Mass spectrometer operation state monitoring method, system, equipment and medium

Abstract

The invention provides a mass spectrometer operation state monitoring method, system and device and a medium, and relates to the technical field of fault monitoring, and the method comprises the steps: collecting environment parameters in a mass spectrometer operation environment, carrying out the vacuum degree influence analysis of a mass spectrometer according to the environment parameters, and obtaining vacuum degree influence parameters; analyzing the mass axis offset influence of the mass spectrometer according to the environmental parameters to obtain mass axis offset parameters; testing to obtain an actual vacuum degree influence parameter and an actual mass error parameter of the mass spectrometer, performing state influence verification by combining the vacuum degree influence parameter and the mass axis offset parameter, and processing to obtain a vacuum verification coefficient and a mass verification coefficient; and according to the vacuum verification coefficient and the quality verification coefficient, performing fusion state anomaly analysis on the vacuum degree influence parameter and the quality axis offset parameter to obtain a state anomaly coefficient, and performing fault judgment and early warning. The technical problem that fault early warning is not timely in the monitoring process of the operation state of the mass spectrometer in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of fault monitoring, and in particular to a method, system, equipment and medium for monitoring the operating status of a mass spectrometer. Background Art

[0002] In the existing technology, the monitoring of the operating status of a mass spectrometer is often limited to the threshold judgment of a single parameter. However, this method can only determine whether a single parameter has exceeded the preset threshold, but cannot capture the coupling relationship between parameters and it is difficult to discover implicit influencing factors, resulting in untimely fault warnings during the monitoring of the operating status of the mass spectrometer. Summary of the Invention

[0003] The present invention aims to solve the technical problem of untimely fault warning in the process of monitoring the operating status of a mass spectrometer in the prior art, and provides a method, system, device and medium for monitoring the operating status of a mass spectrometer.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a method for monitoring the operating status of a mass spectrometer, comprising: Collecting environmental parameters in the mass spectrometer operating environment, performing vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtaining vacuum degree influence parameters; Performing mass axis offset influence analysis on the mass spectrometer according to the environmental parameters to obtain mass axis offset parameters; The actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer are obtained by testing, and the state influence verification is performed in combination with the vacuum degree influence parameters and the mass axis offset parameters, and the vacuum verification coefficient and the mass verification coefficient are obtained by processing; According to the vacuum verification coefficient and the quality verification coefficient, a fusion state abnormality analysis is performed on the vacuum degree influencing parameter and the mass axis offset parameter to obtain a state abnormality coefficient and perform fault identification and early warning.

[0005] In a second aspect, the present invention provides a mass spectrometer operating status monitoring system, comprising: A vacuum analysis module is used to collect environmental parameters in the operating environment of the mass spectrometer, perform vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtain vacuum degree influence parameters; An axis deviation analysis module, configured to analyze the influence of mass axis deviation of the mass spectrometer according to the environmental parameters and obtain mass axis deviation parameters; A state verification module is used to test and obtain the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer, perform state influence verification in combination with the vacuum degree influence parameters and mass axis offset parameters, and process to obtain vacuum verification coefficients and mass verification coefficients; The abnormality warning module is used to perform a fusion state abnormality analysis on the vacuum degree influencing parameter and the mass axis offset parameter according to the vacuum verification coefficient and the mass verification coefficient, obtain the state abnormality coefficient, and perform fault identification and warning.

[0006] In a third aspect, the present invention provides an electronic device, comprising: Memory for storing computer software programs; The processor is used to read and execute the computer software program, thereby implementing a mass spectrometer operating status monitoring method provided in this application.

[0007] In a fourth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, a method for monitoring the operating status of a mass spectrometer as described in the first aspect is implemented.

[0008] The beneficial effects of the present invention are: Compared with the prior art, the present application first collects the environmental parameters in the operating environment of the mass spectrometer, performs the vacuum degree influence analysis of the mass spectrometer according to the environmental parameters, obtains the vacuum degree influence parameters, and can evaluate the operating status of the mass spectrometer based on this, providing a reliable basis for the operating status monitoring of the mass spectrometer. Secondly, the mass axis offset influence analysis of the mass spectrometer is performed according to the environmental parameters to obtain the mass axis offset parameters, which provide a reliable basis for the subsequent result analysis. Thirdly, the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer are obtained by testing, and the state impact verification is performed in combination with the vacuum degree influence parameters and the mass axis offset parameters. The vacuum verification coefficient and the mass verification coefficient are obtained by processing, and the model prediction data is verified by actual data, and data support is provided for subsequent fault discrimination and early warning. Finally, based on the vacuum verification coefficient and the quality verification coefficient, a fusion state anomaly analysis is performed on the vacuum degree influencing parameters and the mass axis offset parameters to obtain the state anomaly coefficient and perform a fault identification and warning. The basic state anomaly coefficient is compensated and amplified by the absolute difference between the vacuum verification coefficient and the quality verification coefficient, avoiding the distortion of the warning results caused by the single-dimensional prediction deviation. Accurate fault identification and warning can be made at an earlier stage, so that relevant technical personnel can carry out operation and maintenance inspections.

[0009] Through the above technical solution, this application inputs environmental parameters through a vacuum impact analysis network and a mass axis offset analysis network constructed based on machine learning, outputs vacuum impact parameters and mass axis offset parameters, and compensates and expands the basic state abnormality coefficient accordingly. In this way, fault identification and warning can be made at an earlier stage, thereby improving the timeliness of mass spectrometer fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a method for monitoring the operating status of a mass spectrometer provided by the present invention; Figure 2 A schematic structural diagram of a mass spectrometer operating status monitoring system provided by the present invention; Figure 3 This is a schematic structural diagram of the electronic device provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are as follows: Vacuum analysis module 11 , axial deviation analysis module 12 , state verification module 13 , abnormality warning module 14 , electronic device 200 , memory 210 , processor 220 , computer program 211 . DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0015] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a method for monitoring the operating status of a mass spectrometer, comprising: S10: collecting environmental parameters in the operating environment of the mass spectrometer, performing vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtaining vacuum degree influence parameters; Vacuum degree is one of the key performance indicators of mass spectrometer, which is the basic condition for ensuring the stable operation of the instrument. Specifically, vacuum degree refers to the degree of vacuum environment inside the mass spectrometer. The fewer the number of gas molecules, the lower the air pressure, and the higher the vacuum degree. In other words, vacuum degree and pressure value are inversely proportional. The lower the pressure, the higher the vacuum degree. Conversely, the higher the pressure, the lower the vacuum degree. In order to ensure the quality of the mass spectrometer, it is usually necessary to maintain a vacuum degree of 10 -3 ~10 -6 Pa high vacuum state, if the pressure is too high, ions will frequently collide with gas molecules, resulting in a significant reduction in ion transmission efficiency, or even failure to reach the detector. In addition, a high vacuum environment can effectively reduce the oxidation of the ion source filament and the contamination of the mass analyzer, thereby extending the service life of the instrument hardware. Furthermore, temperature is one of the important factors affecting the vacuum degree of the mass spectrometer. Increased temperature will cause the mass spectrometer to expand and contract, which will lead to small gaps in the vacuum seal, deteriorating the high vacuum state of the mass spectrometer and increasing the internal pressure. For example, from 10 -3 Pa becomes 10 -2 Pa, which in turn causes the vacuum degree to decrease. Once the vacuum degree decreases, the probability of ions colliding with gas molecules during transmission increases significantly, affecting the normal detection of the mass spectrometer. Therefore, the vacuum degree change trend can be predicted by parameters such as ambient temperature, and the operating status of the mass spectrometer can be monitored accordingly.

[0016] In response to the above problems, the present application collects environmental parameters (including temperature) in the operating environment of the mass spectrometer, performs vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtains vacuum degree influence parameters.

[0017] Specifically, step S10 in the method includes: Collecting environmental parameters in the operating environment of the mass spectrometer, wherein the environmental parameters include ambient temperature; The environmental parameters are input into the vacuum influence analysis network of the mass spectrometer, and the vacuum degree influence parameters are obtained by identification output.

[0018] In this embodiment, environmental parameters of the mass spectrometer's operating environment are first collected. These environmental parameters include the ambient temperature. This is because temperature is a key factor affecting the mass spectrometer's vacuum level; increased temperature can reduce the vacuum level. For example, a temperature sensor deployed in the mass spectrometer's operating environment can collect the ambient temperature in real time with a timestamp. For example, the collected ambient temperature is 25°C (at 4:00 PM on June 5, 2025).

[0019] Secondly, the environmental parameters are input into the mass spectrometer's vacuum impact analysis network, which identifies and outputs vacuum impact parameters. Specifically, the vacuum impact analysis network is built based on machine learning. It takes as input an environmental parameter (such as ambient temperature) and, after computation and processing by multiple layers of internal neurons, outputs a vacuum impact parameter (such as a vacuum variation parameter). The larger the vacuum impact parameter, the greater the deviation from the ideal state, indicating a worsening of the mass spectrometer's current operating state. For example, an environmental parameter (such as ambient temperature: 25°C) is input into the vacuum impact analysis network, and the identified output yields a vacuum impact parameter (such as a vacuum variation parameter: 0.2).

[0020] Specifically, the training steps of the "vacuum impact analysis network" include: According to the operation monitoring data of the mass spectrometer, a set of sample environment parameters is collected, and the vacuum degree change parameters of the mass spectrometer under different sample environment parameters are collected, and the set of sample vacuum degree influencing parameters is marked; Build a vacuum impact analysis network based on machine learning; Under the sample environment parameter set and the sample vacuum degree influence parameter set, supervised training parameter optimization is performed on the vacuum influence analysis network, and the training is completed after the test accuracy converges.

[0021] In this embodiment, training data is first prepared. Specifically, based on the mass spectrometer's operational monitoring data, a set of sample environmental parameters (e.g., ambient temperatures: 25°C, 30°C, 35°C, and 40°C) is collected. The mass spectrometer's vacuum level variation parameters (e.g., 0.2, 0.4, 0.7, and 0.9) under different sample environmental parameters are also collected and annotated to obtain a set of sample vacuum level influencing parameters. Furthermore, the set of sample vacuum level influencing parameters is divided into a training set, a validation set, and a test set in a ratio of 7:1.5:1.5, which serves as the training data for the vacuum level impact analysis network.

[0022] The vacuum degree change parameter = (vacuum degree at current temperature - reference vacuum degree) / reference vacuum degree. This is because the ideal operating temperature of most mass spectrometers (such as quadrupole mass spectrometers and time-of-flight mass spectrometers) is 18°C ​​to 25°C. Temperatures below 15°C can lead to decreased circuit component performance, poor lubrication of mechanical parts, and unstable vacuum systems. Temperatures exceeding 30°C can cause decreased vacuum, increased probability of ion collisions, and decreased sensitivity. Therefore, a reference temperature (such as 22°C) can be determined based on the ideal operating temperature of the mass spectrometer, and the vacuum degree corresponding to the reference temperature (such as 1×10 -5 Pa) as the reference vacuum degree, and analyze the vacuum degree variation parameters at different temperatures based on this. For example, the reference vacuum degree corresponding to the reference temperature (such as 22°C) is (such as 1×10 -5 Pa), the vacuum degree of the mass spectrometer at 25°C was 1.2×10 -5Pa, then the vacuum degree change parameter at this time = (1.2×10 -5 Pa-1×10 -5 Pa) / 1×10 -5 Pa=0.2. Thus, by collecting the vacuum degree of the mass spectrometer at different temperatures, multiple vacuum degree change parameters can be calculated and obtained as the sample vacuum degree influencing parameter set.

[0023] Secondly, a vacuum impact analysis network based on machine learning is constructed. This network is based on machine learning (e.g., LSTM, CNN, and other neural network algorithms). It takes in environmental parameters as input, and after computation and processing by multiple layers of internal neurons, it outputs vacuum impact parameters. The network primarily consists of an input layer, a hidden layer, and an output layer.

[0024] Specifically, the input layer is the interface between the vacuum impact analysis network and external data. It is primarily responsible for receiving the collected mass spectrometer operating environment parameters (such as ambient temperature). The environmental parameters are converted into numerical values ​​that the network can process and input into the next layer. The number of neurons in the input layer corresponds to the number of input parameters, and each neuron is responsible for transmitting information about one parameter. For example, if only temperature is considered, the input layer contains one neuron. The hidden layer is the brain of the vacuum impact analysis network, primarily responsible for data feature extraction and complex relationship operations. It consists of multiple layers of neurons, each layer of neurons communicating with the next layer of neurons through weighted connections. When processing environmental parameter data, the neurons in the hidden layer perform a weighted summation on the input signal (such as ambient temperature), highlighting key features. Nonlinear factors are introduced through activation functions (such as ReLU and Sigmoid), thereby exploring the complex nonlinear relationship between environmental parameters and vacuum changes. This application recommends setting up 3-5 hidden layers, each containing 20 neurons. Those skilled in the art can adjust the number of layers and the number of neurons in each layer based on actual data and task requirements. Generally speaking, the more layers and the more neurons, the stronger the network's expressive power, but this also increases computational complexity and the risk of overfitting. The output layer is primarily responsible for converting the feature information extracted and processed by the hidden layer into specific vacuum-affecting parameters (such as the predicted vacuum pressure change value, the vacuum drop rate, etc.). The number of neurons in the output layer depends on the number of parameters to be output. For example, if only the vacuum pressure change value is output, then the output layer will have only one neuron.

[0025] Finally, the model is trained. Specifically, under the sample environmental parameter set and the sample vacuum degree influence parameter set, the supervised training parameter optimization of the vacuum impact analysis network is performed, and the training is completed after the test accuracy converges. For example, at the beginning of the training, the weights and biases of the network are randomly initialized, and the environmental parameters are input into the network through forward propagation. After calculation by neurons in each layer, the predicted value of the vacuum degree influence is output; then, the difference between the predicted value and the true value is calculated using loss functions such as mean square error (MSE), and the loss gradient is transferred from the output layer to the input layer through the back propagation algorithm, and the weights and biases are updated in combination with optimization algorithms such as Adam to reduce the loss. The training process adopts batch processing (such as Batch Size=32) and multi-epoch iteration strategies, and prevents overfitting through regularization (such as L2 regularization) and Dropout technology. When the loss value on the validation set no longer decreases for multiple consecutive epochs, or reaches a preset error threshold (such as 10 −4 ), the model is considered converged and training is stopped. Finally, the test set is used to evaluate the model's generalization ability to ensure that it can accurately predict the vacuum level change trend during mass spectrometer operation, providing reliable support for equipment status monitoring.

[0026] In summary, compared with the existing technology, the present application collects environmental parameters (including temperature) in the operating environment of the mass spectrometer, analyzes the influence of the vacuum degree of the mass spectrometer based on the environmental parameters, and obtains vacuum degree influence parameters, which can be used to evaluate the operating status of the mass spectrometer, providing a reliable basis for monitoring the operating status of the mass spectrometer.

[0027] S20: performing mass axis offset influence analysis on the mass spectrometer according to the environmental parameters to obtain mass axis offset parameters; The mass axis is one of the key performance indicators of a mass spectrometer. Its essence is the accuracy of measuring the mass-to-charge ratio of ions, and it is often expressed in terms of mass error (in ppm). In the qualitative analysis of compounds, it is especially important to distinguish substances or isomers with very small mass differences. For example, the theoretical mass difference between C2H4O2 and CH4N2O is extremely small, and only when the mass error is controlled to less than 5ppm can they be accurately distinguished. Therefore, when the mass axis shifts, it will lead to analytical errors. Furthermore, temperature is one of the important factors affecting the mass axis shift of a mass spectrometer. Temperature causes the magnetic material to expand and contract, which in turn leads to mass axis shift. Therefore, the mass axis shift parameter can be predicted by environmental parameters such as ambient temperature, and the operating status of the mass spectrometer can be monitored accordingly.

[0028] In response to the above problems, the present application analyzes the impact of mass axis offset of a mass spectrometer based on environmental parameters to obtain mass axis offset parameters.

[0029] Specifically, step S20 in the method includes: Invoking a mass axis offset analysis network, wherein the mass axis offset analysis network is trained using a sample environment parameter set and a sample mass axis offset parameter set, wherein the sample mass axis offset parameter includes a mass error amplitude; The environmental parameters are input into the mass axis offset analysis network, and the mass axis offset parameters are obtained by identifying the output.

[0030] In the embodiment of the present application, a pre-trained mass axis offset analysis network is first called. The structure and training steps of the mass axis offset analysis network are similar to the vacuum effect analysis network in the aforementioned step S10. Specifically, the mass axis offset analysis network is constructed based on machine learning (such as neural network algorithms such as LSTM and CNN). It inputs environmental parameters and, after calculation and processing by multiple internal layers of neurons, outputs mass axis offset parameters. It is mainly composed of an input layer, a hidden layer, and an output layer. Furthermore, the model is trained using a set of sample environmental parameters (such as ambient temperature: 25°C, 30°C, 35°C, and 40°C) and a set of sample mass axis offset parameters (such as mass error amplitude: 0.25, 0.4, 0.7, and 0.9) to obtain a mass axis offset analysis network.

[0031] Here, according to the same logic as the previous steps, mass error magnitude = (mass error at current temperature - reference mass error) / reference mass error. A reference temperature (e.g., 22°C) can be determined based on the ideal operating temperature of the mass spectrometer, and the mass error corresponding to the reference temperature (e.g., 100 ppm) can be collected as the reference mass error. The mass error magnitudes at different temperatures can be analyzed accordingly. For example, if the reference mass error corresponding to the reference temperature (e.g., 22°C) is (e.g., 100 ppm), and the mass error of the mass spectrometer at 25°C is 125 ppm, then the mass error magnitude at this point = (125 ppm - 100 ppm) / 100 ppm = 0.25. In this way, by collecting the mass errors of the mass spectrometer at different temperatures, multiple mass error magnitudes can be calculated and used as the sample mass axis offset parameter set.

[0032] Next, the environmental parameters are input into the mass axis offset analysis network, and the mass axis offset parameters are identified and outputted. For example, an environmental parameter (e.g., ambient temperature: 28°C) is input into the mass axis offset analysis network, and the mass axis offset parameters (e.g., mass error margin: 0.3) are identified and outputted. A larger mass axis offset parameter indicates a greater deviation from the ideal state, i.e., a worsening of the current operating state of the mass spectrometer.

[0033] In summary, compared with the existing technology, this application analyzes the impact of mass axis offset of the mass spectrometer based on environmental parameters and obtains mass axis offset parameters, which can be used to evaluate the operating status of the mass spectrometer and provide a reliable basis for subsequent result analysis.

[0034] S30: testing to obtain actual vacuum degree influencing parameters and actual mass error parameters of the mass spectrometer, performing state influence verification in combination with the vacuum degree influencing parameters and the mass axis offset parameters, and processing to obtain vacuum verification coefficients and mass verification coefficients; In the aforementioned steps, the vacuum degree influencing parameters and mass error parameters predicted and output by the model may be affected by systematic deviations (such as errors in the model algorithm itself) and random deviations (such as accidental sensor noise), resulting in data deviations.

[0035] To address the above problems, this application obtains the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer through testing, combines the vacuum degree influence parameters and mass axis offset parameters to perform state impact verification, and processes to obtain the vacuum verification coefficient and mass verification coefficient.

[0036] Specifically, step S30 in the method includes: Test and obtain the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer; Performing vacuum state influence verification based on the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient; The quality status impact verification is performed according to the actual quality error parameter and the quality axis offset parameter to obtain a quality verification coefficient.

[0037] In the present embodiment, the actual vacuum level influence parameter and the actual mass error parameter of the mass spectrometer are first tested and obtained. For example, the actual vacuum level and the actual mass error of the mass spectrometer are collected by a sensor, and the actual vacuum level influence parameter and the actual mass error parameter are calculated using the same method as in the previous steps. These parameters reflect the current actual operating status of the mass spectrometer.

[0038] Secondly, the vacuum state impact verification is performed based on the vacuum degree influencing parameters and the actual vacuum degree influencing parameters to obtain a vacuum verification coefficient. Specifically, the vacuum deviation amplitude between the vacuum degree influencing parameters and the actual vacuum degree influencing parameters is calculated, and then the vacuum verification coefficient is calculated based on the vacuum deviation amplitude. The vacuum verification coefficient reflects the degree of consistency between the predicted data of the vacuum impact analysis network and the actual detection data, indicating the prediction accuracy of the vacuum impact analysis network. The higher the prediction accuracy of the vacuum impact analysis network, the closer the vacuum degree influencing parameters are to the actual vacuum degree influencing parameters, the smaller the vacuum deviation amplitude, and the larger the vacuum verification coefficient.

[0039] Finally, the quality state impact verification is performed based on the actual mass error parameter and the mass axis offset parameter to obtain a quality verification coefficient. Specifically, similar to the calculation concept of the vacuum verification coefficient, the mass error deviation amplitude of the mass axis offset parameter and the actual mass error parameter is calculated, and the quality verification coefficient is calculated based on the mass error deviation amplitude. The quality verification coefficient reflects the degree of consistency between the predicted data of the mass axis offset analysis network and the actual detection data, indicating the prediction accuracy of the mass axis offset analysis network. The higher the prediction accuracy of the mass axis offset analysis network, the closer the mass axis offset parameter and the actual mass error parameter, the smaller the mass error deviation amplitude, and the larger the quality verification coefficient.

[0040] Furthermore, the “performing vacuum state influence verification according to the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient” includes: Calculating a vacuum deviation amplitude between the vacuum degree influencing parameter and the actual vacuum degree influencing parameter; A vacuum verification coefficient is calculated based on the vacuum deviation amplitude.

[0041] In the embodiments of the present application, the vacuum deviation amplitude between the vacuum degree influencing parameter and the actual vacuum degree influencing parameter is first calculated, where the vacuum deviation amplitude = |vacuum degree influencing parameter - actual vacuum degree influencing parameter| / actual vacuum degree influencing parameter. The vacuum deviation amplitude reflects the deviation between the predicted data and the actual data of the vacuum impact analysis network. The closer the vacuum degree influencing parameter and the actual vacuum degree influencing parameter are, the smaller the vacuum deviation amplitude. For example, if the vacuum impact analysis network predicts and outputs a vacuum degree influencing parameter of 0.2 under the condition of 25°C (ambient temperature), and the actual vacuum degree at 25°C is collected by a sensor and the actual vacuum degree influencing parameter is calculated to be 0.18, then the vacuum deviation amplitude at this time = |0.2-0.18| / 0.18 = 0.11.

[0042] Next, based on the vacuum deviation amplitude, a vacuum verification coefficient is calculated. The vacuum verification coefficient is calculated as 1 minus the vacuum deviation amplitude. The vacuum verification coefficient reflects the degree of agreement between the predicted data from the vacuum impact analysis network and the actual data, reflecting the prediction accuracy of the vacuum impact analysis network. The higher the prediction accuracy of the vacuum impact analysis network, the closer the vacuum degree influencing parameters are to the actual vacuum degree influencing parameters, the smaller the vacuum deviation amplitude, and the larger the vacuum verification coefficient. For example, if the vacuum deviation amplitude is 0.11, the vacuum verification coefficient is 1 minus 0.11, which equals 0.89.

[0043] In summary, compared to existing technologies, this application obtains the actual vacuum influence parameters and actual mass error parameters of the mass spectrometer through testing, combines the vacuum influence parameters and mass axis offset parameters to verify the state impact, and processes them to obtain vacuum verification coefficients and mass verification coefficients. In this way, the model prediction data is verified with actual data, and provides data support for subsequent fault identification and warning.

[0044] S40: performing a fusion state abnormality analysis on the vacuum degree influencing parameter and the mass axis offset parameter according to the vacuum verification coefficient and the mass verification coefficient, obtaining a state abnormality coefficient, and performing a fault identification and warning.

[0045] The aforementioned steps predict and output vacuum effect parameters and mass axis offset parameters based on environmental parameters (temperature). These parameters can be combined to provide fault diagnosis and early warning of abnormal mass spectrometer conditions. However, in practice, both the vacuum effect analysis network and the mass axis offset analysis network may exhibit prediction errors, and these errors may be out of sync. For example, the vacuum effect analysis network may make accurate predictions while the mass axis offset analysis network may make inaccurate predictions. Directly combining these two parameters may cause the mass axis offset analysis network's prediction errors to be masked by the vacuum effect analysis network's accurate predictions, resulting in distorted results and, in turn, failure to trigger timely early warnings.

[0046] In response to the above problems, this application conducts a fusion state abnormality analysis on the vacuum degree influencing parameters and the mass axis offset parameters based on the vacuum verification coefficient and the mass verification coefficient, obtains the state abnormality coefficient, and performs fault identification and early warning.

[0047] Specifically, step S40 in the method includes: Calculate the verification error coefficient based on the vacuum verification coefficient and the quality verification coefficient; Obtain the average vacuum degree impact parameter and average mass axis offset parameter when the mass spectrometer is in an abnormal state; Respectively calculating the ratios of the vacuum degree influencing parameter and the mass axis offset parameter to the average vacuum degree influencing parameter and the average mass axis offset parameter, and calculating the averages to obtain a basic state abnormality coefficient; According to the verification error coefficient, the basic state abnormality coefficient is amplified and compensated to obtain the state abnormality coefficient, and a fault identification and warning is performed.

[0048] In the embodiment of the present application, the verification error coefficient is first calculated based on the vacuum verification coefficient and the quality verification coefficient, wherein the verification error coefficient = |vacuum verification coefficient - quality verification coefficient|, the vacuum verification coefficient represents the prediction accuracy of the vacuum impact analysis network, and the higher the prediction accuracy, the larger the vacuum verification coefficient; the quality verification coefficient represents the prediction accuracy of the mass axis offset analysis network, and the higher the prediction accuracy, the larger the quality verification coefficient. When the prediction accuracy of the two is similar, the verification error coefficient approaches 0, indicating that the model has a strong prediction consistency in the two dimensions of vacuum degree and mass axis offset. Furthermore, when the prediction accuracy of any one of the vacuum impact analysis network and the mass axis offset analysis network is abnormal, if the vacuum degree impact parameter and the mass axis offset parameter are directly integrated for fault warning, the warning result may be distorted due to the single-dimensional prediction deviation. For example, if the vacuum verification coefficient is 0.89 and the mass verification coefficient is 0.84, the verification error coefficient = |0.89-0.84| = 0.05, indicating that the prediction accuracy of the vacuum influence analysis network and the mass axis offset analysis network are very synchronized at this time; if the vacuum verification coefficient is 0.89 and the mass verification coefficient is 0.44, the verification error coefficient = |0.89-0.44| = 0.45, indicating that the prediction accuracy of the mass axis offset analysis network is low at this time. If the vacuum influence parameters and the mass axis offset parameters are directly integrated for fault warning, the warning result may be distorted due to the prediction deviation of the mass axis offset.

[0049] Secondly, the average vacuum influence parameter and average mass axis offset parameter are obtained when the mass spectrometer experiences abnormal conditions. Specifically, based on the historical database, all vacuum influence data and mass error data from when the mass spectrometer experiences abnormal conditions are extracted. All vacuum influence parameters and mass axis offset parameters are then calculated separately. Finally, the average values ​​are calculated to obtain the average vacuum influence parameter and average mass axis offset parameter. The average vacuum influence parameter and average mass axis offset parameter reflect the vacuum and mass axis offset levels during abnormal conditions as recorded in the historical data.

[0050] Next, the ratios of the vacuum influence parameter and mass axis offset parameter to the average vacuum influence parameter and average mass axis offset parameter are calculated, and the averages are calculated to obtain the base state abnormality coefficient, where base state abnormality coefficient = (vacuum influence parameter / average vacuum influence parameter + mass axis offset parameter / average mass axis offset parameter) / 2. For example, at 25°C, the vacuum influence parameter is 0.2, the mass axis offset parameter is 0.25, the average vacuum influence parameter is 0.32, and the average mass axis offset parameter is 0.35. Therefore, the base state abnormality coefficient = (0.2 / 0.32 + 0.25 / 0.35) / 2 = 0.67.

[0051] Finally, based on the verification error coefficient, the base state anomaly coefficient is amplified and compensated to obtain a state anomaly coefficient, which is then used to issue a fault identification and early warning. Here, the state anomaly coefficient = (1 + verification error coefficient) * base state anomaly coefficient. Furthermore, the larger the difference between the vacuum verification coefficient and the mass verification coefficient, the more likely it is that other factors besides temperature are contributing to the mass spectrometer state anomaly. In this case, the larger the verification error coefficient, the greater the compensation amplification for the state anomaly coefficient, leading to a fault identification and early warning, improving the response speed to anomalies. For example, if the verification error coefficient is 0.05 and the base state anomaly coefficient is 0.67, the state anomaly coefficient = (1 + 0.05) * 0.67 = 0.7. This considers the consistency of the prediction accuracy of the vacuum effect analysis network and the mass axis shift analysis network. If either the vacuum effect analysis network or the mass axis shift analysis network exhibits an abnormal prediction accuracy, the verification error coefficient is used to compensate and amplify the base state anomaly coefficient, thereby avoiding the distortion of early warning results caused by single-dimensional prediction bias and enabling accurate fault identification and early warning.

[0052] In summary, compared to existing technologies, this application uses the vacuum verification coefficient and the quality verification coefficient to perform a fusion state anomaly analysis of the vacuum influencing parameters and the mass axis offset parameters, obtaining the state anomaly coefficient and providing fault identification and warning. In this way, the absolute difference between the vacuum verification coefficient and the quality verification coefficient is used to compensate and amplify the basic state anomaly coefficient, avoiding the distortion of warning results caused by single-dimensional prediction bias. This allows for accurate fault identification and warning at an earlier stage, facilitating maintenance and repair by relevant technical personnel.

[0053] In summary, the embodiments of the present application have at least the following technical effects: Compared with the existing technology, the present application collects environmental parameters (including temperature) in the operating environment of the mass spectrometer, analyzes the influence of the vacuum degree of the mass spectrometer based on the environmental parameters, and obtains vacuum degree influence parameters, which can be used to evaluate the operating status of the mass spectrometer, providing a reliable basis for monitoring the operating status of the mass spectrometer.

[0054] Secondly, the present application analyzes the influence of mass axis offset of the mass spectrometer based on environmental parameters and obtains mass axis offset parameters, which can be used to evaluate the operating status of the mass spectrometer and provide a reliable basis for subsequent result analysis.

[0055] Thirdly, this application tests the mass spectrometer to obtain the actual vacuum influence parameters and actual mass error parameters. This is combined with the vacuum influence parameters and mass axis offset parameters to verify the state impact, and then process them to obtain vacuum verification coefficients and mass verification coefficients. In this way, the model prediction data is verified with actual data, providing data support for subsequent fault identification and warning.

[0056] Finally, this application uses the vacuum verification coefficient and the quality verification coefficient to perform a fusion state anomaly analysis of the vacuum influencing parameters and the mass axis offset parameters, obtaining the state anomaly coefficient and providing a fault identification and warning. In this way, the difference between the vacuum verification coefficient and the quality verification coefficient is used to compensate and amplify the basic state anomaly coefficient, avoiding the distortion of warning results caused by single-dimensional prediction bias. This allows for accurate fault identification and warning at an earlier stage, facilitating maintenance and repair by relevant technical personnel.

[0057] Through the above technical solution, this application inputs environmental parameters through a vacuum impact analysis network and a mass axis offset analysis network constructed based on machine learning, outputs vacuum impact parameters and mass axis offset parameters, and compensates and amplifies the basic state abnormality coefficient accordingly. In this way, fault identification and warning can be made at an earlier stage, thereby improving the timeliness of mass spectrometer fault warning.

[0058] Example 2, as Figure 2 As shown, based on the same inventive concept as the method for monitoring the operating status of a mass spectrometer provided in Example 1, an embodiment of the present invention further provides a system for monitoring the operating status of a mass spectrometer, comprising: The vacuum analysis module 11 is used to collect environmental parameters in the operating environment of the mass spectrometer, and perform vacuum degree influence analysis on the mass spectrometer based on the environmental parameters to obtain vacuum degree influence parameters; An axis deviation analysis module 12 is used to analyze the mass axis deviation of the mass spectrometer according to the environmental parameters to obtain mass axis deviation parameters; A state verification module 13 is used to test and obtain actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer, perform state influence verification in combination with the vacuum degree influence parameters and mass axis offset parameters, and process to obtain vacuum verification coefficients and mass verification coefficients; The abnormality warning module 14 is used to perform a fusion state abnormality analysis on the vacuum degree influencing parameter and the mass axis offset parameter according to the vacuum verification coefficient and the mass verification coefficient, obtain a state abnormality coefficient, and perform fault identification and warning.

[0059] The vacuum analysis module 11 is specifically used for: Collecting environmental parameters in the operating environment of the mass spectrometer, wherein the environmental parameters include ambient temperature; The environmental parameters are input into the vacuum influence analysis network of the mass spectrometer, and the vacuum degree influence parameters are obtained by identification output.

[0060] Furthermore, the training steps of the "vacuum impact analysis network" include: According to the operation monitoring data of the mass spectrometer, a set of sample environment parameters is collected, and the vacuum degree change parameters of the mass spectrometer under different sample environment parameters are collected, and the set of sample vacuum degree influencing parameters is marked; Build a vacuum impact analysis network based on machine learning; Under the sample environment parameter set and the sample vacuum degree influence parameter set, supervised training parameter optimization is performed on the vacuum influence analysis network, and the training is completed after the test accuracy converges.

[0061] The axis deviation analysis module 12 is specifically used for: Invoking a mass axis offset analysis network, wherein the mass axis offset analysis network is trained using a sample environment parameter set and a sample mass axis offset parameter set, wherein the sample mass axis offset parameter includes a mass error amplitude; The environmental parameters are input into the mass axis offset analysis network, and the mass axis offset parameters are obtained by identifying the output.

[0062] The status verification module 13 is specifically configured to: Test and obtain the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer; Performing vacuum state influence verification based on the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient; The quality status impact verification is performed according to the actual quality error parameter and the quality axis offset parameter to obtain a quality verification coefficient.

[0063] Furthermore, the “performing vacuum state influence verification according to the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient” includes: Calculating a vacuum deviation amplitude between the vacuum degree influencing parameter and the actual vacuum degree influencing parameter; A vacuum verification coefficient is calculated based on the vacuum deviation amplitude.

[0064] The abnormal warning module 14 is specifically used to: Calculate the verification error coefficient based on the vacuum verification coefficient and the quality verification coefficient; Obtain the average vacuum degree impact parameter and average mass axis offset parameter when the mass spectrometer is in an abnormal state; Respectively calculating the ratios of the vacuum degree influencing parameter and the mass axis offset parameter to the average vacuum degree influencing parameter and the average mass axis offset parameter, and calculating the averages to obtain a basic state abnormality coefficient; According to the verification error coefficient, the basic state abnormality coefficient is amplified and compensated to obtain the state abnormality coefficient, and a fault identification and warning is performed.

[0065] In summary, the embodiments of the present application have at least the following technical effects: Compared with the prior art, the present application first collects environmental parameters in the operating environment of the mass spectrometer through a vacuum analysis module, performs vacuum degree influence analysis on the mass spectrometer according to the environmental parameters, obtains vacuum degree influence parameters, and can evaluate the operating status of the mass spectrometer based on this, providing a reliable basis for monitoring the operating status of the mass spectrometer. Secondly, through the axis deviation analysis module, the mass axis offset influence analysis of the mass spectrometer is performed according to the environmental parameters to obtain the mass axis offset parameters, providing a reliable basis for subsequent result analysis. Thirdly, through the state verification module, the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer are tested and obtained, and the state impact verification is performed in combination with the vacuum degree influence parameters and the mass axis offset parameters. The vacuum verification coefficient and the mass verification coefficient are obtained through processing, the model prediction data is verified by actual data, and data support is provided for subsequent fault discrimination and early warning. Finally, the abnormality warning module uses the vacuum verification coefficient and mass verification coefficient to perform a fusion state anomaly analysis of the vacuum influencing parameters and the mass axis offset parameters, obtaining the state anomaly coefficient for fault identification and warning. The absolute difference between the vacuum verification coefficient and the mass verification coefficient is used to compensate and amplify the basic state anomaly coefficient, avoiding the distortion of warning results caused by single-dimensional prediction bias. This allows for accurate fault identification and warning at an earlier stage, facilitating maintenance and repair by relevant technicians. This improves the timeliness of mass spectrometer fault warnings.

[0066] Example 3, as Figure 3 As shown, an embodiment of the present invention provides an electronic device 200, including a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, a mass spectrometer operating status monitoring method in Example 1 is implemented.

[0067] Embodiment 4: This embodiment provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, a method for monitoring the operating status of a mass spectrometer as in embodiment 1 is implemented.

[0068] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring the operating status of a mass spectrometer, characterized in that: The method comprises: Collecting environmental parameters in the mass spectrometer operating environment, performing vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtaining vacuum degree influence parameters; Performing mass axis offset influence analysis on the mass spectrometer according to the environmental parameters to obtain mass axis offset parameters; The actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer are obtained by testing, and the state influence verification is performed in combination with the vacuum degree influence parameters and the mass axis offset parameters, and the vacuum verification coefficient and the mass verification coefficient are obtained by processing; According to the vacuum verification coefficient and the quality verification coefficient, a fusion state abnormality analysis is performed on the vacuum degree influencing parameter and the mass axis offset parameter to obtain a state abnormality coefficient and perform fault identification and early warning.

2. The method for monitoring the operating status of a mass spectrometer according to claim 1, wherein: Collecting environmental parameters in the mass spectrometer operating environment, performing vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtaining vacuum degree influence parameters, including: Collecting environmental parameters in the operating environment of the mass spectrometer, wherein the environmental parameters include ambient temperature; The environmental parameters are input into the vacuum influence analysis network of the mass spectrometer, and the vacuum degree influence parameters are obtained by identification output.

3. The method for monitoring the operating status of a mass spectrometer according to claim 2, wherein: The training steps of the vacuum impact analysis network include: According to the operation monitoring data of the mass spectrometer, a set of sample environment parameters is collected, and the vacuum degree change parameters of the mass spectrometer under different sample environment parameters are collected, and the set of sample vacuum degree influencing parameters is marked; Build a vacuum impact analysis network based on machine learning; Under the sample environment parameter set and the sample vacuum degree influence parameter set, supervised training parameter optimization is performed on the vacuum influence analysis network, and the training is completed after the test accuracy converges.

4. The method for monitoring the operating status of a mass spectrometer according to claim 1, wherein: Performing mass axis offset influence analysis on the mass spectrometer according to the environmental parameters to obtain mass axis offset parameters includes: Invoking a mass axis offset analysis network, wherein the mass axis offset analysis network is trained using a sample environment parameter set and a sample mass axis offset parameter set, wherein the sample mass axis offset parameter includes a mass error amplitude; The environmental parameters are input into the mass axis offset analysis network, and the mass axis offset parameters are obtained by identifying the output.

5. The method for monitoring the operating status of a mass spectrometer according to claim 1, wherein: The test obtains the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer, combines the vacuum degree influence parameters and the mass axis offset parameters to perform state influence verification, and processes to obtain the vacuum verification coefficient and the mass verification coefficient, including: Test and obtain the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer; Performing vacuum state influence verification based on the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient; The quality status impact verification is performed according to the actual quality error parameter and the quality axis offset parameter to obtain a quality verification coefficient.

6. The method for monitoring the operating status of a mass spectrometer according to claim 5, wherein: The vacuum state influence verification is performed according to the vacuum degree influence parameter and the actual vacuum degree influence parameter to obtain a vacuum verification coefficient, including: Calculating a vacuum deviation amplitude between the vacuum degree influencing parameter and the actual vacuum degree influencing parameter; A vacuum verification coefficient is calculated based on the vacuum deviation amplitude.

7. The method for monitoring the operating status of a mass spectrometer according to claim 1, wherein: According to the vacuum verification coefficient and the quality verification coefficient, a fusion state abnormality analysis is performed on the vacuum degree influencing parameter and the mass axis offset parameter to obtain a state abnormality coefficient and perform fault identification and early warning, including: Calculate the verification error coefficient based on the vacuum verification coefficient and the quality verification coefficient; Obtain the average vacuum degree impact parameter and average mass axis offset parameter when the mass spectrometer is in an abnormal state; Respectively calculating the ratios of the vacuum degree influencing parameter and the mass axis offset parameter to the average vacuum degree influencing parameter and the average mass axis offset parameter, and calculating the averages to obtain a basic state abnormality coefficient; According to the verification error coefficient, the basic state abnormality coefficient is amplified and compensated to obtain the state abnormality coefficient, and a fault identification and warning is performed.

8. A mass spectrometer operating status monitoring system, characterized in that: Used to perform the method according to any one of claims 1 to 7, comprising: A vacuum analysis module is used to collect environmental parameters in the operating environment of the mass spectrometer, perform vacuum degree influence analysis on the mass spectrometer based on the environmental parameters, and obtain vacuum degree influence parameters; An axis deviation analysis module, configured to analyze the influence of mass axis deviation of the mass spectrometer according to the environmental parameters and obtain mass axis deviation parameters; A state verification module is used to test and obtain the actual vacuum degree influence parameters and actual mass error parameters of the mass spectrometer, perform state influence verification in combination with the vacuum degree influence parameters and mass axis offset parameters, and process to obtain vacuum verification coefficients and mass verification coefficients; The abnormality warning module is used to perform a fusion state abnormality analysis on the vacuum degree influencing parameter and the mass axis offset parameter according to the vacuum verification coefficient and the mass verification coefficient, obtain the state abnormality coefficient, and perform fault identification and warning.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the mass spectrometer operating status monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the method for monitoring the operating status of a mass spectrometer according to any one of claims 1 to 7 is implemented.

Images