A method and system for real-time monitoring of the environmental temperature of a biofertilizer fermentation tank

Abstract

The present application relates to the field of temperature measurement technology, and specifically to a method and system for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank. The method comprises: performing anomaly detection on temperature data acquired by each temperature sensor disposed in the bio-fertilizer fermentation tank; obtaining an anomaly factor of the temperature data acquired at the current moment based on the similarity between the temperature data acquired by each temperature sensor and the remaining temperature sensors; performing anomaly detection on the discreteness of the temperature data to determine a first temperature anomaly degree; obtaining a substrate consumption rate at each moment; analyzing the similarity between the substrate consumption rate and the change in temperature data to determine a correction factor at the current moment; performing a comparative analysis on the relationship between the temperature data and the substrate concentration to determine a second temperature anomaly degree; and determining a final anomaly result of the temperature data acquired at the current moment to monitor the ambient temperature of the bio-fertilizer fermentation tank. The present application aims to reduce the error in temperature data anomaly detection and improve the accuracy of temperature monitoring.

Description

Technical Field

[0001] The present application relates to the field of temperature measurement technology, and in particular to a method and system for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank. Background Art

[0002] Biofertilizer fermentation is the process by which organic materials, under the action of microorganisms, decompose and transform into composted fertilizer. This process involves the coordinated metabolic activities of multiple microorganisms, and temperature is a key factor influencing their growth, reproduction, and metabolism. Different microbial communities are active in different temperature ranges, and the activity and metabolic rates of each microorganism vary with temperature, thus affecting the rate and extent of fermentation. However, excessively high temperatures can cause compost materials to dry out, reduce microbial activity, or even kill them, compromising fermentation results. Excessively low temperatures can slow fermentation and prolong the fermentation cycle.

[0003] During the biofertilizer fermentation process, substrate concentration directly affects the metabolic rate of microorganisms and the intensity of the fermentation reaction. When the substrate concentration is high, microbial activity is stronger, and the fermentation reaction generates more heat, which causes the temperature to rise. Therefore, temperature fluctuations are not only affected by the external environment but are also closely related to substrate concentration. Current temperature anomaly analysis algorithms, such as the LOF anomaly detection algorithm, mostly rely solely on historical temperature data from the biofertilizer fermentation tank for analysis, failing to comprehensively consider changes in substrate concentration during the fermentation process. As a result, the resulting temperature anomaly detection results may not accurately reflect the temperature anomalies in the actual fermentation tank environment. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method and system for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank to solve the above problems.

[0005] The first aspect of the present application provides a method for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank, the method comprising:

[0006] Arrange multiple temperature sensors in the bio-fertilizer fermentation tank, perform anomaly detection on the temperature data obtained by each temperature sensor, and extract the anomaly detection result of the temperature data at the current moment; obtain the anomaly factor of the temperature data obtained by each temperature sensor at the current moment based on the similarity between the temperature data obtained by each temperature sensor and the temperature data obtained by the other temperature sensors at the current moment and a preset number of moments before;

[0007] Obtaining the degree of dispersion of temperature data collected by all temperature sensors at each moment, performing anomaly detection on the dispersion degrees at the current moment and a preset number of moments before, obtaining a temperature dispersion anomaly value at the current moment, and determining a first temperature anomaly degree of the temperature data collected by each temperature sensor at the current moment in combination with the anomaly factor and the anomaly detection result;

[0008] For the area corresponding to each temperature sensor, the substrate consumption rate at each moment is obtained based on the change in substrate concentration at adjacent moments; the similarity between the substrate consumption rate at the current moment and the change in temperature data at a preset number of moments is analyzed to determine the correction factor at the current moment; the proportional relationship between the temperature data and the substrate concentration at each moment is determined, and the proportional relationship at the current moment and the preset number of moments is compared and analyzed to determine the second temperature anomaly degree of the temperature data obtained by each temperature sensor at the current moment;

[0009] The first temperature anomaly degree, the correction factor, and the second temperature anomaly degree of the temperature data acquired by each temperature sensor at the current moment are combined to determine a final abnormal result of the temperature data acquired by each temperature sensor at the current moment; and the ambient temperature of the bio-fertilizer fermentation tank is monitored based on the final abnormal result.

[0010] Preferably, the abnormal factor of the temperature data obtained by each temperature sensor at the current moment is obtained, specifically:

[0011] Record the sequence of temperature data collected by each temperature sensor a preset number of times before the current moment as a historical reference sequence, and calculate the similarity between the historical reference sequence of each temperature sensor at the current moment and the historical reference sequences of the other temperature sensors at the current moment, which is recorded as the first similarity;

[0012] Record the sequence of temperature data collected by each temperature sensor at the current moment and a preset number of moments before as the current reference sequence, and obtain the degree of similarity between the current reference sequence of each temperature sensor at the current moment and the current reference sequences of the remaining temperature sensors at the current moment, which is recorded as the second similarity;

[0013] The difference between the first similarity degree and the second similarity degree obtained by each temperature sensor and the remaining temperature sensors is calculated, and forward fused with the anomaly detection results of the temperature data of the remaining temperature sensors at the current moment. All forward fusion results obtained by each temperature sensor are accumulated and normalized to obtain the anomaly factor of the temperature data obtained by each temperature sensor at the current moment.

[0014] Preferably, the obtaining of the discrete abnormal value of temperature at the current moment is specifically as follows:

[0015] Obtain the temperature data collected by all temperature sensors at each moment and form a temperature data sequence at each moment;

[0016] For the current moment and a preset number of moments before, calculate the discrete degree of the elements in the temperature data sequence at each moment, and arrange the obtained discrete degrees in time sequence to form a temperature discrete sequence;

[0017] Anomaly detection is performed on the temperature discrete sequence to obtain the temperature discrete anomaly value at the current moment.

[0018] Preferably, the specific process of determining the first temperature anomaly degree of the temperature data acquired by each temperature sensor at the current moment is:

[0019] The sum of the anomaly factor and the anomaly detection result of the temperature data obtained by each temperature sensor at the current moment is calculated, and then forward-fused with the discrete temperature anomaly value at the current moment. After normalization, the first temperature anomaly degree of the temperature data obtained by each temperature sensor at the current moment is obtained.

[0020] Preferably, the substrate consumption rate at each moment is specifically the absolute value of the difference between the substrate concentration at each moment and the substrate concentration at the previous moment.

[0021] Preferably, the correction factor at the current moment is determined as follows:

[0022] The sequence of substrate consumption rates at the current moment and a preset number of moments before is used as the substrate consumption rate sequence of the area corresponding to each temperature sensor at the current moment;

[0023] Calculate the ratio between the substrate consumption rate sequence at the current moment and the element at the same moment of the current reference sequence at the current moment to obtain the ratio sequence at the current moment;

[0024] The variance of the ratio sequence at the current moment is obtained as the correction factor for the area corresponding to each temperature sensor at the current moment.

[0025] Preferably, the determining of the second temperature abnormality degree of the temperature data acquired by each temperature sensor at the current moment is specifically:

[0026] Calculate the ratio between the temperature value of the area corresponding to each temperature sensor at the current moment and the substrate concentration, and record it as a first ratio;

[0027] Recording a preset number of moments before the current moment as historical reference moments, calculating the ratio between the temperature value of the area corresponding to each temperature sensor at each historical reference moment and the substrate concentration, and recording it as a second ratio;

[0028] calculating a difference between the first ratio and the second ratio;

[0029] The normalized result of accumulating the differences between the current moment and all historical reference moments in the area corresponding to each temperature sensor is used as the second temperature anomaly degree of the area corresponding to each temperature sensor at the current moment.

[0030] Preferably, the final abnormal result of the temperature data acquired by each temperature sensor at the current moment is determined as follows:

[0031] The product of the correction factor and the second temperature anomaly degree of the area corresponding to each temperature sensor at the current moment is calculated, and the normalized result after adding the product to the first temperature anomaly degree is used as the final anomaly result of the temperature data of each temperature sensor at the current moment.

[0032] Preferably, the process of monitoring the environmental temperature of the bio-fertilizer fermentation tank is specifically as follows:

[0033] The final abnormal result is used as the input of the RRCF algorithm, and an early warning is issued when the RRCF algorithm detects an abnormal value.

[0034] In a second aspect, an embodiment of the present application further provides a real-time monitoring system for the ambient temperature of a bio-fertilizer fermentation tank, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0035] The beneficial effects of the above scheme are as follows: the present application uses the existing anomaly detection algorithm to perform anomaly detection on the temperature data of the biofertilizer fermentation tank, which can preliminarily identify anomalies in the temperature data. On this basis, further combined with the similarity analysis of temperature change trends, by calculating the correlation between the temperature data of different temperature sensors, the anomaly factor of the temperature data is constructed, and the temperature obtained by the temperature sensor at the current moment is analyzed to determine whether it is abnormal, making the anomaly detection more accurate and reliable, and effectively reducing the probability of misjudgment and missed judgment; taking the temperature distribution into consideration, based on the discrete degree of the temperature data collected by all temperature sensors based on the time series analysis, the anomaly detection algorithm is used to perform anomaly detection on the temperature discrete sequence, construct a first temperature anomaly degree, and comprehensively judge the abnormality of the temperature sensor data at the current moment; by analyzing the relationship between the substrate consumption rate and the temperature data change, a correction factor is obtained, so that the correction of the temperature data is more consistent with the actual characteristics of the biofermentation process; finally, the temperature data of all temperature sensors are comprehensively evaluated, the anomaly detection results of the temperature data are corrected from multiple angles and the corrected scientific judgment is made, and a second temperature anomaly degree of the temperature data is constructed, so that the correction of the abnormal value of the temperature data is more consistent with the actual characteristics and laws of the fermentation process, thereby enhancing the scientificity and accuracy of the temperature monitoring of the fermentation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a method for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank provided in one embodiment of the present application;

[0037] Figure 2A flowchart for obtaining the final abnormal result provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the art of this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0040] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the methods. Without departing from the scope of protection of this application, the order of executing multiple steps can be interchanged with each other, and some steps can also be deleted.

[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0042] The following describes in detail a method and system for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank provided by the present application with reference to the accompanying drawings.

[0043] See also Figure 1 , which shows a flowchart of a method for real-time monitoring of the ambient temperature of a bio-fertilizer fermentation tank provided by one embodiment of the present application, the method comprising the following steps:

[0044] The first step is to obtain the temperature data collected by each temperature sensor in the bio-fertilizer fermentation tank at each moment, as well as the substrate concentration data at each moment in the area where each temperature sensor is located.

[0045] The present application sets up multiple temperature sensors at different locations of the bio-fertilizer fermentation tank for sampling to obtain more comprehensive temperature information and avoid measurement errors caused by local temperature changes.

[0046] In this embodiment, n=9 temperature sensors are evenly set to collect data. At the same time, an online near-infrared spectrometer is used to collect real-time substrate concentration during the fermentation process in the area where the temperature sensors are located.

[0047] The second step is to perform anomaly detection on the temperature data obtained by each temperature sensor and extract the anomaly detection result of the temperature data at the current moment; based on the similarity between the temperature data obtained by each temperature sensor and the temperature data obtained by the other temperature sensors at the current moment and a preset number of moments before, obtain the anomaly factor of the temperature data obtained by each temperature sensor at the current moment.

[0048] An anomaly detection algorithm is used on the temperature data collected by each temperature sensor to obtain an anomaly detection result of the temperature data of each sensor at each moment; in this embodiment, the anomaly detection algorithm adopts the LOF anomaly detection algorithm, and the anomaly detection result is the LOF value.

[0049] In the same fermentation tank, the temperatures collected by temperature sensors at different locations may be the same and their changing trends may be similar. Therefore, we analyze the similarity of the changing trends of the temperature data between different temperature sensors. If the changing trends of the monitored temperatures at two monitoring locations are consistent, we can analyze whether the temperature collected by the target sensor is abnormal based on the temperature changes of adjacent sensors. The specific calculation method is as follows:

[0050] A sequence consisting of temperature data collected by each temperature sensor at a preset number of moments before the current moment is recorded as a historical reference sequence. In this embodiment, the preset number is 20, and the preset number of moments before the current moment are recorded as historical reference moments. The temperature historical data before the current moment are analyzed to obtain a similarity between the historical reference sequence of each temperature sensor at the current moment and the historical reference sequences of the other temperature sensors at the current moment, which is recorded as a first similarity.

[0051] The sequence consisting of the temperature data collected by each temperature sensor at the current moment and a preset number of moments before is recorded as the current reference sequence. The similarity between the current reference sequence of each temperature sensor at the current moment and the current reference sequences of the remaining temperature sensors at the current moment is obtained, which is recorded as the second similarity.

[0052] Furthermore, the difference between the first similarity degree and the second similarity degree obtained by each temperature sensor and the remaining temperature sensors is calculated, and forward fused with the LOF value of the temperature data of the remaining temperature sensors at the current moment, and all forward fusion results obtained by each temperature sensor are accumulated and normalized to obtain the abnormal factor of the temperature data obtained by each temperature sensor at the current moment; in this embodiment, the similarity degree is calculated using the Pearson correlation coefficient, and the normalization method uses the maximum and minimum normalization method; the difference between the variables is calculated using the absolute value of the difference, and multiple variables are forward fused using the multiplication calculation method.

[0053] It should be understood that the smaller the difference between each temperature sensor and the other temperature sensors before and after the temperature data at the current moment is added, and the smaller the abnormal value of the temperature data of the other temperature sensors at the current moment is, the smaller the possibility that the temperature value obtained by each sensor at the current moment is an abnormal value is.

[0054] The third step is to obtain the degree of discreteness of the temperature data collected by all temperature sensors at each moment, perform anomaly detection on the discreteness at the current moment and a preset number of moments before, obtain the temperature discrete anomaly value at the current moment, and determine the first temperature anomaly degree of the temperature data obtained by each temperature sensor at the current moment by combining the anomaly factor and the anomaly detection result.

[0055] Since the temperature sensors are evenly distributed in the fermentation tank, the temperature distribution information in the fermentation tank at each moment can be obtained. When performing abnormal analysis on the real-time temperature information, the sensor temperature distribution can be analyzed to determine whether the real-time temperature information is abnormal.

[0056] Obtain the temperature data collected by all temperature sensors at each moment to form a temperature data sequence at each moment. Analyze the temperature information in the fermentation tank based on the temperature difference relationship between the sensor temperature data to determine whether the temperature sensor collected by the sensor is abnormal. First, obtain the temperature distribution uniformity in the fermentation tank. That is, the more uniform the temperature distribution in the fermentation tank, the more abnormal the temperature value collected by each temperature sensor can be evaluated based on the temperature distribution. The specific calculation method is as follows:

[0057] For the current moment and a preset number of previous moments, the degree of discreteness of the elements in the temperature data sequence at each moment is calculated, and the obtained degrees of discreteness are arranged in time series to form a temperature discrete sequence. In this embodiment, the degree of discreteness of the sequence elements is calculated using variance. Anomaly detection is performed on the temperature discrete sequence to obtain a temperature discrete anomaly value at the current moment. In this embodiment, the anomaly detection algorithm uses LOF anomaly detection, and the temperature discrete anomaly value is specifically the LOF value of the data at the corresponding moment obtained by the algorithm. It should be understood that the larger the temperature discrete anomaly value at the current moment, the greater the anomaly of the temperature distribution corresponding to the current moment, and therefore the greater the possibility that the temperature data collected by all temperature sensors at the current moment is abnormal.

[0058] The sum of the anomaly factor and the anomaly detection result of the temperature data currently acquired by each temperature sensor is calculated. This is then forward-fused with the current discrete temperature anomaly value. After normalization, the first temperature anomaly degree of the temperature data currently acquired by each temperature sensor is obtained. In this embodiment, the normalization method uses the maximum-minimum normalization method.

[0059] The fourth step: for the area corresponding to each temperature sensor, according to the change of substrate concentration at adjacent moments, obtain the substrate consumption rate at each moment; analyze the similarity between the substrate consumption rate at the current moment and the change of the temperature data at the previous preset number of moments, and determine the correction factor at the current moment; determine the proportional relationship between the temperature data and the substrate concentration at each moment, compare and analyze the proportional relationship at the current moment and the previous preset number of moments, and determine the second temperature anomaly degree of the temperature data obtained by each temperature sensor at the current moment.

[0060] Since the most relevant reason for temperature changes in the microbial fermentation tank is the microbial fermentation metabolism process, which will cause temperature changes in the microbial fermentation tank, when monitoring the ambient temperature of the biofertilizer fermentation tank, it is also possible to analyze the microbial fermentation rate. Generally speaking, the faster the substrate consumption rate, the faster the microbial fermentation metabolism rate, and the higher the corresponding heat generated, which leads to a higher ambient temperature. The microbial fermentation metabolism rate is represented by the substrate consumption rate in this application. Therefore, this application analyzes the relationship between the substrate consumption rate and the ambient temperature in the biofertilizer fermentation tank by combining historical data, and analyzes the real-time collected temperature data based on the substrate consumption rate analyzed in real time. The specific method is as follows:

[0061] For the area corresponding to each temperature sensor, the absolute value of the difference between the substrate concentration at each moment and the previous moment is used as the substrate consumption rate at each moment, and the sequence consisting of the substrate consumption rates at the current moment and a preset number of moments before is used as the substrate consumption rate sequence of the area corresponding to each temperature sensor at the current moment; the ratio between the elements at the same moment of the substrate consumption rate sequence at the current moment and the current reference sequence at the current moment is calculated to obtain the ratio sequence at the current moment, and the variance of the ratio sequence at the current moment is obtained as the correction factor for the area corresponding to each temperature sensor at the current moment.

[0062] It should be understood that the smaller the variance obtained at the current moment for each temperature sensor corresponding area, the stronger the correlation between the temperature and the substrate consumption rate in that area. By further analyzing the abnormality of the ratio between the substrate consumption rate and the temperature, it is indirectly possible to determine whether the corresponding temperature is abnormal. Based on this, the method for obtaining sensor temperature abnormality based on substrate concentration is as follows:

[0063] Calculate the ratio of the current temperature value of each temperature sensor region to the substrate concentration, recording this as a first ratio; calculate the ratio of the current temperature value of each temperature sensor region to the substrate concentration at each historical reference time, recording this as a second ratio; calculate the difference between the first ratio and the second ratio; and accumulate the differences between the current and all historical reference times for each temperature sensor region, and normalize the accumulated differences to obtain the second temperature anomaly degree for each temperature sensor region at the current time. In this embodiment, the differences between the variables are calculated using the absolute values ​​of the differences, and the normalization method uses the maximum-minimum normalization method.

[0064] It should be understood that the smaller the difference between the first ratio acquired in real time by each temperature sensor in the corresponding area and the second ratio obtained at the historical reference moment, the smaller the possibility that the temperature value of each temperature sensor at the current moment is an abnormal temperature value.

[0065] The fifth step is to determine a final abnormal result of the temperature data acquired by each temperature sensor at the current moment by integrating the first temperature abnormality, the correction factor, and the second temperature abnormality of the temperature data acquired by each temperature sensor at the current moment; and monitor the ambient temperature of the bio-fertilizer fermentation tank based on the final abnormal result.

[0066] The product of the correction factor and the second temperature anomaly degree for each temperature sensor's corresponding area at the current moment is calculated, and the normalized result is added to the first temperature anomaly degree to obtain the final anomaly result for the temperature data of each temperature sensor at the current moment. The normalization method employed is the inverse tangent transformation normalization method.

[0067] The final abnormal result acquisition flow chart is as follows: Figure 2 shown.

[0068] The final anomaly results of the temperature data at each moment are calculated separately. During the real-time monitoring process, the final anomaly results of the temperature data at each moment are used as input. The Robust Random Cut Forest (RRCF) algorithm is used to detect anomalies in the input data. When RRCF detects such anomalies, a real-time warning is issued. In this embodiment, since the ambient temperature is monitored in real time, the RRCF algorithm uses a cold start training method. The number of trees is set to 100, and the size of a single tree is set to 256 nodes. RRCF is a commonly used technology in the field of data processing, and the specific process is not repeated here.

[0069] Based on the same inventive concept as the above method, an embodiment of the present application also provides a real-time monitoring system for the environmental temperature of a bio-fertilizer fermentation tank, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for real-time monitoring the environmental temperature of a bio-fertilizer fermentation tank are implemented.

[0070] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0071] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, from any point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; modifications to the technical solutions described in the above embodiments, or equivalent replacement of some of the technical features therein, do not deviate from the essence of the corresponding technical solutions within the scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application.

Claims

1. A method for real-time monitoring of the ambient temperature of a biofertilizer fermentation tank, characterized in that: The method comprises the following steps: Arrange multiple temperature sensors in the bio-fertilizer fermentation tank, perform abnormality detection on the temperature data obtained by each temperature sensor, and extract the abnormality detection result of the temperature data at the current moment; Record the sequence of temperature data collected by each temperature sensor a preset number of times before the current moment as a historical reference sequence, and calculate the similarity between the historical reference sequence of each temperature sensor at the current moment and the historical reference sequences of the other temperature sensors at the current moment, which is recorded as the first similarity; Record the sequence of temperature data collected by each temperature sensor at the current moment and a preset number of moments before as the current reference sequence, and obtain the degree of similarity between the current reference sequence of each temperature sensor at the current moment and the current reference sequences of the remaining temperature sensors at the current moment, which is recorded as the second similarity; Calculate the difference between the first and second similarity levels obtained by each temperature sensor and the remaining temperature sensors, and forward fuse them with the anomaly detection results of the temperature data of the remaining temperature sensors at the current moment. Accumulate all forward fusion results obtained by each temperature sensor and normalize them to obtain the anomaly factor of the temperature data obtained by each temperature sensor at the current moment. Obtain the degree of discreteness of the temperature data collected by all temperature sensors at each moment, perform anomaly detection on the discreteness at the current moment and a preset number of moments before, obtain the temperature discrete anomaly value at the current moment, calculate the sum of the anomaly factor and the anomaly detection result of the temperature data obtained by each temperature sensor at the current moment, and then perform forward fusion with the temperature discrete anomaly value at the current moment. After normalization, obtain the first temperature anomaly degree of the temperature data obtained by each temperature sensor at the current moment; For the area corresponding to each temperature sensor, the substrate consumption rate at each moment is obtained based on the change in substrate concentration at adjacent moments; a sequence consisting of the substrate consumption rates at the current moment and a preset number of moments before is used as the substrate consumption rate sequence for the area corresponding to each temperature sensor at the current moment; the ratio between the substrate consumption rate sequence at the current moment and the elements at the same moment of the current reference sequence at the current moment is calculated to obtain a ratio sequence at the current moment; the variance of the ratio sequence at the current moment is obtained as a correction factor for the area corresponding to each temperature sensor at the current moment; Calculating the ratio between the temperature value of the area corresponding to each temperature sensor at the current moment and the substrate concentration, recording it as a first ratio; recording a preset number of moments before the current moment as historical reference moments, calculating the ratio between the temperature value of the area corresponding to each temperature sensor at each historical reference moment and the substrate concentration, recording it as a second ratio; calculating the difference between the first ratio and the second ratio; accumulating the differences between the current moment and all historical reference moments for each temperature sensor area and normalizing the difference, and taking the result as the second temperature anomaly degree for the area corresponding to each temperature sensor at the current moment; The product of the correction factor and the second temperature anomaly degree for the area corresponding to each temperature sensor at the current moment is calculated, and the normalized result after adding the product to the first temperature anomaly degree is used as the final anomaly result of the temperature data of each temperature sensor at the current moment; based on the final anomaly result, the ambient temperature of the bio-fertilizer fermentation tank is monitored.

2. A method for real-time monitoring of the environmental temperature of a bio-fertilizer fermentation tank according to claim 1, characterized in that: The discrete abnormal value of temperature at the current moment is obtained as follows: Obtain the temperature data collected by all temperature sensors at each moment and form a temperature data sequence at each moment; For the current moment and a preset number of moments before, calculate the discrete degree of the elements in the temperature data sequence at each moment, and arrange the obtained discrete degrees in time sequence to form a temperature discrete sequence; Anomaly detection is performed on the temperature discrete sequence to obtain the temperature discrete anomaly value at the current moment.

3. A method for real-time monitoring of the environmental temperature of a bio-fertilizer fermentation tank according to claim 1, characterized in that: The substrate consumption rate at each moment is specifically the absolute value of the difference between the substrate concentration at each moment and the substrate concentration at the previous moment.

4. A method for real-time monitoring of the environmental temperature of a bio-fertilizer fermentation tank according to claim 1, characterized in that: The process of monitoring the environmental temperature of the bio-fertilizer fermentation tank is specifically as follows: The final abnormal result is used as the input of the RRCF algorithm, and an early warning is issued when the RRCF algorithm detects an abnormal value.

5. A real-time monitoring system for the environmental temperature of a bio-fertilizer fermentation tank, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

Images