Boiler waste heat recovery energy scheduling management method and system and medium

Abstract

The invention belongs to the technical field of boiler energy management, and particularly relates to a boiler waste heat recovery energy scheduling management method and system and a medium, and the system comprises a multi-dimensional sensing array module, a heat energy form identification module, a dynamic scheduling optimization module, an intelligent execution control module, a waste heat recovery influence judgment module and a waste heat recovery supervision end. According to the invention, the heat energy form identification module identifies the waste heat type and the quality attenuation trend based on the collected data information, the dynamic scheduling optimization module integrates various input information and reasonably generates a scheduling instruction, and the intelligent execution control module analyzes the scheduling instruction and carries out corresponding scheduling control operation. Efficient utilization and intelligent management of boiler waste heat resources are achieved, reasonable optimization treatment measures are taken in time by analyzing the influence condition of boiler waste heat recovery stability, the stability, safety and high efficiency of the subsequent boiler waste heat recovery process are guaranteed, and the management difficulty of supervisors is further reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of boiler energy management, and specifically to a method, system and medium for boiler waste heat recovery energy scheduling management. Background Art

[0002] Boiler waste heat recovery refers to the process of converting waste heat generated during the operation of a boiler (such as flue gas, steam condensation, high-temperature flue gas, etc.) into utilizable energy (such as electric energy, heat energy) through technical means, thereby reducing energy waste, lowering operating costs and reducing environmental pollution. For related content, reference can be made to Chinese invention patents with publication numbers CN118548736A, CN116412536A or CN118980086A; Traditional boiler waste heat recovery systems have problems such as single-dimensional data collection, static energy scheduling strategies and poor equipment coordination, resulting in low waste heat utilization efficiency and insufficient system operation stability. Existing technologies generally focus on optimizing single links, lacking a full-process dynamic scheduling mechanism from data perception to execution control, which is not conducive to the efficient utilization and intelligent management of boiler waste heat resources, and cannot reasonably analyze and accurately warn of the affected status during the boiler waste heat recovery scheduling process, making it difficult to ensure the stable, safe and efficient nature of the boiler waste heat recovery process, and the management of boiler waste heat recovery is difficult; In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, system and medium for boiler waste heat recovery energy scheduling management, which solves the problems that existing technologies lack a full-process dynamic scheduling mechanism from data perception to execution control, and cannot reasonably analyze and accurately warn of the affected status during the boiler waste heat recovery scheduling process, and is not conducive to the efficient utilization and intelligent management of boiler waste heat resources.

[0004] To achieve the above purpose, the present invention provides the following technical solutions: A boiler waste heat recovery energy scheduling management system includes a multi-dimensional sensing array module, a heat energy form identification module, a dynamic scheduling optimization module, an intelligent execution control module, a waste heat recovery impact judgment module and a waste heat recovery supervision terminal; The multi-dimensional sensing array module monitors several key nodes of the boiler flue gas by deploying several types of monitoring instruments, collects various monitoring data and transmits them to the heat energy form identification module through industrial Ethernet after preprocessing; the heat energy form identification module identifies the waste heat type and quality decay trend based on the data information transmitted by the multi-dimensional sensing array module, and sends the identification information to the dynamic scheduling optimization module; The dynamic scheduling optimization module integrates various input information, uses an improved ant colony algorithm to search for the optimal scheduling scheme in the solution space, balances the three-dimensional goals of economy, environmental protection, and reliability, generates scheduling instructions, and sends them to the intelligent execution control module; The intelligent execution control module analyzes the scheduling instructions, converts the scheduling instructions into corresponding control signals, performs corresponding scheduling control operations on relevant recycling equipment based on the control signals, and sends the control information to the waste heat recovery supervision terminal; the waste heat recovery impact judgment module analyzes the affected status of the boiler waste heat recovery stability, generates a high waste heat recovery impact signal or a low waste heat recovery impact signal through analysis, and sends the high waste heat recovery impact signal or the low waste heat recovery impact signal to the waste heat recovery supervision terminal. When the waste heat recovery supervision terminal receives the high waste heat recovery impact signal, it issues a warning.

[0005] Furthermore, the monitoring instruments deployed by the multi-dimensional sensing array module include an infrared thermal imager and a piezoelectric flow sensor. Among them, the infrared thermal imager is used to scan the boiler flue gas duct, generate a temperature field distribution map with a resolution of 0.1 °C; the piezoelectric flow sensor is used to measure the steam / smoke flow velocity with a range of 0-30 m / s and an accuracy of ±0.5%; the data preprocessing process of the multi-dimensional sensing array module includes noise filtering, data alignment, and spatio-temporal interpolation.

[0006] Furthermore, the operation process of the heat energy form identification module includes: Feature extraction: Extract temperature entropy value, flow velocity fluctuation coefficient, and latent heat of phase change characteristic parameters; Dynamic classification: Use the fuzzy clustering algorithm to classify the thermal field model and generate labels in combination with the equipment condition database; Quality prediction: Based on the LSTM neural network model, input the current waste heat parameters and environmental variables to predict the quality decay time.

[0007] Furthermore, the input information integrated by the dynamic scheduling optimization module includes waste heat form labels, quality decay prediction values, grid time-of-use electricity price information, user-side heat load prediction curves, and equipment constraint conditions.

[0008] Furthermore, the control operations of the intelligent execution control module include the start-stop and power regulation of the organic Rankine cycle generator set, the charge and discharge control of the heat storage tank, and the speed regulation of the circulation pump / fan, and the recovery paths for boiler waste heat recovery involve organic Rankine cycle power generation, heating / hot water systems, and preheating air / materials.

[0009] Furthermore, the specific analysis process of the waste heat recovery impact judgment module is as follows: Collect the moment when the intelligent execution control module receives the scheduling instruction and mark it as the moment to be parsed, and collect the moment when the intelligent execution module completes the corresponding control operation and mark it as the controlled moment. Calculate the time difference between the controlled moment and the moment to be parsed to obtain the response coefficient. Compare the response coefficient with the corresponding preset response coefficient threshold. If the response coefficient exceeds the corresponding preset response coefficient threshold, mark the corresponding response coefficient as the characteristic coefficient. Obtain the number of characteristic coefficients during the detection period and calculate the ratio with the total number of response coefficients to obtain the non-efficient execution value. Calculate the ratio of the response coefficient to the corresponding preset response coefficient threshold to obtain the response measurement value. Calculate the average value of all response measurement values during the detection period to obtain the response decision value. Compare the non-efficient execution value and the response decision value with the preset non-efficient execution threshold and the preset response decision threshold respectively. If the non-efficient execution value or the response decision value exceeds the corresponding preset threshold, generate a high impact signal for waste heat recovery. If both the non-efficient execution value and the response decision value do not exceed the corresponding preset thresholds, obtain the device operation mark information of all recovery and utilization devices. If there are non-dominant devices in use, generate a high impact signal for waste heat recovery. If there are no non-dominant devices in use, generate a low impact signal for waste heat recovery.

[0010] Further, the waste heat recovery impact judgment module is communicatively connected to the recovery and utilization device diagnosis module. The recovery and utilization device diagnosis module conducts operation monitoring and diagnosis on all involved recovery and utilization devices, marks the corresponding recovery and utilization devices as non-dominant devices in use or highly dominant devices in use through analysis, and sends the device operation mark information of all involved recovery and utilization devices to the waste heat recovery impact judgment module.

[0011] Further, the specific analysis process of the recovery and utilization device diagnosis module is as follows: When the corresponding recovery and utilization device is in operation, obtain the various operation parameters that need to be monitored during the operation of the corresponding recovery and utilization device. Mark the deviation value of the real-time data value of the corresponding operation parameter compared with the corresponding set standard data value as the abnormal target value. If the abnormal target value exceeds the corresponding preset allowable value, mark the corresponding operation parameter as the parameter to be optimized. If there are parameters to be optimized, determine that the corresponding recovery and utilization device is in the improvement warning state. Obtain the total duration of the corresponding recovery and utilization device in the improvement warning state during the detection period and calculate the ratio with the total operation duration of the corresponding recovery and utilization device during the detection period to obtain the improvement warning time evaluation value. Compare the improvement warning time evaluation value with the corresponding preset improvement warning time evaluation threshold. If the improvement warning time evaluation value exceeds the corresponding preset improvement warning time evaluation threshold, mark the corresponding recovery and utilization device as a non-dominant device in use. If the improved warning time evaluation value does not exceed the corresponding preset improved warning time evaluation threshold, then obtain the ratio of all abnormal target values of the corresponding operating parameters during the detection period to the corresponding preset allowable values, and calculate the average value of all ratio results to obtain the target performance value. Mark the ratio result with the largest value during the detection period as the target amplitude value, and define the ratio of the duration during which the corresponding operating parameter is marked as the parameter to be optimized to the total operating duration of the corresponding recycling equipment during the detection period as the time measurement value to be optimized; Calculate the parameter coupling value by performing weighted summation of the time measurement value to be optimized, the target performance value, and the target amplitude value, and calculate the ratio of the parameter coupling value to the corresponding preset parameter coupling threshold to obtain the initial parameter value; Preset a set of preset operating influence weight values corresponding to each operating parameter in advance, multiply the initial parameter value by the corresponding preset operating influence weight value to obtain the target hazard value, and sum up the target hazard values of all operating parameters to obtain the operating advantage coefficient; Compare the operating advantage coefficient with the preset operating advantage coefficient threshold. If the operating advantage coefficient exceeds the preset operating advantage coefficient threshold, mark the corresponding recycling equipment as a non-dominant utilization equipment; If the operating advantage coefficient does not exceed the preset operating advantage coefficient threshold, mark the corresponding recycling equipment as a high-dominance utilization equipment.

[0012] Furthermore, the present invention also proposes a method for boiler waste heat recovery energy scheduling management, including the following steps: Step 1: Data monitoring and collection; Step 2: Identify the waste heat type and the quality decay trend; Step 3: Integrate various input information to generate a scheduling instruction; Step 4: Analyze the scheduling instruction and perform corresponding scheduling control operations on the relevant recycling equipment; Step 5: Analyze the affected status of the boiler waste heat recovery stability, and when generating a high-impact signal for waste heat recovery, make the waste heat recovery supervision end issue a warning.

[0013] A computer storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements a method for boiler waste heat recovery energy scheduling management as described above.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. In the present invention, monitoring and data acquisition are carried out through a multi-dimensional sensing array module. The thermal energy form identification module identifies the type of waste heat and the trend of quality decay based on the collected data information. The dynamic scheduling optimization module integrates various input information and reasonably generates scheduling instructions. The intelligent execution control module analyzes the scheduling instructions and performs corresponding scheduling control operations to achieve multi-objective collaborative optimization of energy efficiency, economy, and environmental protection, which is conducive to the efficient utilization and intelligent management of boiler waste heat resources; 2. In the present invention, the operation monitoring and diagnosis of all recycling equipment involved are carried out through the recycling equipment diagnosis module to determine non-dominant utilization equipment and highly dominant utilization equipment, providing information support for the analysis process of the waste heat recovery impact judgment module. The waste heat recovery impact judgment module analyzes the affected status of the stability of boiler waste heat recovery and makes reasonable optimization measures in a timely manner to ensure the stable, safe, and efficient subsequent boiler waste heat recovery process, further reducing the management difficulty of supervisors. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings; Figure 1 It is the system block diagram of the first embodiment in the present invention; Figure 2 It is the system block diagram of the second embodiment in the present invention; Figure 3 It is the method flowchart of the third embodiment in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1: As Figure 1 shown, a boiler waste heat recovery energy scheduling and management system proposed by the present invention includes a multi-dimensional sensing array module, a thermal energy form identification module, a dynamic scheduling optimization module, an intelligent execution control module, a waste heat recovery impact judgment module, and a waste heat recovery supervision terminal; The multi-dimensional sensing array module monitors several key nodes of the boiler flue gas by deploying several types of monitoring instruments, collects various monitoring data (such as temperature, flow rate, pressure, etc.), and transmits them to the thermal energy form identification module through industrial Ethernet after preprocessing; It should be noted that the monitoring instruments deployed in the multi-dimensional sensing array module include an infrared thermal imager, a piezoelectric flow sensor, etc. Among them, the infrared thermal imager is used to scan the boiler flue gas exhaust pipe to generate a temperature field distribution map with a resolution of 0.1 °C; the piezoelectric flow sensor is used to measure the steam / smoke flow velocity with a range of 0 - 30 m / s and an accuracy of ±0.5%; the data preprocessing process of the multi-dimensional sensing array module includes noise filtering, data alignment, and spatio-temporal interpolation.

[0018] Based on the data information transmitted by the multi-dimensional sensing array module, the waste heat form identification module identifies the type of waste heat (sensible heat / latent heat / mixed heat) and the quality decay trend, and sends the identification information to the dynamic scheduling optimization module to guide the generation of scheduling strategies; the operation process of the waste heat form identification module includes: Feature extraction: Extract the temperature entropy value (characterizing the uniformity of the thermal field), the flow velocity fluctuation coefficient (reflecting the turbulence intensity), and the latent heat of phase change characteristic parameters (through DSC curve fitting); Dynamic classification: Use the fuzzy c-means (FCM) algorithm to classify the thermal field model, and generate labels in combination with the equipment operating condition database (historical waste heat form data);

[0019] Quality prediction: Based on the LSTM neural network model, input the current waste heat parameters and environmental variables (such as ambient temperature, humidity), and predict the quality decay time (such as the conversion moment of "mixed heat → sensible heat").

[0020] It should be noted that the recovery paths for boiler waste heat recovery involve organic Rankine cycle power generation (such as flue gas waste heat utilization), heating / hot water systems (such as steam condensation waste heat utilization), and preheating air / materials (such as the utilization of high-temperature flue gas); the dynamic scheduling optimization module integrates various input information, and uses an improved ant colony optimization (ACO) algorithm to search for the optimal scheduling scheme in the solution space, balancing the three-dimensional goals of economy (lowest cost), environmental protection (least carbon emissions), and reliability (safe operation of equipment), generating scheduling instructions and sending them to the intelligent execution control module.

[0021] Furthermore, the input information integrated by the dynamic scheduling optimization module includes waste heat form labels, quality decay prediction values, grid time-of-use electricity price information (obtained through the electricity market API), user-side heat load prediction curves (predicted based on the historical data LSTM model), and equipment constraint conditions (such as the maximum temperature difference of the heat exchanger, the pipeline pressure limit, etc.).

[0022] The intelligent execution control module analyzes and schedules instructions, converts the scheduling instructions into corresponding control signals, and performs corresponding scheduling control operations on relevant recycling equipment based on the control signals (for example, starting and stopping of organic Rankine cycle generator sets and power regulation, charging and discharging control of heat storage tanks, and speed regulation of circulating pumps / fans, etc.). By dynamically allocating waste heat to the optimal utilization paths (power generation, heat supply, energy storage), and combining external constraints such as electricity price, heat load, and carbon tax, equipment-level control instructions are generated to achieve multi-objective collaborative optimization of energy efficiency, economy, and environmental protection, and the control information is sent to the waste heat recovery supervision terminal to facilitate supervisors to detailedly grasp the scheduling control information.

[0023] For example, typical scheduling scenarios are as follows: Scenario 1: Sudden increase in boiler load: Problem: The exhaust gas temperature rises, and the waste heat quality improves (the proportion of latent heat in the mixed heat increases).

[0024] Scheduling actions: Start the standby organic Rankine cycle generator set for power generation (high-value utilization); adjust the valve opening to increase the flow of exhaust gas to the organic Rankine cycle generator set, and increase the fan speed to enhance the heat transfer efficiency.

[0025] Result: The waste heat utilization rate is increased, the power generation is increased, and at the same time, the damage to equipment caused by too high exhaust gas temperature is avoided.

[0026] Scenario 2: Low electricity price and low heat load: Problem: Excessive waste heat supply and insufficient user demand.

[0027] Scheduling actions: Shut down the organic Rankine cycle generator set, store the waste heat in the heat storage tank; adjust the flow rate of the circulating pump to reduce the heat transfer rate.

[0028] Result: The waste heat energy is stored and released for power generation during the peak electricity price period.

[0029] The waste heat recovery impact judgment module analyzes the affected status of the stability of boiler waste heat recovery, generates a high waste heat recovery impact signal or a low waste heat recovery impact signal through analysis, and sends the high waste heat recovery impact signal or the low waste heat recovery impact signal to the waste heat recovery supervision terminal; When the waste heat recovery supervision terminal receives the high waste heat recovery impact signal, it issues a warning to remind the supervisor to timely conduct a cause investigation and make reasonable optimization measures to ensure the stable, safe and efficient subsequent boiler waste heat recovery process, significantly reducing the management difficulty of the supervisor, with high intelligence and automation level. The specific analysis process of the waste heat recovery impact judgment module is as follows: The time when the intelligent execution control module receives the scheduling instruction is collected and marked as the time to be analyzed, and the time when the intelligent execution module completes the corresponding control operation is collected and marked as the controlled time, and the time difference between the controlled time and the time to be analyzed is calculated to obtain the response coefficient; wherein, the larger the value of the response coefficient is, the less timely the execution of the corresponding scheduling instruction is; Compare the response coefficient with the corresponding preset response coefficient threshold value, if the response coefficient exceeds the corresponding preset response coefficient threshold value, it indicates that the execution of the corresponding scheduling instruction is not timely, then mark the corresponding response coefficient as a characteristic coefficient; The number of characteristic coefficients in the detection period is obtained and the ratio thereof is calculated with the total number of response coefficients to obtain a non-efficient execution value, and the response coefficient is calculated with the corresponding preset response coefficient threshold to obtain a response detection value, and all response detection values in the detection period are averaged to obtain a response decision value; The non-efficient execution value and the response decision value are numerically compared with the preset non-efficient execution threshold and the preset response decision threshold, respectively. If the non-efficient execution value or the response decision value exceeds the corresponding preset threshold, it indicates that the execution efficiency of the dispatch instruction during the detection period is lower, which is not conducive to ensuring the timeliness of the dispatch control, and has a greater adverse impact on the waste heat recovery process, and a waste heat recovery high impact signal is generated; If neither the inefficient execution value nor the response decision value exceeds the corresponding preset threshold, the equipment operation mark information of all recycling equipment is obtained. If non-advantageous equipment is used, it indicates that the waste heat recovery process is greatly adversely affected during the detection period, and a high-impact waste heat recovery signal is generated; if non-advantageous equipment is not used, it indicates that the waste heat recovery process is less adversely affected during the detection period, and a low-impact waste heat recovery signal is generated.

[0030] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the waste heat recovery impact judgment module is communicatively connected to the recycling equipment diagnosis module, and the recycling equipment diagnosis module performs operation monitoring and diagnosis on all the recycling equipment involved, and marks the corresponding recycling equipment (organic Rankine cycle generator set, heat storage tank, circulation pump / fan and other equipment) as non-advantageous equipment or high-advantage equipment through analysis; And the equipment operation mark information of all the recycling equipment involved is sent to the waste heat recovery impact judgment module and the waste heat recovery supervision end, which can reasonably analyze and accurately judge the operation performance of each recycling equipment, and can also provide information support for the analysis process of the waste heat recovery impact judgment module to ensure the accuracy of its analysis results, and is conducive to the supervisory personnel to carry out targeted inspection, maintenance or replacement of the corresponding recycling equipment, ensuring the stability, safety and efficiency of the subsequent boiler waste heat recovery scheduling process, with a high level of intelligence; the specific analysis process of the recycling equipment diagnosis module is as follows: When the corresponding recycling equipment is in operation, various operating parameters that need to be monitored during the operation of the corresponding recycling equipment are obtained. The deviation value of the real-time data value of the corresponding operating parameter compared to the set standard data value is marked as an abnormal target value. If the abnormal target value exceeds the corresponding preset allowable value, indicating that there is an abnormality in the corresponding operating parameter, then the corresponding operating parameter is marked as a parameter to be optimized. If there are parameters to be optimized, indicating that there are current operation hazards in the corresponding recycling equipment, then it is judged that the corresponding recycling equipment is in an improvement warning state; The total duration during which the corresponding recycling equipment is in the improvement warning state within the detection period is obtained, and the ratio is calculated with the total operating duration of the corresponding recycling equipment within the detection period to obtain an improvement warning time evaluation value. The improvement warning time evaluation value is numerically compared with the corresponding preset improvement warning time evaluation threshold. If the improvement warning time evaluation value exceeds the corresponding preset improvement warning time evaluation threshold, indicating that the operating condition of the corresponding recycling equipment during the detection period is poor, then the corresponding recycling equipment is marked as a non-dominant utilization equipment; If the improvement warning time evaluation value does not exceed the corresponding preset improvement warning time evaluation threshold, then the ratio of all abnormal target values of the corresponding operating parameter compared to the corresponding preset allowable value within the detection period is obtained, and the mean value of all ratio results is calculated to obtain a target performance value. The ratio result with the largest numerical value of the corresponding operating parameter within the detection period is marked as the target amplitude value, and the ratio of the duration during which the corresponding operating parameter is marked as a parameter to be optimized within the detection period to the total operating duration of the corresponding recycling equipment within the detection period is defined as the time measurement value to be optimized; The parameter coupling value is calculated by weighted summation of the time measurement value to be optimized, the target performance value, and the target amplitude value, that is, corresponding preset weight coefficients are assigned to the time measurement value to be optimized, the target performance value, and the target amplitude value, and the time measurement value to be optimized, the target performance value, and the target amplitude value are respectively multiplied by the corresponding preset weight coefficients, and the sum of the three product results is marked as the parameter coupling value. It should be noted that the larger the numerical value of the parameter coupling value, the worse the comprehensive parameter performance of the corresponding operating parameter in the corresponding recycling equipment during the detection period, and the greater the adverse impact on the stable operation of the corresponding recycling equipment; The ratio of the parameter coupling value to the corresponding preset parameter coupling threshold is calculated to obtain an initial parameter value. It is preset that each operating parameter corresponds to a set of preset operating influence weight values greater than zero, and moreover, the more important the stability of the corresponding operating parameter, the larger the value of the corresponding preset operating influence weight value. The initial parameter value is multiplied by the corresponding preset operating influence weight value to obtain a target hazard value, and the sum of the target hazard values of all operating parameters is calculated to obtain an operation advantage coefficient; Numerically compare the operation advantage coefficient with the preset operation advantage coefficient threshold. If the operation advantage coefficient exceeds the preset operation advantage coefficient threshold, it indicates that the overall operation condition of the corresponding recycling equipment during the detection period is poor, and then mark the corresponding recycling equipment as a non - dominant utilization equipment; if the operation advantage coefficient does not exceed the preset operation advantage coefficient threshold, it indicates that the overall operation condition of the corresponding recycling equipment during the detection period is good, and then mark the corresponding recycling equipment as a high - advantage utilization equipment.

[0031] Embodiment 3: As Figure 3 shown, the difference between this embodiment and Embodiment 1 and Embodiment 2 is that a boiler waste heat recovery energy scheduling and management method proposed by the present invention includes the following steps: Step 1, data monitoring and collection; Step 2, identify the waste heat type and the quality decay trend; Step 3, integrate various input information and generate a scheduling instruction; Step 4, analyze the scheduling instruction and perform corresponding scheduling control operations on relevant recycling equipment; Step 5, analyze the affected condition of the boiler waste heat recovery stability, and when generating a high - impact signal for waste heat recovery, make the waste heat recovery supervision end issue a warning.

[0032] Moreover, the present invention also proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the above - mentioned boiler waste heat recovery energy scheduling and management method. Those of ordinary skill in the art can understand that all or part of the steps of implementing the above - mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer - readable storage medium. When the program is executed, it executes the steps including the above - mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

[0033] Working principle of the present invention: During use, monitoring and data collection are carried out through the multi-dimensional sensing array module. The thermal energy form identification module identifies the type of waste heat and the trend of quality decay based on the collected data information, guiding the generation of the scheduling strategy. The dynamic scheduling optimization module integrates various input information and reasonably generates scheduling instructions. The intelligent execution control module analyzes the scheduling instructions and performs corresponding scheduling control operations on relevant recovery and utilization equipment, which can dynamically allocate waste heat to the optimal utilization path, and combines external constraints such as electricity price, heat load, and carbon tax to generate equipment-level control instructions, realizing multi-objective collaborative optimization of energy efficiency, economy, and environmental protection, facilitating the efficient utilization and intelligent management of boiler waste heat resources. Moreover, the waste heat recovery impact judgment module analyzes the affected status of the stability of boiler waste heat recovery, conducts a cause investigation and makes reasonable optimization measures when generating a high-impact signal for waste heat recovery, ensuring the stable, safe, and efficient subsequent boiler waste heat recovery process, and further reducing the management difficulty of supervisors.

[0034] In the technical solution of the present invention, the setting of thresholds, preset values, preset ranges, etc. is for result comparison and analysis to determine whether it is good or bad. Regarding the size and value of them, they are set and stored by combining the large model analysis of sample data and manual experience, and can also be appropriately adjusted according to seasonal or regular influencing conditions; and the setting of preset weight coefficients, influencing factors, etc. is to allocate specific values according to the influence degree of each parameter on the result, finally reflecting the influence status on the result, and is also set and stored by combining the large model analysis of sample data and manual experience, and can also be appropriately adjusted according to seasonal or regular influencing conditions.

[0035] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor limit the present invention to only the specific implementation manners. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A boiler waste heat recovery energy scheduling and management system, characterized in that, It includes a multi-dimensional sensing array module, a waste heat form identification module, a dynamic scheduling optimization module, an intelligent execution control module, a waste heat recovery impact judgment module, and a waste heat recovery supervision terminal; the multi-dimensional sensing array module monitors several key nodes of the boiler flue gas, collects various monitoring data, and after preprocessing, transmits them to the waste heat form identification module, and the waste heat form identification module identifies the waste heat type and the quality decay trend based on the received data information; The dynamic scheduling optimization module integrates various input information, uses an improved ant colony algorithm to search for the optimal scheduling scheme in the solution space, generates a scheduling instruction, and sends it to the intelligent execution control module; The intelligent execution control module analyzes the scheduling instruction, converts the scheduling instruction into a corresponding control signal, performs corresponding scheduling control operations on relevant recovery and utilization equipment based on the control signal, and sends the control information to the waste heat recovery supervision terminal; the waste heat recovery impact judgment module analyzes the affected status of the boiler waste heat recovery stability, generates a high waste heat recovery impact signal or a low waste heat recovery impact signal through analysis, and the waste heat recovery supervision terminal issues a warning when receiving the high waste heat recovery impact signal.

2. The energy scheduling and management system for recovering waste heat of a boiler according to claim 1, wherein, The monitoring instruments deployed in the multi-dimensional sensing array module include an infrared thermal imager and a piezoelectric flow sensor. Among them, the infrared thermal imager is used to scan the boiler flue gas pipeline to generate a temperature field distribution map; the piezoelectric flow sensor is used to measure the steam / smoke flow rate; the data preprocessing process of the multi-dimensional sensing array module includes noise filtering, data alignment, and spatio-temporal interpolation.

3. A boiler waste heat recovery energy scheduling and management system according to claim 1, characterized in that, The operation process of the waste heat form identification module includes: Feature extraction: Extract temperature entropy value, flow rate fluctuation coefficient, and latent heat of phase change characteristic parameters; dynamic classification: Use fuzzy clustering algorithm to classify the thermal field model, and generate labels in combination with the equipment operating condition database; quality prediction: Based on the LSTM neural network model, input the current waste heat parameters and environmental variables to predict the quality decay time.

4. A boiler waste heat recovery energy scheduling and management system according to claim 1, characterized in that, The input information integrated by the dynamic scheduling optimization module includes waste heat form label, quality decay prediction value, grid time-of-use electricity price information, user-side heat load prediction curve, and equipment constraint conditions.

5. A boiler waste heat recovery energy scheduling and management system according to claim 1, characterized in that, The control operations of the intelligent execution control module include starting and stopping the organic Rankine cycle power generation unit and power regulation, charging and discharging control of the heat storage tank, and regulating the speed of the circulation pump / fan, and the recovery path for boiler waste heat recovery involves organic Rankine cycle power generation, heating / hot water system, and preheating air / material.

6. The energy scheduling and management system for recovering waste heat of a boiler according to claim 1, characterized in that The specific analysis process of the waste heat recovery impact judgment module is as follows: Obtain the number of characteristic coefficients during the detection period and calculate the ratio with the total number of response coefficients to obtain the non-efficient execution value, and calculate the average value of all response values during the detection period to obtain the response decision value. If the non-efficient execution value or the response decision value exceeds the corresponding preset threshold, generate a high waste heat recovery impact signal; if both the non-efficient execution value and the response decision value do not exceed the corresponding preset threshold, obtain the equipment operation mark information of all recovery and utilization equipment. If there is the use of non-dominant equipment, generate a high waste heat recovery impact signal; if there is no use of non-dominant equipment, generate a low waste heat recovery impact signal.

7. A boiler waste heat recovery energy scheduling and management system according to claim 6, characterized in that, The waste heat recovery impact judgment module is communicatively connected to the recycling equipment diagnosis module. The recycling equipment diagnosis module conducts operation monitoring and diagnosis on all involved recycling equipment, and through analysis, marks the corresponding recycling equipment as non-dominant utilization equipment or high-dominance utilization equipment, and sends the equipment operation marking information to the waste heat recovery impact judgment module and the waste heat recovery supervision terminal.

8. A boiler waste heat recovery energy scheduling and management system according to claim 5, characterized in that, The specific analysis process of the recycling equipment diagnosis module is as follows: Obtain the total duration of the corresponding recycling equipment in the improvement warning state during the detection period and calculate the ratio with the total operation duration of the corresponding recycling equipment during the detection period to obtain the improvement warning time evaluation value. If the improvement warning time evaluation value exceeds the corresponding preset improvement warning time evaluation threshold, mark the corresponding recycling equipment as non-dominant utilization equipment; If the improvement warning time evaluation value does not exceed the corresponding preset improvement warning time evaluation threshold, sum up the target hazard values of all operation parameters to obtain the operation advantage coefficient; if the operation advantage coefficient exceeds the preset operation advantage coefficient threshold, mark the corresponding recycling equipment as non-dominant utilization equipment; otherwise, mark the corresponding recycling equipment as high-dominance utilization equipment.

9. A method for energy scheduling management of boiler waste heat recovery, characterized in that, It includes the following steps: Step 1, data monitoring and collection; Step 2, identifying the waste heat type and the quality decay trend; Step 3, integrating various input information to generate a scheduling instruction; Step 4, parsing the scheduling instruction and performing corresponding scheduling control operations on the relevant recycling equipment; Step 5, analyzing the affected status of the boiler waste heat recovery stability, and when generating a high waste heat recovery impact signal, making the waste heat recovery supervision terminal issue a warning.

10. A computer storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by a processor, it implements a boiler waste heat recovery energy scheduling management method as described in claim 9.

Images