Cogeneration control optimization system

Abstract

The invention relates to the technical field of combined cooling heating and power, and discloses a combined cooling heating and power control optimization system which is composed of a data acquisition module, a data cleaning module, a data complementation module, a data verification module and a data integration module. According to the method, data of heat, electric quantity, cooling capacity and equipment operation states are obtained from various sensors and data sources, the system can obtain comprehensive original data, in the data cleaning stage, the system can remove noise and abnormal values in the data, smooth processing is conducted on the data, and the data cleaning efficiency is improved. According to abnormal value detection, data points deviating from a normal range are recognized through a statistical method, so that the quality of a data set is improved, missing data are filled by a system through a linear interpolation method, missing values are estimated through the linear relation between known data points, information incompleteness caused by data missing is avoided, and the accuracy of data processing is improved. The beneficial effect of performing earlier stage processing on the collected data to avoid errors or missing is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of cogeneration of cooling, heating and power, and in particular to a cogeneration control optimization system. Background Art

[0002] The combined heat and power system is a distributed energy system based on the cascade utilization of energy. The system is installed near the load side. The gas turbine consumes natural gas to generate electricity. The waste heat recovery system recycles the waste heat generated during the gas turbine power generation process for heating or cooling, thereby realizing the combined supply of heat, electricity and cooling on the load side of the system. In this way, the primary energy utilization rate of the entire system is greatly improved, and the cascade utilization of energy is realized. On the energy supply side, the combined heat and power system is composed of different energy generation equipment, and the various energies provided by the system are very different. On the energy consumption side, users have different needs for various energies, and they have different timeliness. This requires that the output of the combined heat and power system must take into account both timeliness and diversity. Under the different demand conditions of heat, cooling and electricity loads in the application scenarios, to achieve the economic operation of the combined heat and power system, a specific optimal control strategy is required to achieve it.

[0003] After searching, it was found that the publication number is CN109471362A, which is a cogeneration optimization system and method. The system includes: a data acquisition module, a system optimization module and a system scheduling module; at the same time, the present invention modularizes the system, which is easy to control and execute the cogeneration system optimization plan. The cogeneration system optimization method based on the improved firefly algorithm greatly improves the disadvantage of the traditional firefly algorithm that it is easy to fall into the local optimal solution by improving the attraction formula and the position update formula, and improves the convergence speed. It can effectively improve the algorithm's optimization ability and obtain a more reasonable cogeneration system optimization plan.

[0004] Although the aforementioned technical solution realizes the optimization control system by improving the algorithm, the system includes a data acquisition module, which means that it is highly dependent on the accuracy and completeness of the input data. If there are errors or omissions in the data, the accuracy of the optimization results will be affected. Summary of the invention

[0005] Technical issues solved:

[0006] In view of the deficiencies in the prior art, the present invention provides a cogeneration control optimization system, which has the advantages of pre-processing the collected data to avoid errors or omissions, and will not cause optimization errors due to data errors or omissions, thereby solving the problems of the above-mentioned technologies.

[0007] Technical solution:

[0008] To achieve the above object, the present invention provides the following technical solutions: a cogeneration control optimization system, the optimization system consisting of a data acquisition module, a data cleaning module, a data completion module, a data verification module and a data integration module;

[0009] The data acquisition module is used to collect raw data from various sensors and data sources, including heat, electricity, cooling and equipment operating status;

[0010] The data cleaning module is used to clean the collected raw data and remove noise and outliers;

[0011] The data completion module is used to handle missing data problems using linear interpolation to fill in missing data values;

[0012] The data verification module is used to verify the processed data, check the rationality and validity of the data, and discover and correct potential errors;

[0013] The data integration module is used to integrate the cleaned, completed and verified data;

[0014] The data completion module expression is:

[0015] Assume n+1 known data points (xi, yi), where i = 0, 1, ..., n, and interpolate the value of y at x.

[0016]

[0017] Preferably, the data acquisition module expression is:

[0018] Q i (t) = reading of heat sensor i at time t

[0019] E i (t) = reading of power sensor i at time t

[0020] C i (t) = reading of cooling sensor i at time t

[0021] S i (t) = reading of equipment operating status sensor i at time t.

[0022] Preferably, the data cleaning module expression includes:

[0023] Noise Removal:

[0024]

[0025] in:

[0026] X tis the smoothed data value at time t, and N is the window size, i.e., the first N data points considered.

[0027] Preferably, the outlier detection in the data cleaning module uses a statistical method based on the mean and standard deviation:

[0028] X t is an outlier if and only if |X t -μ|>α

[0029] Where X t is the data value at time t, and σ is the standard deviation of the data.

[0030] Preferably, the data range verification expression in the data verification module is:

[0031] L≤X t ≤U

[0032] Where: L is the lower limit of the data, X t is the data value at time t.

[0033] Preferably, the data verification module checks whether the data satisfies a specific mathematical relationship expression:

[0034] |X t -R·X t-1 |≤∈

[0035] Where: R is the desired proportional relationship, X t and X t-1 are the data values ​​at the current and previous time points respectively.

[0036] Preferably, the data integrity in the data verification module usually checks whether the data points are continuous, and the expression is:

[0037] X t =X t-1 +Δ

[0038] Where: Δ is the expected change in the data.

[0039] Preferably, the data integration in the data integration module is data merging, and the data merging expression is:

[0040] Y t =f(X 1t , X 2t )

[0041] Where: X 1t and X 2t It is data from different sources;

[0042] The merging method is simple averaging:

[0043]

[0044] Preferably, the data integration in the data integration module is weighted merging, and the weighted merging expression is:

[0045] Y t =w 1 X 1t +w 2 X 2t

[0046] in:

[0047] w 1 and w 2 is the weight, and w 1 +w 2 =1.

[0048] Preferably, the data summary expression in the data integration module is:

[0049] sum:

[0050]

[0051] Mean:

[0052]

[0053] Compared with the prior art, the present invention provides a cogeneration control optimization system having the following features:

[0054] Beneficial effects:

[0055] 1. The present invention obtains data on heat, electricity, cooling and equipment operating status from various sensors and data sources, so that the system can obtain comprehensive raw data. In the data cleaning stage, the system removes noise and outliers in the data and smoothes the data. The system can reduce fluctuations caused by measurement errors or external interference to ensure data reliability. Outlier detection uses statistical methods to identify data points that deviate from the normal range, thereby improving the quality of the data set. For missing data, the system uses a linear interpolation method to fill in the missing data, and estimates the missing values ​​through the linear relationship between known data points, thereby avoiding incomplete information caused by missing data. Data verification includes range checking, consistency checking and integrity checking. The range check ensures that the data is within a predetermined reasonable range; the consistency check verifies whether the data conforms to the expected mathematical relationship; the integrity check ensures the continuity between data points. Through these checks, the system can promptly discover and correct potential errors to ensure the accuracy and consistency of the data. Data integration involves merging the cleaned, completed and verified data into a unified data set, and processing data from different data sources by simple averaging or weighted merging to provide a comprehensive result. In addition, the system also performs data summary calculations, such as sum and mean, to obtain overall information about the data, achieving the beneficial effect of pre-processing the collected data to avoid errors or omissions.

[0056] 2. The present invention obtains various types of data, including heat, electricity, cooling and equipment operating status, through comprehensive data collection. The system performs data cleaning and improves the quality of data by removing noise and detecting outliers. Noise removal reduces random fluctuations in the data through smoothing, while outlier detection excludes extreme or erroneous data points, thereby avoiding the impact of these problems on the optimization results. In the data completion stage, the system uses linear interpolation to fill in the missing data. This process ensures the integrity of the data set by reasonably estimating the missing values, so that the optimization algorithm can process as complete data as possible and reduce the analysis bias caused by missing data. The system checks whether the data is within the predetermined range, verifies whether the data conforms to the expected logical relationship, and ensures that the changes between data points are continuous. Through these checks, the system can promptly detect and correct potential errors in the data, avoid the negative impact of data inconsistency or breakage on the optimization, and achieve the beneficial effect of not causing optimization errors due to missing data errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the structure of the present invention; DETAILED DESCRIPTION

[0058] 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.

[0059] See also Figure 1 , a cogeneration control optimization system, the optimization system is composed of a data acquisition module, a data cleaning module, a data completion module, a data verification module and a data integration module;

[0060] The data acquisition module is used to collect raw data from various sensors and data sources, including heat, electricity, cooling and equipment operating status;

[0061] The data cleaning module is used to clean the collected raw data and remove noise and outliers;

[0062] The data completion module is used to handle missing data problems using linear interpolation to fill in missing data values;

[0063] The data verification module is used to verify the processed data, check the rationality and validity of the data, and discover and correct potential errors;

[0064] The data integration module is used to integrate the cleaned, completed and verified data;

[0065] The data completion module expression is:

[0066] Assume n+1 known data points (xi, yi), where i = 0, 1, ..., n, and interpolate the value of y at x.

[0067]

[0068] Preferably, the data acquisition module expression is:

[0069] Q i (t) = reading of heat sensor i at time t

[0070] E i (t) = reading of power sensor i at time t

[0071] C i (t) = reading of cooling sensor i at time t

[0072] S i (t) = reading of equipment operating status sensor i at time t.

[0073] Preferably, the data cleaning module expression includes:

[0074] Noise Removal:

[0075]

[0076] in.

[0077] is the smoothed data value at time t, and N is the window size, i.e., the first N data points considered.

[0078] Preferably, the outlier detection in the data cleaning module uses a statistical method based on the mean and standard deviation:

[0079] X t is an outlier if and only if |X t -μ|>α

[0080] Where X t is the data value at time t, and σ is the standard deviation of the data.

[0081] Preferably, the data range verification expression in the data verification module is:

[0082] L≤X t ≤U

[0083] Where: L is the lower limit of the data, X t is the data value at time t.

[0084] Preferably, the data verification module checks whether the data satisfies a specific mathematical relationship expression:

[0085] |X t -R·X t-1 |≤∈

[0086] Where: R is the desired proportional relationship, X t and X t-1 are the data values ​​at the current and previous time points respectively.

[0087] Preferably, the data integrity in the data verification module usually checks whether the data points are continuous, and the expression is:

[0088] X t =X t-1 +Δ

[0089] Where: Δ is the expected change in the data.

[0090] Preferably, the data integration in the data integration module is data merging, and the data merging expression is:

[0091] Y t =f(X1t , X 2t )

[0092] Where: X 1t and X 2t It is data from different sources;

[0093] The merging method is simple averaging:

[0094]

[0095] In a cogeneration system, environmental factors or instantaneous changes in equipment may cause data to fluctuate dramatically. Simple averaging can provide more stable data output, helping decision makers make more reasonable judgments. When monitoring the system, simple averaging can be used to avoid overall data deviations caused by a sensor failure, thereby providing more accurate performance evaluation. Simple averaging has a small amount of calculation and is suitable for real-time applications. It can quickly generate integrated data, facilitate real-time monitoring and decision-making. Real-time performance is particularly important for optimizing the control process, and the final data is used as the basis for subsequent analysis, facilitating trend analysis, performance evaluation and optimization decisions. The results obtained by simple averaging are clear and concise, which is helpful for subsequent in-depth analysis. When conducting system performance evaluation or energy efficiency analysis, using the results of simple averaging provides a clear starting point to help conduct deeper data analysis and model building.

[0096] Preferably, the data integration in the data integration module is weighted merging, and the weighted merging expression is:

[0097] Y t =w 1 X 1t +w 2 X 2t

[0098] in:

[0099] w 1 and w 2 is the weight, and w 1 +w 2 =1.

[0100] Through weighted merging, we ensure that more reliable data sources have a greater impact on the final results, thereby improving the quality of data integration. In actual operation, if a data source becomes unreliable due to technical problems or environmental changes, the system temporarily adjusts the weight of the data source to reduce its impact on the overall data integration. In a cogeneration system, different measurement devices may perform differently under different operating conditions. Through weighted merging, the actual contribution of each device is more accurately represented, avoiding the excessive impact of data from certain devices on the results. When optimizing the operation of the cogeneration system, the integrated data is used to evaluate the overall efficiency and performance of the system, supporting more scientific decision-making and adjustments.

[0101] Preferably, the data summary expression in the data integration module is:

[0102] sum:

[0103]

[0104] Mean:

[0105]

[0106] Data summation helps the system quickly obtain the cumulative value of all data points, which is crucial for understanding and evaluating the overall performance of the system. For example, total heat, total electricity or total cooling is used to calculate the energy consumption or output of the system in a certain period of time, supporting energy optimization or monitoring of the system.

[0107] In energy consumption studies and energy efficiency analysis, the sum is used to quickly assess energy usage over a longer period of time, facilitating subsequent trend analysis and energy efficiency optimization.

[0108] The mean provides a way to measure the average level of data in a data set, allowing the system to understand the average characteristics of the data. This is particularly important in a combined heat and power system because it allows the system to monitor and control production efficiency and ensure that the equipment is operating within normal ranges.

[0109] In quality control and fault detection, the mean can be used to detect whether a single data point deviates from the normal level; in performance evaluation, the mean helps the system understand the average power output or system efficiency, thereby achieving performance optimization.

[0110] The system obtains various types of data through comprehensive data collection, including heat, electricity, cooling and equipment operating status. This diversified data collection ensures the comprehensiveness of information and lays a solid foundation for subsequent data processing.

[0111] Next, the system performs data cleaning to improve the quality of the data by removing noise and detecting outliers. Noise removal reduces random fluctuations in the data through smoothing, while outlier detection excludes extreme or erroneous data points, thus preventing these problems from affecting the optimization results.

[0112] In the data completion phase, the system uses linear interpolation to fill in missing data. This process ensures the integrity of the data set by reasonably estimating missing values, so that the optimization algorithm can process data as complete as possible and reduce analysis bias caused by missing data.

[0113] Data validation ensures the validity and consistency of data through multiple steps. The system checks whether the data is within the predetermined range, verifies whether the data conforms to the expected logical relationship, and ensures the continuity of changes between data points. Through these validations, the system can promptly detect and correct potential errors in the data, avoiding the negative impact of inconsistent or broken data on optimization.

[0114] Finally, in the data integration stage, the cleaned and completed data are integrated into a unified result through merging and weighting. Simple averaging and weighted merging methods can effectively balance information from different data sources and provide accurate data integration results. In addition, data summary calculations help the system obtain the overall information of the data, further supporting optimization analysis.

[0115] By acquiring data on heat, electricity, cooling and equipment operating status from various sensors and data sources, the system can obtain comprehensive raw data, which provides the basis for subsequent processing and analysis.

[0116] During the data cleaning phase, the system removes noise and outliers from the data. By smoothing the data, the system can reduce fluctuations caused by measurement errors or external interference and ensure the reliability of the data. Outlier detection uses statistical methods to identify data points that deviate from the normal range, thereby improving the quality of the data set.

[0117] For missing data, the system uses linear interpolation to fill in the missing data. This method estimates the missing values ​​through the linear relationship between known data points, avoiding incomplete information caused by missing data.

[0118] Data verification includes range checking, consistency checking, and integrity checking. Range checking ensures that the data is within a predetermined reasonable range; consistency checking verifies whether the data conforms to the expected mathematical relationship; and integrity checking ensures the continuity between data points. Through these checks, the system can detect and correct potential errors in a timely manner to ensure the accuracy and consistency of the data.

[0119] Data integration involves combining cleaned, completed, and validated data into a unified data set. The system processes data from different data sources by simple averaging or weighted merging to provide a comprehensive result. In addition, the system also performs data summary calculations, such as sums and means, to obtain an overall picture of the data.

[0120] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A cogeneration control optimization system, characterized in that: The optimization system consists of a data acquisition module, a data cleaning module, a data completion module, a data verification module and a data integration module; The data acquisition module is used to collect raw data from various sensors and data sources, including heat, electricity, cooling and equipment operating status; The data cleaning module is used to clean the collected raw data and remove noise and outliers; The data completion module is used to handle missing data problems using linear interpolation to fill in missing data values; The data verification module is used to verify the processed data, check the rationality and validity of the data, and discover and correct potential errors; The data integration module is used to integrate the cleaned, completed and verified data; The data completion module expression is: Suppose there are n+1 known data points (xi,yi), where i=0,1,…,n, interpolate the value of y at x 2. A cogeneration control optimization system according to claim 1, characterized in that: The data acquisition module expression is: Q i (t) = reading of heat sensor i at time t E i (t) = reading of power sensor i at time t C i (t) = reading of cooling sensor i at time t S i (t) = reading of equipment operating status sensor i at time t.

3. A cogeneration control optimization system according to claim 1, characterized in that: The data cleaning module expression includes: Noise Removal: in: is the smoothed data value at time t, and N is the window size, i.e., the first N data points considered.

4. A cogeneration control optimization system according to claim 3, characterized in that: The outlier detection in the data cleaning module uses a statistical method based on mean and standard deviation: X t is an outlier if and only if |X t -μ|>α Where X t is the data value at time t, and σ is the standard deviation of the data.

5. A cogeneration control optimization system according to claim 4, characterized in that: The data range verification expression in the data verification module is: L≤X t ≤U Where: L is the lower limit of the data, X t is the data value at time t.

6. A cogeneration control optimization system according to claim 5, characterized in that: The data verification module checks whether the data satisfies a specific mathematical relationship expression: |X t -R·X t-1 |≤∈ Where: R is the desired proportional relationship, X t and X t-1 are the data values ​​at the current and previous time points respectively.

7. A cogeneration control optimization system according to claim 6, characterized in that: The data integrity in the data verification module usually checks whether the data points are continuous, and its expression is: X t =X t-1 +Δ Where: Δ is the expected change in the data.

8. The cogeneration control optimization system according to claim 1, characterized in that: The data integration in the data integration module is data merging, and the data merging expression is: Y t =f(X 1t ,X 2t ) Where: X 1t and X 2t It is data from different sources; The merging method is simple averaging:

9. The cogeneration control optimization system according to claim 1, characterized in that: The data integration in the data integration module is weighted merging, and the weighted merging expression is: Y t =w1X 1t +w2X 2t in: w1 and w2 are weights, and w1+w2=1.

10. A cogeneration control optimization system according to claim 9, characterized in that: The data summary expression in the data integration module is: sum: Mean:

Images