysis results of the coal ash allocation of each customer, a scheduling task set is formulated, and the scheduling task planning is carried out for the ash bin. The corresponding process analysis data of the power generation enterprise is output through visualization.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based system and method for supervising the sale of power generation byproducts. Background Art

[0002] As a large-volume, highly recyclable thermal power generation product, power generation by-products have always been a stable source of income for thermal power generation companies. In recent years, more and more thermal power generation companies have paid more attention to and attached more importance to the sales management of power generation by-products. However, while all companies are focusing on how to increase the sales revenue of by-products, they have neglected the planning and processing of the production process and on-site scheduling of power generation by-products, resulting in the lack of an efficient and coordinated analysis process and management system, resulting in low process correlation in the sales management of by-products, chaotic on-site scheduling, and the inability to achieve efficient and automated scheduling and supervision. Summary of the invention

[0003] The purpose of the present invention is to provide a power generation by-product sales supervision system and method based on artificial intelligence to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for supervising the sale of power generation byproducts based on artificial intelligence, the method comprising the following steps:

[0006] S100, linking the data storage database of the power generation enterprise by setting up an access channel, and retrieving the enterprise's power generation demand data and the sampling data of the coal material to be burned by accessing the database;

[0007] S200, analyzing the basic ash data of the fuel according to the retrieved sampling data of the corresponding batch of coal materials to be burned; combining the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned, predicting and analyzing the ash output of the enterprise for power generation on the next day;

[0008] S300, based on the enterprise's next-day power generation ash production forecast data, obtain real-time ash storage level data, and perform forecast analysis on the ash storage level; combine the customer's historical transaction data to build a customer information matrix, obtain the corresponding customer's allocation weight based on the customer information matrix, and analyze the next-day coal ash allocation amount for each customer;

[0009] S400. Based on the coal ash distribution analysis results of each customer, a scheduling model is constructed to formulate a scheduling task set, and scheduling tasks are planned for the ash storage; the scheduling task planning results are output, and the corresponding process analysis data output is performed for the power generation enterprise through visualization.

[0010] The specific steps of S100 in which the data storage database of the power generation enterprise is linked by setting up an access channel and accessing the database to retrieve the power generation demand data of the enterprise and the sampling data of the coal material to be burned are as follows:

[0011] S101, setting up a data access channel through the enterprise database management port, generating an access request service, determining the key search term of the access request through the verification access service, locating data in the database with the key search term, and outputting the retrieved data;

[0012] S102. Retrieve the enterprise's next-day power generation demand data and coal material sampling data using database retrieval services; the enterprise's next-day power generation demand data refers to the enterprise's next-day power generation load task data and electricity price data; the coal material sampling data refers to the batch data of coal material to be burned consumed by the enterprise for power generation the next day and the drying data and quality change data of the sampled coal material of the corresponding batch; the drying data refers to placing the coal material sampling sample in a drying oven at 105°C to 110°C for drying to remove moisture from the sample, and weighing the sample after cooling to room temperature to obtain the mass of the dried sample; placing the dried sample in a muffle furnace and performing ashing treatment at (815±10)°C, and after the sample is completely carbonized, weigh it to obtain the mass of the ash after cooling to room temperature.

[0013] The S200 performs basic ash data analysis on the fuel according to the retrieved sampling data of the corresponding periodic batch of coal materials to be burned; and combines the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned to perform a forecast analysis on the ash output of the enterprise power generation on the next day. The specific steps are as follows:

[0014] S201, by retrieving the sampling data of the coal material samples to be burned corresponding to the batch to be burned period, according to the recorded data of the target coal material samples after drying treatment and the quality change data, the basic ash data of the target coal material samples to be burned are analyzed, and the calculation formula is:

[0015]

[0016] Wherein, Jh is the basic ash value of the coal sample to be burned; Hf(Y) is the ash mass of the coal sample to be burned; Gz(Y) is the dry mass of the coal sample to be burned; and the sample set Y=(Y) is constructed by repeatedly sampling the same batch of coal to be burned. 1 ,Y 2 ...Y n );Y 1 ,Y 2 ...Y n are samples of the same batch of coal materials to be burned numbered from 1, 2...n; n is the sample number; based on the sample set, a comprehensive analysis is performed on the basic ash data of the current batch of coal materials to be burned, and the calculation formula is:

[0017]

[0018] Where Jha is the comprehensive basic ash value of the current batch of coal to be burned; Jhn is the basic ash value of each coal sample to be burned in the corresponding sample set;

[0019] S202. Combine the ash content analysis data of the corresponding batch of coal to be burned and the power generation demand data of the power generation enterprise on the next day to predict and analyze the power generation ash output of the enterprise on the next day; obtain the power generation operation parameters of the enterprise's power generation equipment through the database, and analyze the coal consumption rate of the enterprise's power generation equipment. The calculation formula is:

[0020]

[0021] Among them, Bf is the coal consumption rate of the enterprise's thermal power generating units; Bg is the standard power supply coal consumption of the enterprise's thermal power generating units; Qr is the heat consumption rate of the steam turbine; ηg is the thermal efficiency of the boiler; ηp is the system pipeline efficiency; combined with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day, the total coal consumption of the enterprise's power generation on the next day is analyzed, and the calculation formula is:

[0022] Tc=Fh*Bf;

[0023] Among them, Tc is the total coal consumption of the enterprise for power generation the next day; Fh is the power generation load required by the enterprise the next day; combined with the total coal consumption of the enterprise the next day, the total ash production of the enterprise the next day is analyzed, and the calculation formula is:

[0024] Ch = Tc*Jha;

[0025] Among them, Ch is the total ash production of the enterprise on the next day.

[0026] The S300 obtains real-time ash storage level data based on the enterprise's next-day power generation ash production forecast data, and performs forecast analysis on the ash storage level; combines the customer's historical transaction data to build a customer information matrix, obtains the corresponding customer's allocation weight based on the customer information matrix, and analyzes the next-day coal ash allocation amount for each customer in the following specific steps:

[0027] S301. Retrieve the ash bin data of the enterprise through the database; the ash bin data includes the ash bin number and the real-time material level of each ash bin; based on the predicted value of the total ash production of the enterprise on the next day, combined with the storage space attribute of the ash bin, convert the total ash production of the next day into the material level height of the ash bin, and the calculation formula is L=Ch / S; where L is the material level height value of the ash bin converted from the total ash production of the next day; S is the cross-sectional area of ​​the bottom of the ash bin; the calculation premise is that the ash bin is a regular rectangular shape; retrieve the real-time material level of each ash bin, and predict and analyze the storage level of each ash bin by evenly distributing and storing the total ash production of the next day, and the calculation formula is H i =hi +L / i; where H i The predicted material level after the ash material is stored in each ash bin; i is the real-time material level of each ash bin; i corresponds to the number of each ash bin; by setting the ash bin material level warning value Ht, if there is H i >Ht, the ash bin is level controlled, the level after the ash is distributed is adjusted to Ht, and the ash above Ht is evenly distributed to the remaining ash bins that have not reached the level warning value; if there is no Ht i >Ht, then record the material level of each ash bin after ash material distribution;

[0028] S302, by retrieving the customer data of gray material demand for the next day in the database, and constructing the corresponding customer information matrix according to the historical transaction data of each customer; wherein the customer information matrix with two rows and one column is constructed by the total number of historical transactions and the total number of gray materials in the historical transactions; by constructing coordinate points based on the total number of historical transactions and the total number of gray materials in the historical transactions of each customer, mapping them to the same plane coordinate system, connecting the adjacent coordinate points of each customer coordinate point, and vectorizing the connecting line segments of each adjacent coordinate point to obtain the characteristic vector between each adjacent coordinate point; synthesizing the adjacent characteristic vectors through vector synthesis calculation to obtain the unique customer characteristic vector in the plane coordinate system; then, the allocation weight analysis is performed on each customer in combination with the unique customer characteristic vector, and the calculation formula is:

[0029]

[0030] Among them, Aw is the allocation weight of the customer with the corresponding number w; Zw is the total number of historical transaction gray materials of the customer with the corresponding number w; Xw is the total number of historical transactions of the customer with the corresponding number w; is the modulus of the unique customer feature vector; w is the customer quantity number; the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer, and the calculation formula is Cw=Aw*Ch; where Cw is the gray material allocation amount of the corresponding customer number w on the next day.

[0031] The S400 constructs a scheduling model to formulate a scheduling task set based on the coal ash distribution analysis results of each customer, and performs scheduling task planning for the ash storage; outputs the scheduling task planning results, and outputs the corresponding process analysis data of the power generation enterprise through visualization. The specific steps are as follows:

[0032] S401. Based on the analysis results of coal ash distribution of each customer, a scheduling task set is specified for each customer by constructing a scheduling model; the number of scheduled vehicles for each customer the next day is analyzed by combining the carrying capacity of the dispatched trucks, and the calculation formula is Dw=Cw / u; wherein Dw is the number of dispatched vehicles corresponding to customer number w; u is the carrying capacity of the dispatched vehicle; if Sw is not an integer, the integer position is increased by one by rounding the calculation result; by coordinating the number of dispatched vehicles for each customer and combining the dynamic diversion coefficient of the enterprise, the dispatch shift of the dispatched vehicle is analyzed, and the calculation formula is Ve=ke*Da; wherein Ve is the number of dispatched vehicles corresponding to shift number e; ke is the diversion coefficient corresponding to the shift number e; Da is the total number of dispatched vehicles coordinated by the customer; the dispatching task set of each shift is formulated by constructing a dispatching model, which is Te={t1,t2...tp}; where Te is the task set corresponding to the shift number e; t1,t2...tp are the dispatching tasks corresponding to the shift number e; p is the number of tasks; the number of tasks is consistent with the number of ash warehouses, and each task corresponds to the dispatching vehicle allocation plan of each numbered ash warehouse; by defining the priority function P(t), the priority of each task set in the single-shift dispatching task set corresponding to the ash warehouse material level height is assigned; by analyzing the priority value of each task in a single shift, the calculation formula is:

[0033] tr(tp∈Te)=argP(tp∈Te);

[0034] Among them, tr(tp∈Te) is the priority value of the task numbered p in the task set corresponding to the shift numbered e; P(tp∈Te) is the priority allocation value of the task numbered p in the task set corresponding to the shift numbered e; according to the priority value analysis results of each task in the single-shift task set, the task set is sorted in descending order from large to small, and the task corresponding to max[tr(tp∈Te)] is taken as the most prioritized task; combined with the priority value analysis results of each task in the task set, the dispatch vehicle of each task in the corresponding shift task set is allocated and analyzed, and the calculation formula is:

[0035]

[0036] Among them, V[tp∈Te] is the number of dispatched vehicles corresponding to the ash material depot of task number p in the task set corresponding to shift number e; the dispatched vehicles of each task are combined into the number of dispatched vehicles of the corresponding shift. When the calculation result of the number of dispatched vehicles for a task is not an integer, the calculation result is rounded, and the sum of the number of vehicles after rounding is calculated. If it is less than the number of dispatched vehicles for the shift, the missing vehicles are dispatched in order from high to low according to the material level height of the ash material depot; the dispatch of ash materials for each task is satisfied according to the priority of each customer's allocation weight from large to small;

[0037] S402: Visually output the ash content of the corresponding coal to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and the scheduling task analysis data for the power generation enterprise, and output the scheduling tasks of each shift and pre-execute them.

[0038] A power generation byproduct sales supervision system based on artificial intelligence, the system includes a database access module, an ash production prediction and analysis module, a customer demand allocation and analysis module, and a scheduling task planning module;

[0039] The database access module links the data storage database of the power generation enterprise by setting up an access channel, and retrieves the enterprise's power generation demand data and the sampling data of the coal to be burned by accessing the database; the ash production prediction and analysis module analyzes the basic ash data of the fuel according to the retrieved sampling data of the coal to be burned of the corresponding periodic batch; combines the enterprise's power generation demand data with the basic ash analysis results of the corresponding batch of coal to be burned, and predicts and analyzes the ash production of the enterprise's power generation on the next day; the customer demand allocation analysis module obtains real-time ash bin material level data based on the enterprise's next day power generation ash production forecast data, and predicts and analyzes the ash bin material level; combines the customer's historical transaction data, constructs a customer information matrix, obtains the allocation weight of the corresponding customer based on the customer information matrix, and analyzes the next day's coal ash allocation of each customer; the scheduling task planning module constructs a scheduling model based on the coal ash allocation analysis results of each customer to formulate a scheduling task set, and performs scheduling task planning for the ash bin; outputs the scheduling task planning results, and outputs the corresponding process analysis data of the power generation enterprise through visualization.

[0040] The database access module includes a database channel setting unit and a data retrieval unit;

[0041] The database channel establishment unit establishes a data access channel through the enterprise database management port, generates an access request service, determines the access request key search term through the verification access service, performs data search and positioning in the database with the key search term, and outputs the searched data;

[0042] The data retrieval unit uses database retrieval services to retrieve the enterprise's next day's power generation demand data and coal material sampling data to be burned; the enterprise's next day's power generation demand data is the enterprise's next day's power generation load task data and electricity price data; the coal material sampling data to be burned is the batch data of the coal material to be burned consumed by the enterprise's next day's power generation and the drying processing data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned.

[0043] The ash production prediction and analysis module includes a coal-based ash analysis unit to be burned and a next-day ash production prediction unit;

[0044] The coal material to be burned basic ash analysis unit retrieves the sampling data of the coal material to be burned samples corresponding to the batch to be burned period, and analyzes the basic ash data of the target coal material to be burned sample according to the recorded data of the target coal material to be burned sample after drying and its quality change data; constructs a sample set by repeatedly sampling the same batch of coal material to be burned; and comprehensively analyzes the basic ash data of the current batch of coal material to be burned according to the sample set;

[0045] The next-day ash production prediction unit combines the ash analysis data of the corresponding batch of coal to be burned with the next-day power generation demand data of the power generation enterprise to predict and analyze the next-day power generation ash production of the enterprise; obtains the power generation operation parameters of the enterprise's power generation equipment through a database, and analyzes the coal consumption rate of the enterprise's power generation equipment; analyzes the total coal consumption of the enterprise's power generation on the next day in combination with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day; and analyzes the total ash production of the enterprise on the next day in combination with the total coal consumption of the enterprise on the next day.

[0046] The customer demand allocation analysis module includes an ash storage level prediction analysis unit and a customer demand allocation analysis unit;

[0047] The ash bin level prediction and analysis unit retrieves the enterprise's ash bin data through a database; the ash bin data includes the ash bin number and the real-time level of each ash bin; based on the predicted value of the total ash production of the enterprise the next day, combined with the storage space attribute of the ash bin, the total ash production of the next day is converted into the ash bin level height; the real-time level of each ash bin is retrieved, and the storage level of each ash bin is predicted and analyzed by evenly distributing and storing the total ash production of the next day; by setting the ash bin level warning value, the ash bin is regulated and the level of each ash bin after the ash is distributed is recorded;

[0048] The customer demand allocation analysis unit retrieves the customer data of gray material demand for the next day from the database, and constructs a corresponding customer information matrix according to the historical transaction data of each customer; wherein a two-row and one-column customer information matrix is ​​constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions; coordinate points are constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions of each customer and mapped to the same plane coordinate system, adjacent coordinate points of each customer coordinate point are connected, and the connecting line segments of each adjacent coordinate point are vectorized to obtain the feature vectors between each adjacent coordinate point; adjacent feature vectors are synthesized by vector synthesis calculation to obtain a unique customer feature vector in the plane coordinate system; then, allocation weight analysis is performed on each customer in combination with the unique customer feature vector; and the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer.

[0049] The scheduling task planning module includes a scheduling task planning unit and a comprehensive data feedback unit;

[0050] The scheduling task planning unit specifies a scheduling task set for each customer by constructing a scheduling model based on the coal ash distribution analysis results of each customer; analyzes the number of next-day scheduling vehicles for each customer by combining the carrying capacity of the scheduling truck; analyzes the scheduling shifts of the scheduling vehicles by coordinating the number of scheduling vehicles for each customer and combining the dynamic diversion coefficient of the enterprise; formulates the scheduling task set for each shift by constructing a scheduling model; allocates priority to the ash storage material level height corresponding to each task set in the single-shift scheduling task set by defining a priority function; analyzes the priority value of each task in a single shift; sorts the task set in descending order from large to small according to the priority value analysis results of each task in the single-shift task set, and takes the task corresponding to the maximum value as the most prioritized task; analyzes the priority value analysis results of each task in the task set, and allocates and analyzes the scheduling vehicles for each task in the corresponding shift task set; and satisfies the ash delivery of each task by taking the vehicle according to the allocation weight of each customer from large to small.

[0051] The comprehensive data feedback unit visualizes the output of the corresponding coal material ash content to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and scheduling task analysis data for the power generation enterprise, and outputs and pre-executes the scheduling tasks for each shift.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention realizes the overall analysis and planning of the production sampling, basic ash analysis, output prediction, customer demand allocation and scheduling task planning processes of thermal power generation by-products by associating multiple supervision processes; through the association analysis of the basic ash content of the coal to be burned, the coal consumption rate of the thermal power generation equipment, and then the prediction analysis of the coal consumption and ash output, the demand allocation of each customer is calculated in association with the analysis of the ash output, and the retrieval tasks are formulated according to the needs of each customer, thereby realizing the coherent overall planning of the production and sales of thermal power generation by-products and strengthening the correlation between the various processes; and through the serial formulation of scheduling tasks, the disorder of on-site scheduling is greatly improved, and efficient and automated scheduling supervision is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a structural schematic diagram of an artificial intelligence-based power generation by-product sales supervision system of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0056] Example: Figure 1 As shown, the present invention provides a technical solution:

[0057] A method for supervising the sale of power generation byproducts based on artificial intelligence, the method comprising the following steps:

[0058] S100, linking the data storage database of the power generation enterprise by setting up an access channel, and retrieving the enterprise's power generation demand data and the sampling data of the coal material to be burned by accessing the database;

[0059] S200, analyzing the basic ash data of the fuel according to the retrieved sampling data of the corresponding batch of coal materials to be burned; combining the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned, predicting and analyzing the ash output of the enterprise for power generation on the next day;

[0060] S300, based on the enterprise's next-day power generation ash production forecast data, obtain real-time ash storage level data, and perform forecast analysis on the ash storage level; combine the customer's historical transaction data to build a customer information matrix, obtain the corresponding customer's allocation weight based on the customer information matrix, and analyze the next-day coal ash allocation amount for each customer;

[0061] S400. Based on the coal ash distribution analysis results of each customer, a scheduling model is constructed to formulate a scheduling task set, and scheduling tasks are planned for the ash storage; the scheduling task planning results are output, and the corresponding process analysis data output is performed for the power generation enterprise through visualization.

[0062] The specific steps of S100 in which the data storage database of the power generation enterprise is linked by setting up an access channel and accessing the database to retrieve the power generation demand data of the enterprise and the sampling data of the coal material to be burned are as follows:

[0063] S101, setting up a data access channel through the enterprise database management port, generating an access request service, determining the key search term of the access request through the verification access service, locating data in the database with the key search term, and outputting the retrieved data;

[0064] S102. Retrieve the enterprise's next-day power generation demand data and coal material sampling data by using database retrieval service; the enterprise's next-day power generation demand data refers to the enterprise's next-day power generation load task data and electricity price data; the coal material sampling data refers to the batch data of coal material to be burned consumed by the enterprise's next-day power generation and the drying processing data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned.

[0065] The S200 performs basic ash data analysis on the fuel according to the retrieved sampling data of the corresponding periodic batch of coal materials to be burned; and combines the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned to perform a forecast analysis on the ash output of the enterprise power generation on the next day. The specific steps are as follows:

[0066] S201, by retrieving the sampling data of the coal material samples to be burned corresponding to the batch to be burned period, according to the recorded data of the target coal material samples after drying treatment and the quality change data, the basic ash data of the target coal material samples to be burned are analyzed, and the calculation formula is:

[0067]

[0068] Wherein, Jh is the basic ash value of the coal sample to be burned; Hf(Y) is the ash mass of the coal sample to be burned; Gz(Y) is the dry mass of the coal sample to be burned; and the sample set Y=(Y) is constructed by repeatedly sampling the same batch of coal to be burned. 1 ,Y 2 ...Y n );Y 1 ,Y 2 ...Y n are samples of the same batch of coal materials to be burned numbered from 1, 2...n; n is the sample number; based on the sample set, a comprehensive analysis is performed on the basic ash data of the current batch of coal materials to be burned, and the calculation formula is:

[0069]

[0070] Where Jha is the comprehensive basic ash value of the current batch of coal to be burned; Jhn is the basic ash value of each coal sample to be burned in the corresponding sample set;

[0071] S202. Combine the ash content analysis data of the corresponding batch of coal to be burned and the power generation demand data of the power generation enterprise on the next day to predict and analyze the power generation ash output of the enterprise on the next day; obtain the power generation operation parameters of the enterprise's power generation equipment through the database, and analyze the coal consumption rate of the enterprise's power generation equipment. The calculation formula is:

[0072]

[0073] Among them, Bf is the coal consumption rate of the enterprise's thermal power generating units; Bg is the standard power supply coal consumption of the enterprise's thermal power generating units; Qr is the heat consumption rate of the steam turbine; ηg is the thermal efficiency of the boiler; ηp is the system pipeline efficiency; combined with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day, the total coal consumption of the enterprise's power generation on the next day is analyzed, and the calculation formula is:

[0074] Tc=Fh*Bf;

[0075] Among them, Tc is the total coal consumption of the enterprise for power generation the next day; Fh is the power generation load required by the enterprise the next day; combined with the total coal consumption of the enterprise the next day, the total ash production of the enterprise the next day is analyzed, and the calculation formula is:

[0076] Ch = Tc*Jha;

[0077] Among them, Ch is the total ash production of the enterprise on the next day.

[0078] The S300 obtains real-time ash storage level data based on the enterprise's next-day power generation ash production forecast data, and performs forecast analysis on the ash storage level; combines the customer's historical transaction data to build a customer information matrix, obtains the corresponding customer's allocation weight based on the customer information matrix, and analyzes the next-day coal ash allocation amount for each customer in the following specific steps:

[0079] S301. Retrieve the ash bin data of the enterprise through the database; the ash bin data includes the ash bin number and the real-time material level of each ash bin; based on the predicted value of the total ash production of the enterprise on the next day, combined with the storage space attribute of the ash bin, convert the total ash production of the next day into the material level height of the ash bin, and the calculation formula is L=Ch / S; where L is the material level height value of the ash bin converted from the total ash production of the next day; S is the cross-sectional area of ​​the bottom of the ash bin; retrieve the real-time material level of each ash bin, and predict and analyze the storage level of each ash bin by evenly distributing and storing the total ash production of the next day, and the calculation formula is H i =h i +L / i; where H i The predicted material level after the ash material is stored in each ash bin; i is the real-time material level of each ash bin; i corresponds to the number of each ash bin; by setting the ash bin material level warning value Ht, if there is H i >Ht, the ash bin is level controlled, the level after the ash is distributed is adjusted to Ht, and the ash above Ht is evenly distributed to the remaining ash bins that have not reached the level warning value; if there is no Ht i >Ht, then record the material level of each ash bin after ash material distribution;

[0080] S302, by retrieving the customer data of gray material demand for the next day in the database, and constructing the corresponding customer information matrix according to the historical transaction data of each customer; wherein the customer information matrix with two rows and one column is constructed by the total number of historical transactions and the total number of gray materials in the historical transactions; by constructing coordinate points based on the total number of historical transactions and the total number of gray materials in the historical transactions of each customer, mapping them to the same plane coordinate system, connecting the adjacent coordinate points of each customer coordinate point, and vectorizing the connecting line segments of each adjacent coordinate point to obtain the characteristic vector between each adjacent coordinate point; synthesizing the adjacent characteristic vectors through vector synthesis calculation to obtain the unique customer characteristic vector in the plane coordinate system; then, the allocation weight analysis is performed on each customer in combination with the unique customer characteristic vector, and the calculation formula is:

[0081]

[0082] Among them, Aw is the allocation weight of the customer with the corresponding number w; Zw is the total number of historical transaction gray materials of the customer with the corresponding number w; Xw is the total number of historical transactions of the customer with the corresponding number w; is the modulus of the unique customer feature vector; w is the customer quantity number; the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer, and the calculation formula is Cw=Aw*Ch; where Cw is the gray material allocation amount of the corresponding customer number w on the next day.

[0083] The S400 constructs a scheduling model to formulate a scheduling task set based on the coal ash distribution analysis results of each customer, and performs scheduling task planning for the ash storage; outputs the scheduling task planning results, and outputs the corresponding process analysis data of the power generation enterprise through visualization. The specific steps are as follows:

[0084] S401. Based on the analysis results of coal ash distribution for each customer, a scheduling task set is assigned to each customer by constructing a scheduling model; the number of scheduled vehicles for each customer the next day is analyzed by combining the carrying capacity of the dispatched trucks, and the calculation formula is Dw=Cw / u; where Dw is the number of dispatched vehicles corresponding to customer number w; u is the carrying capacity of the dispatched vehicle; by coordinating the number of dispatched vehicles for each customer and combining the dynamic diversion coefficient of the enterprise, the dispatch shift of the dispatched vehicle is analyzed, and the calculation formula is Ve=ke*Da; where Ve is the number of dispatched vehicles corresponding to shift number e; ke is the diversion coefficient corresponding to the shift number e; Da is the total number of dispatched vehicles coordinated by the customer; the dispatching task set of each shift is formulated by constructing a dispatching model, which is Te={t1,t2...tp}; where Te is the task set corresponding to the shift number e; t1,t2...tp are the dispatching tasks corresponding to the shift number e; p is the number of tasks; by defining the priority function P(t), the priority of each task set in the single-shift dispatching task set corresponding to the material level height of the ash storage is assigned; by analyzing the priority value of each task in a single shift, the calculation formula is

[0085] tr(tp∈Te)=argP(tp∈Te);

[0086] Among them, tr(tp∈Te) is the priority value of the task numbered p in the task set corresponding to the shift numbered e; P(tp∈Te) is the priority allocation value of the task numbered p in the task set corresponding to the shift numbered e; according to the priority value analysis results of each task in the single-shift task set, the task set is sorted in descending order from large to small, and the task corresponding to max[tr(tp∈Te)] is taken as the most prioritized task; combined with the priority value analysis results of each task in the task set, the dispatch vehicle of each task in the corresponding shift task set is allocated and analyzed, and the calculation formula is:

[0087]

[0088] Among them, V[tp∈Te] is the number of dispatched vehicles corresponding to the gray material warehouse of task number p in the task set corresponding to shift number e; the gray material dispatch of each task to retrieve the vehicle is satisfied according to the priority of each customer's allocation weight from large to small;

[0089] S402: Visually output the ash content of the corresponding coal to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and the scheduling task analysis data for the power generation enterprise, and output the scheduling tasks of each shift and pre-execute them.

[0090] A power generation byproduct sales supervision system based on artificial intelligence, the system includes a database access module, an ash production prediction and analysis module, a customer demand allocation and analysis module, and a scheduling task planning module;

[0091] The database access module links the data storage database of the power generation enterprise by setting up an access channel, and retrieves the enterprise's power generation demand data and the sampling data of the coal to be burned by accessing the database; the ash production prediction and analysis module analyzes the basic ash data of the fuel according to the retrieved sampling data of the coal to be burned of the corresponding periodic batch; combines the enterprise's power generation demand data with the basic ash analysis results of the corresponding batch of coal to be burned, and predicts and analyzes the ash production of the enterprise's power generation on the next day; the customer demand allocation analysis module obtains real-time ash bin material level data based on the enterprise's next day power generation ash production forecast data, and predicts and analyzes the ash bin material level; combines the customer's historical transaction data, constructs a customer information matrix, obtains the allocation weight of the corresponding customer based on the customer information matrix, and analyzes the next day's coal ash allocation of each customer; the scheduling task planning module constructs a scheduling model based on the coal ash allocation analysis results of each customer to formulate a scheduling task set, and performs scheduling task planning for the ash bin; outputs the scheduling task planning results, and outputs the corresponding process analysis data of the power generation enterprise through visualization.

[0092] The database access module includes a database channel setting unit and a data retrieval unit;

[0093] The database channel establishment unit establishes a data access channel through the enterprise database management port, generates an access request service, determines the access request key search term through the verification access service, performs data search and positioning in the database with the key search term, and outputs the searched data;

[0094] The data retrieval unit uses database retrieval services to retrieve the enterprise's next day's power generation demand data and coal material sampling data to be burned; the enterprise's next day's power generation demand data is the enterprise's next day's power generation load task data and electricity price data; the coal material sampling data to be burned is the batch data of the coal material to be burned consumed by the enterprise's next day's power generation and the drying processing data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned.

[0095] The ash production prediction and analysis module includes a coal-based ash analysis unit to be burned and a next-day ash production prediction unit;

[0096] The coal material to be burned basic ash analysis unit retrieves the sampling data of the coal material to be burned samples corresponding to the batch to be burned period, and analyzes the basic ash data of the target coal material to be burned sample according to the recorded data of the target coal material to be burned sample after drying and its quality change data; constructs a sample set by repeatedly sampling the same batch of coal material to be burned; and comprehensively analyzes the basic ash data of the current batch of coal material to be burned according to the sample set;

[0097] The next-day ash production prediction unit combines the ash analysis data of the corresponding batch of coal to be burned with the next-day power generation demand data of the power generation enterprise to predict and analyze the next-day power generation ash production of the enterprise; obtains the power generation operation parameters of the enterprise's power generation equipment through a database, and analyzes the coal consumption rate of the enterprise's power generation equipment; analyzes the total coal consumption of the enterprise's power generation on the next day in combination with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day; and analyzes the total ash production of the enterprise on the next day in combination with the total coal consumption of the enterprise on the next day.

[0098] The customer demand allocation analysis module includes an ash storage level prediction analysis unit and a customer demand allocation analysis unit;

[0099] The ash bin level prediction and analysis unit retrieves the enterprise's ash bin data through a database; the ash bin data includes the ash bin number and the real-time level of each ash bin; based on the predicted value of the total ash production of the enterprise the next day, combined with the storage space attribute of the ash bin, the total ash production of the next day is converted into the ash bin level height; the real-time level of each ash bin is retrieved, and the storage level of each ash bin is predicted and analyzed by evenly distributing and storing the total ash production of the next day; by setting the ash bin level warning value, the ash bin is regulated and the level of each ash bin after the ash is distributed is recorded;

[0100] The customer demand allocation analysis unit retrieves the customer data of gray material demand for the next day from the database, and constructs a corresponding customer information matrix according to the historical transaction data of each customer; wherein a two-row and one-column customer information matrix is ​​constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions; coordinate points are constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions of each customer and mapped to the same plane coordinate system, adjacent coordinate points of each customer coordinate point are connected, and the connecting line segments of each adjacent coordinate point are vectorized to obtain the feature vectors between each adjacent coordinate point; adjacent feature vectors are synthesized by vector synthesis calculation to obtain a unique customer feature vector in the plane coordinate system; then, allocation weight analysis is performed on each customer in combination with the unique customer feature vector; and the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer.

[0101] The scheduling task planning module includes a scheduling task planning unit and a comprehensive data feedback unit;

[0102] The scheduling task planning unit specifies a scheduling task set for each customer by constructing a scheduling model based on the coal ash distribution analysis results of each customer; analyzes the number of next-day scheduling vehicles for each customer by combining the carrying capacity of the scheduling truck; analyzes the scheduling shifts of the scheduling vehicles by coordinating the number of scheduling vehicles for each customer and combining the dynamic diversion coefficient of the enterprise; formulates the scheduling task set for each shift by constructing a scheduling model; allocates priority to the ash storage material level height corresponding to each task set in the single-shift scheduling task set by defining a priority function; analyzes the priority value of each task in a single shift; sorts the task set in descending order from large to small according to the priority value analysis results of each task in the single-shift task set, and takes the task corresponding to the maximum value as the most prioritized task; analyzes the priority value analysis results of each task in the task set, and allocates and analyzes the scheduling vehicles for each task in the corresponding shift task set; and satisfies the ash delivery of each task by taking the vehicle according to the allocation weight of each customer from large to small.

[0103] The comprehensive data feedback unit visualizes the output of the corresponding coal material ash content to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and the scheduling task analysis data of the power generation enterprise, and outputs and pre-executes the scheduling tasks of each shift;

[0104] In the examples:

[0105] At present, a certain thermal power generation enterprise adopts the power generation by-product sales supervision system based on artificial intelligence of the present invention to supervise the by-product production and sales management process; a data access channel is set up through the enterprise database management port, an access request service is generated, the access request key search term is determined by verifying the access service, data retrieval and positioning are performed in the database with the key search term, and the retrieved data is output; the database retrieval service is used to retrieve the enterprise's next day power generation demand data and the sampling data of the coal material to be burned; the enterprise's next day power generation demand data is the enterprise's next day power generation load task data and electricity price data; the sampling data of the coal material to be burned is the batch data of the coal material to be burned consumed by the enterprise's next day power generation and the drying treatment data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned;

[0106] By retrieving the sampling data of the coal samples to be burned corresponding to the batch to be burned period, and according to the recorded data of the target coal samples after drying and their quality change data, the basic ash data of the target coal samples to be burned are analyzed, and the calculation formula is:

[0107]

[0108] By repeatedly sampling the same batch of coal to be burned, a sample set Y = (Y 1 ,Y 2 ...Y n ); Comprehensively analyze the basic ash data of the current batch of coal to be burned according to the sample set, and the calculation formula is:

[0109]

[0110] Combined with the ash content analysis data of the corresponding batch of coal to be burned, combined with the power generation demand data of the power generation enterprise on the next day, the next day's power generation ash production of the enterprise is predicted and analyzed; the power generation operation parameters of the enterprise's power generation equipment are obtained through the database, and the coal consumption rate of the enterprise's power generation equipment is analyzed. The calculation formula is:

[0111]

[0112] Combining the coal consumption rate of the enterprise's power generation equipment with the enterprise's power generation demand for the next day, the total coal consumption for power generation on the next day is analyzed. The calculation formula is:

[0113] Tc=Fh*Bf;

[0114] Combined with the total coal consumption of the enterprise on the next day, the total ash production of the enterprise on the next day is analyzed, and the calculation formula is:

[0115] Ch = Tc*Jha;

[0116] The ash storage data of the enterprise is retrieved through the database; the ash storage data includes the ash storage number and the real-time material level of each ash storage; based on the predicted value of the total ash production of the enterprise on the next day, combined with the storage space attribute of the ash storage, the total ash production of the next day is converted into the ash storage material level height, and the calculation formula is L=Ch / S; the real-time material level of each ash storage is retrieved, and the storage level of each ash storage is predicted and analyzed by evenly distributing the total ash production of the next day, and the calculation formula is H i =h i +L / i; By setting the ash bin material level warning value Ht, if there is H i >Ht, the ash bin is level controlled, the level after the ash is distributed is adjusted to Ht, and the ash above Ht is evenly distributed to the remaining ash bins that have not reached the level warning value; if there is no Ht i >Ht, then record the material level of each ash bin after ash material distribution;

[0117] By retrieving the customer data of gray material demand for the next day from the database, the corresponding customer information matrix is ​​constructed according to the historical transaction data of each customer; a two-row and one-column customer information matrix is ​​constructed with the total number of historical transactions and the total amount of gray materials in the historical transactions; coordinate points are constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions of each customer and mapped to the same plane coordinate system, adjacent coordinate points of each customer coordinate point are connected, and the connecting line segments of each adjacent coordinate point are vectorized to obtain the characteristic vectors between each adjacent coordinate point; adjacent characteristic vectors are synthesized by vector synthesis calculation to obtain the unique customer characteristic vector in the plane coordinate system; and the weight distribution analysis is performed on each customer in combination with the unique customer characteristic vector, and the calculation formula is:

[0118]

[0119] The ash material allocation for each customer on the next day is analyzed according to the allocation weight of each customer, and the calculation formula is Cw=Aw*Ch;

[0120] Based on the analysis results of coal ash distribution of each customer, a scheduling task set is specified for each customer by constructing a scheduling model; the number of scheduled vehicles for each customer the next day is analyzed by combining the carrying capacity of the dispatched trucks, and the calculation formula is Dw=Cw / u; the number of dispatched vehicles for each customer is coordinated, and the dispatch shifts of the dispatched vehicles are analyzed in combination with the dynamic diversion coefficient of the enterprise, and the calculation formula is Ve=ke*Da; the scheduling task set for each shift is formulated by constructing a scheduling model, which is Te={t1,t2...tp}; by defining the priority function P(t), the priority of each task set in the single-shift scheduling task set corresponding to the ash storage material level height is assigned; by analyzing the priority value of each task in a single shift, the calculation formula is

[0121] tr(tp∈Te)=argP(tp∈Te);

[0122] According to the priority value analysis results of each task in the single-shift task set, the task set is sorted in descending order from large to small, and the task corresponding to max[tr(tp∈Te)] is taken as the most prioritized task; combined with the priority value analysis results of each task in the task set, the dispatch vehicle allocation analysis of each task in the corresponding shift task set is performed, and the calculation formula is:

[0123]

[0124] The ash delivery of each task vehicle is prioritized from high to low according to the allocation weight of each customer; the corresponding ash content of the coal to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand allocation analysis and scheduling task analysis data of the power generation enterprise are visualized and output, and the scheduling tasks of each shift are output and pre-executed.

[0125] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for supervising the sale of power generation byproducts based on artificial intelligence, characterized in that: The method comprises the following steps: S100, linking the data storage database of the power generation enterprise by setting up an access channel, and retrieving the power generation demand data and the sampling data of the coal material to be burned by accessing the database; S200, analyzing the basic ash data of the fuel according to the retrieved sampling data of the corresponding batch of coal materials to be burned; combining the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned, predicting and analyzing the ash output of the enterprise for power generation on the next day; S300, based on the enterprise's next-day power generation ash production forecast data, obtain real-time ash storage level data, and perform forecast analysis on the ash storage level; combine the customer's historical transaction data to build a customer information matrix, obtain the corresponding customer's allocation weight based on the customer information matrix, and analyze the next-day coal ash allocation amount for each customer; S400. Based on the coal ash distribution analysis results of each customer, a scheduling model is constructed to formulate a scheduling task set, and scheduling tasks are planned for the ash storage; the scheduling task planning results are output, and the corresponding process analysis data output is performed for the power generation enterprise through visualization.

2. The method for supervising the sale of power generation byproducts based on artificial intelligence according to claim 1, characterized in that: The specific steps of S100 in which the data storage database of the power generation enterprise is linked by setting up an access channel and accessing the database to retrieve the power generation demand data of the enterprise and the sampling data of the coal material to be burned are as follows: S101, setting up a data access channel through the enterprise database management port, generating an access request service, determining the key search term of the access request through the verification access service, locating data in the database with the key search term, and outputting the retrieved data; S102. Retrieve the enterprise's next-day power generation demand data and coal material sampling data by using database retrieval service; the enterprise's next-day power generation demand data refers to the enterprise's next-day power generation load task data and electricity price data; the coal material sampling data refers to the batch data of coal material to be burned consumed by the enterprise's next-day power generation and the drying processing data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned.

3. The method for supervising the sale of power generation byproducts based on artificial intelligence according to claim 2, characterized in that: The S200 performs basic ash data analysis on the fuel according to the retrieved sampling data of the corresponding periodic batch of coal materials to be burned; and combines the power generation demand data of the enterprise with the basic ash analysis results of the corresponding batch of coal materials to be burned to perform a forecast analysis on the ash output of the enterprise power generation on the next day. The specific steps are as follows: By retrieving the sampling data of the coal samples to be burned corresponding to the batch to be burned period, and according to the recorded data of the target coal samples after drying and their quality change data, the basic ash data of the target coal samples to be burned are analyzed, and the calculation formula is: Wherein, Jh is the basic ash value of the coal sample to be burned; Hf(Y) is the ash mass of the coal sample to be burned; Gz(Y) is the dry mass of the coal sample to be burned; and the sample set Y=(Y1,Y2...Y n ); where Y1, Y2...Y n are samples of the same batch of coal materials to be burned numbered from 1, 2...n; n is the sample number; based on the sample set, a comprehensive analysis is performed on the basic ash data of the current batch of coal materials to be burned, and the calculation formula is: Wherein Jha is the comprehensive basic ash value of the current batch of coal to be burned; Jhn is the basic ash value of each coal sample to be burned in the corresponding sample set.

4. The method for supervising the sale of power generation byproducts based on artificial intelligence according to claim 3 is characterized in that: Combined with the ash content analysis data of the corresponding batch of coal to be burned, combined with the power generation demand data of the power generation enterprise on the next day, the next day's power generation ash production of the enterprise is predicted and analyzed; the power generation operation parameters of the enterprise's power generation equipment are obtained through the database, and the coal consumption rate of the enterprise's power generation equipment is analyzed. The calculation formula is: Among them, Bf is the coal consumption rate of the enterprise's thermal power generating units; Bg is the standard power supply coal consumption of the enterprise's thermal power generating units; Qr is the heat consumption rate of the steam turbine; ηg is the thermal efficiency of the boiler; ηp is the system pipeline efficiency; combined with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day, the total coal consumption of the enterprise's power generation on the next day is analyzed, and the calculation formula is: Tc=Fh*Bf; Among them, Tc is the total coal consumption of the enterprise for power generation the next day; Fh is the power generation load required by the enterprise the next day; combined with the total coal consumption of the enterprise the next day, the total ash production of the enterprise the next day is analyzed, and the calculation formula is: Ch=Tc*Jh a ; Among them, Ch is the total ash production of the enterprise on the next day.

5. The method for supervising the sale of power generation byproducts based on artificial intelligence according to claim 4 is characterized in that: The S300 obtains real-time ash storage level data based on the enterprise's next-day power generation ash production forecast data, and performs forecast analysis on the ash storage level; combines the customer's historical transaction data to build a customer information matrix, obtains the corresponding customer's allocation weight based on the customer information matrix, and analyzes the next-day coal ash allocation amount for each customer in the following specific steps: S301. Retrieve the ash bin data of the enterprise through the database; the ash bin data includes the ash bin number and the real-time material level of each ash bin; based on the predicted value of the total ash production of the enterprise on the next day, combined with the storage space attribute of the ash bin, convert the total ash production of the next day into the material level height of the ash bin, and the calculation formula is L=Ch / S; where L is the material level height value of the ash bin converted from the total ash production of the next day; S is the cross-sectional area of ​​the bottom of the ash bin; retrieve the real-time material level of each ash bin, and predict and analyze the storage level of each ash bin by evenly distributing and storing the total ash production of the next day, and the calculation formula is H i =h i +L / i; where H i The predicted material level after the ash material is stored in each ash bin; i is the real-time material level of each ash bin; i corresponds to the number of each ash bin; by setting the ash bin material level warning value Ht, if there is H i >Ht, the ash bin is level controlled, the level after the ash is distributed is adjusted to Ht, and the ash above Ht is evenly distributed to the remaining ash bins that have not reached the level warning value; if there is no Ht i >Ht, then record the material level of each ash bin after ash material distribution; S302, by retrieving the customer data of gray material demand for the next day in the database, and constructing the corresponding customer information matrix according to the historical transaction data of each customer; wherein the customer information matrix with two rows and one column is constructed by the total number of historical transactions and the total number of gray materials in the historical transactions; by constructing coordinate points based on the total number of historical transactions and the total number of gray materials in the historical transactions of each customer, mapping them to the same plane coordinate system, connecting the adjacent coordinate points of each customer coordinate point, and vectorizing the connecting line segments of each adjacent coordinate point to obtain the characteristic vector between each adjacent coordinate point; synthesizing the adjacent characteristic vectors through vector synthesis calculation to obtain the unique customer characteristic vector in the plane coordinate system; then, the allocation weight analysis is performed on each customer in combination with the unique customer characteristic vector, and the calculation formula is: Among them, Aw is the allocation weight of the customer with the corresponding number w; Zw is the total number of historical transaction gray materials of the customer with the corresponding number w; Xw is the total number of historical transactions of the customer with the corresponding number w; is the modulus of the unique customer feature vector; w is the customer quantity number; the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer, and the calculation formula is Cw=Aw*Ch; where Cw is the gray material allocation amount of the corresponding customer number w on the next day.

6. The method for supervising the sale of power generation byproducts based on artificial intelligence according to claim 5, characterized in that: The S400 constructs a scheduling model to formulate a scheduling task set based on the coal ash distribution analysis results of each customer, and performs scheduling task planning for the ash storage; outputs the scheduling task planning results, and outputs the corresponding process analysis data of the power generation enterprise through visualization. The specific steps are as follows: S401. Based on the analysis results of coal ash distribution for each customer, a scheduling task set is assigned to each customer by constructing a scheduling model; the number of scheduled vehicles for each customer the next day is analyzed by combining the carrying capacity of the dispatched trucks, and the calculation formula is Dw=Cw / u; where Dw is the number of dispatched vehicles corresponding to customer number w; u is the carrying capacity of the dispatched vehicle; by coordinating the number of dispatched vehicles for each customer and combining the dynamic diversion coefficient of the enterprise, the dispatch shift of the dispatched vehicle is analyzed, and the calculation formula is Ve=ke*Da; where Ve is the number of dispatched vehicles corresponding to shift number e; ke is the diversion coefficient corresponding to the shift number e; Da is the total number of dispatched vehicles coordinated by the customer; the dispatching task set of each shift is formulated by constructing a dispatching model, which is Te={t1,t2...tp}; where Te is the task set corresponding to the shift number e; t1,t2...tp are the dispatching tasks corresponding to the shift number e; p is the number of tasks; by defining the priority function P(t), the priority of each task set in the single-shift dispatching task set corresponding to the material level height of the ash storage is assigned; by analyzing the priority value of each task in a single shift, the calculation formula is tr(tp∈Te)=argP(tp∈Te); Among them, tr(tp∈Te) is the priority value of the task numbered p in the task set corresponding to the shift numbered e; P(tp∈Te) is the priority allocation value of the task numbered p in the task set corresponding to the shift numbered e; according to the priority value analysis results of each task in the single-shift task set, the task set is sorted in descending order from large to small, and the task corresponding to max[tr(tp∈Te)] is taken as the most prioritized task; combined with the priority value analysis results of each task in the task set, the dispatch vehicle of each task in the corresponding shift task set is allocated and analyzed, and the calculation formula is: Among them, V[tp∈Te] is the number of dispatched vehicles corresponding to the gray material warehouse of task number p in the task set corresponding to shift number e; the gray material dispatch of each task to retrieve the vehicle is satisfied according to the priority of each customer's allocation weight from large to small; S402: Visually output the ash content of the corresponding coal to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and the scheduling task analysis data for the power generation enterprise, and output the scheduling tasks of each shift and pre-execute them.

7. An artificial intelligence-based power generation byproduct sales supervision system, characterized by: The system includes a database access module, an ash production prediction and analysis module, a customer demand allocation and analysis module, and a scheduling task planning module; The database access module links the data storage database of the power generation enterprise by setting up an access channel, and retrieves the enterprise's power generation demand data and the sampling data of the coal to be burned by accessing the database; the ash production prediction and analysis module analyzes the basic ash data of the fuel according to the retrieved sampling data of the coal to be burned of the corresponding periodic batch; combines the enterprise's power generation demand data with the basic ash analysis results of the corresponding batch of coal to be burned, and predicts and analyzes the enterprise's power generation ash production on the next day; the customer demand allocation analysis module obtains real-time ash warehouse material level data based on the enterprise's next-day power generation ash production forecast data, and predicts and analyzes the ash warehouse material level; combines the customer's historical transaction data to build a customer information matrix, obtains the corresponding customer's allocation weight based on the customer information matrix, and analyzes the next-day coal ash allocation amount of each customer; The scheduling task planning module constructs a scheduling model to formulate a scheduling task set based on the coal ash distribution analysis results of each customer, and performs scheduling task planning for the ash storage; The scheduling task planning results are output, and the corresponding process analysis data output for the power generation enterprise is carried out through visualization.

8. The power generation byproduct sales supervision system based on artificial intelligence according to claim 7 is characterized by: The database access module includes a database channel setting unit and a data retrieval unit; The database channel establishment unit establishes a data access channel through the enterprise database management port, generates an access request service, determines the access request key search term through the verification access service, performs data search and positioning in the database with the key search term, and outputs the searched data; The data retrieval unit uses database retrieval services to retrieve the enterprise's next day's power generation demand data and coal material sampling data to be burned; the enterprise's next day's power generation demand data is the enterprise's next day's power generation load task data and electricity price data; the coal material sampling data to be burned is the batch data of the coal material to be burned consumed by the enterprise's next day's power generation and the drying processing data and quality change data of the sampled coal material of the corresponding batch of coal material to be burned.

9. The power generation byproduct sales supervision system based on artificial intelligence according to claim 8 is characterized by: The ash production prediction and analysis module includes a coal-based ash analysis unit to be burned and a next-day ash production prediction unit; The coal material to be burned basic ash analysis unit retrieves the sampling data of the coal material to be burned samples corresponding to the batch to be burned period, and analyzes the basic ash data of the target coal material to be burned sample according to the recorded data of the target coal material to be burned sample after drying and its quality change data; constructs a sample set by repeatedly sampling the same batch of coal material to be burned; and comprehensively analyzes the basic ash data of the current batch of coal material to be burned according to the sample set; The next-day ash production prediction unit combines the ash analysis data of the corresponding batch of coal to be burned with the next-day power generation demand data of the power generation enterprise to predict and analyze the next-day power generation ash production of the enterprise; obtains the power generation operation parameters of the enterprise's power generation equipment through a database, and analyzes the coal consumption rate of the enterprise's power generation equipment; analyzes the total coal consumption of the enterprise's power generation on the next day in combination with the coal consumption rate of the enterprise's power generation equipment and the enterprise's power generation demand on the next day; and analyzes the total ash production of the enterprise on the next day in combination with the total coal consumption of the enterprise on the next day.

10. The power generation byproduct sales supervision system based on artificial intelligence according to claim 9 is characterized by: The customer demand allocation analysis module includes an ash storage level prediction analysis unit and a customer demand allocation analysis unit; The ash bin level prediction and analysis unit retrieves the enterprise's ash bin data through a database; the ash bin data includes the ash bin number and the real-time level of each ash bin; based on the predicted value of the total ash production of the enterprise the next day, combined with the storage space attribute of the ash bin, the total ash production of the next day is converted into the ash bin level height; the real-time level of each ash bin is retrieved, and the storage level of each ash bin is predicted and analyzed by evenly distributing and storing the total ash production of the next day; by setting the ash bin level warning value, the ash bin is regulated and the level of each ash bin after the ash is distributed is recorded; The customer demand allocation analysis unit retrieves the customer data of gray material demand for the next day from the database, and constructs a corresponding customer information matrix according to the historical transaction data of each customer; wherein a two-row and one-column customer information matrix is ​​constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions; coordinate points are constructed by the total number of historical transactions and the total amount of gray materials in the historical transactions of each customer and mapped to the same plane coordinate system, adjacent coordinate points of each customer coordinate point are connected, and the connecting line segments of each adjacent coordinate point are vectorized to obtain the feature vectors between each adjacent coordinate point; adjacent feature vectors are synthesized by vector synthesis calculation to obtain a unique customer feature vector in the plane coordinate system; then, allocation weight analysis is performed on each customer in combination with the unique customer feature vector; and the gray material allocation amount of each customer on the next day is analyzed according to the allocation weight of each customer.

11. The power generation byproduct sales supervision system based on artificial intelligence according to claim 10 is characterized by: The scheduling task planning module includes a scheduling task planning unit and a comprehensive data feedback unit; The dispatch task planning unit specifies a dispatch task set for each customer based on the coal ash distribution analysis results of each customer by constructing a dispatch model; analyzes the number of dispatch vehicles for each customer the next day by combining the carrying capacity of the dispatch truck; and analyzes the dispatch shifts of the dispatch vehicles by coordinating the number of dispatch vehicles for each customer and combining the dynamic diversion coefficient of the enterprise; Formulate the scheduling task set for each shift by constructing a scheduling model; define the priority function to assign priority to the material level height of the ash storage for each task set in the single-shift scheduling task set; analyze the priority value of each task in a single shift; sort the task set in descending order from large to small according to the priority value analysis results of each task in the single-shift task set, and take the task corresponding to the maximum value as the most prioritized task; combine the priority value analysis results of each task in the task set, and perform allocation analysis on the scheduling vehicles for each task in the corresponding shift task set; satisfy the ash material delivery of each task's vehicle according to the allocation weight of each customer from large to small; The comprehensive data feedback unit visualizes the output of the corresponding coal material ash content to be burned, the total amount of coal to be burned the next day, the total ash production the next day, the customer demand distribution analysis and scheduling task analysis data for the power generation enterprise, and outputs and pre-executes the scheduling tasks for each shift.

Images